diff --git a/mlir/include/mlir/Dialect/Linalg/IR/LinalgOps.td b/mlir/include/mlir/Dialect/Linalg/IR/LinalgOps.td --- a/mlir/include/mlir/Dialect/Linalg/IR/LinalgOps.td +++ b/mlir/include/mlir/Dialect/Linalg/IR/LinalgOps.td @@ -510,4 +510,51 @@ }]; } +// +// The following operations bootstrap working with sparse tensors solely +// within the Linalg dialect. They provide temporary bridges between a +// future SparseTensorType (now an opaque pointer), the actual TensorType, +// and MemRef arrays underlying an actual sparse storage scheme in memory. +// **** +// TODO: introduce SparseTensorType as first class citizen in MLIR +// **** + +def Linalg_SparseTensorFromPointerOp : + Linalg_Op<"sparse_tensor", [NoSideEffect]>, + Arguments<(ins AnyType:$ptr)>, + Results<(outs AnyTensor:$result)> { + let summary = "Views an opaque sparse tensor pointer as a tensor"; + let verifier = ?; + let assemblyFormat = "$ptr attr-dict `:` type($ptr) `into` type($result)"; +} + +def Linalg_SparseTensorToValuesMemRefOp : + Linalg_Op<"sparse_values", [NoSideEffect]>, + Arguments<(ins AnyTensor:$tensor)>, + Results<(outs AnyStridedMemRef:$result)> { + let summary = "Extract numerical values array from a sparse tensor"; + let verifier = ?; + let assemblyFormat = "$tensor attr-dict `:` type($tensor) `into` type($result)"; +} + +def Linalg_SparseTensorToIndicesMemRefOp : + Linalg_Op<"sparse_indices", [NoSideEffect]>, + Arguments<(ins AnyTensor:$tensor, Index:$dim)>, + Results<(outs AnyStridedMemRef:$result)> { + let summary = "Extract indices array at given dimension from a sparse tensor"; + let verifier = ?; + let assemblyFormat = "$tensor `,` $dim attr-dict `:` type($tensor)" + " `into` type($result)"; +} + +def Linalg_SparseTensorToPointersMemRefOp : + Linalg_Op<"sparse_pointers", [NoSideEffect]>, + Arguments<(ins AnyTensor:$tensor, Index:$dim)>, + Results<(outs AnyStridedMemRef:$result)> { + let summary = "Extract pointers array at given dimension from a sparse tensor"; + let verifier = ?; + let assemblyFormat = "$tensor `,` $dim attr-dict `:` type($tensor)" + " `into` type($result)"; +} + #endif // LINALG_OPS diff --git a/mlir/include/mlir/Dialect/Linalg/Transforms/Transforms.h b/mlir/include/mlir/Dialect/Linalg/Transforms/Transforms.h --- a/mlir/include/mlir/Dialect/Linalg/Transforms/Transforms.h +++ b/mlir/include/mlir/Dialect/Linalg/Transforms/Transforms.h @@ -944,9 +944,9 @@ struct SparsificationOptions { SparsificationOptions(SparseParallelizationStrategy p, SparseVectorizationStrategy v, unsigned vl, - SparseIntType pt, SparseIntType it) + SparseIntType pt, SparseIntType it, bool fo) : parallelizationStrategy(p), vectorizationStrategy(v), vectorLength(vl), - ptrType(pt), indType(it) { + ptrType(pt), indType(it), fastOutput(fo) { // TODO: remove restriction when vectors with index elements are supported assert((v != SparseVectorizationStrategy::kAnyStorageInnerLoop || (ptrType != SparseIntType::kNative && @@ -956,12 +956,14 @@ SparsificationOptions() : SparsificationOptions(SparseParallelizationStrategy::kNone, SparseVectorizationStrategy::kNone, 1u, - SparseIntType::kNative, SparseIntType::kNative) {} + SparseIntType::kNative, SparseIntType::kNative, + false) {} SparseParallelizationStrategy parallelizationStrategy; SparseVectorizationStrategy vectorizationStrategy; unsigned vectorLength; SparseIntType ptrType; SparseIntType indType; + bool fastOutput; // experimental: fast output buffers }; /// Set up sparsification rewriting rules with the given options. @@ -969,6 +971,10 @@ MLIRContext *context, OwningRewritePatternList &patterns, const SparsificationOptions &options = SparsificationOptions()); +/// Set up sparsification conversion rules with the given options. +void populateSparsificationConversionPatterns( + MLIRContext *context, OwningRewritePatternList &patterns); + } // namespace linalg } // namespace mlir diff --git a/mlir/integration_test/Sparse/CPU/sparse_sum.mlir b/mlir/integration_test/Sparse/CPU/sparse_sum.mlir new file mode 100644 --- /dev/null +++ b/mlir/integration_test/Sparse/CPU/sparse_sum.mlir @@ -0,0 +1,106 @@ +// RUN: mlir-opt %s \ +// RUN: --test-sparsification="lower" \ +// RUN: --convert-linalg-to-loops \ +// RUN: --func-bufferize --tensor-constant-bufferize --tensor-bufferize --finalizing-bufferize \ +// RUN: --convert-scf-to-std --convert-vector-to-llvm --convert-std-to-llvm | \ +// RUN: TENSOR0="%mlir_integration_test_dir/data/test.mtx" \ +// RUN: mlir-cpu-runner \ +// RUN: -e entry -entry-point-result=void \ +// RUN: -shared-libs=%mlir_integration_test_dir/libmlir_c_runner_utils%shlibext | \ +// RUN: FileCheck %s + +// +// Use descriptive names for opaque pointers. +// +!Filename = type !llvm.ptr +!SparseTensor = type !llvm.ptr + +#trait_sum_reduce = { + indexing_maps = [ + affine_map<(i,j) -> (i,j)>, // A + affine_map<(i,j) -> ()> // x (out) + ], + sparse = [ + [ "S", "S" ], // A + [ ] // x + ], + iterator_types = ["reduction", "reduction"], + doc = "x += A(i,j)" +} + +// +// Integration test that lowers a kernel annotated as sparse into +// actual sparse code, initializes a matching sparse storage scheme +// from file, and runs the resulting code with the JIT compiler. +// +module { + // + // The kernel expressed as an annotated Linalg op. The kernel + // sum reduces a matrix into a single scalar. + // + func @kernel_sum_reduce(%argA: !SparseTensor, + %argx: tensor) -> tensor { + %arga = linalg.sparse_tensor %argA : !SparseTensor into tensor<5x5xf64> + %0 = linalg.generic #trait_sum_reduce + ins(%arga: tensor<5x5xf64>) + outs(%argx: tensor) { + ^bb(%a: f64, %x: f64): + %0 = addf %x, %a : f64 + linalg.yield %0 : f64 + } -> tensor + return %0 : tensor + } + + // + // Runtime support library that is called directly from here. + // + func private @getTensorFilename(index) -> (!Filename) + func private @newSparseTensor(!Filename, memref) -> (!SparseTensor) + func private @delSparseTensor(!SparseTensor) -> () + func private @print_memref_f64(%ptr : tensor<*xf64>) + + // + // Main driver that reads matrix from file and calls the sparse kernel. + // + func @entry() { + %d0 = constant 0.0 : f64 + %c0 = constant 0 : index + %c1 = constant 1 : index + %c2 = constant 2 : index + + // Mark both dimensions of the matrix as sparse + // (this must match the annotation in the trait). + %annotations = alloc(%c2) : memref + %sparse = constant true + store %sparse, %annotations[%c0] : memref + store %sparse, %annotations[%c1] : memref + + // Setup memory for a single reduction scalar, + // initialized to zero. + %xdata = alloc() : memref + store %d0, %xdata[] : memref + %x = tensor_load %xdata : memref + + // Read the sparse matrix from file, construct sparse storage + // according to in memory, and call the kernl. + %fileName = call @getTensorFilename(%c0) : (index) -> (!Filename) + %a = call @newSparseTensor(%fileName, %annotations) + : (!Filename, memref) -> (!SparseTensor) + %0 = call @kernel_sum_reduce(%a, %x) + : (!SparseTensor, tensor) -> tensor + + // Print the result for verification. + // + // CHECK: 28.2 + // + %m = tensor_to_memref %0 : memref + %v = load %m[] : memref + vector.print %v : f64 + + // Release the resources. + call @delSparseTensor(%a) : (!SparseTensor) -> () + dealloc %xdata : memref + + return + } +} diff --git a/mlir/lib/Dialect/Linalg/Transforms/CMakeLists.txt b/mlir/lib/Dialect/Linalg/Transforms/CMakeLists.txt --- a/mlir/lib/Dialect/Linalg/Transforms/CMakeLists.txt +++ b/mlir/lib/Dialect/Linalg/Transforms/CMakeLists.txt @@ -10,6 +10,7 @@ Interchange.cpp Loops.cpp Promotion.cpp + SparseLowering.cpp Sparsification.cpp Tiling.cpp Transforms.cpp diff --git a/mlir/lib/Dialect/Linalg/Transforms/SparseLowering.cpp b/mlir/lib/Dialect/Linalg/Transforms/SparseLowering.cpp new file mode 100644 --- /dev/null +++ b/mlir/lib/Dialect/Linalg/Transforms/SparseLowering.cpp @@ -0,0 +1,124 @@ +//===- SparseLowering.cpp - Lowers sparse primitives to library calls. ---===// +// +// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions. +// See https://llvm.org/LICENSE.txt for license information. +// SPDX-License-Identifier: Apache-2. +// rewriter.replaceOpWithNewOp(0 WITH LLVM-exception +// +//===----------------------------------------------------------------------===// + +#include "mlir/Dialect/LLVMIR/LLVMTypes.h" +#include "mlir/Dialect/Linalg/IR/LinalgOps.h" +#include "mlir/Dialect/Linalg/Transforms/Transforms.h" + +using namespace mlir; + +namespace { + +/// Returns function reference (first hit also inserts into module). +static FlatSymbolRefAttr getFunc(Operation *op, StringRef name, Type result, + ArrayRef operands) { + MLIRContext *context = op->getContext(); + auto module = op->getParentOfType(); + auto func = module.lookupSymbol(name); + if (!func) { + SmallVector params(operands.size()); + for (unsigned i = 0, n = operands.size(); i < n; i++) + params[i] = operands[i].getType(); + OpBuilder moduleBuilder(module.getBodyRegion()); + moduleBuilder + .create(op->getLoc(), name, + FunctionType::get(context, params, result)) + .setPrivate(); + } + return SymbolRefAttr::get(name, context); +} + +/// Sparse conversion rule to remove opaque pointer cast. +class TensorFromPointerConverter + : public OpConversionPattern { + using OpConversionPattern::OpConversionPattern; + LogicalResult + matchAndRewrite(linalg::SparseTensorFromPointerOp op, + ArrayRef operands, + ConversionPatternRewriter &rewriter) const override { + rewriter.replaceOp(op, operands[0]); + return success(); + } +}; + +/// Sparse conversion rule for pointer accesses. +class TensorToPointersConverter + : public OpConversionPattern { +public: + using OpConversionPattern::OpConversionPattern; + LogicalResult + matchAndRewrite(linalg::SparseTensorToPointersMemRefOp op, + ArrayRef operands, + ConversionPatternRewriter &rewriter) const override { + Type resType = op.getType(); + Type eltType = resType.cast().getElementType(); + StringRef name; + if (eltType.isIndex() || eltType.isInteger(64)) + name = "sparsePtrsI64"; + else + return failure(); + rewriter.replaceOpWithNewOp( + op, resType, getFunc(op, name, resType, operands), operands); + return success(); + } +}; + +/// Sparse conversion rule for index accesses. +class TensorToIndicesConverter + : public OpConversionPattern { +public: + using OpConversionPattern::OpConversionPattern; + LogicalResult + matchAndRewrite(linalg::SparseTensorToIndicesMemRefOp op, + ArrayRef operands, + ConversionPatternRewriter &rewriter) const override { + Type resType = op.getType(); + Type eltType = resType.cast().getElementType(); + StringRef name; + if (eltType.isIndex() || eltType.isInteger(64)) + name = "sparseIndxsI64"; + else + return failure(); + rewriter.replaceOpWithNewOp( + op, resType, getFunc(op, name, resType, operands), operands); + return success(); + } +}; + +/// Sparse conversion rule for value accesses. +class TensorToValuesConverter + : public OpConversionPattern { +public: + using OpConversionPattern::OpConversionPattern; + LogicalResult + matchAndRewrite(linalg::SparseTensorToValuesMemRefOp op, + ArrayRef operands, + ConversionPatternRewriter &rewriter) const override { + Type resType = op.getType(); + Type eltType = resType.cast().getElementType(); + StringRef name; + if (eltType.isF64()) + name = "sparseValsF64"; + else + return failure(); + rewriter.replaceOpWithNewOp( + op, resType, getFunc(op, name, resType, operands), operands); + return success(); + } +}; + +} // namespace + +/// Populates the given patterns list with conversion rules required for +/// the sparsification of linear algebra operations. +void linalg::populateSparsificationConversionPatterns( + MLIRContext *context, OwningRewritePatternList &patterns) { + patterns.insert(context); +} diff --git a/mlir/lib/Dialect/Linalg/Transforms/Sparsification.cpp b/mlir/lib/Dialect/Linalg/Transforms/Sparsification.cpp --- a/mlir/lib/Dialect/Linalg/Transforms/Sparsification.cpp +++ b/mlir/lib/Dialect/Linalg/Transforms/Sparsification.cpp @@ -520,6 +520,32 @@ llvm_unreachable("unexpected SparseIntType"); } +/// Generates buffer for output tensor (note that the sparse compiler always +/// assumes that the ouput buffer is already initialized to all zeros in +/// case the full dense output could potentially be written, or simply to +/// the initial value when an update is done). +static Value genOutputBuffer(CodeGen &codegen, PatternRewriter &rewriter, + linalg::GenericOp op, MemRefType denseTp, + ArrayRef args) { + Location loc = op.getLoc(); + Value tensor = op.getOutput(0); + // The output tensor simply could materialize from the buffer that will + // be generated for the tensor present in the outs() clause. This has + // the major advantage that the sparse kernel only updates the nonzero + // positions for the output tensor. Currently this results in functional, + // but slightly imprecise IR, so it is put under an experimental option. + if (codegen.options.fastOutput) + return rewriter.create(loc, denseTp, tensor); + // By default, a new buffer is allocated which is initialized to the + // tensor defined in the outs() clause. Ths is always correct but + // introduces a dense initialization component that may negatively + // impact the running complexity of the sparse kernel. + Value init = rewriter.create(loc, denseTp, tensor); + Value alloc = rewriter.create(loc, denseTp, args); + rewriter.create(loc, init, alloc); + return alloc; +} + /// Local bufferization of all dense and sparse data structures. /// This code enables testing the first prototype sparse compiler. // TODO: replace this with a proliferated bufferization strategy @@ -529,15 +555,11 @@ unsigned numTensors = op.getNumShapedOperands(); unsigned numInputs = op.getNumInputs(); assert(numTensors == numInputs + 1); - - // For now, set all unknown dimensions to 999. - // TODO: compute these values (using sparsity or by reading tensor) - Value unknown = rewriter.create(loc, 999); - // For every tensor, find lower and upper bound on dimensions, set the - // same bounds on loop indices, and allocate dense or sparse buffer(s). + // same bounds on loop indices, and obtain dense or sparse buffer(s). SmallVector args; for (unsigned t = 0; t < numTensors; t++) { + Value tensor = t < numInputs ? op.getInput(t) : op.getOutput(0); auto tensorType = op.getShapedType(t); auto shape = tensorType.getShape(); auto map = op.getIndexingMap(t); @@ -554,28 +576,42 @@ dynShape, genIntType(rewriter, codegen.options.ptrType)); auto indTp = MemRefType::get( dynShape, genIntType(rewriter, codegen.options.indType)); - codegen.pointers[t][i] = rewriter.create(loc, ptrTp, unknown); - codegen.indices[t][i] = rewriter.create(loc, indTp, unknown); + Value dim = rewriter.create(loc, d); + // Generate sparse primitives to obtains pointer and indices. + codegen.pointers[t][i] = + rewriter.create( + loc, ptrTp, tensor, dim); + codegen.indices[t][i] = + rewriter.create(loc, indTp, + tensor, dim); } // Find lower and upper bound in current dimension. Value up; if (shape[d] == TensorType::kDynamicSize) { - Value arg = t < numInputs ? op.getInput(t) : op.getOutput(0); - up = rewriter.create(loc, arg, d); + up = rewriter.create(loc, tensor, d); args.push_back(up); } else { up = rewriter.create(loc, shape[d]); } codegen.sizes[i] = codegen.highs[t][i] = up; } - // Allocate dense or sparse buffer for numerical values. + // Perform the required bufferization. All dense inputs materialize + // from the input tensor. The dense output tensor needs special + // handling. Sparse inputs use a sparse primitive to obtain the values. if (allDense) { auto denseTp = MemRefType::get(shape, tensorType.getElementType()); - codegen.buffers[t] = rewriter.create(loc, denseTp, args); + if (t < numInputs) + codegen.buffers[t] = + rewriter.create(loc, denseTp, tensor); + else + codegen.buffers[t] = + genOutputBuffer(codegen, rewriter, op, denseTp, args); } else { - auto sparseTp = MemRefType::get({ShapedType::kDynamicSize}, - tensorType.getElementType()); - codegen.buffers[t] = rewriter.create(loc, sparseTp, unknown); + auto dynShape = {ShapedType::kDynamicSize}; + auto sparseTp = MemRefType::get(dynShape, tensorType.getElementType()); + codegen.buffers[t] = + rewriter.create(loc, sparseTp, + tensor); } } } diff --git a/mlir/lib/ExecutionEngine/SparseUtils.cpp b/mlir/lib/ExecutionEngine/SparseUtils.cpp --- a/mlir/lib/ExecutionEngine/SparseUtils.cpp +++ b/mlir/lib/ExecutionEngine/SparseUtils.cpp @@ -42,6 +42,8 @@ namespace { +class SparseTensorStorage; + /// A sparse tensor element in coordinate scheme (value and indices). /// For example, a rank-1 vector element would look like /// ({i}, a[i]) @@ -92,6 +94,86 @@ std::vector sizes; // per-rank dimension sizes std::vector elements; uint64_t pos; + + friend SparseTensorStorage; +}; + +/// A memory-resident sparse tensor using a storage scheme based on per-rank +/// annotations on dense/sparse. This data structure provides a bufferized +/// form of an imaginary SparseTensorType, until such a type becomes a +/// first-class citizen of MLIR. In contrast to generating setup methods for +/// each differently annotated sparse tensor, this method provides a convenient +/// "one-size-fits-all" solution that simply takes an input tensor and +/// annotations to mplement all required setup in a general manner. +class SparseTensorStorage { +public: + /// Constructs sparse tensor storage scheme following the given + /// per-rank dimension dense/sparse annotations. + SparseTensorStorage(SparseTensor *tensor, bool *sparsity) + : rank(tensor->sizes.size()), positions(rank), indices(rank) { + // Provide hints on capacity. + // TODO: needs fine-tuning based on sparsity + values.reserve(tensor->elements.size()); + for (unsigned d = 0, s = 1; d < rank; d++) { + s *= tensor->sizes[d]; + if (sparsity[d]) { + positions[d].reserve(s + 1); + indices[d].reserve(s); + s = 1; + } + } + // Then setup the tensor. + traverse(tensor, sparsity, 0, tensor->elements.size(), 0); + } + + /// Initialize sparse tensor storage scheme from a memory-resident + /// representation of an external sparse tensor. This method prepares + /// the pointers and indices arrays under the given per-rank dimension + /// dense/sparse annotations. + void traverse(SparseTensor *tensor, bool *sparsity, uint64_t lo, uint64_t hi, + uint64_t d) { + const std::vector &elements = tensor->elements; + // Once dimensions are exhausted, insert the numerical values. + if (d == rank) { + values.push_back(lo < hi ? elements[lo].value : 0.0); + return; + } + // Prepare a sparse pointer structure at this dimension. + if (sparsity[d] && positions[d].empty()) + positions[d].push_back(0); + // Visit all elements in this interval. + uint64_t full = 0; + while (lo < hi) { + // Find segment in interval with same index elements in this dimension. + unsigned idx = elements[lo].indices[d]; + unsigned seg = lo + 1; + while (seg < hi && elements[seg].indices[d] == idx) + seg++; + // Handle segment in interval for sparse or dense dimension. + if (sparsity[d]) { + indices[d].push_back(idx); + } else { + for (; full < idx; full++) + traverse(tensor, sparsity, 0, 0, d + 1); // pass empty + full++; + } + traverse(tensor, sparsity, lo, seg, d + 1); + // And move on to next segment in interval. + lo = seg; + } + // Finalize the sparse pointer structure at this dimension. + if (sparsity[d]) { + positions[d].push_back(indices[d].size()); + } else { + for (uint64_t sz = tensor->sizes[d]; full < sz; full++) + traverse(tensor, sparsity, 0, 0, d + 1); // pas empty + } + } + + const uint64_t rank; + std::vector> positions; + std::vector> indices; + std::vector values; }; /// Helper to convert string to lower case. @@ -200,24 +282,37 @@ // // // Note that input parameters in the "MLIRized" version of a function mimic -// the data layout of a MemRef: -// -// struct MemRef { -// T *base; -// T *data; -// int64_t off; -// int64_t sizes[1]; -// int64_t strides[1]; -// } +// the data layout of a MemRef (but cannot use a direct struxt). The +// output parameter uses a direct struct. // //===----------------------------------------------------------------------===// +extern "C" { + +/// Cannot use templates with C linkage. + +struct MemRefU64 { + const uint64_t *base; + const uint64_t *data; + uint64_t off; + uint64_t sizes[1]; + uint64_t strides[1]; +}; + +struct MemRefF64 { + const double *base; + const double *data; + uint64_t off; + uint64_t sizes[1]; + uint64_t strides[1]; +}; + /// Reads in a sparse tensor with the given filename. The call yields a /// pointer to an opaque memory-resident sparse tensor object that is only /// understood by other methods in the sparse runtime support library. An /// array parameter is used to pass the rank, the number of nonzero elements, /// and the dimension sizes (one per rank). -extern "C" void *openTensorC(char *filename, uint64_t *idata) { +void *openTensorC(char *filename, uint64_t *idata) { // Open the file. FILE *file = fopen(filename, "r"); if (!file) { @@ -264,14 +359,14 @@ } /// "MLIRized" version. -extern "C" void *openTensor(char *filename, uint64_t *ibase, uint64_t *idata, - uint64_t ioff, uint64_t isize, uint64_t istride) { +void *openTensor(char *filename, uint64_t *ibase, uint64_t *idata, + uint64_t ioff, uint64_t isize, uint64_t istride) { assert(istride == 1); return openTensorC(filename, idata + ioff); } /// Yields the next element from the given opaque sparse tensor object. -extern "C" void readTensorItemC(void *tensor, uint64_t *idata, double *ddata) { +void readTensorItemC(void *tensor, uint64_t *idata, double *ddata) { const Element &e = static_cast(tensor)->next(); for (uint64_t r = 0, rank = e.indices.size(); r < rank; r++) idata[r] = e.indices[r]; @@ -279,27 +374,69 @@ } /// "MLIRized" version. -extern "C" void readTensorItem(void *tensor, uint64_t *ibase, uint64_t *idata, - uint64_t ioff, uint64_t isize, uint64_t istride, - double *dbase, double *ddata, uint64_t doff, - uint64_t dsize, uint64_t dstride) { +void readTensorItem(void *tensor, uint64_t *ibase, uint64_t *idata, + uint64_t ioff, uint64_t isize, uint64_t istride, + double *dbase, double *ddata, uint64_t doff, uint64_t dsize, + uint64_t dstride) { assert(istride == 1 && dstride == 1); readTensorItemC(tensor, idata + ioff, ddata + doff); } /// Closes the given opaque sparse tensor object, releasing its memory -/// resources. After this call, the opague object cannot be used anymore. -extern "C" void closeTensor(void *tensor) { - delete static_cast(tensor); -} +/// resources. After this call, the opaque object cannot be used anymore. +void closeTensor(void *tensor) { delete static_cast(tensor); } /// Helper method to read a sparse tensor filename from the environment, /// defined with the naming convention ${TENSOR0}, ${TENSOR1}, etc. -extern "C" char *getTensorFilename(uint64_t id) { +char *getTensorFilename(uint64_t id) { char var[80]; sprintf(var, "TENSOR%" PRIu64, id); char *env = getenv(var); return env; } +/// +/// Sparse primitives that support an opaque implementation of a bufferized +/// SparseTensor in MLIR. This could be replaced by actual codegen in MLIR. +/// + +void *newSparseTensorC(char *filename, bool *annotations) { + uint64_t idata[64]; + SparseTensor *t = static_cast(openTensorC(filename, idata)); + SparseTensorStorage *tensor = new SparseTensorStorage(t, annotations); + delete t; + return tensor; +} + +/// "MLIRized" version. +void *newSparseTensor(char *filename, bool *abase, bool *adata, uint64_t aoff, + uint64_t asize, uint64_t astride) { + assert(astride == 1); + return newSparseTensorC(filename, abase + aoff); +} + +MemRefU64 sparsePtrsI64(void *tensor, uint64_t d) { + const std::vector &v = + static_cast(tensor)->positions[d]; + return {v.data(), v.data(), 0, {v.size()}, {1}}; +} + +MemRefU64 sparseIndxsI64(void *tensor, uint64_t d) { + const std::vector &v = + static_cast(tensor)->indices[d]; + return {v.data(), v.data(), 0, {v.size()}, {1}}; +} + +MemRefF64 sparseValsF64(void *tensor) { + const std::vector &v = + static_cast(tensor)->values; + return {v.data(), v.data(), 0, {v.size()}, {1}}; +} + +void delSparseTensor(void *tensor) { + delete static_cast(tensor); +} + +} // extern "C" + #endif // MLIR_CRUNNERUTILS_DEFINE_FUNCTIONS diff --git a/mlir/test/Dialect/Linalg/sparse_1d.mlir b/mlir/test/Dialect/Linalg/sparse_1d.mlir --- a/mlir/test/Dialect/Linalg/sparse_1d.mlir +++ b/mlir/test/Dialect/Linalg/sparse_1d.mlir @@ -21,15 +21,17 @@ // CHECK: %[[VAL_3:.*]] = constant 32 : index // CHECK: %[[VAL_4:.*]] = constant 0 : index // CHECK: %[[VAL_5:.*]] = constant 1 : index -// CHECK: %[[VAL_6:.*]] = alloca() : memref<32xf32> -// CHECK: %[[VAL_7:.*]] = alloca() : memref<32xf32> -// CHECK: scf.for %[[VAL_8:.*]] = %[[VAL_4]] to %[[VAL_3]] step %[[VAL_5]] { -// CHECK: %[[VAL_9:.*]] = load %[[VAL_6]]{{\[}}%[[VAL_8]]] : memref<32xf32> -// CHECK: %[[VAL_10:.*]] = addf %[[VAL_9]], %[[VAL_1]] : f32 -// CHECK: store %[[VAL_10]], %[[VAL_7]]{{\[}}%[[VAL_8]]] : memref<32xf32> +// CHECK: %[[VAL_6:.*]] = tensor_to_memref %[[VAL_0]] : memref<32xf32> +// CHECK: %[[VAL_7:.*]] = tensor_to_memref %[[VAL_2]] : memref<32xf32> +// CHECK: %[[VAL_8:.*]] = alloc() : memref<32xf32> +// CHECK: linalg.copy(%[[VAL_7]], %[[VAL_8]]) : memref<32xf32>, memref<32xf32> +// CHECK: scf.for %[[VAL_9:.*]] = %[[VAL_4]] to %[[VAL_3]] step %[[VAL_5]] { +// CHECK: %[[VAL_10:.*]] = load %[[VAL_6]]{{\[}}%[[VAL_9]]] : memref<32xf32> +// CHECK: %[[VAL_11:.*]] = addf %[[VAL_10]], %[[VAL_1]] : f32 +// CHECK: store %[[VAL_11]], %[[VAL_8]]{{\[}}%[[VAL_9]]] : memref<32xf32> // CHECK: } -// CHECK: %[[VAL_11:.*]] = tensor_load %[[VAL_7]] : memref<32xf32> -// CHECK: return %[[VAL_11]] : tensor<32xf32> +// CHECK: %[[VAL_12:.*]] = tensor_load %[[VAL_8]] : memref<32xf32> +// CHECK: return %[[VAL_12]] : tensor<32xf32> // CHECK: } func @add_d(%arga: tensor<32xf32>, %argb: f32, %argx: tensor<32xf32>) -> tensor<32xf32> { %0 = linalg.generic #trait_d @@ -49,15 +51,17 @@ // CHECK: %[[VAL_3:.*]] = constant 32 : index // CHECK: %[[VAL_4:.*]] = constant 0 : index // CHECK: %[[VAL_5:.*]] = constant 1 : index -// CHECK: %[[VAL_6:.*]] = alloca() : memref<32xf32> -// CHECK: %[[VAL_7:.*]] = alloca() : memref<32xf32> -// CHECK: scf.for %[[VAL_8:.*]] = %[[VAL_4]] to %[[VAL_3]] step %[[VAL_5]] { -// CHECK: %[[VAL_9:.*]] = load %[[VAL_6]]{{\[}}%[[VAL_8]]] : memref<32xf32> -// CHECK: %[[VAL_10:.*]] = mulf %[[VAL_9]], %[[VAL_1]] : f32 -// CHECK: store %[[VAL_10]], %[[VAL_7]]{{\[}}%[[VAL_8]]] : memref<32xf32> +// CHECK: %[[VAL_6:.*]] = tensor_to_memref %[[VAL_0]] : memref<32xf32> +// CHECK: %[[VAL_7:.*]] = tensor_to_memref %[[VAL_2]] : memref<32xf32> +// CHECK: %[[VAL_8:.*]] = alloc() : memref<32xf32> +// CHECK: linalg.copy(%[[VAL_7]], %[[VAL_8]]) : memref<32xf32>, memref<32xf32> +// CHECK: scf.for %[[VAL_9:.*]] = %[[VAL_4]] to %[[VAL_3]] step %[[VAL_5]] { +// CHECK: %[[VAL_10:.*]] = load %[[VAL_6]]{{\[}}%[[VAL_9]]] : memref<32xf32> +// CHECK: %[[VAL_11:.*]] = mulf %[[VAL_10]], %[[VAL_1]] : f32 +// CHECK: store %[[VAL_11]], %[[VAL_8]]{{\[}}%[[VAL_9]]] : memref<32xf32> // CHECK: } -// CHECK: %[[VAL_11:.*]] = tensor_load %[[VAL_7]] : memref<32xf32> -// CHECK: return %[[VAL_11]] : tensor<32xf32> +// CHECK: %[[VAL_12:.*]] = tensor_load %[[VAL_8]] : memref<32xf32> +// CHECK: return %[[VAL_12]] : tensor<32xf32> // CHECK: } func @mul_d(%arga: tensor<32xf32>, %argb: f32, %argx: tensor<32xf32>) -> tensor<32xf32> { %0 = linalg.generic #trait_d @@ -87,41 +91,42 @@ // CHECK-SAME: %[[VAL_0:.*]]: tensor<32xf32>, // CHECK-SAME: %[[VAL_1:.*]]: f32, // CHECK-SAME: %[[VAL_2:.*]]: tensor<32xf32>) -> tensor<32xf32> { -// CHECK: %[[VAL_3:.*]] = constant 999 : index -// CHECK: %[[VAL_4:.*]] = constant 32 : index -// CHECK: %[[VAL_5:.*]] = constant 0 : index -// CHECK: %[[VAL_6:.*]] = constant true -// CHECK: %[[VAL_7:.*]] = constant 1 : index -// CHECK: %[[VAL_8:.*]] = alloca(%[[VAL_3]]) : memref -// CHECK: %[[VAL_9:.*]] = alloca(%[[VAL_3]]) : memref -// CHECK: %[[VAL_10:.*]] = alloca(%[[VAL_3]]) : memref -// CHECK: %[[VAL_11:.*]] = alloca() : memref<32xf32> -// CHECK: %[[VAL_12:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_5]]] : memref -// CHECK: %[[VAL_13:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_7]]] : memref -// CHECK: %[[VAL_14:.*]]:2 = scf.while (%[[VAL_15:.*]] = %[[VAL_12]], %[[VAL_16:.*]] = %[[VAL_5]]) : (index, index) -> (index, index) { +// CHECK: %[[VAL_3:.*]] = constant 32 : index +// CHECK: %[[VAL_4:.*]] = constant 0 : index +// CHECK: %[[VAL_5:.*]] = constant true +// CHECK: %[[VAL_6:.*]] = constant 1 : index +// CHECK: %[[VAL_7:.*]] = linalg.sparse_pointers %[[VAL_0]], %[[VAL_4]] : tensor<32xf32> into memref +// CHECK: %[[VAL_8:.*]] = linalg.sparse_indices %[[VAL_0]], %[[VAL_4]] : tensor<32xf32> into memref +// CHECK: %[[VAL_9:.*]] = linalg.sparse_values %[[VAL_0]] : tensor<32xf32> into memref +// CHECK: %[[VAL_10:.*]] = tensor_to_memref %[[VAL_2]] : memref<32xf32> +// CHECK: %[[VAL_11:.*]] = alloc() : memref<32xf32> +// CHECK: linalg.copy(%[[VAL_10]], %[[VAL_11]]) : memref<32xf32>, memref<32xf32> +// CHECK: %[[VAL_12:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_4]]] : memref +// CHECK: %[[VAL_13:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_6]]] : memref +// CHECK: %[[VAL_14:.*]]:2 = scf.while (%[[VAL_15:.*]] = %[[VAL_12]], %[[VAL_16:.*]] = %[[VAL_4]]) : (index, index) -> (index, index) { // CHECK: %[[VAL_17:.*]] = cmpi ult, %[[VAL_15]], %[[VAL_13]] : index // CHECK: scf.condition(%[[VAL_17]]) %[[VAL_15]], %[[VAL_16]] : index, index // CHECK: } do { // CHECK: ^bb0(%[[VAL_18:.*]]: index, %[[VAL_19:.*]]: index): -// CHECK: %[[VAL_20:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_18]]] : memref +// CHECK: %[[VAL_20:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_18]]] : memref // CHECK: %[[VAL_21:.*]] = cmpi eq, %[[VAL_20]], %[[VAL_19]] : index // CHECK: scf.if %[[VAL_21]] { -// CHECK: %[[VAL_22:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_18]]] : memref +// CHECK: %[[VAL_22:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_18]]] : memref // CHECK: %[[VAL_23:.*]] = addf %[[VAL_22]], %[[VAL_1]] : f32 // CHECK: store %[[VAL_23]], %[[VAL_11]]{{\[}}%[[VAL_19]]] : memref<32xf32> // CHECK: } else { -// CHECK: scf.if %[[VAL_6]] { +// CHECK: scf.if %[[VAL_5]] { // CHECK: store %[[VAL_1]], %[[VAL_11]]{{\[}}%[[VAL_19]]] : memref<32xf32> // CHECK: } else { // CHECK: } // CHECK: } // CHECK: %[[VAL_24:.*]] = cmpi eq, %[[VAL_20]], %[[VAL_19]] : index -// CHECK: %[[VAL_25:.*]] = addi %[[VAL_18]], %[[VAL_7]] : index +// CHECK: %[[VAL_25:.*]] = addi %[[VAL_18]], %[[VAL_6]] : index // CHECK: %[[VAL_26:.*]] = select %[[VAL_24]], %[[VAL_25]], %[[VAL_18]] : index -// CHECK: %[[VAL_27:.*]] = addi %[[VAL_19]], %[[VAL_7]] : index +// CHECK: %[[VAL_27:.*]] = addi %[[VAL_19]], %[[VAL_6]] : index // CHECK: scf.yield %[[VAL_26]], %[[VAL_27]] : index, index // CHECK: } -// CHECK: scf.for %[[VAL_28:.*]] = %[[VAL_29:.*]]#1 to %[[VAL_4]] step %[[VAL_7]] { +// CHECK: scf.for %[[VAL_28:.*]] = %[[VAL_29:.*]]#1 to %[[VAL_3]] step %[[VAL_6]] { // CHECK: store %[[VAL_1]], %[[VAL_11]]{{\[}}%[[VAL_28]]] : memref<32xf32> // CHECK: } // CHECK: %[[VAL_30:.*]] = tensor_load %[[VAL_11]] : memref<32xf32> @@ -141,22 +146,23 @@ // CHECK-LABEL: func @repeated_add_s( // CHECK-SAME: %[[VAL_0:.*]]: tensor<32xf32>, // CHECK-SAME: %[[VAL_1:.*]]: tensor<32xf32>) -> tensor<32xf32> { -// CHECK: %[[VAL_2:.*]] = constant 999 : index -// CHECK: %[[VAL_3:.*]] = constant 0 : index -// CHECK: %[[VAL_4:.*]] = constant 1 : index -// CHECK: %[[VAL_5:.*]] = alloca(%[[VAL_2]]) : memref -// CHECK: %[[VAL_6:.*]] = alloca(%[[VAL_2]]) : memref -// CHECK: %[[VAL_7:.*]] = alloca(%[[VAL_2]]) : memref -// CHECK: %[[VAL_8:.*]] = alloca() : memref<32xf32> -// CHECK: %[[VAL_9:.*]] = load %[[VAL_5]]{{\[}}%[[VAL_3]]] : memref -// CHECK: %[[VAL_10:.*]] = load %[[VAL_5]]{{\[}}%[[VAL_4]]] : memref -// CHECK: scf.for %[[VAL_11:.*]] = %[[VAL_9]] to %[[VAL_10]] step %[[VAL_4]] { -// CHECK: %[[VAL_12:.*]] = load %[[VAL_6]]{{\[}}%[[VAL_11]]] : memref -// CHECK: %[[VAL_13:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_11]]] : memref -// CHECK: %[[VAL_14:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_11]]] : memref +// CHECK: %[[VAL_2:.*]] = constant 0 : index +// CHECK: %[[VAL_3:.*]] = constant 1 : index +// CHECK: %[[VAL_4:.*]] = linalg.sparse_pointers %[[VAL_0]], %[[VAL_2]] : tensor<32xf32> into memref +// CHECK: %[[VAL_5:.*]] = linalg.sparse_indices %[[VAL_0]], %[[VAL_2]] : tensor<32xf32> into memref +// CHECK: %[[VAL_6:.*]] = linalg.sparse_values %[[VAL_0]] : tensor<32xf32> into memref +// CHECK: %[[VAL_7:.*]] = tensor_to_memref %[[VAL_1]] : memref<32xf32> +// CHECK: %[[VAL_8:.*]] = alloc() : memref<32xf32> +// CHECK: linalg.copy(%[[VAL_7]], %[[VAL_8]]) : memref<32xf32>, memref<32xf32> +// CHECK: %[[VAL_9:.*]] = load %[[VAL_4]]{{\[}}%[[VAL_2]]] : memref +// CHECK: %[[VAL_10:.*]] = load %[[VAL_4]]{{\[}}%[[VAL_3]]] : memref +// CHECK: scf.for %[[VAL_11:.*]] = %[[VAL_9]] to %[[VAL_10]] step %[[VAL_3]] { +// CHECK: %[[VAL_12:.*]] = load %[[VAL_5]]{{\[}}%[[VAL_11]]] : memref +// CHECK: %[[VAL_13:.*]] = load %[[VAL_6]]{{\[}}%[[VAL_11]]] : memref +// CHECK: %[[VAL_14:.*]] = load %[[VAL_6]]{{\[}}%[[VAL_11]]] : memref // CHECK: %[[VAL_15:.*]] = addf %[[VAL_13]], %[[VAL_14]] : f32 -// CHECK: %[[VAL_16:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_11]]] : memref -// CHECK: %[[VAL_17:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_11]]] : memref +// CHECK: %[[VAL_16:.*]] = load %[[VAL_6]]{{\[}}%[[VAL_11]]] : memref +// CHECK: %[[VAL_17:.*]] = load %[[VAL_6]]{{\[}}%[[VAL_11]]] : memref // CHECK: %[[VAL_18:.*]] = addf %[[VAL_16]], %[[VAL_17]] : f32 // CHECK: %[[VAL_19:.*]] = addf %[[VAL_15]], %[[VAL_18]] : f32 // CHECK: store %[[VAL_19]], %[[VAL_8]]{{\[}}%[[VAL_12]]] : memref<32xf32> @@ -181,18 +187,19 @@ // CHECK-SAME: %[[VAL_0:.*]]: tensor<32xf32>, // CHECK-SAME: %[[VAL_1:.*]]: f32, // CHECK-SAME: %[[VAL_2:.*]]: tensor<32xf32>) -> tensor<32xf32> { -// CHECK: %[[VAL_3:.*]] = constant 999 : index -// CHECK: %[[VAL_4:.*]] = constant 0 : index -// CHECK: %[[VAL_5:.*]] = constant 1 : index -// CHECK: %[[VAL_6:.*]] = alloca(%[[VAL_3]]) : memref -// CHECK: %[[VAL_7:.*]] = alloca(%[[VAL_3]]) : memref -// CHECK: %[[VAL_8:.*]] = alloca(%[[VAL_3]]) : memref -// CHECK: %[[VAL_9:.*]] = alloca() : memref<32xf32> -// CHECK: %[[VAL_10:.*]] = load %[[VAL_6]]{{\[}}%[[VAL_4]]] : memref -// CHECK: %[[VAL_11:.*]] = load %[[VAL_6]]{{\[}}%[[VAL_5]]] : memref -// CHECK: scf.for %[[VAL_12:.*]] = %[[VAL_10]] to %[[VAL_11]] step %[[VAL_5]] { -// CHECK: %[[VAL_13:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_12]]] : memref -// CHECK: %[[VAL_14:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_12]]] : memref +// CHECK: %[[VAL_3:.*]] = constant 0 : index +// CHECK: %[[VAL_4:.*]] = constant 1 : index +// CHECK: %[[VAL_5:.*]] = linalg.sparse_pointers %[[VAL_0]], %[[VAL_3]] : tensor<32xf32> into memref +// CHECK: %[[VAL_6:.*]] = linalg.sparse_indices %[[VAL_0]], %[[VAL_3]] : tensor<32xf32> into memref +// CHECK: %[[VAL_7:.*]] = linalg.sparse_values %[[VAL_0]] : tensor<32xf32> into memref +// CHECK: %[[VAL_8:.*]] = tensor_to_memref %[[VAL_2]] : memref<32xf32> +// CHECK: %[[VAL_9:.*]] = alloc() : memref<32xf32> +// CHECK: linalg.copy(%[[VAL_8]], %[[VAL_9]]) : memref<32xf32>, memref<32xf32> +// CHECK: %[[VAL_10:.*]] = load %[[VAL_5]]{{\[}}%[[VAL_3]]] : memref +// CHECK: %[[VAL_11:.*]] = load %[[VAL_5]]{{\[}}%[[VAL_4]]] : memref +// CHECK: scf.for %[[VAL_12:.*]] = %[[VAL_10]] to %[[VAL_11]] step %[[VAL_4]] { +// CHECK: %[[VAL_13:.*]] = load %[[VAL_6]]{{\[}}%[[VAL_12]]] : memref +// CHECK: %[[VAL_14:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_12]]] : memref // CHECK: %[[VAL_15:.*]] = mulf %[[VAL_14]], %[[VAL_1]] : f32 // CHECK: store %[[VAL_15]], %[[VAL_9]]{{\[}}%[[VAL_13]]] : memref<32xf32> // CHECK: } @@ -232,17 +239,19 @@ // CHECK: %[[VAL_3:.*]] = constant 32 : index // CHECK: %[[VAL_4:.*]] = constant 0 : index // CHECK: %[[VAL_5:.*]] = constant 1 : index -// CHECK: %[[VAL_6:.*]] = alloca() : memref<32xf32> -// CHECK: %[[VAL_7:.*]] = alloca() : memref<32xf32> -// CHECK: %[[VAL_8:.*]] = alloca() : memref<32xf32> -// CHECK: scf.for %[[VAL_9:.*]] = %[[VAL_4]] to %[[VAL_3]] step %[[VAL_5]] { -// CHECK: %[[VAL_10:.*]] = load %[[VAL_6]]{{\[}}%[[VAL_9]]] : memref<32xf32> -// CHECK: %[[VAL_11:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_9]]] : memref<32xf32> -// CHECK: %[[VAL_12:.*]] = addf %[[VAL_10]], %[[VAL_11]] : f32 -// CHECK: store %[[VAL_12]], %[[VAL_8]]{{\[}}%[[VAL_9]]] : memref<32xf32> +// CHECK: %[[VAL_6:.*]] = tensor_to_memref %[[VAL_0]] : memref<32xf32> +// CHECK: %[[VAL_7:.*]] = tensor_to_memref %[[VAL_1]] : memref<32xf32> +// CHECK: %[[VAL_8:.*]] = tensor_to_memref %[[VAL_2]] : memref<32xf32> +// CHECK: %[[VAL_9:.*]] = alloc() : memref<32xf32> +// CHECK: linalg.copy(%[[VAL_8]], %[[VAL_9]]) : memref<32xf32>, memref<32xf32> +// CHECK: scf.for %[[VAL_10:.*]] = %[[VAL_4]] to %[[VAL_3]] step %[[VAL_5]] { +// CHECK: %[[VAL_11:.*]] = load %[[VAL_6]]{{\[}}%[[VAL_10]]] : memref<32xf32> +// CHECK: %[[VAL_12:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_10]]] : memref<32xf32> +// CHECK: %[[VAL_13:.*]] = addf %[[VAL_11]], %[[VAL_12]] : f32 +// CHECK: store %[[VAL_13]], %[[VAL_9]]{{\[}}%[[VAL_10]]] : memref<32xf32> // CHECK: } -// CHECK: %[[VAL_13:.*]] = tensor_load %[[VAL_8]] : memref<32xf32> -// CHECK: return %[[VAL_13]] : tensor<32xf32> +// CHECK: %[[VAL_14:.*]] = tensor_load %[[VAL_9]] : memref<32xf32> +// CHECK: return %[[VAL_14]] : tensor<32xf32> // CHECK: } func @add_dd(%arga: tensor<32xf32>, %argb: tensor<32xf32>, %argx: tensor<32xf32>) -> tensor<32xf32> { %0 = linalg.generic #trait_dd @@ -262,17 +271,19 @@ // CHECK: %[[VAL_3:.*]] = constant 32 : index // CHECK: %[[VAL_4:.*]] = constant 0 : index // CHECK: %[[VAL_5:.*]] = constant 1 : index -// CHECK: %[[VAL_6:.*]] = alloca() : memref<32xf32> -// CHECK: %[[VAL_7:.*]] = alloca() : memref<32xf32> -// CHECK: %[[VAL_8:.*]] = alloca() : memref<32xf32> -// CHECK: scf.for %[[VAL_9:.*]] = %[[VAL_4]] to %[[VAL_3]] step %[[VAL_5]] { -// CHECK: %[[VAL_10:.*]] = load %[[VAL_6]]{{\[}}%[[VAL_9]]] : memref<32xf32> -// CHECK: %[[VAL_11:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_9]]] : memref<32xf32> -// CHECK: %[[VAL_12:.*]] = mulf %[[VAL_10]], %[[VAL_11]] : f32 -// CHECK: store %[[VAL_12]], %[[VAL_8]]{{\[}}%[[VAL_9]]] : memref<32xf32> +// CHECK: %[[VAL_6:.*]] = tensor_to_memref %[[VAL_0]] : memref<32xf32> +// CHECK: %[[VAL_7:.*]] = tensor_to_memref %[[VAL_1]] : memref<32xf32> +// CHECK: %[[VAL_8:.*]] = tensor_to_memref %[[VAL_2]] : memref<32xf32> +// CHECK: %[[VAL_9:.*]] = alloc() : memref<32xf32> +// CHECK: linalg.copy(%[[VAL_8]], %[[VAL_9]]) : memref<32xf32>, memref<32xf32> +// CHECK: scf.for %[[VAL_10:.*]] = %[[VAL_4]] to %[[VAL_3]] step %[[VAL_5]] { +// CHECK: %[[VAL_11:.*]] = load %[[VAL_6]]{{\[}}%[[VAL_10]]] : memref<32xf32> +// CHECK: %[[VAL_12:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_10]]] : memref<32xf32> +// CHECK: %[[VAL_13:.*]] = mulf %[[VAL_11]], %[[VAL_12]] : f32 +// CHECK: store %[[VAL_13]], %[[VAL_9]]{{\[}}%[[VAL_10]]] : memref<32xf32> // CHECK: } -// CHECK: %[[VAL_13:.*]] = tensor_load %[[VAL_8]] : memref<32xf32> -// CHECK: return %[[VAL_13]] : tensor<32xf32> +// CHECK: %[[VAL_14:.*]] = tensor_load %[[VAL_9]] : memref<32xf32> +// CHECK: return %[[VAL_14]] : tensor<32xf32> // CHECK: } func @mul_dd(%arga: tensor<32xf32>, %argb: tensor<32xf32>, %argx: tensor<32xf32>) -> tensor<32xf32> { %0 = linalg.generic #trait_dd @@ -304,45 +315,46 @@ // CHECK-SAME: %[[VAL_0:.*0]]: tensor<32xf32>, // CHECK-SAME: %[[VAL_1:.*1]]: tensor<32xf32>, // CHECK-SAME: %[[VAL_2:.*2]]: tensor<32xf32>) -> tensor<32xf32> { -// CHECK: %[[VAL_3:.*]] = constant 999 : index -// CHECK: %[[VAL_4:.*]] = constant 32 : index -// CHECK: %[[VAL_5:.*]] = constant 0 : index -// CHECK: %[[VAL_6:.*]] = constant true -// CHECK: %[[VAL_7:.*]] = constant 1 : index -// CHECK: %[[VAL_8:.*]] = alloca() : memref<32xf32> -// CHECK: %[[VAL_9:.*]] = alloca(%[[VAL_3]]) : memref -// CHECK: %[[VAL_10:.*]] = alloca(%[[VAL_3]]) : memref -// CHECK: %[[VAL_11:.*]] = alloca(%[[VAL_3]]) : memref -// CHECK: %[[VAL_12:.*]] = alloca() : memref<32xf32> -// CHECK: %[[VAL_13:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_5]]] : memref -// CHECK: %[[VAL_14:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_7]]] : memref -// CHECK: %[[VAL_15:.*]]:2 = scf.while (%[[VAL_16:.*]] = %[[VAL_13]], %[[VAL_17:.*]] = %[[VAL_5]]) : (index, index) -> (index, index) { +// CHECK: %[[VAL_3:.*]] = constant 32 : index +// CHECK: %[[VAL_4:.*]] = constant 0 : index +// CHECK: %[[VAL_5:.*]] = constant true +// CHECK: %[[VAL_6:.*]] = constant 1 : index +// CHECK: %[[VAL_7:.*]] = tensor_to_memref %[[VAL_0]] : memref<32xf32> +// CHECK: %[[VAL_8:.*]] = linalg.sparse_pointers %[[VAL_1]], %[[VAL_4]] : tensor<32xf32> into memref +// CHECK: %[[VAL_9:.*]] = linalg.sparse_indices %[[VAL_1]], %[[VAL_4]] : tensor<32xf32> into memref +// CHECK: %[[VAL_10:.*]] = linalg.sparse_values %[[VAL_1]] : tensor<32xf32> into memref +// CHECK: %[[VAL_11:.*]] = tensor_to_memref %[[VAL_2]] : memref<32xf32> +// CHECK: %[[VAL_12:.*]] = alloc() : memref<32xf32> +// CHECK: linalg.copy(%[[VAL_11]], %[[VAL_12]]) : memref<32xf32>, memref<32xf32> +// CHECK: %[[VAL_13:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_4]]] : memref +// CHECK: %[[VAL_14:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_6]]] : memref +// CHECK: %[[VAL_15:.*]]:2 = scf.while (%[[VAL_16:.*]] = %[[VAL_13]], %[[VAL_17:.*]] = %[[VAL_4]]) : (index, index) -> (index, index) { // CHECK: %[[VAL_18:.*]] = cmpi ult, %[[VAL_16]], %[[VAL_14]] : index // CHECK: scf.condition(%[[VAL_18]]) %[[VAL_16]], %[[VAL_17]] : index, index // CHECK: } do { // CHECK: ^bb0(%[[VAL_19:.*]]: index, %[[VAL_20:.*]]: index): -// CHECK: %[[VAL_21:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_19]]] : memref +// CHECK: %[[VAL_21:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_19]]] : memref // CHECK: %[[VAL_22:.*]] = cmpi eq, %[[VAL_21]], %[[VAL_20]] : index // CHECK: scf.if %[[VAL_22]] { -// CHECK: %[[VAL_23:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_20]]] : memref<32xf32> -// CHECK: %[[VAL_24:.*]] = load %[[VAL_11]]{{\[}}%[[VAL_19]]] : memref +// CHECK: %[[VAL_23:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_20]]] : memref<32xf32> +// CHECK: %[[VAL_24:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_19]]] : memref // CHECK: %[[VAL_25:.*]] = addf %[[VAL_23]], %[[VAL_24]] : f32 // CHECK: store %[[VAL_25]], %[[VAL_12]]{{\[}}%[[VAL_20]]] : memref<32xf32> // CHECK: } else { -// CHECK: scf.if %[[VAL_6]] { -// CHECK: %[[VAL_26:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_20]]] : memref<32xf32> +// CHECK: scf.if %[[VAL_5]] { +// CHECK: %[[VAL_26:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_20]]] : memref<32xf32> // CHECK: store %[[VAL_26]], %[[VAL_12]]{{\[}}%[[VAL_20]]] : memref<32xf32> // CHECK: } else { // CHECK: } // CHECK: } // CHECK: %[[VAL_27:.