[mlir][math] Split off the math dialect.

[herhut]

Summary

This does not split transformations, yet. Those will be done as future clean ups.

RFC in https://llvm.discourse.group/t/rfc-split-the-math-dialect-from-std/

[ftynse]

Thanks!

mlir/include/mlir/Dialect/Linalg/EDSC/FoldedIntrinsics.h

59–60

Nit: keep dialect prefixes sorted

mlir/include/mlir/Dialect/Math/IR/MathOps.td

2

copy-pasta

mlir/include/mlir/Dialect/Math/Transforms/Passes.h

10–11

Copy-pasta of copy-pasta

mlir/lib/Conversion/StandardToSPIRV/StandardToSPIRV.cpp

1136

Nit: we drop usernames in LLVM

mlir/test/lib/Transforms/TestExpandTanh.cpp

1–2

Something went wrong here

[herhut]

Fix formatting issues.

[herhut]

Added missing tests

[herhut]

Thanks for the review!

[herhut]

Implement inlining interface

mlir/include/mlir/Dialect/CMakeLists.txt

 add_subdirectory(Affine)
 add_subdirectory(Async)
 add_subdirectory(ArmNeon)
 add_subdirectory(ArmSVE)
 add_subdirectory(AVX512)
 add_subdirectory(Complex)
 add_subdirectory(GPU)
+add_subdirectory(Math)
 add_subdirectory(Linalg)
 add_subdirectory(LLVMIR)
 add_subdirectory(OpenACC)
 add_subdirectory(OpenMP)
 add_subdirectory(PDL)
 add_subdirectory(PDLInterp)
 add_subdirectory(Quant)
 add_subdirectory(SCF)
 add_subdirectory(Shape)
 add_subdirectory(SPIRV)
 add_subdirectory(StandardOps)
 add_subdirectory(Tensor)
 add_subdirectory(Tosa)
 add_subdirectory(Vector)

mlir/include/mlir/Dialect/Linalg/EDSC/FoldedIntrinsics.h

 //===- FoldedIntrinsics.h - MLIR EDSC Intrinsics for Linalg -----*- C++ -*-===//
 //
 // 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-2.0 WITH LLVM-exception
 //
 //===----------------------------------------------------------------------===//
 #ifndef MLIR_DIALECT_LINALG_EDSC_FOLDEDINTRINSICS_H_
 #define MLIR_DIALECT_LINALG_EDSC_FOLDEDINTRINSICS_H_
 
 #include "mlir/Dialect/Linalg/EDSC/Builders.h"
 #include "mlir/Dialect/Linalg/EDSC/Intrinsics.h"
+#include "mlir/Dialect/Math/IR/Math.h"
 #include "mlir/Dialect/Tensor/IR/Tensor.h"
 
 #include "mlir/Transforms/FoldUtils.h"
 
 namespace mlir {
 namespace edsc {
 namespace intrinsics {
 
 template <typename Op>
 struct FoldedValueBuilder {
   // Builder-based
   template <typename... Args>
   FoldedValueBuilder(OperationFolder *folder, Args... args) {
     value = folder ? folder->create<Op>(ScopedContext::getBuilderRef(),
                                         ScopedContext::getLocation(), args...)
                    : ScopedContext::getBuilderRef().create<Op>(
                          ScopedContext::getLocation(), args...);
   }
 
   operator Value() { return value; }
   Value value;
 };
 
