Changed wrong ROCDL instructions in GPU lowering.

[dfki-jugr]

Summary

In the scope of the lowering phase from GPU to ROCDL, the intructions for the conversion patterns seems to be wrong.
According to https://github.com/ROCm-Developer-Tools/HIP/blob/master/include/hip/hcc_detail/math_fwd.h the instructions need two underscores in the beginning instead of one.

[herhut]

Nice catch!

We do not currently have end-to-end tests for these but as this shows we should.

[merge_guards_bot]

Unit tests: fail. 62254 tests passed, 1 failed and 827 were skipped.

failed: MLIR.Conversion/GPUToROCDL/gpu-to-rocdl.mlir

clang-tidy: pass.

clang-format: fail. Please format your changes with clang-format by running git-clang-format HEAD^ or applying this patch.

Build artifacts: diff.json, clang-tidy.txt, clang-format.patch, CMakeCache.txt, console-log.txt, test-results.xml

Pre-merge checks is in beta. Report issue. Please join beta or enable it for your project.

[rriddle]

Please fix the clang format issue and add/fix the test.

[dfki-jugr]

Fixed test cases and format issues.

[merge_guards_bot]

Unit tests: pass. 62255 tests passed, 0 failed and 827 were skipped.

clang-tidy: pass.

clang-format: pass.

Build artifacts: diff.json, clang-tidy.txt, clang-format.patch, CMakeCache.txt, console-log.txt, test-results.xml

Pre-merge checks is in beta. Report issue. Please join beta or enable it for your project.

mlir/lib/Conversion/GPUToROCDL/LowerGpuOpsToROCDLOps.cpp

patterns.insert<
                                     ROCDL::ThreadIdYOp, ROCDL::ThreadIdZOp>,
         GPUIndexIntrinsicOpLowering<gpu::BlockDimOp, ROCDL::BlockDimXOp,
                                     ROCDL::BlockDimYOp, ROCDL::BlockDimZOp>,
         GPUIndexIntrinsicOpLowering<gpu::BlockIdOp, ROCDL::BlockIdXOp,
                                     ROCDL::BlockIdYOp, ROCDL::BlockIdZOp>,
         GPUIndexIntrinsicOpLowering<gpu::GridDimOp, ROCDL::GridDimXOp,
                                     ROCDL::GridDimYOp, ROCDL::GridDimZOp>>(
         converter);
-    patterns.insert<OpToFuncCallLowering<AbsFOp>>(converter, "_ocml_fabs_f32",
-                                                 "_ocml_fabs_f64");
-    patterns.insert<OpToFuncCallLowering<CeilFOp>>(converter, "_ocml_ceil_f32",
-                                                 "_ocml_ceil_f64");
-    patterns.insert<OpToFuncCallLowering<CosOp>>(converter, "_ocml_cos_f32",
-                                                 "_ocml_cos_f64");
-    patterns.insert<OpToFuncCallLowering<ExpOp>>(converter, "_ocml_exp_f32",
-                                                 "_ocml_exp_f64");
-    patterns.insert<OpToFuncCallLowering<TanhOp>>(converter, "_ocml_tanh_f32",
-                                                  "_ocml_tanh_f64");
+    patterns.insert<OpToFuncCallLowering<AbsFOp>>(converter, "__ocml_fabs_f32",
+                                                  "__ocml_fabs_f64");
+    patterns.insert<OpToFuncCallLowering<CeilFOp>>(converter, "__ocml_ceil_f32",
+                                                   "__ocml_ceil_f64");
+    patterns.insert<OpToFuncCallLowering<CosOp>>(converter, "__ocml_cos_f32",
+                                                 "__ocml_cos_f64");
+    patterns.insert<OpToFuncCallLowering<ExpOp>>(converter, "__ocml_exp_f32",
+                                                 "__ocml_exp_f64");
+    patterns.insert<OpToFuncCallLowering<TanhOp>>(converter, "__ocml_tanh_f32",
+                                                  "__ocml_tanh_f64");
 