*]] = cmpi eq, %[[VAL_21]], %[[VAL_20]] : index -// CHECK: %[[VAL_28:.*]] = addi %[[VAL_19]], %[[VAL_7]] : index +// CHECK: %[[VAL_28:.*]] = addi %[[VAL_19]], %[[VAL_6]] : index // CHECK: %[[VAL_29:.*]] = select %[[VAL_27]], %[[VAL_28]], %[[VAL_19]] : index -// CHECK: %[[VAL_30:.*]] = addi %[[VAL_20]], %[[VAL_7]] : index +// CHECK: %[[VAL_30:.*]] = addi %[[VAL_20]], %[[VAL_6]] : index // CHECK: scf.yield %[[VAL_29]], %[[VAL_30]] : index, index // CHECK: } -// CHECK: scf.for %[[VAL_31:.*]] = %[[VAL_32:.*]]#1 to %[[VAL_4]] step %[[VAL_7]] { -// CHECK: %[[VAL_33:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_31]]] : memref<32xf32> +// CHECK: scf.for %[[VAL_31:.*]] = %[[VAL_32:.*]]#1 to %[[VAL_3]] step %[[VAL_6]] { +// CHECK: %[[VAL_33:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_31]]] : memref<32xf32> // CHECK: store %[[VAL_33]], %[[VAL_12]]{{\[}}%[[VAL_31]]] : memref<32xf32> // CHECK: } // CHECK: %[[VAL_34:.*]] = tensor_load %[[VAL_12]] : memref<32xf32> @@ -363,20 +375,21 @@ // CHECK-SAME: %[[VAL_0:.*0]]: tensor<32xf32>, // CHECK-SAME: %[[VAL_1:.*1]]: tensor<32xf32>, // CHECK-SAME: %[[VAL_2:.*2]]: tensor<32xf32>) -> tensor<32xf32> { -// CHECK: %[[VAL_3:.*]] = constant 999 : index -// CHECK: %[[VAL_4:.*]] = constant 0 : index -// CHECK: %[[VAL_5:.*]] = constant 1 : index -// CHECK: %[[VAL_6:.*]] = alloca() : memref<32xf32> -// CHECK: %[[VAL_7:.*]] = alloca(%[[VAL_3]]) : memref -// CHECK: %[[VAL_8:.*]] = alloca(%[[VAL_3]]) : memref -// CHECK: %[[VAL_9:.*]] = alloca(%[[VAL_3]]) : memref -// CHECK: %[[VAL_10:.*]] = alloca() : memref<32xf32> -// CHECK: %[[VAL_11:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_4]]] : memref -// CHECK: %[[VAL_12:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_5]]] : memref -// CHECK: scf.for %[[VAL_13:.*]] = %[[VAL_11]] to %[[VAL_12]] step %[[VAL_5]] { -// CHECK: %[[VAL_14:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_13]]] : memref -// CHECK: %[[VAL_15:.*]] = load %[[VAL_6]]{{\[}}%[[VAL_14]]] : memref<32xf32> -// CHECK: %[[VAL_16:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_13]]] : memref +// CHECK: %[[VAL_3:.*]] = constant 0 : index +// CHECK: %[[VAL_4:.*]] = constant 1 : index +// CHECK: %[[VAL_5:.*]] = tensor_to_memref %[[VAL_0]] : memref<32xf32> +// CHECK: %[[VAL_6:.*]] = linalg.sparse_pointers %[[VAL_1]], %[[VAL_3]] : tensor<32xf32> into memref +// CHECK: %[[VAL_7:.*]] = linalg.sparse_indices %[[VAL_1]], %[[VAL_3]] : tensor<32xf32> into memref +// CHECK: %[[VAL_8:.*]] = linalg.sparse_values %[[VAL_1]] : tensor<32xf32> into memref +// CHECK: %[[VAL_9:.*]] = tensor_to_memref %[[VAL_2]] : memref<32xf32> +// CHECK: %[[VAL_10:.*]] = alloc() : memref<32xf32> +// CHECK: linalg.copy(%[[VAL_9]], %[[VAL_10]]) : memref<32xf32>, memref<32xf32> +// CHECK: %[[VAL_11:.*]] = load %[[VAL_6]]{{\[}}%[[VAL_3]]] : memref +// CHECK: %[[VAL_12:.*]] = load %[[VAL_6]]{{\[}}%[[VAL_4]]] : memref +// CHECK: scf.for %[[VAL_13:.*]] = %[[VAL_11]] to %[[VAL_12]] step %[[VAL_4]] { +// CHECK: %[[VAL_14:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_13]]] : memref +// CHECK: %[[VAL_15:.*]] = load %[[VAL_5]]{{\[}}%[[VAL_14]]] : memref<32xf32> +// CHECK: %[[VAL_16:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_13]]] : memref // CHECK: %[[VAL_17:.*]] = mulf %[[VAL_15]], %[[VAL_16]] : f32 // CHECK: store %[[VAL_17]], %[[VAL_10]]{{\[}}%[[VAL_14]]] : memref<32xf32> // CHECK: } @@ -413,45 +426,46 @@ // CHECK-SAME: %[[VAL_0:.*0]]: tensor<32xf32>, // CHECK-SAME: %[[VAL_1:.*1]]: tensor<32xf32>, // CHECK-SAME: %[[VAL_2:.*2]]: tensor<32xf32>) -> tensor<32xf32> { -// CHECK: %[[VAL_3:.*]] = constant 999 : index -// CHECK: %[[VAL_4:.*]] = constant 32 : index -// CHECK: %[[VAL_5:.*]] = constant 0 : index -// CHECK: %[[VAL_6:.*]] = constant true -// CHECK: %[[VAL_7:.*]] = constant 1 : index -// CHECK: %[[VAL_8:.*]] = alloca(%[[VAL_3]]) : memref -// CHECK: %[[VAL_9:.*]] = alloca(%[[VAL_3]]) : memref -// CHECK: %[[VAL_10:.*]] = alloca(%[[VAL_3]]) : memref -// CHECK: %[[VAL_11:.*]] = alloca() : memref<32xf32> -// CHECK: %[[VAL_12:.*]] = alloca() : memref<32xf32> -// CHECK: %[[VAL_13:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_5]]] : memref -// CHECK: %[[VAL_14:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_7]]] : memref -// CHECK: %[[VAL_15:.*]]:2 = scf.while (%[[VAL_16:.*]] = %[[VAL_13]], %[[VAL_17:.*]] = %[[VAL_5]]) : (index, index) -> (index, index) { +// CHECK: %[[VAL_3:.*]] = constant 32 : index +// CHECK: %[[VAL_4:.*]] = constant 0 : index +// CHECK: %[[VAL_5:.*]] = constant true +// CHECK: %[[VAL_6:.*]] = constant 1 : index +// CHECK: %[[VAL_7:.*]] = linalg.sparse_pointers %[[VAL_0]], %[[VAL_4]] : tensor<32xf32> into memref +// CHECK: %[[VAL_8:.*]] = linalg.sparse_indices %[[VAL_0]], %[[VAL_4]] : tensor<32xf32> into memref +// CHECK: %[[VAL_9:.*]] = linalg.sparse_values %[[VAL_0]] : tensor<32xf32> into memref +// CHECK: %[[VAL_10:.*]] = tensor_to_memref %[[VAL_1]] : memref<32xf32> +// CHECK: %[[VAL_11:.*]] = tensor_to_memref %[[VAL_2]] : memref<32xf32> +// CHECK: %[[VAL_12:.*]] = alloc() : memref<32xf32> +// CHECK: linalg.copy(%[[VAL_11]], %[[VAL_12]]) : memref<32xf32>, memref<32xf32> +// CHECK: %[[VAL_13:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_4]]] : memref +// CHECK: %[[VAL_14:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_6]]] : memref +// CHECK: %[[VAL_15:.*]]:2 = scf.while (%[[VAL_16:.*]] = %[[VAL_13]], %[[VAL_17:.*]] = %[[VAL_4]]) : (index, index) -> (index, index) { // CHECK: %[[VAL_18:.*]] = cmpi ult, %[[VAL_16]], %[[VAL_14]] : index // CHECK: scf.condition(%[[VAL_18]]) %[[VAL_16]], %[[VAL_17]] : index, index // CHECK: } do { // CHECK: ^bb0(%[[VAL_19:.*]]: index, %[[VAL_20:.*]]: index): -// CHECK: %[[VAL_21:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_19]]] : memref +// CHECK: %[[VAL_21:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_19]]] : memref // CHECK: %[[VAL_22:.*]] = cmpi eq, %[[VAL_21]], %[[VAL_20]] : index // CHECK: scf.if %[[VAL_22]] { -// CHECK: %[[VAL_23:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_19]]] : memref -// CHECK: %[[VAL_24:.*]] = load %[[VAL_11]]{{\[}}%[[VAL_20]]] : memref<32xf32> +// CHECK: %[[VAL_23:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_19]]] : memref +// CHECK: %[[VAL_24:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_20]]] : memref<32xf32> // CHECK: %[[VAL_25:.*]] = addf %[[VAL_23]], %[[VAL_24]] : f32 // CHECK: store %[[VAL_25]], %[[VAL_12]]{{\[}}%[[VAL_20]]] : memref<32xf32> // CHECK: } else { -// CHECK: scf.if %[[VAL_6]] { -// CHECK: %[[VAL_26:.*]] = load %[[VAL_11]]{{\[}}%[[VAL_20]]] : memref<32xf32> +// CHECK: scf.if %[[VAL_5]] { +// CHECK: %[[VAL_26:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_20]]] : memref<32xf32> // CHECK: store %[[VAL_26]], %[[VAL_12]]{{\[}}%[[VAL_20]]] : memref<32xf32> // CHECK: } else { // CHECK: } // CHECK: } // CHECK: %[[VAL_27:.*]] = cmpi eq, %[[VAL_21]], %[[VAL_20]] : index -// CHECK: %[[VAL_28:.*]] = addi %[[VAL_19]], %[[VAL_7]] : index +// CHECK: %[[VAL_28:.*]] = addi %[[VAL_19]], %[[VAL_6]] : index // CHECK: %[[VAL_29:.*]] = select %[[VAL_27]], %[[VAL_28]], %[[VAL_19]] : index -// CHECK: %[[VAL_30:.*]] = addi %[[VAL_20]], %[[VAL_7]] : index +// CHECK: %[[VAL_30:.*]] = addi %[[VAL_20]], %[[VAL_6]] : index // CHECK: scf.yield %[[VAL_29]], %[[VAL_30]] : index, index // CHECK: } -// CHECK: scf.for %[[VAL_31:.*]] = %[[VAL_32:.*]]#1 to %[[VAL_4]] step %[[VAL_7]] { -// CHECK: %[[VAL_33:.*]] = load %[[VAL_11]]{{\[}}%[[VAL_31]]] : memref<32xf32> +// CHECK: scf.for %[[VAL_31:.*]] = %[[VAL_32:.*]]#1 to %[[VAL_3]] step %[[VAL_6]] { +// CHECK: %[[VAL_33:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_31]]] : memref<32xf32> // CHECK: store %[[VAL_33]], %[[VAL_12]]{{\[}}%[[VAL_31]]] : memref<32xf32> // CHECK: } // CHECK: %[[VAL_34:.*]] = tensor_load %[[VAL_12]] : memref<32xf32> @@ -472,20 +486,21 @@ // CHECK-SAME: %[[VAL_0:.*0]]: tensor<32xf32>, // CHECK-SAME: %[[VAL_1:.*1]]: tensor<32xf32>, // CHECK-SAME: %[[VAL_2:.*2]]: tensor<32xf32>) -> tensor<32xf32> { -// CHECK: %[[VAL_3:.*]] = constant 999 : index -// CHECK: %[[VAL_4:.*]] = constant 0 : index -// CHECK: %[[VAL_5:.*]] = constant 1 : index -// CHECK: %[[VAL_6:.*]] = alloca(%[[VAL_3]]) : memref -// CHECK: %[[VAL_7:.*]] = alloca(%[[VAL_3]]) : memref -// CHECK: %[[VAL_8:.*]] = alloca(%[[VAL_3]]) : memref -// CHECK: %[[VAL_9:.*]] = alloca() : memref<32xf32> -// CHECK: %[[VAL_10:.*]] = alloca() : memref<32xf32> -// CHECK: %[[VAL_11:.*]] = load %[[VAL_6]]{{\[}}%[[VAL_4]]] : memref -// CHECK: %[[VAL_12:.*]] = load %[[VAL_6]]{{\[}}%[[VAL_5]]] : memref -// CHECK: scf.for %[[VAL_13:.*]] = %[[VAL_11]] to %[[VAL_12]] step %[[VAL_5]] { -// CHECK: %[[VAL_14:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_13]]] : memref -// CHECK: %[[VAL_15:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_13]]] : memref -// CHECK: %[[VAL_16:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_14]]] : memref<32xf32> +// CHECK: %[[VAL_3:.*]] = constant 0 : index +// CHECK: %[[VAL_4:.*]] = constant 1 : index +// CHECK: %[[VAL_5:.*]] = linalg.sparse_pointers %[[VAL_0]], %[[VAL_3]] : tensor<32xf32> into memref +// CHECK: %[[VAL_6:.*]] = linalg.sparse_indices %[[VAL_0]], %[[VAL_3]] : tensor<32xf32> into memref +// CHECK: %[[VAL_7:.*]] = linalg.sparse_values %[[VAL_0]] : tensor<32xf32> into memref +// CHECK: %[[VAL_8:.*]] = tensor_to_memref %[[VAL_1]] : memref<32xf32> +// CHECK: %[[VAL_9:.*]] = tensor_to_memref %[[VAL_2]] : memref<32xf32> +// CHECK: %[[VAL_10:.*]] = alloc() : memref<32xf32> +// CHECK: linalg.copy(%[[VAL_9]], %[[VAL_10]]) : memref<32xf32>, memref<32xf32> +// CHECK: %[[VAL_11:.*]] = load %[[VAL_5]]{{\[}}%[[VAL_3]]] : memref +// CHECK: %[[VAL_12:.*]] = load %[[VAL_5]]{{\[}}%[[VAL_4]]] : memref +// CHECK: scf.for %[[VAL_13:.*]] = %[[VAL_11]] to %[[VAL_12]] step %[[VAL_4]] { +// CHECK: %[[VAL_14:.*]] = load %[[VAL_6]]{{\[}}%[[VAL_13]]] : memref +// CHECK: %[[VAL_15:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_13]]] : memref +// CHECK: %[[VAL_16:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_14]]] : memref<32xf32> // CHECK: %[[VAL_17:.*]] = mulf %[[VAL_15]], %[[VAL_16]] : f32 // CHECK: store %[[VAL_17]], %[[VAL_10]]{{\[}}%[[VAL_14]]] : memref<32xf32> // CHECK: } @@ -522,20 +537,21 @@ // CHECK-SAME: %[[VAL_0:.*0]]: tensor<32xf32>, // CHECK-SAME: %[[VAL_1:.*1]]: tensor<32xf32>, // CHECK-SAME: %[[VAL_2:.*2]]: tensor<32xf32>) -> tensor<32xf32> { -// CHECK: %[[VAL_3:.*]] = constant 999 : index -// CHECK: %[[VAL_4:.*]] = constant 0 : index -// CHECK: %[[VAL_5:.*]] = constant 1 : index -// CHECK: %[[VAL_6:.*]] = alloca(%[[VAL_3]]) : memref -// CHECK: %[[VAL_7:.*]] = alloca(%[[VAL_3]]) : memref -// CHECK: %[[VAL_8:.*]] = alloca(%[[VAL_3]]) : memref -// CHECK: %[[VAL_9:.*]] = alloca(%[[VAL_3]]) : memref -// CHECK: %[[VAL_10:.*]] = alloca(%[[VAL_3]]) : memref -// CHECK: %[[VAL_11:.*]] = alloca(%[[VAL_3]]) : memref -// CHECK: %[[VAL_12:.*]] = alloca() : memref<32xf32> -// CHECK: %[[VAL_13:.*]] = load %[[VAL_6]]{{\[}}%[[VAL_4]]] : memref -// CHECK: %[[VAL_14:.*]] = load %[[VAL_6]]{{\[}}%[[VAL_5]]] : memref -// CHECK: %[[VAL_15:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_4]]] : memref -// CHECK: %[[VAL_16:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_5]]] : memref +// CHECK: %[[VAL_3:.*]] = constant 0 : index +// CHECK: %[[VAL_4:.*]] = constant 1 : index +// CHECK: %[[VAL_5:.*]] = linalg.sparse_pointers %[[VAL_0]], %[[VAL_3]] : tensor<32xf32> into memref +// CHECK: %[[VAL_6:.*]] = linalg.sparse_indices %[[VAL_0]], %[[VAL_3]] : tensor<32xf32> into memref +// CHECK: %[[VAL_7:.*]] = linalg.sparse_values %[[VAL_0]] : tensor<32xf32> into memref +// CHECK: %[[VAL_8:.*]] = linalg.sparse_pointers %[[VAL_1]], %[[VAL_3]] : tensor<32xf32> into memref +// CHECK: %[[VAL_9:.*]] = linalg.sparse_indices %[[VAL_1]], %[[VAL_3]] : tensor<32xf32> into memref +// CHECK: %[[VAL_10:.*]] = linalg.sparse_values %[[VAL_1]] : tensor<32xf32> into memref +// CHECK: %[[VAL_11:.*]] = tensor_to_memref %[[VAL_2]] : memref<32xf32> +// CHECK: %[[VAL_12:.*]] = alloc() : memref<32xf32> +// CHECK: linalg.copy(%[[VAL_11]], %[[VAL_12]]) : memref<32xf32>, memref<32xf32> +// CHECK: %[[VAL_13:.*]] = load %[[VAL_5]]{{\[}}%[[VAL_3]]] : memref +// CHECK: %[[VAL_14:.*]] = load %[[VAL_5]]{{\[}}%[[VAL_4]]] : memref +// CHECK: %[[VAL_15:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_3]]] : memref +// CHECK: %[[VAL_16:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_4]]] : memref // CHECK: %[[VAL_17:.*]]:2 = scf.while (%[[VAL_18:.*]] = %[[VAL_13]], %[[VAL_19:.*]] = %[[VAL_15]]) : (index, index) -> (index, index) { // CHECK: %[[VAL_20:.*]] = cmpi ult, %[[VAL_18]], %[[VAL_14]] : index // CHECK: %[[VAL_21:.*]] = cmpi ult, %[[VAL_19]], %[[VAL_16]] : index @@ -543,48 +559,48 @@ // CHECK: scf.condition(%[[VAL_22]]) %[[VAL_18]], %[[VAL_19]] : index, index // CHECK: } do { // CHECK: ^bb0(%[[VAL_23:.*]]: index, %[[VAL_24:.*]]: index): -// CHECK: %[[VAL_25:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_23]]] : memref -// CHECK: %[[VAL_26:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_24]]] : memref +// CHECK: %[[VAL_25:.*]] = load %[[VAL_6]]{{\[}}%[[VAL_23]]] : memref +// CHECK: %[[VAL_26:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_24]]] : memref // CHECK: %[[VAL_27:.*]] = cmpi ult, %[[VAL_26]], %[[VAL_25]] : index // CHECK: %[[VAL_28:.*]] = select %[[VAL_27]], %[[VAL_26]], %[[VAL_25]] : index // CHECK: %[[VAL_29:.*]] = cmpi eq, %[[VAL_25]], %[[VAL_28]] : index // CHECK: %[[VAL_30:.*]] = cmpi eq, %[[VAL_26]], %[[VAL_28]] : index // CHECK: %[[VAL_31:.*]] = and %[[VAL_29]], %[[VAL_30]] : i1 // CHECK: scf.if %[[VAL_31]] { -// CHECK: %[[VAL_32:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_23]]] : memref -// CHECK: %[[VAL_33:.*]] = load %[[VAL_11]]{{\[}}%[[VAL_24]]] : memref +// CHECK: %[[VAL_32:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_23]]] : memref +// CHECK: %[[VAL_33:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_24]]] : memref // CHECK: %[[VAL_34:.*]] = addf %[[VAL_32]], %[[VAL_33]] : f32 // CHECK: store %[[VAL_34]], %[[VAL_12]]{{\[}}%[[VAL_28]]] : memref<32xf32> // CHECK: } else { // CHECK: %[[VAL_35:.*]] = cmpi eq, %[[VAL_25]], %[[VAL_28]] : index // CHECK: scf.if %[[VAL_35]] { -// CHECK: %[[VAL_36:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_23]]] : memref +// CHECK: %[[VAL_36:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_23]]] : memref // CHECK: store %[[VAL_36]], %[[VAL_12]]{{\[}}%[[VAL_28]]] : memref<32xf32> // CHECK: } else { // CHECK: %[[VAL_37:.*]] = cmpi eq, %[[VAL_26]], %[[VAL_28]] : index // CHECK: scf.if %[[VAL_37]] { -// CHECK: %[[VAL_38:.*]] = load %[[VAL_11]]{{\[}}%[[VAL_24]]] : memref +// CHECK: %[[VAL_38:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_24]]] : memref // CHECK: store %[[VAL_38]], %[[VAL_12]]{{\[}}%[[VAL_28]]] : memref<32xf32> // CHECK: } else { // CHECK: } // CHECK: } // CHECK: } // CHECK: %[[VAL_39:.*]] = cmpi eq, %[[VAL_25]], %[[VAL_28]] : index -// CHECK: %[[VAL_40:.*]] = addi %[[VAL_23]], %[[VAL_5]] : index +// CHECK: %[[VAL_40:.*]] = addi %[[VAL_23]], %[[VAL_4]] : index // CHECK: %[[VAL_41:.*]] = select %[[VAL_39]], %[[VAL_40]], %[[VAL_23]] : index // CHECK: %[[VAL_42:.*]] = cmpi eq, %[[VAL_26]], %[[VAL_28]] : index -// CHECK: %[[VAL_43:.*]] = addi %[[VAL_24]], %[[VAL_5]] : index +// CHECK: %[[VAL_43:.*]] = addi %[[VAL_24]], %[[VAL_4]] : index // CHECK: %[[VAL_44:.*]] = select %[[VAL_42]], %[[VAL_43]], %[[VAL_24]] : index // CHECK: scf.yield %[[VAL_41]], %[[VAL_44]] : index, index // CHECK: } -// CHECK: scf.for %[[VAL_45:.*]] = %[[VAL_46:.*]]#0 to %[[VAL_14]] step %[[VAL_5]] { -// CHECK: %[[VAL_47:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_45]]] : memref -// CHECK: %[[VAL_48:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_45]]] : memref +// CHECK: scf.for %[[VAL_45:.*]] = %[[VAL_46:.*]]#0 to %[[VAL_14]] step %[[VAL_4]] { +// CHECK: %[[VAL_47:.*]] = load %[[VAL_6]]{{\[}}%[[VAL_45]]] : memref +// CHECK: %[[VAL_48:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_45]]] : memref // CHECK: store %[[VAL_48]], %[[VAL_12]]{{\[}}%[[VAL_47]]] : memref<32xf32> // CHECK: } -// CHECK: scf.for %[[VAL_49:.*]] = %[[VAL_50:.*]]#1 to %[[VAL_16]] step %[[VAL_5]] { -// CHECK: %[[VAL_51:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_49]]] : memref -// CHECK: %[[VAL_52:.*]] = load %[[VAL_11]]{{\[}}%[[VAL_49]]] : memref +// CHECK: scf.for %[[VAL_49:.*]] = %[[VAL_50:.*]]#1 to %[[VAL_16]] step %[[VAL_4]] { +// CHECK: %[[VAL_51:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_49]]] : memref +// CHECK: %[[VAL_52:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_49]]] : memref // CHECK: store %[[VAL_52]], %[[VAL_12]]{{\[}}%[[VAL_51]]] : memref<32xf32> // CHECK: } // CHECK: %[[VAL_53:.*]] = tensor_load %[[VAL_12]] : memref<32xf32> @@ -605,20 +621,21 @@ // CHECK-SAME: %[[VAL_0:.*0]]: tensor<32xf32>, // CHECK-SAME: %[[VAL_1:.*1]]: tensor<32xf32>, // CHECK-SAME: %[[VAL_2:.*2]]: tensor<32xf32>) -> tensor<32xf32> { -// CHECK: %[[VAL_3:.*]] = constant 999 : index -// CHECK: %[[VAL_4:.*]] = constant 0 : index -// CHECK: %[[VAL_5:.*]] = constant 1 : index -// CHECK: %[[VAL_6:.*]] = alloca(%[[VAL_3]]) : memref -// CHECK: %[[VAL_7:.*]] = alloca(%[[VAL_3]]) : memref -// CHECK: %[[VAL_8:.*]] = alloca(%[[VAL_3]]) : memref -// CHECK: %[[VAL_9:.*]] = alloca(%[[VAL_3]]) : memref -// CHECK: %[[VAL_10:.*]] = alloca(%[[VAL_3]]) : memref -// CHECK: %[[VAL_11:.*]] = alloca(%[[VAL_3]]) : memref -// CHECK: %[[VAL_12:.*]] = alloca() : memref<32xf32> -// CHECK: %[[VAL_13:.*]] = load %[[VAL_6]]{{\[}}%[[VAL_4]]] : memref -// CHECK: %[[VAL_14:.*]] = load %[[VAL_6]]{{\[}}%[[VAL_5]]] : memref -// CHECK: %[[VAL_15:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_4]]] : memref -// CHECK: %[[VAL_16:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_5]]] : memref +// CHECK: %[[VAL_3:.*]] = constant 0 : index +// CHECK: %[[VAL_4:.*]] = constant 1 : index +// CHECK: %[[VAL_5:.*]] = linalg.sparse_pointers %[[VAL_0]], %[[VAL_3]] : tensor<32xf32> into memref +// CHECK: %[[VAL_6:.*]] = linalg.sparse_indices %[[VAL_0]], %[[VAL_3]] : tensor<32xf32> into memref +// CHECK: %[[VAL_7:.*]] = linalg.sparse_values %[[VAL_0]] : tensor<32xf32> into memref +// CHECK: %[[VAL_8:.*]] = linalg.sparse_pointers %[[VAL_1]], %[[VAL_3]] : tensor<32xf32> into memref +// CHECK: %[[VAL_9:.*]] = linalg.sparse_indices %[[VAL_1]], %[[VAL_3]] : tensor<32xf32> into memref +// CHECK: %[[VAL_10:.*]] = linalg.sparse_values %[[VAL_1]] : tensor<32xf32> into memref +// CHECK: %[[VAL_11:.*]] = tensor_to_memref %[[VAL_2]] : memref<32xf32> +// CHECK: %[[VAL_12:.*]] = alloc() : memref<32xf32> +// CHECK: linalg.copy(%[[VAL_11]], %[[VAL_12]]) : memref<32xf32>, memref<32xf32> +// CHECK: %[[VAL_13:.*]] = load %[[VAL_5]]{{\[}}%[[VAL_3]]] : memref +// CHECK: %[[VAL_14:.*]] = load %[[VAL_5]]{{\[}}%[[VAL_4]]] : memref +// CHECK: %[[VAL_15:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_3]]] : memref +// CHECK: %[[VAL_16:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_4]]] : memref // CHECK: %[[VAL_17:.*]]:2 = scf.while (%[[VAL_18:.*]] = %[[VAL_13]], %[[VAL_19:.*]] = %[[VAL_15]]) : (index, index) -> (index, index) { // CHECK: %[[VAL_20:.*]] = cmpi ult, %[[VAL_18]], %[[VAL_14]] : index // CHECK: %[[VAL_21:.*]] = cmpi ult, %[[VAL_19]], %[[VAL_16]] : index @@ -626,25 +643,25 @@ // CHECK: scf.condition(%[[VAL_22]]) %[[VAL_18]], %[[VAL_19]] : index, index // CHECK: } do { // CHECK: ^bb0(%[[VAL_23:.*]]: index, %[[VAL_24:.*]]: index): -// CHECK: %[[VAL_25:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_23]]] : memref -// CHECK: %[[VAL_26:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_24]]] : memref +// CHECK: %[[VAL_25:.*]] = load %[[VAL_6]]{{\[}}%[[VAL_23]]] : memref +// CHECK: %[[VAL_26:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_24]]] : memref // CHECK: %[[VAL_27:.*]] = cmpi ult, %[[VAL_26]], %[[VAL_25]] : index // CHECK: %[[VAL_28:.*]] = select %[[VAL_27]], %[[VAL_26]], %[[VAL_25]] : index // CHECK: %[[VAL_29:.*]] = cmpi eq, %[[VAL_25]], %[[VAL_28]] : index // CHECK: %[[VAL_30:.*]] = cmpi eq, %[[VAL_26]], %[[VAL_28]] : index // CHECK: %[[VAL_31:.*]] = and %[[VAL_29]], %[[VAL_30]] : i1 // CHECK: scf.if %[[VAL_31]] { -// CHECK: %[[VAL_32:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_23]]] : memref -// CHECK: %[[VAL_33:.*]] = load %[[VAL_11]]{{\[}}%[[VAL_24]]] : memref +// CHECK: %[[VAL_32:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_23]]] : memref +// CHECK: %[[VAL_33:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_24]]] : memref // CHECK: %[[VAL_34:.*]] = mulf %[[VAL_32]], %[[VAL_33]] : f32 // CHECK: store %[[VAL_34]], %[[VAL_12]]{{\[}}%[[VAL_28]]] : memref<32xf32> // CHECK: } else { // CHECK: } // CHECK: %[[VAL_35:.*]] = cmpi eq, %[[VAL_25]], %[[VAL_28]] : index -// CHECK: %[[VAL_36:.*]] = addi %[[VAL_23]], %[[VAL_5]] : index +// CHECK: %[[VAL_36:.*]] = addi %[[VAL_23]], %[[VAL_4]] : index // CHECK: %[[VAL_37:.*]] = select %[[VAL_35]], %[[VAL_36]], %[[VAL_23]] : index // CHECK: %[[VAL_38:.*]] = cmpi eq, %[[VAL_26]], %[[VAL_28]] : index -// CHECK: %[[VAL_39:.*]] = addi %[[VAL_24]], %[[VAL_5]] : index +// CHECK: %[[VAL_39:.*]] = addi %[[VAL_24]], %[[VAL_4]] : index // CHECK: %[[VAL_40:.*]] = select %[[VAL_38]], %[[VAL_39]], %[[VAL_24]] : index // CHECK: scf.yield %[[VAL_37]], %[[VAL_40]] : index, index // CHECK: } @@ -682,49 +699,50 @@ // CHECK-SAME: %[[VAL_1:.*1]]: tensor<16xf32>, // CHECK-SAME: %[[VAL_2:.*2]]: f32, // CHECK-SAME: %[[VAL_3:.*3]]: tensor<16xf32>) -> tensor<16xf32> { -// CHECK: %[[VAL_4:.*]] = constant 999 : index -// CHECK: %[[VAL_5:.*]] = constant 0 : index -// CHECK: %[[VAL_6:.*]] = constant 1 : index -// CHECK: %[[VAL_7:.*]] = alloca(%[[VAL_4]]) : memref -// CHECK: %[[VAL_8:.*]] = alloca(%[[VAL_4]]) : memref -// CHECK: %[[VAL_9:.*]] = alloca(%[[VAL_4]]) : memref -// CHECK: %[[VAL_10:.*]] = alloca(%[[VAL_4]]) : memref -// CHECK: %[[VAL_11:.*]] = alloca(%[[VAL_4]]) : memref -// CHECK: %[[VAL_12:.*]] = alloca(%[[VAL_4]]) : memref -// CHECK: %[[VAL_13:.*]] = alloca() : memref<16xf32> -// CHECK: %[[VAL_14:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_5]]] : memref -// CHECK: %[[VAL_15:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_6]]] : memref -// CHECK: %[[VAL_16:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_5]]] : memref -// CHECK: %[[VAL_17:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_6]]] : memref -// CHECK: %[[VAL_18:.*]]:3 = scf.while (%[[VAL_19:.*]] = %[[VAL_14]], %[[VAL_20:.*]] = %[[VAL_16]], %[[VAL_21:.*]] = %[[VAL_5]]) : (index, index, index) -> (index, index, index) { +// CHECK: %[[VAL_4:.*]] = constant 0 : index +// CHECK: %[[VAL_5:.*]] = constant 1 : index +// CHECK: %[[VAL_6:.*]] = linalg.sparse_pointers %[[VAL_0]], %[[VAL_4]] : tensor<16xf32> into memref +// CHECK: %[[VAL_7:.*]] = linalg.sparse_indices %[[VAL_0]], %[[VAL_4]] : tensor<16xf32> into memref +// CHECK: %[[VAL_8:.*]] = linalg.sparse_values %[[VAL_0]] : tensor<16xf32> into memref +// CHECK: %[[VAL_9:.*]] = linalg.sparse_pointers %[[VAL_1]], %[[VAL_4]] : tensor<16xf32> into memref +// CHECK: %[[VAL_10:.*]] = linalg.sparse_indices %[[VAL_1]], %[[VAL_4]] : tensor<16xf32> into memref +// CHECK: %[[VAL_11:.*]] = linalg.sparse_values %[[VAL_1]] : tensor<16xf32> into memref +// CHECK: %[[VAL_12:.*]] = tensor_to_memref %[[VAL_3]] : memref<16xf32> +// CHECK: %[[VAL_13:.*]] = alloc() : memref<16xf32> +// CHECK: linalg.copy(%[[VAL_12]], %[[VAL_13]]) : memref<16xf32>, memref<16xf32> +// CHECK: %[[VAL_14:.*]] = load %[[VAL_6]]{{\[}}%[[VAL_4]]] : memref +// CHECK: %[[VAL_15:.*]] = load %[[VAL_6]]{{\[}}%[[VAL_5]]] : memref +// CHECK: %[[VAL_16:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_4]]] : memref +// CHECK: %[[VAL_17:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_5]]] : memref +// CHECK: %[[VAL_18:.*]]:3 = scf.while (%[[VAL_19:.*]] = %[[VAL_14]], %[[VAL_20:.*]] = %[[VAL_16]], %[[VAL_21:.*]] = %[[VAL_4]]) : (index, index, index) -> (index, index, index) { // CHECK: %[[VAL_22:.*]] = cmpi ult, %[[VAL_19]], %[[VAL_15]] : index // CHECK: %[[VAL_23:.*]] = cmpi ult, %[[VAL_20]], %[[VAL_17]] : index // CHECK: %[[VAL_24:.*]] = and %[[VAL_22]], %[[VAL_23]] : i1 // CHECK: scf.condition(%[[VAL_24]]) %[[VAL_19]], %[[VAL_20]], %[[VAL_21]] : index, index, index // CHECK: } do { // CHECK: ^bb0(%[[VAL_25:.*]]: index, %[[VAL_26:.*]]: index, %[[VAL_27:.*]]: index): -// CHECK: %[[VAL_28:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_25]]] : memref -// CHECK: %[[VAL_29:.*]] = load %[[VAL_11]]{{\[}}%[[VAL_26]]] : memref +// CHECK: %[[VAL_28:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_25]]] : memref +// CHECK: %[[VAL_29:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_26]]] : memref // CHECK: %[[VAL_30:.*]] = cmpi eq, %[[VAL_28]], %[[VAL_27]] : index // CHECK: %[[VAL_31:.*]] = cmpi eq, %[[VAL_29]], %[[VAL_27]] : index // CHECK: %[[VAL_32:.*]] = and %[[VAL_30]], %[[VAL_31]] : i1 // CHECK: scf.if %[[VAL_32]] { -// CHECK: %[[VAL_33:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_25]]] : memref +// CHECK: %[[VAL_33:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_25]]] : memref // CHECK: %[[VAL_34:.*]] = mulf %[[VAL_33]], %[[VAL_2]] : f32 -// CHECK: %[[VAL_35:.*]] = load %[[VAL_12]]{{\[}}%[[VAL_26]]] : memref +// CHECK: %[[VAL_35:.*]] = load %[[VAL_11]]{{\[}}%[[VAL_26]]] : memref // CHECK: %[[VAL_36:.*]] = mulf %[[VAL_35]], %[[VAL_2]] : f32 // CHECK: %[[VAL_37:.*]] = addf %[[VAL_34]], %[[VAL_36]] : f32 // CHECK: store %[[VAL_37]], %[[VAL_13]]{{\[}}%[[VAL_27]]] : memref<16xf32> // CHECK: } else { // CHECK: %[[VAL_38:.*]] = cmpi eq, %[[VAL_28]], %[[VAL_27]] : index // CHECK: scf.if %[[VAL_38]] { -// CHECK: %[[VAL_39:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_25]]] : memref +// CHECK: %[[VAL_39:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_25]]] : memref // CHECK: %[[VAL_40:.*]] = mulf %[[VAL_39]], %[[VAL_2]] : f32 // CHECK: store %[[VAL_40]], %[[VAL_13]]{{\[}}%[[VAL_27]]] : memref<16xf32> // CHECK: } else { // CHECK: %[[VAL_41:.*]] = cmpi eq, %[[VAL_29]], %[[VAL_27]] : index // CHECK: scf.if %[[VAL_41]] { -// CHECK: %[[VAL_42:.*]] = load %[[VAL_12]]{{\[}}%[[VAL_26]]] : memref +// CHECK: %[[VAL_42:.*]] = load %[[VAL_11]]{{\[}}%[[VAL_26]]] : memref // CHECK: %[[VAL_43:.*]] = mulf %[[VAL_42]], %[[VAL_2]] : f32 // CHECK: store %[[VAL_43]], %[[VAL_13]]{{\[}}%[[VAL_27]]] : memref<16xf32> // CHECK: } else { @@ -732,22 +750,22 @@ // CHECK: } // CHECK: } // CHECK: %[[VAL_44:.*]] = cmpi eq, %[[VAL_28]], %[[VAL_27]] : index -// CHECK: %[[VAL_45:.*]] = addi %[[VAL_25]], %[[VAL_6]] : index +// CHECK: %[[VAL_45:.*]] = addi %[[VAL_25]], %[[VAL_5]] : index // CHECK: %[[VAL_46:.*]] = select %[[VAL_44]], %[[VAL_45]], %[[VAL_25]] : index // CHECK: %[[VAL_47:.*]] = cmpi eq, %[[VAL_29]], %[[VAL_27]] : index -// CHECK: %[[VAL_48:.*]] = addi %[[VAL_26]], %[[VAL_6]] : index +// CHECK: %[[VAL_48:.*]] = addi %[[VAL_26]], %[[VAL_5]] : index // CHECK: %[[VAL_49:.*]] = select %[[VAL_47]], %[[VAL_48]], %[[VAL_26]] : index -// CHECK: %[[VAL_50:.*]] = addi %[[VAL_27]], %[[VAL_6]] : index +// CHECK: %[[VAL_50:.*]] = addi %[[VAL_27]], %[[VAL_5]] : index // CHECK: scf.yield %[[VAL_46]], %[[VAL_49]], %[[VAL_50]] : index, index, index // CHECK: } -// CHECK: scf.for %[[VAL_51:.*]] = %[[VAL_52:.*]]#0 to %[[VAL_15]] step %[[VAL_6]] { -// CHECK: %[[VAL_53:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_51]]] : memref +// CHECK: scf.for %[[VAL_51:.*]] = %[[VAL_52:.*]]#0 to %[[VAL_15]] step %[[VAL_5]] { +// CHECK: %[[VAL_53:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_51]]] : memref // CHECK: %[[VAL_54:.*]] = mulf %[[VAL_53]], %[[VAL_2]] : f32 // CHECK: store %[[VAL_54]], %[[VAL_13]]{{\[}}%[[VAL_52]]#2] : memref<16xf32> // CHECK: } -// CHECK: scf.for %[[VAL_55:.*]] = %[[VAL_56:.*]]#1 to %[[VAL_17]] step %[[VAL_6]] { -// CHECK: %[[VAL_57:.*]] = load %[[VAL_11]]{{\[}}%[[VAL_55]]] : memref -// CHECK: %[[VAL_58:.*]] = load %[[VAL_12]]{{\[}}%[[VAL_55]]] : memref +// CHECK: scf.for %[[VAL_55:.*]] = %[[VAL_56:.*]]#1 to %[[VAL_17]] step %[[VAL_5]] { +// CHECK: %[[VAL_57:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_55]]] : memref +// CHECK: %[[VAL_58:.*]] = load %[[VAL_11]]{{\[}}%[[VAL_55]]] : memref // CHECK: %[[VAL_59:.*]] = mulf %[[VAL_58]], %[[VAL_2]] : f32 // CHECK: store %[[VAL_59]], %[[VAL_13]]{{\[}}%[[VAL_57]]] : memref<16xf32> // CHECK: } @@ -772,48 +790,49 @@ // CHECK-SAME: %[[VAL_1:.*1]]: tensor<16xf32>, // CHECK-SAME: %[[VAL_2:.*2]]: f32, // CHECK-SAME: %[[VAL_3:.*3]]: tensor<16xf32>) -> tensor<16xf32> { -// CHECK: %[[VAL_4:.*]] = constant 999 : index -// CHECK: %[[VAL_5:.*]] = constant 0 : index -// CHECK: %[[VAL_6:.*]] = constant 1 : index -// CHECK: %[[VAL_7:.*]] = alloca(%[[VAL_4]]) : memref -// CHECK: %[[VAL_8:.*]] = alloca(%[[VAL_4]]) : memref -// CHECK: %[[VAL_9:.*]] = alloca(%[[VAL_4]]) : memref -// CHECK: %[[VAL_10:.*]] = alloca(%[[VAL_4]]) : memref -// CHECK: %[[VAL_11:.*]] = alloca(%[[VAL_4]]) : memref -// CHECK: %[[VAL_12:.*]] = alloca(%[[VAL_4]]) : memref -// CHECK: %[[VAL_13:.*]] = alloca() : memref<16xf32> -// CHECK: %[[VAL_14:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_5]]] : memref -// CHECK: %[[VAL_15:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_6]]] : memref -// CHECK: %[[VAL_16:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_5]]] : memref -// CHECK: %[[VAL_17:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_6]]] : memref -// CHECK: %[[VAL_18:.*]]:3 = scf.while (%[[VAL_19:.*]] = %[[VAL_14]], %[[VAL_20:.*]] = %[[VAL_16]], %[[VAL_21:.*]] = %[[VAL_5]]) : (index, index, index) -> (index, index, index) { +// CHECK: %[[VAL_4:.*]] = constant 0 : index +// CHECK: %[[VAL_5:.*]] = constant 1 : index +// CHECK: %[[VAL_6:.*]] = linalg.sparse_pointers %[[VAL_0]], %[[VAL_4]] : tensor<16xf32> into memref +// CHECK: %[[VAL_7:.*]] = linalg.sparse_indices %[[VAL_0]], %[[VAL_4]] : tensor<16xf32> into memref +// CHECK: %[[VAL_8:.*]] = linalg.sparse_values %[[VAL_0]] : tensor<16xf32> into memref +// CHECK: %[[VAL_9:.*]] = linalg.sparse_pointers %[[VAL_1]], %[[VAL_4]] : tensor<16xf32> into memref +// CHECK: %[[VAL_10:.*]] = linalg.sparse_indices %[[VAL_1]], %[[VAL_4]] : tensor<16xf32> into memref +// CHECK: %[[VAL_11:.*]] = linalg.sparse_values %[[VAL_1]] : tensor<16xf32> into memref +// CHECK: %[[VAL_12:.*]] = tensor_to_memref %[[VAL_3]] : memref<16xf32> +// CHECK: %[[VAL_13:.*]] = alloc() : memref<16xf32> +// CHECK: linalg.copy(%[[VAL_12]], %[[VAL_13]]) : memref<16xf32>, memref<16xf32> +// CHECK: %[[VAL_14:.*]] = load %[[VAL_6]]{{\[}}%[[VAL_4]]] : memref +// CHECK: %[[VAL_15:.*]] = load %[[VAL_6]]{{\[}}%[[VAL_5]]] : memref +// CHECK: %[[VAL_16:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_4]]] : memref +// CHECK: %[[VAL_17:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_5]]] : memref +// CHECK: %[[VAL_18:.*]]:3 = scf.while (%[[VAL_19:.*]] = %[[VAL_14]], %[[VAL_20:.*]] = %[[VAL_16]], %[[VAL_21:.*]] = %[[VAL_4]]) : (index, index, index) -> (index, index, index) { // CHECK: %[[VAL_22:.*]] = cmpi ult, %[[VAL_19]], %[[VAL_15]] : index // CHECK: %[[VAL_23:.*]] = cmpi ult, %[[VAL_20]], %[[VAL_17]] : index // CHECK: %[[VAL_24:.*]] = and %[[VAL_22]], %[[VAL_23]] : i1 // CHECK: scf.condition(%[[VAL_24]]) %[[VAL_19]], %[[VAL_20]], %[[VAL_21]] : index, index, index // CHECK: } do { // CHECK: ^bb0(%[[VAL_25:.*]]: index, %[[VAL_26:.*]]: index, %[[VAL_27:.*]]: index): -// CHECK: %[[VAL_28:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_25]]] : memref -// CHECK: %[[VAL_29:.*]] = load %[[VAL_11]]{{\[}}%[[VAL_26]]] : memref +// CHECK: %[[VAL_28:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_25]]] : memref +// CHECK: %[[VAL_29:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_26]]] : memref // CHECK: %[[VAL_30:.*]] = cmpi eq, %[[VAL_28]], %[[VAL_27]] : index // CHECK: %[[VAL_31:.*]] = cmpi eq, %[[VAL_29]], %[[VAL_27]] : index // CHECK: %[[VAL_32:.*]] = and %[[VAL_30]], %[[VAL_31]] : i1 // CHECK: scf.if %[[VAL_32]] { -// CHECK: %[[VAL_33:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_25]]] : memref -// CHECK: %[[VAL_34:.*]] = load %[[VAL_12]]{{\[}}%[[VAL_26]]] : memref +// CHECK: %[[VAL_33:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_25]]] : memref +// CHECK: %[[VAL_34:.*]] = load %[[VAL_11]]{{\[}}%[[VAL_26]]] : memref // CHECK: %[[VAL_35:.*]] = addf %[[VAL_33]], %[[VAL_34]] : f32 // CHECK: %[[VAL_36:.*]] = mulf %[[VAL_35]], %[[VAL_2]] : f32 // CHECK: store %[[VAL_36]], %[[VAL_13]]{{\[}}%[[VAL_27]]] : memref<16xf32> // CHECK: } else { // CHECK: %[[VAL_37:.*]] = cmpi eq, %[[VAL_28]], %[[VAL_27]] : index // CHECK: scf.if %[[VAL_37]] { -// CHECK: %[[VAL_38:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_25]]] : memref +// CHECK: %[[VAL_38:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_25]]] : memref // CHECK: %[[VAL_39:.*]] = mulf %[[VAL_38]], %[[VAL_2]] : f32 // CHECK: store %[[VAL_39]], %[[VAL_13]]{{\[}}%[[VAL_27]]] : memref<16xf32> // CHECK: } else { // CHECK: %[[VAL_40:.*]] = cmpi eq, %[[VAL_29]], %[[VAL_27]] : index // CHECK: scf.if %[[VAL_40]] { -// CHECK: %[[VAL_41:.*]] = load %[[VAL_12]]{{\[}}%[[VAL_26]]] : memref +// CHECK: %[[VAL_41:.*]] = load %[[VAL_11]]{{\[}}%[[VAL_26]]] : memref // CHECK: %[[VAL_42:.*]] = mulf %[[VAL_41]], %[[VAL_2]] : f32 // CHECK: store %[[VAL_42]], %[[VAL_13]]{{\[}}%[[VAL_27]]] : memref<16xf32> // CHECK: } else { @@ -821,22 +840,22 @@ // CHECK: } // CHECK: } // CHECK: %[[VAL_43:.*]] = cmpi eq, %[[VAL_28]], %[[VAL_27]] : index -// CHECK: %[[VAL_44:.*]] = addi %[[VAL_25]], %[[VAL_6]] : index +// CHECK: %[[VAL_44:.*]] = addi %[[VAL_25]], %[[VAL_5]] : index // CHECK: %[[VAL_45:.*]] = select %[[VAL_43]], %[[VAL_44]], %[[VAL_25]] : index // CHECK: %[[VAL_46:.*]] = cmpi eq, %[[VAL_29]], %[[VAL_27]] : index -// CHECK: %[[VAL_47:.*]] = addi %[[VAL_26]], %[[VAL_6]] : index +// CHECK: %[[VAL_47:.*]] = addi %[[VAL_26]], %[[VAL_5]] : index // CHECK: %[[VAL_48:.*]] = select %[[VAL_46]], %[[VAL_47]], %[[VAL_26]] : index -// CHECK: %[[VAL_49:.*]] = addi %[[VAL_27]], %[[VAL_6]] : index +// CHECK: %[[VAL_49:.*]] = addi %[[VAL_27]], %[[VAL_5]] : index // CHECK: scf.yield %[[VAL_45]], %[[VAL_48]], %[[VAL_49]] : index, index, index // CHECK: } -// CHECK: scf.for %[[VAL_50:.*]] = %[[VAL_51:.*]]#0 to %[[VAL_15]] step %[[VAL_6]] { -// CHECK: %[[VAL_52:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_50]]] : memref +// CHECK: scf.for %[[VAL_50:.*]] = %[[VAL_51:.*]]#0 to %[[VAL_15]] step %[[VAL_5]] { +// CHECK: %[[VAL_52:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_50]]] : memref // CHECK: %[[VAL_53:.*]] = mulf %[[VAL_52]], %[[VAL_2]] : f32 // CHECK: store %[[VAL_53]], %[[VAL_13]]{{\[}}%[[VAL_51]]#2] : memref<16xf32> // CHECK: } -// CHECK: scf.for %[[VAL_54:.*]] = %[[VAL_55:.*]]#1 to %[[VAL_17]] step %[[VAL_6]] { -// CHECK: %[[VAL_56:.*]] = load %[[VAL_11]]{{\[}}%[[VAL_54]]] : memref -// CHECK: %[[VAL_57:.*]] = load %[[VAL_12]]{{\[}}%[[VAL_54]]] : memref +// CHECK: scf.for %[[VAL_54:.*]] = %[[VAL_55:.*]]#1 to %[[VAL_17]] step %[[VAL_5]] { +// CHECK: %[[VAL_56:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_54]]] : memref +// CHECK: %[[VAL_57:.*]] = load %[[VAL_11]]{{\[}}%[[VAL_54]]] : memref // CHECK: %[[VAL_58:.*]] = mulf %[[VAL_57]], %[[VAL_2]] : f32 // CHECK: store %[[VAL_58]], %[[VAL_13]]{{\[}}%[[VAL_56]]] : memref<16xf32> // CHECK: } @@ -873,17 +892,18 @@ // CHECK-LABEL: func @sum_reduction( // CHECK-SAME: %[[VAL_0:.*]]: tensor, // CHECK-SAME: %[[VAL_1:.*]]: tensor) -> tensor { -// CHECK: %[[VAL_2:.*]] = constant 999 : index -// CHECK: %[[VAL_3:.*]] = constant 0 : index -// CHECK: %[[VAL_4:.*]] = constant 1 : index -// CHECK: %[[VAL_5:.*]] = alloca(%[[VAL_2]]) : memref -// CHECK: %[[VAL_6:.*]] = alloca(%[[VAL_2]]) : memref -// CHECK: %[[VAL_7:.*]] = alloca() : memref -// CHECK: %[[VAL_8:.*]] = load %[[VAL_5]]{{\[}}%[[VAL_3]]] : memref -// CHECK: %[[VAL_9:.*]] = load %[[VAL_5]]{{\[}}%[[VAL_4]]] : memref +// CHECK: %[[VAL_2:.*]] = constant 0 : index +// CHECK: %[[VAL_3:.*]] = constant 1 : index +// CHECK: %[[VAL_4:.*]] = linalg.sparse_pointers %[[VAL_0]], %[[VAL_2]] : tensor into memref +// CHECK: %[[VAL_5:.*]] = linalg.sparse_values %[[VAL_0]] : tensor into memref +// CHECK: %[[VAL_6:.*]] = tensor_to_memref %[[VAL_1]] : memref +// CHECK: %[[VAL_7:.*]] = alloc() : memref +// CHECK: linalg.copy(%[[VAL_6]], %[[VAL_7]]) : memref, memref +// CHECK: %[[VAL_8:.*]] = load %[[VAL_4]]{{\[}}%[[VAL_2]]] : memref +// CHECK: %[[VAL_9:.*]] = load %[[VAL_4]]{{\[}}%[[VAL_3]]] : memref // CHECK: %[[VAL_10:.*]] = load %[[VAL_7]][] : memref -// CHECK: %[[VAL_11:.*]] = scf.for %[[VAL_12:.*]] = %[[VAL_8]] to %[[VAL_9]] step %[[VAL_4]] iter_args(%[[VAL_13:.*]] = %[[VAL_10]]) -> (f32) { -// CHECK: %[[VAL_14:.*]] = load %[[VAL_6]]{{\[}}%[[VAL_12]]] : memref +// CHECK: %[[VAL_11:.*]] = scf.for %[[VAL_12:.*]] = %[[VAL_8]] to %[[VAL_9]] step %[[VAL_3]] iter_args(%[[VAL_13:.*]] = %[[VAL_10]]) -> (f32) { +// CHECK: %[[VAL_14:.*]] = load %[[VAL_5]]{{\[}}%[[VAL_12]]] : memref // CHECK: %[[VAL_15:.*]] = addf %[[VAL_13]], %[[VAL_14]] : f32 // CHECK: scf.yield %[[VAL_15]] : f32 // CHECK: } @@ -921,36 +941,37 @@ // CHECK-SAME: %[[VAL_0:.*0]]: tensor<16xf32>, // CHECK-SAME: %[[VAL_1:.*1]]: tensor<16xf32>, // CHECK-SAME: %[[VAL_2:.*2]]: tensor) -> tensor { -// CHECK: %[[VAL_3:.*]] = constant 999 : index -// CHECK: %[[VAL_4:.*]] = constant 0 : index -// CHECK: %[[VAL_5:.*]] = constant 1 : index -// CHECK: %[[VAL_6:.*]] = alloca(%[[VAL_3]]) : memref -// CHECK: %[[VAL_7:.*]] = alloca(%[[VAL_3]]) : memref -// CHECK: %[[VAL_8:.*]] = alloca(%[[VAL_3]]) : memref -// CHECK: %[[VAL_9:.*]] = alloca(%[[VAL_3]]) : memref -// CHECK: %[[VAL_10:.*]] = alloca(%[[VAL_3]]) : memref -// CHECK: %[[VAL_11:.*]] = alloca(%[[VAL_3]]) : memref -// CHECK: %[[VAL_12:.*]] = alloca() : memref -// CHECK: %[[VAL_13:.*]] = load %[[VAL_6]]{{\[}}%[[VAL_4]]] : memref -// CHECK: %[[VAL_14:.*]] = load %[[VAL_6]]{{\[}}%[[VAL_5]]] : memref -// CHECK: %[[VAL_15:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_4]]] : memref -// CHECK: %[[VAL_16:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_5]]] : memref -// CHECK: %[[VAL_17:.*]]:3 = scf.while (%[[VAL_18:.*]] = %[[VAL_13]], %[[VAL_19:.*]] = %[[VAL_15]], %[[VAL_20:.*]] = %[[VAL_4]]) : (index, index, index) -> (index, index, index) { +// CHECK: %[[VAL_3:.*]] = constant 0 : index +// CHECK: %[[VAL_4:.*]] = constant 1 : index +// CHECK: %[[VAL_5:.*]] = linalg.sparse_pointers %[[VAL_0]], %[[VAL_3]] : tensor<16xf32> into memref +// CHECK: %[[VAL_6:.*]] = linalg.sparse_indices %[[VAL_0]], %[[VAL_3]] : tensor<16xf32> into memref +// CHECK: %[[VAL_7:.*]] = linalg.sparse_values %[[VAL_0]] : tensor<16xf32> into memref +// CHECK: %[[VAL_8:.*]] = linalg.sparse_pointers %[[VAL_1]], %[[VAL_3]] : tensor<16xf32> into memref +// CHECK: %[[VAL_9:.*]] = linalg.sparse_indices %[[VAL_1]], %[[VAL_3]] : tensor<16xf32> into memref +// CHECK: %[[VAL_10:.*]] = linalg.sparse_values %[[VAL_1]] : tensor<16xf32> into memref +// CHECK: %[[VAL_11:.*]] = tensor_to_memref %[[VAL_2]] : memref +// CHECK: %[[VAL_12:.*]] = alloc() : memref +// CHECK: linalg.copy(%[[VAL_11]], %[[VAL_12]]) : memref, memref +// CHECK: %[[VAL_13:.*]] = load %[[VAL_5]]{{\[}}%[[VAL_3]]] : memref +// CHECK: %[[VAL_14:.*]] = load %[[VAL_5]]{{\[}}%[[VAL_4]]] : memref +// CHECK: %[[VAL_15:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_3]]] : memref +// CHECK: %[[VAL_16:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_4]]] : memref +// CHECK: %[[VAL_17:.*]]:3 = scf.while (%[[VAL_18:.*]] = %[[VAL_13]], %[[VAL_19:.*]] = %[[VAL_15]], %[[VAL_20:.*]] = %[[VAL_3]]) : (index, index, index) -> (index, index, index) { // CHECK: %[[VAL_21:.*]] = cmpi ult, %[[VAL_18]], %[[VAL_14]] : index // CHECK: %[[VAL_22:.*]] = cmpi ult, %[[VAL_19]], %[[VAL_16]] : index // CHECK: %[[VAL_23:.*]] = and %[[VAL_21]], %[[VAL_22]] : i1 // CHECK: scf.condition(%[[VAL_23]]) %[[VAL_18]], %[[VAL_19]], %[[VAL_20]] : index, index, index // CHECK: } do { // CHECK: ^bb0(%[[VAL_24:.*]]: index, %[[VAL_25:.*]]: index, %[[VAL_26:.*]]: index): -// CHECK: %[[VAL_27:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_24]]] : memref -// CHECK: %[[VAL_28:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_25]]] : memref +// CHECK: %[[VAL_27:.*]] = load %[[VAL_6]]{{\[}}%[[VAL_24]]] : memref +// CHECK: %[[VAL_28:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_25]]] : memref // CHECK: %[[VAL_29:.*]] = cmpi eq, %[[VAL_27]], %[[VAL_26]] : index // CHECK: %[[VAL_30:.*]] = cmpi eq, %[[VAL_28]], %[[VAL_26]] : index // CHECK: %[[VAL_31:.*]] = and %[[VAL_29]], %[[VAL_30]] : i1 // CHECK: scf.if %[[VAL_31]] { // CHECK: %[[VAL_32:.*]] = load %[[VAL_12]][] : memref -// CHECK: %[[VAL_33:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_24]]] : memref -// CHECK: %[[VAL_34:.*]] = load %[[VAL_11]]{{\[}}%[[VAL_25]]] : memref +// CHECK: %[[VAL_33:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_24]]] : memref +// CHECK: %[[VAL_34:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_25]]] : memref // CHECK: %[[VAL_35:.*]] = addf %[[VAL_33]], %[[VAL_34]] : f32 // CHECK: %[[VAL_36:.*]] = addf %[[VAL_32]], %[[VAL_35]] : f32 // CHECK: store %[[VAL_36]], %[[VAL_12]][] : memref @@ -958,14 +979,14 @@ // CHECK: %[[VAL_37:.*]] = cmpi eq, %[[VAL_27]], %[[VAL_26]] : index // CHECK: scf.if %[[VAL_37]] { // CHECK: %[[VAL_38:.*]] = load %[[VAL_12]][] : memref -// CHECK: %[[VAL_39:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_24]]] : memref +// CHECK: %[[VAL_39:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_24]]] : memref // CHECK: %[[VAL_40:.*]] = addf %[[VAL_38]], %[[VAL_39]] : f32 // CHECK: store %[[VAL_40]], %[[VAL_12]][] : memref // CHECK: } else { // CHECK: %[[VAL_41:.*]] = cmpi eq, %[[VAL_28]], %[[VAL_26]] : index // CHECK: scf.if %[[VAL_41]] { // CHECK: %[[VAL_42:.*]] = load %[[VAL_12]][] : memref -// CHECK: %[[VAL_43:.*]] = load %[[VAL_11]]{{\[}}%[[VAL_25]]] : memref +// CHECK: %[[VAL_43:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_25]]] : memref // CHECK: %[[VAL_44:.*]] = addf %[[VAL_42]], %[[VAL_43]] : f32 // CHECK: store %[[VAL_44]], %[[VAL_12]][] : memref // CHECK: } else { @@ -973,22 +994,22 @@ // CHECK: } // CHECK: } // CHECK: %[[VAL_45:.*]] = cmpi eq, %[[VAL_27]], %[[VAL_26]] : index -// CHECK: %[[VAL_46:.*]] = addi %[[VAL_24]], %[[VAL_5]] : index +// CHECK: %[[VAL_46:.*]] = addi %[[VAL_24]], %[[VAL_4]] : index // CHECK: %[[VAL_47:.*]] = select %[[VAL_45]], %[[VAL_46]], %[[VAL_24]] : index // CHECK: %[[VAL_48:.*]] = cmpi eq, %[[VAL_28]], %[[VAL_26]] : index -// CHECK: %[[VAL_49:.