+using folded_math_tanh = FoldedValueBuilder<math::TanhOp>;
 using folded_std_constant_index = FoldedValueBuilder<ConstantIndexOp>;
 using folded_std_constant_float = FoldedValueBuilder<ConstantFloatOp>;
 using folded_std_constant_int = FoldedValueBuilder<ConstantIntOp>;
 using folded_std_constant = FoldedValueBuilder<ConstantOp>;
 using folded_std_dim = FoldedValueBuilder<DimOp>;
 using folded_std_muli = FoldedValueBuilder<MulIOp>;
 using folded_std_addi = FoldedValueBuilder<AddIOp>;
 using folded_std_addf = FoldedValueBuilder<AddFOp>;
 using folded_std_alloc = FoldedValueBuilder<AllocOp>;
 using folded_std_constant = FoldedValueBuilder<ConstantOp>;
 using folded_std_constant_float = FoldedValueBuilder<ConstantFloatOp>;
 using folded_std_constant_index = FoldedValueBuilder<ConstantIndexOp>;
 using folded_std_constant_int = FoldedValueBuilder<ConstantIntOp>;
 using folded_std_dim = FoldedValueBuilder<DimOp>;
 using folded_std_index_cast = FoldedValueBuilder<IndexCastOp>;
 using folded_std_muli = FoldedValueBuilder<MulIOp>;
 using folded_std_mulf = FoldedValueBuilder<MulFOp>;
 using folded_std_memref_cast = FoldedValueBuilder<MemRefCastOp>;
 using folded_std_select = FoldedValueBuilder<SelectOp>;
 using folded_std_load = FoldedValueBuilder<LoadOp>;
 using folded_std_subi = FoldedValueBuilder<SubIOp>;
 using folded_std_sub_view = FoldedValueBuilder<SubViewOp>;
-using folded_std_tanh = FoldedValueBuilder<TanhOp>;
 using folded_std_tensor_load = FoldedValueBuilder<TensorLoadOp>;
 using folded_std_view = FoldedValueBuilder<ViewOp>;
 using folded_std_zero_extendi = FoldedValueBuilder<ZeroExtendIOp>;
 using folded_std_sign_extendi = FoldedValueBuilder<SignExtendIOp>;
 using folded_tensor_extract = FoldedValueBuilder<tensor::ExtractOp>;
 } // namespace intrinsics
 } // namespace edsc
 } // namespace mlir
 
 #endif // MLIR_DIALECT_LINALG_EDSC_FOLDEDINTRINSICS_H_

mlir/include/mlir/Dialect/Math/CMakeLists.txt

+add_subdirectory(IR)

mlir/include/mlir/Dialect/Math/EDSC/Intrinsics.h

+//===- Intrinsics.h - MLIR EDSC Intrinsics for Math ops ---------*- C++ -*-===//
+//
+// 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-2.0 WITH LLVM-exception
+//
+//===----------------------------------------------------------------------===//
+#ifndef MLIR_DIALECT_MATH_EDSC_INTRINSICS_H_
+#define MLIR_DIALECT_MATH_EDSC_INTRINSICS_H_
+
+#include "mlir/Dialect/Math/IR/Math.h"
+#include "mlir/EDSC/Builders.h"
+
+namespace mlir {
+namespace edsc {
+namespace intrinsics {
+
+using math_rsqrt = ValueBuilder<math::RsqrtOp>;
+using math_tanh = ValueBuilder<math::TanhOp>;
+
+} // namespace intrinsics
+} // namespace edsc
+} // namespace mlir
+
+#endif // MLIR_DIALECT_MATH_EDSC_INTRINSICS_H_

mlir/include/mlir/Dialect/Math/IR/CMakeLists.txt

+add_mlir_dialect(MathOps math)
+add_mlir_doc(MathOps -gen-dialect-doc MathOps Dialects/)

mlir/include/mlir/Dialect/Math/IR/Math.h

+//===- Math.h - Math dialect --------------------------------------*- C++-*-==//
+//
+// 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-2.0 WITH LLVM-exception
+//
+//===----------------------------------------------------------------------===//
+
+#ifndef MLIR_DIALECT_MATH_IR_MATH_H_
+#define MLIR_DIALECT_MATH_IR_MATH_H_
+
+#include "mlir/IR/BuiltinTypes.h"
+#include "mlir/IR/Dialect.h"
+#include "mlir/IR/OpDefinition.h"
+#include "mlir/IR/OpImplementation.h"
+#include "mlir/Interfaces/SideEffectInterfaces.h"
+#include "mlir/Interfaces/VectorInterfaces.h"
+
+//===----------------------------------------------------------------------===//
+// Math Dialect
+//===----------------------------------------------------------------------===//
+
+#include "mlir/Dialect/Math/IR/MathOpsDialect.h.inc"
+
+//===----------------------------------------------------------------------===//
+// Math Dialect Operations
+//===----------------------------------------------------------------------===//
+
+#define GET_OP_CLASSES
+#include "mlir/Dialect/Math/IR/MathOps.h.inc"
+
+#endif // MLIR_DIALECT_MATH_IR_MATH_H_