     ConversionTarget target(getContext());
     target.addLegalDialect<LLVM::LLVMDialect, ROCDL::ROCDLDialect>();
     target.addIllegalOp<LLVM::FAbsOp, LLVM::FCeilOp, LLVM::CosOp,
                         LLVM::ExpOp>();
     target.addDynamicallyLegalOp<FuncOp>(
         [&](FuncOp op) { return converter.isSignatureLegal(op.getType()); });
     if (failed(applyPartialConversion(m, target, patterns, &converter)))

mlir/test/Conversion/GPUToROCDL/gpu-to-rocdl.mlir

func @gpu_index_ops()
 
     std.return
   }
 }
 
 // -----
 
 gpu.module @kernel_module {
-  // CHECK: llvm.func @_ocml_fabs_f32(!llvm.float) -> !llvm.float
-  // CHECK: llvm.func @_ocml_fabs_f64(!llvm.double) -> !llvm.double
+  // CHECK: llvm.func @__ocml_fabs_f32(!llvm.float) -> !llvm.float
+  // CHECK: llvm.func @__ocml_fabs_f64(!llvm.double) -> !llvm.double
   // CHECK-LABEL: func @gpu_fabs
   func @gpu_fabs(%arg_f32 : f32, %arg_f64 : f64) {
     %result32 = std.absf %arg_f32 : f32
-    // CHECK: llvm.call @_ocml_fabs_f32(%{{.*}}) : (!llvm.float) -> !llvm.float
+    // CHECK: llvm.call @__ocml_fabs_f32(%{{.*}}) : (!llvm.float) -> !llvm.float
     %result64 = std.absf %arg_f64 : f64
-    // CHECK: llvm.call @_ocml_fabs_f64(%{{.*}}) : (!llvm.double) -> !llvm.double
+    // CHECK: llvm.call @__ocml_fabs_f64(%{{.*}}) : (!llvm.double) -> !llvm.double
     std.return
   }
 }
 
 // -----
 
 gpu.module @kernel_module {
-  // CHECK: llvm.func @_ocml_ceil_f32(!llvm.float) -> !llvm.float
-  // CHECK: llvm.func @_ocml_ceil_f64(!llvm.double) -> !llvm.double
+  // CHECK: llvm.func @__ocml_ceil_f32(!llvm.float) -> !llvm.float
+  // CHECK: llvm.func @__ocml_ceil_f64(!llvm.double) -> !llvm.double
   // CHECK-LABEL: func @gpu_ceil
   func @gpu_ceil(%arg_f32 : f32, %arg_f64 : f64) {
     %result32 = std.ceilf %arg_f32 : f32
-    // CHECK: llvm.call @_ocml_ceil_f32(%{{.*}}) : (!llvm.float) -> !llvm.float
+    // CHECK: llvm.call @__ocml_ceil_f32(%{{.*}}) : (!llvm.float) -> !llvm.float
     %result64 = std.ceilf %arg_f64 : f64
-    // CHECK: llvm.call @_ocml_ceil_f64(%{{.*}}) : (!llvm.double) -> !llvm.double
+    // CHECK: llvm.call @__ocml_ceil_f64(%{{.*}}) : (!llvm.double) -> !llvm.double
     std.return
   }
 }
 
 // -----
 
 gpu.module @kernel_module {
-  // CHECK: llvm.func @_ocml_cos_f32(!llvm.float) -> !llvm.float
-  // CHECK: llvm.func @_ocml_cos_f64(!llvm.double) -> !llvm.double
+  // CHECK: llvm.func @__ocml_cos_f32(!llvm.float) -> !llvm.float
+  // CHECK: llvm.func @__ocml_cos_f64(!llvm.double) -> !llvm.double
   // CHECK-LABEL: func @gpu_cos
   func @gpu_cos(%arg_f32 : f32, %arg_f64 : f64) {
     %result32 = std.cos %arg_f32 : f32
-    // CHECK: llvm.call @_ocml_cos_f32(%{{.*}}) : (!llvm.float) -> !llvm.float
+    // CHECK: llvm.call @__ocml_cos_f32(%{{.*}}) : (!llvm.float) -> !llvm.float
     %result64 = std.cos %arg_f64 : f64
-    // CHECK: llvm.call @_ocml_cos_f64(%{{.*}}) : (!llvm.double) -> !llvm.double
+    // CHECK: llvm.call @__ocml_cos_f64(%{{.*}}) : (!llvm.double) -> !llvm.double
     std.return
   }
 }
 