*]] = addi %[[VAL_25]], %[[VAL_5]] : index +// CHECK: %[[VAL_49:.*]] = addi %[[VAL_25]], %[[VAL_4]] : index // CHECK: %[[VAL_50:.*]] = select %[[VAL_48]], %[[VAL_49]], %[[VAL_25]] : index -// CHECK: %[[VAL_51:.*]] = addi %[[VAL_26]], %[[VAL_5]] : index +// CHECK: %[[VAL_51:.*]] = addi %[[VAL_26]], %[[VAL_4]] : index // CHECK: scf.yield %[[VAL_47]], %[[VAL_50]], %[[VAL_51]] : index, index, index // CHECK: } // CHECK: %[[VAL_52:.*]] = load %[[VAL_12]][] : memref -// CHECK: %[[VAL_53:.*]] = scf.for %[[VAL_54:.*]] = %[[VAL_55:.*]]#0 to %[[VAL_14]] step %[[VAL_5]] iter_args(%[[VAL_56:.*]] = %[[VAL_52]]) -> (f32) { -// CHECK: %[[VAL_57:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_54]]] : memref +// CHECK: %[[VAL_53:.*]] = scf.for %[[VAL_54:.*]] = %[[VAL_55:.*]]#0 to %[[VAL_14]] step %[[VAL_4]] iter_args(%[[VAL_56:.*]] = %[[VAL_52]]) -> (f32) { +// CHECK: %[[VAL_57:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_54]]] : memref // CHECK: %[[VAL_58:.*]] = addf %[[VAL_56]], %[[VAL_57]] : f32 // CHECK: scf.yield %[[VAL_58]] : f32 // CHECK: } -// CHECK: %[[VAL_59:.*]] = scf.for %[[VAL_60:.*]] = %[[VAL_61:.*]]#1 to %[[VAL_16]] step %[[VAL_5]] iter_args(%[[VAL_62:.*]] = %[[VAL_63:.*]]) -> (f32) { -// CHECK: %[[VAL_64:.*]] = load %[[VAL_11]]{{\[}}%[[VAL_60]]] : memref +// CHECK: %[[VAL_59:.*]] = scf.for %[[VAL_60:.*]] = %[[VAL_61:.*]]#1 to %[[VAL_16]] step %[[VAL_4]] iter_args(%[[VAL_62:.*]] = %[[VAL_63:.*]]) -> (f32) { +// CHECK: %[[VAL_64:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_60]]] : memref // CHECK: %[[VAL_65:.*]] = addf %[[VAL_62]], %[[VAL_64]] : f32 // CHECK: scf.yield %[[VAL_65]] : f32 // CHECK: } @@ -1034,39 +1055,40 @@ // CHECK-SAME: %[[VAL_1:.*1]]: tensor, // CHECK-SAME: %[[VAL_2:.*2]]: tensor<16xf32>, // CHECK-SAME: %[[VAL_3:.*3]]: tensor) -> tensor { -// CHECK: %[[VAL_4:.*]] = constant 999 : index -// CHECK: %[[VAL_5:.*]] = constant 0 : index -// CHECK: %[[VAL_6:.*]] = constant 1 : index -// CHECK: %[[VAL_7:.*]] = alloca(%[[VAL_4]]) : memref -// CHECK: %[[VAL_8:.*]] = alloca(%[[VAL_4]]) : memref -// CHECK: %[[VAL_9:.*]] = alloca(%[[VAL_4]]) : memref -// CHECK: %[[VAL_10:.*]] = alloca() : memref -// CHECK: %[[VAL_11:.*]] = alloca(%[[VAL_4]]) : memref -// CHECK: %[[VAL_12:.*]] = alloca(%[[VAL_4]]) : memref -// CHECK: %[[VAL_13:.*]] = alloca(%[[VAL_4]]) : memref -// CHECK: %[[VAL_14:.*]] = alloca() : memref -// CHECK: %[[VAL_15:.*]] = load %[[VAL_10]][] : memref -// CHECK: %[[VAL_16:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_5]]] : memref -// CHECK: %[[VAL_17:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_6]]] : memref -// CHECK: %[[VAL_18:.*]] = load %[[VAL_11]]{{\[}}%[[VAL_5]]] : memref -// CHECK: %[[VAL_19:.*]] = load %[[VAL_11]]{{\[}}%[[VAL_6]]] : memref -// CHECK: %[[VAL_20:.*]]:3 = scf.while (%[[VAL_21:.*]] = %[[VAL_16]], %[[VAL_22:.*]] = %[[VAL_18]], %[[VAL_23:.*]] = %[[VAL_5]]) : (index, index, index) -> (index, index, index) { +// CHECK: %[[VAL_4:.*]] = constant 0 : index +// CHECK: %[[VAL_5:.*]] = constant 1 : index +// CHECK: %[[VAL_6:.*]] = linalg.sparse_pointers %[[VAL_0]], %[[VAL_4]] : tensor<16xf32> into memref +// CHECK: %[[VAL_7:.*]] = linalg.sparse_indices %[[VAL_0]], %[[VAL_4]] : tensor<16xf32> into memref +// CHECK: %[[VAL_8:.*]] = linalg.sparse_values %[[VAL_0]] : tensor<16xf32> into memref +// CHECK: %[[VAL_9:.*]] = tensor_to_memref %[[VAL_1]] : memref +// CHECK: %[[VAL_10:.*]] = linalg.sparse_pointers %[[VAL_2]], %[[VAL_4]] : tensor<16xf32> into memref +// CHECK: %[[VAL_11:.*]] = linalg.sparse_indices %[[VAL_2]], %[[VAL_4]] : tensor<16xf32> into memref +// CHECK: %[[VAL_12:.*]] = linalg.sparse_values %[[VAL_2]] : tensor<16xf32> into memref +// CHECK: %[[VAL_13:.*]] = tensor_to_memref %[[VAL_3]] : memref +// CHECK: %[[VAL_14:.*]] = alloc() : memref +// CHECK: linalg.copy(%[[VAL_13]], %[[VAL_14]]) : memref, memref +// CHECK: %[[VAL_15:.*]] = load %[[VAL_9]][] : memref +// CHECK: %[[VAL_16:.*]] = load %[[VAL_6]]{{\[}}%[[VAL_4]]] : memref +// CHECK: %[[VAL_17:.*]] = load %[[VAL_6]]{{\[}}%[[VAL_5]]] : memref +// CHECK: %[[VAL_18:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_4]]] : memref +// CHECK: %[[VAL_19:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_5]]] : memref +// CHECK: %[[VAL_20:.*]]:3 = scf.while (%[[VAL_21:.*]] = %[[VAL_16]], %[[VAL_22:.*]] = %[[VAL_18]], %[[VAL_23:.*]] = %[[VAL_4]]) : (index, index, index) -> (index, index, index) { // CHECK: %[[VAL_24:.*]] = cmpi ult, %[[VAL_21]], %[[VAL_17]] : index // CHECK: %[[VAL_25:.*]] = cmpi ult, %[[VAL_22]], %[[VAL_19]] : index // CHECK: %[[VAL_26:.*]] = and %[[VAL_24]], %[[VAL_25]] : i1 // CHECK: scf.condition(%[[VAL_26]]) %[[VAL_21]], %[[VAL_22]], %[[VAL_23]] : index, index, index // CHECK: } do { // CHECK: ^bb0(%[[VAL_27:.*]]: index, %[[VAL_28:.*]]: index, %[[VAL_29:.*]]: index): -// CHECK: %[[VAL_30:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_27]]] : memref -// CHECK: %[[VAL_31:.*]] = load %[[VAL_12]]{{\[}}%[[VAL_28]]] : memref +// CHECK: %[[VAL_30:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_27]]] : memref +// CHECK: %[[VAL_31:.*]] = load %[[VAL_11]]{{\[}}%[[VAL_28]]] : memref // CHECK: %[[VAL_32:.*]] = cmpi eq, %[[VAL_30]], %[[VAL_29]] : index // CHECK: %[[VAL_33:.*]] = cmpi eq, %[[VAL_31]], %[[VAL_29]] : index // CHECK: %[[VAL_34:.*]] = and %[[VAL_32]], %[[VAL_33]] : i1 // CHECK: scf.if %[[VAL_34]] { // CHECK: %[[VAL_35:.*]] = load %[[VAL_14]][] : memref -// CHECK: %[[VAL_36:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_27]]] : memref +// CHECK: %[[VAL_36:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_27]]] : memref // CHECK: %[[VAL_37:.*]] = mulf %[[VAL_36]], %[[VAL_15]] : f32 -// CHECK: %[[VAL_38:.*]] = load %[[VAL_13]]{{\[}}%[[VAL_28]]] : memref +// CHECK: %[[VAL_38:.*]] = load %[[VAL_12]]{{\[}}%[[VAL_28]]] : memref // CHECK: %[[VAL_39:.*]] = addf %[[VAL_37]], %[[VAL_38]] : f32 // CHECK: %[[VAL_40:.*]] = addf %[[VAL_35]], %[[VAL_39]] : f32 // CHECK: store %[[VAL_40]], %[[VAL_14]][] : memref @@ -1074,7 +1096,7 @@ // CHECK: %[[VAL_41:.*]] = cmpi eq, %[[VAL_30]], %[[VAL_29]] : index // CHECK: scf.if %[[VAL_41]] { // CHECK: %[[VAL_42:.*]] = load %[[VAL_14]][] : memref -// CHECK: %[[VAL_43:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_27]]] : memref +// CHECK: %[[VAL_43:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_27]]] : memref // CHECK: %[[VAL_44:.*]] = mulf %[[VAL_43]], %[[VAL_15]] : f32 // CHECK: %[[VAL_45:.*]] = addf %[[VAL_42]], %[[VAL_44]] : f32 // CHECK: store %[[VAL_45]], %[[VAL_14]][] : memref @@ -1082,7 +1104,7 @@ // CHECK: %[[VAL_46:.*]] = cmpi eq, %[[VAL_31]], %[[VAL_29]] : index // CHECK: scf.if %[[VAL_46]] { // CHECK: %[[VAL_47:.*]] = load %[[VAL_14]][] : memref -// CHECK: %[[VAL_48:.*]] = load %[[VAL_13]]{{\[}}%[[VAL_28]]] : memref +// CHECK: %[[VAL_48:.*]] = load %[[VAL_12]]{{\[}}%[[VAL_28]]] : memref // CHECK: %[[VAL_49:.*]] = addf %[[VAL_47]], %[[VAL_48]] : f32 // CHECK: store %[[VAL_49]], %[[VAL_14]][] : memref // CHECK: } else { @@ -1090,23 +1112,23 @@ // CHECK: } // CHECK: } // CHECK: %[[VAL_50:.*]] = cmpi eq, %[[VAL_30]], %[[VAL_29]] : index -// CHECK: %[[VAL_51:.*]] = addi %[[VAL_27]], %[[VAL_6]] : index +// CHECK: %[[VAL_51:.*]] = addi %[[VAL_27]], %[[VAL_5]] : index // CHECK: %[[VAL_52:.*]] = select %[[VAL_50]], %[[VAL_51]], %[[VAL_27]] : index // CHECK: %[[VAL_53:.*]] = cmpi eq, %[[VAL_31]], %[[VAL_29]] : index -// CHECK: %[[VAL_54:.*]] = addi %[[VAL_28]], %[[VAL_6]] : index +// CHECK: %[[VAL_54:.*]] = addi %[[VAL_28]], %[[VAL_5]] : index // CHECK: %[[VAL_55:.*]] = select %[[VAL_53]], %[[VAL_54]], %[[VAL_28]] : index -// CHECK: %[[VAL_56:.*]] = addi %[[VAL_29]], %[[VAL_6]] : index +// CHECK: %[[VAL_56:.*]] = addi %[[VAL_29]], %[[VAL_5]] : index // CHECK: scf.yield %[[VAL_52]], %[[VAL_55]], %[[VAL_56]] : index, index, index // CHECK: } // CHECK: %[[VAL_57:.*]] = load %[[VAL_14]][] : memref -// CHECK: %[[VAL_58:.*]] = scf.for %[[VAL_59:.*]] = %[[VAL_60:.*]]#0 to %[[VAL_17]] step %[[VAL_6]] iter_args(%[[VAL_61:.*]] = %[[VAL_57]]) -> (f32) { -// CHECK: %[[VAL_62:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_59]]] : memref +// CHECK: %[[VAL_58:.*]] = scf.for %[[VAL_59:.*]] = %[[VAL_60:.*]]#0 to %[[VAL_17]] step %[[VAL_5]] iter_args(%[[VAL_61:.*]] = %[[VAL_57]]) -> (f32) { +// CHECK: %[[VAL_62:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_59]]] : memref // CHECK: %[[VAL_63:.*]] = mulf %[[VAL_62]], %[[VAL_15]] : f32 // CHECK: %[[VAL_64:.*]] = addf %[[VAL_61]], %[[VAL_63]] : f32 // CHECK: scf.yield %[[VAL_64]] : f32 // CHECK: } -// CHECK: %[[VAL_65:.*]] = scf.for %[[VAL_66:.*]] = %[[VAL_67:.*]]#1 to %[[VAL_19]] step %[[VAL_6]] iter_args(%[[VAL_68:.*]] = %[[VAL_69:.*]]) -> (f32) { -// CHECK: %[[VAL_70:.*]] = load %[[VAL_13]]{{\[}}%[[VAL_66]]] : memref +// CHECK: %[[VAL_65:.*]] = scf.for %[[VAL_66:.*]] = %[[VAL_67:.*]]#1 to %[[VAL_19]] step %[[VAL_5]] iter_args(%[[VAL_68:.*]] = %[[VAL_69:.*]]) -> (f32) { +// CHECK: %[[VAL_70:.*]] = load %[[VAL_12]]{{\[}}%[[VAL_66]]] : memref // CHECK: %[[VAL_71:.*]] = addf %[[VAL_68]], %[[VAL_70]] : f32 // CHECK: scf.yield %[[VAL_71]] : f32 // CHECK: } diff --git a/mlir/test/Dialect/Linalg/sparse_2d.mlir b/mlir/test/Dialect/Linalg/sparse_2d.mlir --- a/mlir/test/Dialect/Linalg/sparse_2d.mlir +++ b/mlir/test/Dialect/Linalg/sparse_2d.mlir @@ -24,19 +24,21 @@ // CHECK: %[[VAL_4:.*]] = constant 16 : index // CHECK: %[[VAL_5:.*]] = constant 0 : index // CHECK: %[[VAL_6:.*]] = constant 1 : index -// CHECK: %[[VAL_7:.*]] = alloca() : memref<32x16xf32> -// CHECK: %[[VAL_8:.*]] = alloca() : memref<32x16xf32> -// CHECK: %[[VAL_9:.*]] = alloca() : memref<32x16xf32> -// CHECK: scf.for %[[VAL_10:.*]] = %[[VAL_5]] to %[[VAL_3]] step %[[VAL_6]] { -// CHECK: scf.for %[[VAL_11:.*]] = %[[VAL_5]] to %[[VAL_4]] step %[[VAL_6]] { -// CHECK: %[[VAL_12:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_10]], %[[VAL_11]]] : memref<32x16xf32> -// CHECK: %[[VAL_13:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_10]], %[[VAL_11]]] : memref<32x16xf32> -// CHECK: %[[VAL_14:.*]] = addf %[[VAL_12]], %[[VAL_13]] : f32 -// CHECK: store %[[VAL_14]], %[[VAL_9]]{{\[}}%[[VAL_10]], %[[VAL_11]]] : memref<32x16xf32> +// CHECK: %[[VAL_7:.*]] = tensor_to_memref %[[VAL_0]] : memref<32x16xf32> +// CHECK: %[[VAL_8:.*]] = tensor_to_memref %[[VAL_1]] : memref<32x16xf32> +// CHECK: %[[VAL_9:.*]] = tensor_to_memref %[[VAL_2]] : memref<32x16xf32> +// CHECK: %[[VAL_10:.*]] = alloc() : memref<32x16xf32> +// CHECK: linalg.copy(%[[VAL_9]], %[[VAL_10]]) : memref<32x16xf32>, memref<32x16xf32> +// CHECK: scf.for %[[VAL_11:.*]] = %[[VAL_5]] to %[[VAL_3]] step %[[VAL_6]] { +// CHECK: scf.for %[[VAL_12:.*]] = %[[VAL_5]] to %[[VAL_4]] step %[[VAL_6]] { +// CHECK: %[[VAL_13:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_11]], %[[VAL_12]]] : memref<32x16xf32> +// CHECK: %[[VAL_14:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_11]], %[[VAL_12]]] : memref<32x16xf32> +// CHECK: %[[VAL_15:.*]] = addf %[[VAL_13]], %[[VAL_14]] : f32 +// CHECK: store %[[VAL_15]], %[[VAL_10]]{{\[}}%[[VAL_11]], %[[VAL_12]]] : memref<32x16xf32> // CHECK: } // CHECK: } -// CHECK: %[[VAL_15:.*]] = tensor_load %[[VAL_9]] : memref<32x16xf32> -// CHECK: return %[[VAL_15]] : tensor<32x16xf32> +// CHECK: %[[VAL_16:.*]] = tensor_load %[[VAL_10]] : memref<32x16xf32> +// CHECK: return %[[VAL_16]] : tensor<32x16xf32> // CHECK: } func @add_dd(%arga: tensor<32x16xf32>, %argb: tensor<32x16xf32>, %argx: tensor<32x16xf32>) -> tensor<32x16xf32> { %0 = linalg.generic #trait_dd @@ -57,19 +59,21 @@ // CHECK: %[[VAL_4:.*]] = constant 16 : index // CHECK: %[[VAL_5:.*]] = constant 0 : index // CHECK: %[[VAL_6:.*]] = constant 1 : index -// CHECK: %[[VAL_7:.*]] = alloca() : memref<32x16xf32> -// CHECK: %[[VAL_8:.*]] = alloca() : memref<32x16xf32> -// CHECK: %[[VAL_9:.*]] = alloca() : memref<32x16xf32> -// CHECK: scf.for %[[VAL_10:.*]] = %[[VAL_5]] to %[[VAL_3]] step %[[VAL_6]] { -// CHECK: scf.for %[[VAL_11:.*]] = %[[VAL_5]] to %[[VAL_4]] step %[[VAL_6]] { -// CHECK: %[[VAL_12:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_10]], %[[VAL_11]]] : memref<32x16xf32> -// CHECK: %[[VAL_13:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_10]], %[[VAL_11]]] : memref<32x16xf32> -// CHECK: %[[VAL_14:.*]] = mulf %[[VAL_12]], %[[VAL_13]] : f32 -// CHECK: store %[[VAL_14]], %[[VAL_9]]{{\[}}%[[VAL_10]], %[[VAL_11]]] : memref<32x16xf32> +// CHECK: %[[VAL_7:.*]] = tensor_to_memref %[[VAL_0]] : memref<32x16xf32> +// CHECK: %[[VAL_8:.*]] = tensor_to_memref %[[VAL_1]] : memref<32x16xf32> +// CHECK: %[[VAL_9:.*]] = tensor_to_memref %[[VAL_2]] : memref<32x16xf32> +// CHECK: %[[VAL_10:.*]] = alloc() : memref<32x16xf32> +// CHECK: linalg.copy(%[[VAL_9]], %[[VAL_10]]) : memref<32x16xf32>, memref<32x16xf32> +// CHECK: scf.for %[[VAL_11:.*]] = %[[VAL_5]] to %[[VAL_3]] step %[[VAL_6]] { +// CHECK: scf.for %[[VAL_12:.*]] = %[[VAL_5]] to %[[VAL_4]] step %[[VAL_6]] { +// CHECK: %[[VAL_13:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_11]], %[[VAL_12]]] : memref<32x16xf32> +// CHECK: %[[VAL_14:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_11]], %[[VAL_12]]] : memref<32x16xf32> +// CHECK: %[[VAL_15:.*]] = mulf %[[VAL_13]], %[[VAL_14]] : f32 +// CHECK: store %[[VAL_15]], %[[VAL_10]]{{\[}}%[[VAL_11]], %[[VAL_12]]] : memref<32x16xf32> // CHECK: } // CHECK: } -// CHECK: %[[VAL_15:.*]] = tensor_load %[[VAL_9]] : memref<32x16xf32> -// CHECK: return %[[VAL_15]] : tensor<32x16xf32> +// CHECK: %[[VAL_16:.*]] = tensor_load %[[VAL_10]] : memref<32x16xf32> +// CHECK: return %[[VAL_16]] : tensor<32x16xf32> // CHECK: } func @mul_dd(%arga: tensor<32x16xf32>, %argb: tensor<32x16xf32>, %argx: tensor<32x16xf32>) -> tensor<32x16xf32> { %0 = linalg.generic #trait_dd @@ -101,48 +105,49 @@ // CHECK-SAME: %[[VAL_0:.*0]]: tensor<32x16xf32>, // CHECK-SAME: %[[VAL_1:.*1]]: tensor<32x16xf32>, // CHECK-SAME: %[[VAL_2:.*2]]: tensor<32x16xf32>) -> tensor<32x16xf32> { -// CHECK: %[[VAL_3:.*]] = constant 999 : index -// CHECK: %[[VAL_4:.*]] = constant 32 : index -// CHECK: %[[VAL_5:.*]] = constant 16 : index -// CHECK: %[[VAL_6:.*]] = constant 0 : index -// CHECK: %[[VAL_7:.*]] = constant true -// CHECK: %[[VAL_8:.*]] = constant 1 : index -// CHECK: %[[VAL_9:.*]] = alloca(%[[VAL_3]]) : memref -// CHECK: %[[VAL_10:.*]] = alloca(%[[VAL_3]]) : memref -// CHECK: %[[VAL_11:.*]] = alloca(%[[VAL_3]]) : memref -// CHECK: %[[VAL_12:.*]] = alloca() : memref<32x16xf32> -// CHECK: %[[VAL_13:.*]] = alloca() : memref<32x16xf32> -// CHECK: scf.for %[[VAL_14:.*]] = %[[VAL_6]] to %[[VAL_4]] step %[[VAL_8]] { -// CHECK: %[[VAL_15:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_14]]] : memref -// CHECK: %[[VAL_16:.*]] = addi %[[VAL_14]], %[[VAL_8]] : index -// CHECK: %[[VAL_17:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_16]]] : memref -// CHECK: %[[VAL_18:.*]]:2 = scf.while (%[[VAL_19:.*]] = %[[VAL_15]], %[[VAL_20:.*]] = %[[VAL_6]]) : (index, index) -> (index, index) { +// CHECK: %[[VAL_3:.*]] = constant 32 : index +// CHECK: %[[VAL_4:.*]] = constant 16 : index +// CHECK: %[[VAL_5:.*]] = constant 0 : index +// CHECK: %[[VAL_6:.*]] = constant true +// CHECK: %[[VAL_7:.*]] = constant 1 : index +// CHECK: %[[VAL_8:.*]] = linalg.sparse_pointers %[[VAL_0]], %[[VAL_7]] : tensor<32x16xf32> into memref +// CHECK: %[[VAL_9:.*]] = linalg.sparse_indices %[[VAL_0]], %[[VAL_7]] : tensor<32x16xf32> into memref +// CHECK: %[[VAL_10:.*]] = linalg.sparse_values %[[VAL_0]] : tensor<32x16xf32> into memref +// CHECK: %[[VAL_11:.*]] = tensor_to_memref %[[VAL_1]] : memref<32x16xf32> +// CHECK: %[[VAL_12:.*]] = tensor_to_memref %[[VAL_2]] : memref<32x16xf32> +// CHECK: %[[VAL_13:.*]] = alloc() : memref<32x16xf32> +// CHECK: linalg.copy(%[[VAL_12]], %[[VAL_13]]) : memref<32x16xf32>, memref<32x16xf32> +// CHECK: scf.for %[[VAL_14:.*]] = %[[VAL_5]] to %[[VAL_3]] step %[[VAL_7]] { +// CHECK: %[[VAL_15:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_14]]] : memref +// CHECK: %[[VAL_16:.*]] = addi %[[VAL_14]], %[[VAL_7]] : index +// CHECK: %[[VAL_17:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_16]]] : memref +// CHECK: %[[VAL_18:.*]]:2 = scf.while (%[[VAL_19:.*]] = %[[VAL_15]], %[[VAL_20:.*]] = %[[VAL_5]]) : (index, index) -> (index, index) { // CHECK: %[[VAL_21:.*]] = cmpi ult, %[[VAL_19]], %[[VAL_17]] : index // CHECK: scf.condition(%[[VAL_21]]) %[[VAL_19]], %[[VAL_20]] : index, index // CHECK: } do { // CHECK: ^bb0(%[[VAL_22:.*]]: index, %[[VAL_23:.*]]: index): -// CHECK: %[[VAL_24:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_22]]] : memref +// CHECK: %[[VAL_24:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_22]]] : memref // CHECK: %[[VAL_25:.*]] = cmpi eq, %[[VAL_24]], %[[VAL_23]] : index // CHECK: scf.if %[[VAL_25]] { -// CHECK: %[[VAL_26:.*]] = load %[[VAL_11]]{{\[}}%[[VAL_22]]] : memref -// CHECK: %[[VAL_27:.*]] = load %[[VAL_12]]{{\[}}%[[VAL_14]], %[[VAL_23]]] : memref<32x16xf32> +// CHECK: %[[VAL_26:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_22]]] : memref +// CHECK: %[[VAL_27:.*]] = load %[[VAL_11]]{{\[}}%[[VAL_14]], %[[VAL_23]]] : memref<32x16xf32> // CHECK: %[[VAL_28:.*]] = addf %[[VAL_26]], %[[VAL_27]] : f32 // CHECK: store %[[VAL_28]], %[[VAL_13]]{{\[}}%[[VAL_14]], %[[VAL_23]]] : memref<32x16xf32> // CHECK: } else { -// CHECK: scf.if %[[VAL_7]] { -// CHECK: %[[VAL_29:.*]] = load %[[VAL_12]]{{\[}}%[[VAL_14]], %[[VAL_23]]] : memref<32x16xf32> +// CHECK: scf.if %[[VAL_6]] { +// CHECK: %[[VAL_29:.*]] = load %[[VAL_11]]{{\[}}%[[VAL_14]], %[[VAL_23]]] : memref<32x16xf32> // CHECK: store %[[VAL_29]], %[[VAL_13]]{{\[}}%[[VAL_14]], %[[VAL_23]]] : memref<32x16xf32> // CHECK: } else { // CHECK: } // CHECK: } // CHECK: %[[VAL_30:.*]] = cmpi eq, %[[VAL_24]], %[[VAL_23]] : index -// CHECK: %[[VAL_31:.*]] = addi %[[VAL_22]], %[[VAL_8]] : index +// CHECK: %[[VAL_31:.*]] = addi %[[VAL_22]], %[[VAL_7]] : index // CHECK: %[[VAL_32:.*]] = select %[[VAL_30]], %[[VAL_31]], %[[VAL_22]] : index -// CHECK: %[[VAL_33:.*]] = addi %[[VAL_23]], %[[VAL_8]] : index +// CHECK: %[[VAL_33:.*]] = addi %[[VAL_23]], %[[VAL_7]] : index // CHECK: scf.yield %[[VAL_32]], %[[VAL_33]] : index, index // CHECK: } -// CHECK: scf.for %[[VAL_34:.*]] = %[[VAL_35:.*]]#1 to %[[VAL_5]] step %[[VAL_8]] { -// CHECK: %[[VAL_36:.*]] = load %[[VAL_12]]{{\[}}%[[VAL_14]], %[[VAL_34]]] : memref<32x16xf32> +// CHECK: scf.for %[[VAL_34:.*]] = %[[VAL_35:.*]]#1 to %[[VAL_4]] step %[[VAL_7]] { +// CHECK: %[[VAL_36:.*]] = load %[[VAL_11]]{{\[}}%[[VAL_14]], %[[VAL_34]]] : memref<32x16xf32> // CHECK: store %[[VAL_36]], %[[VAL_13]]{{\[}}%[[VAL_14]], %[[VAL_34]]] : memref<32x16xf32> // CHECK: } // CHECK: } @@ -164,23 +169,24 @@ // CHECK-SAME: %[[VAL_0:.*0]]: tensor<32x16xf32>, // CHECK-SAME: %[[VAL_1:.*1]]: tensor<32x16xf32>, // CHECK-SAME: %[[VAL_2:.*2]]: tensor<32x16xf32>) -> tensor<32x16xf32> { -// CHECK: %[[VAL_3:.*]] = constant 999 : index -// CHECK: %[[VAL_4:.*]] = constant 32 : index -// CHECK: %[[VAL_5:.*]] = constant 0 : index -// CHECK: %[[VAL_6:.*]] = constant 1 : index -// CHECK: %[[VAL_7:.*]] = alloca(%[[VAL_3]]) : memref -// CHECK: %[[VAL_8:.*]] = alloca(%[[VAL_3]]) : memref -// CHECK: %[[VAL_9:.*]] = alloca(%[[VAL_3]]) : memref -// CHECK: %[[VAL_10:.*]] = alloca() : memref<32x16xf32> -// CHECK: %[[VAL_11:.*]] = alloca() : memref<32x16xf32> -// CHECK: scf.for %[[VAL_12:.*]] = %[[VAL_5]] to %[[VAL_4]] step %[[VAL_6]] { -// CHECK: %[[VAL_13:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_12]]] : memref -// CHECK: %[[VAL_14:.*]] = addi %[[VAL_12]], %[[VAL_6]] : index -// CHECK: %[[VAL_15:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_14]]] : memref -// CHECK: scf.for %[[VAL_16:.*]] = %[[VAL_13]] to %[[VAL_15]] step %[[VAL_6]] { -// CHECK: %[[VAL_17:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_16]]] : memref -// CHECK: %[[VAL_18:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_16]]] : memref -// CHECK: %[[VAL_19:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_12]], %[[VAL_17]]] : memref<32x16xf32> +// CHECK: %[[VAL_3:.*]] = constant 32 : index +// CHECK: %[[VAL_4:.*]] = constant 0 : index +// CHECK: %[[VAL_5:.*]] = constant 1 : index +// CHECK: %[[VAL_6:.*]] = linalg.sparse_pointers %[[VAL_0]], %[[VAL_5]] : tensor<32x16xf32> into memref +// CHECK: %[[VAL_7:.*]] = linalg.sparse_indices %[[VAL_0]], %[[VAL_5]] : tensor<32x16xf32> into memref +// CHECK: %[[VAL_8:.*]] = linalg.sparse_values %[[VAL_0]] : tensor<32x16xf32> into memref +// CHECK: %[[VAL_9:.*]] = tensor_to_memref %[[VAL_1]] : memref<32x16xf32> +// CHECK: %[[VAL_10:.*]] = tensor_to_memref %[[VAL_2]] : memref<32x16xf32> +// CHECK: %[[VAL_11:.*]] = alloc() : memref<32x16xf32> +// CHECK: linalg.copy(%[[VAL_10]], %[[VAL_11]]) : memref<32x16xf32>, memref<32x16xf32> +// CHECK: scf.for %[[VAL_12:.*]] = %[[VAL_4]] to %[[VAL_3]] step %[[VAL_5]] { +// CHECK: %[[VAL_13:.*]] = load %[[VAL_6]]{{\[}}%[[VAL_12]]] : memref +// CHECK: %[[VAL_14:.*]] = addi %[[VAL_12]], %[[VAL_5]] : index +// CHECK: %[[VAL_15:.*]] = load %[[VAL_6]]{{\[}}%[[VAL_14]]] : memref +// CHECK: scf.for %[[VAL_16:.*]] = %[[VAL_13]] to %[[VAL_15]] step %[[VAL_5]] { +// CHECK: %[[VAL_17:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_16]]] : memref +// CHECK: %[[VAL_18:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_16]]] : memref +// CHECK: %[[VAL_19:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_12]], %[[VAL_17]]] : memref<32x16xf32> // CHECK: %[[VAL_20:.*]] = mulf %[[VAL_18]], %[[VAL_19]] : f32 // CHECK: store %[[VAL_20]], %[[VAL_11]]{{\[}}%[[VAL_12]], %[[VAL_17]]] : memref<32x16xf32> // CHECK: } @@ -218,53 +224,54 @@ // CHECK-SAME: %[[VAL_0:.*0]]: tensor<32x16xf32>, // CHECK-SAME: %[[VAL_1:.*1]]: tensor<32x16xf32>, // CHECK-SAME: %[[VAL_2:.*2]]: tensor<32x16xf32>) -> tensor<32x16xf32> { -// CHECK: %[[VAL_3:.*]] = constant 999 : index -// CHECK: %[[VAL_4:.*]] = constant 32 : index -// CHECK: %[[VAL_5:.*]] = constant 16 : index -// CHECK: %[[VAL_6:.*]] = constant true -// CHECK: %[[VAL_7:.*]] = constant 0 : index -// CHECK: %[[VAL_8:.*]] = constant 1 : index -// CHECK: %[[VAL_9:.*]] = alloca(%[[VAL_3]]) : memref -// CHECK: %[[VAL_10:.*]] = alloca(%[[VAL_3]]) : memref -// CHECK: %[[VAL_11:.*]] = alloca(%[[VAL_3]]) : memref -// CHECK: %[[VAL_12:.*]] = alloca() : memref<32x16xf32> -// CHECK: %[[VAL_13:.*]] = alloca() : memref<32x16xf32> -// CHECK: %[[VAL_14:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_7]]] : memref -// CHECK: %[[VAL_15:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_8]]] : memref -// CHECK: %[[VAL_16:.*]]:2 = scf.while (%[[VAL_17:.*]] = %[[VAL_14]], %[[VAL_18:.*]] = %[[VAL_7]]) : (index, index) -> (index, index) { +// CHECK: %[[VAL_3:.*]] = constant 32 : index +// CHECK: %[[VAL_4:.*]] = constant 16 : index +// CHECK: %[[VAL_5:.*]] = constant true +// CHECK: %[[VAL_6:.*]] = constant 0 : index +// CHECK: %[[VAL_7:.*]] = constant 1 : index +// CHECK: %[[VAL_8:.*]] = linalg.sparse_pointers %[[VAL_0]], %[[VAL_6]] : tensor<32x16xf32> into memref +// CHECK: %[[VAL_9:.*]] = linalg.sparse_indices %[[VAL_0]], %[[VAL_6]] : tensor<32x16xf32> into memref +// CHECK: %[[VAL_10:.*]] = linalg.sparse_values %[[VAL_0]] : tensor<32x16xf32> into memref +// CHECK: %[[VAL_11:.*]] = tensor_to_memref %[[VAL_1]] : memref<32x16xf32> +// CHECK: %[[VAL_12:.*]] = tensor_to_memref %[[VAL_2]] : memref<32x16xf32> +// CHECK: %[[VAL_13:.*]] = alloc() : memref<32x16xf32> +// CHECK: linalg.copy(%[[VAL_12]], %[[VAL_13]]) : memref<32x16xf32>, memref<32x16xf32> +// CHECK: %[[VAL_14:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_6]]] : memref +// CHECK: %[[VAL_15:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_7]]] : memref +// CHECK: %[[VAL_16:.*]]:2 = scf.while (%[[VAL_17:.*]] = %[[VAL_14]], %[[VAL_18:.*]] = %[[VAL_6]]) : (index, index) -> (index, index) { // CHECK: %[[VAL_19:.*]] = cmpi ult, %[[VAL_17]], %[[VAL_15]] : index // CHECK: scf.condition(%[[VAL_19]]) %[[VAL_17]], %[[VAL_18]] : index, index // CHECK: } do { // CHECK: ^bb0(%[[VAL_20:.*]]: index, %[[VAL_21:.*]]: index): -// CHECK: %[[VAL_22:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_20]]] : memref +// CHECK: %[[VAL_22:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_20]]] : memref // CHECK: %[[VAL_23:.*]] = cmpi eq, %[[VAL_22]], %[[VAL_21]] : index // CHECK: scf.if %[[VAL_23]] { -// CHECK: scf.for %[[VAL_24:.*]] = %[[VAL_7]] to %[[VAL_5]] step %[[VAL_8]] { -// CHECK: %[[VAL_25:.*]] = muli %[[VAL_20]], %[[VAL_5]] : index +// CHECK: scf.for %[[VAL_24:.*]] = %[[VAL_6]] to %[[VAL_4]] step %[[VAL_7]] { +// CHECK: %[[VAL_25:.*]] = muli %[[VAL_20]], %[[VAL_4]] : index // CHECK: %[[VAL_26:.*]] = addi %[[VAL_25]], %[[VAL_24]] : index -// CHECK: %[[VAL_27:.*]] = load %[[VAL_11]]{{\[}}%[[VAL_26]]] : memref -// CHECK: %[[VAL_28:.*]] = load %[[VAL_12]]{{\[}}%[[VAL_21]], %[[VAL_24]]] : memref<32x16xf32> +// CHECK: %[[VAL_27:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_26]]] : memref +// CHECK: %[[VAL_28:.*]] = load %[[VAL_11]]{{\[}}%[[VAL_21]], %[[VAL_24]]] : memref<32x16xf32> // CHECK: %[[VAL_29:.*]] = addf %[[VAL_27]], %[[VAL_28]] : f32 // CHECK: store %[[VAL_29]], %[[VAL_13]]{{\[}}%[[VAL_21]], %[[VAL_24]]] : memref<32x16xf32> // CHECK: } // CHECK: } else { -// CHECK: scf.if %[[VAL_6]] { -// CHECK: scf.for %[[VAL_30:.*]] = %[[VAL_7]] to %[[VAL_5]] step %[[VAL_8]] { -// CHECK: %[[VAL_31:.*]] = load %[[VAL_12]]{{\[}}%[[VAL_21]], %[[VAL_30]]] : memref<32x16xf32> +// CHECK: scf.if %[[VAL_5]] { +// CHECK: scf.for %[[VAL_30:.*]] = %[[VAL_6]] to %[[VAL_4]] step %[[VAL_7]] { +// CHECK: %[[VAL_31:.*]] = load %[[VAL_11]]{{\[}}%[[VAL_21]], %[[VAL_30]]] : memref<32x16xf32> // CHECK: store %[[VAL_31]], %[[VAL_13]]{{\[}}%[[VAL_21]], %[[VAL_30]]] : memref<32x16xf32> // CHECK: } // CHECK: } else { // CHECK: } // CHECK: } // CHECK: %[[VAL_32:.*]] = cmpi eq, %[[VAL_22]], %[[VAL_21]] : index -// CHECK: %[[VAL_33:.*]] = addi %[[VAL_20]], %[[VAL_8]] : index +// CHECK: %[[VAL_33:.*]] = addi %[[VAL_20]], %[[VAL_7]] : index // CHECK: %[[VAL_34:.*]] = select %[[VAL_32]], %[[VAL_33]], %[[VAL_20]] : index -// CHECK: %[[VAL_35:.*]] = addi %[[VAL_21]], %[[VAL_8]] : index +// CHECK: %[[VAL_35:.*]] = addi %[[VAL_21]], %[[VAL_7]] : index // CHECK: scf.yield %[[VAL_34]], %[[VAL_35]] : index, index // CHECK: } -// CHECK: scf.for %[[VAL_36:.*]] = %[[VAL_37:.*]]#1 to %[[VAL_4]] step %[[VAL_8]] { -// CHECK: scf.for %[[VAL_38:.*]] = %[[VAL_7]] to %[[VAL_5]] step %[[VAL_8]] { -// CHECK: %[[VAL_39:.*]] = load %[[VAL_12]]{{\[}}%[[VAL_36]], %[[VAL_38]]] : memref<32x16xf32> +// CHECK: scf.for %[[VAL_36:.*]] = %[[VAL_37:.*]]#1 to %[[VAL_3]] step %[[VAL_7]] { +// CHECK: scf.for %[[VAL_38:.*]] = %[[VAL_6]] to %[[VAL_4]] step %[[VAL_7]] { +// CHECK: %[[VAL_39:.*]] = load %[[VAL_11]]{{\[}}%[[VAL_36]], %[[VAL_38]]] : memref<32x16xf32> // CHECK: store %[[VAL_39]], %[[VAL_13]]{{\[}}%[[VAL_36]], %[[VAL_38]]] : memref<32x16xf32> // CHECK: } // CHECK: } @@ -286,24 +293,25 @@ // CHECK-SAME: %[[VAL_0:.*0]]: tensor<32x16xf32>, // CHECK-SAME: %[[VAL_1:.*1]]: tensor<32x16xf32>, // CHECK-SAME: %[[VAL_2:.*2]]: tensor<32x16xf32>) -> tensor<32x16xf32> { -// CHECK: %[[VAL_3:.*]] = constant 999 : index -// CHECK: %[[VAL_4:.*]] = constant 16 : index -// CHECK: %[[VAL_5:.*]] = constant 0 : index -// CHECK: %[[VAL_6:.*]] = constant 1 : index -// CHECK: %[[VAL_7:.*]] = alloca(%[[VAL_3]]) : memref -// CHECK: %[[VAL_8:.*]] = alloca(%[[VAL_3]]) : memref -// CHECK: %[[VAL_9:.*]] = alloca(%[[VAL_3]]) : memref -// CHECK: %[[VAL_10:.*]] = alloca() : memref<32x16xf32> -// CHECK: %[[VAL_11:.*]] = alloca() : memref<32x16xf32> -// CHECK: %[[VAL_12:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_5]]] : memref -// CHECK: %[[VAL_13:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_6]]] : memref -// CHECK: scf.for %[[VAL_14:.*]] = %[[VAL_12]] to %[[VAL_13]] step %[[VAL_6]] { -// CHECK: %[[VAL_15:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_14]]] : memref -// CHECK: scf.for %[[VAL_16:.*]] = %[[VAL_5]] to %[[VAL_4]] step %[[VAL_6]] { -// CHECK: %[[VAL_17:.*]] = muli %[[VAL_14]], %[[VAL_4]] : index +// CHECK: %[[VAL_3:.*]] = constant 16 : index +// CHECK: %[[VAL_4:.*]] = constant 0 : index +// CHECK: %[[VAL_5:.*]] = constant 1 : index +// CHECK: %[[VAL_6:.*]] = linalg.sparse_pointers %[[VAL_0]], %[[VAL_4]] : tensor<32x16xf32> into memref +// CHECK: %[[VAL_7:.*]] = linalg.sparse_indices %[[VAL_0]], %[[VAL_4]] : tensor<32x16xf32> into memref +// CHECK: %[[VAL_8:.*]] = linalg.sparse_values %[[VAL_0]] : tensor<32x16xf32> into memref +// CHECK: %[[VAL_9:.*]] = tensor_to_memref %[[VAL_1]] : memref<32x16xf32> +// CHECK: %[[VAL_10:.*]] = tensor_to_memref %[[VAL_2]] : memref<32x16xf32> +// CHECK: %[[VAL_11:.*]] = alloc() : memref<32x16xf32> +// CHECK: linalg.copy(%[[VAL_10]], %[[VAL_11]]) : memref<32x16xf32>, memref<32x16xf32> +// CHECK: %[[VAL_12:.*]] = load %[[VAL_6]]{{\[}}%[[VAL_4]]] : memref +// CHECK: %[[VAL_13:.*]] = load %[[VAL_6]]{{\[}}%[[VAL_5]]] : memref +// CHECK: scf.for %[[VAL_14:.*]] = %[[VAL_12]] to %[[VAL_13]] step %[[VAL_5]] { +// CHECK: %[[VAL_15:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_14]]] : memref +// CHECK: scf.for %[[VAL_16:.*]] = %[[VAL_4]] to %[[VAL_3]] step %[[VAL_5]] { +// CHECK: %[[VAL_17:.*]] = muli %[[VAL_14]], %[[VAL_3]] : index // CHECK: %[[VAL_18:.*]] = addi %[[VAL_17]], %[[VAL_16]] : index -// CHECK: %[[VAL_19:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_18]]] : memref -// CHECK: %[[VAL_20:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_15]], %[[VAL_16]]] : memref<32x16xf32> +// CHECK: %[[VAL_19:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_18]]] : memref +// CHECK: %[[VAL_20:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_15]], %[[VAL_16]]] : memref<32x16xf32> // CHECK: %[[VAL_21:.*]] = mulf %[[VAL_19]], %[[VAL_20]] : f32 // CHECK: store %[[VAL_21]], %[[VAL_11]]{{\[}}%[[VAL_15]], %[[VAL_16]]] : memref<32x16xf32> // CHECK: } @@ -341,79 +349,80 @@ // CHECK-SAME: %[[VAL_0:.*0]]: tensor<32x16xf32>, // CHECK-SAME: %[[VAL_1:.*1]]: tensor<32x16xf32>, // CHECK-SAME: %[[VAL_2:.*2]]: tensor<32x16xf32>) -> tensor<32x16xf32> { -// CHECK: %[[VAL_3:.*]] = constant 999 : index -// CHECK: %[[VAL_4:.*]] = constant 32 : index -// CHECK: %[[VAL_5:.*]] = constant 16 : index -// CHECK: %[[VAL_6:.*]] = constant true -// CHECK: %[[VAL_7:.*]] = constant 0 : index -// CHECK: %[[VAL_8:.*]] = constant 1 : index -// CHECK: %[[VAL_9:.*]] = alloca(%[[VAL_3]]) : memref -// CHECK: %[[VAL_10:.*]] = alloca(%[[VAL_3]]) : memref -// CHECK: %[[VAL_11:.*]] = alloca(%[[VAL_3]]) : memref -// CHECK: %[[VAL_12:.*]] = alloca(%[[VAL_3]]) : memref -// CHECK: %[[VAL_13:.*]] = alloca(%[[VAL_3]]) : memref -// CHECK: %[[VAL_14:.*]] = alloca() : memref<32x16xf32> -// CHECK: %[[VAL_15:.*]] = alloca() : memref<32x16xf32> -// CHECK: %[[VAL_16:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_7]]] : memref -// CHECK: %[[VAL_17:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_8]]] : memref -// CHECK: %[[VAL_18:.*]]:2 = scf.while (%[[VAL_19:.*]] = %[[VAL_16]], %[[VAL_20:.*]] = %[[VAL_7]]) : (index, index) -> (index, index) { +// CHECK: %[[VAL_3:.*]] = constant 32 : index +// CHECK: %[[VAL_4:.*]] = constant 16 : index +// CHECK: %[[VAL_5:.*]] = constant true +// CHECK: %[[VAL_6:.*]] = constant 0 : index +// CHECK: %[[VAL_7:.*]] = constant 1 : index +// CHECK: %[[VAL_8:.*]] = linalg.sparse_pointers %[[VAL_0]], %[[VAL_6]] : tensor<32x16xf32> into memref +// CHECK: %[[VAL_9:.*]] = linalg.sparse_indices %[[VAL_0]], %[[VAL_6]] : tensor<32x16xf32> into memref +// CHECK: %[[VAL_10:.*]] = linalg.sparse_pointers %[[VAL_0]], %[[VAL_7]] : tensor<32x16xf32> into memref +// CHECK: %[[VAL_11:.*]] = linalg.sparse_indices %[[VAL_0]], %[[VAL_7]] : tensor<32x16xf32> into memref +// CHECK: %[[VAL_12:.*]] = linalg.sparse_values %[[VAL_0]] : tensor<32x16xf32> into memref +// CHECK: %[[VAL_13:.*]] = tensor_to_memref %[[VAL_1]] : memref<32x16xf32> +// CHECK: %[[VAL_14:.*]] = tensor_to_memref %[[VAL_2]] : memref<32x16xf32> +// CHECK: %[[VAL_15:.*]] = alloc() : memref<32x16xf32> +// CHECK: linalg.copy(%[[VAL_14]], %[[VAL_15]]) : memref<32x16xf32>, memref<32x16xf32> +// CHECK: %[[VAL_16:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_6]]] : memref +// CHECK: %[[VAL_17:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_7]]] : memref +// CHECK: %[[VAL_18:.*]]:2 = scf.while (%[[VAL_19:.*]] = %[[VAL_16]], %[[VAL_20:.*]] = %[[VAL_6]]) : (index, index) -> (index, index) { // CHECK: %[[VAL_21:.*]] = cmpi ult, %[[VAL_19]], %[[VAL_17]] : index // CHECK: scf.condition(%[[VAL_21]]) %[[VAL_19]], %[[VAL_20]] : index, index // CHECK: } do { // CHECK: ^bb0(%[[VAL_22:.*]]: index, %[[VAL_23:.*]]: index): -// CHECK: %[[VAL_24:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_22]]] : memref +// CHECK: %[[VAL_24:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_22]]] : memref // CHECK: %[[VAL_25:.*]] = cmpi eq, %[[VAL_24]], %[[VAL_23]] : index // CHECK: scf.if %[[VAL_25]] { -// CHECK: %[[VAL_26:.*]] = load %[[VAL_11]]{{\[}}%[[VAL_22]]] : memref -// CHECK: %[[VAL_27:.*]] = addi %[[VAL_22]], %[[VAL_8]] : index -// CHECK: %[[VAL_28:.*]] = load %[[VAL_11]]{{\[}}%[[VAL_27]]] : memref -// CHECK: %[[VAL_29:.*]]:2 = scf.while (%[[VAL_30:.*]] = %[[VAL_26]], %[[VAL_31:.*]] = %[[VAL_7]]) : (index, index) -> (index, index) { +// CHECK: %[[VAL_26:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_22]]] : memref +// CHECK: %[[VAL_27:.*]] = addi %[[VAL_22]], %[[VAL_7]] : index +// CHECK: %[[VAL_28:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_27]]] : memref +// CHECK: %[[VAL_29:.*]]:2 = scf.while (%[[VAL_30:.*]] = %[[VAL_26]], %[[VAL_31:.*]] = %[[VAL_6]]) : (index, index) -> (index, index) { // CHECK: %[[VAL_32:.*]] = cmpi ult, %[[VAL_30]], %[[VAL_28]] : index // CHECK: scf.condition(%[[VAL_32]]) %[[VAL_30]], %[[VAL_31]] : index, index // CHECK: } do { // CHECK: ^bb0(%[[VAL_33:.*]]: index, %[[VAL_34:.*]]: index): -// CHECK: %[[VAL_35:.*]] = load %[[VAL_12]]{{\[}}%[[VAL_33]]] : memref +// CHECK: %[[VAL_35:.*]] = load %[[VAL_11]]{{\[}}%[[VAL_33]]] : memref // CHECK: %[[VAL_36:.*]] = cmpi eq, %[[VAL_35]], %[[VAL_34]] : index // CHECK: scf.if %[[VAL_36]] { -// CHECK: %[[VAL_37:.*]] = load %[[VAL_13]]{{\[}}%[[VAL_33]]] : memref -// CHECK: %[[VAL_38:.*]] = load %[[VAL_14]]{{\[}}%[[VAL_23]], %[[VAL_34]]] : memref<32x16xf32> +// CHECK: %[[VAL_37:.*]] = load %[[VAL_12]]{{\[}}%[[VAL_33]]] : memref +// CHECK: %[[VAL_38:.*]] = load %[[VAL_13]]{{\[}}%[[VAL_23]], %[[VAL_34]]] : memref<32x16xf32> // CHECK: %[[VAL_39:.*]] = addf %[[VAL_37]], %[[VAL_38]] : f32 // CHECK: store %[[VAL_39]], %[[VAL_15]]{{\[}}%[[VAL_23]], %[[VAL_34]]] : memref<32x16xf32> // CHECK: } else { -// CHECK: scf.if %[[VAL_6]] { -// CHECK: %[[VAL_40:.*]] = load %[[VAL_14]]{{\[}}%[[VAL_23]], %[[VAL_34]]] : memref<32x16xf32> +// CHECK: scf.if %[[VAL_5]] { +// CHECK: %[[VAL_40:.*]] = load %[[VAL_13]]{{\[}}%[[VAL_23]], %[[VAL_34]]] : memref<32x16xf32> // CHECK: store %[[VAL_40]], %[[VAL_15]]{{\[}}%[[VAL_23]], %[[VAL_34]]] : memref<32x16xf32> // CHECK: } else { // CHECK: } // CHECK: } // CHECK: %[[VAL_41:.*]] = cmpi eq, %[[VAL_35]], %[[VAL_34]] : index -// CHECK: %[[VAL_42:.*]] = addi %[[VAL_33]], %[[VAL_8]] : index +// CHECK: %[[VAL_42:.*]] = addi %[[VAL_33]], %[[VAL_7]] : index // CHECK: %[[VAL_43:.*]] = select %[[VAL_41]], %[[VAL_42]], %[[VAL_33]] : index -// CHECK: %[[VAL_44:.*]] = addi %[[VAL_34]], %[[VAL_8]] : index +// CHECK: %[[VAL_44:.*]] = addi %[[VAL_34]], %[[VAL_7]] : index // CHECK: scf.yield %[[VAL_43]], %[[VAL_44]] : index, index // CHECK: } -// CHECK: scf.for %[[VAL_45:.*]] = %[[VAL_46:.*]]#1 to %[[VAL_5]] step %[[VAL_8]] { -// CHECK: %[[VAL_47:.*]] = load %[[VAL_14]]{{\[}}%[[VAL_23]], %[[VAL_45]]] : memref<32x16xf32> +// CHECK: scf.for %[[VAL_45:.*]] = %[[VAL_46:.*]]#1 to %[[VAL_4]] step %[[VAL_7]] { +// CHECK: %[[VAL_47:.*]] = load %[[VAL_13]]{{\[}}%[[VAL_23]], %[[VAL_45]]] : memref<32x16xf32> // CHECK: store %[[VAL_47]], %[[VAL_15]]{{\[}}%[[VAL_23]], %[[VAL_45]]] : memref<32x16xf32> // CHECK: } // CHECK: } else { -// CHECK: scf.if %[[VAL_6]] { -// CHECK: scf.for %[[VAL_48:.*]] = %[[VAL_7]] to %[[VAL_5]] step %[[VAL_8]] { -// CHECK: %[[VAL_49:.*]] = load %[[VAL_14]]{{\[}}%[[VAL_23]], %[[VAL_48]]] : memref<32x16xf32> +// CHECK: scf.if %[[VAL_5]] { +// CHECK: scf.for %[[VAL_48:.*]] = %[[VAL_6]] to %[[VAL_4]] step %[[VAL_7]] { +// CHECK: %[[VAL_49:.*]] = load %[[VAL_13]]{{\[}}%[[VAL_23]], %[[VAL_48]]] : memref<32x16xf32> // CHECK: store %[[VAL_49]], %[[VAL_15]]{{\[}}%[[VAL_23]], %[[VAL_48]]] : memref<32x16xf32> // CHECK: } // CHECK: } else { // CHECK: } // CHECK: } // CHECK: %[[VAL_50:.*]] = cmpi eq, %[[VAL_24]], %[[VAL_23]] : index -// CHECK: %[[VAL_51:.*]] = addi %[[VAL_22]], %[[VAL_8]] : index +// CHECK: %[[VAL_51:.*]] = addi %[[VAL_22]], %[[VAL_7]] : index // CHECK: %[[VAL_52:.*]] = select %[[VAL_50]], %[[VAL_51]], %[[VAL_22]] : index -// CHECK: %[[VAL_53:.*]] = addi %[[VAL_23]], %[[VAL_8]] : index +// CHECK: %[[VAL_53:.*]] = addi %[[VAL_23]], %[[VAL_7]] : index // CHECK: scf.yield %[[VAL_52]], %[[VAL_53]] : index, index // CHECK: } -// CHECK: scf.for %[[VAL_54:.*]] = %[[VAL_55:.*]]#1 to %[[VAL_4]] step %[[VAL_8]] { -// CHECK: scf.for %[[VAL_56:.*]] = %[[VAL_7]] to %[[VAL_5]] step %[[VAL_8]] { -// CHECK: %[[VAL_57:.*]] = load %[[VAL_14]]{{\[}}%[[VAL_54]], %[[VAL_56]]] : memref<32x16xf32> +// CHECK: scf.for %[[VAL_54:.*]] = %[[VAL_55:.*]]#1 to %[[VAL_3]] step %[[VAL_7]] { +// CHECK: scf.for %[[VAL_56:.*]] = %[[VAL_6]] to %[[VAL_4]] step %[[VAL_7]] { +// CHECK: %[[VAL_57:.*]] = load %[[VAL_13]]{{\[}}%[[VAL_54]], %[[VAL_56]]] : memref<32x16xf32> // CHECK: store %[[VAL_57]], %[[VAL_15]]{{\[}}%[[VAL_54]], %[[VAL_56]]] : memref<32x16xf32> // CHECK: } // CHECK: } @@ -435,27 +444,28 @@ // CHECK-SAME: %[[VAL_0:.*0]]: tensor<32x16xf32>, // CHECK-SAME: %[[VAL_1:.*1]]: tensor<32x16xf32>, // CHECK-SAME: %[[VAL_2:.*2]]: tensor<32x16xf32>) -> tensor<32x16xf32> { -// CHECK: %[[VAL_3:.*]] = constant 999 : index -// CHECK: %[[VAL_4:.*]] = constant 0 : index -// CHECK: %[[VAL_5:.*]] = constant 1 : index -// CHECK: %[[VAL_6:.*]] = alloca(%[[VAL_3]]) : memref -// CHECK: %[[VAL_7:.*]] = alloca(%[[VAL_3]]) : memref -// CHECK: %[[VAL_8:.*]] = alloca(%[[VAL_3]]) : memref -// CHECK: %[[VAL_9:.*]] = alloca(%[[VAL_3]]) : memref -// CHECK: %[[VAL_10:.*]] = alloca(%[[VAL_3]]) : memref -// CHECK: %[[VAL_11:.*]] = alloca() : memref<32x16xf32> -// CHECK: %[[VAL_12:.*]] = alloca() : memref<32x16xf32> -// CHECK: %[[VAL_13:.*]] = load %[[VAL_6]]{{\[}}%[[VAL_4]]] : memref -// CHECK: %[[VAL_14:.*]] = load %[[VAL_6]]{{\[}}%[[VAL_5]]] : memref -// CHECK: scf.for %[[VAL_15:.*]] = %[[VAL_13]] to %[[VAL_14]] step %[[VAL_5]] { -// CHECK: %[[VAL_16:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_15]]] : memref -// CHECK: %[[VAL_17:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_15]]] : memref -// CHECK: %[[VAL_18:.*]] = addi %[[VAL_15]], %[[VAL_5]] : index -// CHECK: %[[VAL_19:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_18]]] : memref -// CHECK: scf.for %[[VAL_20:.*]] = %[[VAL_17]] to %[[VAL_19]] step %[[VAL_5]] { -// CHECK: %[[VAL_21:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_20]]] : memref -// CHECK: %[[VAL_22:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_20]]] : memref -// CHECK: %[[VAL_23:.*]] = load %[[VAL_11]]{{\[}}%[[VAL_16]], %[[VAL_21]]] : memref<32x16xf32> +// CHECK: %[[VAL_3:.*]] = constant 0 : index +// CHECK: %[[VAL_4:.*]] = constant 1 : index +// CHECK: %[[VAL_5:.*]] = linalg.sparse_pointers %[[VAL_0]], %[[VAL_3]] : tensor<32x16xf32> into memref +// CHECK: %[[VAL_6:.*]] = linalg.sparse_indices %[[VAL_0]], %[[VAL_3]] : tensor<32x16xf32> into memref +// CHECK: %[[VAL_7:.*]] = linalg.sparse_pointers %[[VAL_0]], %[[VAL_4]] : tensor<32x16xf32> into memref +// CHECK: %[[VAL_8:.*]] = linalg.sparse_indices %[[VAL_0]], %[[VAL_4]] : tensor<32x16xf32> into memref +// CHECK: %[[VAL_9:.*]] = linalg.sparse_values %[[VAL_0]] : tensor<32x16xf32> into memref +// CHECK: %[[VAL_10:.*]] = tensor_to_memref %[[VAL_1]] : memref<32x16xf32> +// CHECK: %[[VAL_11:.*]] = tensor_to_memref %[[VAL_2]] : memref<32x16xf32> +// CHECK: %[[VAL_12:.*]] = alloc() : memref<32x16xf32> +// CHECK: linalg.copy(%[[VAL_11]], %[[VAL_12]]) : memref<32x16xf32>, memref<32x16xf32> +// CHECK: %[[VAL_13:.*]] = load %[[VAL_5]]{{\[}}%[[VAL_3]]] : memref +// CHECK: %[[VAL_14:.*]] = load %[[VAL_5]]{{\[}}%[[VAL_4]]] : memref +// CHECK: scf.for %[[VAL_15:.*]] = %[[VAL_13]] to %[[VAL_14]] step %[[VAL_4]] { +// CHECK: %[[VAL_16:.*]] = load %[[VAL_6]]{{\[}}%[[VAL_15]]] : memref +// CHECK: %[[VAL_17:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_15]]] : memref +// CHECK: %[[VAL_18:.*]] = addi %[[VAL_15]], %[[VAL_4]] : index +// CHECK: %[[VAL_19:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_18]]] : memref +// CHECK: scf.for %[[VAL_20:.*]] = %[[VAL_17]] to %[[VAL_19]] step %[[VAL_4]] { +// CHECK: %[[VAL_21:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_20]]] : memref +// CHECK: %[[VAL_22:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_20]]] : memref +// CHECK: %[[VAL_23:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_16]], %[[VAL_21]]] : memref<32x16xf32> // CHECK: %[[VAL_24:.*]] = mulf %[[VAL_22]], %[[VAL_23]] : f32 // CHECK: store %[[VAL_24]], %[[VAL_12]]{{\[}}%[[VAL_16]], %[[VAL_21]]] : memref<32x16xf32> // CHECK: } @@ -493,24 +503,25 @@ // CHECK-SAME: %[[VAL_0:.*0]]: tensor<32x16xf32>, // CHECK-SAME: %[[VAL_1:.*1]]: tensor<32x16xf32>, // CHECK-SAME: %[[VAL_2:.*2]]: tensor<32x16xf32>) -> tensor<32x16xf32> { -// CHECK: %[[VAL_3:.*]] = constant 999 : index -// CHECK: %[[VAL_4:.*]] = constant 0 : index -// CHECK: %[[VAL_5:.*]] = constant 1 : index -// CHECK: %[[VAL_6:.*]] = alloca(%[[VAL_3]]) : memref -// CHECK: %[[VAL_7:.*]] = alloca(%[[VAL_3]]) : memref -// CHECK: %[[VAL_8:.*]] = alloca(%[[VAL_3]]) : memref -// CHECK: %[[VAL_9:.*]] = alloca(%[[VAL_3]]) : memref -// CHECK: %[[VAL_10:.*]] = alloca(%[[VAL_3]]) : memref -// CHECK: %[[VAL_11:.*]] = alloca(%[[VAL_3]]) : memref -// CHECK: %[[VAL_12:.*]] = alloca(%[[VAL_3]]) : memref -// CHECK: %[[VAL_13:.*]] = alloca(%[[VAL_3]]) : memref -// CHECK: %[[VAL_14:.*]] = alloca(%[[VAL_3]]) : memref -// CHECK: %[[VAL_15:.*]] = alloca(%[[VAL_3]]) : memref -// CHECK: %[[VAL_16:.*]] = alloca() : memref<32x16xf32> -// CHECK: %[[VAL_17:.*]] = load %[[VAL_6]]{{\[}}%[[VAL_4]]] : memref -// CHECK: %[[VAL_18:.*]] = load %[[VAL_6]]{{\[}}%[[VAL_5]]] : memref -// CHECK: %[[VAL_19:.*]] = load %[[VAL_11]]{{\[}}%[[VAL_4]]] : memref -// CHECK: %[[VAL_20:.*]] = load %[[VAL_11]]{{\[}}%[[VAL_5]]] : memref +// CHECK: %[[VAL_3:.*]] = constant 0 : index +// CHECK: %[[VAL_4:.*]] = constant 1 : index +// CHECK: %[[VAL_5:.*]] = linalg.sparse_pointers %[[VAL_0]], %[[VAL_3]] : tensor<32x16xf32> into memref +// CHECK: %[[VAL_6:.*]] = linalg.sparse_indices %[[VAL_0]], %[[VAL_3]] : tensor<32x16xf32> into memref +// CHECK: %[[VAL_7:.