mlir/include/mlir/Dialect/Math/IR/MathBase.td

+//===- MathBase.td - Base definitions for math dialect ------*- tablegen -*-==//
+//
+// 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-2.0 WITH LLVM-exception
+//
+//===----------------------------------------------------------------------===//
+#ifndef MATH_BASE
+#define MATH_BASE
+include "mlir/IR/OpBase.td"
+def Math_Dialect : Dialect {
+  let name = "math";
+  let cppNamespace = "::mlir::math";
+  let description = [{
+    The math dialect is intended to hold mathematical operations on integer and
+    floating type beyond simple arithmetics.
+  }];
+}
+#endif // MATH_BASE

mlir/include/mlir/Dialect/Math/IR/MathOps.td

+//===- MathOps.td - Math op definitions --------------------*- tablegen -*-===//
+//
+// 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-2.0 WITH LLVM-exception
+//
+//===----------------------------------------------------------------------===//
+
+#ifndef MATH_OPS
+#define MATH_OPS
+
+include "mlir/Dialect/Math/IR/MathBase.td"
+include "mlir/Interfaces/VectorInterfaces.td"
+include "mlir/Interfaces/SideEffectInterfaces.td"
+
+class MathOp<string mnemonic, list<OpTrait> traits = []>
+    : Op<Math_Dialect, mnemonic, traits # [NoSideEffect]>;
+
+class FloatUnaryOp<string mnemonic, list<OpTrait> traits = []> :
+    MathOp<mnemonic,
+      traits # [DeclareOpInterfaceMethods<VectorUnrollOpInterface>,
+                ElementwiseMappable,
+                SameOperandsAndResultType]> {
+  let arguments = (ins FloatLike:$operand);
+
+  let results = (outs FloatLike:$result);
+
+  let assemblyFormat = "$operand attr-dict `:` type($result)";
+}
+
+class FloatBinaryOp<string mnemonic, list<OpTrait> traits = []> :
+    MathOp<mnemonic,
+      traits # [DeclareOpInterfaceMethods<VectorUnrollOpInterface>,
+                ElementwiseMappable,
+                SameOperandsAndResultType]> {
+  let arguments = (ins FloatLike:$lhs, FloatLike:$rhs);
+  let results = (outs FloatLike:$result);
+
+  let assemblyFormat = "$lhs `,` $rhs attr-dict `:` type($result)";
+}
+
+//===----------------------------------------------------------------------===//
+// AtanOp
+//===----------------------------------------------------------------------===//
+
+def AtanOp : FloatUnaryOp<"atan">{
+  let summary = "arcus tangent of the given value";
+  let description = [{
+    Syntax:
+
+    ```
+    operation ::= ssa-id `=` `math.atan` ssa-use `:` type
+    ```
+
+    The `atan` operation computes the arcus tangent of a given value.  It takes
+    one operand and returns one result of the same type.  This type may be a
+    float scalar type, a vector whose element type is float, or a tensor of
+    floats.  It has no standard attributes.
+
+    Example:
+
+    ```mlir
+    // Arcus tangent of scalar value.
+    %a = math.atan %b : f64
+
+    // SIMD vector element-wise arcus tangent.
+    %f = math.atan %g : vector<4xf32>
+
+    // Tensor element-wise arcus tangent.
+    %x = math.atan %y : tensor<4x?xf8>
+    ```
+  }];
+}
+
+//===----------------------------------------------------------------------===//
+// Atan2Op
+//===----------------------------------------------------------------------===//
+
+def Atan2Op : FloatBinaryOp<"atan2">{
+  let summary = "2-argument arcus tangent of the given values";
+  let description = [{
+    Syntax:
+
+    ```
+    operation ::= ssa-id `=` `math.atan2` ssa-use `,` ssa-use `:` type
+    ```
+
+    The `atan2` operation takes two operands and returns one result, all of
+    which must be of the same type.  This type may be a floating point scalar
+    type, a vector whose element type is a floating point type, or a floating
+    point tensor.
+
+    The 2-argument arcus tangent `atan2(y, x)` returns the angle in the
+    Euclidian plane between the positive x-axis and the ray through the point
+    (x, y).  It is a generalization of the 1-argument arcus tangent which
+    returns the angle on the basis of the ratio y/x.
+
+    See also https://en.wikipedia.org/wiki/Atan2
+
+    Example:
+
+    ```mlir
+    // Scalar variant.
+    %a = math.atan2 %b, %c : f32
+
+    // SIMD vector variant.
+    %f = math.atan2 %g, %h : vector<4xf32>
+
+    // Tensor variant.
+    %x = math.atan2 %y, %z : tensor<4x?xf32>
+    ```
+  }];
+}
+
+//===----------------------------------------------------------------------===//
+// CosOp
+//===----------------------------------------------------------------------===//
+
+def CosOp : FloatUnaryOp<"cos"> {