 // -----
 
 gpu.module @kernel_module {
-  // CHECK: llvm.func @_ocml_tanh_f32(!llvm.float) -> !llvm.float
-  // CHECK: llvm.func @_ocml_tanh_f64(!llvm.double) -> !llvm.double
+  // CHECK: llvm.func @__ocml_tanh_f32(!llvm.float) -> !llvm.float
+  // CHECK: llvm.func @__ocml_tanh_f64(!llvm.double) -> !llvm.double
   // CHECK-LABEL: func @gpu_tanh
   func @gpu_tanh(%arg_f32 : f32, %arg_f64 : f64) {
     %result32 = std.tanh %arg_f32 : f32
-    // CHECK: llvm.call @_ocml_tanh_f32(%{{.*}}) : (!llvm.float) -> !llvm.float
+    // CHECK: llvm.call @__ocml_tanh_f32(%{{.*}}) : (!llvm.float) -> !llvm.float
     %result64 = std.tanh %arg_f64 : f64
-    // CHECK: llvm.call @_ocml_tanh_f64(%{{.*}}) : (!llvm.double) -> !llvm.double
+    // CHECK: llvm.call @__ocml_tanh_f64(%{{.*}}) : (!llvm.double) -> !llvm.double
     std.return
   }
 }
 
 // -----
 gpu.module @kernel_module {
-  // CHECK: llvm.func @_ocml_exp_f32(!llvm.float) -> !llvm.float
-  // CHECK: llvm.func @_ocml_exp_f64(!llvm.double) -> !llvm.double
+  // CHECK: llvm.func @__ocml_exp_f32(!llvm.float) -> !llvm.float
+  // CHECK: llvm.func @__ocml_exp_f64(!llvm.double) -> !llvm.double
   // CHECK-LABEL: func @gpu_exp
   func @gpu_exp(%arg_f32 : f32, %arg_f64 : f64) {
     %exp_f32 = std.exp %arg_f32 : f32
-    // CHECK: llvm.call @_ocml_exp_f32(%{{.*}}) : (!llvm.float) -> !llvm.float
+    // CHECK: llvm.call @__ocml_exp_f32(%{{.*}}) : (!llvm.float) -> !llvm.float
     %result_f32 = std.exp %exp_f32 : f32
-    // CHECK: llvm.call @_ocml_exp_f32(%{{.*}}) : (!llvm.float) -> !llvm.float
+    // CHECK: llvm.call @__ocml_exp_f32(%{{.*}}) : (!llvm.float) -> !llvm.float
     %result64 = std.exp %arg_f64 : f64
-    // CHECK: llvm.call @_ocml_exp_f64(%{{.*}}) : (!llvm.double) -> !llvm.double
+    // CHECK: llvm.call @__ocml_exp_f64(%{{.*}}) : (!llvm.double) -> !llvm.double
     std.return
   }
 }
 
 
 // -----
 
 // Test that we handled properly operation with SymbolTable other than module op
 gpu.module @kernel_module {
   "test.symbol_scope"() ({
     // CHECK: test.symbol_scope
-    // CHECK: llvm.func @_ocml_exp_f32(!llvm.float) -> !llvm.float
-    // CHECK: llvm.func @_ocml_exp_f64(!llvm.double) -> !llvm.double
+    // CHECK: llvm.func @__ocml_exp_f32(!llvm.float) -> !llvm.float
+    // CHECK: llvm.func @__ocml_exp_f64(!llvm.double) -> !llvm.double
     // CHECK-LABEL: func @gpu_exp
     func @gpu_exp(%arg_f32 : f32, %arg_f64 : f64) {
       %exp_f32 = std.exp %arg_f32 : f32
-      // CHECK: llvm.call @_ocml_exp_f32(%{{.*}}) : (!llvm.float) -> !llvm.float
+      // CHECK: llvm.call @__ocml_exp_f32(%{{.*}}) : (!llvm.float) -> !llvm.float
       %result_f32 = std.exp %exp_f32 : f32
-      // CHECK: llvm.call @_ocml_exp_f32(%{{.*}}) : (!llvm.float) -> !llvm.float
+      // CHECK: llvm.call @__ocml_exp_f32(%{{.*}}) : (!llvm.float) -> !llvm.float
       %result64 = std.exp %arg_f64 : f64
-      // CHECK: llvm.call @_ocml_exp_f64(%{{.*}}) : (!llvm.double) -> !llvm.double
+      // CHECK: llvm.call @__ocml_exp_f64(%{{.*}}) : (!llvm.double) -> !llvm.double
       std.return
     }
     "test.finish" () : () -> ()
   }) : () -> ()
 }