*]] = linalg.sparse_pointers %[[VAL_0]], %[[VAL_4]] : tensor<32x16xf32> into memref +// CHECK: %[[VAL_8:.*]] = linalg.sparse_indices %[[VAL_0]], %[[VAL_4]] : tensor<32x16xf32> into memref +// CHECK: %[[VAL_9:.*]] = linalg.sparse_values %[[VAL_0]] : tensor<32x16xf32> into memref +// CHECK: %[[VAL_10:.*]] = linalg.sparse_pointers %[[VAL_1]], %[[VAL_3]] : tensor<32x16xf32> into memref +// CHECK: %[[VAL_11:.*]] = linalg.sparse_indices %[[VAL_1]], %[[VAL_3]] : tensor<32x16xf32> into memref +// CHECK: %[[VAL_12:.*]] = linalg.sparse_pointers %[[VAL_1]], %[[VAL_4]] : tensor<32x16xf32> into memref +// CHECK: %[[VAL_13:.*]] = linalg.sparse_indices %[[VAL_1]], %[[VAL_4]] : tensor<32x16xf32> into memref +// CHECK: %[[VAL_14:.*]] = linalg.sparse_values %[[VAL_1]] : tensor<32x16xf32> into memref +// CHECK: %[[VAL_15:.*]] = tensor_to_memref %[[VAL_2]] : memref<32x16xf32> +// CHECK: %[[VAL_16:.*]] = alloc() : memref<32x16xf32> +// CHECK: linalg.copy(%[[VAL_15]], %[[VAL_16]]) : memref<32x16xf32>, memref<32x16xf32> +// CHECK: %[[VAL_17:.*]] = load %[[VAL_5]]{{\[}}%[[VAL_3]]] : memref +// CHECK: %[[VAL_18:.*]] = load %[[VAL_5]]{{\[}}%[[VAL_4]]] : memref +// CHECK: %[[VAL_19:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_3]]] : memref +// CHECK: %[[VAL_20:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_4]]] : memref // CHECK: %[[VAL_21:.*]]:2 = scf.while (%[[VAL_22:.*]] = %[[VAL_17]], %[[VAL_23:.*]] = %[[VAL_19]]) : (index, index) -> (index, index) { // CHECK: %[[VAL_24:.*]] = cmpi ult, %[[VAL_22]], %[[VAL_18]] : index // CHECK: %[[VAL_25:.*]] = cmpi ult, %[[VAL_23]], %[[VAL_20]] : index @@ -518,20 +529,20 @@ // CHECK: scf.condition(%[[VAL_26]]) %[[VAL_22]], %[[VAL_23]] : index, index // CHECK: } do { // CHECK: ^bb0(%[[VAL_27:.*]]: index, %[[VAL_28:.*]]: index): -// CHECK: %[[VAL_29:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_27]]] : memref -// CHECK: %[[VAL_30:.*]] = load %[[VAL_12]]{{\[}}%[[VAL_28]]] : memref +// CHECK: %[[VAL_29:.*]] = load %[[VAL_6]]{{\[}}%[[VAL_27]]] : memref +// CHECK: %[[VAL_30:.*]] = load %[[VAL_11]]{{\[}}%[[VAL_28]]] : memref // CHECK: %[[VAL_31:.*]] = cmpi ult, %[[VAL_30]], %[[VAL_29]] : index // CHECK: %[[VAL_32:.*]] = select %[[VAL_31]], %[[VAL_30]], %[[VAL_29]] : index // CHECK: %[[VAL_33:.*]] = cmpi eq, %[[VAL_29]], %[[VAL_32]] : index // CHECK: %[[VAL_34:.*]] = cmpi eq, %[[VAL_30]], %[[VAL_32]] : index // CHECK: %[[VAL_35:.*]] = and %[[VAL_33]], %[[VAL_34]] : i1 // CHECK: scf.if %[[VAL_35]] { -// CHECK: %[[VAL_36:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_27]]] : memref -// CHECK: %[[VAL_37:.*]] = addi %[[VAL_27]], %[[VAL_5]] : index -// CHECK: %[[VAL_38:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_37]]] : memref -// CHECK: %[[VAL_39:.*]] = load %[[VAL_13]]{{\[}}%[[VAL_28]]] : memref -// CHECK: %[[VAL_40:.*]] = addi %[[VAL_28]], %[[VAL_5]] : index -// CHECK: %[[VAL_41:.*]] = load %[[VAL_13]]{{\[}}%[[VAL_40]]] : memref +// CHECK: %[[VAL_36:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_27]]] : memref +// CHECK: %[[VAL_37:.*]] = addi %[[VAL_27]], %[[VAL_4]] : index +// CHECK: %[[VAL_38:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_37]]] : memref +// CHECK: %[[VAL_39:.*]] = load %[[VAL_12]]{{\[}}%[[VAL_28]]] : memref +// CHECK: %[[VAL_40:.*]] = addi %[[VAL_28]], %[[VAL_4]] : index +// CHECK: %[[VAL_41:.*]] = load %[[VAL_12]]{{\[}}%[[VAL_40]]] : memref // CHECK: %[[VAL_42:.*]]:2 = scf.while (%[[VAL_43:.*]] = %[[VAL_36]], %[[VAL_44:.*]] = %[[VAL_39]]) : (index, index) -> (index, index) { // CHECK: %[[VAL_45:.*]] = cmpi ult, %[[VAL_43]], %[[VAL_38]] : index // CHECK: %[[VAL_46:.*]] = cmpi ult, %[[VAL_44]], %[[VAL_41]] : index @@ -539,70 +550,70 @@ // CHECK: scf.condition(%[[VAL_47]]) %[[VAL_43]], %[[VAL_44]] : index, index // CHECK: } do { // CHECK: ^bb0(%[[VAL_48:.*]]: index, %[[VAL_49:.*]]: index): -// CHECK: %[[VAL_50:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_48]]] : memref -// CHECK: %[[VAL_51:.*]] = load %[[VAL_14]]{{\[}}%[[VAL_49]]] : memref +// CHECK: %[[VAL_50:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_48]]] : memref +// CHECK: %[[VAL_51:.*]] = load %[[VAL_13]]{{\[}}%[[VAL_49]]] : memref // CHECK: %[[VAL_52:.*]] = cmpi ult, %[[VAL_51]], %[[VAL_50]] : index // CHECK: %[[VAL_53:.*]] = select %[[VAL_52]], %[[VAL_51]], %[[VAL_50]] : index // CHECK: %[[VAL_54:.*]] = cmpi eq, %[[VAL_50]], %[[VAL_53]] : index // CHECK: %[[VAL_55:.*]] = cmpi eq, %[[VAL_51]], %[[VAL_53]] : index // CHECK: %[[VAL_56:.*]] = and %[[VAL_54]], %[[VAL_55]] : i1 // CHECK: scf.if %[[VAL_56]] { -// CHECK: %[[VAL_57:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_48]]] : memref -// CHECK: %[[VAL_58:.*]] = load %[[VAL_15]]{{\[}}%[[VAL_49]]] : memref +// CHECK: %[[VAL_57:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_48]]] : memref +// CHECK: %[[VAL_58:.*]] = load %[[VAL_14]]{{\[}}%[[VAL_49]]] : memref // CHECK: %[[VAL_59:.*]] = addf %[[VAL_57]], %[[VAL_58]] : f32 // CHECK: store %[[VAL_59]], %[[VAL_16]]{{\[}}%[[VAL_32]], %[[VAL_53]]] : memref<32x16xf32> // CHECK: } else { // CHECK: %[[VAL_60:.*]] = cmpi eq, %[[VAL_50]], %[[VAL_53]] : index // CHECK: scf.if %[[VAL_60]] { -// CHECK: %[[VAL_61:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_48]]] : memref +// CHECK: %[[VAL_61:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_48]]] : memref // CHECK: store %[[VAL_61]], %[[VAL_16]]{{\[}}%[[VAL_32]], %[[VAL_53]]] : memref<32x16xf32> // CHECK: } else { // CHECK: %[[VAL_62:.*]] = cmpi eq, %[[VAL_51]], %[[VAL_53]] : index // CHECK: scf.if %[[VAL_62]] { -// CHECK: %[[VAL_63:.*]] = load %[[VAL_15]]{{\[}}%[[VAL_49]]] : memref +// CHECK: %[[VAL_63:.*]] = load %[[VAL_14]]{{\[}}%[[VAL_49]]] : memref // CHECK: store %[[VAL_63]], %[[VAL_16]]{{\[}}%[[VAL_32]], %[[VAL_53]]] : memref<32x16xf32> // CHECK: } else { // CHECK: } // CHECK: } // CHECK: } // CHECK: %[[VAL_64:.*]] = cmpi eq, %[[VAL_50]], %[[VAL_53]] : index -// CHECK: %[[VAL_65:.*]] = addi %[[VAL_48]], %[[VAL_5]] : index +// CHECK: %[[VAL_65:.*]] = addi %[[VAL_48]], %[[VAL_4]] : index // CHECK: %[[VAL_66:.*]] = select %[[VAL_64]], %[[VAL_65]], %[[VAL_48]] : index // CHECK: %[[VAL_67:.*]] = cmpi eq, %[[VAL_51]], %[[VAL_53]] : index -// CHECK: %[[VAL_68:.*]] = addi %[[VAL_49]], %[[VAL_5]] : index +// CHECK: %[[VAL_68:.*]] = addi %[[VAL_49]], %[[VAL_4]] : index // CHECK: %[[VAL_69:.*]] = select %[[VAL_67]], %[[VAL_68]], %[[VAL_49]] : index // CHECK: scf.yield %[[VAL_66]], %[[VAL_69]] : index, index // CHECK: } -// CHECK: scf.for %[[VAL_70:.*]] = %[[VAL_71:.*]]#0 to %[[VAL_38]] step %[[VAL_5]] { -// CHECK: %[[VAL_72:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_70]]] : memref -// CHECK: %[[VAL_73:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_70]]] : memref +// CHECK: scf.for %[[VAL_70:.*]] = %[[VAL_71:.*]]#0 to %[[VAL_38]] step %[[VAL_4]] { +// CHECK: %[[VAL_72:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_70]]] : memref +// CHECK: %[[VAL_73:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_70]]] : memref // CHECK: store %[[VAL_73]], %[[VAL_16]]{{\[}}%[[VAL_32]], %[[VAL_72]]] : memref<32x16xf32> // CHECK: } -// CHECK: scf.for %[[VAL_74:.*]] = %[[VAL_75:.*]]#1 to %[[VAL_41]] step %[[VAL_5]] { -// CHECK: %[[VAL_76:.*]] = load %[[VAL_14]]{{\[}}%[[VAL_74]]] : memref -// CHECK: %[[VAL_77:.*]] = load %[[VAL_15]]{{\[}}%[[VAL_74]]] : memref +// CHECK: scf.for %[[VAL_74:.*]] = %[[VAL_75:.*]]#1 to %[[VAL_41]] step %[[VAL_4]] { +// CHECK: %[[VAL_76:.*]] = load %[[VAL_13]]{{\[}}%[[VAL_74]]] : memref +// CHECK: %[[VAL_77:.*]] = load %[[VAL_14]]{{\[}}%[[VAL_74]]] : memref // CHECK: store %[[VAL_77]], %[[VAL_16]]{{\[}}%[[VAL_32]], %[[VAL_76]]] : memref<32x16xf32> // CHECK: } // CHECK: } else { // CHECK: %[[VAL_78:.*]] = cmpi eq, %[[VAL_29]], %[[VAL_32]] : index // CHECK: scf.if %[[VAL_78]] { -// CHECK: %[[VAL_79:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_27]]] : memref -// CHECK: %[[VAL_80:.*]] = addi %[[VAL_27]], %[[VAL_5]] : index -// CHECK: %[[VAL_81:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_80]]] : memref -// CHECK: scf.for %[[VAL_82:.*]] = %[[VAL_79]] to %[[VAL_81]] step %[[VAL_5]] { -// CHECK: %[[VAL_83:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_82]]] : memref -// CHECK: %[[VAL_84:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_82]]] : memref +// CHECK: %[[VAL_79:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_27]]] : memref +// CHECK: %[[VAL_80:.*]] = addi %[[VAL_27]], %[[VAL_4]] : index +// CHECK: %[[VAL_81:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_80]]] : memref +// CHECK: scf.for %[[VAL_82:.*]] = %[[VAL_79]] to %[[VAL_81]] step %[[VAL_4]] { +// CHECK: %[[VAL_83:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_82]]] : memref +// CHECK: %[[VAL_84:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_82]]] : memref // CHECK: store %[[VAL_84]], %[[VAL_16]]{{\[}}%[[VAL_32]], %[[VAL_83]]] : memref<32x16xf32> // CHECK: } // CHECK: } else { // CHECK: %[[VAL_85:.*]] = cmpi eq, %[[VAL_30]], %[[VAL_32]] : index // CHECK: scf.if %[[VAL_85]] { -// CHECK: %[[VAL_86:.*]] = load %[[VAL_13]]{{\[}}%[[VAL_28]]] : memref -// CHECK: %[[VAL_87:.*]] = addi %[[VAL_28]], %[[VAL_5]] : index -// CHECK: %[[VAL_88:.*]] = load %[[VAL_13]]{{\[}}%[[VAL_87]]] : memref -// CHECK: scf.for %[[VAL_89:.*]] = %[[VAL_86]] to %[[VAL_88]] step %[[VAL_5]] { -// CHECK: %[[VAL_90:.*]] = load %[[VAL_14]]{{\[}}%[[VAL_89]]] : memref -// CHECK: %[[VAL_91:.*]] = load %[[VAL_15]]{{\[}}%[[VAL_89]]] : memref +// CHECK: %[[VAL_86:.*]] = load %[[VAL_12]]{{\[}}%[[VAL_28]]] : memref +// CHECK: %[[VAL_87:.*]] = addi %[[VAL_28]], %[[VAL_4]] : index +// CHECK: %[[VAL_88:.*]] = load %[[VAL_12]]{{\[}}%[[VAL_87]]] : memref +// CHECK: scf.for %[[VAL_89:.*]] = %[[VAL_86]] to %[[VAL_88]] step %[[VAL_4]] { +// CHECK: %[[VAL_90:.*]] = load %[[VAL_13]]{{\[}}%[[VAL_89]]] : memref +// CHECK: %[[VAL_91:.*]] = load %[[VAL_14]]{{\[}}%[[VAL_89]]] : memref // CHECK: store %[[VAL_91]], %[[VAL_16]]{{\[}}%[[VAL_32]], %[[VAL_90]]] : memref<32x16xf32> // CHECK: } // CHECK: } else { @@ -610,32 +621,32 @@ // CHECK: } // CHECK: } // CHECK: %[[VAL_92:.*]] = cmpi eq, %[[VAL_29]], %[[VAL_32]] : index -// CHECK: %[[VAL_93:.*]] = addi %[[VAL_27]], %[[VAL_5]] : index +// CHECK: %[[VAL_93:.*]] = addi %[[VAL_27]], %[[VAL_4]] : index // CHECK: %[[VAL_94:.*]] = select %[[VAL_92]], %[[VAL_93]], %[[VAL_27]] : index // CHECK: %[[VAL_95:.*]] = cmpi eq, %[[VAL_30]], %[[VAL_32]] : index -// CHECK: %[[VAL_96:.*]] = addi %[[VAL_28]], %[[VAL_5]] : index +// CHECK: %[[VAL_96:.*]] = addi %[[VAL_28]], %[[VAL_4]] : index // CHECK: %[[VAL_97:.*]] = select %[[VAL_95]], %[[VAL_96]], %[[VAL_28]] : index // CHECK: scf.yield %[[VAL_94]], %[[VAL_97]] : index, index // CHECK: } -// CHECK: scf.for %[[VAL_98:.*]] = %[[VAL_99:.*]]#0 to %[[VAL_18]] step %[[VAL_5]] { -// CHECK: %[[VAL_100:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_98]]] : memref -// CHECK: %[[VAL_101:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_98]]] : memref -// CHECK: %[[VAL_102:.*]] = addi %[[VAL_98]], %[[VAL_5]] : index -// CHECK: %[[VAL_103:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_102]]] : memref -// CHECK: scf.for %[[VAL_104:.*]] = %[[VAL_101]] to %[[VAL_103]] step %[[VAL_5]] { -// CHECK: %[[VAL_105:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_104]]] : memref -// CHECK: %[[VAL_106:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_104]]] : memref +// CHECK: scf.for %[[VAL_98:.*]] = %[[VAL_99:.*]]#0 to %[[VAL_18]] step %[[VAL_4]] { +// CHECK: %[[VAL_100:.*]] = load %[[VAL_6]]{{\[}}%[[VAL_98]]] : memref +// CHECK: %[[VAL_101:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_98]]] : memref +// CHECK: %[[VAL_102:.*]] = addi %[[VAL_98]], %[[VAL_4]] : index +// CHECK: %[[VAL_103:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_102]]] : memref +// CHECK: scf.for %[[VAL_104:.*]] = %[[VAL_101]] to %[[VAL_103]] step %[[VAL_4]] { +// CHECK: %[[VAL_105:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_104]]] : memref +// CHECK: %[[VAL_106:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_104]]] : memref // CHECK: store %[[VAL_106]], %[[VAL_16]]{{\[}}%[[VAL_100]], %[[VAL_105]]] : memref<32x16xf32> // CHECK: } // CHECK: } -// CHECK: scf.for %[[VAL_107:.*]] = %[[VAL_108:.*]]#1 to %[[VAL_20]] step %[[VAL_5]] { -// CHECK: %[[VAL_109:.*]] = load %[[VAL_12]]{{\[}}%[[VAL_107]]] : memref -// CHECK: %[[VAL_110:.*]] = load %[[VAL_13]]{{\[}}%[[VAL_107]]] : memref -// CHECK: %[[VAL_111:.*]] = addi %[[VAL_107]], %[[VAL_5]] : index -// CHECK: %[[VAL_112:.*]] = load %[[VAL_13]]{{\[}}%[[VAL_111]]] : memref -// CHECK: scf.for %[[VAL_113:.*]] = %[[VAL_110]] to %[[VAL_112]] step %[[VAL_5]] { -// CHECK: %[[VAL_114:.*]] = load %[[VAL_14]]{{\[}}%[[VAL_113]]] : memref -// CHECK: %[[VAL_115:.*]] = load %[[VAL_15]]{{\[}}%[[VAL_113]]] : memref +// CHECK: scf.for %[[VAL_107:.*]] = %[[VAL_108:.*]]#1 to %[[VAL_20]] step %[[VAL_4]] { +// CHECK: %[[VAL_109:.*]] = load %[[VAL_11]]{{\[}}%[[VAL_107]]] : memref +// CHECK: %[[VAL_110:.*]] = load %[[VAL_12]]{{\[}}%[[VAL_107]]] : memref +// CHECK: %[[VAL_111:.*]] = addi %[[VAL_107]], %[[VAL_4]] : index +// CHECK: %[[VAL_112:.*]] = load %[[VAL_12]]{{\[}}%[[VAL_111]]] : memref +// CHECK: scf.for %[[VAL_113:.*]] = %[[VAL_110]] to %[[VAL_112]] step %[[VAL_4]] { +// CHECK: %[[VAL_114:.*]] = load %[[VAL_13]]{{\[}}%[[VAL_113]]] : memref +// CHECK: %[[VAL_115:.*]] = load %[[VAL_14]]{{\[}}%[[VAL_113]]] : memref // CHECK: store %[[VAL_115]], %[[VAL_16]]{{\[}}%[[VAL_109]], %[[VAL_114]]] : memref<32x16xf32> // CHECK: } // CHECK: } @@ -657,24 +668,25 @@ // CHECK-SAME: %[[VAL_0:.*0]]: tensor<32x16xf32>, // CHECK-SAME: %[[VAL_1:.*1]]: tensor<32x16xf32>, // CHECK-SAME: %[[VAL_2:.*2]]: tensor<32x16xf32>) -> tensor<32x16xf32> { -// CHECK: %[[VAL_3:.*]] = constant 999 : index -// CHECK: %[[VAL_4:.*]] = constant 0 : index -// CHECK: %[[VAL_5:.*]] = constant 1 : index -// CHECK: %[[VAL_6:.*]] = alloca(%[[VAL_3]]) : memref -// CHECK: %[[VAL_7:.*]] = alloca(%[[VAL_3]]) : memref -// CHECK: %[[VAL_8:.*]] = alloca(%[[VAL_3]]) : memref -// CHECK: %[[VAL_9:.*]] = alloca(%[[VAL_3]]) : memref -// CHECK: %[[VAL_10:.*]] = alloca(%[[VAL_3]]) : memref -// CHECK: %[[VAL_11:.*]] = alloca(%[[VAL_3]]) : memref -// CHECK: %[[VAL_12:.*]] = alloca(%[[VAL_3]]) : memref -// CHECK: %[[VAL_13:.*]] = alloca(%[[VAL_3]]) : memref -// CHECK: %[[VAL_14:.*]] = alloca(%[[VAL_3]]) : memref -// CHECK: %[[VAL_15:.*]] = alloca(%[[VAL_3]]) : memref -// CHECK: %[[VAL_16:.*]] = alloca() : memref<32x16xf32> -// CHECK: %[[VAL_17:.*]] = load %[[VAL_6]]{{\[}}%[[VAL_4]]] : memref -// CHECK: %[[VAL_18:.*]] = load %[[VAL_6]]{{\[}}%[[VAL_5]]] : memref -// CHECK: %[[VAL_19:.*]] = load %[[VAL_11]]{{\[}}%[[VAL_4]]] : memref -// CHECK: %[[VAL_20:.*]] = load %[[VAL_11]]{{\[}}%[[VAL_5]]] : memref +// CHECK: %[[VAL_3:.*]] = constant 0 : index +// CHECK: %[[VAL_4:.*]] = constant 1 : index +// CHECK: %[[VAL_5:.*]] = linalg.sparse_pointers %[[VAL_0]], %[[VAL_3]] : tensor<32x16xf32> into memref +// CHECK: %[[VAL_6:.*]] = linalg.sparse_indices %[[VAL_0]], %[[VAL_3]] : tensor<32x16xf32> into memref +// CHECK: %[[VAL_7:.*]] = linalg.sparse_pointers %[[VAL_0]], %[[VAL_4]] : tensor<32x16xf32> into memref +// CHECK: %[[VAL_8:.*]] = linalg.sparse_indices %[[VAL_0]], %[[VAL_4]] : tensor<32x16xf32> into memref +// CHECK: %[[VAL_9:.*]] = linalg.sparse_values %[[VAL_0]] : tensor<32x16xf32> into memref +// CHECK: %[[VAL_10:.*]] = linalg.sparse_pointers %[[VAL_1]], %[[VAL_3]] : tensor<32x16xf32> into memref +// CHECK: %[[VAL_11:.*]] = linalg.sparse_indices %[[VAL_1]], %[[VAL_3]] : tensor<32x16xf32> into memref +// CHECK: %[[VAL_12:.*]] = linalg.sparse_pointers %[[VAL_1]], %[[VAL_4]] : tensor<32x16xf32> into memref +// CHECK: %[[VAL_13:.*]] = linalg.sparse_indices %[[VAL_1]], %[[VAL_4]] : tensor<32x16xf32> into memref +// CHECK: %[[VAL_14:.*]] = linalg.sparse_values %[[VAL_1]] : tensor<32x16xf32> into memref +// CHECK: %[[VAL_15:.*]] = tensor_to_memref %[[VAL_2]] : memref<32x16xf32> +// CHECK: %[[VAL_16:.*]] = alloc() : memref<32x16xf32> +// CHECK: linalg.copy(%[[VAL_15]], %[[VAL_16]]) : memref<32x16xf32>, memref<32x16xf32> +// CHECK: %[[VAL_17:.*]] = load %[[VAL_5]]{{\[}}%[[VAL_3]]] : memref +// CHECK: %[[VAL_18:.*]] = load %[[VAL_5]]{{\[}}%[[VAL_4]]] : memref +// CHECK: %[[VAL_19:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_3]]] : memref +// CHECK: %[[VAL_20:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_4]]] : memref // CHECK: %[[VAL_21:.*]]:2 = scf.while (%[[VAL_22:.*]] = %[[VAL_17]], %[[VAL_23:.*]] = %[[VAL_19]]) : (index, index) -> (index, index) { // CHECK: %[[VAL_24:.*]] = cmpi ult, %[[VAL_22]], %[[VAL_18]] : index // CHECK: %[[VAL_25:.*]] = cmpi ult, %[[VAL_23]], %[[VAL_20]] : index @@ -682,20 +694,20 @@ // CHECK: scf.condition(%[[VAL_26]]) %[[VAL_22]], %[[VAL_23]] : index, index // CHECK: } do { // CHECK: ^bb0(%[[VAL_27:.*]]: index, %[[VAL_28:.*]]: index): -// CHECK: %[[VAL_29:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_27]]] : memref -// CHECK: %[[VAL_30:.*]] = load %[[VAL_12]]{{\[}}%[[VAL_28]]] : memref +// CHECK: %[[VAL_29:.*]] = load %[[VAL_6]]{{\[}}%[[VAL_27]]] : memref +// CHECK: %[[VAL_30:.*]] = load %[[VAL_11]]{{\[}}%[[VAL_28]]] : memref // CHECK: %[[VAL_31:.*]] = cmpi ult, %[[VAL_30]], %[[VAL_29]] : index // CHECK: %[[VAL_32:.*]] = select %[[VAL_31]], %[[VAL_30]], %[[VAL_29]] : index // CHECK: %[[VAL_33:.*]] = cmpi eq, %[[VAL_29]], %[[VAL_32]] : index // CHECK: %[[VAL_34:.*]] = cmpi eq, %[[VAL_30]], %[[VAL_32]] : index // CHECK: %[[VAL_35:.*]] = and %[[VAL_33]], %[[VAL_34]] : i1 // CHECK: scf.if %[[VAL_35]] { -// CHECK: %[[VAL_36:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_27]]] : memref -// CHECK: %[[VAL_37:.*]] = addi %[[VAL_27]], %[[VAL_5]] : index -// CHECK: %[[VAL_38:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_37]]] : memref -// CHECK: %[[VAL_39:.*]] = load %[[VAL_13]]{{\[}}%[[VAL_28]]] : memref -// CHECK: %[[VAL_40:.*]] = addi %[[VAL_28]], %[[VAL_5]] : index -// CHECK: %[[VAL_41:.*]] = load %[[VAL_13]]{{\[}}%[[VAL_40]]] : memref +// CHECK: %[[VAL_36:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_27]]] : memref +// CHECK: %[[VAL_37:.*]] = addi %[[VAL_27]], %[[VAL_4]] : index +// CHECK: %[[VAL_38:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_37]]] : memref +// CHECK: %[[VAL_39:.*]] = load %[[VAL_12]]{{\[}}%[[VAL_28]]] : memref +// CHECK: %[[VAL_40:.*]] = addi %[[VAL_28]], %[[VAL_4]] : index +// CHECK: %[[VAL_41:.*]] = load %[[VAL_12]]{{\[}}%[[VAL_40]]] : memref // CHECK: %[[VAL_42:.*]]:2 = scf.while (%[[VAL_43:.*]] = %[[VAL_36]], %[[VAL_44:.*]] = %[[VAL_39]]) : (index, index) -> (index, index) { // CHECK: %[[VAL_45:.*]] = cmpi ult, %[[VAL_43]], %[[VAL_38]] : index // CHECK: %[[VAL_46:.*]] = cmpi ult, %[[VAL_44]], %[[VAL_41]] : index @@ -703,35 +715,35 @@ // CHECK: scf.condition(%[[VAL_47]]) %[[VAL_43]], %[[VAL_44]] : index, index // CHECK: } do { // CHECK: ^bb0(%[[VAL_48:.*]]: index, %[[VAL_49:.*]]: index): -// CHECK: %[[VAL_50:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_48]]] : memref -// CHECK: %[[VAL_51:.*]] = load %[[VAL_14]]{{\[}}%[[VAL_49]]] : memref +// CHECK: %[[VAL_50:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_48]]] : memref +// CHECK: %[[VAL_51:.*]] = load %[[VAL_13]]{{\[}}%[[VAL_49]]] : memref // CHECK: %[[VAL_52:.*]] = cmpi ult, %[[VAL_51]], %[[VAL_50]] : index // CHECK: %[[VAL_53:.*]] = select %[[VAL_52]], %[[VAL_51]], %[[VAL_50]] : index // CHECK: %[[VAL_54:.*]] = cmpi eq, %[[VAL_50]], %[[VAL_53]] : index // CHECK: %[[VAL_55:.*]] = cmpi eq, %[[VAL_51]], %[[VAL_53]] : index // CHECK: %[[VAL_56:.*]] = and %[[VAL_54]], %[[VAL_55]] : i1 // CHECK: scf.if %[[VAL_56]] { -// CHECK: %[[VAL_57:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_48]]] : memref -// CHECK: %[[VAL_58:.*]] = load %[[VAL_15]]{{\[}}%[[VAL_49]]] : memref +// CHECK: %[[VAL_57:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_48]]] : memref +// CHECK: %[[VAL_58:.*]] = load %[[VAL_14]]{{\[}}%[[VAL_49]]] : memref // CHECK: %[[VAL_59:.*]] = mulf %[[VAL_57]], %[[VAL_58]] : f32 // CHECK: store %[[VAL_59]], %[[VAL_16]]{{\[}}%[[VAL_32]], %[[VAL_53]]] : memref<32x16xf32> // CHECK: } else { // CHECK: } // CHECK: %[[VAL_60:.*]] = cmpi eq, %[[VAL_50]], %[[VAL_53]] : index -// CHECK: %[[VAL_61:.*]] = addi %[[VAL_48]], %[[VAL_5]] : index +// CHECK: %[[VAL_61:.*]] = addi %[[VAL_48]], %[[VAL_4]] : index // CHECK: %[[VAL_62:.*]] = select %[[VAL_60]], %[[VAL_61]], %[[VAL_48]] : index // CHECK: %[[VAL_63:.*]] = cmpi eq, %[[VAL_51]], %[[VAL_53]] : index -// CHECK: %[[VAL_64:.*]] = addi %[[VAL_49]], %[[VAL_5]] : index +// CHECK: %[[VAL_64:.*]] = addi %[[VAL_49]], %[[VAL_4]] : index // CHECK: %[[VAL_65:.*]] = select %[[VAL_63]], %[[VAL_64]], %[[VAL_49]] : index // CHECK: scf.yield %[[VAL_62]], %[[VAL_65]] : index, index // CHECK: } // CHECK: } else { // CHECK: } // CHECK: %[[VAL_66:.*]] = cmpi eq, %[[VAL_29]], %[[VAL_32]] : index -// CHECK: %[[VAL_67:.*]] = addi %[[VAL_27]], %[[VAL_5]] : index +// CHECK: %[[VAL_67:.*]] = addi %[[VAL_27]], %[[VAL_4]] : index // CHECK: %[[VAL_68:.*]] = select %[[VAL_66]], %[[VAL_67]], %[[VAL_27]] : index // CHECK: %[[VAL_69:.*]] = cmpi eq, %[[VAL_30]], %[[VAL_32]] : index -// CHECK: %[[VAL_70:.*]] = addi %[[VAL_28]], %[[VAL_5]] : index +// CHECK: %[[VAL_70:.*]] = addi %[[VAL_28]], %[[VAL_4]] : index // CHECK: %[[VAL_71:.*]] = select %[[VAL_69]], %[[VAL_70]], %[[VAL_28]] : index // CHECK: scf.yield %[[VAL_68]], %[[VAL_71]] : index, index // CHECK: } @@ -768,24 +780,25 @@ // CHECK-SAME: %[[VAL_0:.*0]]: tensor<32x16xf32>, // CHECK-SAME: %[[VAL_1:.*1]]: tensor<32x16xf32>, // CHECK-SAME: %[[VAL_2:.*2]]: tensor<32x16xf32>) -> tensor<32x16xf32> { -// CHECK: %[[VAL_3:.*]] = constant 999 : index -// CHECK: %[[VAL_4:.*]] = constant 0 : index -// CHECK: %[[VAL_5:.*]] = constant 1 : index -// CHECK: %[[VAL_6:.*]] = alloca(%[[VAL_3]]) : memref -// CHECK: %[[VAL_7:.*]] = alloca(%[[VAL_3]]) : memref -// CHECK: %[[VAL_8:.*]] = alloca(%[[VAL_3]]) : memref -// CHECK: %[[VAL_9:.*]] = alloca(%[[VAL_3]]) : memref -// CHECK: %[[VAL_10:.*]] = alloca(%[[VAL_3]]) : memref -// CHECK: %[[VAL_11:.*]] = alloca(%[[VAL_3]]) : memref -// CHECK: %[[VAL_12:.*]] = alloca(%[[VAL_3]]) : memref -// CHECK: %[[VAL_13:.*]] = alloca(%[[VAL_3]]) : memref -// CHECK: %[[VAL_14:.*]] = alloca(%[[VAL_3]]) : memref -// CHECK: %[[VAL_15:.*]] = alloca(%[[VAL_3]]) : memref -// CHECK: %[[VAL_16:.*]] = alloca() : memref<32x16xf32> -// CHECK: %[[VAL_17:.*]] = load %[[VAL_6]]{{\[}}%[[VAL_4]]] : memref -// CHECK: %[[VAL_18:.*]] = load %[[VAL_6]]{{\[}}%[[VAL_5]]] : memref -// CHECK: %[[VAL_19:.*]] = load %[[VAL_11]]{{\[}}%[[VAL_4]]] : memref -// CHECK: %[[VAL_20:.*]] = load %[[VAL_11]]{{\[}}%[[VAL_5]]] : memref +// CHECK: %[[VAL_3:.*]] = constant 0 : index +// CHECK: %[[VAL_4:.*]] = constant 1 : index +// CHECK: %[[VAL_5:.*]] = linalg.sparse_pointers %[[VAL_0]], %[[VAL_3]] : tensor<32x16xf32> into memref +// CHECK: %[[VAL_6:.*]] = linalg.sparse_indices %[[VAL_0]], %[[VAL_3]] : tensor<32x16xf32> into memref +// CHECK: %[[VAL_7:.*]] = linalg.sparse_pointers %[[VAL_0]], %[[VAL_4]] : tensor<32x16xf32> into memref +// CHECK: %[[VAL_8:.*]] = linalg.sparse_indices %[[VAL_0]], %[[VAL_4]] : tensor<32x16xf32> into memref +// CHECK: %[[VAL_9:.*]] = linalg.sparse_values %[[VAL_0]] : tensor<32x16xf32> into memref +// CHECK: %[[VAL_10:.*]] = linalg.sparse_pointers %[[VAL_1]], %[[VAL_3]] : tensor<32x16xf32> into memref +// CHECK: %[[VAL_11:.*]] = linalg.sparse_indices %[[VAL_1]], %[[VAL_3]] : tensor<32x16xf32> into memref +// CHECK: %[[VAL_12:.*]] = linalg.sparse_pointers %[[VAL_1]], %[[VAL_4]] : tensor<32x16xf32> into memref +// CHECK: %[[VAL_13:.*]] = linalg.sparse_indices %[[VAL_1]], %[[VAL_4]] : tensor<32x16xf32> into memref +// CHECK: %[[VAL_14:.*]] = linalg.sparse_values %[[VAL_1]] : tensor<32x16xf32> into memref +// CHECK: %[[VAL_15:.*]] = tensor_to_memref %[[VAL_2]] : memref<32x16xf32> +// CHECK: %[[VAL_16:.*]] = alloc() : memref<32x16xf32> +// CHECK: linalg.copy(%[[VAL_15]], %[[VAL_16]]) : memref<32x16xf32>, memref<32x16xf32> +// CHECK: %[[VAL_17:.*]] = load %[[VAL_5]]{{\[}}%[[VAL_3]]] : memref +// CHECK: %[[VAL_18:.*]] = load %[[VAL_5]]{{\[}}%[[VAL_4]]] : memref +// CHECK: %[[VAL_19:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_3]]] : memref +// CHECK: %[[VAL_20:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_4]]] : memref // CHECK: %[[VAL_21:.*]]:2 = scf.while (%[[VAL_22:.*]] = %[[VAL_17]], %[[VAL_23:.*]] = %[[VAL_19]]) : (index, index) -> (index, index) { // CHECK: %[[VAL_24:.*]] = cmpi ult, %[[VAL_22]], %[[VAL_18]] : index // CHECK: %[[VAL_25:.*]] = cmpi ult, %[[VAL_23]], %[[VAL_20]] : index @@ -793,20 +806,20 @@ // CHECK: scf.condition(%[[VAL_26]]) %[[VAL_22]], %[[VAL_23]] : index, index // CHECK: } do { // CHECK: ^bb0(%[[VAL_27:.*]]: index, %[[VAL_28:.*]]: index): -// CHECK: %[[VAL_29:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_27]]] : memref -// CHECK: %[[VAL_30:.*]] = load %[[VAL_12]]{{\[}}%[[VAL_28]]] : memref +// CHECK: %[[VAL_29:.*]] = load %[[VAL_6]]{{\[}}%[[VAL_27]]] : memref +// CHECK: %[[VAL_30:.*]] = load %[[VAL_11]]{{\[}}%[[VAL_28]]] : memref // CHECK: %[[VAL_31:.*]] = cmpi ult, %[[VAL_30]], %[[VAL_29]] : index // CHECK: %[[VAL_32:.*]] = select %[[VAL_31]], %[[VAL_30]], %[[VAL_29]] : index // CHECK: %[[VAL_33:.*]] = cmpi eq, %[[VAL_29]], %[[VAL_32]] : index // CHECK: %[[VAL_34:.*]] = cmpi eq, %[[VAL_30]], %[[VAL_32]] : index // CHECK: %[[VAL_35:.*]] = and %[[VAL_33]], %[[VAL_34]] : i1 // CHECK: scf.if %[[VAL_35]] { -// CHECK: %[[VAL_36:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_27]]] : memref -// CHECK: %[[VAL_37:.*]] = addi %[[VAL_27]], %[[VAL_5]] : index -// CHECK: %[[VAL_38:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_37]]] : memref -// CHECK: %[[VAL_39:.*]] = load %[[VAL_13]]{{\[}}%[[VAL_28]]] : memref -// CHECK: %[[VAL_40:.*]] = addi %[[VAL_28]], %[[VAL_5]] : index -// CHECK: %[[VAL_41:.*]] = load %[[VAL_13]]{{\[}}%[[VAL_40]]] : memref +// CHECK: %[[VAL_36:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_27]]] : memref +// CHECK: %[[VAL_37:.*]] = addi %[[VAL_27]], %[[VAL_4]] : index +// CHECK: %[[VAL_38:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_37]]] : memref +// CHECK: %[[VAL_39:.*]] = load %[[VAL_12]]{{\[}}%[[VAL_28]]] : memref +// CHECK: %[[VAL_40:.*]] = addi %[[VAL_28]], %[[VAL_4]] : index +// CHECK: %[[VAL_41:.*]] = load %[[VAL_12]]{{\[}}%[[VAL_40]]] : memref // CHECK: %[[VAL_42:.*]]:2 = scf.while (%[[VAL_43:.*]] = %[[VAL_36]], %[[VAL_44:.*]] = %[[VAL_39]]) : (index, index) -> (index, index) { // CHECK: %[[VAL_45:.*]] = cmpi ult, %[[VAL_43]], %[[VAL_38]] : index // CHECK: %[[VAL_46:.*]] = cmpi ult, %[[VAL_44]], %[[VAL_41]] : index @@ -814,70 +827,70 @@ // CHECK: scf.condition(%[[VAL_47]]) %[[VAL_43]], %[[VAL_44]] : index, index // CHECK: } do { // CHECK: ^bb0(%[[VAL_48:.*]]: index, %[[VAL_49:.*]]: index): -// CHECK: %[[VAL_50:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_48]]] : memref -// CHECK: %[[VAL_51:.*]] = load %[[VAL_14]]{{\[}}%[[VAL_49]]] : memref +// CHECK: %[[VAL_50:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_48]]] : memref +// CHECK: %[[VAL_51:.*]] = load %[[VAL_13]]{{\[}}%[[VAL_49]]] : memref // CHECK: %[[VAL_52:.*]] = cmpi ult, %[[VAL_51]], %[[VAL_50]] : index // CHECK: %[[VAL_53:.*]] = select %[[VAL_52]], %[[VAL_51]], %[[VAL_50]] : index // CHECK: %[[VAL_54:.*]] = cmpi eq, %[[VAL_50]], %[[VAL_53]] : index // CHECK: %[[VAL_55:.*]] = cmpi eq, %[[VAL_51]], %[[VAL_53]] : index // CHECK: %[[VAL_56:.*]] = and %[[VAL_54]], %[[VAL_55]] : i1 // CHECK: scf.if %[[VAL_56]] { -// CHECK: %[[VAL_57:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_48]]] : memref -// CHECK: %[[VAL_58:.*]] = load %[[VAL_15]]{{\[}}%[[VAL_49]]] : memref +// CHECK: %[[VAL_57:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_48]]] : memref +// CHECK: %[[VAL_58:.*]] = load %[[VAL_14]]{{\[}}%[[VAL_49]]] : memref // CHECK: %[[VAL_59:.*]] = addf %[[VAL_57]], %[[VAL_58]] : f32 // CHECK: store %[[VAL_59]], %[[VAL_16]]{{\[}}%[[VAL_32]], %[[VAL_53]]] : memref<32x16xf32> // CHECK: } else { // CHECK: %[[VAL_60:.*]] = cmpi eq, %[[VAL_50]], %[[VAL_53]] : index // CHECK: scf.if %[[VAL_60]] { -// CHECK: %[[VAL_61:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_48]]] : memref +// CHECK: %[[VAL_61:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_48]]] : memref // CHECK: store %[[VAL_61]], %[[VAL_16]]{{\[}}%[[VAL_32]], %[[VAL_53]]] : memref<32x16xf32> // CHECK: } else { // CHECK: %[[VAL_62:.*]] = cmpi eq, %[[VAL_51]], %[[VAL_53]] : index // CHECK: scf.if %[[VAL_62]] { -// CHECK: %[[VAL_63:.*]] = load %[[VAL_15]]{{\[}}%[[VAL_49]]] : memref +// CHECK: %[[VAL_63:.*]] = load %[[VAL_14]]{{\[}}%[[VAL_49]]] : memref // CHECK: store %[[VAL_63]], %[[VAL_16]]{{\[}}%[[VAL_32]], %[[VAL_53]]] : memref<32x16xf32> // CHECK: } else { // CHECK: } // CHECK: } // CHECK: } // CHECK: %[[VAL_64:.*]] = cmpi eq, %[[VAL_50]], %[[VAL_53]] : index -// CHECK: %[[VAL_65:.*]] = addi %[[VAL_48]], %[[VAL_5]] : index +// CHECK: %[[VAL_65:.*]] = addi %[[VAL_48]], %[[VAL_4]] : index // CHECK: %[[VAL_66:.*]] = select %[[VAL_64]], %[[VAL_65]], %[[VAL_48]] : index // CHECK: %[[VAL_67:.*]] = cmpi eq, %[[VAL_51]], %[[VAL_53]] : index -// CHECK: %[[VAL_68:.*]] = addi %[[VAL_49]], %[[VAL_5]] : index +// CHECK: %[[VAL_68:.*]] = addi %[[VAL_49]], %[[VAL_4]] : index // CHECK: %[[VAL_69:.*]] = select %[[VAL_67]], %[[VAL_68]], %[[VAL_49]] : index // CHECK: scf.yield %[[VAL_66]], %[[VAL_69]] : index, index // CHECK: } -// CHECK: scf.for %[[VAL_70:.*]] = %[[VAL_71:.*]]#0 to %[[VAL_38]] step %[[VAL_5]] { -// CHECK: %[[VAL_72:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_70]]] : memref -// CHECK: %[[VAL_73:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_70]]] : memref +// CHECK: scf.for %[[VAL_70:.*]] = %[[VAL_71:.*]]#0 to %[[VAL_38]] step %[[VAL_4]] { +// CHECK: %[[VAL_72:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_70]]] : memref +// CHECK: %[[VAL_73:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_70]]] : memref // CHECK: store %[[VAL_73]], %[[VAL_16]]{{\[}}%[[VAL_32]], %[[VAL_72]]] : memref<32x16xf32> // CHECK: } -// CHECK: scf.for %[[VAL_74:.*]] = %[[VAL_75:.*]]#1 to %[[VAL_41]] step %[[VAL_5]] { -// CHECK: %[[VAL_76:.*]] = load %[[VAL_14]]{{\[}}%[[VAL_74]]] : memref -// CHECK: %[[VAL_77:.*]] = load %[[VAL_15]]{{\[}}%[[VAL_74]]] : memref +// CHECK: scf.for %[[VAL_74:.*]] = %[[VAL_75:.*]]#1 to %[[VAL_41]] step %[[VAL_4]] { +// CHECK: %[[VAL_76:.*]] = load %[[VAL_13]]{{\[}}%[[VAL_74]]] : memref +// CHECK: %[[VAL_77:.*]] = load %[[VAL_14]]{{\[}}%[[VAL_74]]] : memref // CHECK: store %[[VAL_77]], %[[VAL_16]]{{\[}}%[[VAL_32]], %[[VAL_76]]] : memref<32x16xf32> // CHECK: } // CHECK: } else { // CHECK: %[[VAL_78:.*]] = cmpi eq, %[[VAL_29]], %[[VAL_32]] : index // CHECK: scf.if %[[VAL_78]] { -// CHECK: %[[VAL_79:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_27]]] : memref -// CHECK: %[[VAL_80:.*]] = addi %[[VAL_27]], %[[VAL_5]] : index -// CHECK: %[[VAL_81:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_80]]] : memref -// CHECK: scf.for %[[VAL_82:.*]] = %[[VAL_79]] to %[[VAL_81]] step %[[VAL_5]] { -// CHECK: %[[VAL_83:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_82]]] : memref -// CHECK: %[[VAL_84:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_82]]] : memref +// CHECK: %[[VAL_79:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_27]]] : memref +// CHECK: %[[VAL_80:.*]] = addi %[[VAL_27]], %[[VAL_4]] : index +// CHECK: %[[VAL_81:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_80]]] : memref +// CHECK: scf.for %[[VAL_82:.*]] = %[[VAL_79]] to %[[VAL_81]] step %[[VAL_4]] { +// CHECK: %[[VAL_83:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_82]]] : memref +// CHECK: %[[VAL_84:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_82]]] : memref // CHECK: store %[[VAL_84]], %[[VAL_16]]{{\[}}%[[VAL_32]], %[[VAL_83]]] : memref<32x16xf32> // CHECK: } // CHECK: } else { // CHECK: %[[VAL_85:.*]] = cmpi eq, %[[VAL_30]], %[[VAL_32]] : index // CHECK: scf.if %[[VAL_85]] { -// CHECK: %[[VAL_86:.*]] = load %[[VAL_13]]{{\[}}%[[VAL_28]]] : memref -// CHECK: %[[VAL_87:.*]] = addi %[[VAL_28]], %[[VAL_5]] : index -// CHECK: %[[VAL_88:.*]] = load %[[VAL_13]]{{\[}}%[[VAL_87]]] : memref -// CHECK: scf.for %[[VAL_89:.*]] = %[[VAL_86]] to %[[VAL_88]] step %[[VAL_5]] { -// CHECK: %[[VAL_90:.*]] = load %[[VAL_14]]{{\[}}%[[VAL_89]]] : memref -// CHECK: %[[VAL_91:.*]] = load %[[VAL_15]]{{\[}}%[[VAL_89]]] : memref +// CHECK: %[[VAL_86:.*]] = load %[[VAL_12]]{{\[}}%[[VAL_28]]] : memref +// CHECK: %[[VAL_87:.*]] = addi %[[VAL_28]], %[[VAL_4]] : index +// CHECK: %[[VAL_88:.*]] = load %[[VAL_12]]{{\[}}%[[VAL_87]]] : memref +// CHECK: scf.for %[[VAL_89:.*]] = %[[VAL_86]] to %[[VAL_88]] step %[[VAL_4]] { +// CHECK: %[[VAL_90:.*]] = load %[[VAL_13]]{{\[}}%[[VAL_89]]] : memref +// CHECK: %[[VAL_91:.*]] = load %[[VAL_14]]{{\[}}%[[VAL_89]]] : memref // CHECK: store %[[VAL_91]], %[[VAL_16]]{{\[}}%[[VAL_32]], %[[VAL_90]]] : memref<32x16xf32> // CHECK: } // CHECK: } else { @@ -885,32 +898,32 @@ // CHECK: } // CHECK: } // CHECK: %[[VAL_92:.*]] = cmpi eq, %[[VAL_29]], %[[VAL_32]] : index -// CHECK: %[[VAL_93:.*]] = addi %[[VAL_27]], %[[VAL_5]] : index +// CHECK: %[[VAL_93:.*]] = addi %[[VAL_27]], %[[VAL_4]] : index // CHECK: %[[VAL_94:.*]] = select %[[VAL_92]], %[[VAL_93]], %[[VAL_27]] : index // CHECK: %[[VAL_95:.*]] = cmpi eq, %[[VAL_30]], %[[VAL_32]] : index -// CHECK: %[[VAL_96:.*]] = addi %[[VAL_28]], %[[VAL_5]] : index +// CHECK: %[[VAL_96:.*]] = addi %[[VAL_28]], %[[VAL_4]] : index // CHECK: %[[VAL_97:.*]] = select %[[VAL_95]], %[[VAL_96]], %[[VAL_28]] : index // CHECK: scf.yield %[[VAL_94]], %[[VAL_97]] : index, index // CHECK: } -// CHECK: scf.for %[[VAL_98:.*]] = %[[VAL_99:.*]]#0 to %[[VAL_18]] step %[[VAL_5]] { -// CHECK: %[[VAL_100:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_98]]] : memref -// CHECK: %[[VAL_101:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_98]]] : memref -// CHECK: %[[VAL_102:.*]] = addi %[[VAL_98]], %[[VAL_5]] : index -// CHECK: %[[VAL_103:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_102]]] : memref -// CHECK: scf.for %[[VAL_104:.*]] = %[[VAL_101]] to %[[VAL_103]] step %[[VAL_5]] { -// CHECK: %[[VAL_105:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_104]]] : memref -// CHECK: %[[VAL_106:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_104]]] : memref +// CHECK: scf.for %[[VAL_98:.*]] = %[[VAL_99:.*]]#0 to %[[VAL_18]] step %[[VAL_4]] { +// CHECK: %[[VAL_100:.*]] = load %[[VAL_6]]{{\[}}%[[VAL_98]]] : memref +// CHECK: %[[VAL_101:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_98]]] : memref +// CHECK: %[[VAL_102:.*]] = addi %[[VAL_98]], %[[VAL_4]] : index +// CHECK: %[[VAL_103:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_102]]] : memref +// CHECK: scf.for %[[VAL_104:.*]] = %[[VAL_101]] to %[[VAL_103]] step %[[VAL_4]] { +// CHECK: %[[VAL_105:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_104]]] : memref +// CHECK: %[[VAL_106:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_104]]] : memref // CHECK: store %[[VAL_106]], %[[VAL_16]]{{\[}}%[[VAL_100]], %[[VAL_105]]] : memref<32x16xf32> // CHECK: } // CHECK: } -// CHECK: scf.for %[[VAL_107:.*]] = %[[VAL_108:.*]]#1 to %[[VAL_20]] step %[[VAL_5]] { -// CHECK: %[[VAL_109:.*]] = load %[[VAL_12]]{{\[}}%[[VAL_107]]] : memref -// CHECK: %[[VAL_110:.*]] = load %[[VAL_13]]{{\[}}%[[VAL_107]]] : memref -// CHECK: %[[VAL_111:.*]] = addi %[[VAL_107]], %[[VAL_5]] : index -// CHECK: %[[VAL_112:.*]] = load %[[VAL_13]]{{\[}}%[[VAL_111]]] : memref -// CHECK: scf.for %[[VAL_113:.*]] = %[[VAL_110]] to %[[VAL_112]] step %[[VAL_5]] { -// CHECK: %[[VAL_114:.*]] = load %[[VAL_14]]{{\[}}%[[VAL_113]]] : memref -// CHECK: %[[VAL_115:.*]] = load %[[VAL_15]]{{\[}}%[[VAL_113]]] : memref +// CHECK: scf.for %[[VAL_107:.*]] = %[[VAL_108:.*]]#1 to %[[VAL_20]] step %[[VAL_4]] { +// CHECK: %[[VAL_109:.*]] = load %[[VAL_11]]{{\[}}%[[VAL_107]]] : memref +// CHECK: %[[VAL_110:.*]] = load %[[VAL_12]]{{\[}}%[[VAL_107]]] : memref +// CHECK: %[[VAL_111:.*]] = addi %[[VAL_107]], %[[VAL_4]] : index +// CHECK: %[[VAL_112:.*]] = load %[[VAL_12]]{{\[}}%[[VAL_111]]] : memref +// CHECK: scf.for %[[VAL_113:.*]] = %[[VAL_110]] to %[[VAL_112]] step %[[VAL_4]] { +// CHECK: %[[VAL_114:.*]] = load %[[VAL_13]]{{\[}}%[[VAL_113]]] : memref +// CHECK: %[[VAL_115:.*]] = load %[[VAL_14]]{{\[}}%[[VAL_113]]] : memref // CHECK: store %[[VAL_115]], %[[VAL_16]]{{\[}}%[[VAL_109]], %[[VAL_114]]] : memref<32x16xf32> // CHECK: } // CHECK: } @@ -932,24 +945,25 @@ // CHECK-SAME: %[[VAL_0:.*0]]: tensor<32x16xf32>, // CHECK-SAME: %[[VAL_1:.*1]]: tensor<32x16xf32>, // CHECK-SAME: %[[VAL_2:.*2]]: tensor<32x16xf32>) -> tensor<32x16xf32> { -// CHECK: %[[VAL_3:.*]] = constant 999 : index -// CHECK: %[[VAL_4:.*]] = constant 0 : index -// CHECK: %[[VAL_5:.*]] = constant 1 : index -// CHECK: %[[VAL_6:.*]] = alloca(%[[VAL_3]]) : memref -// CHECK: %[[VAL_7:.*]] = alloca(%[[VAL_3]]) : memref -// CHECK: %[[VAL_8:.*]] = alloca(%[[VAL_3]]) : memref -// CHECK: %[[VAL_9:.*]] = alloca(%[[VAL_3]]) : memref -// CHECK: %[[VAL_10:.*]] = alloca(%[[VAL_3]]) : memref -// CHECK: %[[VAL_11:.*]] = alloca(%[[VAL_3]]) : memref -// CHECK: %[[VAL_12:.*]] = alloca(%[[VAL_3]]) : memref -// CHECK: %[[VAL_13:.*]] = alloca(%[[VAL_3]]) : memref -// CHECK: %[[VAL_14:.*]] = alloca(%[[VAL_3]]) : memref -// CHECK: %[[VAL_15:.*]] = alloca(%[[VAL_3]]) : memref -// CHECK: %[[VAL_16:.*]] = alloca() : memref<32x16xf32> -// CHECK: %[[VAL_17:.*]] = load %[[VAL_6]]{{\[}}%[[VAL_4]]] : memref -// CHECK: %[[VAL_18:.*]] = load %[[VAL_6]]{{\[}}%[[VAL_5]]] : memref -// CHECK: %[[VAL_19:.*]] = load %[[VAL_11]]{{\[}}%[[VAL_4]]] : memref -// CHECK: %[[VAL_20:.*]] = load %[[VAL_11]]{{\[}}%[[VAL_5]]] : memref +// CHECK: %[[VAL_3:.*]] = constant 0 : index +// CHECK: %[[VAL_4:.*]] = constant 1 : index +// CHECK: %[[VAL_5:.*]] = linalg.sparse_pointers %[[VAL_0]], %[[VAL_3]] : tensor<32x16xf32> into memref +// CHECK: %[[VAL_6:.*]] = linalg.sparse_indices %[[VAL_0]], %[[VAL_3]] : tensor<32x16xf32> into memref +// CHECK: %[[VAL_7:.*]] = linalg.sparse_pointers %[[VAL_0]], %[[VAL_4]] : tensor<32x16xf32> into memref +// CHECK: %[[VAL_8:.*]] = linalg.sparse_indices %[[VAL_0]], %[[VAL_4]] : tensor<32x16xf32> into memref +// CHECK: %[[VAL_9:.*]] = linalg.sparse_values %[[VAL_0]] : tensor<32x16xf32> into memref +// CHECK: %[[VAL_10:.*]] = linalg.sparse_pointers %[[VAL_1]], %[[VAL_3]] : tensor<32x16xf32> into memref +// CHECK: %[[VAL_11:.*]] = linalg.sparse_indices %[[VAL_1]], %[[VAL_3]] : tensor<32x16xf32> into memref +// CHECK: %[[VAL_12:.*]] = linalg.sparse_pointers %[[VAL_1]], %[[VAL_4]] : tensor<32x16xf32> into memref +// CHECK: %[[VAL_13:.*]] = linalg.sparse_indices %[[VAL_1]], %[[VAL_4]] : tensor<32x16xf32> into memref +// CHECK: %[[VAL_14:.*]] = linalg.sparse_values %[[VAL_1]] : tensor<32x16xf32> into memref +// CHECK: %[[VAL_15:.*]] = tensor_to_memref %[[VAL_2]] : memref<32x16xf32> +// CHECK: %[[VAL_16:.*]] = alloc() : memref<32x16xf32> +// CHECK: linalg.copy(%[[VAL_15]], %[[VAL_16]]) : memref<32x16xf32>, memref<32x16xf32> +// CHECK: %[[VAL_17:.*]] = load %[[VAL_5]]{{\[}}%[[VAL_3]]] : memref +// CHECK: %[[VAL_18:.*]] = load %[[VAL_5]]{{\[}}%[[VAL_4]]] : memref +// CHECK: %[[VAL_19:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_3]]] : memref +// CHECK: %[[VAL_20:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_4]]] : memref // CHECK: %[[VAL_21:.*]]:2 = scf.while (%[[VAL_22:.*]] = %[[VAL_17]], %[[VAL_23:.*]] = %[[VAL_19]]) : (index, index) -> (index, index) { // CHECK: %[[VAL_24:.*]] = cmpi ult, %[[VAL_22]], %[[VAL_18]] : index // CHECK: %[[VAL_25:.*]] = cmpi ult, %[[VAL_23]], %[[VAL_20]] : index @@ -957,20 +971,20 @@ // CHECK: scf.condition(%[[VAL_26]]) %[[VAL_22]], %[[VAL_23]] : index, index // CHECK: } do { // CHECK: ^bb0(%[[VAL_27:.*]]: index, %[[VAL_28:.*]]: index): -// CHECK: %[[VAL_29:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_27]]] : memref -// CHECK: %[[VAL_30:.*]] = load %[[VAL_12]]{{\[}}%[[VAL_28]]] : memref +// CHECK: %[[VAL_29:.*]] = load %[[VAL_6]]{{\[}}%[[VAL_27]]] : memref +// CHECK: %[[VAL_30:.*]] = load %[[VAL_11]]{{\[}}%[[VAL_28]]] : memref // CHECK: %[[VAL_31:.*]] = cmpi ult, %[[VAL_30]], %[[VAL_29]] : index // CHECK: %[[VAL_32:.*]] = select %[[VAL_31]], %[[VAL_30]], %[[VAL_29]] : index // CHECK: %[[VAL_33:.*]] = cmpi eq, %[[VAL_29]], %[[VAL_32]] : index // CHECK: %[[VAL_34:.*]] = cmpi eq, %[[VAL_30]], %[[VAL_32]] : index // CHECK: %[[VAL_35:.*]] = and %[[VAL_33]], %[[VAL_34]] : i1 // CHECK: scf.if %[[VAL_35]] { -// CHECK: %[[VAL_36:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_27]]] : memref -// CHECK: %[[VAL_37:.*]] = addi %[[VAL_27]], %[[VAL_5]] : index -// CHECK: %[[VAL_38:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_37]]] : memref -// CHECK: %[[VAL_39:.*]] = load %[[VAL_13]]{{\[}}%[[VAL_28]]] : memref -// CHECK: %[[VAL_40:.*]] = addi %[[VAL_28]], %[[VAL_5]] : index -// CHECK: %[[VAL_41:.*]] = load %[[VAL_13]]{{\[}}%[[VAL_40]]] : memref +// CHECK: %[[VAL_36:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_27]]] : memref +// CHECK: %[[VAL_37:.*]] = addi %[[VAL_27]], %[[VAL_4]] : index +// CHECK: %[[VAL_38:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_37]]] : memref +// CHECK: %[[VAL_39:.*]] = load %[[VAL_12]]{{\[}}%[[VAL_28]]] : memref +// CHECK: %[[VAL_40:.*]] = addi %[[VAL_28]], %[[VAL_4]] : index +// CHECK: %[[VAL_41:.*]] = load %[[VAL_12]]{{\[}}%[[VAL_40]]] : memref // CHECK: %[[VAL_42:.*]]:2 = scf.while (%[[VAL_43:.*]] = %[[VAL_36]], %[[VAL_44:.*]] = %[[VAL_39]]) : (index, index) -> (index, index) { // CHECK: %[[VAL_45:.*]] = cmpi ult, %[[VAL_43]], %[[VAL_38]] : index // CHECK: %[[VAL_46:.*]] = cmpi ult, %[[VAL_44]], %[[VAL_41]] : index @@ -978,35 +992,35 @@ // CHECK: scf.condition(%[[VAL_47]]) %[[VAL_43]], %[[VAL_44]] : index, index // CHECK: } do { // CHECK: ^bb0(%[[VAL_48:.*]]: index, %[[VAL_49:.*]]: index): -// CHECK: %[[VAL_50:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_48]]] : memref -// CHECK: %[[VAL_51:.*]] = load %[[VAL_14]]{{\[}}%[[VAL_49]]] : memref +// CHECK: %[[VAL_50:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_48]]] : memref +// CHECK: %[[VAL_51:.*]] = load %[[VAL_13]]{{\[}}%[[VAL_49]]] : memref // CHECK: %[[VAL_52:.*]] = cmpi ult, %[[VAL_51]], %[[VAL_50]] : index // CHECK: %[[VAL_53:.*]] = select %[[VAL_52]], %[[VAL_51]], %[[VAL_50]] : index // CHECK: %[[VAL_54:.*]] = cmpi eq, %[[VAL_50]], %[[VAL_53]] : index // CHECK: %[[VAL_55:.*]] = cmpi eq, %[[VAL_51]], %[[VAL_53]] : index // CHECK: %[[VAL_56:.*]] = and %[[VAL_54]], %[[VAL_55]] : i1 // CHECK: scf.if %[[VAL_56]] { -// CHECK: %[[VAL_57:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_48]]] : memref -// CHECK: %[[VAL_58:.