+  let summary = "cosine of the specified value";
+  let description = [{
+    Syntax:
+
+    ```
+    operation ::= ssa-id `=` `math.cos` ssa-use `:` type
+    ```
+
+    The `cos` operation computes the cosine of a given value. It takes one
+    operand and returns one result of the same type. This type may be a float
+    scalar type, a vector whose element type is float, or a tensor of floats.
+    It has no standard attributes.
+
+    Example:
+
+    ```mlir
+    // Scalar cosine value.
+    %a = math.cos %b : f64
+
+    // SIMD vector element-wise cosine value.
+    %f = math.cos %g : vector<4xf32>
+
+    // Tensor element-wise cosine value.
+    %x = math.cos %y : tensor<4x?xf8>
+    ```
+  }];
+}
+
+//===----------------------------------------------------------------------===//
+// SinOp
+//===----------------------------------------------------------------------===//
+
+def SinOp : FloatUnaryOp<"sin"> {
+  let summary = "sine of the specified value";
+  let description = [{
+    Syntax:
+
+    ```
+    operation ::= ssa-id `=` `math.sin` ssa-use `:` type
+    ```
+
+    The `sin` operation computes the sine of a given value. It takes one
+    operand and returns one result of the same type. This type may be a float
+    scalar type, a vector whose element type is float, or a tensor of floats.
+    It has no standard attributes.
+
+    Example:
+
+    ```mlir
+    // Scalar sine value.
+    %a = math.sin %b : f64
+
+    // SIMD vector element-wise sine value.
+    %f = math.sin %g : vector<4xf32>
+
+    // Tensor element-wise sine value.
+    %x = math.sin %y : tensor<4x?xf8>
+    ```
+  }];
+}
+
+
+//===----------------------------------------------------------------------===//
+// ExpOp
+//===----------------------------------------------------------------------===//
+
+def ExpOp : FloatUnaryOp<"exp"> {
+  let summary = "base-e exponential of the specified value";
+  let description = [{
+    Syntax:
+
+    ```
+    operation ::= ssa-id `=` `math.exp` ssa-use `:` type
+    ```
+
+    The `exp` operation takes one operand and returns one result of the same
+    type. This type may be a float scalar type, a vector whose element type is
+    float, or a tensor of floats. It has no standard attributes.
+
+    Example:
+
+    ```mlir
+    // Scalar natural exponential.
+    %a = math.exp %b : f64
+
+    // SIMD vector element-wise natural exponential.
+    %f = math.exp %g : vector<4xf32>
+
+    // Tensor element-wise natural exponential.
+    %x = math.exp %y : tensor<4x?xf8>
+    ```
+  }];
+}
+
+//===----------------------------------------------------------------------===//
+// Exp2Op
+//===----------------------------------------------------------------------===//
+
+def Exp2Op : FloatUnaryOp<"exp2"> {
+  let summary = "base-2 exponential of the specified value";
+
+  let description = [{
+    Syntax:
+
+    ```
+    operation ::= ssa-id `=` `math.exp2` ssa-use `:` type
+    ```
+
+    The `exp` operation takes one operand and returns one result of the same
+    type. This type may be a float scalar type, a vector whose element type is
+    float, or a tensor of floats. It has no standard attributes.
+
+    Example:
+
+    ```mlir
+    // Scalar natural exponential.
+    %a = math.exp2 %b : f64
+
+    // SIMD vector element-wise natural exponential.
+    %f = math.exp2 %g : vector<4xf32>
+
+    // Tensor element-wise natural exponential.
+    %x = math.exp2 %y : tensor<4x?xf8>
+    ```
+  }];
+}
+
+//===----------------------------------------------------------------------===//
+// LogOp
+//===----------------------------------------------------------------------===//
+
+def LogOp : FloatUnaryOp<"log"> {
+  let summary = "base-e logarithm of the specified value";
+
+  let description = [{
+    Computes the base-e logarithm of the given value. It takes one operand and
+    returns one result of the same type.
+
+    Example:
+
+    ```mlir
+    %y = math.log %x : f64
+    ```
+  }];
+}
+
+//===----------------------------------------------------------------------===//
+// Log10Op
+//===----------------------------------------------------------------------===//
+
+def Log10Op : FloatUnaryOp<"log10"> {
+  let summary = "base-10 logarithm of the specified value";
+
+  let description = [{
+    Computes the base-10 logarithm of the given value. It takes one operand and
+    returns one result of the same type.
+
+    Example:
+
+    ```mlir
+    %y = math.log10 %x : f64
+    ```
+  }];
+}
+
+//===----------------------------------------------------------------------===//
+// Log1pOp
+//===----------------------------------------------------------------------===//
+
+def Log1pOp : FloatUnaryOp<"log1p"> {
+  let summary = "Computes the natural logarithm of one plus the given value";
+
+  let description = [{
+    Computes the base-e logarithm of one plus the given value. It takes one
+    operand and returns one result of the same type.
+
+    log1p(x) := log(1 + x)
+
+    Example:
+
+    ```mlir
+    %y = math.log1p %x : f64
+    ```
+  }];
+}
+
+//===----------------------------------------------------------------------===//
+// Log2Op
+//===----------------------------------------------------------------------===//
+
+def Log2Op : FloatUnaryOp<"log2"> {
+  let summary = "base-2 logarithm of the specified value";
+
+  let description = [{
+    Computes the base-2 logarithm of the given value. It takes one operand and
+    returns one result of the same type.
+
+    Example:
+
+    ```mlir
+    %y = math.log2 %x : f64
+    ```
+  }];
+}
+
+//===----------------------------------------------------------------------===//
+// PowFOp
+//===----------------------------------------------------------------------===//
+
+def PowFOp : FloatBinaryOp<"powf"> {
+  let summary = "floating point raised to the power of operation";
+  let description = [{
+    Syntax:
+
+    ```
+    operation ::= ssa-id `=` `math.powf` ssa-use `,` ssa-use `:` type
+    ```
+
+    The `powf` operation takes two operands and returns one result, each of
+    these is required to be the same type. This type may be a floating point
+    scalar type, a vector whose element type is a floating point type, or a
+    floating point tensor.
+
+    Example:
+
+    ```mlir
+    // Scalar exponentiation.
+    %a = math.powf %b, %c : f64
+
+    // SIMD pointwise vector exponentiation
+    %f = math.powf %g, %h : vector<4xf32>
+
+    // Tensor pointwise exponentiation.
+    %x = math.powf %y, %z : tensor<4x?xbf16>
+    ```
+  }];
+}
+
+//===----------------------------------------------------------------------===//
+// RsqrtOp
+//===----------------------------------------------------------------------===//
+
+def RsqrtOp : FloatUnaryOp<"rsqrt"> {
+  let summary = "reciprocal of sqrt (1 / sqrt of the specified value)";
+  let description = [{
+    The `rsqrt` operation computes the reciprocal of the square root. It takes
+    one operand and returns one result of the same type. This type may be a
+    float scalar type, a vector whose element type is float, or a tensor of
+    floats. It has no standard attributes.
+  }];
+}
+
+//===----------------------------------------------------------------------===//
+// SqrtOp
+//===----------------------------------------------------------------------===//
+
+def SqrtOp : FloatUnaryOp<"sqrt"> {
+  let summary = "sqrt of the specified value";
+  let description = [{
+    The `sqrt` operation computes the square root. It takes one operand and
+    returns one result of the same type. This type may be a float scalar type, a
+    vector whose element type is float, or a tensor of floats. It has no standard
+    attributes.
+
+    Example:
+
+    ```mlir
+    // Scalar square root value.
+    %a = math.sqrt %b : f64
+    // SIMD vector element-wise square root value.
+    %f = math.sqrt %g : vector<4xf32>
+    // Tensor element-wise square root value.
+    %x = math.sqrt %y : tensor<4x?xf32>
+    ```
+  }];
+}
+
+//===----------------------------------------------------------------------===//
+// TanhOp
+//===----------------------------------------------------------------------===//
+
+def TanhOp : FloatUnaryOp<"tanh"> {
+  let summary = "hyperbolic tangent of the specified value";
+  let description = [{
+    Syntax:
+
+    ```
+    operation ::= ssa-id `=` `std.tanh` ssa-use `:` type
+    ```
+
+    The `tanh` operation computes the hyperbolic tangent. It takes one operand
+    and returns one result of the same type. This type may be a float scalar
+    type, a vector whose element type is float, or a tensor of floats. It has
+    no standard attributes.
+
+    Example:
+
+    ```mlir
+    // Scalar hyperbolic tangent value.
+    %a = math.tanh %b : f64
+
+    // SIMD vector element-wise hyperbolic tangent value.
+    %f = math.tanh %g : vector<4xf32>
+
+    // Tensor element-wise hyperbolic tangent value.
+    %x = math.tanh %y : tensor<4x?xf8>
+    ```
+  }];
+}
+
+#endif // MATH_OPS