*]] = load %[[VAL_15]]{{\[}}%[[VAL_49]]] : memref +// CHECK: %[[VAL_57:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_48]]] : memref +// CHECK: %[[VAL_58:.*]] = load %[[VAL_14]]{{\[}}%[[VAL_49]]] : memref // CHECK: %[[VAL_59:.*]] = mulf %[[VAL_57]], %[[VAL_58]] : f32 // CHECK: store %[[VAL_59]], %[[VAL_16]]{{\[}}%[[VAL_32]], %[[VAL_53]]] : memref<32x16xf32> // CHECK: } else { // CHECK: } // CHECK: %[[VAL_60:.*]] = cmpi eq, %[[VAL_50]], %[[VAL_53]] : index -// CHECK: %[[VAL_61:.*]] = addi %[[VAL_48]], %[[VAL_5]] : index +// CHECK: %[[VAL_61:.*]] = addi %[[VAL_48]], %[[VAL_4]] : index // CHECK: %[[VAL_62:.*]] = select %[[VAL_60]], %[[VAL_61]], %[[VAL_48]] : index // CHECK: %[[VAL_63:.*]] = cmpi eq, %[[VAL_51]], %[[VAL_53]] : index -// CHECK: %[[VAL_64:.*]] = addi %[[VAL_49]], %[[VAL_5]] : index +// CHECK: %[[VAL_64:.*]] = addi %[[VAL_49]], %[[VAL_4]] : index // CHECK: %[[VAL_65:.*]] = select %[[VAL_63]], %[[VAL_64]], %[[VAL_49]] : index // CHECK: scf.yield %[[VAL_62]], %[[VAL_65]] : index, index // CHECK: } // CHECK: } else { // CHECK: } // CHECK: %[[VAL_66:.*]] = cmpi eq, %[[VAL_29]], %[[VAL_32]] : index -// CHECK: %[[VAL_67:.*]] = addi %[[VAL_27]], %[[VAL_5]] : index +// CHECK: %[[VAL_67:.*]] = addi %[[VAL_27]], %[[VAL_4]] : index // CHECK: %[[VAL_68:.*]] = select %[[VAL_66]], %[[VAL_67]], %[[VAL_27]] : index // CHECK: %[[VAL_69:.*]] = cmpi eq, %[[VAL_30]], %[[VAL_32]] : index -// CHECK: %[[VAL_70:.*]] = addi %[[VAL_28]], %[[VAL_5]] : index +// CHECK: %[[VAL_70:.*]] = addi %[[VAL_28]], %[[VAL_4]] : index // CHECK: %[[VAL_71:.*]] = select %[[VAL_69]], %[[VAL_70]], %[[VAL_28]] : index // CHECK: scf.yield %[[VAL_68]], %[[VAL_71]] : index, index // CHECK: } @@ -1040,27 +1054,28 @@ } // CHECK-LABEL: func @matvec( -// CHECK-SAME: %[[VAL_0:.*0]]: tensor<16x32xf32>, -// CHECK-SAME: %[[VAL_1:.*1]]: tensor<32xf32>, -// CHECK-SAME: %[[VAL_2:.*2]]: tensor<16xf32>) -> tensor<16xf32> { -// CHECK: %[[VAL_3:.*]] = constant 999 : index -// CHECK: %[[VAL_4:.*]] = constant 16 : index -// CHECK: %[[VAL_5:.*]] = constant 0 : index -// CHECK: %[[VAL_6:.*]] = constant 1 : index -// CHECK: %[[VAL_7:.*]] = alloca(%[[VAL_3]]) : memref -// CHECK: %[[VAL_8:.*]] = alloca(%[[VAL_3]]) : memref -// CHECK: %[[VAL_9:.*]] = alloca(%[[VAL_3]]) : memref -// CHECK: %[[VAL_10:.*]] = alloca() : memref<32xf32> -// CHECK: %[[VAL_11:.*]] = alloca() : memref<16xf32> -// CHECK: scf.for %[[VAL_12:.*]] = %[[VAL_5]] to %[[VAL_4]] step %[[VAL_6]] { -// CHECK: %[[VAL_13:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_12]]] : memref -// CHECK: %[[VAL_14:.*]] = addi %[[VAL_12]], %[[VAL_6]] : index -// CHECK: %[[VAL_15:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_14]]] : memref +// CHECK-SAME: %[[VAL_0:.*]]: tensor<16x32xf32>, +// CHECK-SAME: %[[VAL_1:.*]]: tensor<32xf32>, +// CHECK-SAME: %[[VAL_2:.*]]: tensor<16xf32>) -> tensor<16xf32> { +// CHECK: %[[VAL_3:.*]] = constant 16 : index +// CHECK: %[[VAL_4:.*]] = constant 0 : index +// CHECK: %[[VAL_5:.*]] = constant 1 : index +// CHECK: %[[VAL_6:.*]] = linalg.sparse_pointers %[[VAL_0]], %[[VAL_5]] : tensor<16x32xf32> into memref +// CHECK: %[[VAL_7:.*]] = linalg.sparse_indices %[[VAL_0]], %[[VAL_5]] : tensor<16x32xf32> into memref +// CHECK: %[[VAL_8:.*]] = linalg.sparse_values %[[VAL_0]] : tensor<16x32xf32> into memref +// CHECK: %[[VAL_9:.*]] = tensor_to_memref %[[VAL_1]] : memref<32xf32> +// CHECK: %[[VAL_10:.*]] = tensor_to_memref %[[VAL_2]] : memref<16xf32> +// CHECK: %[[VAL_11:.*]] = alloc() : memref<16xf32> +// CHECK: linalg.copy(%[[VAL_10]], %[[VAL_11]]) : memref<16xf32>, memref<16xf32> +// CHECK: scf.for %[[VAL_12:.*]] = %[[VAL_4]] to %[[VAL_3]] step %[[VAL_5]] { +// CHECK: %[[VAL_13:.*]] = load %[[VAL_6]]{{\[}}%[[VAL_12]]] : memref +// CHECK: %[[VAL_14:.*]] = addi %[[VAL_12]], %[[VAL_5]] : index +// CHECK: %[[VAL_15:.*]] = load %[[VAL_6]]{{\[}}%[[VAL_14]]] : memref // CHECK: %[[VAL_16:.*]] = load %[[VAL_11]]{{\[}}%[[VAL_12]]] : memref<16xf32> -// CHECK: %[[VAL_17:.*]] = scf.for %[[VAL_18:.*]] = %[[VAL_13]] to %[[VAL_15]] step %[[VAL_6]] iter_args(%[[VAL_19:.*]] = %[[VAL_16]]) -> (f32) { -// CHECK: %[[VAL_20:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_18]]] : memref -// CHECK: %[[VAL_21:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_18]]] : memref -// CHECK: %[[VAL_22:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_20]]] : memref<32xf32> +// CHECK: %[[VAL_17:.*]] = scf.for %[[VAL_18:.*]] = %[[VAL_13]] to %[[VAL_15]] step %[[VAL_5]] iter_args(%[[VAL_19:.*]] = %[[VAL_16]]) -> (f32) { +// CHECK: %[[VAL_20:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_18]]] : memref +// CHECK: %[[VAL_21:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_18]]] : memref +// CHECK: %[[VAL_22:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_20]]] : memref<32xf32> // CHECK: %[[VAL_23:.*]] = mulf %[[VAL_21]], %[[VAL_22]] : f32 // CHECK: %[[VAL_24:.*]] = addf %[[VAL_23]], %[[VAL_19]] : f32 // CHECK: scf.yield %[[VAL_24]] : f32 @@ -1098,20 +1113,21 @@ // CHECK-LABEL: func @sum_reduction( // CHECK-SAME: %[[VAL_0:.*]]: tensor<10x20xf32>, // CHECK-SAME: %[[VAL_1:.*]]: tensor) -> tensor { -// CHECK: %[[VAL_2:.*]] = constant 999 : index -// CHECK: %[[VAL_3:.*]] = constant 10 : index -// CHECK: %[[VAL_4:.*]] = constant 0 : index -// CHECK: %[[VAL_5:.*]] = constant 1 : index -// CHECK: %[[VAL_6:.*]] = alloca(%[[VAL_2]]) : memref -// CHECK: %[[VAL_7:.*]] = alloca(%[[VAL_2]]) : memref -// CHECK: %[[VAL_8:.*]] = alloca() : memref -// CHECK: scf.for %[[VAL_9:.*]] = %[[VAL_4]] to %[[VAL_3]] step %[[VAL_5]] { -// CHECK: %[[VAL_10:.*]] = load %[[VAL_6]]{{\[}}%[[VAL_9]]] : memref -// CHECK: %[[VAL_11:.*]] = addi %[[VAL_9]], %[[VAL_5]] : index -// CHECK: %[[VAL_12:.*]] = load %[[VAL_6]]{{\[}}%[[VAL_11]]] : memref +// CHECK: %[[VAL_2:.*]] = constant 10 : index +// CHECK: %[[VAL_3:.*]] = constant 0 : index +// CHECK: %[[VAL_4:.*]] = constant 1 : index +// CHECK: %[[VAL_5:.*]] = linalg.sparse_pointers %[[VAL_0]], %[[VAL_4]] : tensor<10x20xf32> into memref +// CHECK: %[[VAL_6:.*]] = linalg.sparse_values %[[VAL_0]] : tensor<10x20xf32> into memref +// CHECK: %[[VAL_7:.*]] = tensor_to_memref %[[VAL_1]] : memref +// CHECK: %[[VAL_8:.*]] = alloc() : memref +// CHECK: linalg.copy(%[[VAL_7]], %[[VAL_8]]) : memref, memref +// CHECK: scf.for %[[VAL_9:.*]] = %[[VAL_3]] to %[[VAL_2]] step %[[VAL_4]] { +// CHECK: %[[VAL_10:.*]] = load %[[VAL_5]]{{\[}}%[[VAL_9]]] : memref +// CHECK: %[[VAL_11:.*]] = addi %[[VAL_9]], %[[VAL_4]] : index +// CHECK: %[[VAL_12:.*]] = load %[[VAL_5]]{{\[}}%[[VAL_11]]] : memref // CHECK: %[[VAL_13:.*]] = load %[[VAL_8]][] : memref -// CHECK: %[[VAL_14:.*]] = scf.for %[[VAL_15:.*]] = %[[VAL_10]] to %[[VAL_12]] step %[[VAL_5]] iter_args(%[[VAL_16:.*]] = %[[VAL_13]]) -> (f32) { -// CHECK: %[[VAL_17:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_15]]] : memref +// CHECK: %[[VAL_14:.*]] = scf.for %[[VAL_15:.*]] = %[[VAL_10]] to %[[VAL_12]] step %[[VAL_4]] iter_args(%[[VAL_16:.*]] = %[[VAL_13]]) -> (f32) { +// CHECK: %[[VAL_17:.*]] = load %[[VAL_6]]{{\[}}%[[VAL_15]]] : memref // CHECK: %[[VAL_18:.*]] = addf %[[VAL_16]], %[[VAL_17]] : f32 // CHECK: scf.yield %[[VAL_18]] : f32 // CHECK: } @@ -1148,22 +1164,23 @@ // CHECK-SAME: %[[VAL_0:.*]]: tensor, // CHECK-SAME: %[[VAL_1:.*]]: tensor) -> tensor { // CHECK: %[[VAL_2:.*]] = constant 2.000000e+00 : f64 -// CHECK: %[[VAL_3:.*]] = constant 999 : index -// CHECK: %[[VAL_4:.*]] = constant 0 : index -// CHECK: %[[VAL_5:.*]] = constant 1 : index -// CHECK: %[[VAL_6:.*]] = alloca(%[[VAL_3]]) : memref -// CHECK: %[[VAL_7:.*]] = alloca(%[[VAL_3]]) : memref -// CHECK: %[[VAL_8:.*]] = alloca(%[[VAL_3]]) : memref +// CHECK: %[[VAL_3:.*]] = constant 0 : index +// CHECK: %[[VAL_4:.*]] = constant 1 : index +// CHECK: %[[VAL_5:.*]] = linalg.sparse_pointers %[[VAL_0]], %[[VAL_4]] : tensor into memref +// CHECK: %[[VAL_6:.*]] = linalg.sparse_indices %[[VAL_0]], %[[VAL_4]] : tensor into memref +// CHECK: %[[VAL_7:.*]] = linalg.sparse_values %[[VAL_0]] : tensor into memref +// CHECK: %[[VAL_8:.*]] = dim %[[VAL_1]], %[[VAL_3]] : tensor // CHECK: %[[VAL_9:.*]] = dim %[[VAL_1]], %[[VAL_4]] : tensor -// CHECK: %[[VAL_10:.*]] = dim %[[VAL_1]], %[[VAL_5]] : tensor -// CHECK: %[[VAL_11:.*]] = alloca(%[[VAL_9]], %[[VAL_10]]) : memref -// CHECK: scf.for %[[VAL_12:.*]] = %[[VAL_4]] to %[[VAL_9]] step %[[VAL_5]] { -// CHECK: %[[VAL_13:.*]] = load %[[VAL_6]]{{\[}}%[[VAL_12]]] : memref -// CHECK: %[[VAL_14:.*]] = addi %[[VAL_12]], %[[VAL_5]] : index -// CHECK: %[[VAL_15:.*]] = load %[[VAL_6]]{{\[}}%[[VAL_14]]] : memref -// CHECK: scf.for %[[VAL_16:.*]] = %[[VAL_13]] to %[[VAL_15]] step %[[VAL_5]] { -// CHECK: %[[VAL_17:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_16]]] : memref -// CHECK: %[[VAL_18:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_16]]] : memref +// CHECK: %[[VAL_10:.*]] = tensor_to_memref %[[VAL_1]] : memref +// CHECK: %[[VAL_11:.*]] = alloc(%[[VAL_8]], %[[VAL_9]]) : memref +// CHECK: linalg.copy(%[[VAL_10]], %[[VAL_11]]) : memref, memref +// CHECK: scf.for %[[VAL_12:.*]] = %[[VAL_3]] to %[[VAL_8]] step %[[VAL_4]] { +// CHECK: %[[VAL_13:.*]] = load %[[VAL_5]]{{\[}}%[[VAL_12]]] : memref +// CHECK: %[[VAL_14:.*]] = addi %[[VAL_12]], %[[VAL_4]] : index +// CHECK: %[[VAL_15:.*]] = load %[[VAL_5]]{{\[}}%[[VAL_14]]] : memref +// CHECK: scf.for %[[VAL_16:.*]] = %[[VAL_13]] to %[[VAL_15]] step %[[VAL_4]] { +// CHECK: %[[VAL_17:.*]] = load %[[VAL_6]]{{\[}}%[[VAL_16]]] : memref +// CHECK: %[[VAL_18:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_16]]] : memref // CHECK: %[[VAL_19:.*]] = mulf %[[VAL_18]], %[[VAL_2]] : f64 // CHECK: store %[[VAL_19]], %[[VAL_11]]{{\[}}%[[VAL_12]], %[[VAL_17]]] : memref // CHECK: } @@ -1205,46 +1222,44 @@ // CHECK-SAME: %[[VAL_1:.*1]]: tensor, // CHECK-SAME: %[[VAL_2:.*2]]: tensor, // CHECK-SAME: %[[VAL_3:.*3]]: tensor) -> tensor { -// CHECK: %[[VAL_4:.*]] = constant 999 : index -// CHECK: %[[VAL_5:.*]] = constant 0 : index -// CHECK: %[[VAL_6:.*]] = constant 1 : index -// CHECK: %[[VAL_7:.*]] = alloca(%[[VAL_4]]) : memref -// CHECK: %[[VAL_8:.*]] = alloca(%[[VAL_4]]) : memref -// CHECK: %[[VAL_9:.*]] = alloca(%[[VAL_4]]) : memref -// CHECK: %[[VAL_10:.*]] = alloca(%[[VAL_4]]) : memref -// CHECK: %[[VAL_11:.*]] = alloca(%[[VAL_4]]) : memref -// CHECK: %[[VAL_12:.*]] = dim %[[VAL_1]], %[[VAL_5]] : tensor -// CHECK: %[[VAL_13:.*]] = dim %[[VAL_1]], %[[VAL_6]] : tensor -// CHECK: %[[VAL_14:.*]] = alloca(%[[VAL_12]], %[[VAL_13]]) : memref -// CHECK: %[[VAL_15:.*]] = dim %[[VAL_2]], %[[VAL_5]] : tensor -// CHECK: %[[VAL_16:.*]] = dim %[[VAL_2]], %[[VAL_6]] : tensor -// CHECK: %[[VAL_17:.*]] = alloca(%[[VAL_15]], %[[VAL_16]]) : memref -// CHECK: %[[VAL_18:.*]] = dim %[[VAL_3]], %[[VAL_5]] : tensor -// CHECK: %[[VAL_19:.*]] = dim %[[VAL_3]], %[[VAL_6]] : tensor -// CHECK: %[[VAL_20:.*]] = alloca(%[[VAL_18]], %[[VAL_19]]) : memref -// CHECK: %[[VAL_21:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_5]]] : memref -// CHECK: %[[VAL_22:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_6]]] : memref -// CHECK: scf.for %[[VAL_23:.*]] = %[[VAL_21]] to %[[VAL_22]] step %[[VAL_6]] { -// CHECK: %[[VAL_24:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_23]]] : memref -// CHECK: scf.for %[[VAL_25:.*]] = %[[VAL_5]] to %[[VAL_15]] step %[[VAL_6]] { -// CHECK: %[[VAL_26:.*]] = load %[[VAL_14]]{{\[}}%[[VAL_24]], %[[VAL_25]]] : memref -// CHECK: %[[VAL_27:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_23]]] : memref -// CHECK: %[[VAL_28:.*]] = addi %[[VAL_23]], %[[VAL_6]] : index -// CHECK: %[[VAL_29:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_28]]] : memref -// CHECK: scf.for %[[VAL_30:.*]] = %[[VAL_27]] to %[[VAL_29]] step %[[VAL_6]] { -// CHECK: %[[VAL_31:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_30]]] : memref -// CHECK: %[[VAL_32:.*]] = load %[[VAL_20]]{{\[}}%[[VAL_24]], %[[VAL_31]]] : memref -// CHECK: %[[VAL_33:.*]] = load %[[VAL_11]]{{\[}}%[[VAL_30]]] : memref -// CHECK: %[[VAL_34:.*]] = load %[[VAL_17]]{{\[}}%[[VAL_25]], %[[VAL_31]]] : memref -// CHECK: %[[VAL_35:.*]] = mulf %[[VAL_26]], %[[VAL_34]] : f32 -// CHECK: %[[VAL_36:.*]] = mulf %[[VAL_33]], %[[VAL_35]] : f32 -// CHECK: %[[VAL_37:.*]] = addf %[[VAL_32]], %[[VAL_36]] : f32 -// CHECK: store %[[VAL_37]], %[[VAL_20]]{{\[}}%[[VAL_24]], %[[VAL_31]]] : memref +// CHECK: %[[VAL_4:.*]] = constant 0 : index +// CHECK: %[[VAL_5:.*]] = constant 1 : index +// CHECK: %[[VAL_6:.*]] = linalg.sparse_pointers %[[VAL_0]], %[[VAL_4]] : tensor into memref +// CHECK: %[[VAL_7:.*]] = linalg.sparse_indices %[[VAL_0]], %[[VAL_4]] : tensor into memref +// CHECK: %[[VAL_8:.*]] = linalg.sparse_pointers %[[VAL_0]], %[[VAL_5]] : tensor into memref +// CHECK: %[[VAL_9:.*]] = linalg.sparse_indices %[[VAL_0]], %[[VAL_5]] : tensor into memref +// CHECK: %[[VAL_10:.*]] = linalg.sparse_values %[[VAL_0]] : tensor into memref +// CHECK: %[[VAL_11:.*]] = tensor_to_memref %[[VAL_1]] : memref +// CHECK: %[[VAL_12:.*]] = dim %[[VAL_2]], %[[VAL_4]] : tensor +// CHECK: %[[VAL_13:.*]] = tensor_to_memref %[[VAL_2]] : memref +// CHECK: %[[VAL_14:.*]] = dim %[[VAL_3]], %[[VAL_4]] : tensor +// CHECK: %[[VAL_15:.*]] = dim %[[VAL_3]], %[[VAL_5]] : tensor +// CHECK: %[[VAL_16:.*]] = tensor_to_memref %[[VAL_3]] : memref +// CHECK: %[[VAL_17:.*]] = alloc(%[[VAL_14]], %[[VAL_15]]) : memref +// CHECK: linalg.copy(%[[VAL_16]], %[[VAL_17]]) : memref, memref +// CHECK: %[[VAL_18:.*]] = load %[[VAL_6]]{{\[}}%[[VAL_4]]] : memref +// CHECK: %[[VAL_19:.*]] = load %[[VAL_6]]{{\[}}%[[VAL_5]]] : memref +// CHECK: scf.for %[[VAL_20:.*]] = %[[VAL_18]] to %[[VAL_19]] step %[[VAL_5]] { +// CHECK: %[[VAL_21:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_20]]] : memref +// CHECK: scf.for %[[VAL_22:.*]] = %[[VAL_4]] to %[[VAL_12]] step %[[VAL_5]] { +// CHECK: %[[VAL_23:.*]] = load %[[VAL_11]]{{\[}}%[[VAL_21]], %[[VAL_22]]] : memref +// CHECK: %[[VAL_24:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_20]]] : memref +// CHECK: %[[VAL_25:.*]] = addi %[[VAL_20]], %[[VAL_5]] : index +// CHECK: %[[VAL_26:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_25]]] : memref +// CHECK: scf.for %[[VAL_27:.*]] = %[[VAL_24]] to %[[VAL_26]] step %[[VAL_5]] { +// CHECK: %[[VAL_28:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_27]]] : memref +// CHECK: %[[VAL_29:.*]] = load %[[VAL_17]]{{\[}}%[[VAL_21]], %[[VAL_28]]] : memref +// CHECK: %[[VAL_30:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_27]]] : memref +// CHECK: %[[VAL_31:.*]] = load %[[VAL_13]]{{\[}}%[[VAL_22]], %[[VAL_28]]] : memref +// CHECK: %[[VAL_32:.*]] = mulf %[[VAL_23]], %[[VAL_31]] : f32 +// CHECK: %[[VAL_33:.*]] = mulf %[[VAL_30]], %[[VAL_32]] : f32 +// CHECK: %[[VAL_34:.*]] = addf %[[VAL_29]], %[[VAL_33]] : f32 +// CHECK: store %[[VAL_34]], %[[VAL_17]]{{\[}}%[[VAL_21]], %[[VAL_28]]] : memref // CHECK: } // CHECK: } // CHECK: } -// CHECK: %[[VAL_38:.*]] = tensor_load %[[VAL_20]] : memref -// CHECK: return %[[VAL_38]] : tensor +// CHECK: %[[VAL_35:.*]] = tensor_load %[[VAL_17]] : memref +// CHECK: return %[[VAL_35]] : tensor // CHECK: } func @sampled_dense_dense(%args: tensor, %arga: tensor, @@ -1290,185 +1305,185 @@ // CHECK-SAME: %[[VAL_3:.*3]]: tensor, // CHECK-SAME: %[[VAL_4:.*4]]: tensor, // CHECK-SAME: %[[VAL_5:.*5]]: tensor) -> tensor { -// CHECK: %[[VAL_6:.*]] = constant 999 : index -// CHECK: %[[VAL_7:.*]] = constant 0 : index -// CHECK: %[[VAL_8:.*]] = constant true -// CHECK: %[[VAL_9:.*]] = constant 1 : index -// CHECK: %[[VAL_10:.*]] = alloca(%[[VAL_6]]) : memref -// CHECK: %[[VAL_11:.*]] = alloca(%[[VAL_6]]) : memref -// CHECK: %[[VAL_12:.*]] = alloca(%[[VAL_6]]) : memref -// CHECK: %[[VAL_13:.*]] = alloca(%[[VAL_6]]) : memref -// CHECK: %[[VAL_14:.*]] = alloca(%[[VAL_6]]) : memref -// CHECK: %[[VAL_15:.*]] = alloca(%[[VAL_6]]) : memref -// CHECK: %[[VAL_16:.*]] = alloca(%[[VAL_6]]) : memref -// CHECK: %[[VAL_17:.*]] = alloca(%[[VAL_6]]) : memref -// CHECK: %[[VAL_18:.*]] = alloca(%[[VAL_6]]) : memref -// CHECK: %[[VAL_19:.*]] = alloca(%[[VAL_6]]) : memref -// CHECK: %[[VAL_20:.*]] = alloca(%[[VAL_6]]) : memref -// CHECK: %[[VAL_21:.*]] = dim %[[VAL_3]], %[[VAL_7]] : tensor -// CHECK: %[[VAL_22:.*]] = alloca(%[[VAL_21]]) : memref -// CHECK: %[[VAL_23:.*]] = alloca() : memref -// CHECK: %[[VAL_24:.*]] = dim %[[VAL_5]], %[[VAL_7]] : tensor -// CHECK: %[[VAL_25:.*]] = alloca(%[[VAL_24]]) : memref -// CHECK: %[[VAL_26:.*]] = load %[[VAL_23]][] : memref -// CHECK: %[[VAL_27:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_7]]] : memref -// CHECK: %[[VAL_28:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_9]]] : memref -// CHECK: %[[VAL_29:.*]]:2 = scf.while (%[[VAL_30:.*]] = %[[VAL_27]], %[[VAL_31:.*]] = %[[VAL_7]]) : (index, index) -> (index, index) { -// CHECK: %[[VAL_32:.*]] = cmpi ult, %[[VAL_30]], %[[VAL_28]] : index -// CHECK: scf.condition(%[[VAL_32]]) %[[VAL_30]], %[[VAL_31]] : index, index +// CHECK: %[[VAL_6:.*]] = constant 0 : index +// CHECK: %[[VAL_7:.*]] = constant true +// CHECK: %[[VAL_8:.*]] = constant 1 : index +// CHECK: %[[VAL_9:.*]] = linalg.sparse_pointers %[[VAL_0]], %[[VAL_6]] : tensor into memref +// CHECK: %[[VAL_10:.*]] = linalg.sparse_indices %[[VAL_0]], %[[VAL_6]] : tensor into memref +// CHECK: %[[VAL_11:.*]] = linalg.sparse_pointers %[[VAL_0]], %[[VAL_8]] : tensor into memref +// CHECK: %[[VAL_12:.*]] = linalg.sparse_indices %[[VAL_0]], %[[VAL_8]] : tensor into memref +// CHECK: %[[VAL_13:.*]] = linalg.sparse_values %[[VAL_0]] : tensor into memref +// CHECK: %[[VAL_14:.*]] = linalg.sparse_pointers %[[VAL_1]], %[[VAL_8]] : tensor into memref +// CHECK: %[[VAL_15:.*]] = linalg.sparse_indices %[[VAL_1]], %[[VAL_8]] : tensor into memref +// CHECK: %[[VAL_16:.*]] = linalg.sparse_values %[[VAL_1]] : tensor into memref +// CHECK: %[[VAL_17:.*]] = linalg.sparse_pointers %[[VAL_2]], %[[VAL_8]] : tensor into memref +// CHECK: %[[VAL_18:.*]] = linalg.sparse_indices %[[VAL_2]], %[[VAL_8]] : tensor into memref +// CHECK: %[[VAL_19:.*]] = linalg.sparse_values %[[VAL_2]] : tensor into memref +// CHECK: %[[VAL_20:.*]] = tensor_to_memref %[[VAL_3]] : memref +// CHECK: %[[VAL_21:.*]] = tensor_to_memref %[[VAL_4]] : memref +// CHECK: %[[VAL_22:.*]] = dim %[[VAL_5]], %[[VAL_6]] : tensor +// CHECK: %[[VAL_23:.*]] = tensor_to_memref %[[VAL_5]] : memref +// CHECK: %[[VAL_24:.*]] = alloc(%[[VAL_22]]) : memref +// CHECK: linalg.copy(%[[VAL_23]], %[[VAL_24]]) : memref, memref +// CHECK: %[[VAL_25:.*]] = load %[[VAL_21]][] : memref +// CHECK: %[[VAL_26:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_6]]] : memref +// CHECK: %[[VAL_27:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_8]]] : memref +// CHECK: %[[VAL_28:.*]]:2 = scf.while (%[[VAL_29:.*]] = %[[VAL_26]], %[[VAL_30:.*]] = %[[VAL_6]]) : (index, index) -> (index, index) { +// CHECK: %[[VAL_31:.*]] = cmpi ult, %[[VAL_29]], %[[VAL_27]] : index +// CHECK: scf.condition(%[[VAL_31]]) %[[VAL_29]], %[[VAL_30]] : index, index // CHECK: } do { -// CHECK: ^bb0(%[[VAL_33:.*]]: index, %[[VAL_34:.*]]: index): -// CHECK: %[[VAL_35:.*]] = load %[[VAL_11]]{{\[}}%[[VAL_33]]] : memref -// CHECK: %[[VAL_36:.*]] = cmpi eq, %[[VAL_35]], %[[VAL_34]] : index -// CHECK: scf.if %[[VAL_36]] { -// CHECK: %[[VAL_37:.*]] = load %[[VAL_22]]{{\[}}%[[VAL_34]]] : memref -// CHECK: %[[VAL_38:.*]] = load %[[VAL_12]]{{\[}}%[[VAL_33]]] : memref -// CHECK: %[[VAL_39:.*]] = addi %[[VAL_33]], %[[VAL_9]] : index -// CHECK: %[[VAL_40:.*]] = load %[[VAL_12]]{{\[}}%[[VAL_39]]] : memref -// CHECK: %[[VAL_41:.*]] = load %[[VAL_15]]{{\[}}%[[VAL_34]]] : memref -// CHECK: %[[VAL_42:.*]] = addi %[[VAL_34]], %[[VAL_9]] : index -// CHECK: %[[VAL_43:.*]] = load %[[VAL_15]]{{\[}}%[[VAL_42]]] : memref -// CHECK: %[[VAL_44:.*]] = load %[[VAL_18]]{{\[}}%[[VAL_34]]] : memref -// CHECK: %[[VAL_45:.*]] = addi %[[VAL_34]], %[[VAL_9]] : index -// CHECK: %[[VAL_46:.*]] = load %[[VAL_18]]{{\[}}%[[VAL_45]]] : memref -// CHECK: %[[VAL_47:.*]]:4 = scf.while (%[[VAL_48:.*]] = %[[VAL_38]], %[[VAL_49:.*]] = %[[VAL_41]], %[[VAL_50:.*]] = %[[VAL_44]], %[[VAL_51:.*]] = %[[VAL_7]]) : (index, index, index, index) -> (index, index, index, index) { -// CHECK: %[[VAL_52:.*]] = cmpi ult, %[[VAL_48]], %[[VAL_40]] : index -// CHECK: %[[VAL_53:.*]] = cmpi ult, %[[VAL_49]], %[[VAL_43]] : index -// CHECK: %[[VAL_54:.*]] = and %[[VAL_52]], %[[VAL_53]] : i1 -// CHECK: %[[VAL_55:.*]] = cmpi ult, %[[VAL_50]], %[[VAL_46]] : index -// CHECK: %[[VAL_56:.*]] = and %[[VAL_54]], %[[VAL_55]] : i1 -// CHECK: scf.condition(%[[VAL_56]]) %[[VAL_48]], %[[VAL_49]], %[[VAL_50]], %[[VAL_51]] : index, index, index, index +// CHECK: ^bb0(%[[VAL_32:.*]]: index, %[[VAL_33:.*]]: index): +// CHECK: %[[VAL_34:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_32]]] : memref +// CHECK: %[[VAL_35:.*]] = cmpi eq, %[[VAL_34]], %[[VAL_33]] : index +// CHECK: scf.if %[[VAL_35]] { +// CHECK: %[[VAL_36:.*]] = load %[[VAL_20]]{{\[}}%[[VAL_33]]] : memref +// CHECK: %[[VAL_37:.*]] = load %[[VAL_11]]{{\[}}%[[VAL_32]]] : memref +// CHECK: %[[VAL_38:.*]] = addi %[[VAL_32]], %[[VAL_8]] : index +// CHECK: %[[VAL_39:.*]] = load %[[VAL_11]]{{\[}}%[[VAL_38]]] : memref +// CHECK: %[[VAL_40:.*]] = load %[[VAL_14]]{{\[}}%[[VAL_33]]] : memref +// CHECK: %[[VAL_41:.*]] = addi %[[VAL_33]], %[[VAL_8]] : index +// CHECK: %[[VAL_42:.*]] = load %[[VAL_14]]{{\[}}%[[VAL_41]]] : memref +// CHECK: %[[VAL_43:.*]] = load %[[VAL_17]]{{\[}}%[[VAL_33]]] : memref +// CHECK: %[[VAL_44:.*]] = addi %[[VAL_33]], %[[VAL_8]] : index +// CHECK: %[[VAL_45:.*]] = load %[[VAL_17]]{{\[}}%[[VAL_44]]] : memref +// CHECK: %[[VAL_46:.*]]:4 = scf.while (%[[VAL_47:.*]] = %[[VAL_37]], %[[VAL_48:.*]] = %[[VAL_40]], %[[VAL_49:.*]] = %[[VAL_43]], %[[VAL_50:.*]] = %[[VAL_6]]) : (index, index, index, index) -> (index, index, index, index) { +// CHECK: %[[VAL_51:.*]] = cmpi ult, %[[VAL_47]], %[[VAL_39]] : index +// CHECK: %[[VAL_52:.*]] = cmpi ult, %[[VAL_48]], %[[VAL_42]] : index +// CHECK: %[[VAL_53:.*]] = and %[[VAL_51]], %[[VAL_52]] : i1 +// CHECK: %[[VAL_54:.*]] = cmpi ult, %[[VAL_49]], %[[VAL_45]] : index +// CHECK: %[[VAL_55:.*]] = and %[[VAL_53]], %[[VAL_54]] : i1 +// CHECK: scf.condition(%[[VAL_55]]) %[[VAL_47]], %[[VAL_48]], %[[VAL_49]], %[[VAL_50]] : index, index, index, index // CHECK: } do { -// CHECK: ^bb0(%[[VAL_57:.*]]: index, %[[VAL_58:.*]]: index, %[[VAL_59:.*]]: index, %[[VAL_60:.*]]: index): -// CHECK: %[[VAL_61:.*]] = load %[[VAL_13]]{{\[}}%[[VAL_57]]] : memref -// CHECK: %[[VAL_62:.*]] = load %[[VAL_16]]{{\[}}%[[VAL_58]]] : memref -// CHECK: %[[VAL_63:.*]] = load %[[VAL_19]]{{\[}}%[[VAL_59]]] : memref -// CHECK: %[[VAL_64:.*]] = cmpi eq, %[[VAL_61]], %[[VAL_60]] : index -// CHECK: %[[VAL_65:.*]] = cmpi eq, %[[VAL_62]], %[[VAL_60]] : index -// CHECK: %[[VAL_66:.*]] = and %[[VAL_64]], %[[VAL_65]] : i1 -// CHECK: %[[VAL_67:.*]] = cmpi eq, %[[VAL_63]], %[[VAL_60]] : index -// CHECK: %[[VAL_68:.*]] = and %[[VAL_66]], %[[VAL_67]] : i1 -// CHECK: scf.if %[[VAL_68]] { -// CHECK: %[[VAL_69:.*]] = load %[[VAL_25]]{{\[}}%[[VAL_34]]] : memref -// CHECK: %[[VAL_70:.*]] = load %[[VAL_14]]{{\[}}%[[VAL_57]]] : memref -// CHECK: %[[VAL_71:.*]] = load %[[VAL_17]]{{\[}}%[[VAL_58]]] : memref -// CHECK: %[[VAL_72:.*]] = mulf %[[VAL_70]], %[[VAL_71]] : f32 -// CHECK: %[[VAL_73:.*]] = mulf %[[VAL_72]], %[[VAL_37]] : f32 -// CHECK: %[[VAL_74:.*]] = mulf %[[VAL_73]], %[[VAL_26]] : f32 -// CHECK: %[[VAL_75:.*]] = load %[[VAL_20]]{{\[}}%[[VAL_59]]] : memref -// CHECK: %[[VAL_76:.*]] = addf %[[VAL_74]], %[[VAL_75]] : f32 -// CHECK: %[[VAL_77:.*]] = addf %[[VAL_69]], %[[VAL_76]] : f32 -// CHECK: store %[[VAL_77]], %[[VAL_25]]{{\[}}%[[VAL_34]]] : memref +// CHECK: ^bb0(%[[VAL_56:.*]]: index, %[[VAL_57:.*]]: index, %[[VAL_58:.*]]: index, %[[VAL_59:.*]]: index): +// CHECK: %[[VAL_60:.*]] = load %[[VAL_12]]{{\[}}%[[VAL_56]]] : memref +// CHECK: %[[VAL_61:.*]] = load %[[VAL_15]]{{\[}}%[[VAL_57]]] : memref +// CHECK: %[[VAL_62:.*]] = load %[[VAL_18]]{{\[}}%[[VAL_58]]] : memref +// CHECK: %[[VAL_63:.*]] = cmpi eq, %[[VAL_60]], %[[VAL_59]] : index +// CHECK: %[[VAL_64:.*]] = cmpi eq, %[[VAL_61]], %[[VAL_59]] : index +// CHECK: %[[VAL_65:.*]] = and %[[VAL_63]], %[[VAL_64]] : i1 +// CHECK: %[[VAL_66:.*]] = cmpi eq, %[[VAL_62]], %[[VAL_59]] : index +// CHECK: %[[VAL_67:.*]] = and %[[VAL_65]], %[[VAL_66]] : i1 +// CHECK: scf.if %[[VAL_67]] { +// CHECK: %[[VAL_68:.*]] = load %[[VAL_24]]{{\[}}%[[VAL_33]]] : memref +// CHECK: %[[VAL_69:.*]] = load %[[VAL_13]]{{\[}}%[[VAL_56]]] : memref +// CHECK: %[[VAL_70:.*]] = load %[[VAL_16]]{{\[}}%[[VAL_57]]] : memref +// CHECK: %[[VAL_71:.*]] = mulf %[[VAL_69]], %[[VAL_70]] : f32 +// CHECK: %[[VAL_72:.*]] = mulf %[[VAL_71]], %[[VAL_36]] : f32 +// CHECK: %[[VAL_73:.*]] = mulf %[[VAL_72]], %[[VAL_25]] : f32 +// CHECK: %[[VAL_74:.*]] = load %[[VAL_19]]{{\[}}%[[VAL_58]]] : memref +// CHECK: %[[VAL_75:.*]] = addf %[[VAL_73]], %[[VAL_74]] : f32 +// CHECK: %[[VAL_76:.*]] = addf %[[VAL_68]], %[[VAL_75]] : f32 +// CHECK: store %[[VAL_76]], %[[VAL_24]]{{\[}}%[[VAL_33]]] : memref // CHECK: } else { -// CHECK: %[[VAL_78:.*]] = cmpi eq, %[[VAL_61]], %[[VAL_60]] : index -// CHECK: %[[VAL_79:.*]] = cmpi eq, %[[VAL_62]], %[[VAL_60]] : index -// CHECK: %[[VAL_80:.*]] = and %[[VAL_78]], %[[VAL_79]] : i1 -// CHECK: scf.if %[[VAL_80]] { -// CHECK: %[[VAL_81:.*]] = load %[[VAL_25]]{{\[}}%[[VAL_34]]] : memref -// CHECK: %[[VAL_82:.*]] = load %[[VAL_14]]{{\[}}%[[VAL_57]]] : memref -// CHECK: %[[VAL_83:.*]] = load %[[VAL_17]]{{\[}}%[[VAL_58]]] : memref -// CHECK: %[[VAL_84:.*]] = mulf %[[VAL_82]], %[[VAL_83]] : f32 -// CHECK: %[[VAL_85:.*]] = mulf %[[VAL_84]], %[[VAL_37]] : f32 -// CHECK: %[[VAL_86:.*]] = mulf %[[VAL_85]], %[[VAL_26]] : f32 -// CHECK: %[[VAL_87:.*]] = addf %[[VAL_81]], %[[VAL_86]] : f32 -// CHECK: store %[[VAL_87]], %[[VAL_25]]{{\[}}%[[VAL_34]]] : memref +// CHECK: %[[VAL_77:.*]] = cmpi eq, %[[VAL_60]], %[[VAL_59]] : index +// CHECK: %[[VAL_78:.*]] = cmpi eq, %[[VAL_61]], %[[VAL_59]] : index +// CHECK: %[[VAL_79:.*]] = and %[[VAL_77]], %[[VAL_78]] : i1 +// CHECK: scf.if %[[VAL_79]] { +// CHECK: %[[VAL_80:.*]] = load %[[VAL_24]]{{\[}}%[[VAL_33]]] : memref +// CHECK: %[[VAL_81:.*]] = load %[[VAL_13]]{{\[}}%[[VAL_56]]] : memref +// CHECK: %[[VAL_82:.*]] = load %[[VAL_16]]{{\[}}%[[VAL_57]]] : memref +// CHECK: %[[VAL_83:.*]] = mulf %[[VAL_81]], %[[VAL_82]] : f32 +// CHECK: %[[VAL_84:.*]] = mulf %[[VAL_83]], %[[VAL_36]] : f32 +// CHECK: %[[VAL_85:.*]] = mulf %[[VAL_84]], %[[VAL_25]] : f32 +// CHECK: %[[VAL_86:.*]] = addf %[[VAL_80]], %[[VAL_85]] : f32 +// CHECK: store %[[VAL_86]], %[[VAL_24]]{{\[}}%[[VAL_33]]] : memref // CHECK: } else { -// CHECK: %[[VAL_88:.*]] = cmpi eq, %[[VAL_63]], %[[VAL_60]] : index -// CHECK: scf.if %[[VAL_88]] { -// CHECK: %[[VAL_89:.*]] = load %[[VAL_25]]{{\[}}%[[VAL_34]]] : memref -// CHECK: %[[VAL_90:.*]] = load %[[VAL_20]]{{\[}}%[[VAL_59]]] : memref -// CHECK: %[[VAL_91:.*]] = addf %[[VAL_89]], %[[VAL_90]] : f32 -// CHECK: store %[[VAL_91]], %[[VAL_25]]{{\[}}%[[VAL_34]]] : memref +// CHECK: %[[VAL_87:.*]] = cmpi eq, %[[VAL_62]], %[[VAL_59]] : index +// CHECK: scf.if %[[VAL_87]] { +// CHECK: %[[VAL_88:.*]] = load %[[VAL_24]]{{\[}}%[[VAL_33]]] : memref +// CHECK: %[[VAL_89:.*]] = load %[[VAL_19]]{{\[}}%[[VAL_58]]] : memref +// CHECK: %[[VAL_90:.*]] = addf %[[VAL_88]], %[[VAL_89]] : f32 +// CHECK: store %[[VAL_90]], %[[VAL_24]]{{\[}}%[[VAL_33]]] : memref // CHECK: } else { // CHECK: } // CHECK: } // CHECK: } -// CHECK: %[[VAL_92:.*]] = cmpi eq, %[[VAL_61]], %[[VAL_60]] : index -// CHECK: %[[VAL_93:.*]] = addi %[[VAL_57]], %[[VAL_9]] : index -// CHECK: %[[VAL_94:.*]] = select %[[VAL_92]], %[[VAL_93]], %[[VAL_57]] : index -// CHECK: %[[VAL_95:.*]] = cmpi eq, %[[VAL_62]], %[[VAL_60]] : index -// CHECK: %[[VAL_96:.*]] = addi %[[VAL_58]], %[[VAL_9]] : index -// CHECK: %[[VAL_97:.*]] = select %[[VAL_95]], %[[VAL_96]], %[[VAL_58]] : index -// CHECK: %[[VAL_98:.*]] = cmpi eq, %[[VAL_63]], %[[VAL_60]] : index -// CHECK: %[[VAL_99:.*]] = addi %[[VAL_59]], %[[VAL_9]] : index -// CHECK: %[[VAL_100:.*]] = select %[[VAL_98]], %[[VAL_99]], %[[VAL_59]] : index -// CHECK: %[[VAL_101:.*]] = addi %[[VAL_60]], %[[VAL_9]] : index -// CHECK: scf.yield %[[VAL_94]], %[[VAL_97]], %[[VAL_100]], %[[VAL_101]] : index, index, index, index +// CHECK: %[[VAL_91:.*]] = cmpi eq, %[[VAL_60]], %[[VAL_59]] : index +// CHECK: %[[VAL_92:.*]] = addi %[[VAL_56]], %[[VAL_8]] : index +// CHECK: %[[VAL_93:.*]] = select %[[VAL_91]], %[[VAL_92]], %[[VAL_56]] : index +// CHECK: %[[VAL_94:.*]] = cmpi eq, %[[VAL_61]], %[[VAL_59]] : index +// CHECK: %[[VAL_95:.*]] = addi %[[VAL_57]], %[[VAL_8]] : index +// CHECK: %[[VAL_96:.*]] = select %[[VAL_94]], %[[VAL_95]], %[[VAL_57]] : index +// CHECK: %[[VAL_97:.*]] = cmpi eq, %[[VAL_62]], %[[VAL_59]] : index +// CHECK: %[[VAL_98:.*]] = addi %[[VAL_58]], %[[VAL_8]] : index +// CHECK: %[[VAL_99:.*]] = select %[[VAL_97]], %[[VAL_98]], %[[VAL_58]] : index +// CHECK: %[[VAL_100:.*]] = addi %[[VAL_59]], %[[VAL_8]] : index +// CHECK: scf.yield %[[VAL_93]], %[[VAL_96]], %[[VAL_99]], %[[VAL_100]] : index, index, index, index // CHECK: } -// CHECK: %[[VAL_102:.*]]:3 = scf.while (%[[VAL_103:.*]] = %[[VAL_104:.*]]#0, %[[VAL_105:.*]] = %[[VAL_104]]#1, %[[VAL_106:.*]] = %[[VAL_104]]#3) : (index, index, index) -> (index, index, index) { -// CHECK: %[[VAL_107:.*]] = cmpi ult, %[[VAL_103]], %[[VAL_40]] : index -// CHECK: %[[VAL_108:.*]] = cmpi ult, %[[VAL_105]], %[[VAL_43]] : index -// CHECK: %[[VAL_109:.*]] = and %[[VAL_107]], %[[VAL_108]] : i1 -// CHECK: scf.condition(%[[VAL_109]]) %[[VAL_103]], %[[VAL_105]], %[[VAL_106]] : index, index, index +// CHECK: %[[VAL_101:.*]]:3 = scf.while (%[[VAL_102:.*]] = %[[VAL_103:.*]]#0, %[[VAL_104:.*]] = %[[VAL_103]]#1, %[[VAL_105:.*]] = %[[VAL_103]]#3) : (index, index, index) -> (index, index, index) { +// CHECK: %[[VAL_106:.*]] = cmpi ult, %[[VAL_102]], %[[VAL_39]] : index +// CHECK: %[[VAL_107:.*]] = cmpi ult, %[[VAL_104]], %[[VAL_42]] : index +// CHECK: %[[VAL_108:.*]] = and %[[VAL_106]], %[[VAL_107]] : i1 +// CHECK: scf.condition(%[[VAL_108]]) %[[VAL_102]], %[[VAL_104]], %[[VAL_105]] : index, index, index // CHECK: } do { -// CHECK: ^bb0(%[[VAL_110:.*]]: index, %[[VAL_111:.*]]: index, %[[VAL_112:.*]]: index): -// CHECK: %[[VAL_113:.*]] = load %[[VAL_13]]{{\[}}%[[VAL_110]]] : memref -// CHECK: %[[VAL_114:.*]] = load %[[VAL_16]]{{\[}}%[[VAL_111]]] : memref -// CHECK: %[[VAL_115:.*]] = cmpi eq, %[[VAL_113]], %[[VAL_112]] : index -// CHECK: %[[VAL_116:.*]] = cmpi eq, %[[VAL_114]], %[[VAL_112]] : index -// CHECK: %[[VAL_117:.*]] = and %[[VAL_115]], %[[VAL_116]] : i1 -// CHECK: scf.if %[[VAL_117]] { -// CHECK: %[[VAL_118:.*]] = load %[[VAL_25]]{{\[}}%[[VAL_34]]] : memref -// CHECK: %[[VAL_119:.*]] = load %[[VAL_14]]{{\[}}%[[VAL_110]]] : memref -// CHECK: %[[VAL_120:.*]] = load %[[VAL_17]]{{\[}}%[[VAL_111]]] : memref -// CHECK: %[[VAL_121:.*]] = mulf %[[VAL_119]], %[[VAL_120]] : f32 -// CHECK: %[[VAL_122:.*]] = mulf %[[VAL_121]], %[[VAL_37]] : f32 -// CHECK: %[[VAL_123:.*]] = mulf %[[VAL_122]], %[[VAL_26]] : f32 -// CHECK: %[[VAL_124:.*]] = addf %[[VAL_118]], %[[VAL_123]] : f32 -// CHECK: store %[[VAL_124]], %[[VAL_25]]{{\[}}%[[VAL_34]]] : memref +// CHECK: ^bb0(%[[VAL_109:.*]]: index, %[[VAL_110:.*]]: index, %[[VAL_111:.*]]: index): +// CHECK: %[[VAL_112:.*]] = load %[[VAL_12]]{{\[}}%[[VAL_109]]] : memref +// CHECK: %[[VAL_113:.*]] = load %[[VAL_15]]{{\[}}%[[VAL_110]]] : memref +// CHECK: %[[VAL_114:.*]] = cmpi eq, %[[VAL_112]], %[[VAL_111]] : index +// CHECK: %[[VAL_115:.*]] = cmpi eq, %[[VAL_113]], %[[VAL_111]] : index +// CHECK: %[[VAL_116:.*]] = and %[[VAL_114]], %[[VAL_115]] : i1 +// CHECK: scf.if %[[VAL_116]] { +// CHECK: %[[VAL_117:.*]] = load %[[VAL_24]]{{\[}}%[[VAL_33]]] : memref +// CHECK: %[[VAL_118:.*]] = load %[[VAL_13]]{{\[}}%[[VAL_109]]] : memref +// CHECK: %[[VAL_119:.*]] = load %[[VAL_16]]{{\[}}%[[VAL_110]]] : memref +// CHECK: %[[VAL_120:.*]] = mulf %[[VAL_118]], %[[VAL_119]] : f32 +// CHECK: %[[VAL_121:.*]] = mulf %[[VAL_120]], %[[VAL_36]] : f32 +// CHECK: %[[VAL_122:.*]] = mulf %[[VAL_121]], %[[VAL_25]] : f32 +// CHECK: %[[VAL_123:.*]] = addf %[[VAL_117]], %[[VAL_122]] : f32 +// CHECK: store %[[VAL_123]], %[[VAL_24]]{{\[}}%[[VAL_33]]] : memref // CHECK: } else { // CHECK: } -// CHECK: %[[VAL_125:.*]] = cmpi eq, %[[VAL_113]], %[[VAL_112]] : index -// CHECK: %[[VAL_126:.*]] = addi %[[VAL_110]], %[[VAL_9]] : index -// CHECK: %[[VAL_127:.*]] = select %[[VAL_125]], %[[VAL_126]], %[[VAL_110]] : index -// CHECK: %[[VAL_128:.*]] = cmpi eq, %[[VAL_114]], %[[VAL_112]] : index -// CHECK: %[[VAL_129:.*]] = addi %[[VAL_111]], %[[VAL_9]] : index -// CHECK: %[[VAL_130:.*]] = select %[[VAL_128]], %[[VAL_129]], %[[VAL_111]] : index -// CHECK: %[[VAL_131:.*]] = addi %[[VAL_112]], %[[VAL_9]] : index -// CHECK: scf.yield %[[VAL_127]], %[[VAL_130]], %[[VAL_131]] : index, index, index +// CHECK: %[[VAL_124:.*]] = cmpi eq, %[[VAL_112]], %[[VAL_111]] : index +// CHECK: %[[VAL_125:.*]] = addi %[[VAL_109]], %[[VAL_8]] : index +// CHECK: %[[VAL_126:.*]] = select %[[VAL_124]], %[[VAL_125]], %[[VAL_109]] : index +// CHECK: %[[VAL_127:.*]] = cmpi eq, %[[VAL_113]], %[[VAL_111]] : index +// CHECK: %[[VAL_128:.*]] = addi %[[VAL_110]], %[[VAL_8]] : index +// CHECK: %[[VAL_129:.*]] = select %[[VAL_127]], %[[VAL_128]], %[[VAL_110]] : index +// CHECK: %[[VAL_130:.*]] = addi %[[VAL_111]], %[[VAL_8]] : index +// CHECK: scf.yield %[[VAL_126]], %[[VAL_129]], %[[VAL_130]] : index, index, index // CHECK: } -// CHECK: %[[VAL_132:.*]] = load %[[VAL_25]]{{\[}}%[[VAL_34]]] : memref -// CHECK: %[[VAL_133:.*]] = scf.for %[[VAL_134:.*]] = %[[VAL_135:.*]]#2 to %[[VAL_46]] step %[[VAL_9]] iter_args(%[[VAL_136:.*]] = %[[VAL_132]]) -> (f32) { -// CHECK: %[[VAL_137:.*]] = load %[[VAL_20]]{{\[}}%[[VAL_134]]] : memref -// CHECK: %[[VAL_138:.*]] = addf %[[VAL_136]], %[[VAL_137]] : f32 -// CHECK: scf.yield %[[VAL_138]] : f32 +// CHECK: %[[VAL_131:.*]] = load %[[VAL_24]]{{\[}}%[[VAL_33]]] : memref +// CHECK: %[[VAL_132:.*]] = scf.for %[[VAL_133:.*]] = %[[VAL_134:.*]]#2 to %[[VAL_45]] step %[[VAL_8]] iter_args(%[[VAL_135:.*]] = %[[VAL_131]]) -> (f32) { +// CHECK: %[[VAL_136:.*]] = load %[[VAL_19]]{{\[}}%[[VAL_133]]] : memref +// CHECK: %[[VAL_137:.*]] = addf %[[VAL_135]], %[[VAL_136]] : f32 +// CHECK: scf.yield %[[VAL_137]] : f32 // CHECK: } -// CHECK: store %[[VAL_139:.*]], %[[VAL_25]]{{\[}}%[[VAL_34]]] : memref +// CHECK: store %[[VAL_138:.*]], %[[VAL_24]]{{\[}}%[[VAL_33]]] : memref // CHECK: } else { -// CHECK: scf.if %[[VAL_8]] { -// CHECK: %[[VAL_140:.*]] = load %[[VAL_18]]{{\[}}%[[VAL_34]]] : memref -// CHECK: %[[VAL_141:.*]] = addi %[[VAL_34]], %[[VAL_9]] : index -// CHECK: %[[VAL_142:.*]] = load %[[VAL_18]]{{\[}}%[[VAL_141]]] : memref -// CHECK: %[[VAL_143:.*]] = load %[[VAL_25]]{{\[}}%[[VAL_34]]] : memref -// CHECK: %[[VAL_144:.*]] = scf.for %[[VAL_145:.*]] = %[[VAL_140]] to %[[VAL_142]] step %[[VAL_9]] iter_args(%[[VAL_146:.*]] = %[[VAL_143]]) -> (f32) { -// CHECK: %[[VAL_147:.*]] = load %[[VAL_20]]{{\[}}%[[VAL_145]]] : memref -// CHECK: %[[VAL_148:.*]] = addf %[[VAL_146]], %[[VAL_147]] : f32 -// CHECK: scf.yield %[[VAL_148]] : f32 +// CHECK: scf.if %[[VAL_7]] { +// CHECK: %[[VAL_139:.*]] = load %[[VAL_17]]{{\[}}%[[VAL_33]]] : memref +// CHECK: %[[VAL_140:.*]] = addi %[[VAL_33]], %[[VAL_8]] : index +// CHECK: %[[VAL_141:.*]] = load %[[VAL_17]]{{\[}}%[[VAL_140]]] : memref +// CHECK: %[[VAL_142:.*]] = load %[[VAL_24]]{{\[}}%[[VAL_33]]] : memref +// CHECK: %[[VAL_143:.*]] = scf.for %[[VAL_144:.*]] = %[[VAL_139]] to %[[VAL_141]] step %[[VAL_8]] iter_args(%[[VAL_145:.*]] = %[[VAL_142]]) -> (f32) { +// CHECK: %[[VAL_146:.*]] = load %[[VAL_19]]{{\[}}%[[VAL_144]]] : memref +// CHECK: %[[VAL_147:.*]] = addf %[[VAL_145]], %[[VAL_146]] : f32 +// CHECK: scf.yield %[[VAL_147]] : f32 // CHECK: } -// CHECK: store %[[VAL_149:.*]], %[[VAL_25]]{{\[}}%[[VAL_34]]] : memref +// CHECK: store %[[VAL_148:.*]], %[[VAL_24]]{{\[}}%[[VAL_33]]] : memref // CHECK: } else { // CHECK: } // CHECK: } -// CHECK: %[[VAL_150:.*]] = cmpi eq, %[[VAL_35]], %[[VAL_34]] : index -// CHECK: %[[VAL_151:.*]] = addi %[[VAL_33]], %[[VAL_9]] : index -// CHECK: %[[VAL_152:.*]] = select %[[VAL_150]], %[[VAL_151]], %[[VAL_33]] : index -// CHECK: %[[VAL_153:.*]] = addi %[[VAL_34]], %[[VAL_9]] : index -// CHECK: scf.yield %[[VAL_152]], %[[VAL_153]] : index, index +// CHECK: %[[VAL_149:.*]] = cmpi eq, %[[VAL_34]], %[[VAL_33]] : index +// CHECK: %[[VAL_150:.*]] = addi %[[VAL_32]], %[[VAL_8]] : index +// CHECK: %[[VAL_151:.*]] = select %[[VAL_149]], %[[VAL_150]], %[[VAL_32]] : index +// CHECK: %[[VAL_152:.*]] = addi %[[VAL_33]], %[[VAL_8]] : index +// CHECK: scf.yield %[[VAL_151]], %[[VAL_152]] : index, index // CHECK: } -// CHECK: scf.for %[[VAL_154:.*]] = %[[VAL_155:.*]]#1 to %[[VAL_24]] step %[[VAL_9]] { -// CHECK: %[[VAL_156:.*]] = load %[[VAL_18]]{{\[}}%[[VAL_154]]] : memref -// CHECK: %[[VAL_157:.*]] = addi %[[VAL_154]], %[[VAL_9]] : index -// CHECK: %[[VAL_158:.*]] = load %[[VAL_18]]{{\[}}%[[VAL_157]]] : memref -// CHECK: %[[VAL_159:.*]] = load %[[VAL_25]]{{\[}}%[[VAL_154]]] : memref -// CHECK: %[[VAL_160:.*]] = scf.for %[[VAL_161:.*]] = %[[VAL_156]] to %[[VAL_158]] step %[[VAL_9]] iter_args(%[[VAL_162:.*]] = %[[VAL_159]]) -> (f32) { -// CHECK: %[[VAL_163:.*]] = load %[[VAL_20]]{{\[}}%[[VAL_161]]] : memref -// CHECK: %[[VAL_164:.*]] = addf %[[VAL_162]], %[[VAL_163]] : f32 -// CHECK: scf.yield %[[VAL_164]] : f32 +// CHECK: scf.for %[[VAL_153:.*]] = %[[VAL_154:.*]]#1 to %[[VAL_22]] step %[[VAL_8]] { +// CHECK: %[[VAL_155:.*]] = load %[[VAL_17]]{{\[}}%[[VAL_153]]] : memref +// CHECK: %[[VAL_156:.*]] = addi %[[VAL_153]], %[[VAL_8]] : index +// CHECK: %[[VAL_157:.*]] = load %[[VAL_17]]{{\[}}%[[VAL_156]]] : memref +// CHECK: %[[VAL_158:.*]] = load %[[VAL_24]]{{\[}}%[[VAL_153]]] : memref +// CHECK: %[[VAL_159:.*]] = scf.for %[[VAL_160:.*]] = %[[VAL_155]] to %[[VAL_157]] step %[[VAL_8]] iter_args(%[[VAL_161:.*]] = %[[VAL_158]]) -> (f32) { +// CHECK: %[[VAL_162:.*]] = load %[[VAL_19]]{{\[}}%[[VAL_160]]] : memref +// CHECK: %[[VAL_163:.*]] = addf %[[VAL_161]], %[[VAL_162]] : f32 +// CHECK: scf.yield %[[VAL_163]] : f32 // CHECK: } -// CHECK: store %[[VAL_165:.*]], %[[VAL_25]]{{\[}}%[[VAL_154]]] : memref +// CHECK: store %[[VAL_164:.*]], %[[VAL_24]]{{\[}}%[[VAL_153]]] : memref // CHECK: } -// CHECK: %[[VAL_166:.*]] = tensor_load %[[VAL_25]] : memref -// CHECK: return %[[VAL_166]] : tensor +// CHECK: %[[VAL_165:.*]] = tensor_load %[[VAL_24]] : memref +// CHECK: return %[[VAL_165]] : tensor // CHECK: } func @sum_kernel_with_inv(%arga: tensor, %argb: tensor, diff --git a/mlir/test/Dialect/Linalg/sparse_3d.mlir b/mlir/test/Dialect/Linalg/sparse_3d.mlir --- a/mlir/test/Dialect/Linalg/sparse_3d.mlir +++ b/mlir/test/Dialect/Linalg/sparse_3d.mlir @@ -25,21 +25,23 @@ // CHECK: %[[VAL_5:.*]] = constant 8 : index // CHECK: %[[VAL_6:.*]] = constant 0 : index // CHECK: %[[VAL_7:.*]] = constant 1 : index -// CHECK: %[[VAL_8:.*]] = alloca() : memref<32x16x8xf32> -// CHECK: %[[VAL_9:.*]] = alloca() : memref<32x16x8xf32> -// CHECK: %[[VAL_10:.*]] = alloca() : memref<32x16x8xf32> -// CHECK: scf.for %[[VAL_11:.*]] = %[[VAL_6]] to %[[VAL_3]] step %[[VAL_7]] { -// CHECK: scf.for %[[VAL_12:.*]] = %[[VAL_6]] to %[[VAL_4]] step %[[VAL_7]] { -// CHECK: scf.for %[[VAL_13:.*]] = %[[VAL_6]] to %[[VAL_5]] step %[[VAL_7]] { -// CHECK: %[[VAL_14:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_11]], %[[VAL_12]], %[[VAL_13]]] : memref<32x16x8xf32> -// CHECK: %[[VAL_15:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_11]], %[[VAL_12]], %[[VAL_13]]] : memref<32x16x8xf32> -// CHECK: %[[VAL_16:.*]] = addf %[[VAL_14]], %[[VAL_15]] : f32 -// CHECK: store %[[VAL_16]], %[[VAL_10]]{{\[}}%[[VAL_11]], %[[VAL_12]], %[[VAL_13]]] : memref<32x16x8xf32> +// CHECK: %[[VAL_8:.*]] = tensor_to_memref %[[VAL_0]] : memref<32x16x8xf32> +// CHECK: %[[VAL_9:.*]] = tensor_to_memref %[[VAL_1]] : memref<32x16x8xf32> +// CHECK: %[[VAL_10:.*]] = tensor_to_memref %[[VAL_2]] : memref<32x16x8xf32> +// CHECK: %[[VAL_11:.*]] = alloc() : memref<32x16x8xf32> +// CHECK: linalg.copy(%[[VAL_10]], %[[VAL_11]]) : memref<32x16x8xf32>, memref<32x16x8xf32> +// CHECK: scf.for %[[VAL_12:.*]] = %[[VAL_6]] to %[[VAL_3]] step %[[VAL_7]] { +// CHECK: scf.for %[[VAL_13:.*]] = %[[VAL_6]] to %[[VAL_4]] step %[[VAL_7]] { +// CHECK: scf.for %[[VAL_14:.*]] = %[[VAL_6]] to %[[VAL_5]] step %[[VAL_7]] { +// CHECK: %[[VAL_15:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_12]], %[[VAL_13]], %[[VAL_14]]] : memref<32x16x8xf32> +// CHECK: %[[VAL_16:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_12]], %[[VAL_13]], %[[VAL_14]]] : memref<32x16x8xf32> +// CHECK: %[[VAL_17:.*]] = addf %[[VAL_15]], %[[VAL_16]] : f32 +// CHECK: store %[[VAL_17]], %[[VAL_11]]{{\[}}%[[VAL_12]], %[[VAL_13]], %[[VAL_14]]] : memref<32x16x8xf32> // CHECK: } // CHECK: } // CHECK: } -// CHECK: %[[VAL_17:.*]] = tensor_load %[[VAL_10]] : memref<32x16x8xf32> -// CHECK: return %[[VAL_17]] : tensor<32x16x8xf32> +// CHECK: %[[VAL_18:.*]] = tensor_load %[[VAL_11]] : memref<32x16x8xf32> +// CHECK: return %[[VAL_18]] : tensor<32x16x8xf32> // CHECK: } func @add_ddd(%arga: tensor<32x16x8xf32>, %argb: tensor<32x16x8xf32>, %argx: tensor<32x16x8xf32>) -> tensor<32x16x8xf32> { %0 = linalg.generic #trait_ddd @@ -61,21 +63,23 @@ // CHECK: %[[VAL_5:.*]] = constant 8 : index // CHECK: %[[VAL_6:.*]] = constant 0 : index // CHECK: %[[VAL_7:.*]] = constant 1 : index -// CHECK: %[[VAL_8:.*]] = alloca() : memref<32x16x8xf32> -// CHECK: %[[VAL_9:.*]] = alloca() : memref<32x16x8xf32> -// CHECK: %[[VAL_10:.*]] = alloca() : memref<32x16x8xf32> -// CHECK: scf.for %[[VAL_11:.*]] = %[[VAL_6]] to %[[VAL_3]] step %[[VAL_7]] { -// CHECK: scf.for %[[VAL_12:.*]] = %[[VAL_6]] to %[[VAL_4]] step %[[VAL_7]] { -// CHECK: scf.for %[[VAL_13:.*]] = %[[VAL_6]] to %[[VAL_5]] step %[[VAL_7]] { -// CHECK: %[[VAL_14:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_11]], %[[VAL_12]], %[[VAL_13]]] : memref<32x16x8xf32> -// CHECK: %[[VAL_15:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_11]], %[[VAL_12]], %[[VAL_13]]] : memref<32x16x8xf32> -// CHECK: %[[VAL_16:.*]] = mulf %[[VAL_14]], %[[VAL_15]] : f32 -// CHECK: store %[[VAL_16]], %[[VAL_10]]{{\[}}%[[VAL_11]], %[[VAL_12]], %[[VAL_13]]] : memref<32x16x8xf32> +// CHECK: %[[VAL_8:.*]] = tensor_to_memref %[[VAL_0]] : memref<32x16x8xf32> +// CHECK: %[[VAL_9:.*]] = tensor_to_memref %[[VAL_1]] : memref<32x16x8xf32> +// CHECK: %[[VAL_10:.*]] = tensor_to_memref %[[VAL_2]] : memref<32x16x8xf32> +// CHECK: %[[VAL_11:.*]] = alloc() : memref<32x16x8xf32> +// CHECK: linalg.copy(%[[VAL_10]], %[[VAL_11]]) : memref<32x16x8xf32>, memref<32x16x8xf32> +// CHECK: scf.for %[[VAL_12:.*]] = %[[VAL_6]] to %[[VAL_3]] step %[[VAL_7]] { +// CHECK: scf.for %[[VAL_13:.*]] = %[[VAL_6]] to %[[VAL_4]] step %[[VAL_7]] { +// CHECK: scf.for %[[VAL_14:.