mlir/include/mlir/Dialect/Math/Transforms/Passes.h

+//===- Passes.h - Pass Entrypoints ------------------------------*- C++ -*-===//
+//
+// 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-2.0 WITH LLVM-exception
+//
+//===----------------------------------------------------------------------===//
+
+#ifndef MLIR_DIALECT_MATH_TRANSFORMS_PASSES_H_
+#define MLIR_DIALECT_MATH_TRANSFORMS_PASSES_H_
+
+#include "mlir/Pass/Pass.h"
+#include "mlir/Transforms/Bufferize.h"
+
+namespace mlir {
+
+class OwningRewritePatternList;
+
+void populateExpandTanhPattern(OwningRewritePatternList &patterns,
+                               MLIRContext *ctx);
+
+} // namespace mlir
+
+#endif // MLIR_DIALECT_MATH_TRANSFORMS_PASSES_H_

mlir/include/mlir/Dialect/StandardOps/EDSC/Intrinsics.h

 using std_dim = ValueBuilder<DimOp>;
 using std_fpext = ValueBuilder<FPExtOp>;
 using std_fptrunc = ValueBuilder<FPTruncOp>;
 using std_index_cast = ValueBuilder<IndexCastOp>;
 using std_muli = ValueBuilder<MulIOp>;
 using std_mulf = ValueBuilder<MulFOp>;
 using std_memref_cast = ValueBuilder<MemRefCastOp>;
 using std_ret = OperationBuilder<ReturnOp>;
-using std_rsqrt = ValueBuilder<RsqrtOp>;
 using std_select = ValueBuilder<SelectOp>;
 using std_load = ValueBuilder<LoadOp>;
 using std_sign_extendi = ValueBuilder<SignExtendIOp>;
 using std_splat = ValueBuilder<SplatOp>;
 using std_store = OperationBuilder<StoreOp>;
 using std_subf = ValueBuilder<SubFOp>;
 using std_subi = ValueBuilder<SubIOp>;
 using std_sub_view = ValueBuilder<SubViewOp>;
-using std_tanh = ValueBuilder<TanhOp>;
 using std_tensor_load = ValueBuilder<TensorLoadOp>;
 using std_tensor_store = OperationBuilder<TensorStoreOp>;
 using std_view = ValueBuilder<ViewOp>;
 using std_zero_extendi = ValueBuilder<ZeroExtendIOp>;
 using tensor_extract = ValueBuilder<tensor::ExtractOp>;
 