*]] = %[[VAL_6]] to %[[VAL_5]] step %[[VAL_7]] { +// CHECK: %[[VAL_15:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_12]], %[[VAL_13]], %[[VAL_14]]] : memref<32x16x8xf32> +// CHECK: %[[VAL_16:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_12]], %[[VAL_13]], %[[VAL_14]]] : memref<32x16x8xf32> +// CHECK: %[[VAL_17:.*]] = mulf %[[VAL_15]], %[[VAL_16]] : f32 +// CHECK: store %[[VAL_17]], %[[VAL_11]]{{\[}}%[[VAL_12]], %[[VAL_13]], %[[VAL_14]]] : memref<32x16x8xf32> // CHECK: } // CHECK: } // CHECK: } -// CHECK: %[[VAL_17:.*]] = tensor_load %[[VAL_10]] : memref<32x16x8xf32> -// CHECK: return %[[VAL_17]] : tensor<32x16x8xf32> +// CHECK: %[[VAL_18:.*]] = tensor_load %[[VAL_11]] : memref<32x16x8xf32> +// CHECK: return %[[VAL_18]] : tensor<32x16x8xf32> // CHECK: } func @mul_ddd(%arga: tensor<32x16x8xf32>, %argb: tensor<32x16x8xf32>, %argx: tensor<32x16x8xf32>) -> tensor<32x16x8xf32> { %0 = linalg.generic #trait_ddd @@ -107,58 +111,60 @@ // CHECK-SAME: %[[VAL_0:.*0]]: tensor<32x16x8xf32>, // CHECK-SAME: %[[VAL_1:.*1]]: tensor<32x16x8xf32>, // CHECK-SAME: %[[VAL_2:.*2]]: tensor<32x16x8xf32>) -> tensor<32x16x8xf32> { -// CHECK: %[[VAL_3:.*]] = constant 999 : index +// CHECK: %[[VAL_3:.*]] = constant 2 : index // CHECK: %[[VAL_4:.*]] = constant 32 : index // CHECK: %[[VAL_5:.*]] = constant 16 : index // CHECK: %[[VAL_6:.*]] = constant 8 : index // CHECK: %[[VAL_7:.*]] = constant 0 : index // CHECK: %[[VAL_8:.*]] = constant true // CHECK: %[[VAL_9:.*]] = constant 1 : index -// CHECK: %[[VAL_10:.*]] = alloca(%[[VAL_3]]) : memref -// CHECK: %[[VAL_11:.*]] = alloca(%[[VAL_3]]) : memref -// CHECK: %[[VAL_12:.*]] = alloca(%[[VAL_3]]) : memref -// CHECK: %[[VAL_13:.*]] = alloca() : memref<32x16x8xf32> -// CHECK: %[[VAL_14:.*]] = alloca() : memref<32x16x8xf32> -// CHECK: scf.for %[[VAL_15:.*]] = %[[VAL_7]] to %[[VAL_4]] step %[[VAL_9]] { -// CHECK: scf.for %[[VAL_16:.*]] = %[[VAL_7]] to %[[VAL_5]] step %[[VAL_9]] { -// CHECK: %[[VAL_17:.*]] = muli %[[VAL_15]], %[[VAL_5]] : index -// CHECK: %[[VAL_18:.*]] = addi %[[VAL_17]], %[[VAL_16]] : index -// CHECK: %[[VAL_19:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_18]]] : memref -// CHECK: %[[VAL_20:.*]] = addi %[[VAL_18]], %[[VAL_9]] : index -// CHECK: %[[VAL_21:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_20]]] : memref -// CHECK: %[[VAL_22:.*]]:2 = scf.while (%[[VAL_23:.*]] = %[[VAL_19]], %[[VAL_24:.*]] = %[[VAL_7]]) : (index, index) -> (index, index) { -// CHECK: %[[VAL_25:.*]] = cmpi ult, %[[VAL_23]], %[[VAL_21]] : index -// CHECK: scf.condition(%[[VAL_25]]) %[[VAL_23]], %[[VAL_24]] : index, index +// CHECK: %[[VAL_10:.*]] = linalg.sparse_pointers %[[VAL_0]], %[[VAL_3]] : tensor<32x16x8xf32> into memref +// CHECK: %[[VAL_11:.*]] = linalg.sparse_indices %[[VAL_0]], %[[VAL_3]] : tensor<32x16x8xf32> into memref +// CHECK: %[[VAL_12:.*]] = linalg.sparse_values %[[VAL_0]] : tensor<32x16x8xf32> into memref +// CHECK: %[[VAL_13:.*]] = tensor_to_memref %[[VAL_1]] : memref<32x16x8xf32> +// CHECK: %[[VAL_14:.*]] = tensor_to_memref %[[VAL_2]] : memref<32x16x8xf32> +// CHECK: %[[VAL_15:.*]] = alloc() : memref<32x16x8xf32> +// CHECK: linalg.copy(%[[VAL_14]], %[[VAL_15]]) : memref<32x16x8xf32>, memref<32x16x8xf32> +// CHECK: scf.for %[[VAL_16:.*]] = %[[VAL_7]] to %[[VAL_4]] step %[[VAL_9]] { +// CHECK: scf.for %[[VAL_17:.*]] = %[[VAL_7]] to %[[VAL_5]] step %[[VAL_9]] { +// CHECK: %[[VAL_18:.*]] = muli %[[VAL_16]], %[[VAL_5]] : index +// CHECK: %[[VAL_19:.*]] = addi %[[VAL_18]], %[[VAL_17]] : index +// CHECK: %[[VAL_20:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_19]]] : memref +// CHECK: %[[VAL_21:.*]] = addi %[[VAL_19]], %[[VAL_9]] : index +// CHECK: %[[VAL_22:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_21]]] : memref +// CHECK: %[[VAL_23:.*]]:2 = scf.while (%[[VAL_24:.*]] = %[[VAL_20]], %[[VAL_25:.*]] = %[[VAL_7]]) : (index, index) -> (index, index) { +// CHECK: %[[VAL_26:.*]] = cmpi ult, %[[VAL_24]], %[[VAL_22]] : index +// CHECK: scf.condition(%[[VAL_26]]) %[[VAL_24]], %[[VAL_25]] : index, index // CHECK: } do { -// CHECK: ^bb0(%[[VAL_26:.*]]: index, %[[VAL_27:.*]]: index): -// CHECK: %[[VAL_28:.*]] = load %[[VAL_11]]{{\[}}%[[VAL_26]]] : memref -// CHECK: %[[VAL_29:.*]] = cmpi eq, %[[VAL_28]], %[[VAL_27]] : index -// CHECK: scf.if %[[VAL_29]] { -// CHECK: %[[VAL_30:.*]] = load %[[VAL_12]]{{\[}}%[[VAL_26]]] : memref -// CHECK: %[[VAL_31:.*]] = load %[[VAL_13]]{{\[}}%[[VAL_15]], %[[VAL_16]], %[[VAL_27]]] : memref<32x16x8xf32> -// CHECK: %[[VAL_32:.*]] = addf %[[VAL_30]], %[[VAL_31]] : f32 -// CHECK: store %[[VAL_32]], %[[VAL_14]]{{\[}}%[[VAL_15]], %[[VAL_16]], %[[VAL_27]]] : memref<32x16x8xf32> +// CHECK: ^bb0(%[[VAL_27:.*]]: index, %[[VAL_28:.*]]: index): +// CHECK: %[[VAL_29:.*]] = load %[[VAL_11]]{{\[}}%[[VAL_27]]] : memref +// CHECK: %[[VAL_30:.*]] = cmpi eq, %[[VAL_29]], %[[VAL_28]] : index +// CHECK: scf.if %[[VAL_30]] { +// CHECK: %[[VAL_31:.*]] = load %[[VAL_12]]{{\[}}%[[VAL_27]]] : memref +// CHECK: %[[VAL_32:.*]] = load %[[VAL_13]]{{\[}}%[[VAL_16]], %[[VAL_17]], %[[VAL_28]]] : memref<32x16x8xf32> +// CHECK: %[[VAL_33:.*]] = addf %[[VAL_31]], %[[VAL_32]] : f32 +// CHECK: store %[[VAL_33]], %[[VAL_15]]{{\[}}%[[VAL_16]], %[[VAL_17]], %[[VAL_28]]] : memref<32x16x8xf32> // CHECK: } else { // CHECK: scf.if %[[VAL_8]] { -// CHECK: %[[VAL_33:.*]] = load %[[VAL_13]]{{\[}}%[[VAL_15]], %[[VAL_16]], %[[VAL_27]]] : memref<32x16x8xf32> -// CHECK: store %[[VAL_33]], %[[VAL_14]]{{\[}}%[[VAL_15]], %[[VAL_16]], %[[VAL_27]]] : memref<32x16x8xf32> +// CHECK: %[[VAL_34:.*]] = load %[[VAL_13]]{{\[}}%[[VAL_16]], %[[VAL_17]], %[[VAL_28]]] : memref<32x16x8xf32> +// CHECK: store %[[VAL_34]], %[[VAL_15]]{{\[}}%[[VAL_16]], %[[VAL_17]], %[[VAL_28]]] : memref<32x16x8xf32> // CHECK: } else { // CHECK: } // CHECK: } -// CHECK: %[[VAL_34:.*]] = cmpi eq, %[[VAL_28]], %[[VAL_27]] : index -// CHECK: %[[VAL_35:.*]] = addi %[[VAL_26]], %[[VAL_9]] : index -// CHECK: %[[VAL_36:.*]] = select %[[VAL_34]], %[[VAL_35]], %[[VAL_26]] : index -// CHECK: %[[VAL_37:.*]] = addi %[[VAL_27]], %[[VAL_9]] : index -// CHECK: scf.yield %[[VAL_36]], %[[VAL_37]] : index, index +// CHECK: %[[VAL_35:.*]] = cmpi eq, %[[VAL_29]], %[[VAL_28]] : index +// CHECK: %[[VAL_36:.*]] = addi %[[VAL_27]], %[[VAL_9]] : index +// CHECK: %[[VAL_37:.*]] = select %[[VAL_35]], %[[VAL_36]], %[[VAL_27]] : index +// CHECK: %[[VAL_38:.*]] = addi %[[VAL_28]], %[[VAL_9]] : index +// CHECK: scf.yield %[[VAL_37]], %[[VAL_38]] : index, index // CHECK: } -// CHECK: scf.for %[[VAL_38:.*]] = %[[VAL_39:.*]]#1 to %[[VAL_6]] step %[[VAL_9]] { -// CHECK: %[[VAL_40:.*]] = load %[[VAL_13]]{{\[}}%[[VAL_15]], %[[VAL_16]], %[[VAL_38]]] : memref<32x16x8xf32> -// CHECK: store %[[VAL_40]], %[[VAL_14]]{{\[}}%[[VAL_15]], %[[VAL_16]], %[[VAL_38]]] : memref<32x16x8xf32> +// CHECK: scf.for %[[VAL_39:.*]] = %[[VAL_40:.*]]#1 to %[[VAL_6]] step %[[VAL_9]] { +// CHECK: %[[VAL_41:.*]] = load %[[VAL_13]]{{\[}}%[[VAL_16]], %[[VAL_17]], %[[VAL_39]]] : memref<32x16x8xf32> +// CHECK: store %[[VAL_41]], %[[VAL_15]]{{\[}}%[[VAL_16]], %[[VAL_17]], %[[VAL_39]]] : memref<32x16x8xf32> // CHECK: } // CHECK: } // CHECK: } -// CHECK: %[[VAL_41:.*]] = tensor_load %[[VAL_14]] : memref<32x16x8xf32> -// CHECK: return %[[VAL_41]] : tensor<32x16x8xf32> +// CHECK: %[[VAL_42:.*]] = tensor_load %[[VAL_15]] : memref<32x16x8xf32> +// CHECK: return %[[VAL_42]] : tensor<32x16x8xf32> // CHECK: } func @add_dds(%arga: tensor<32x16x8xf32>, %argb: tensor<32x16x8xf32>, %argx: tensor<32x16x8xf32>) -> tensor<32x16x8xf32> { %0 = linalg.generic #trait_dds @@ -175,34 +181,36 @@ // CHECK-SAME: %[[VAL_0:.*0]]: tensor<32x16x8xf32>, // CHECK-SAME: %[[VAL_1:.*1]]: tensor<32x16x8xf32>, // CHECK-SAME: %[[VAL_2:.*2]]: tensor<32x16x8xf32>) -> tensor<32x16x8xf32> { -// CHECK: %[[VAL_3:.*]] = constant 999 : index +// CHECK: %[[VAL_3:.*]] = constant 2 : index // CHECK: %[[VAL_4:.*]] = constant 32 : index // CHECK: %[[VAL_5:.*]] = constant 16 : index // CHECK: %[[VAL_6:.*]] = constant 0 : index // CHECK: %[[VAL_7:.*]] = constant 1 : index -// CHECK: %[[VAL_8:.*]] = alloca(%[[VAL_3]]) : memref -// CHECK: %[[VAL_9:.*]] = alloca(%[[VAL_3]]) : memref -// CHECK: %[[VAL_10:.*]] = alloca(%[[VAL_3]]) : memref -// CHECK: %[[VAL_11:.*]] = alloca() : memref<32x16x8xf32> -// CHECK: %[[VAL_12:.*]] = alloca() : memref<32x16x8xf32> -// CHECK: scf.for %[[VAL_13:.*]] = %[[VAL_6]] to %[[VAL_4]] step %[[VAL_7]] { -// CHECK: scf.for %[[VAL_14:.*]] = %[[VAL_6]] to %[[VAL_5]] step %[[VAL_7]] { -// CHECK: %[[VAL_15:.*]] = muli %[[VAL_13]], %[[VAL_5]] : index -// CHECK: %[[VAL_16:.*]] = addi %[[VAL_15]], %[[VAL_14]] : index -// CHECK: %[[VAL_17:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_16]]] : memref -// CHECK: %[[VAL_18:.*]] = addi %[[VAL_16]], %[[VAL_7]] : index -// CHECK: %[[VAL_19:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_18]]] : memref -// CHECK: scf.for %[[VAL_20:.*]] = %[[VAL_17]] to %[[VAL_19]] step %[[VAL_7]] { -// CHECK: %[[VAL_21:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_20]]] : memref -// CHECK: %[[VAL_22:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_20]]] : memref -// CHECK: %[[VAL_23:.*]] = load %[[VAL_11]]{{\[}}%[[VAL_13]], %[[VAL_14]], %[[VAL_21]]] : memref<32x16x8xf32> -// CHECK: %[[VAL_24:.*]] = mulf %[[VAL_22]], %[[VAL_23]] : f32 -// CHECK: store %[[VAL_24]], %[[VAL_12]]{{\[}}%[[VAL_13]], %[[VAL_14]], %[[VAL_21]]] : memref<32x16x8xf32> +// CHECK: %[[VAL_8:.*]] = linalg.sparse_pointers %[[VAL_0]], %[[VAL_3]] : tensor<32x16x8xf32> into memref +// CHECK: %[[VAL_9:.*]] = linalg.sparse_indices %[[VAL_0]], %[[VAL_3]] : tensor<32x16x8xf32> into memref +// CHECK: %[[VAL_10:.*]] = linalg.sparse_values %[[VAL_0]] : tensor<32x16x8xf32> into memref +// CHECK: %[[VAL_11:.*]] = tensor_to_memref %[[VAL_1]] : memref<32x16x8xf32> +// CHECK: %[[VAL_12:.*]] = tensor_to_memref %[[VAL_2]] : memref<32x16x8xf32> +// CHECK: %[[VAL_13:.*]] = alloc() : memref<32x16x8xf32> +// CHECK: linalg.copy(%[[VAL_12]], %[[VAL_13]]) : memref<32x16x8xf32>, memref<32x16x8xf32> +// CHECK: scf.for %[[VAL_14:.*]] = %[[VAL_6]] to %[[VAL_4]] step %[[VAL_7]] { +// CHECK: scf.for %[[VAL_15:.*]] = %[[VAL_6]] to %[[VAL_5]] step %[[VAL_7]] { +// CHECK: %[[VAL_16:.*]] = muli %[[VAL_14]], %[[VAL_5]] : index +// CHECK: %[[VAL_17:.*]] = addi %[[VAL_16]], %[[VAL_15]] : index +// CHECK: %[[VAL_18:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_17]]] : memref +// CHECK: %[[VAL_19:.*]] = addi %[[VAL_17]], %[[VAL_7]] : index +// CHECK: %[[VAL_20:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_19]]] : memref +// CHECK: scf.for %[[VAL_21:.*]] = %[[VAL_18]] to %[[VAL_20]] step %[[VAL_7]] { +// CHECK: %[[VAL_22:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_21]]] : memref +// CHECK: %[[VAL_23:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_21]]] : memref +// CHECK: %[[VAL_24:.*]] = load %[[VAL_11]]{{\[}}%[[VAL_14]], %[[VAL_15]], %[[VAL_22]]] : memref<32x16x8xf32> +// CHECK: %[[VAL_25:.*]] = mulf %[[VAL_23]], %[[VAL_24]] : f32 +// CHECK: store %[[VAL_25]], %[[VAL_13]]{{\[}}%[[VAL_14]], %[[VAL_15]], %[[VAL_22]]] : memref<32x16x8xf32> // CHECK: } // CHECK: } // CHECK: } -// CHECK: %[[VAL_25:.*]] = tensor_load %[[VAL_12]] : memref<32x16x8xf32> -// CHECK: return %[[VAL_25]] : tensor<32x16x8xf32> +// CHECK: %[[VAL_26:.*]] = tensor_load %[[VAL_13]] : memref<32x16x8xf32> +// CHECK: return %[[VAL_26]] : tensor<32x16x8xf32> // CHECK: } func @mul_dds(%arga: tensor<32x16x8xf32>, %argb: tensor<32x16x8xf32>, %argx: tensor<32x16x8xf32>) -> tensor<32x16x8xf32> { %0 = linalg.generic #trait_dds @@ -234,56 +242,57 @@ // CHECK-SAME: %[[VAL_0:.*0]]: tensor<32x16x8xf32>, // CHECK-SAME: %[[VAL_1:.*1]]: tensor<32x16x8xf32>, // CHECK-SAME: %[[VAL_2:.*2]]: tensor<32x16x8xf32>) -> tensor<32x16x8xf32> { -// CHECK: %[[VAL_3:.*]] = constant 999 : index -// CHECK: %[[VAL_4:.*]] = constant 32 : index -// CHECK: %[[VAL_5:.*]] = constant 16 : index -// CHECK: %[[VAL_6:.*]] = constant 8 : index -// CHECK: %[[VAL_7:.*]] = constant true -// CHECK: %[[VAL_8:.*]] = constant 0 : index -// CHECK: %[[VAL_9:.*]] = constant 1 : index -// CHECK: %[[VAL_10:.*]] = alloca(%[[VAL_3]]) : memref -// CHECK: %[[VAL_11:.*]] = alloca(%[[VAL_3]]) : memref -// CHECK: %[[VAL_12:.*]] = alloca(%[[VAL_3]]) : memref -// CHECK: %[[VAL_13:.*]] = alloca() : memref<32x16x8xf32> -// CHECK: %[[VAL_14:.*]] = alloca() : memref<32x16x8xf32> -// CHECK: scf.for %[[VAL_15:.*]] = %[[VAL_8]] to %[[VAL_4]] step %[[VAL_9]] { -// CHECK: %[[VAL_16:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_15]]] : memref -// CHECK: %[[VAL_17:.*]] = addi %[[VAL_15]], %[[VAL_9]] : index -// CHECK: %[[VAL_18:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_17]]] : memref -// CHECK: %[[VAL_19:.*]]:2 = scf.while (%[[VAL_20:.*]] = %[[VAL_16]], %[[VAL_21:.*]] = %[[VAL_8]]) : (index, index) -> (index, index) { +// CHECK: %[[VAL_3:.*]] = constant 32 : index +// CHECK: %[[VAL_4:.*]] = constant 16 : index +// CHECK: %[[VAL_5:.*]] = constant 8 : index +// CHECK: %[[VAL_6:.*]] = constant true +// CHECK: %[[VAL_7:.*]] = constant 0 : index +// CHECK: %[[VAL_8:.*]] = constant 1 : index +// CHECK: %[[VAL_9:.*]] = linalg.sparse_pointers %[[VAL_0]], %[[VAL_8]] : tensor<32x16x8xf32> into memref +// CHECK: %[[VAL_10:.*]] = linalg.sparse_indices %[[VAL_0]], %[[VAL_8]] : tensor<32x16x8xf32> into memref +// CHECK: %[[VAL_11:.*]] = linalg.sparse_values %[[VAL_0]] : tensor<32x16x8xf32> into memref +// CHECK: %[[VAL_12:.*]] = tensor_to_memref %[[VAL_1]] : memref<32x16x8xf32> +// CHECK: %[[VAL_13:.*]] = tensor_to_memref %[[VAL_2]] : memref<32x16x8xf32> +// CHECK: %[[VAL_14:.*]] = alloc() : memref<32x16x8xf32> +// CHECK: linalg.copy(%[[VAL_13]], %[[VAL_14]]) : memref<32x16x8xf32>, memref<32x16x8xf32> +// CHECK: scf.for %[[VAL_15:.*]] = %[[VAL_7]] to %[[VAL_3]] step %[[VAL_8]] { +// CHECK: %[[VAL_16:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_15]]] : memref +// CHECK: %[[VAL_17:.*]] = addi %[[VAL_15]], %[[VAL_8]] : index +// CHECK: %[[VAL_18:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_17]]] : memref +// CHECK: %[[VAL_19:.*]]:2 = scf.while (%[[VAL_20:.*]] = %[[VAL_16]], %[[VAL_21:.*]] = %[[VAL_7]]) : (index, index) -> (index, index) { // CHECK: %[[VAL_22:.*]] = cmpi ult, %[[VAL_20]], %[[VAL_18]] : index // CHECK: scf.condition(%[[VAL_22]]) %[[VAL_20]], %[[VAL_21]] : index, index // CHECK: } do { // CHECK: ^bb0(%[[VAL_23:.*]]: index, %[[VAL_24:.*]]: index): -// CHECK: %[[VAL_25:.*]] = load %[[VAL_11]]{{\[}}%[[VAL_23]]] : memref +// CHECK: %[[VAL_25:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_23]]] : memref // CHECK: %[[VAL_26:.*]] = cmpi eq, %[[VAL_25]], %[[VAL_24]] : index // CHECK: scf.if %[[VAL_26]] { -// CHECK: scf.for %[[VAL_27:.*]] = %[[VAL_8]] to %[[VAL_6]] step %[[VAL_9]] { -// CHECK: %[[VAL_28:.*]] = muli %[[VAL_23]], %[[VAL_6]] : index +// CHECK: scf.for %[[VAL_27:.*]] = %[[VAL_7]] to %[[VAL_5]] step %[[VAL_8]] { +// CHECK: %[[VAL_28:.*]] = muli %[[VAL_23]], %[[VAL_5]] : index // CHECK: %[[VAL_29:.*]] = addi %[[VAL_28]], %[[VAL_27]] : index -// CHECK: %[[VAL_30:.*]] = load %[[VAL_12]]{{\[}}%[[VAL_29]]] : memref -// CHECK: %[[VAL_31:.*]] = load %[[VAL_13]]{{\[}}%[[VAL_15]], %[[VAL_24]], %[[VAL_27]]] : memref<32x16x8xf32> +// CHECK: %[[VAL_30:.*]] = load %[[VAL_11]]{{\[}}%[[VAL_29]]] : memref +// CHECK: %[[VAL_31:.*]] = load %[[VAL_12]]{{\[}}%[[VAL_15]], %[[VAL_24]], %[[VAL_27]]] : memref<32x16x8xf32> // CHECK: %[[VAL_32:.*]] = addf %[[VAL_30]], %[[VAL_31]] : f32 // CHECK: store %[[VAL_32]], %[[VAL_14]]{{\[}}%[[VAL_15]], %[[VAL_24]], %[[VAL_27]]] : memref<32x16x8xf32> // CHECK: } // CHECK: } else { -// CHECK: scf.if %[[VAL_7]] { -// CHECK: scf.for %[[VAL_33:.*]] = %[[VAL_8]] to %[[VAL_6]] step %[[VAL_9]] { -// CHECK: %[[VAL_34:.*]] = load %[[VAL_13]]{{\[}}%[[VAL_15]], %[[VAL_24]], %[[VAL_33]]] : memref<32x16x8xf32> +// CHECK: scf.if %[[VAL_6]] { +// CHECK: scf.for %[[VAL_33:.*]] = %[[VAL_7]] to %[[VAL_5]] step %[[VAL_8]] { +// CHECK: %[[VAL_34:.*]] = load %[[VAL_12]]{{\[}}%[[VAL_15]], %[[VAL_24]], %[[VAL_33]]] : memref<32x16x8xf32> // CHECK: store %[[VAL_34]], %[[VAL_14]]{{\[}}%[[VAL_15]], %[[VAL_24]], %[[VAL_33]]] : memref<32x16x8xf32> // CHECK: } // CHECK: } else { // CHECK: } // CHECK: } // CHECK: %[[VAL_35:.*]] = cmpi eq, %[[VAL_25]], %[[VAL_24]] : index -// CHECK: %[[VAL_36:.*]] = addi %[[VAL_23]], %[[VAL_9]] : index +// CHECK: %[[VAL_36:.*]] = addi %[[VAL_23]], %[[VAL_8]] : index // CHECK: %[[VAL_37:.*]] = select %[[VAL_35]], %[[VAL_36]], %[[VAL_23]] : index -// CHECK: %[[VAL_38:.*]] = addi %[[VAL_24]], %[[VAL_9]] : index +// CHECK: %[[VAL_38:.*]] = addi %[[VAL_24]], %[[VAL_8]] : index // CHECK: scf.yield %[[VAL_37]], %[[VAL_38]] : index, index // CHECK: } -// CHECK: scf.for %[[VAL_39:.*]] = %[[VAL_40:.*]]#1 to %[[VAL_5]] step %[[VAL_9]] { -// CHECK: scf.for %[[VAL_41:.*]] = %[[VAL_8]] to %[[VAL_6]] step %[[VAL_9]] { -// CHECK: %[[VAL_42:.*]] = load %[[VAL_13]]{{\[}}%[[VAL_15]], %[[VAL_39]], %[[VAL_41]]] : memref<32x16x8xf32> +// CHECK: scf.for %[[VAL_39:.*]] = %[[VAL_40:.*]]#1 to %[[VAL_4]] step %[[VAL_8]] { +// CHECK: scf.for %[[VAL_41:.*]] = %[[VAL_7]] to %[[VAL_5]] step %[[VAL_8]] { +// CHECK: %[[VAL_42:.*]] = load %[[VAL_12]]{{\[}}%[[VAL_15]], %[[VAL_39]], %[[VAL_41]]] : memref<32x16x8xf32> // CHECK: store %[[VAL_42]], %[[VAL_14]]{{\[}}%[[VAL_15]], %[[VAL_39]], %[[VAL_41]]] : memref<32x16x8xf32> // CHECK: } // CHECK: } @@ -306,27 +315,28 @@ // CHECK-SAME: %[[VAL_0:.*0]]: tensor<32x16x8xf32>, // CHECK-SAME: %[[VAL_1:.*1]]: tensor<32x16x8xf32>, // CHECK-SAME: %[[VAL_2:.*2]]: tensor<32x16x8xf32>) -> tensor<32x16x8xf32> { -// CHECK: %[[VAL_3:.*]] = constant 999 : index -// CHECK: %[[VAL_4:.*]] = constant 32 : index -// CHECK: %[[VAL_5:.*]] = constant 8 : index -// CHECK: %[[VAL_6:.*]] = constant 0 : index -// CHECK: %[[VAL_7:.*]] = constant 1 : index -// CHECK: %[[VAL_8:.*]] = alloca(%[[VAL_3]]) : memref -// CHECK: %[[VAL_9:.*]] = alloca(%[[VAL_3]]) : memref -// CHECK: %[[VAL_10:.*]] = alloca(%[[VAL_3]]) : memref -// CHECK: %[[VAL_11:.*]] = alloca() : memref<32x16x8xf32> -// CHECK: %[[VAL_12:.*]] = alloca() : memref<32x16x8xf32> -// CHECK: scf.for %[[VAL_13:.*]] = %[[VAL_6]] to %[[VAL_4]] step %[[VAL_7]] { -// CHECK: %[[VAL_14:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_13]]] : memref -// CHECK: %[[VAL_15:.*]] = addi %[[VAL_13]], %[[VAL_7]] : index -// CHECK: %[[VAL_16:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_15]]] : memref -// CHECK: scf.for %[[VAL_17:.*]] = %[[VAL_14]] to %[[VAL_16]] step %[[VAL_7]] { -// CHECK: %[[VAL_18:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_17]]] : memref -// CHECK: scf.for %[[VAL_19:.*]] = %[[VAL_6]] to %[[VAL_5]] step %[[VAL_7]] { -// CHECK: %[[VAL_20:.*]] = muli %[[VAL_17]], %[[VAL_5]] : index +// CHECK: %[[VAL_3:.*]] = constant 32 : index +// CHECK: %[[VAL_4:.*]] = constant 8 : index +// CHECK: %[[VAL_5:.*]] = constant 0 : index +// CHECK: %[[VAL_6:.*]] = constant 1 : index +// CHECK: %[[VAL_7:.*]] = linalg.sparse_pointers %[[VAL_0]], %[[VAL_6]] : tensor<32x16x8xf32> into memref +// CHECK: %[[VAL_8:.*]] = linalg.sparse_indices %[[VAL_0]], %[[VAL_6]] : tensor<32x16x8xf32> into memref +// CHECK: %[[VAL_9:.*]] = linalg.sparse_values %[[VAL_0]] : tensor<32x16x8xf32> into memref +// CHECK: %[[VAL_10:.*]] = tensor_to_memref %[[VAL_1]] : memref<32x16x8xf32> +// CHECK: %[[VAL_11:.*]] = tensor_to_memref %[[VAL_2]] : memref<32x16x8xf32> +// CHECK: %[[VAL_12:.*]] = alloc() : memref<32x16x8xf32> +// CHECK: linalg.copy(%[[VAL_11]], %[[VAL_12]]) : memref<32x16x8xf32>, memref<32x16x8xf32> +// CHECK: scf.for %[[VAL_13:.*]] = %[[VAL_5]] to %[[VAL_3]] step %[[VAL_6]] { +// CHECK: %[[VAL_14:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_13]]] : memref +// CHECK: %[[VAL_15:.*]] = addi %[[VAL_13]], %[[VAL_6]] : index +// CHECK: %[[VAL_16:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_15]]] : memref +// CHECK: scf.for %[[VAL_17:.*]] = %[[VAL_14]] to %[[VAL_16]] step %[[VAL_6]] { +// CHECK: %[[VAL_18:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_17]]] : memref +// CHECK: scf.for %[[VAL_19:.*]] = %[[VAL_5]] to %[[VAL_4]] step %[[VAL_6]] { +// CHECK: %[[VAL_20:.*]] = muli %[[VAL_17]], %[[VAL_4]] : index // CHECK: %[[VAL_21:.*]] = addi %[[VAL_20]], %[[VAL_19]] : index -// CHECK: %[[VAL_22:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_21]]] : memref -// CHECK: %[[VAL_23:.*]] = load %[[VAL_11]]{{\[}}%[[VAL_13]], %[[VAL_18]], %[[VAL_19]]] : memref<32x16x8xf32> +// CHECK: %[[VAL_22:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_21]]] : memref +// CHECK: %[[VAL_23:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_13]], %[[VAL_18]], %[[VAL_19]]] : memref<32x16x8xf32> // CHECK: %[[VAL_24:.*]] = mulf %[[VAL_22]], %[[VAL_23]] : f32 // CHECK: store %[[VAL_24]], %[[VAL_12]]{{\[}}%[[VAL_13]], %[[VAL_18]], %[[VAL_19]]] : memref<32x16x8xf32> // CHECK: } @@ -365,88 +375,90 @@ // CHECK-SAME: %[[VAL_0:.*0]]: tensor<32x16x8xf32>, // CHECK-SAME: %[[VAL_1:.*1]]: tensor<32x16x8xf32>, // CHECK-SAME: %[[VAL_2:.*2]]: tensor<32x16x8xf32>) -> tensor<32x16x8xf32> { -// CHECK: %[[VAL_3:.*]] = constant 999 : index +// CHECK: %[[VAL_3:.*]] = constant 2 : index // CHECK: %[[VAL_4:.*]] = constant 32 : index // CHECK: %[[VAL_5:.*]] = constant 16 : index // CHECK: %[[VAL_6:.*]] = constant 8 : index // CHECK: %[[VAL_7:.*]] = constant true // CHECK: %[[VAL_8:.*]] = constant 0 : index // CHECK: %[[VAL_9:.*]] = constant 1 : index -// CHECK: %[[VAL_10:.*]] = alloca(%[[VAL_3]]) : memref -// CHECK: %[[VAL_11:.*]] = alloca(%[[VAL_3]]) : memref -// CHECK: %[[VAL_12:.*]] = alloca(%[[VAL_3]]) : memref -// CHECK: %[[VAL_13:.*]] = alloca(%[[VAL_3]]) : memref -// CHECK: %[[VAL_14:.*]] = alloca(%[[VAL_3]]) : memref -// CHECK: %[[VAL_15:.*]] = alloca() : memref<32x16x8xf32> -// CHECK: %[[VAL_16:.*]] = alloca() : memref<32x16x8xf32> -// CHECK: scf.for %[[VAL_17:.*]] = %[[VAL_8]] to %[[VAL_4]] step %[[VAL_9]] { -// CHECK: %[[VAL_18:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_17]]] : memref -// CHECK: %[[VAL_19:.*]] = addi %[[VAL_17]], %[[VAL_9]] : index -// CHECK: %[[VAL_20:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_19]]] : memref -// CHECK: %[[VAL_21:.*]]:2 = scf.while (%[[VAL_22:.*]] = %[[VAL_18]], %[[VAL_23:.*]] = %[[VAL_8]]) : (index, index) -> (index, index) { -// CHECK: %[[VAL_24:.*]] = cmpi ult, %[[VAL_22]], %[[VAL_20]] : index -// CHECK: scf.condition(%[[VAL_24]]) %[[VAL_22]], %[[VAL_23]] : index, index +// CHECK: %[[VAL_10:.*]] = linalg.sparse_pointers %[[VAL_0]], %[[VAL_9]] : tensor<32x16x8xf32> into memref +// CHECK: %[[VAL_11:.*]] = linalg.sparse_indices %[[VAL_0]], %[[VAL_9]] : tensor<32x16x8xf32> into memref +// CHECK: %[[VAL_12:.*]] = linalg.sparse_pointers %[[VAL_0]], %[[VAL_3]] : tensor<32x16x8xf32> into memref +// CHECK: %[[VAL_13:.*]] = linalg.sparse_indices %[[VAL_0]], %[[VAL_3]] : tensor<32x16x8xf32> into memref +// CHECK: %[[VAL_14:.*]] = linalg.sparse_values %[[VAL_0]] : tensor<32x16x8xf32> into memref +// CHECK: %[[VAL_15:.*]] = tensor_to_memref %[[VAL_1]] : memref<32x16x8xf32> +// CHECK: %[[VAL_16:.*]] = tensor_to_memref %[[VAL_2]] : memref<32x16x8xf32> +// CHECK: %[[VAL_17:.*]] = alloc() : memref<32x16x8xf32> +// CHECK: linalg.copy(%[[VAL_16]], %[[VAL_17]]) : memref<32x16x8xf32>, memref<32x16x8xf32> +// CHECK: scf.for %[[VAL_18:.*]] = %[[VAL_8]] to %[[VAL_4]] step %[[VAL_9]] { +// CHECK: %[[VAL_19:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_18]]] : memref +// CHECK: %[[VAL_20:.*]] = addi %[[VAL_18]], %[[VAL_9]] : index +// CHECK: %[[VAL_21:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_20]]] : memref +// CHECK: %[[VAL_22:.*]]:2 = scf.while (%[[VAL_23:.*]] = %[[VAL_19]], %[[VAL_24:.*]] = %[[VAL_8]]) : (index, index) -> (index, index) { +// CHECK: %[[VAL_25:.*]] = cmpi ult, %[[VAL_23]], %[[VAL_21]] : index +// CHECK: scf.condition(%[[VAL_25]]) %[[VAL_23]], %[[VAL_24]] : index, index // CHECK: } do { -// CHECK: ^bb0(%[[VAL_25:.*]]: index, %[[VAL_26:.*]]: index): -// CHECK: %[[VAL_27:.*]] = load %[[VAL_11]]{{\[}}%[[VAL_25]]] : memref -// CHECK: %[[VAL_28:.*]] = cmpi eq, %[[VAL_27]], %[[VAL_26]] : index -// CHECK: scf.if %[[VAL_28]] { -// CHECK: %[[VAL_29:.*]] = load %[[VAL_12]]{{\[}}%[[VAL_25]]] : memref -// CHECK: %[[VAL_30:.*]] = addi %[[VAL_25]], %[[VAL_9]] : index -// CHECK: %[[VAL_31:.*]] = load %[[VAL_12]]{{\[}}%[[VAL_30]]] : memref -// CHECK: %[[VAL_32:.*]]:2 = scf.while (%[[VAL_33:.*]] = %[[VAL_29]], %[[VAL_34:.*]] = %[[VAL_8]]) : (index, index) -> (index, index) { -// CHECK: %[[VAL_35:.*]] = cmpi ult, %[[VAL_33]], %[[VAL_31]] : index -// CHECK: scf.condition(%[[VAL_35]]) %[[VAL_33]], %[[VAL_34]] : index, index +// CHECK: ^bb0(%[[VAL_26:.*]]: index, %[[VAL_27:.*]]: index): +// CHECK: %[[VAL_28:.*]] = load %[[VAL_11]]{{\[}}%[[VAL_26]]] : memref +// CHECK: %[[VAL_29:.*]] = cmpi eq, %[[VAL_28]], %[[VAL_27]] : index +// CHECK: scf.if %[[VAL_29]] { +// CHECK: %[[VAL_30:.*]] = load %[[VAL_12]]{{\[}}%[[VAL_26]]] : memref +// CHECK: %[[VAL_31:.*]] = addi %[[VAL_26]], %[[VAL_9]] : index +// CHECK: %[[VAL_32:.*]] = load %[[VAL_12]]{{\[}}%[[VAL_31]]] : memref +// CHECK: %[[VAL_33:.*]]:2 = scf.while (%[[VAL_34:.*]] = %[[VAL_30]], %[[VAL_35:.*]] = %[[VAL_8]]) : (index, index) -> (index, index) { +// CHECK: %[[VAL_36:.*]] = cmpi ult, %[[VAL_34]], %[[VAL_32]] : index +// CHECK: scf.condition(%[[VAL_36]]) %[[VAL_34]], %[[VAL_35]] : index, index // CHECK: } do { -// CHECK: ^bb0(%[[VAL_36:.*]]: index, %[[VAL_37:.*]]: index): -// CHECK: %[[VAL_38:.*]] = load %[[VAL_13]]{{\[}}%[[VAL_36]]] : memref -// CHECK: %[[VAL_39:.*]] = cmpi eq, %[[VAL_38]], %[[VAL_37]] : index -// CHECK: scf.if %[[VAL_39]] { -// CHECK: %[[VAL_40:.*]] = load %[[VAL_14]]{{\[}}%[[VAL_36]]] : memref -// CHECK: %[[VAL_41:.*]] = load %[[VAL_15]]{{\[}}%[[VAL_17]], %[[VAL_26]], %[[VAL_37]]] : memref<32x16x8xf32> -// CHECK: %[[VAL_42:.*]] = addf %[[VAL_40]], %[[VAL_41]] : f32 -// CHECK: store %[[VAL_42]], %[[VAL_16]]{{\[}}%[[VAL_17]], %[[VAL_26]], %[[VAL_37]]] : memref<32x16x8xf32> +// CHECK: ^bb0(%[[VAL_37:.*]]: index, %[[VAL_38:.*]]: index): +// CHECK: %[[VAL_39:.*]] = load %[[VAL_13]]{{\[}}%[[VAL_37]]] : memref +// CHECK: %[[VAL_40:.*]] = cmpi eq, %[[VAL_39]], %[[VAL_38]] : index +// CHECK: scf.if %[[VAL_40]] { +// CHECK: %[[VAL_41:.*]] = load %[[VAL_14]]{{\[}}%[[VAL_37]]] : memref +// CHECK: %[[VAL_42:.*]] = load %[[VAL_15]]{{\[}}%[[VAL_18]], %[[VAL_27]], %[[VAL_38]]] : memref<32x16x8xf32> +// CHECK: %[[VAL_43:.*]] = addf %[[VAL_41]], %[[VAL_42]] : f32 +// CHECK: store %[[VAL_43]], %[[VAL_17]]{{\[}}%[[VAL_18]], %[[VAL_27]], %[[VAL_38]]] : memref<32x16x8xf32> // CHECK: } else { // CHECK: scf.if %[[VAL_7]] { -// CHECK: %[[VAL_43:.*]] = load %[[VAL_15]]{{\[}}%[[VAL_17]], %[[VAL_26]], %[[VAL_37]]] : memref<32x16x8xf32> -// CHECK: store %[[VAL_43]], %[[VAL_16]]{{\[}}%[[VAL_17]], %[[VAL_26]], %[[VAL_37]]] : memref<32x16x8xf32> +// CHECK: %[[VAL_44:.*]] = load %[[VAL_15]]{{\[}}%[[VAL_18]], %[[VAL_27]], %[[VAL_38]]] : memref<32x16x8xf32> +// CHECK: store %[[VAL_44]], %[[VAL_17]]{{\[}}%[[VAL_18]], %[[VAL_27]], %[[VAL_38]]] : memref<32x16x8xf32> // CHECK: } else { // CHECK: } // CHECK: } -// CHECK: %[[VAL_44:.*]] = cmpi eq, %[[VAL_38]], %[[VAL_37]] : index -// CHECK: %[[VAL_45:.*]] = addi %[[VAL_36]], %[[VAL_9]] : index -// CHECK: %[[VAL_46:.*]] = select %[[VAL_44]], %[[VAL_45]], %[[VAL_36]] : index -// CHECK: %[[VAL_47:.*]] = addi %[[VAL_37]], %[[VAL_9]] : index -// CHECK: scf.yield %[[VAL_46]], %[[VAL_47]] : index, index +// CHECK: %[[VAL_45:.*]] = cmpi eq, %[[VAL_39]], %[[VAL_38]] : index +// CHECK: %[[VAL_46:.*]] = addi %[[VAL_37]], %[[VAL_9]] : index +// CHECK: %[[VAL_47:.*]] = select %[[VAL_45]], %[[VAL_46]], %[[VAL_37]] : index +// CHECK: %[[VAL_48:.*]] = addi %[[VAL_38]], %[[VAL_9]] : index +// CHECK: scf.yield %[[VAL_47]], %[[VAL_48]] : index, index // CHECK: } -// CHECK: scf.for %[[VAL_48:.*]] = %[[VAL_49:.*]]#1 to %[[VAL_6]] step %[[VAL_9]] { -// CHECK: %[[VAL_50:.*]] = load %[[VAL_15]]{{\[}}%[[VAL_17]], %[[VAL_26]], %[[VAL_48]]] : memref<32x16x8xf32> -// CHECK: store %[[VAL_50]], %[[VAL_16]]{{\[}}%[[VAL_17]], %[[VAL_26]], %[[VAL_48]]] : memref<32x16x8xf32> +// CHECK: scf.for %[[VAL_49:.*]] = %[[VAL_50:.*]]#1 to %[[VAL_6]] step %[[VAL_9]] { +// CHECK: %[[VAL_51:.*]] = load %[[VAL_15]]{{\[}}%[[VAL_18]], %[[VAL_27]], %[[VAL_49]]] : memref<32x16x8xf32> +// CHECK: store %[[VAL_51]], %[[VAL_17]]{{\[}}%[[VAL_18]], %[[VAL_27]], %[[VAL_49]]] : memref<32x16x8xf32> // CHECK: } // CHECK: } else { // CHECK: scf.if %[[VAL_7]] { -// CHECK: scf.for %[[VAL_51:.*]] = %[[VAL_8]] to %[[VAL_6]] step %[[VAL_9]] { -// CHECK: %[[VAL_52:.*]] = load %[[VAL_15]]{{\[}}%[[VAL_17]], %[[VAL_26]], %[[VAL_51]]] : memref<32x16x8xf32> -// CHECK: store %[[VAL_52]], %[[VAL_16]]{{\[}}%[[VAL_17]], %[[VAL_26]], %[[VAL_51]]] : memref<32x16x8xf32> +// CHECK: scf.for %[[VAL_52:.*]] = %[[VAL_8]] to %[[VAL_6]] step %[[VAL_9]] { +// CHECK: %[[VAL_53:.*]] = load %[[VAL_15]]{{\[}}%[[VAL_18]], %[[VAL_27]], %[[VAL_52]]] : memref<32x16x8xf32> +// CHECK: store %[[VAL_53]], %[[VAL_17]]{{\[}}%[[VAL_18]], %[[VAL_27]], %[[VAL_52]]] : memref<32x16x8xf32> // CHECK: } // CHECK: } else { // CHECK: } // CHECK: } -// CHECK: %[[VAL_53:.*]] = cmpi eq, %[[VAL_27]], %[[VAL_26]] : index -// CHECK: %[[VAL_54:.*]] = addi %[[VAL_25]], %[[VAL_9]] : index -// CHECK: %[[VAL_55:.*]] = select %[[VAL_53]], %[[VAL_54]], %[[VAL_25]] : index -// CHECK: %[[VAL_56:.*]] = addi %[[VAL_26]], %[[VAL_9]] : index -// CHECK: scf.yield %[[VAL_55]], %[[VAL_56]] : index, index +// CHECK: %[[VAL_54:.*]] = cmpi eq, %[[VAL_28]], %[[VAL_27]] : index +// CHECK: %[[VAL_55:.*]] = addi %[[VAL_26]], %[[VAL_9]] : index +// CHECK: %[[VAL_56:.*]] = select %[[VAL_54]], %[[VAL_55]], %[[VAL_26]] : index +// CHECK: %[[VAL_57:.*]] = addi %[[VAL_27]], %[[VAL_9]] : index +// CHECK: scf.yield %[[VAL_56]], %[[VAL_57]] : index, index // CHECK: } -// CHECK: scf.for %[[VAL_57:.*]] = %[[VAL_58:.*]]#1 to %[[VAL_5]] step %[[VAL_9]] { -// CHECK: scf.for %[[VAL_59:.*]] = %[[VAL_8]] to %[[VAL_6]] step %[[VAL_9]] { -// CHECK: %[[VAL_60:.*]] = load %[[VAL_15]]{{\[}}%[[VAL_17]], %[[VAL_57]], %[[VAL_59]]] : memref<32x16x8xf32> -// CHECK: store %[[VAL_60]], %[[VAL_16]]{{\[}}%[[VAL_17]], %[[VAL_57]], %[[VAL_59]]] : memref<32x16x8xf32> +// CHECK: scf.for %[[VAL_58:.*]] = %[[VAL_59:.*]]#1 to %[[VAL_5]] step %[[VAL_9]] { +// CHECK: scf.for %[[VAL_60:.*]] = %[[VAL_8]] to %[[VAL_6]] step %[[VAL_9]] { +// CHECK: %[[VAL_61:.*]] = load %[[VAL_15]]{{\[}}%[[VAL_18]], %[[VAL_58]], %[[VAL_60]]] : memref<32x16x8xf32> +// CHECK: store %[[VAL_61]], %[[VAL_17]]{{\[}}%[[VAL_18]], %[[VAL_58]], %[[VAL_60]]] : memref<32x16x8xf32> // CHECK: } // CHECK: } // CHECK: } -// CHECK: %[[VAL_61:.*]] = tensor_load %[[VAL_16]] : memref<32x16x8xf32> -// CHECK: return %[[VAL_61]] : tensor<32x16x8xf32> +// CHECK: %[[VAL_62:.*]] = tensor_load %[[VAL_17]] : memref<32x16x8xf32> +// CHECK: return %[[VAL_62]] : tensor<32x16x8xf32> // CHECK: } func @add_dss(%arga: tensor<32x16x8xf32>, %argb: tensor<32x16x8xf32>, %argx: tensor<32x16x8xf32>) -> tensor<32x16x8xf32> { %0 = linalg.generic #trait_dss @@ -463,37 +475,39 @@ // CHECK-SAME: %[[VAL_0:.*0]]: tensor<32x16x8xf32>, // CHECK-SAME: %[[VAL_1:.*1]]: tensor<32x16x8xf32>, // CHECK-SAME: %[[VAL_2:.*2]]: tensor<32x16x8xf32>) -> tensor<32x16x8xf32> { -// CHECK: %[[VAL_3:.*]] = constant 999 : index +// CHECK: %[[VAL_3:.*]] = constant 2 : index // CHECK: %[[VAL_4:.*]] = constant 32 : index // CHECK: %[[VAL_5:.*]] = constant 0 : index // CHECK: %[[VAL_6:.*]] = constant 1 : index -// CHECK: %[[VAL_7:.*]] = alloca(%[[VAL_3]]) : memref -// CHECK: %[[VAL_8:.*]] = alloca(%[[VAL_3]]) : memref -// CHECK: %[[VAL_9:.*]] = alloca(%[[VAL_3]]) : memref -// CHECK: %[[VAL_10:.*]] = alloca(%[[VAL_3]]) : memref -// CHECK: %[[VAL_11:.*]] = alloca(%[[VAL_3]]) : memref -// CHECK: %[[VAL_12:.*]] = alloca() : memref<32x16x8xf32> -// CHECK: %[[VAL_13:.*]] = alloca() : memref<32x16x8xf32> -// CHECK: scf.for %[[VAL_14:.*]] = %[[VAL_5]] to %[[VAL_4]] step %[[VAL_6]] { -// CHECK: %[[VAL_15:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_14]]] : memref -// CHECK: %[[VAL_16:.*]] = addi %[[VAL_14]], %[[VAL_6]] : index -// CHECK: %[[VAL_17:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_16]]] : memref -// CHECK: scf.for %[[VAL_18:.*]] = %[[VAL_15]] to %[[VAL_17]] step %[[VAL_6]] { -// CHECK: %[[VAL_19:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_18]]] : memref -// CHECK: %[[VAL_20:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_18]]] : memref -// CHECK: %[[VAL_21:.*]] = addi %[[VAL_18]], %[[VAL_6]] : index -// CHECK: %[[VAL_22:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_21]]] : memref -// CHECK: scf.for %[[VAL_23:.*]] = %[[VAL_20]] to %[[VAL_22]] step %[[VAL_6]] { -// CHECK: %[[VAL_24:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_23]]] : memref -// CHECK: %[[VAL_25:.*]] = load %[[VAL_11]]{{\[}}%[[VAL_23]]] : memref -// CHECK: %[[VAL_26:.*]] = load %[[VAL_12]]{{\[}}%[[VAL_14]], %[[VAL_19]], %[[VAL_24]]] : memref<32x16x8xf32> -// CHECK: %[[VAL_27:.*]] = mulf %[[VAL_25]], %[[VAL_26]] : f32 -// CHECK: store %[[VAL_27]], %[[VAL_13]]{{\[}}%[[VAL_14]], %[[VAL_19]], %[[VAL_24]]] : memref<32x16x8xf32> +// CHECK: %[[VAL_7:.*]] = linalg.sparse_pointers %[[VAL_0]], %[[VAL_6]] : tensor<32x16x8xf32> into memref +// CHECK: %[[VAL_8:.*]] = linalg.sparse_indices %[[VAL_0]], %[[VAL_6]] : tensor<32x16x8xf32> into memref +// CHECK: %[[VAL_9:.*]] = linalg.sparse_pointers %[[VAL_0]], %[[VAL_3]] : tensor<32x16x8xf32> into memref +// CHECK: %[[VAL_10:.*]] = linalg.sparse_indices %[[VAL_0]], %[[VAL_3]] : tensor<32x16x8xf32> into memref +// CHECK: %[[VAL_11:.*]] = linalg.sparse_values %[[VAL_0]] : tensor<32x16x8xf32> into memref +// CHECK: %[[VAL_12:.*]] = tensor_to_memref %[[VAL_1]] : memref<32x16x8xf32> +// CHECK: %[[VAL_13:.*]] = tensor_to_memref %[[VAL_2]] : memref<32x16x8xf32> +// CHECK: %[[VAL_14:.*]] = alloc() : memref<32x16x8xf32> +// CHECK: linalg.copy(%[[VAL_13]], %[[VAL_14]]) : memref<32x16x8xf32>, memref<32x16x8xf32> +// CHECK: scf.for %[[VAL_15:.*]] = %[[VAL_5]] to %[[VAL_4]] step %[[VAL_6]] { +// CHECK: %[[VAL_16:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_15]]] : memref +// CHECK: %[[VAL_17:.*]] = addi %[[VAL_15]], %[[VAL_6]] : index +// CHECK: %[[VAL_18:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_17]]] : memref +// CHECK: scf.for %[[VAL_19:.*]] = %[[VAL_16]] to %[[VAL_18]] step %[[VAL_6]] { +// CHECK: %[[VAL_20:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_19]]] : memref +// CHECK: %[[VAL_21:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_19]]] : memref +// CHECK: %[[VAL_22:.*]] = addi %[[VAL_19]], %[[VAL_6]] : index +// CHECK: %[[VAL_23:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_22]]] : memref +// CHECK: scf.for %[[VAL_24:.*]] = %[[VAL_21]] to %[[VAL_23]] step %[[VAL_6]] { +// CHECK: %[[VAL_25:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_24]]] : memref +// CHECK: %[[VAL_26:.*]] = load %[[VAL_11]]{{\[}}%[[VAL_24]]] : memref +// CHECK: %[[VAL_27:.*]] = load %[[VAL_12]]{{\[}}%[[VAL_15]], %[[VAL_20]], %[[VAL_25]]] : memref<32x16x8xf32> +// CHECK: %[[VAL_28:.*]] = mulf %[[VAL_26]], %[[VAL_27]] : f32 +// CHECK: store %[[VAL_28]], %[[VAL_14]]{{\[}}%[[VAL_15]], %[[VAL_20]], %[[VAL_25]]] : memref<32x16x8xf32> // CHECK: } // CHECK: } // CHECK: } -// CHECK: %[[VAL_28:.*]] = tensor_load %[[VAL_13]] : memref<32x16x8xf32> -// CHECK: return %[[VAL_28]] : tensor<32x16x8xf32> +// CHECK: %[[VAL_29:.*]] = tensor_load %[[VAL_14]] : memref<32x16x8xf32> +// CHECK: return %[[VAL_29]] : tensor<32x16x8xf32> // CHECK: } func @mul_dss(%arga: tensor<32x16x8xf32>, %argb: tensor<32x16x8xf32>, %argx: tensor<32x16x8xf32>) -> tensor<32x16x8xf32> { %0 = linalg.generic #trait_dss @@ -525,45 +539,46 @@ // CHECK-SAME: %[[VAL_0:.*0]]: tensor<32x16x8xf32>, // CHECK-SAME: %[[VAL_1:.*1]]: tensor<32x16x8xf32>, // CHECK-SAME: %[[VAL_2:.*2]]: tensor<32x16x8xf32>) -> tensor<32x16x8xf32> { -// CHECK: %[[VAL_3:.*]] = constant 999 : index -// CHECK: %[[VAL_4:.*]] = constant 32 : index -// CHECK: %[[VAL_5:.*]] = constant 16 : index -// CHECK: %[[VAL_6:.*]] = constant 8 : index -// CHECK: %[[VAL_7:.*]] = constant true -// CHECK: %[[VAL_8:.*]] = constant 0 : index -// CHECK: %[[VAL_9:.*]] = constant 1 : index -// CHECK: %[[VAL_10:.*]] = alloca(%[[VAL_3]]) : memref -// CHECK: %[[VAL_11:.*]] = alloca(%[[VAL_3]]) : memref -// CHECK: %[[VAL_12:.*]] = alloca(%[[VAL_3]]) : memref -// CHECK: %[[VAL_13:.*]] = alloca() : memref<32x16x8xf32> -// CHECK: %[[VAL_14:.*]] = alloca() : memref<32x16x8xf32> -// CHECK: %[[VAL_15:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_8]]] : memref -// CHECK: %[[VAL_16:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_9]]] : memref -// CHECK: %[[VAL_17:.*]]:2 = scf.while (%[[VAL_18:.*]] = %[[VAL_15]], %[[VAL_19:.*]] = %[[VAL_8]]) : (index, index) -> (index, index) { +// CHECK: %[[VAL_3:.*]] = constant 32 : index +// CHECK: %[[VAL_4:.*]] = constant 16 : index +// CHECK: %[[VAL_5:.*]] = constant 8 : index +// CHECK: %[[VAL_6:.*]] = constant true +// CHECK: %[[VAL_7:.*]] = constant 0 : index +// CHECK: %[[VAL_8:.*]] = constant 1 : index +// CHECK: %[[VAL_9:.*]] = linalg.sparse_pointers %[[VAL_0]], %[[VAL_7]] : tensor<32x16x8xf32> into memref +// CHECK: %[[VAL_10:.*]] = linalg.sparse_indices %[[VAL_0]], %[[VAL_7]] : tensor<32x16x8xf32> into memref +// CHECK: %[[VAL_11:.*]] = linalg.sparse_values %[[VAL_0]] : tensor<32x16x8xf32> into memref +// CHECK: %[[VAL_12:.*]] = tensor_to_memref %[[VAL_1]] : memref<32x16x8xf32> +// CHECK: %[[VAL_13:.*]] = tensor_to_memref %[[VAL_2]] : memref<32x16x8xf32> +// CHECK: %[[VAL_14:.*]] = alloc() : memref<32x16x8xf32> +// CHECK: linalg.copy(%[[VAL_13]], %[[VAL_14]]) : memref<32x16x8xf32>, memref<32x16x8xf32> +// CHECK: %[[VAL_15:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_7]]] : memref +// CHECK: %[[VAL_16:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_8]]] : memref +// CHECK: %[[VAL_17:.*]]:2 = scf.while (%[[VAL_18:.*]] = %[[VAL_15]], %[[VAL_19:.*]] = %[[VAL_7]]) : (index, index) -> (index, index) { // CHECK: %[[VAL_20:.*]] = cmpi ult, %[[VAL_18]], %[[VAL_16]] : index // CHECK: scf.condition(%[[VAL_20]]) %[[VAL_18]], %[[VAL_19]] : index, index // CHECK: } do { // CHECK: ^bb0(%[[VAL_21:.*]]: index, %[[VAL_22:.*]]: index): -// CHECK: %[[VAL_23:.*]] = load %[[VAL_11]]{{\[}}%[[VAL_21]]] : memref +// CHECK: %[[VAL_23:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_21]]] : memref // CHECK: %[[VAL_24:.*]] = cmpi eq, %[[VAL_23]], %[[VAL_22]] : index // CHECK: scf.if %[[VAL_24]] { -// CHECK: scf.for %[[VAL_25:.*]] = %[[VAL_8]] to %[[VAL_5]] step %[[VAL_9]] { -// CHECK: %[[VAL_26:.*]] = muli %[[VAL_21]], %[[VAL_5]] : index +// CHECK: scf.for %[[VAL_25:.*]] = %[[VAL_7]] to %[[VAL_4]] step %[[VAL_8]] { +// CHECK: %[[VAL_26:.*]] = muli %[[VAL_21]], %[[VAL_4]] : index // CHECK: %[[VAL_27:.*]] = addi %[[VAL_26]], %[[VAL_25]] : index -// CHECK: scf.for %[[VAL_28:.*]] = %[[VAL_8]] to %[[VAL_6]] step %[[VAL_9]] { -// CHECK: %[[VAL_29:.*]] = muli %[[VAL_27]], %[[VAL_6]] : index +// CHECK: scf.for %[[VAL_28:.*]] = %[[VAL_7]] to %[[VAL_5]] step %[[VAL_8]] { +// CHECK: %[[VAL_29:.*]] = muli %[[VAL_27]], %[[VAL_5]] : index // CHECK: %[[VAL_30:.*]] = addi %[[VAL_29]], %[[VAL_28]] : index -// CHECK: %[[VAL_31:.*]] = load %[[VAL_12]]{{\[}}%[[VAL_30]]] : memref -// CHECK: %[[VAL_32:.*]] = load %[[VAL_13]]{{\[}}%[[VAL_22]], %[[VAL_25]], %[[VAL_28]]] : memref<32x16x8xf32> +// CHECK: %[[VAL_31:.*]] = load %[[VAL_11]]{{\[}}%[[VAL_30]]] : memref +// CHECK: %[[VAL_32:.*]] = load %[[VAL_12]]{{\[}}%[[VAL_22]], %[[VAL_25]], %[[VAL_28]]] : memref<32x16x8xf32> // CHECK: %[[VAL_33:.*]] = addf %[[VAL_31]], %[[VAL_32]] : f32 // CHECK: store %[[VAL_33]], %[[VAL_14]]{{\[}}%[[VAL_22]], %[[VAL_25]], %[[VAL_28]]] : memref<32x16x8xf32> // CHECK: } // CHECK: } // CHECK: } else { -// CHECK: scf.if %[[VAL_7]] { -// CHECK: scf.for %[[VAL_34:.*]] = %[[VAL_8]] to %[[VAL_5]] step %[[VAL_9]] { -// CHECK: scf.for %[[VAL_35:.*]] = %[[VAL_8]] to %[[VAL_6]] step %[[VAL_9]] { -// CHECK: %[[VAL_36:.*]] = load %[[VAL_13]]{{\[}}%[[VAL_22]], %[[VAL_34]], %[[VAL_35]]] : memref<32x16x8xf32> +// CHECK: scf.if %[[VAL_6]] { +// CHECK: scf.for %[[VAL_34:.*]] = %[[VAL_7]] to %[[VAL_4]] step %[[VAL_8]] { +// CHECK: scf.for %[[VAL_35:.*]] = %[[VAL_7]] to %[[VAL_5]] step %[[VAL_8]] { +// CHECK: %[[VAL_36:.*]] = load %[[VAL_12]]{{\[}}%[[VAL_22]], %[[VAL_34]], %[[VAL_35]]] : memref<32x16x8xf32> // CHECK: store %[[VAL_36]], %[[VAL_14]]{{\[}}%[[VAL_22]], %[[VAL_34]], %[[VAL_35]]] : memref<32x16x8xf32> // CHECK: } // CHECK: } @@ -571,15 +586,15 @@ // CHECK: } // CHECK: } // CHECK: %[[VAL_37:.*]] = cmpi eq, %[[VAL_23]], %[[VAL_22]] : index -// CHECK: %[[VAL_38:.*]] = addi %[[VAL_21]], %[[VAL_9]] : index +// CHECK: %[[VAL_38:.*]] = addi %[[VAL_21]], %[[VAL_8]] : index // CHECK: %[[VAL_39:.*]] = select %[[VAL_37]], %[[VAL_38]], %[[VAL_21]] : index -// CHECK: %[[VAL_40:.*]] = addi %[[VAL_22]], %[[VAL_9]] : index +// CHECK: %[[VAL_40:.*]] = addi %[[VAL_22]], %[[VAL_8]] : index // CHECK: scf.yield %[[VAL_39]], %[[VAL_40]] : index, index // CHECK: } -// CHECK: scf.for %[[VAL_41:.*]] = %[[VAL_42:.*]]#1 to %[[VAL_4]] step %[[VAL_9]] { -// CHECK: scf.for %[[VAL_43:.*]] = %[[VAL_8]] to %[[VAL_5]] step %[[VAL_9]] { -// CHECK: scf.for %[[VAL_44:.*]] = %[[VAL_8]] to %[[VAL_6]] step %[[VAL_9]] { -// CHECK: %[[VAL_45:.*]] = load %[[VAL_13]]{{\[}}%[[VAL_41]], %[[VAL_43]], %[[VAL_44]]] : memref<32x16x8xf32> +// CHECK: scf.for %[[VAL_41:.*]] = %[[VAL_42:.*]]#1 to %[[VAL_3]] step %[[VAL_8]] { +// CHECK: scf.for %[[VAL_43:.*]] = %[[VAL_7]] to %[[VAL_4]] step %[[VAL_8]] { +// CHECK: scf.for %[[VAL_44:.*]] = %[[VAL_7]] to %[[VAL_5]] step %[[VAL_8]] { +// CHECK: %[[VAL_45:.*]] = load %[[VAL_12]]{{\[}}%[[VAL_41]], %[[VAL_43]], %[[VAL_44]]] : memref<32x16x8xf32> // CHECK: store %[[VAL_45]], %[[VAL_14]]{{\[}}%[[VAL_41]], %[[VAL_43]], %[[VAL_44]]] : memref<32x16x8xf32> // CHECK: } // CHECK: } @@ -602,28 +617,29 @@ // CHECK-SAME: %[[VAL_0:.*0]]: tensor<32x16x8xf32>, // CHECK-SAME: %[[VAL_1:.*1]]: tensor<32x16x8xf32>, // CHECK-SAME: %[[VAL_2:.*2]]: tensor<32x16x8xf32>) -> tensor<32x16x8xf32> { -// CHECK: %[[VAL_3:.*]] = constant 999 : index -// CHECK: %[[VAL_4:.*]] = constant 16 : index -// CHECK: %[[VAL_5:.*]] = constant 8 : index -// CHECK: %[[VAL_6:.*]] = constant 0 : index -// CHECK: %[[VAL_7:.*]] = constant 1 : index -// CHECK: %[[VAL_8:.*]] = alloca(%[[VAL_3]]) : memref -// CHECK: %[[VAL_9:.*]] = alloca(%[[VAL_3]]) : memref -// CHECK: %[[VAL_10:.*]] = alloca(%[[VAL_3]]) : memref -// CHECK: %[[VAL_11:.*]] = alloca() : memref<32x16x8xf32> -// CHECK: %[[VAL_12:.*]] = alloca() : memref<32x16x8xf32> -// CHECK: %[[VAL_13:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_6]]] : memref -// CHECK: %[[VAL_14:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_7]]] : memref -// CHECK: scf.for %[[VAL_15:.*]] = %[[VAL_13]] to %[[VAL_14]] step %[[VAL_7]] { -// CHECK: %[[VAL_16:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_15]]] : memref -// CHECK: scf.for %[[VAL_17:.*]] = %[[VAL_6]] to %[[VAL_4]] step %[[VAL_7]] { -// CHECK: %[[VAL_18:.*]] = muli %[[VAL_15]], %[[VAL_4]] : index +// CHECK: %[[VAL_3:.*]] = constant 16 : index +// CHECK: %[[VAL_4:.*]] = constant 8 : index +// CHECK: %[[VAL_5:.*]] = constant 0 : index +// CHECK: %[[VAL_6:.*]] = constant 1 : index +// CHECK: %[[VAL_7:.*]] = linalg.sparse_pointers %[[VAL_0]], %[[VAL_5]] : tensor<32x16x8xf32> into memref +// CHECK: %[[VAL_8:.*]] = linalg.sparse_indices %[[VAL_0]], %[[VAL_5]] : tensor<32x16x8xf32> into memref +// CHECK: %[[VAL_9:.*]] = linalg.sparse_values %[[VAL_0]] : tensor<32x16x8xf32> into memref +// CHECK: %[[VAL_10:.*]] = tensor_to_memref %[[VAL_1]] : memref<32x16x8xf32> +// CHECK: %[[VAL_11:.*]] = tensor_to_memref %[[VAL_2]] : memref<32x16x8xf32> +// CHECK: %[[VAL_12:.*]] = alloc() : memref<32x16x8xf32> +// CHECK: linalg.copy(%[[VAL_11]], %[[VAL_12]]) : memref<32x16x8xf32>, memref<32x16x8xf32> +// CHECK: %[[VAL_13:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_5]]] : memref +// CHECK: %[[VAL_14:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_6]]] : memref +// CHECK: scf.for %[[VAL_15:.*]] = %[[VAL_13]] to %[[VAL_14]] step %[[VAL_6]] { +// CHECK: %[[VAL_16:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_15]]] : memref +// CHECK: scf.for %[[VAL_17:.*]] = %[[VAL_5]] to %[[VAL_3]] step %[[VAL_6]] { +// CHECK: %[[VAL_18:.*]] = muli %[[VAL_15]], %[[VAL_3]] : index // CHECK: %[[VAL_19:.*]] = addi %[[VAL_18]], %[[VAL_17]] : index -// CHECK: scf.for %[[VAL_20:.*]] = %[[VAL_6]] to %[[VAL_5]] step %[[VAL_7]] { -// CHECK: %[[VAL_21:.*]] = muli %[[VAL_19]], %[[VAL_5]] : index +// CHECK: scf.for %[[VAL_20:.*]] = %[[VAL_5]] to %[[VAL_4]] step %[[VAL_6]] { +// CHECK: %[[VAL_21:.*]] = muli %[[VAL_19]], %[[VAL_4]] : index // CHECK: %[[VAL_22:.*]] = addi %[[VAL_21]], %[[VAL_20]] : index -// CHECK: %[[VAL_23:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_22]]] : memref -// CHECK: %[[VAL_24:.*]] = load %[[VAL_11]]{{\[}}%[[VAL_16]], %[[VAL_17]], %[[VAL_20]]] : memref<32x16x8xf32> +// CHECK: %[[VAL_23:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_22]]] : memref +// CHECK: %[[VAL_24:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_16]], %[[VAL_17]], %[[VAL_20]]] : memref<32x16x8xf32> // CHECK: %[[VAL_25:.*]] = mulf %[[VAL_23]], %[[VAL_24]] : f32 // CHECK: store %[[VAL_25]], %[[VAL_12]]{{\[}}%[[VAL_16]], %[[VAL_17]], %[[VAL_20]]] : memref<32x16x8xf32> // CHECK: } @@ -662,93 +678,95 @@ // CHECK-SAME: %[[VAL_0:.*0]]: tensor<32x16x8xf32>, // CHECK-SAME: %[[VAL_1:.*1]]: tensor<32x16x8xf32>, // CHECK-SAME: %[[VAL_2:.*2]]: tensor<32x16x8xf32>) -> tensor<32x16x8xf32> { -// CHECK: %[[VAL_3:.*]] = constant 999 : index +// CHECK: %[[VAL_3:.*]] = constant 2 : index // CHECK: %[[VAL_4:.*]] = constant 32 : index // CHECK: %[[VAL_5:.*]] = constant 16 : index // CHECK: %[[VAL_6:.*]] = constant 8 : index // CHECK: %[[VAL_7:.*]] = constant true // CHECK: %[[VAL_8:.*]] = constant 0 : index // CHECK: %[[VAL_9:.*]] = constant 1 : index -// CHECK: %[[VAL_10:.*]] = alloca(%[[VAL_3]]) : memref -// CHECK: %[[VAL_11:.*]] = alloca(%[[VAL_3]]) : memref -// CHECK: %[[VAL_12:.*]] = alloca(%[[VAL_3]]) : memref -// CHECK: %[[VAL_13:.*]] = alloca(%[[VAL_3]]) : memref -// CHECK: %[[VAL_14:.*]] = alloca(%[[VAL_3]]) : memref -// CHECK: %[[VAL_15:.*]] = alloca() : memref<32x16x8xf32> -// CHECK: %[[VAL_16:.*]] = alloca() : memref<32x16x8xf32> -// CHECK: %[[VAL_17:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_8]]] : memref -// CHECK: %[[VAL_18:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_9]]] : memref -// CHECK: %[[VAL_19:.*]]:2 = scf.while (%[[VAL_20:.*]] = %[[VAL_17]], %[[VAL_21:.*]] = %[[VAL_8]]) : (index, index) -> (index, index) { -// CHECK: %[[VAL_22:.*]] = cmpi ult, %[[VAL_20]], %[[VAL_18]] : index -// CHECK: scf.condition(%[[VAL_22]]) %[[VAL_20]], %[[VAL_21]] : index, index +// CHECK: %[[VAL_10:.*]] = linalg.sparse_pointers %[[VAL_0]], %[[VAL_8]] : tensor<32x16x8xf32> into memref +// CHECK: %[[VAL_11:.*]] = linalg.sparse_indices %[[VAL_0]], %[[VAL_8]] : tensor<32x16x8xf32> into memref +// CHECK: %[[VAL_12:.*]] = linalg.sparse_pointers %[[VAL_0]], %[[VAL_3]] : tensor<32x16x8xf32> into memref +// CHECK: %[[VAL_13:.*]] = linalg.sparse_indices %[[VAL_0]], %[[VAL_3]] : tensor<32x16x8xf32> into memref +// CHECK: %[[VAL_14:.*]] = linalg.sparse_values %[[VAL_0]] : tensor<32x16x8xf32> into memref +// CHECK: %[[VAL_15:.*]] = tensor_to_memref %[[VAL_1]] : memref<32x16x8xf32> +// CHECK: %[[VAL_16:.*]] = tensor_to_memref %[[VAL_2]] : memref<32x16x8xf32> +// CHECK: %[[VAL_17:.*]] = alloc() : memref<32x16x8xf32> +// CHECK: linalg.copy(%[[VAL_16]], %[[VAL_17]]) : memref<32x16x8xf32>, memref<32x16x8xf32> +// CHECK: %[[VAL_18:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_8]]] : memref +// CHECK: %[[VAL_19:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_9]]] : memref +// CHECK: %[[VAL_20:.*]]:2 = scf.while (%[[VAL_21:.*]] = %[[VAL_18]], %[[VAL_22:.*]] = %[[VAL_8]]) : (index, index) -> (index, index) { +// CHECK: %[[VAL_23:.*]] = cmpi ult, %[[VAL_21]], %[[VAL_19]] : index +// CHECK: scf.condition(%[[VAL_23]]) %[[VAL_21]], %[[VAL_22]] : index, index // CHECK: } do { -// CHECK: ^bb0(%[[VAL_23:.*]]: index, %[[VAL_24:.*]]: index): -// CHECK: %[[VAL_25:.*]] = load %[[VAL_11]]{{\[}}%[[VAL_23]]] : memref -// CHECK: %[[VAL_26:.*]] = cmpi eq, %[[VAL_25]], %[[VAL_24]] : index -// CHECK: scf.if %[[VAL_26]] { -// CHECK: scf.for %[[VAL_27:.*]] = %[[VAL_8]] to %[[VAL_5]] step %[[VAL_9]] { -// CHECK: %[[VAL_28:.*]] = muli %[[VAL_23]], %[[VAL_5]] : index -// CHECK: %[[VAL_29:.*]] = addi %[[VAL_28]], %[[VAL_27]] : index -// CHECK: %[[VAL_30:.*]] = load %[[VAL_12]]{{\[}}%[[VAL_29]]] : memref -// CHECK: %[[VAL_31:.*]] = addi %[[VAL_29]], %[[VAL_9]] : index -// CHECK: %[[VAL_32:.*]] = load %[[VAL_12]]{{\[}}%[[VAL_31]]] : memref -// CHECK: %[[VAL_33:.*]]:2 = scf.while (%[[VAL_34:.*]] = %[[VAL_30]], %[[VAL_35:.*]] = %[[VAL_8]]) : (index, index) -> (index, index) { -// CHECK: %[[VAL_36:.*]] = cmpi ult, %[[VAL_34]], %[[VAL_32]] : index -// CHECK: scf.condition(%[[VAL_36]]) %[[VAL_34]], %[[VAL_35]] : index, index +// CHECK: ^bb0(%[[VAL_24:.*]]: index, %[[VAL_25:.*]]: index): +// CHECK: %[[VAL_26:.*]] = load %[[VAL_11]]{{\[}}%[[VAL_24]]] : memref +// CHECK: %[[VAL_27:.*]] = cmpi eq, %[[VAL_26]], %[[VAL_25]] : index +// CHECK: scf.if %[[VAL_27]] { +// CHECK: scf.for %[[VAL_28:.*]] = %[[VAL_8]] to %[[VAL_5]] step %[[VAL_9]] { +// CHECK: %[[VAL_29:.*]] = muli %[[VAL_24]], %[[VAL_5]] : index +// CHECK: %[[VAL_30:.*]] = addi %[[VAL_29]], %[[VAL_28]] : index +// CHECK: %[[VAL_31:.*]] = load %[[VAL_12]]{{\[}}%[[VAL_30]]] : memref +// CHECK: %[[VAL_32:.*]] = addi %[[VAL_30]], %[[VAL_9]] : index +// CHECK: %[[VAL_33:.*]] = load %[[VAL_12]]{{\[}}%[[VAL_32]]] : memref +// CHECK: %[[VAL_34:.*]]:2 = scf.while (%[[VAL_35:.*]] = %[[VAL_31]], %[[VAL_36:.*]] = %[[VAL_8]]) : (index, index) -> (index, index) { +// CHECK: %[[VAL_37:.*]] = cmpi ult, %[[VAL_35]], %[[VAL_33]] : index +// CHECK: scf.condition(%[[VAL_37]]) %[[VAL_35]], %[[VAL_36]] : index, index // CHECK: } do { -// CHECK: ^bb0(%[[VAL_37:.*]]: index, %[[VAL_38:.*]]: index): -// CHECK: %[[VAL_39:.*]] = load %[[VAL_13]]{{\[}}%[[VAL_37]]] : memref -// CHECK: %[[VAL_40:.*]] = cmpi eq, %[[VAL_39]], %[[VAL_38]] : index -// CHECK: scf.if %[[VAL_40]] { -// CHECK: %[[VAL_41:.*]] = load %[[VAL_14]]{{\[}}%[[VAL_37]]] : memref -// CHECK: %[[VAL_42:.*]] = load %[[VAL_15]]{{\[}}%[[VAL_24]], %[[VAL_27]], %[[VAL_38]]] : memref<32x16x8xf32> -// CHECK: %[[VAL_43:.*]] = addf %[[VAL_41]], %[[VAL_42]] : f32 -// CHECK: store %[[VAL_43]], %[[VAL_16]]{{\[}}%[[VAL_24]], %[[VAL_27]], %[[VAL_38]]] : memref<32x16x8xf32> +// CHECK: ^bb0(%[[VAL_38:.*]]: index, %[[VAL_39:.*]]: index): +// CHECK: %[[VAL_40:.*]] = load %[[VAL_13]]{{\[}}%[[VAL_38]]] : memref +// CHECK: %[[VAL_41:.*]] = cmpi eq, %[[VAL_40]], %[[VAL_39]] : index +// CHECK: scf.if %[[VAL_41]] { +// CHECK: %[[VAL_42:.*]] = load %[[VAL_14]]{{\[}}%[[VAL_38]]] : memref +// CHECK: %[[VAL_43:.*]] = load %[[VAL_15]]{{\[}}%[[VAL_25]], %[[VAL_28]], %[[VAL_39]]] : memref<32x16x8xf32> +// CHECK: %[[VAL_44:.*]] = addf %[[VAL_42]], %[[VAL_43]] : f32 +// CHECK: store %[[VAL_44]], %[[VAL_17]]{{\[}}%[[VAL_25]], %[[VAL_28]], %[[VAL_39]]] : memref<32x16x8xf32> // CHECK: } else { // CHECK: scf.if %[[VAL_7]] { -// CHECK: %[[VAL_44:.*]] = load %[[VAL_15]]{{\[}}%[[VAL_24]], %[[VAL_27]], %[[VAL_38]]] : memref<32x16x8xf32> -// CHECK: store %[[VAL_44]], %[[VAL_16]]{{\[}}%[[VAL_24]], %[[VAL_27]], %[[VAL_38]]] : memref<32x16x8xf32> +// CHECK: %[[VAL_45:.*]] = load %[[VAL_15]]{{\[}}%[[VAL_25]], %[[VAL_28]], %[[VAL_39]]] : memref<32x16x8xf32> +// CHECK: store %[[VAL_45]], %[[VAL_17]]{{\[}}%[[VAL_25]], %[[VAL_28]], %[[VAL_39]]] : memref<32x16x8xf32> // CHECK: } else { // CHECK: } // CHECK: } -// CHECK: %[[VAL_45:.*]] = cmpi eq, %[[VAL_39]], %[[VAL_38]] : index -// CHECK: %[[VAL_46:.*]] = addi %[[VAL_37]], %[[VAL_9]] : index -// CHECK: %[[VAL_47:.*]] = select %[[VAL_45]], %[[VAL_46]], %[[VAL_37]] : index -// CHECK: %[[VAL_48:.*]] = addi %[[VAL_38]], %[[VAL_9]] : index -// CHECK: scf.yield %[[VAL_47]], %[[VAL_48]] : index, index +// CHECK: %[[VAL_46:.*]] = cmpi eq, %[[VAL_40]], %[[VAL_39]] : index +// CHECK: %[[VAL_47:.*]] = addi %[[VAL_38]], %[[VAL_9]] : index +// CHECK: %[[VAL_48:.*]] = select %[[VAL_46]], %[[VAL_47]], %[[VAL_38]] : index +// CHECK: %[[VAL_49:.*]] = addi %[[VAL_39]], %[[VAL_9]] : index +// CHECK: scf.yield %[[VAL_48]], %[[VAL_49]] : index, index // CHECK: } -// CHECK: scf.for %[[VAL_49:.*]] = %[[VAL_50:.*]]#1 to %[[VAL_6]] step %[[VAL_9]] { -// CHECK: %[[VAL_51:.*]] = load %[[VAL_15]]{{\[}}%[[VAL_24]], %[[VAL_27]], %[[VAL_49]]] : memref<32x16x8xf32> -// CHECK: store %[[VAL_51]], %[[VAL_16]]{{\[}}%[[VAL_24]], %[[VAL_27]], %[[VAL_49]]] : memref<32x16x8xf32> +// CHECK: scf.for %[[VAL_50:.*]] = %[[VAL_51:.*]]#1 to %[[VAL_6]] step %[[VAL_9]] { +// CHECK: %[[VAL_52:.*]] = load %[[VAL_15]]{{\[}}%[[VAL_25]], %[[VAL_28]], %[[VAL_50]]] : memref<32x16x8xf32> +// CHECK: store %[[VAL_52]], %[[VAL_17]]{{\[}}%[[VAL_25]], %[[VAL_28]], %[[VAL_50]]] : memref<32x16x8xf32> // CHECK: } // CHECK: } // CHECK: } else { // CHECK: scf.if %[[VAL_7]] { -// CHECK: scf.for %[[VAL_52:.*]] = %[[VAL_8]] to %[[VAL_5]] step %[[VAL_9]] { -// CHECK: scf.for %[[VAL_53:.*]] = %[[VAL_8]] to %[[VAL_6]] step %[[VAL_9]] { -// CHECK: %[[VAL_54:.*]] = load %[[VAL_15]]{{\[}}%[[VAL_24]], %[[VAL_52]], %[[VAL_53]]] : memref<32x16x8xf32> -// CHECK: store %[[VAL_54]], %[[VAL_16]]{{\[}}%[[VAL_24]], %[[VAL_52]], %[[VAL_53]]] : memref<32x16x8xf32> +// CHECK: scf.for %[[VAL_53:.*]] = %[[VAL_8]] to %[[VAL_5]] step %[[VAL_9]] { +// CHECK: scf.for %[[VAL_54:.*]] = %[[VAL_8]] to %[[VAL_6]] step %[[VAL_9]] { +// CHECK: %[[VAL_55:.*]] = load %[[VAL_15]]{{\[}}%[[VAL_25]], %[[VAL_53]], %[[VAL_54]]] : memref<32x16x8xf32> +// CHECK: store %[[VAL_55]], %[[VAL_17]]{{\[}}%[[VAL_25]], %[[VAL_53]], %[[VAL_54]]] : memref<32x16x8xf32> // CHECK: } // CHECK: } // CHECK: } else { // CHECK: } // CHECK: } -// CHECK: %[[VAL_55:.*]] = cmpi eq, %[[VAL_25]], %[[VAL_24]] : index -// CHECK: %[[VAL_56:.*]] = addi %[[VAL_23]], %[[VAL_9]] : index -// CHECK: %[[VAL_57:.*]] = select %[[VAL_55]], %[[VAL_56]], %[[VAL_23]] : index -// CHECK: %[[VAL_58:.*]] = addi %[[VAL_24]], %[[VAL_9]] : index -// CHECK: scf.yield %[[VAL_57]], %[[VAL_58]] : index, index +// CHECK: %[[VAL_56:.*]] = cmpi eq, %[[VAL_26]], %[[VAL_25]] : index +// CHECK: %[[VAL_57:.*]] = addi %[[VAL_24]], %[[VAL_9]] : index +// CHECK: %[[VAL_58:.*]] = select %[[VAL_56]], %[[VAL_57]], %[[VAL_24]] : index +// CHECK: %[[VAL_59:.*]] = addi %[[VAL_25]], %[[VAL_9]] : index +// CHECK: scf.yield %[[VAL_58]], %[[VAL_59]] : index, index // CHECK: } -// CHECK: scf.for %[[VAL_59:.*]] = %[[VAL_60:.*]]#1 to %[[VAL_4]] step %[[VAL_9]] { -// CHECK: scf.for %[[VAL_61:.*]] = %[[VAL_8]] to %[[VAL_5]] step %[[VAL_9]] { -// CHECK: scf.for %[[VAL_62:.*]] = %[[VAL_8]] to %[[VAL_6]] step %[[VAL_9]] { -// CHECK: %[[VAL_63:.*]] = load %[[VAL_15]]{{\[}}%[[VAL_59]], %[[VAL_61]], %[[VAL_62]]] : memref<32x16x8xf32> -// CHECK: store %[[VAL_63]], %[[VAL_16]]{{\[}}%[[VAL_59]], %[[VAL_61]], %[[VAL_62]]] : memref<32x16x8xf32> +// CHECK: scf.for %[[VAL_60:.*]] = %[[VAL_61:.*]]#1 to %[[VAL_4]] step %[[VAL_9]] { +// CHECK: scf.for %[[VAL_62:.*]] = %[[VAL_8]] to %[[VAL_5]] step %[[VAL_9]] { +// CHECK: scf.for %[[VAL_63:.*]] = %[[VAL_8]] to %[[VAL_6]] step %[[VAL_9]] { +// CHECK: %[[VAL_64:.*]] = load %[[VAL_15]]{{\[}}%[[VAL_60]], %[[VAL_62]], %[[VAL_63]]] : memref<32x16x8xf32> +// CHECK: store %[[VAL_64]], %[[VAL_17]]{{\[}}%[[VAL_60]], %[[VAL_62]], %[[VAL_63]]] : memref<32x16x8xf32> // CHECK: } // CHECK: } // CHECK: } -// CHECK: %[[VAL_64:.*]] = tensor_load %[[VAL_16]] : memref<32x16x8xf32> -// CHECK: return %[[VAL_64]] : tensor<32x16x8xf32> +// CHECK: %[[VAL_65:.*]] = tensor_load %[[VAL_17]] : memref<32x16x8xf32> +// CHECK: return %[[VAL_65]] : tensor<32x16x8xf32> // CHECK: } func @add_sds(%arga: tensor<32x16x8xf32>, %argb: tensor<32x16x8xf32>, %argx: tensor<32x16x8xf32>) -> tensor<32x16x8xf32> { %0 = linalg.generic #trait_sds @@ -765,38 +783,40 @@ // CHECK-SAME: %[[VAL_0:.*0]]: tensor<32x16x8xf32>, // CHECK-SAME: %[[VAL_1:.*1]]: tensor<32x16x8xf32>, // CHECK-SAME: %[[VAL_2:.*2]]: tensor<32x16x8xf32>) -> tensor<32x16x8xf32> { -// CHECK: %[[VAL_3:.*]] = constant 999 : index +// CHECK: %[[VAL_3:.*]] = constant 2 : index // CHECK: %[[VAL_4:.*]] = constant 16 : index // CHECK: %[[VAL_5:.*]] = constant 0 : index // CHECK: %[[VAL_6:.*]] = constant 1 : index -// CHECK: %[[VAL_7:.*]] = alloca(%[[VAL_3]]) : memref -// CHECK: %[[VAL_8:.*]] = alloca(%[[VAL_3]]) : memref -// CHECK: %[[VAL_9:.*]] = alloca(%[[VAL_3]]) : memref -// CHECK: %[[VAL_10:.*]] = alloca(%[[VAL_3]]) : memref -// CHECK: %[[VAL_11:.*]] = alloca(%[[VAL_3]]) : memref -// CHECK: %[[VAL_12:.*]] = alloca() : memref<32x16x8xf32> -// CHECK: %[[VAL_13:.*]] = alloca() : memref<32x16x8xf32> -// CHECK: %[[VAL_14:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_5]]] : memref -// CHECK: %[[VAL_15:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_6]]] : memref -// CHECK: scf.for %[[VAL_16:.*]] = %[[VAL_14]] to %[[VAL_15]] step %[[VAL_6]] { -// CHECK: %[[VAL_17:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_16]]] : memref -// CHECK: scf.for %[[VAL_18:.*]] = %[[VAL_5]] to %[[VAL_4]] step %[[VAL_6]] { -// CHECK: %[[VAL_19:.*]] = muli %[[VAL_16]], %[[VAL_4]] : index -// CHECK: %[[VAL_20:.*]] = addi %[[VAL_19]], %[[VAL_18]] : index -// CHECK: %[[VAL_21:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_20]]] : memref -// CHECK: %[[VAL_22:.*]] = addi %[[VAL_20]], %[[VAL_6]] : index -// CHECK: %[[VAL_23:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_22]]] : memref -// CHECK: scf.for %[[VAL_24:.*]] = %[[VAL_21]] to %[[VAL_23]] step %[[VAL_6]] { -// CHECK: %[[VAL_25:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_24]]] : memref -// CHECK: %[[VAL_26:.*]] = load %[[VAL_11]]{{\[}}%[[VAL_24]]] : memref -// CHECK: %[[VAL_27:.*]] = load %[[VAL_12]]{{\[}}%[[VAL_17]], %[[VAL_18]], %[[VAL_25]]] : memref<32x16x8xf32> -// CHECK: %[[VAL_28:.*]] = mulf %[[VAL_26]], %[[VAL_27]] : f32 -// CHECK: store %[[VAL_28]], %[[VAL_13]]{{\[}}%[[VAL_17]], %[[VAL_18]], %[[VAL_25]]] : memref<32x16x8xf32> +// CHECK: %[[VAL_7:.*]] = linalg.sparse_pointers %[[VAL_0]], %[[VAL_5]] : tensor<32x16x8xf32> into memref +// CHECK: %[[VAL_8:.*]] = linalg.sparse_indices %[[VAL_0]], %[[VAL_5]] : tensor<32x16x8xf32> into memref +// CHECK: %[[VAL_9:.*]] = linalg.sparse_pointers %[[VAL_0]], %[[VAL_3]] : tensor<32x16x8xf32> into memref +// CHECK: %[[VAL_10:.*]] = linalg.sparse_indices %[[VAL_0]], %[[VAL_3]] : tensor<32x16x8xf32> into memref +// CHECK: %[[VAL_11:.*]] = linalg.sparse_values %[[VAL_0]] : tensor<32x16x8xf32> into memref +// CHECK: %[[VAL_12:.*]] = tensor_to_memref %[[VAL_1]] : memref<32x16x8xf32> +// CHECK: %[[VAL_13:.*]] = tensor_to_memref %[[VAL_2]] : memref<32x16x8xf32> +// CHECK: %[[VAL_14:.*]] = alloc() : memref<32x16x8xf32> +// CHECK: linalg.copy(%[[VAL_13]], %[[VAL_14]]) : memref<32x16x8xf32>, memref<32x16x8xf32> +// CHECK: %[[VAL_15:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_5]]] : memref +// CHECK: %[[VAL_16:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_6]]] : memref +// CHECK: scf.for %[[VAL_17:.*]] = %[[VAL_15]] to %[[VAL_16]] step %[[VAL_6]] { +// CHECK: %[[VAL_18:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_17]]] : memref +// CHECK: scf.for %[[VAL_19:.*]] = %[[VAL_5]] to %[[VAL_4]] step %[[VAL_6]] { +// CHECK: %[[VAL_20:.*]] = muli %[[VAL_17]], %[[VAL_4]] : index +// CHECK: %[[VAL_21:.*]] = addi %[[VAL_20]], %[[VAL_19]] : index +// CHECK: %[[VAL_22:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_21]]] : memref +// CHECK: %[[VAL_23:.*]] = addi %[[VAL_21]], %[[VAL_6]] : index +// CHECK: %[[VAL_24:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_23]]] : memref +// CHECK: scf.for %[[VAL_25:.*]] = %[[VAL_22]] to %[[VAL_24]] step %[[VAL_6]] { +// CHECK: %[[VAL_26:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_25]]] : memref +// CHECK: %[[VAL_27:.*]] = load %[[VAL_11]]{{\[}}%[[VAL_25]]] : memref +// CHECK: %[[VAL_28:.*]] = load %[[VAL_12]]{{\[}}%[[VAL_18]], %[[VAL_19]], %[[VAL_26]]] : memref<32x16x8xf32> +// CHECK: %[[VAL_29:.*]] = mulf %[[VAL_27]], %[[VAL_28]] : f32 +// CHECK: store %[[VAL_29]], %[[VAL_14]]{{\[}}%[[VAL_18]], %[[VAL_19]], %[[VAL_26]]] : memref<32x16x8xf32> // CHECK: } // CHECK: } // CHECK: } -// CHECK: %[[VAL_29:.*]] = tensor_load %[[VAL_13]] : memref<32x16x8xf32> -// CHECK: return %[[VAL_29]] : tensor<32x16x8xf32> +// CHECK: %[[VAL_30:.*]] = tensor_load %[[VAL_14]] : memref<32x16x8xf32> +// CHECK: return %[[VAL_30]] : tensor<32x16x8xf32> // CHECK: } func @mul_sds(%arga: tensor<32x16x8xf32>, %argb: tensor<32x16x8xf32>, %argx: tensor<32x16x8xf32>) -> tensor<32x16x8xf32> { %0 = linalg.generic #trait_sds @@ -828,75 +848,76 @@ // CHECK-SAME: %[[VAL_0:.*0]]: tensor<32x16x8xf32>, // CHECK-SAME: %[[VAL_1:.*1]]: tensor<32x16x8xf32>, // CHECK-SAME: %[[VAL_2:.*2]]: tensor<32x16x8xf32>) -> tensor<32x16x8xf32> { -// CHECK: %[[VAL_3:.*]] = constant 999 : index -// CHECK: %[[VAL_4:.*]] = constant 32 : index -// CHECK: %[[VAL_5:.*]] = constant 16 : index -// CHECK: %[[VAL_6:.*]] = constant 8 : index -// CHECK: %[[VAL_7:.*]] = constant true -// CHECK: %[[VAL_8:.*]] = constant 0 : index -// CHECK: %[[VAL_9:.*]] = constant 1 : index -// CHECK: %[[VAL_10:.*]] = alloca(%[[VAL_3]]) : memref -// CHECK: %[[VAL_11:.*]] = alloca(%[[VAL_3]]) : memref -// CHECK: %[[VAL_12:.*]] = alloca(%[[VAL_3]]) : memref -// CHECK: %[[VAL_13:.*]] = alloca(%[[VAL_3]]) : memref -// CHECK: %[[VAL_14:.*]] = alloca(%[[VAL_3]]) : memref -// CHECK: %[[VAL_15:.*]] = alloca() : memref<32x16x8xf32> -// CHECK: %[[VAL_16:.*]] = alloca() : memref<32x16x8xf32> -// CHECK: %[[VAL_17:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_8]]] : memref -// CHECK: %[[VAL_18:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_9]]] : memref -// CHECK: %[[VAL_19:.*]]:2 = scf.while (%[[VAL_20:.*]] = %[[VAL_17]], %[[VAL_21:.*]] = %[[VAL_8]]) : (index, index) -> (index, index) { +// CHECK: %[[VAL_3:.*]] = constant 32 : index +// CHECK: %[[VAL_4:.*]] = constant 16 : index +// CHECK: %[[VAL_5:.*]] = constant 8 : index +// CHECK: %[[VAL_6:.*]] = constant true +// CHECK: %[[VAL_7:.*]] = constant 0 : index +// CHECK: %[[VAL_8:.*]] = constant 1 : index +// CHECK: %[[VAL_9:.*]] = linalg.sparse_pointers %[[VAL_0]], %[[VAL_7]] : tensor<32x16x8xf32> into memref +// CHECK: %[[VAL_10:.*]] = linalg.sparse_indices %[[VAL_0]], %[[VAL_7]] : tensor<32x16x8xf32> into memref +// CHECK: %[[VAL_11:.*]] = linalg.sparse_pointers %[[VAL_0]], %[[VAL_8]] : tensor<32x16x8xf32> into memref +// CHECK: %[[VAL_12:.*]] = linalg.sparse_indices %[[VAL_0]], %[[VAL_8]] : tensor<32x16x8xf32> into memref +// CHECK: %[[VAL_13:.*]] = linalg.sparse_values %[[VAL_0]] : tensor<32x16x8xf32> into memref +// CHECK: %[[VAL_14:.*]] = tensor_to_memref %[[VAL_1]] : memref<32x16x8xf32> +// CHECK: %[[VAL_15:.*]] = tensor_to_memref %[[VAL_2]] : memref<32x16x8xf32> +// CHECK: %[[VAL_16:.*]] = alloc() : memref<32x16x8xf32> +// CHECK: linalg.copy(%[[VAL_15]], %[[VAL_16]]) : memref<32x16x8xf32>, memref<32x16x8xf32> +// CHECK: %[[VAL_17:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_7]]] : memref +// CHECK: %[[VAL_18:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_8]]] : memref +// CHECK: %[[VAL_19:.*]]:2 = scf.while (%[[VAL_20:.*]] = %[[VAL_17]], %[[VAL_21:.*]] = %[[VAL_7]]) : (index, index) -> (index, index) { // CHECK: %[[VAL_22:.*]] = cmpi ult, %[[VAL_20]], %[[VAL_18]] : index // CHECK: scf.condition(%[[VAL_22]]) %[[VAL_20]], %[[VAL_21]] : index, index // CHECK: } do { // CHECK: ^bb0(%[[VAL_23:.*]]: index, %[[VAL_24:.*]]: index): -// CHECK: %[[VAL_25:.*]] = load %[[VAL_11]]{{\[}}%[[VAL_23]]] : memref +// CHECK: %[[VAL_25:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_23]]] : memref // CHECK: %[[VAL_26:.*]] = cmpi eq, %[[VAL_25]], %[[VAL_24]] : index // CHECK: scf.if %[[VAL_26]] { -// CHECK: %[[VAL_27:.*]] = load %[[VAL_12]]{{\[}}%[[VAL_23]]] : memref -// CHECK: %[[VAL_28:.*]] = addi %[[VAL_23]], %[[VAL_9]] : index -// CHECK: %[[VAL_29:.*]] = load %[[VAL_12]]{{\[}}%[[VAL_28]]] : memref -// CHECK: %[[VAL_30:.*]]:2 = scf.while (%[[VAL_31:.*]] = %[[VAL_27]], %[[VAL_32:.*]] = %[[VAL_8]]) : (index, index) -> (index, index) { +// CHECK: %[[VAL_27:.*]] = load %[[VAL_11]]{{\[}}%[[VAL_23]]] : memref +// CHECK: %[[VAL_28:.*]] = addi %[[VAL_23]], %[[VAL_8]] : index +// CHECK: %[[VAL_29:.*]] = load %[[VAL_11]]{{\[}}%[[VAL_28]]] : memref +// CHECK: %[[VAL_30:.*]]:2 = scf.while (%[[VAL_31:.*]] = %[[VAL_27]], %[[VAL_32:.*]] = %[[VAL_7]]) : (index, index) -> (index, index) { // CHECK: %[[VAL_33:.*]] = cmpi ult, %[[VAL_31]], %[[VAL_29]] : index // CHECK: scf.condition(%[[VAL_33]]) %[[VAL_31]], %[[VAL_32]] : index, index // CHECK: } do { // CHECK: ^bb0(%[[VAL_34:.*]]: index, %[[VAL_35:.*]]: index): -// CHECK: %[[VAL_36:.*]] = load %[[VAL_13]]{{\[}}%[[VAL_34]]] : memref +// CHECK: %[[VAL_36:.*]] = load %[[VAL_12]]{{\[}}%[[VAL_34]]] : memref // CHECK: %[[VAL_37:.*]] = cmpi eq, %[[VAL_36]], %[[VAL_35]] : index // CHECK: scf.if %[[VAL_37]] { -// CHECK: scf.for %[[VAL_38:.*]] = %[[VAL_8]] to %[[VAL_6]] step %[[VAL_9]] { -// CHECK: %[[VAL_39:.*]] = muli %[[VAL_34]], %[[VAL_6]] : index +// CHECK: scf.for %[[VAL_38:.*]] = %[[VAL_7]] to %[[VAL_5]] step %[[VAL_8]] { +// CHECK: %[[VAL_39:.*]] = muli %[[VAL_34]], %[[VAL_5]] : index // CHECK: %[[VAL_40:.*]] = addi %[[VAL_39]], %[[VAL_38]] : index -// CHECK: %[[VAL_41:.*]] = load %[[VAL_14]]{{\[}}%[[VAL_40]]] : memref -// CHECK: %[[VAL_42:.*]] = load %[[VAL_15]]{{\[}}%[[VAL_24]], %[[VAL_35]], %[[VAL_38]]] : memref<32x16x8xf32> +// CHECK: %[[VAL_41:.*]] = load %[[VAL_13]]{{\[}}%[[VAL_40]]] : memref +// CHECK: %[[VAL_42:.*]] = load %[[VAL_14]]{{\[}}%[[VAL_24]], %[[VAL_35]], %[[VAL_38]]] : memref<32x16x8xf32> // CHECK: %[[VAL_43:.*]] = addf %[[VAL_41]], %[[VAL_42]] : f32 // CHECK: store %[[VAL_43]], %[[VAL_16]]{{\[}}%[[VAL_24]], %[[VAL_35]], %[[VAL_38]]] : memref<32x16x8xf32> // CHECK: } // CHECK: } else { -// CHECK: scf.if %[[VAL_7]] { -// CHECK: scf.for %[[VAL_44:.*]] = %[[VAL_8]] to %[[VAL_6]] step %[[VAL_9]] { -// CHECK: %[[VAL_45:.*]] = load %[[VAL_15]]{{\[}}%[[VAL_24]], %[[VAL_35]], %[[VAL_44]]] : memref<32x16x8xf32> +// CHECK: scf.if %[[VAL_6]] { +// CHECK: scf.for %[[VAL_44:.*]] = %[[VAL_7]] to %[[VAL_5]] step %[[VAL_8]] { +// CHECK: %[[VAL_45:.*]] = load %[[VAL_14]]{{\[}}%[[VAL_24]], %[[VAL_35]], %[[VAL_44]]] : memref<32x16x8xf32> // CHECK: store %[[VAL_45]], %[[VAL_16]]{{\[}}%[[VAL_24]], %[[VAL_35]], %[[VAL_44]]] : memref<32x16x8xf32> // CHECK: } // CHECK: } else { // CHECK: } // CHECK: } // CHECK: %[[VAL_46:.*]] = cmpi eq, %[[VAL_36]], %[[VAL_35]] : index -// CHECK: %[[VAL_47:.*]] = addi %[[VAL_34]], %[[VAL_9]] : index +// CHECK: %[[VAL_47:.*]] = addi %[[VAL_34]], %[[VAL_8]] : index // CHECK: %[[VAL_48:.*]] = select %[[VAL_46]], %[[VAL_47]], %[[VAL_34]] : index -// CHECK: %[[VAL_49:.*]] = addi %[[VAL_35]], %[[VAL_9]] : index +// CHECK: %[[VAL_49:.*]] = addi %[[VAL_35]], %[[VAL_8]] : index // CHECK: scf.yield %[[VAL_48]], %[[VAL_49]] : index, index // CHECK: } -// CHECK: scf.for %[[VAL_50:.*]] = %[[VAL_51:.*]]#1 to %[[VAL_5]] step %[[VAL_9]] { -// CHECK: scf.for %[[VAL_52:.*]] = %[[VAL_8]] to %[[VAL_6]] step %[[VAL_9]] { -// CHECK: %[[VAL_53:.*]] = load %[[VAL_15]]{{\[}}%[[VAL_24]], %[[VAL_50]], %[[VAL_52]]] : memref<32x16x8xf32> +// CHECK: scf.for %[[VAL_50:.*]] = %[[VAL_51:.*]]#1 to %[[VAL_4]] step %[[VAL_8]] { +// CHECK: scf.for %[[VAL_52:.*]] = %[[VAL_7]] to %[[VAL_5]] step %[[VAL_8]] { +// CHECK: %[[VAL_53:.*]] = load %[[VAL_14]]{{\[}}%[[VAL_24]], %[[VAL_50]], %[[VAL_52]]] : memref<32x16x8xf32> // CHECK: store %[[VAL_53]], %[[VAL_16]]{{\[}}%[[VAL_24]], %[[VAL_50]], %[[VAL_52]]] : memref<32x16x8xf32> // CHECK: } // CHECK: } // CHECK: } else { -// CHECK: scf.if %[[VAL_7]] { -// CHECK: scf.for %[[VAL_54:.*]] = %[[VAL_8]] to %[[VAL_5]] step %[[VAL_9]] { -// CHECK: scf.for %[[VAL_55:.*]] = %[[VAL_8]] to %[[VAL_6]] step %[[VAL_9]] { -// CHECK: %[[VAL_56:.*]] = load %[[VAL_15]]{{\[}}%[[VAL_24]], %[[VAL_54]], %[[VAL_55]]] : memref<32x16x8xf32> +// CHECK: scf.if %[[VAL_6]] { +// CHECK: scf.for %[[VAL_54:.*]] = %[[VAL_7]] to %[[VAL_4]] step %[[VAL_8]] { +// CHECK: scf.for %[[VAL_55:.*]] = %[[VAL_7]] to %[[VAL_5]] step %[[VAL_8]] { +// CHECK: %[[VAL_56:.*]] = load %[[VAL_14]]{{\[}}%[[VAL_24]], %[[VAL_54]], %[[VAL_55]]] : memref<32x16x8xf32> // CHECK: store %[[VAL_56]], %[[VAL_16]]{{\[}}%[[VAL_24]], %[[VAL_54]], %[[VAL_55]]] : memref<32x16x8xf32> // CHECK: } // CHECK: } @@ -904,15 +925,15 @@ // CHECK: } // CHECK: } // CHECK: %[[VAL_57:.*]] = cmpi eq, %[[VAL_25]], %[[VAL_24]] : index -// CHECK: %[[VAL_58:.*]] = addi %[[VAL_23]], %[[VAL_9]] : index +// CHECK: %[[VAL_58:.*]] = addi %[[VAL_23]], %[[VAL_8]] : index // CHECK: %[[VAL_59:.*]] = select %[[VAL_57]], %[[VAL_58]], %[[VAL_23]] : index -// CHECK: %[[VAL_60:.*]] = addi %[[VAL_24]], %[[VAL_9]] : index +// CHECK: %[[VAL_60:.*]] = addi %[[VAL_24]], %[[VAL_8]] : index // CHECK: scf.yield %[[VAL_59]], %[[VAL_60]] : index, index // CHECK: } -// CHECK: scf.for %[[VAL_61:.*]] = %[[VAL_62:.*]]#1 to %[[VAL_4]] step %[[VAL_9]] { -// CHECK: scf.for %[[VAL_63:.*]] = %[[VAL_8]] to %[[VAL_5]] step %[[VAL_9]] { -// CHECK: scf.for %[[VAL_64:.*]] = %[[VAL_8]] to %[[VAL_6]] step %[[VAL_9]] { -// CHECK: %[[VAL_65:.*]] = load %[[VAL_15]]{{\[}}%[[VAL_61]], %[[VAL_63]], %[[VAL_64]]] : memref<32x16x8xf32> +// CHECK: scf.for %[[VAL_61:.*]] = %[[VAL_62:.*]]#1 to %[[VAL_3]] step %[[VAL_8]] { +// CHECK: scf.for %[[VAL_63:.*]] = %[[VAL_7]] to %[[VAL_4]] step %[[VAL_8]] { +// CHECK: scf.for %[[VAL_64:.*]] = %[[VAL_7]] to %[[VAL_5]] step %[[VAL_8]] { +// CHECK: %[[VAL_65:.*]] = load %[[VAL_14]]{{\[}}%[[VAL_61]], %[[VAL_63]], %[[VAL_64]]] : memref<32x16x8xf32> // CHECK: store %[[VAL_65]], %[[VAL_16]]{{\[}}%[[VAL_61]], %[[VAL_63]], %[[VAL_64]]] : memref<32x16x8xf32> // CHECK: } // CHECK: } @@ -935,31 +956,32 @@ // CHECK-SAME: %[[VAL_0:.*0]]: tensor<32x16x8xf32>, // CHECK-SAME: %[[VAL_1:.*1]]: tensor<32x16x8xf32>, // CHECK-SAME: %[[VAL_2:.*2]]: tensor<32x16x8xf32>) -> tensor<32x16x8xf32> { -// CHECK: %[[VAL_3:.*]] = constant 999 : index -// CHECK: %[[VAL_4:.*]] = constant 8 : index -// CHECK: %[[VAL_5:.*]] = constant 0 : index -// CHECK: %[[VAL_6:.*]] = constant 1 : index -// CHECK: %[[VAL_7:.*]] = alloca(%[[VAL_3]]) : memref -// CHECK: %[[VAL_8:.*]] = alloca(%[[VAL_3]]) : memref -// CHECK: %[[VAL_9:.*]] = alloca(%[[VAL_3]]) : memref -// CHECK: %[[VAL_10:.*]] = alloca(%[[VAL_3]]) : memref -// CHECK: %[[VAL_11:.*]] = alloca(%[[VAL_3]]) : memref -// CHECK: %[[VAL_12:.*]] = alloca() : memref<32x16x8xf32> -// CHECK: %[[VAL_13:.*]] = alloca() : memref<32x16x8xf32> -// CHECK: %[[VAL_14:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_5]]] : memref -// CHECK: %[[VAL_15:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_6]]] : memref -// CHECK: scf.for %[[VAL_16:.*]] = %[[VAL_14]] to %[[VAL_15]] step %[[VAL_6]] { -// CHECK: %[[VAL_17:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_16]]] : memref -// CHECK: %[[VAL_18:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_16]]] : memref -// CHECK: %[[VAL_19:.*]] = addi %[[VAL_16]], %[[VAL_6]] : index -// CHECK: %[[VAL_20:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_19]]] : memref -// CHECK: scf.for %[[VAL_21:.*]] = %[[VAL_18]] to %[[VAL_20]] step %[[VAL_6]] { -// CHECK: %[[VAL_22:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_21]]] : memref -// CHECK: scf.for %[[VAL_23:.*]] = %[[VAL_5]] to %[[VAL_4]] step %[[VAL_6]] { -// CHECK: %[[VAL_24:.*]] = muli %[[VAL_21]], %[[VAL_4]] : index +// CHECK: %[[VAL_3:.*]] = constant 8 : index +// CHECK: %[[VAL_4:.*]] = constant 0 : index +// CHECK: %[[VAL_5:.*]] = constant 1 : index +// CHECK: %[[VAL_6:.*]] = linalg.sparse_pointers %[[VAL_0]], %[[VAL_4]] : tensor<32x16x8xf32> into memref +// CHECK: %[[VAL_7:.*]] = linalg.sparse_indices %[[VAL_0]], %[[VAL_4]] : tensor<32x16x8xf32> into memref +// CHECK: %[[VAL_8:.*]] = linalg.sparse_pointers %[[VAL_0]], %[[VAL_5]] : tensor<32x16x8xf32> into memref +// CHECK: %[[VAL_9:.*]] = linalg.sparse_indices %[[VAL_0]], %[[VAL_5]] : tensor<32x16x8xf32> into memref +// CHECK: %[[VAL_10:.*]] = linalg.sparse_values %[[VAL_0]] : tensor<32x16x8xf32> into memref +// CHECK: %[[VAL_11:.*]] = tensor_to_memref %[[VAL_1]] : memref<32x16x8xf32> +// CHECK: %[[VAL_12:.*]] = tensor_to_memref %[[VAL_2]] : memref<32x16x8xf32> +// CHECK: %[[VAL_13:.*]] = alloc() : memref<32x16x8xf32> +// CHECK: linalg.copy(%[[VAL_12]], %[[VAL_13]]) : memref<32x16x8xf32>, memref<32x16x8xf32> +// CHECK: %[[VAL_14:.*]] = load %[[VAL_6]]{{\[}}%[[VAL_4]]] : memref +// CHECK: %[[VAL_15:.*]] = load %[[VAL_6]]{{\[}}%[[VAL_5]]] : memref +// CHECK: scf.for %[[VAL_16:.*]] = %[[VAL_14]] to %[[VAL_15]] step %[[VAL_5]] { +// CHECK: %[[VAL_17:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_16]]] : memref +// CHECK: %[[VAL_18:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_16]]] : memref +// CHECK: %[[VAL_19:.*]] = addi %[[VAL_16]], %[[VAL_5]] : index +// CHECK: %[[VAL_20:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_19]]] : memref +// CHECK: scf.for %[[VAL_21:.*]] = %[[VAL_18]] to %[[VAL_20]] step %[[VAL_5]] { +// CHECK: %[[VAL_22:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_21]]] : memref +// CHECK: scf.for %[[VAL_23:.*]] = %[[VAL_4]] to %[[VAL_3]] step %[[VAL_5]] { +// CHECK: %[[VAL_24:.*]] = muli %[[VAL_21]], %[[VAL_3]] : index // CHECK: %[[VAL_25:.*]] = addi %[[VAL_24]], %[[VAL_23]] : index -// CHECK: %[[VAL_26:.*]] = load %[[VAL_11]]{{\[}}%[[VAL_25]]] : memref -// CHECK: %[[VAL_27:.*]] = load %[[VAL_12]]{{\[}}%[[VAL_17]], %[[VAL_22]], %[[VAL_23]]] : memref<32x16x8xf32> +// CHECK: %[[VAL_26:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_25]]] : memref +// CHECK: %[[VAL_27:.*]] = load %[[VAL_11]]{{\[}}%[[VAL_17]], %[[VAL_22]], %[[VAL_23]]] : memref<32x16x8xf32> // CHECK: %[[VAL_28:.*]] = mulf %[[VAL_26]], %[[VAL_27]] : f32 // CHECK: store %[[VAL_28]], %[[VAL_13]]{{\[}}%[[VAL_17]], %[[VAL_22]], %[[VAL_23]]] : memref<32x16x8xf32> // CHECK: } @@ -998,123 +1020,125 @@ // CHECK-SAME: %[[VAL_0:.*0]]: tensor<32x16x8xf32>, // CHECK-SAME: %[[VAL_1:.*1]]: tensor<32x16x8xf32>, // CHECK-SAME: %[[VAL_2:.*2]]: tensor<32x16x8xf32>) -> tensor<32x16x8xf32> { -// CHECK: %[[VAL_3:.*]] = constant 999 : index +// CHECK: %[[VAL_3:.*]] = constant 2 : index // CHECK: %[[VAL_4:.*]] = constant 32 : index // CHECK: %[[VAL_5:.*]] = constant 16 : index // CHECK: %[[VAL_6:.*]] = constant 8 : index // CHECK: %[[VAL_7:.*]] = constant true // CHECK: %[[VAL_8:.*]] = constant 0 : index // CHECK: %[[VAL_9:.*]] = constant 1 : index -// CHECK: %[[VAL_10:.*]] = alloca(%[[VAL_3]]) : memref -// CHECK: %[[VAL_11:.*]] = alloca(%[[VAL_3]]) : memref -// CHECK: %[[VAL_12:.*]] = alloca(%[[VAL_3]]) : memref -// CHECK: %[[VAL_13:.*]] = alloca(%[[VAL_3]]) : memref -// CHECK: %[[VAL_14:.*]] = alloca(%[[VAL_3]]) : memref -// CHECK: %[[VAL_15:.*]] = alloca(%[[VAL_3]]) : memref -// CHECK: %[[VAL_16:.*]] = alloca(%[[VAL_3]]) : memref -// CHECK: %[[VAL_17:.*]] = alloca() : memref<32x16x8xf32> -// CHECK: %[[VAL_18:.*]] = alloca() : memref<32x16x8xf32> -// CHECK: %[[VAL_19:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_8]]] : memref -// CHECK: %[[VAL_20:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_9]]] : memref -// CHECK: %[[VAL_21:.*]]:2 = scf.while (%[[VAL_22:.*]] = %[[VAL_19]], %[[VAL_23:.*]] = %[[VAL_8]]) : (index, index) -> (index, index) { -// CHECK: %[[VAL_24:.*]] = cmpi ult, %[[VAL_22]], %[[VAL_20]] : index -// CHECK: scf.condition(%[[VAL_24]]) %[[VAL_22]], %[[VAL_23]] : index, index +// CHECK: %[[VAL_10:.*]] = linalg.sparse_pointers %[[VAL_0]], %[[VAL_8]] : tensor<32x16x8xf32> into memref +// CHECK: %[[VAL_11:.*]] = linalg.sparse_indices %[[VAL_0]], %[[VAL_8]] : tensor<32x16x8xf32> into memref +// CHECK: %[[VAL_12:.*]] = linalg.sparse_pointers %[[VAL_0]], %[[VAL_9]] : tensor<32x16x8xf32> into memref +// CHECK: %[[VAL_13:.*]] = linalg.sparse_indices %[[VAL_0]], %[[VAL_9]] : tensor<32x16x8xf32> into memref +// CHECK: %[[VAL_14:.*]] = linalg.sparse_pointers %[[VAL_0]], %[[VAL_3]] : tensor<32x16x8xf32> into memref +// CHECK: %[[VAL_15:.*]] = linalg.sparse_indices %[[VAL_0]], %[[VAL_3]] : tensor<32x16x8xf32> into memref +// CHECK: %[[VAL_16:.*]] = linalg.sparse_values %[[VAL_0]] : tensor<32x16x8xf32> into memref +// CHECK: %[[VAL_17:.*]] = tensor_to_memref %[[VAL_1]] : memref<32x16x8xf32> +// CHECK: %[[VAL_18:.*]] = tensor_to_memref %[[VAL_2]] : memref<32x16x8xf32> +// CHECK: %[[VAL_19:.*]] = alloc() : memref<32x16x8xf32> +// CHECK: linalg.copy(%[[VAL_18]], %[[VAL_19]]) : memref<32x16x8xf32>, memref<32x16x8xf32> +// CHECK: %[[VAL_20:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_8]]] : memref +// CHECK: %[[VAL_21:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_9]]] : memref +// CHECK: %[[VAL_22:.*]]:2 = scf.while (%[[VAL_23:.*]] = %[[VAL_20]], %[[VAL_24:.*]] = %[[VAL_8]]) : (index, index) -> (index, index) { +// CHECK: %[[VAL_25:.*]] = cmpi ult, %[[VAL_23]], %[[VAL_21]] : index +// CHECK: scf.condition(%[[VAL_25]]) %[[VAL_23]], %[[VAL_24]] : index, index // CHECK: } do { -// CHECK: ^bb0(%[[VAL_25:.*]]: index, %[[VAL_26:.*]]: index): -// CHECK: %[[VAL_27:.*]] = load %[[VAL_11]]{{\[}}%[[VAL_25]]] : memref -// CHECK: %[[VAL_28:.*]] = cmpi eq, %[[VAL_27]], %[[VAL_26]] : index -// CHECK: scf.if %[[VAL_28]] { -// CHECK: %[[VAL_29:.*]] = load %[[VAL_12]]{{\[}}%[[VAL_25]]] : memref -// CHECK: %[[VAL_30:.*]] = addi %[[VAL_25]], %[[VAL_9]] : index -// CHECK: %[[VAL_31:.*]] = load %[[VAL_12]]{{\[}}%[[VAL_30]]] : memref -// CHECK: %[[VAL_32:.*]]:2 = scf.while (%[[VAL_33:.*]] = %[[VAL_29]], %[[VAL_34:.*]] = %[[VAL_8]]) : (index, index) -> (index, index) { -// CHECK: %[[VAL_35:.*]] = cmpi ult, %[[VAL_33]], %[[VAL_31]] : index -// CHECK: scf.condition(%[[VAL_35]]) %[[VAL_33]], %[[VAL_34]] : index, index +// CHECK: ^bb0(%[[VAL_26:.*]]: index, %[[VAL_27:.*]]: index): +// CHECK: %[[VAL_28:.*]] = load %[[VAL_11]]{{\[}}%[[VAL_26]]] : memref +// CHECK: %[[VAL_29:.*]] = cmpi eq, %[[VAL_28]], %[[VAL_27]] : index +// CHECK: scf.if %[[VAL_29]] { +// CHECK: %[[VAL_30:.*]] = load %[[VAL_12]]{{\[}}%[[VAL_26]]] : memref +// CHECK: %[[VAL_31:.*]] = addi %[[VAL_26]], %[[VAL_9]] : index +// CHECK: %[[VAL_32:.*]] = load %[[VAL_12]]{{\[}}%[[VAL_31]]] : memref +// CHECK: %[[VAL_33:.*]]:2 = scf.while (%[[VAL_34:.*]] = %[[VAL_30]], %[[VAL_35:.*]] = %[[VAL_8]]) : (index, index) -> (index, index) { +// CHECK: %[[VAL_36:.*]] = cmpi ult, %[[VAL_34]], %[[VAL_32]] : index +// CHECK: scf.condition(%[[VAL_36]]) %[[VAL_34]], %[[VAL_35]] : index, index // CHECK: } do { -// CHECK: ^bb0(%[[VAL_36:.*]]: index, %[[VAL_37:.*]]: index): -// CHECK: %[[VAL_38:.*]] = load %[[VAL_13]]{{\[}}%[[VAL_36]]] : memref -// CHECK: %[[VAL_39:.*]] = cmpi eq, %[[VAL_38]], %[[VAL_37]] : index -// CHECK: scf.if %[[VAL_39]] { -// CHECK: %[[VAL_40:.*]] = load %[[VAL_14]]{{\[}}%[[VAL_36]]] : memref -// CHECK: %[[VAL_41:.*]] = addi %[[VAL_36]], %[[VAL_9]] : index -// CHECK: %[[VAL_42:.*]] = load %[[VAL_14]]{{\[}}%[[VAL_41]]] : memref -// CHECK: %[[VAL_43:.*]]:2 = scf.while (%[[VAL_44:.*]] = %[[VAL_40]], %[[VAL_45:.*]] = %[[VAL_8]]) : (index, index) -> (index, index) { -// CHECK: %[[VAL_46:.*]] = cmpi ult, %[[VAL_44]], %[[VAL_42]] : index -// CHECK: scf.condition(%[[VAL_46]]) %[[VAL_44]], %[[VAL_45]] : index, index +// CHECK: ^bb0(%[[VAL_37:.*]]: index, %[[VAL_38:.*]]: index): +// CHECK: %[[VAL_39:.*]] = load %[[VAL_13]]{{\[}}%[[VAL_37]]] : memref +// CHECK: %[[VAL_40:.*]] = cmpi eq, %[[VAL_39]], %[[VAL_38]] : index +// CHECK: scf.if %[[VAL_40]] { +// CHECK: %[[VAL_41:.*]] = load %[[VAL_14]]{{\[}}%[[VAL_37]]] : memref +// CHECK: %[[VAL_42:.*]] = addi %[[VAL_37]], %[[VAL_9]] : index +// CHECK: %[[VAL_43:.*]] = load %[[VAL_14]]{{\[}}%[[VAL_42]]] : memref +// CHECK: %[[VAL_44:.*]]:2 = scf.while (%[[VAL_45:.*]] = %[[VAL_41]], %[[VAL_46:.*]] = %[[VAL_8]]) : (index, index) -> (index, index) { +// CHECK: %[[VAL_47:.*]] = cmpi ult, %[[VAL_45]], %[[VAL_43]] : index +// CHECK: scf.condition(%[[VAL_47]]) %[[VAL_45]], %[[VAL_46]] : index, index // CHECK: } do { -// CHECK: ^bb0(%[[VAL_47:.*]]: index, %[[VAL_48:.*]]: index): -// CHECK: %[[VAL_49:.*]] = load %[[VAL_15]]{{\[}}%[[VAL_47]]] : memref -// CHECK: %[[VAL_50:.*]] = cmpi eq, %[[VAL_49]], %[[VAL_48]] : index -// CHECK: scf.if %[[VAL_50]] { -// CHECK: %[[VAL_51:.*]] = load %[[VAL_16]]{{\[}}%[[VAL_47]]] : memref -// CHECK: %[[VAL_52:.*]] = load %[[VAL_17]]{{\[}}%[[VAL_26]], %[[VAL_37]], %[[VAL_48]]] : memref<32x16x8xf32> -// CHECK: %[[VAL_53:.*]] = addf %[[VAL_51]], %[[VAL_52]] : f32 -// CHECK: store %[[VAL_53]], %[[VAL_18]]{{\[}}%[[VAL_26]], %[[VAL_37]], %[[VAL_48]]] : memref<32x16x8xf32> +// CHECK: ^bb0(%[[VAL_48:.*]]: index, %[[VAL_49:.*]]: index): +// CHECK: %[[VAL_50:.*]] = load %[[VAL_15]]{{\[}}%[[VAL_48]]] : memref +// CHECK: %[[VAL_51:.*]] = cmpi eq, %[[VAL_50]], %[[VAL_49]] : index +// CHECK: scf.if %[[VAL_51]] { +// CHECK: %[[VAL_52:.*]] = load %[[VAL_16]]{{\[}}%[[VAL_48]]] : memref +// CHECK: %[[VAL_53:.*]] = load %[[VAL_17]]{{\[}}%[[VAL_27]], %[[VAL_38]], %[[VAL_49]]] : memref<32x16x8xf32> +// CHECK: %[[VAL_54:.*]] = addf %[[VAL_52]], %[[VAL_53]] : f32 +// CHECK: store %[[VAL_54]], %[[VAL_19]]{{\[}}%[[VAL_27]], %[[VAL_38]], %[[VAL_49]]] : memref<32x16x8xf32> // CHECK: } else { // CHECK: scf.if %[[VAL_7]] { -// CHECK: %[[VAL_54:.*]] = load %[[VAL_17]]{{\[}}%[[VAL_26]], %[[VAL_37]], %[[VAL_48]]] : memref<32x16x8xf32> -// CHECK: store %[[VAL_54]], %[[VAL_18]]{{\[}}%[[VAL_26]], %[[VAL_37]], %[[VAL_48]]] : memref<32x16x8xf32> +// CHECK: %[[VAL_55:.*]] = load %[[VAL_17]]{{\[}}%[[VAL_27]], %[[VAL_38]], %[[VAL_49]]] : memref<32x16x8xf32> +// CHECK: store %[[VAL_55]], %[[VAL_19]]{{\[}}%[[VAL_27]], %[[VAL_38]], %[[VAL_49]]] : memref<32x16x8xf32> // CHECK: } else { // CHECK: } // CHECK: } -// CHECK: %[[VAL_55:.*]] = cmpi eq, %[[VAL_49]], %[[VAL_48]] : index -// CHECK: %[[VAL_56:.*]] = addi %[[VAL_47]], %[[VAL_9]] : index -// CHECK: %[[VAL_57:.*]] = select %[[VAL_55]], %[[VAL_56]], %[[VAL_47]] : index -// CHECK: %[[VAL_58:.*]] = addi %[[VAL_48]], %[[VAL_9]] : index -// CHECK: scf.yield %[[VAL_57]], %[[VAL_58]] : index, index +// CHECK: %[[VAL_56:.*]] = cmpi eq, %[[VAL_50]], %[[VAL_49]] : index +// CHECK: %[[VAL_57:.*]] = addi %[[VAL_48]], %[[VAL_9]] : index +// CHECK: %[[VAL_58:.*]] = select %[[VAL_56]], %[[VAL_57]], %[[VAL_48]] : index +// CHECK: %[[VAL_59:.*]] = addi %[[VAL_49]], %[[VAL_9]] : index +// CHECK: scf.yield %[[VAL_58]], %[[VAL_59]] : index, index // CHECK: } -// CHECK: scf.for %[[VAL_59:.*]] = %[[VAL_60:.*]]#1 to %[[VAL_6]] step %[[VAL_9]] { -// CHECK: %[[VAL_61:.*]] = load %[[VAL_17]]{{\[}}%[[VAL_26]], %[[VAL_37]], %[[VAL_59]]] : memref<32x16x8xf32> -// CHECK: store %[[VAL_61]], %[[VAL_18]]{{\[}}%[[VAL_26]], %[[VAL_37]], %[[VAL_59]]] : memref<32x16x8xf32> +// CHECK: scf.for %[[VAL_60:.*]] = %[[VAL_61:.*]]#1 to %[[VAL_6]] step %[[VAL_9]] { +// CHECK: %[[VAL_62:.*]] = load %[[VAL_17]]{{\[}}%[[VAL_27]], %[[VAL_38]], %[[VAL_60]]] : memref<32x16x8xf32> +// CHECK: store %[[VAL_62]], %[[VAL_19]]{{\[}}%[[VAL_27]], %[[VAL_38]], %[[VAL_60]]] : memref<32x16x8xf32> // CHECK: } // CHECK: } else { // CHECK: scf.if %[[VAL_7]] { -// CHECK: scf.for %[[VAL_62:.*]] = %[[VAL_8]] to %[[VAL_6]] step %[[VAL_9]] { -// CHECK: %[[VAL_63:.*]] = load %[[VAL_17]]{{\[}}%[[VAL_26]], %[[VAL_37]], %[[VAL_62]]] : memref<32x16x8xf32> -// CHECK: store %[[VAL_63]], %[[VAL_18]]{{\[}}%[[VAL_26]], %[[VAL_37]], %[[VAL_62]]] : memref<32x16x8xf32> +// CHECK: scf.for %[[VAL_63:.*]] = %[[VAL_8]] to %[[VAL_6]] step %[[VAL_9]] { +// CHECK: %[[VAL_64:.*]] = load %[[VAL_17]]{{\[}}%[[VAL_27]], %[[VAL_38]], %[[VAL_63]]] : memref<32x16x8xf32> +// CHECK: store %[[VAL_64]], %[[VAL_19]]{{\[}}%[[VAL_27]], %[[VAL_38]], %[[VAL_63]]] : memref<32x16x8xf32> // CHECK: } // CHECK: } else { // CHECK: } // CHECK: } -// CHECK: %[[VAL_64:.*]] = cmpi eq, %[[VAL_38]], %[[VAL_37]] : index -// CHECK: %[[VAL_65:.*]] = addi %[[VAL_36]], %[[VAL_9]] : index -// CHECK: %[[VAL_66:.*]] = select %[[VAL_64]], %[[VAL_65]], %[[VAL_36]] : index -// CHECK: %[[VAL_67:.*]] = addi %[[VAL_37]], %[[VAL_9]] : index -// CHECK: scf.yield %[[VAL_66]], %[[VAL_67]] : index, index +// CHECK: %[[VAL_65:.*]] = cmpi eq, %[[VAL_39]], %[[VAL_38]] : index +// CHECK: %[[VAL_66:.*]] = addi %[[VAL_37]], %[[VAL_9]] : index +// CHECK: %[[VAL_67:.*]] = select %[[VAL_65]], %[[VAL_66]], %[[VAL_37]] : index +// CHECK: %[[VAL_68:.*]] = addi %[[VAL_38]], %[[VAL_9]] : index +// CHECK: scf.yield %[[VAL_67]], %[[VAL_68]] : index, index // CHECK: } -// CHECK: scf.for %[[VAL_68:.*]] = %[[VAL_69:.*]]#1 to %[[VAL_5]] step %[[VAL_9]] { -// CHECK: scf.for %[[VAL_70:.*]] = %[[VAL_8]] to %[[VAL_6]] step %[[VAL_9]] { -// CHECK: %[[VAL_71:.*]] = load %[[VAL_17]]{{\[}}%[[VAL_26]], %[[VAL_68]], %[[VAL_70]]] : memref<32x16x8xf32> -// CHECK: store %[[VAL_71]], %[[VAL_18]]{{\[}}%[[VAL_26]], %[[VAL_68]], %[[VAL_70]]] : memref<32x16x8xf32> +// CHECK: scf.for %[[VAL_69:.*]] = %[[VAL_70:.*]]#1 to %[[VAL_5]] step %[[VAL_9]] { +// CHECK: scf.for %[[VAL_71:.*]] = %[[VAL_8]] to %[[VAL_6]] step %[[VAL_9]] { +// CHECK: %[[VAL_72:.*]] = load %[[VAL_17]]{{\[}}%[[VAL_27]], %[[VAL_69]], %[[VAL_71]]] : memref<32x16x8xf32> +// CHECK: store %[[VAL_72]], %[[VAL_19]]{{\[}}%[[VAL_27]], %[[VAL_69]], %[[VAL_71]]] : memref<32x16x8xf32> // CHECK: } // CHECK: } // CHECK: } else { // CHECK: scf.if %[[VAL_7]] { -// CHECK: scf.for %[[VAL_72:.*]] = %[[VAL_8]] to %[[VAL_5]] step %[[VAL_9]] { -// CHECK: scf.for %[[VAL_73:.*]] = %[[VAL_8]] to %[[VAL_6]] step %[[VAL_9]] { -// CHECK: %[[VAL_74:.*]] = load %[[VAL_17]]{{\[}}%[[VAL_26]], %[[VAL_72]], %[[VAL_73]]] : memref<32x16x8xf32> -// CHECK: store %[[VAL_74]], %[[VAL_18]]{{\[}}%[[VAL_26]], %[[VAL_72]], %[[VAL_73]]] : memref<32x16x8xf32> +// CHECK: scf.for %[[VAL_73:.*]] = %[[VAL_8]] to %[[VAL_5]] step %[[VAL_9]] { +// CHECK: scf.for %[[VAL_74:.*]] = %[[VAL_8]] to %[[VAL_6]] step %[[VAL_9]] { +// CHECK: %[[VAL_75:.*]] = load %[[VAL_17]]{{\[}}%[[VAL_27]], %[[VAL_73]], %[[VAL_74]]] : memref<32x16x8xf32> +// CHECK: store %[[VAL_75]], %[[VAL_19]]{{\[}}%[[VAL_27]], %[[VAL_73]], %[[VAL_74]]] : memref<32x16x8xf32> // CHECK: } // CHECK: } // CHECK: } else { // CHECK: } // CHECK: } -// CHECK: %[[VAL_75:.*]] = cmpi eq, %[[VAL_27]], %[[VAL_26]] : index -// CHECK: %[[VAL_76:.*]] = addi %[[VAL_25]], %[[VAL_9]] : index -// CHECK: %[[VAL_77:.*]] = select %[[VAL_75]], %[[VAL_76]], %[[VAL_25]] : index -// CHECK: %[[VAL_78:.*]] = addi %[[VAL_26]], %[[VAL_9]] : index -// CHECK: scf.yield %[[VAL_77]], %[[VAL_78]] : index, index +// CHECK: %[[VAL_76:.*]] = cmpi eq, %[[VAL_28]], %[[VAL_27]] : index +// CHECK: %[[VAL_77:.*]] = addi %[[VAL_26]], %[[VAL_9]] : index +// CHECK: %[[VAL_78:.*]] = select %[[VAL_76]], %[[VAL_77]], %[[VAL_26]] : index +// CHECK: %[[VAL_79:.*]] = addi %[[VAL_27]], %[[VAL_9]] : index +// CHECK: scf.yield %[[VAL_78]], %[[VAL_79]] : index, index // CHECK: } -// CHECK: scf.for %[[VAL_79:.*]] = %[[VAL_80:.*]]#1 to %[[VAL_4]] step %[[VAL_9]] { -// CHECK: scf.for %[[VAL_81:.*]] = %[[VAL_8]] to %[[VAL_5]] step %[[VAL_9]] { -// CHECK: scf.for %[[VAL_82:.*]] = %[[VAL_8]] to %[[VAL_6]] step %[[VAL_9]] { -// CHECK: %[[VAL_83:.*]] = load %[[VAL_17]]{{\[}}%[[VAL_79]], %[[VAL_81]], %[[VAL_82]]] : memref<32x16x8xf32> -// CHECK: store %[[VAL_83]], %[[VAL_18]]{{\[}}%[[VAL_79]], %[[VAL_81]], %[[VAL_82]]] : memref<32x16x8xf32> +// CHECK: scf.for %[[VAL_80:.*]] = %[[VAL_81:.*]]#1 to %[[VAL_4]] step %[[VAL_9]] { +// CHECK: scf.for %[[VAL_82:.*]] = %[[VAL_8]] to %[[VAL_5]] step %[[VAL_9]] { +// CHECK: scf.for %[[VAL_83:.*]] = %[[VAL_8]] to %[[VAL_6]] step %[[VAL_9]] { +// CHECK: %[[VAL_84:.*]] = load %[[VAL_17]]{{\[}}%[[VAL_80]], %[[VAL_82]], %[[VAL_83]]] : memref<32x16x8xf32> +// CHECK: store %[[VAL_84]], %[[VAL_19]]{{\[}}%[[VAL_80]], %[[VAL_82]], %[[VAL_83]]] : memref<32x16x8xf32> // CHECK: } // CHECK: } // CHECK: } -// CHECK: %[[VAL_84:.*]] = tensor_load %[[VAL_18]] : memref<32x16x8xf32> -// CHECK: return %[[VAL_84]] : tensor<32x16x8xf32> +// CHECK: %[[VAL_85:.*]] = tensor_load %[[VAL_19]] : memref<32x16x8xf32> +// CHECK: return %[[VAL_85]] : tensor<32x16x8xf32> // CHECK: } func @add_sss(%arga: tensor<32x16x8xf32>, %argb: tensor<32x16x8xf32>, %argx: tensor<32x16x8xf32>) -> tensor<32x16x8xf32> { %0 = linalg.generic #trait_sss @@ -1131,41 +1155,43 @@ // CHECK-SAME: %[[VAL_0:.*0]]: tensor<32x16x8xf32>, // CHECK-SAME: %[[VAL_1:.*1]]: tensor<32x16x8xf32>, // CHECK-SAME: %[[VAL_2:.*2]]: tensor<32x16x8xf32>) -> tensor<32x16x8xf32> { -// CHECK: %[[VAL_3:.*]] = constant 999 : index +// CHECK: %[[VAL_3:.*]] = constant 2 : index // CHECK: %[[VAL_4:.*]] = constant 0 : index // CHECK: %[[VAL_5:.*]] = constant 1 : index -// CHECK: %[[VAL_6:.*]] = alloca(%[[VAL_3]]) : memref -// CHECK: %[[VAL_7:.*]] = alloca(%[[VAL_3]]) : memref -// CHECK: %[[VAL_8:.*]] = alloca(%[[VAL_3]]) : memref -// CHECK: %[[VAL_9:.*]] = alloca(%[[VAL_3]]) : memref -// CHECK: %[[VAL_10:.*]] = alloca(%[[VAL_3]]) : memref -// CHECK: %[[VAL_11:.*]] = alloca(%[[VAL_3]]) : memref -// CHECK: %[[VAL_12:.*]] = alloca(%[[VAL_3]]) : memref -// CHECK: %[[VAL_13:.*]] = alloca() : memref<32x16x8xf32> -// CHECK: %[[VAL_14:.*]] = alloca() : memref<32x16x8xf32> -// CHECK: %[[VAL_15:.*]] = load %[[VAL_6]]{{\[}}%[[VAL_4]]] : memref -// CHECK: %[[VAL_16:.*]] = load %[[VAL_6]]{{\[}}%[[VAL_5]]] : memref -// CHECK: scf.for %[[VAL_17:.*]] = %[[VAL_15]] to %[[VAL_16]] step %[[VAL_5]] { -// CHECK: %[[VAL_18:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_17]]] : memref -// CHECK: %[[VAL_19:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_17]]] : memref -// CHECK: %[[VAL_20:.*]] = addi %[[VAL_17]], %[[VAL_5]] : index -// CHECK: %[[VAL_21:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_20]]] : memref -// CHECK: scf.for %[[VAL_22:.*]] = %[[VAL_19]] to %[[VAL_21]] step %[[VAL_5]] { -// CHECK: %[[VAL_23:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_22]]] : memref -// CHECK: %[[VAL_24:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_22]]] : memref -// CHECK: %[[VAL_25:.*]] = addi %[[VAL_22]], %[[VAL_5]] : index -// CHECK: %[[VAL_26:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_25]]] : memref -// CHECK: scf.for %[[VAL_27:.*]] = %[[VAL_24]] to %[[VAL_26]] step %[[VAL_5]] { -// CHECK: %[[VAL_28:.*]] = load %[[VAL_11]]{{\[}}%[[VAL_27]]] : memref -// CHECK: %[[VAL_29:.*]] = load %[[VAL_12]]{{\[}}%[[VAL_27]]] : memref -// CHECK: %[[VAL_30:.*]] = load %[[VAL_13]]{{\[}}%[[VAL_18]], %[[VAL_23]], %[[VAL_28]]] : memref<32x16x8xf32> -// CHECK: %[[VAL_31:.*]] = mulf %[[VAL_29]], %[[VAL_30]] : f32 -// CHECK: store %[[VAL_31]], %[[VAL_14]]{{\[}}%[[VAL_18]], %[[VAL_23]], %[[VAL_28]]] : memref<32x16x8xf32> +// CHECK: %[[VAL_6:.*]] = linalg.sparse_pointers %[[VAL_0]], %[[VAL_4]] : tensor<32x16x8xf32> into memref +// CHECK: %[[VAL_7:.*]] = linalg.sparse_indices %[[VAL_0]], %[[VAL_4]] : tensor<32x16x8xf32> into memref +// CHECK: %[[VAL_8:.*]] = linalg.sparse_pointers %[[VAL_0]], %[[VAL_5]] : tensor<32x16x8xf32> into memref +// CHECK: %[[VAL_9:.*]] = linalg.sparse_indices %[[VAL_0]], %[[VAL_5]] : tensor<32x16x8xf32> into memref +// CHECK: %[[VAL_10:.*]] = linalg.sparse_pointers %[[VAL_0]], %[[VAL_3]] : tensor<32x16x8xf32> into memref +// CHECK: %[[VAL_11:.*]] = linalg.sparse_indices %[[VAL_0]], %[[VAL_3]] : tensor<32x16x8xf32> into memref +// CHECK: %[[VAL_12:.*]] = linalg.sparse_values %[[VAL_0]] : tensor<32x16x8xf32> into memref +// CHECK: %[[VAL_13:.*]] = tensor_to_memref %[[VAL_1]] : memref<32x16x8xf32> +// CHECK: %[[VAL_14:.*]] = tensor_to_memref %[[VAL_2]] : memref<32x16x8xf32> +// CHECK: %[[VAL_15:.*]] = alloc() : memref<32x16x8xf32> +// CHECK: linalg.copy(%[[VAL_14]], %[[VAL_15]]) : memref<32x16x8xf32>, memref<32x16x8xf32> +// CHECK: %[[VAL_16:.*]] = load %[[VAL_6]]{{\[}}%[[VAL_4]]] : memref +// CHECK: %[[VAL_17:.*]] = load %[[VAL_6]]{{\[}}%[[VAL_5]]] : memref +// CHECK: scf.for %[[VAL_18:.*]] = %[[VAL_16]] to %[[VAL_17]] step %[[VAL_5]] { +// CHECK: %[[VAL_19:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_18]]] : memref +// CHECK: %[[VAL_20:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_18]]] : memref +// CHECK: %[[VAL_21:.*]] = addi %[[VAL_18]], %[[VAL_5]] : index +// CHECK: %[[VAL_22:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_21]]] : memref +// CHECK: scf.for %[[VAL_23:.*]] = %[[VAL_20]] to %[[VAL_22]] step %[[VAL_5]] { +// CHECK: %[[VAL_24:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_23]]] : memref +// CHECK: %[[VAL_25:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_23]]] : memref +// CHECK: %[[VAL_26:.*]] = addi %[[VAL_23]], %[[VAL_5]] : index +// CHECK: %[[VAL_27:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_26]]] : memref +// CHECK: scf.for %[[VAL_28:.*]] = %[[VAL_25]] to %[[VAL_27]] step %[[VAL_5]] { +// CHECK: %[[VAL_29:.*]] = load %[[VAL_11]]{{\[}}%[[VAL_28]]] : memref +// CHECK: %[[VAL_30:.*]] = load %[[VAL_12]]{{\[}}%[[VAL_28]]] : memref +// CHECK: %[[VAL_31:.*]] = load %[[VAL_13]]{{\[}}%[[VAL_19]], %[[VAL_24]], %[[VAL_29]]] : memref<32x16x8xf32> +// CHECK: %[[VAL_32:.*]] = mulf %[[VAL_30]], %[[VAL_31]] : f32 +// CHECK: store %[[VAL_32]], %[[VAL_15]]{{\[}}%[[VAL_19]], %[[VAL_24]], %[[VAL_29]]] : memref<32x16x8xf32> // CHECK: } // CHECK: } // CHECK: } -// CHECK: %[[VAL_32:.*]] = tensor_load %[[VAL_14]] : memref<32x16x8xf32> -// CHECK: return %[[VAL_32]] : tensor<32x16x8xf32> +// CHECK: %[[VAL_33:.*]] = tensor_load %[[VAL_15]] : memref<32x16x8xf32> +// CHECK: return %[[VAL_33]] : tensor<32x16x8xf32> // CHECK: } func @mul_sss(%arga: tensor<32x16x8xf32>, %argb: tensor<32x16x8xf32>, %argx: tensor<32x16x8xf32>) -> tensor<32x16x8xf32> { %0 = linalg.generic #trait_sss @@ -1200,45 +1226,44 @@ // CHECK-SAME: %[[VAL_1:.*1]]: tensor, // CHECK-SAME: %[[VAL_2:.*2]]: tensor, // CHECK-SAME: %[[VAL_3:.*3]]: tensor) -> tensor { -// CHECK: %[[VAL_4:.*]] = constant 999 : index +// CHECK: %[[VAL_4:.*]] = constant 2 : index // CHECK: %[[VAL_5:.*]] = constant 0 : index // CHECK: %[[VAL_6:.*]] = constant 1 : index -// CHECK: %[[VAL_7:.*]] = alloca(%[[VAL_4]]) : memref -// CHECK: %[[VAL_8:.*]] = alloca(%[[VAL_4]]) : memref -// CHECK: %[[VAL_9:.*]] = alloca(%[[VAL_4]]) : memref +// CHECK: %[[VAL_7:.*]] = linalg.sparse_pointers %[[VAL_1]], %[[VAL_4]] : tensor into memref +// CHECK: %[[VAL_8:.*]] = linalg.sparse_indices %[[VAL_1]], %[[VAL_4]] : tensor into memref +// CHECK: %[[VAL_9:.*]] = linalg.sparse_values %[[VAL_1]] : tensor into memref // CHECK: %[[VAL_10:.*]] = dim %[[VAL_2]], %[[VAL_5]] : tensor -// CHECK: %[[VAL_11:.*]] = dim %[[VAL_2]], %[[VAL_6]] : tensor -// CHECK: %[[VAL_12:.*]] = alloca(%[[VAL_10]], %[[VAL_11]]) : memref -// CHECK: %[[VAL_13:.*]] = dim %[[VAL_3]], %[[VAL_5]] : tensor -// CHECK: %[[VAL_14:.*]] = dim %[[VAL_3]], %[[VAL_6]] : tensor -// CHECK: %[[VAL_15:.*]] = alloca(%[[VAL_13]], %[[VAL_14]]) : memref -// CHECK: %[[VAL_16:.*]] = dim %[[VAL_0]], %[[VAL_5]] : tensor -// CHECK: %[[VAL_17:.*]] = dim %[[VAL_0]], %[[VAL_6]] : tensor -// CHECK: %[[VAL_18:.*]] = alloca(%[[VAL_16]], %[[VAL_17]]) : memref -// CHECK: scf.for %[[VAL_19:.*]] = %[[VAL_5]] to %[[VAL_16]] step %[[VAL_6]] { -// CHECK: scf.for %[[VAL_20:.*]] = %[[VAL_5]] to %[[VAL_10]] step %[[VAL_6]] { -// CHECK: %[[VAL_21:.*]] = muli %[[VAL_10]], %[[VAL_19]] : index -// CHECK: %[[VAL_22:.*]] = addi %[[VAL_21]], %[[VAL_20]] : index +// CHECK: %[[VAL_11:.*]] = tensor_to_memref %[[VAL_2]] : memref +// CHECK: %[[VAL_12:.*]] = tensor_to_memref %[[VAL_3]] : memref +// CHECK: %[[VAL_13:.*]] = dim %[[VAL_0]], %[[VAL_5]] : tensor +// CHECK: %[[VAL_14:.*]] = dim %[[VAL_0]], %[[VAL_6]] : tensor +// CHECK: %[[VAL_15:.*]] = tensor_to_memref %[[VAL_0]] : memref +// CHECK: %[[VAL_16:.*]] = alloc(%[[VAL_13]], %[[VAL_14]]) : memref +// CHECK: linalg.copy(%[[VAL_15]], %[[VAL_16]]) : memref, memref +// CHECK: scf.for %[[VAL_17:.*]] = %[[VAL_5]] to %[[VAL_13]] step %[[VAL_6]] { +// CHECK: scf.for %[[VAL_18:.*]] = %[[VAL_5]] to %[[VAL_10]] step %[[VAL_6]] { +// CHECK: %[[VAL_19:.*]] = muli %[[VAL_10]], %[[VAL_17]] : index +// CHECK: %[[VAL_20:.*]] = addi %[[VAL_19]], %[[VAL_18]] : index +// CHECK: %[[VAL_21:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_20]]] : memref +// CHECK: %[[VAL_22:.*]] = addi %[[VAL_20]], %[[VAL_6]] : index // CHECK: %[[VAL_23:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_22]]] : memref -// CHECK: %[[VAL_24:.*]] = addi %[[VAL_22]], %[[VAL_6]] : index -// CHECK: %[[VAL_25:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_24]]] : memref -// CHECK: scf.for %[[VAL_26:.*]] = %[[VAL_23]] to %[[VAL_25]] step %[[VAL_6]] { -// CHECK: %[[VAL_27:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_26]]] : memref -// CHECK: %[[VAL_28:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_26]]] : memref -// CHECK: scf.for %[[VAL_29:.*]] = %[[VAL_5]] to %[[VAL_17]] step %[[VAL_6]] { -// CHECK: %[[VAL_30:.*]] = load %[[VAL_12]]{{\[}}%[[VAL_20]], %[[VAL_29]]] : memref -// CHECK: %[[VAL_31:.*]] = mulf %[[VAL_28]], %[[VAL_30]] : f32 -// CHECK: %[[VAL_32:.*]] = load %[[VAL_15]]{{\[}}%[[VAL_27]], %[[VAL_29]]] : memref -// CHECK: %[[VAL_33:.*]] = mulf %[[VAL_31]], %[[VAL_32]] : f32 -// CHECK: %[[VAL_34:.*]] = load %[[VAL_18]]{{\[}}%[[VAL_19]], %[[VAL_29]]] : memref -// CHECK: %[[VAL_35:.*]] = addf %[[VAL_33]], %[[VAL_34]] : f32 -// CHECK: store %[[VAL_35]], %[[VAL_18]]{{\[}}%[[VAL_19]], %[[VAL_29]]] : memref +// CHECK: scf.for %[[VAL_24:.*]] = %[[VAL_21]] to %[[VAL_23]] step %[[VAL_6]] { +// CHECK: %[[VAL_25:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_24]]] : memref +// CHECK: %[[VAL_26:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_24]]] : memref +// CHECK: scf.for %[[VAL_27:.*]] = %[[VAL_5]] to %[[VAL_14]] step %[[VAL_6]] { +// CHECK: %[[VAL_28:.*]] = load %[[VAL_11]]{{\[}}%[[VAL_18]], %[[VAL_27]]] : memref +// CHECK: %[[VAL_29:.*]] = mulf %[[VAL_26]], %[[VAL_28]] : f32 +// CHECK: %[[VAL_30:.*]] = load %[[VAL_12]]{{\[}}%[[VAL_25]], %[[VAL_27]]] : memref +// CHECK: %[[VAL_31:.*]] = mulf %[[VAL_29]], %[[VAL_30]] : f32 +// CHECK: %[[VAL_32:.*]] = load %[[VAL_16]]{{\[}}%[[VAL_17]], %[[VAL_27]]] : memref +// CHECK: %[[VAL_33:.*]] = addf %[[VAL_31]], %[[VAL_32]] : f32 +// CHECK: store %[[VAL_33]], %[[VAL_16]]{{\[}}%[[VAL_17]], %[[VAL_27]]] : memref // CHECK: } // CHECK: } // CHECK: } // CHECK: } -// CHECK: %[[VAL_36:.*]] = tensor_load %[[VAL_18]] : memref -// CHECK: return %[[VAL_36]] : tensor +// CHECK: %[[VAL_34:.*]] = tensor_load %[[VAL_16]] : memref +// CHECK: return %[[VAL_34]] : tensor // CHECK: } func @kernel_3d(%arga: tensor, %argb: tensor, @@ -1272,35 +1297,37 @@ // CHECK-LABEL: func @sum_reduction( // CHECK-SAME: %[[VAL_0:.*]]: tensor<10x20x30xf32>, // CHECK-SAME: %[[VAL_1:.*]]: tensor) -> tensor { -// CHECK: %[[VAL_2:.*]] = constant 999 : index +// CHECK: %[[VAL_2:.*]] = constant 2 : index // CHECK: %[[VAL_3:.*]] = constant 0 : index // CHECK: %[[VAL_4:.*]] = constant 1 : index -// CHECK: %[[VAL_5:.*]] = alloca(%[[VAL_2]]) : memref -// CHECK: %[[VAL_6:.*]] = alloca(%[[VAL_2]]) : memref -// CHECK: %[[VAL_7:.*]] = alloca(%[[VAL_2]]) : memref -// CHECK: %[[VAL_8:.*]] = alloca(%[[VAL_2]]) : memref -// CHECK: %[[VAL_9:.*]] = alloca() : memref -// CHECK: %[[VAL_10:.*]] = load %[[VAL_5]]{{\[}}%[[VAL_3]]] : memref -// CHECK: %[[VAL_11:.*]] = load %[[VAL_5]]{{\[}}%[[VAL_4]]] : memref -// CHECK: scf.for %[[VAL_12:.*]] = %[[VAL_10]] to %[[VAL_11]] step %[[VAL_4]] { -// CHECK: %[[VAL_13:.*]] = load %[[VAL_6]]{{\[}}%[[VAL_12]]] : memref -// CHECK: %[[VAL_14:.*]] = addi %[[VAL_12]], %[[VAL_4]] : index -// CHECK: %[[VAL_15:.*]] = load %[[VAL_6]]{{\[}}%[[VAL_14]]] : memref -// CHECK: scf.for %[[VAL_16:.*]] = %[[VAL_13]] to %[[VAL_15]] step %[[VAL_4]] { -// CHECK: %[[VAL_17:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_16]]] : memref -// CHECK: %[[VAL_18:.*]] = addi %[[VAL_16]], %[[VAL_4]] : index -// CHECK: %[[VAL_19:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_18]]] : memref -// CHECK: %[[VAL_20:.*]] = load %[[VAL_9]][] : memref -// CHECK: %[[VAL_21:.*]] = scf.for %[[VAL_22:.*]] = %[[VAL_17]] to %[[VAL_19]] step %[[VAL_4]] iter_args(%[[VAL_23:.*]] = %[[VAL_20]]) -> (f32) { -// CHECK: %[[VAL_24:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_22]]] : memref -// CHECK: %[[VAL_25:.*]] = addf %[[VAL_23]], %[[VAL_24]] : f32 -// CHECK: scf.yield %[[VAL_25]] : f32 +// CHECK: %[[VAL_5:.*]] = linalg.sparse_pointers %[[VAL_0]], %[[VAL_3]] : tensor<10x20x30xf32> into memref +// CHECK: %[[VAL_6:.*]] = linalg.sparse_pointers %[[VAL_0]], %[[VAL_4]] : tensor<10x20x30xf32> into memref +// CHECK: %[[VAL_7:.*]] = linalg.sparse_pointers %[[VAL_0]], %[[VAL_2]] : tensor<10x20x30xf32> into memref +// CHECK: %[[VAL_8:.*]] = linalg.sparse_values %[[VAL_0]] : tensor<10x20x30xf32> into memref +// CHECK: %[[VAL_9:.*]] = tensor_to_memref %[[VAL_1]] : memref +// CHECK: %[[VAL_10:.*]] = alloc() : memref +// CHECK: linalg.copy(%[[VAL_9]], %[[VAL_10]]) : memref, memref +// CHECK: %[[VAL_11:.*]] = load %[[VAL_5]]{{\[}}%[[VAL_3]]] : memref +// CHECK: %[[VAL_12:.*]] = load %[[VAL_5]]{{\[}}%[[VAL_4]]] : memref +// CHECK: scf.for %[[VAL_13:.*]] = %[[VAL_11]] to %[[VAL_12]] step %[[VAL_4]] { +// CHECK: %[[VAL_14:.*]] = load %[[VAL_6]]{{\[}}%[[VAL_13]]] : memref +// CHECK: %[[VAL_15:.*]] = addi %[[VAL_13]], %[[VAL_4]] : index +// CHECK: %[[VAL_16:.*]] = load %[[VAL_6]]{{\[}}%[[VAL_15]]] : memref +// CHECK: scf.for %[[VAL_17:.*]] = %[[VAL_14]] to %[[VAL_16]] step %[[VAL_4]] { +// CHECK: %[[VAL_18:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_17]]] : memref +// CHECK: %[[VAL_19:.*]] = addi %[[VAL_17]], %[[VAL_4]] : index +// CHECK: %[[VAL_20:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_19]]] : memref +// CHECK: %[[VAL_21:.*]] = load %[[VAL_10]][] : memref +// CHECK: %[[VAL_22:.*]] = scf.for %[[VAL_23:.*]] = %[[VAL_18]] to %[[VAL_20]] step %[[VAL_4]] iter_args(%[[VAL_24:.*]] = %[[VAL_21]]) -> (f32) { +// CHECK: %[[VAL_25:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_23]]] : memref +// CHECK: %[[VAL_26:.*]] = addf %[[VAL_24]], %[[VAL_25]] : f32 +// CHECK: scf.yield %[[VAL_26]] : f32 // CHECK: } -// CHECK: store %[[VAL_26:.*]], %[[VAL_9]][] : memref +// CHECK: store %[[VAL_27:.*]], %[[VAL_10]][] : memref // CHECK: } // CHECK: } -// CHECK: %[[VAL_27:.*]] = tensor_load %[[VAL_9]] : memref -// CHECK: return %[[VAL_27]] : tensor +// CHECK: %[[VAL_28:.*]] = tensor_load %[[VAL_10]] : memref +// CHECK: return %[[VAL_28]] : tensor // CHECK: } func @sum_reduction(%arga: tensor<10x20x30xf32>, %argx: tensor) -> tensor { %0 = linalg.generic #trait_sum_reduction @@ -1335,19 +1362,20 @@ // CHECK: %[[VAL_3:.*]] = constant 2 : index // CHECK: %[[VAL_4:.*]] = constant 0 : index // CHECK: %[[VAL_5:.*]] = constant 1 : index -// CHECK: %[[VAL_6:.*]] = dim %[[VAL_0]], %[[VAL_4]] : tensor -// CHECK: %[[VAL_7:.*]] = dim %[[VAL_0]], %[[VAL_5]] : tensor -// CHECK: %[[VAL_8:.*]] = dim %[[VAL_0]], %[[VAL_3]] : tensor -// CHECK: %[[VAL_9:.*]] = alloca(%[[VAL_6]], %[[VAL_7]], %[[VAL_8]]) : memref -// CHECK: %[[VAL_10:.*]] = dim %[[VAL_1]], %[[VAL_4]] : tensor -// CHECK: %[[VAL_11:.*]] = alloca(%[[VAL_10]]) : memref -// CHECK: %[[VAL_12:.*]] = alloca() : memref -// CHECK: scf.for %[[VAL_13:.*]] = %[[VAL_4]] to %[[VAL_10]] step %[[VAL_5]] { -// CHECK: %[[VAL_14:.*]] = load %[[VAL_11]]{{\[}}%[[VAL_13]]] : memref -// CHECK: scf.for %[[VAL_15:.*]] = %[[VAL_4]] to %[[VAL_7]] step %[[VAL_5]] { +// CHECK: %[[VAL_6:.*]] = dim %[[VAL_0]], %[[VAL_5]] : tensor +// CHECK: %[[VAL_7:.*]] = dim %[[VAL_0]], %[[VAL_3]] : tensor +// CHECK: %[[VAL_8:.*]] = tensor_to_memref %[[VAL_0]] : memref +// CHECK: %[[VAL_9:.*]] = dim %[[VAL_1]], %[[VAL_4]] : tensor +// CHECK: %[[VAL_10:.*]] = tensor_to_memref %[[VAL_1]] : memref +// CHECK: %[[VAL_11:.*]] = tensor_to_memref %[[VAL_2]] : memref +// CHECK: %[[VAL_12:.*]] = alloc() : memref +// CHECK: linalg.copy(%[[VAL_11]], %[[VAL_12]]) : memref, memref +// CHECK: scf.for %[[VAL_13:.*]] = %[[VAL_4]] to %[[VAL_9]] step %[[VAL_5]] { +// CHECK: %[[VAL_14:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_13]]] : memref +// CHECK: scf.for %[[VAL_15:.*]] = %[[VAL_4]] to %[[VAL_6]] step %[[VAL_5]] { // CHECK: %[[VAL_16:.*]] = load %[[VAL_12]][] : memref -// CHECK: %[[VAL_17:.*]] = scf.for %[[VAL_18:.*]] = %[[VAL_4]] to %[[VAL_8]] step %[[VAL_5]] iter_args(%[[VAL_19:.*]] = %[[VAL_16]]) -> (f32) { -// CHECK: %[[VAL_20:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_13]], %[[VAL_15]], %[[VAL_18]]] : memref +// CHECK: %[[VAL_17:.*]] = scf.for %[[VAL_18:.*]] = %[[VAL_4]] to %[[VAL_7]] step %[[VAL_5]] iter_args(%[[VAL_19:.*]] = %[[VAL_16]]) -> (f32) { +// CHECK: %[[VAL_20:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_13]], %[[VAL_15]], %[[VAL_18]]] : memref // CHECK: %[[VAL_21:.*]] = mulf %[[VAL_20]], %[[VAL_14]] : f32 // CHECK: %[[VAL_22:.*]] = addf %[[VAL_19]], %[[VAL_21]] : f32 // CHECK: scf.yield %[[VAL_22]] : f32 @@ -1399,24 +1427,26 @@ // CHECK: %[[VAL_6:.*]] = constant 30 : index // CHECK: %[[VAL_7:.*]] = constant 0 : index // CHECK: %[[VAL_8:.*]] = constant 1 : index -// CHECK: %[[VAL_9:.*]] = alloca() : memref<10xf32> -// CHECK: %[[VAL_10:.*]] = alloca() : memref<20xf32> -// CHECK: %[[VAL_11:.*]] = alloca() : memref<30xf32> -// CHECK: %[[VAL_12:.*]] = alloca() : memref<10x20x30xf32> -// CHECK: scf.for %[[VAL_13:.*]] = %[[VAL_7]] to %[[VAL_4]] step %[[VAL_8]] { -// CHECK: %[[VAL_14:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_13]]] : memref<10xf32> -// CHECK: scf.for %[[VAL_15:.*]] = %[[VAL_7]] to %[[VAL_5]] step %[[VAL_8]] { -// CHECK: %[[VAL_16:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_15]]] : memref<20xf32> -// CHECK: scf.for %[[VAL_17:.*]] = %[[VAL_7]] to %[[VAL_6]] step %[[VAL_8]] { -// CHECK: %[[VAL_18:.*]] = mulf %[[VAL_14]], %[[VAL_16]] : f32 -// CHECK: %[[VAL_19:.*]] = load %[[VAL_11]]{{\[}}%[[VAL_17]]] : memref<30xf32> -// CHECK: %[[VAL_20:.*]] = mulf %[[VAL_18]], %[[VAL_19]] : f32 -// CHECK: store %[[VAL_20]], %[[VAL_12]]{{\[}}%[[VAL_13]], %[[VAL_15]], %[[VAL_17]]] : memref<10x20x30xf32> +// CHECK: %[[VAL_9:.*]] = tensor_to_memref %[[VAL_0]] : memref<10xf32> +// CHECK: %[[VAL_10:.*]] = tensor_to_memref %[[VAL_1]] : memref<20xf32> +// CHECK: %[[VAL_11:.*]] = tensor_to_memref %[[VAL_2]] : memref<30xf32> +// CHECK: %[[VAL_12:.*]] = tensor_to_memref %[[VAL_3]] : memref<10x20x30xf32> +// CHECK: %[[VAL_13:.*]] = alloc() : memref<10x20x30xf32> +// CHECK: linalg.copy(%[[VAL_12]], %[[VAL_13]]) : memref<10x20x30xf32>, memref<10x20x30xf32> +// CHECK: scf.for %[[VAL_14:.*]] = %[[VAL_7]] to %[[VAL_4]] step %[[VAL_8]] { +// CHECK: %[[VAL_15:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_14]]] : memref<10xf32> +// CHECK: scf.for %[[VAL_16:.*]] = %[[VAL_7]] to %[[VAL_5]] step %[[VAL_8]] { +// CHECK: %[[VAL_17:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_16]]] : memref<20xf32> +// CHECK: scf.for %[[VAL_18:.*]] = %[[VAL_7]] to %[[VAL_6]] step %[[VAL_8]] { +// CHECK: %[[VAL_19:.*]] = mulf %[[VAL_15]], %[[VAL_17]] : f32 +// CHECK: %[[VAL_20:.*]] = load %[[VAL_11]]{{\[}}%[[VAL_18]]] : memref<30xf32> +// CHECK: %[[VAL_21:.*]] = mulf %[[VAL_19]], %[[VAL_20]] : f32 +// CHECK: store %[[VAL_21]], %[[VAL_13]]{{\[}}%[[VAL_14]], %[[VAL_16]], %[[VAL_18]]] : memref<10x20x30xf32> // CHECK: } // CHECK: } // CHECK: } -// CHECK: %[[VAL_21:.*]] = tensor_load %[[VAL_12]] : memref<10x20x30xf32> -// CHECK: return %[[VAL_21]] : tensor<10x20x30xf32> +// CHECK: %[[VAL_22:.*]] = tensor_load %[[VAL_13]] : memref<10x20x30xf32> +// CHECK: return %[[VAL_22]] : tensor<10x20x30xf32> // CHECK: } func @invariants(%arga: tensor<10xf32>, %argb: tensor<20xf32>, diff --git a/mlir/test/Dialect/Linalg/sparse_lower.mlir b/mlir/test/Dialect/Linalg/sparse_lower.mlir new file mode 100644 --- /dev/null +++ b/mlir/test/Dialect/Linalg/sparse_lower.mlir @@ -0,0 +1,181 @@ +// RUN: mlir-opt %s -test-sparsification | \ +// RUN: FileCheck %s --check-prefix=CHECK-HIR +// +// RUN: mlir-opt %s -test-sparsification="lower" --convert-linalg-to-loops | \ +// RUN: FileCheck %s --check-prefix=CHECK-MIR +// +// RUN: mlir-opt %s -test-sparsification="lower" --convert-linalg-to-loops \ +// RUN: --func-bufferize --tensor-constant-bufferize \ +// RUN: --tensor-bufferize --finalizing-bufferize | \ +// RUN: FileCheck %s --check-prefix=CHECK-LIR +// +// RUN: mlir-opt %s -test-sparsification="lower fast-output" --convert-linalg-to-loops \ +// RUN: --func-bufferize --tensor-constant-bufferize \ +// RUN: --tensor-bufferize --finalizing-bufferize | \ +// RUN: FileCheck %s --check-prefix=CHECK-FAST + +#trait_matvec = { + indexing_maps = [ + affine_map<(i,j) -> (i,j)>, // A + affine_map<(i,j) -> (j)>, // b + affine_map<(i,j) -> (i)> // x (out) + ], + iterator_types = ["parallel","reduction"], + sparse = [ + [ "D", "S" ], // A + [ "D" ], // b + [ "D" ] // x (out) + ], + sparse_dim_map = [ + affine_map<(i,j) -> (j,i)>, // A: column-wise + affine_map<(i) -> (i)>, // x + affine_map<(i) -> (i)> // b + ], + doc = "x(i) += A(i,j) * b(j)" +} + +// CHECK-HIR-LABEL: func @matvec( +// CHECK-HIR-SAME: %[[VAL_0:.*]]: !llvm.ptr, +// CHECK-HIR-SAME: %[[VAL_1:.*]]: tensor<64xf64>, +// CHECK-HIR-SAME: %[[VAL_2:.*]]: tensor<64xf64>) -> tensor<64xf64> { +// CHECK-HIR: %[[VAL_3:.*]] = constant 64 : index +// CHECK-HIR: %[[VAL_4:.*]] = constant 0 : index +// CHECK-HIR: %[[VAL_5:.*]] = constant 1 : index +// CHECK-HIR: %[[VAL_6:.*]] = linalg.sparse_tensor %[[VAL_0]] : !llvm.ptr into tensor<64x64xf64> +// CHECK-HIR: %[[VAL_7:.*]] = linalg.sparse_pointers %[[VAL_6]], %[[VAL_5]] : tensor<64x64xf64> into memref +// CHECK-HIR: %[[VAL_8:.*]] = linalg.sparse_indices %[[VAL_6]], %[[VAL_5]] : tensor<64x64xf64> into memref +// CHECK-HIR: %[[VAL_9:.*]] = linalg.sparse_values %[[VAL_6]] : tensor<64x64xf64> into memref +// CHECK-HIR: %[[VAL_10:.*]] = tensor_to_memref %[[VAL_1]] : memref<64xf64> +// CHECK-HIR: %[[VAL_11:.*]] = tensor_to_memref %[[VAL_2]] : memref<64xf64> +// CHECK-HIR: %[[VAL_12:.*]] = alloc() : memref<64xf64> +// CHECK-HIR: linalg.copy(%[[VAL_11]], %[[VAL_12]]) : memref<64xf64>, memref<64xf64> +// CHECK-HIR: scf.for %[[VAL_13:.*]] = %[[VAL_4]] to %[[VAL_3]] step %[[VAL_5]] { +// CHECK-HIR: %[[VAL_14:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_13]]] : memref +// CHECK-HIR: %[[VAL_15:.*]] = addi %[[VAL_13]], %[[VAL_5]] : index +// CHECK-HIR: %[[VAL_16:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_15]]] : memref +// CHECK-HIR: %[[VAL_17:.*]] = load %[[VAL_12]]{{\[}}%[[VAL_13]]] : memref<64xf64> +// CHECK-HIR: %[[VAL_18:.*]] = scf.for %[[VAL_19:.*]] = %[[VAL_14]] to %[[VAL_16]] step %[[VAL_5]] iter_args(%[[VAL_20:.*]] = %[[VAL_17]]) -> (f64) { +// CHECK-HIR: %[[VAL_21:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_19]]] : memref +// CHECK-HIR: %[[VAL_22:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_19]]] : memref +// CHECK-HIR: %[[VAL_23:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_21]]] : memref<64xf64> +// CHECK-HIR: %[[VAL_24:.*]] = mulf %[[VAL_22]], %[[VAL_23]] : f64 +// CHECK-HIR: %[[VAL_25:.*]] = addf %[[VAL_20]], %[[VAL_24]] : f64 +// CHECK-HIR: scf.yield %[[VAL_25]] : f64 +// CHECK-HIR: } +// CHECK-HIR: store %[[VAL_26:.*]], %[[VAL_12]]{{\[}}%[[VAL_13]]] : memref<64xf64> +// CHECK-HIR: } +// CHECK-HIR: %[[VAL_27:.*]] = tensor_load %[[VAL_12]] : memref<64xf64> +// CHECK-HIR: return %[[VAL_27]] : tensor<64xf64> +// CHECK-HIR: } + +// CHECK-MIR-LABEL: func @matvec( +// CHECK-MIR-SAME: %[[VAL_0:.*]]: !llvm.ptr, +// CHECK-MIR-SAME: %[[VAL_1:.*]]: tensor<64xf64>, +// CHECK-MIR-SAME: %[[VAL_2:.*]]: tensor<64xf64>) -> tensor<64xf64> { +// CHECK-MIR: %[[VAL_3:.*]] = constant 64 : index +// CHECK-MIR: %[[VAL_4:.*]] = constant 0 : index +// CHECK-MIR: %[[VAL_5:.*]] = constant 1 : index +// CHECK-MIR: %[[VAL_6:.*]] = call @sparsePtrsI64(%[[VAL_0]], %[[VAL_5]]) : (!llvm.ptr, index) -> memref +// CHECK-MIR: %[[VAL_7:.*]] = call @sparseIndxsI64(%[[VAL_0]], %[[VAL_5]]) : (!llvm.ptr, index) -> memref +// CHECK-MIR: %[[VAL_8:.*]] = call @sparseValsF64(%[[VAL_0]]) : (!llvm.ptr) -> memref +// CHECK-MIR: %[[VAL_9:.*]] = tensor_to_memref %[[VAL_1]] : memref<64xf64> +// CHECK-MIR: %[[VAL_10:.*]] = tensor_to_memref %[[VAL_2]] : memref<64xf64> +// CHECK-MIR: %[[VAL_11:.*]] = alloc() : memref<64xf64> +// CHECK-MIR: scf.for %[[VAL_12:.*]] = %[[VAL_4]] to %[[VAL_3]] step %[[VAL_5]] { +// CHECK-MIR: %[[VAL_13:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_12]]] : memref<64xf64> +// CHECK-MIR: store %[[VAL_13]], %[[VAL_11]]{{\[}}%[[VAL_12]]] : memref<64xf64> +// CHECK-MIR: } +// CHECK-MIR: scf.for %[[VAL_14:.*]] = %[[VAL_4]] to %[[VAL_3]] step %[[VAL_5]] { +// CHECK-MIR: %[[VAL_15:.*]] = load %[[VAL_6]]{{\[}}%[[VAL_14]]] : memref +// CHECK-MIR: %[[VAL_16:.*]] = addi %[[VAL_14]], %[[VAL_5]] : index +// CHECK-MIR: %[[VAL_17:.*]] = load %[[VAL_6]]{{\[}}%[[VAL_16]]] : memref +// CHECK-MIR: %[[VAL_18:.*]] = load %[[VAL_11]]{{\[}}%[[VAL_14]]] : memref<64xf64> +// CHECK-MIR: %[[VAL_19:.*]] = scf.for %[[VAL_20:.*]] = %[[VAL_15]] to %[[VAL_17]] step %[[VAL_5]] iter_args(%[[VAL_21:.*]] = %[[VAL_18]]) -> (f64) { +// CHECK-MIR: %[[VAL_22:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_20]]] : memref +// CHECK-MIR: %[[VAL_23:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_20]]] : memref +// CHECK-MIR: %[[VAL_24:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_22]]] : memref<64xf64> +// CHECK-MIR: %[[VAL_25:.*]] = mulf %[[VAL_23]], %[[VAL_24]] : f64 +// CHECK-MIR: %[[VAL_26:.*]] = addf %[[VAL_21]], %[[VAL_25]] : f64 +// CHECK-MIR: scf.yield %[[VAL_26]] : f64 +// CHECK-MIR: } +// CHECK-MIR: store %[[VAL_27:.*]], %[[VAL_11]]{{\[}}%[[VAL_14]]] : memref<64xf64> +// CHECK-MIR: } +// CHECK-MIR: %[[VAL_28:.*]] = tensor_load %[[VAL_11]] : memref<64xf64> +// CHECK-MIR: return %[[VAL_28]] : tensor<64xf64> +// CHECK-MIR: } + +// CHECK-LIR-LABEL: func @matvec( +// CHECK-LIR-SAME: %[[VAL_0:.*]]: !llvm.ptr, +// CHECK-LIR-SAME: %[[VAL_1:.*]]: memref<64xf64>, +// CHECK-LIR-SAME: %[[VAL_2:.*]]: memref<64xf64>) -> memref<64xf64> { +// CHECK-LIR: %[[VAL_3:.*]] = constant 64 : index +// CHECK-LIR: %[[VAL_4:.*]] = constant 0 : index +// CHECK-LIR: %[[VAL_5:.*]] = constant 1 : index +// CHECK-LIR: %[[VAL_6:.*]] = call @sparsePtrsI64(%[[VAL_0]], %[[VAL_5]]) : (!llvm.ptr, index) -> memref +// CHECK-LIR: %[[VAL_7:.*]] = call @sparseIndxsI64(%[[VAL_0]], %[[VAL_5]]) : (!llvm.ptr, index) -> memref +// CHECK-LIR: %[[VAL_8:.*]] = call @sparseValsF64(%[[VAL_0]]) : (!llvm.ptr) -> memref +// CHECK-LIR: %[[VAL_9:.*]] = alloc() : memref<64xf64> +// CHECK-LIR: scf.for %[[VAL_10:.*]] = %[[VAL_4]] to %[[VAL_3]] step %[[VAL_5]] { +// CHECK-LIR: %[[VAL_11:.*]] = load %[[VAL_2]]{{\[}}%[[VAL_10]]] : memref<64xf64> +// CHECK-LIR: store %[[VAL_11]], %[[VAL_9]]{{\[}}%[[VAL_10]]] : memref<64xf64> +// CHECK-LIR: } +// CHECK-LIR: scf.for %[[VAL_12:.*]] = %[[VAL_4]] to %[[VAL_3]] step %[[VAL_5]] { +// CHECK-LIR: %[[VAL_13:.*]] = load %[[VAL_6]]{{\[}}%[[VAL_12]]] : memref +// CHECK-LIR: %[[VAL_14:.*]] = addi %[[VAL_12]], %[[VAL_5]] : index +// CHECK-LIR: %[[VAL_15:.*]] = load %[[VAL_6]]{{\[}}%[[VAL_14]]] : memref +// CHECK-LIR: %[[VAL_16:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_12]]] : memref<64xf64> +// CHECK-LIR: %[[VAL_17:.*]] = scf.for %[[VAL_18:.*]] = %[[VAL_13]] to %[[VAL_15]] step %[[VAL_5]] iter_args(%[[VAL_19:.*]] = %[[VAL_16]]) -> (f64) { +// CHECK-LIR: %[[VAL_20:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_18]]] : memref +// CHECK-LIR: %[[VAL_21:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_18]]] : memref +// CHECK-LIR: %[[VAL_22:.*]] = load %[[VAL_1]]{{\[}}%[[VAL_20]]] : memref<64xf64> +// CHECK-LIR: %[[VAL_23:.*]] = mulf %[[VAL_21]], %[[VAL_22]] : f64 +// CHECK-LIR: %[[VAL_24:.*]] = addf %[[VAL_19]], %[[VAL_23]] : f64 +// CHECK-LIR: scf.yield %[[VAL_24]] : f64 +// CHECK-LIR: } +// CHECK-LIR: store %[[VAL_25:.*]], %[[VAL_9]]{{\[}}%[[VAL_12]]] : memref<64xf64> +// CHECK-LIR: } +// CHECK-LIR: return %[[VAL_9]] : memref<64xf64> +// CHECK-LIR: } + +// CHECK-FAST-LABEL: func @matvec( +// CHECK-FAST-SAME: %[[VAL_0:.*]]: !llvm.ptr, +// CHECK-FAST-SAME: %[[VAL_1:.*]]: memref<64xf64>, +// CHECK-FAST-SAME: %[[VAL_2:.*]]: memref<64xf64>) -> memref<64xf64> { +// CHECK-FAST: %[[VAL_3:.*]] = constant 64 : index +// CHECK-FAST: %[[VAL_4:.*]] = constant 0 : index +// CHECK-FAST: %[[VAL_5:.*]] = constant 1 : index +// CHECK-FAST: %[[VAL_6:.*]] = call @sparsePtrsI64(%[[VAL_0]], %[[VAL_5]]) : (!llvm.ptr, index) -> memref +// CHECK-FAST: %[[VAL_7:.*]] = call @sparseIndxsI64(%[[VAL_0]], %[[VAL_5]]) : (!llvm.ptr, index) -> memref +// CHECK-FAST: %[[VAL_8:.*]] = call @sparseValsF64(%[[VAL_0]]) : (!llvm.ptr) -> memref +// CHECK-FAST: scf.for %[[VAL_9:.*]] = %[[VAL_4]] to %[[VAL_3]] step %[[VAL_5]] { +// CHECK-FAST: %[[VAL_10:.*]] = load %[[VAL_6]]{{\[}}%[[VAL_9]]] : memref +// CHECK-FAST: %[[VAL_11:.*]] = addi %[[VAL_9]], %[[VAL_5]] : index +// CHECK-FAST: %[[VAL_12:.*]] = load %[[VAL_6]]{{\[}}%[[VAL_11]]] : memref +// CHECK-FAST: %[[VAL_13:.*]] = load %[[VAL_2]]{{\[}}%[[VAL_9]]] : memref<64xf64> +// CHECK-FAST: %[[VAL_14:.*]] = scf.for %[[VAL_15:.*]] = %[[VAL_10]] to %[[VAL_12]] step %[[VAL_5]] iter_args(%[[VAL_16:.*]] = %[[VAL_13]]) -> (f64) { +// CHECK-FAST: %[[VAL_17:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_15]]] : memref +// CHECK-FAST: %[[VAL_18:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_15]]] : memref +// CHECK-FAST: %[[VAL_19:.*]] = load %[[VAL_1]]{{\[}}%[[VAL_17]]] : memref<64xf64> +// CHECK-FAST: %[[VAL_20:.*]] = mulf %[[VAL_18]], %[[VAL_19]] : f64 +// CHECK-FAST: %[[VAL_21:.*]] = addf %[[VAL_16]], %[[VAL_20]] : f64 +// CHECK-FAST: scf.yield %[[VAL_21]] : f64 +// CHECK-FAST: } +// CHECK-FAST: store %[[VAL_22:.*]], %[[VAL_2]]{{\[}}%[[VAL_9]]] : memref<64xf64> +// CHECK-FAST: } +// CHECK-FAST: return %[[VAL_2]] : memref<64xf64> +// CHECK-FAST: } + +!SparseTensor = type !llvm.ptr + +func @matvec(%argA: !SparseTensor, %argb: tensor<64xf64>, %argx: tensor<64xf64>) -> tensor<64xf64> { + %arga = linalg.sparse_tensor %argA : !SparseTensor into tensor<64x64xf64> + %0 = linalg.generic #trait_matvec + ins(%arga, %argb : tensor<64x64xf64>, tensor<64xf64>) + outs(%argx: tensor<64xf64>) { + ^bb(%A: f64, %b: f64, %x: f64): + %0 = mulf %A, %b : f64 + %1 = addf %x, %0 : f64 + linalg.yield %1 : f64 + } -> tensor<64xf64> + return %0 : tensor<64xf64> +} diff --git a/mlir/test/Dialect/Linalg/sparse_nd.mlir b/mlir/test/Dialect/Linalg/sparse_nd.mlir --- a/mlir/test/Dialect/Linalg/sparse_nd.mlir +++ b/mlir/test/Dialect/Linalg/sparse_nd.mlir @@ -23,52 +23,55 @@ // CHECK-SAME: %[[VAL_0:.*0]]: tensor<100x200x300x400x500x600x700x800xf32>, // CHECK-SAME: %[[VAL_1:.*1]]: tensor<100x200x300x400x500x600x700x800xf32>, // CHECK-SAME: %[[VAL_2:.*2]]: tensor<100x200x300x400x500x600x700x800xf32>) -> tensor<100x200x300x400x500x600x700x800xf32> { -// CHECK: %[[VAL_3:.*]] = constant 999 : index -// CHECK: %[[VAL_4:.*]] = constant 100 : index -// CHECK: %[[VAL_5:.*]] = constant 200 : index -// CHECK: %[[VAL_6:.*]] = constant 300 : index -// CHECK: %[[VAL_7:.*]] = constant 600 : index -// CHECK: %[[VAL_8:.*]] = constant 700 : index -// CHECK: %[[VAL_9:.*]] = constant 800 : index -// CHECK: %[[VAL_10:.*]] = constant 0 : index -// CHECK: %[[VAL_11:.*]] = constant 1 : index -// CHECK: %[[VAL_12:.*]] = alloca() : memref<100x200x300x400x500x600x700x800xf32> -// CHECK: %[[VAL_13:.*]] = alloca(%[[VAL_3]]) : memref -// CHECK: %[[VAL_14:.*]] = alloca(%[[VAL_3]]) : memref -// CHECK: %[[VAL_15:.*]] = alloca(%[[VAL_3]]) : memref -// CHECK: %[[VAL_16:.*]] = alloca(%[[VAL_3]]) : memref -// CHECK: %[[VAL_17:.*]] = alloca(%[[VAL_3]]) : memref -// CHECK: %[[VAL_18:.*]] = alloca() : memref<100x200x300x400x500x600x700x800xf32> -// CHECK: scf.for %[[VAL_19:.*]] = %[[VAL_10]] to %[[VAL_9]] step %[[VAL_11]] { -// CHECK: scf.for %[[VAL_20:.*]] = %[[VAL_10]] to %[[VAL_8]] step %[[VAL_11]] { -// CHECK: %[[VAL_21:.*]] = muli %[[VAL_19]], %[[VAL_8]] : index -// CHECK: %[[VAL_22:.*]] = addi %[[VAL_21]], %[[VAL_20]] : index -// CHECK: scf.for %[[VAL_23:.*]] = %[[VAL_10]] to %[[VAL_7]] step %[[VAL_11]] { -// CHECK: %[[VAL_24:.*]] = muli %[[VAL_22]], %[[VAL_7]] : index -// CHECK: %[[VAL_25:.*]] = addi %[[VAL_24]], %[[VAL_23]] : index -// CHECK: %[[VAL_26:.*]] = load %[[VAL_13]]{{\[}}%[[VAL_25]]] : memref -// CHECK: %[[VAL_27:.*]] = addi %[[VAL_25]], %[[VAL_11]] : index -// CHECK: %[[VAL_28:.*]] = load %[[VAL_13]]{{\[}}%[[VAL_27]]] : memref -// CHECK: scf.for %[[VAL_29:.*]] = %[[VAL_26]] to %[[VAL_28]] step %[[VAL_11]] { -// CHECK: %[[VAL_30:.*]] = load %[[VAL_14]]{{\[}}%[[VAL_29]]] : memref -// CHECK: %[[VAL_31:.*]] = load %[[VAL_15]]{{\[}}%[[VAL_29]]] : memref -// CHECK: %[[VAL_32:.*]] = addi %[[VAL_29]], %[[VAL_11]] : index -// CHECK: %[[VAL_33:.*]] = load %[[VAL_15]]{{\[}}%[[VAL_32]]] : memref -// CHECK: scf.for %[[VAL_34:.*]] = %[[VAL_31]] to %[[VAL_33]] step %[[VAL_11]] { -// CHECK: %[[VAL_35:.*]] = load %[[VAL_16]]{{\[}}%[[VAL_34]]] : memref -// CHECK: scf.for %[[VAL_36:.*]] = %[[VAL_10]] to %[[VAL_6]] step %[[VAL_11]] { -// CHECK: %[[VAL_37:.*]] = muli %[[VAL_34]], %[[VAL_6]] : index -// CHECK: %[[VAL_38:.*]] = addi %[[VAL_37]], %[[VAL_36]] : index -// CHECK: scf.for %[[VAL_39:.*]] = %[[VAL_10]] to %[[VAL_5]] step %[[VAL_11]] { -// CHECK: %[[VAL_40:.*]] = muli %[[VAL_38]], %[[VAL_5]] : index -// CHECK: %[[VAL_41:.*]] = addi %[[VAL_40]], %[[VAL_39]] : index -// CHECK: scf.for %[[VAL_42:.*]] = %[[VAL_10]] to %[[VAL_4]] step %[[VAL_11]] { -// CHECK: %[[VAL_43:.*]] = muli %[[VAL_41]], %[[VAL_4]] : index -// CHECK: %[[VAL_44:.*]] = addi %[[VAL_43]], %[[VAL_42]] : index -// CHECK: %[[VAL_45:.*]] = load %[[VAL_12]]{{\[}}%[[VAL_42]], %[[VAL_39]], %[[VAL_36]], %[[VAL_35]], %[[VAL_30]], %[[VAL_23]], %[[VAL_20]], %[[VAL_19]]] : memref<100x200x300x400x500x600x700x800xf32> -// CHECK: %[[VAL_46:.*]] = load %[[VAL_17]]{{\[}}%[[VAL_44]]] : memref -// CHECK: %[[VAL_47:.*]] = mulf %[[VAL_45]], %[[VAL_46]] : f32 -// CHECK: store %[[VAL_47]], %[[VAL_18]]{{\[}}%[[VAL_42]], %[[VAL_39]], %[[VAL_36]], %[[VAL_35]], %[[VAL_30]], %[[VAL_23]], %[[VAL_20]], %[[VAL_19]]] : memref<100x200x300x400x500x600x700x800xf32> +// CHECK: %[[VAL_3:.*]] = constant 3 : index +// CHECK: %[[VAL_4:.*]] = constant 4 : index +// CHECK: %[[VAL_5:.*]] = constant 100 : index +// CHECK: %[[VAL_6:.*]] = constant 200 : index +// CHECK: %[[VAL_7:.*]] = constant 300 : index +// CHECK: %[[VAL_8:.*]] = constant 600 : index +// CHECK: %[[VAL_9:.*]] = constant 700 : index +// CHECK: %[[VAL_10:.*]] = constant 800 : index +// CHECK: %[[VAL_11:.*]] = constant 0 : index +// CHECK: %[[VAL_12:.*]] = constant 1 : index +// CHECK: %[[VAL_13:.*]] = tensor_to_memref %[[VAL_0]] : memref<100x200x300x400x500x600x700x800xf32> +// CHECK: %[[VAL_14:.*]] = linalg.sparse_pointers %[[VAL_1]], %[[VAL_3]] : tensor<100x200x300x400x500x600x700x800xf32> into memref +// CHECK: %[[VAL_15:.*]] = linalg.sparse_indices %[[VAL_1]], %[[VAL_3]] : tensor<100x200x300x400x500x600x700x800xf32> into memref +// CHECK: %[[VAL_16:.*]] = linalg.sparse_pointers %[[VAL_1]], %[[VAL_4]] : tensor<100x200x300x400x500x600x700x800xf32> into memref +// CHECK: %[[VAL_17:.*]] = linalg.sparse_indices %[[VAL_1]], %[[VAL_4]] : tensor<100x200x300x400x500x600x700x800xf32> into memref +// CHECK: %[[VAL_18:.*]] = linalg.sparse_values %[[VAL_1]] : tensor<100x200x300x400x500x600x700x800xf32> into memref +// CHECK: %[[VAL_19:.*]] = tensor_to_memref %[[VAL_2]] : memref<100x200x300x400x500x600x700x800xf32> +// CHECK: %[[VAL_20:.*]] = alloc() : memref<100x200x300x400x500x600x700x800xf32> +// CHECK: linalg.copy(%[[VAL_19]], %[[VAL_20]]) : memref<100x200x300x400x500x600x700x800xf32>, memref<100x200x300x400x500x600x700x800xf32> +// CHECK: scf.for %[[VAL_21:.*]] = %[[VAL_11]] to %[[VAL_10]] step %[[VAL_12]] { +// CHECK: scf.for %[[VAL_22:.*]] = %[[VAL_11]] to %[[VAL_9]] step %[[VAL_12]] { +// CHECK: %[[VAL_23:.*]] = muli %[[VAL_21]], %[[VAL_9]] : index +// CHECK: %[[VAL_24:.*]] = addi %[[VAL_23]], %[[VAL_22]] : index +// CHECK: scf.for %[[VAL_25:.*]] = %[[VAL_11]] to %[[VAL_8]] step %[[VAL_12]] { +// CHECK: %[[VAL_26:.*]] = muli %[[VAL_24]], %[[VAL_8]] : index +// CHECK: %[[VAL_27:.*]] = addi %[[VAL_26]], %[[VAL_25]] : index +// CHECK: %[[VAL_28:.*]] = load %[[VAL_14]]{{\[}}%[[VAL_27]]] : memref +// CHECK: %[[VAL_29:.*]] = addi %[[VAL_27]], %[[VAL_12]] : index +// CHECK: %[[VAL_30:.*]] = load %[[VAL_14]]{{\[}}%[[VAL_29]]] : memref +// CHECK: scf.for %[[VAL_31:.*]] = %[[VAL_28]] to %[[VAL_30]] step %[[VAL_12]] { +// CHECK: %[[VAL_32:.*]] = load %[[VAL_15]]{{\[}}%[[VAL_31]]] : memref +// CHECK: %[[VAL_33:.*]] = load %[[VAL_16]]{{\[}}%[[VAL_31]]] : memref +// CHECK: %[[VAL_34:.*]] = addi %[[VAL_31]], %[[VAL_12]] : index +// CHECK: %[[VAL_35:.*]] = load %[[VAL_16]]{{\[}}%[[VAL_34]]] : memref +// CHECK: scf.for %[[VAL_36:.*]] = %[[VAL_33]] to %[[VAL_35]] step %[[VAL_12]] { +// CHECK: %[[VAL_37:.*]] = load %[[VAL_17]]{{\[}}%[[VAL_36]]] : memref +// CHECK: scf.for %[[VAL_38:.*]] = %[[VAL_11]] to %[[VAL_7]] step %[[VAL_12]] { +// CHECK: %[[VAL_39:.*]] = muli %[[VAL_36]], %[[VAL_7]] : index +// CHECK: %[[VAL_40:.*]] = addi %[[VAL_39]], %[[VAL_38]] : index +// CHECK: scf.for %[[VAL_41:.*]] = %[[VAL_11]] to %[[VAL_6]] step %[[VAL_12]] { +// CHECK: %[[VAL_42:.*]] = muli %[[VAL_40]], %[[VAL_6]] : index +// CHECK: %[[VAL_43:.*]] = addi %[[VAL_42]], %[[VAL_41]] : index +// CHECK: scf.for %[[VAL_44:.*]] = %[[VAL_11]] to %[[VAL_5]] step %[[VAL_12]] { +// CHECK: %[[VAL_45:.*]] = muli %[[VAL_43]], %[[VAL_5]] : index +// CHECK: %[[VAL_46:.*]] = addi %[[VAL_45]], %[[VAL_44]] : index +// CHECK: %[[VAL_47:.*]] = load %[[VAL_13]]{{\[}}%[[VAL_44]], %[[VAL_41]], %[[VAL_38]], %[[VAL_37]], %[[VAL_32]], %[[VAL_25]], %[[VAL_22]], %[[VAL_21]]] : memref<100x200x300x400x500x600x700x800xf32> +// CHECK: %[[VAL_48:.*]] = load %[[VAL_18]]{{\[}}%[[VAL_46]]] : memref +// CHECK: %[[VAL_49:.*]] = mulf %[[VAL_47]], %[[VAL_48]] : f32 +// CHECK: store %[[VAL_49]], %[[VAL_20]]{{\[}}%[[VAL_44]], %[[VAL_41]], %[[VAL_38]], %[[VAL_37]], %[[VAL_32]], %[[VAL_25]], %[[VAL_22]], %[[VAL_21]]] : memref<100x200x300x400x500x600x700x800xf32> // CHECK: } // CHECK: } // CHECK: } @@ -77,8 +80,8 @@ // CHECK: } // CHECK: } // CHECK: } -// CHECK: %[[VAL_48:.*]] = tensor_load %[[VAL_18]] : memref<100x200x300x400x500x600x700x800xf32> -// CHECK: return %[[VAL_48]] : tensor<100x200x300x400x500x600x700x800xf32> +// CHECK: %[[VAL_50:.*]] = tensor_load %[[VAL_20]] : memref<100x200x300x400x500x600x700x800xf32> +// CHECK: return %[[VAL_50]] : tensor<100x200x300x400x500x600x700x800xf32> // CHECK: } func @mul(%arga: tensor<100x200x300x400x500x600x700x800xf32>, %argb: tensor<100x200x300x400x500x600x700x800xf32>, diff --git a/mlir/test/lib/Transforms/TestSparsification.cpp b/mlir/test/lib/Transforms/TestSparsification.cpp --- a/mlir/test/lib/Transforms/TestSparsification.cpp +++ b/mlir/test/lib/Transforms/TestSparsification.cpp @@ -6,6 +6,7 @@ // //===----------------------------------------------------------------------===// +#include "mlir/Dialect/LLVMIR/LLVMDialect.h" #include "mlir/Dialect/Linalg/Transforms/Transforms.h" #include "mlir/Dialect/Vector/VectorOps.h" #include "mlir/Pass/Pass.h" @@ -40,9 +41,17 @@ llvm::cl::desc("Set the index type"), llvm::cl::init(0)}; + Option fastOutput{*this, "fast-output", + llvm::cl::desc("Allows fast output buffers"), + llvm::cl::init(false)}; + + Option lower{*this, "lower", llvm::cl::desc("Lower sparse primitives"), + llvm::cl::init(false)}; + /// Registers all dialects required by testing. void getDependentDialects(DialectRegistry ®istry) const override { - registry.insert(); + registry + .insert(); } /// Returns parallelization strategy given on command line. @@ -96,11 +105,25 @@ // Translate strategy flags to strategy options. linalg::SparsificationOptions options(parallelOption(), vectorOption(), vectorLength, typeOption(ptrType), - typeOption(indType)); + typeOption(indType), fastOutput); // Apply rewriting. linalg::populateSparsificationPatterns(ctx, patterns, options); vector::populateVectorToVectorCanonicalizationPatterns(patterns, ctx); applyPatternsAndFoldGreedily(getFunction(), std::move(patterns)); + // Lower sparse primitives to calls into runtime support library. + if (lower) { + OwningRewritePatternList conversionPatterns; + ConversionTarget target(*ctx); + target.addIllegalOp(); + target.addLegalOp(); + linalg::populateSparsificationConversionPatterns(ctx, conversionPatterns); + if (failed(applyPartialConversion(getOperation(), target, + std::move(conversionPatterns)))) + signalPassFailure(); + } } };