 template <int N>
 struct SExtiValueBuilder : public ValueBuilder<SignExtendIOp> {

mlir/include/mlir/Dialect/StandardOps/IR/Ops.td

def AssumeAlignmentOp : Std_Op<"assume_alignment"> {
   let arguments = (ins AnyMemRef:$memref,
                        Confined<I32Attr, [IntPositive]>:$alignment);
   let results = (outs);
 
   let assemblyFormat = "$memref `,` $alignment attr-dict `:` type($memref)";
 }
 
 //===----------------------------------------------------------------------===//
-// AtanOp
-//===----------------------------------------------------------------------===//
-
-def AtanOp : FloatUnaryOp<"atan", []>{
-  let summary = "arcus tangent of the given value";
-  let description = [{
-    Syntax:
-
-    ```
-    operation ::= ssa-id `=` `std.atan` ssa-use `:` type
-    ```
-
-    The `atan` operation computes the arcus tangent of a given value.  It takes
-    one operand and returns one result of the same type.  This type may be a
-    float scalar type, a vector whose element type is float, or a tensor of
-    floats.  It has no standard attributes.
-
-    Example:
-
-    ```mlir
-    // Arcus tangent of scalar value.
-    %a = atan %b : f64
-
-    // SIMD vector element-wise arcus tangent.
-    %f = atan %g : vector<4xf32>
-
-    // Tensor element-wise arcus tangent.
-    %x = atan %y : tensor<4x?xf8>
-    ```
-  }];
-}
-
-//===----------------------------------------------------------------------===//
-// Atan2Op
-//===----------------------------------------------------------------------===//
-
-def Atan2Op : FloatArithmeticOp<"atan2">{
-  let summary = "2-argument arcus tangent of the given values";
-  let description = [{
-    Syntax:
-
-    ```
-    operation ::= ssa-id `=` `std.atan2` ssa-use `,` ssa-use `:` type
-    ```
-
-    The `atan2` operation takes two operands and returns one result, all of
-    which must be of the same type.  This type may be a floating point scalar
-    type, a vector whose element type is a floating point type, or a floating
-    point tensor.
-
-    The 2-argument arcus tangent `atan2(y, x)` returns the angle in the
-    Euclidian plane between the positive x-axis and the ray through the point
-    (x, y).  It is a generalization of the 1-argument arcus tangent which
-    returns the angle on the basis of the ratio y/x.
-
-    See also https://en.wikipedia.org/wiki/Atan2
-
-    Example:
-
-    ```mlir
-    // Scalar variant.
-    %a = atan2 %b, %c : f32
-
-    // SIMD vector variant.
-    %f = atan2 %g, %h : vector<4xf32>
-
-    // Tensor variant.
-    %x = atan2 %y, %z : tensor<4x?xf32>
-    ```
-  }];
-}
-
-//===----------------------------------------------------------------------===//
 // AtomicRMWOp
 //===----------------------------------------------------------------------===//
 
 def AtomicRMWOp : Std_Op<"atomic_rmw", [
       AllTypesMatch<["value", "result"]>,
       TypesMatchWith<"value type matches element type of memref",
                      "memref", "value",
                      "$_self.cast<MemRefType>().getElementType()">
let description = [{
 
     // Tensor element-wise copysign value.
     %x = copysign %y, %z : tensor<4x?xf8>
     ```
   }];
 }
 
 //===----------------------------------------------------------------------===//
-// CosOp
-//===----------------------------------------------------------------------===//
-
-def CosOp : FloatUnaryOp<"cos"> {
-  let summary = "cosine of the specified value";
-  let description = [{
-    Syntax:
-
-    ```
-    operation ::= ssa-id `=` `std.cos` ssa-use `:` type
-    ```
-
-    The `cos` operation computes the cosine of a given value. It takes one
-    operand and returns one result of the same type. This type may be a float
-    scalar type, a vector whose element type is float, or a tensor of floats.
-    It has no standard attributes.
-
-    Example:
-
-    ```mlir
-    // Scalar cosine value.
-    %a = cos %b : f64
-
-    // SIMD vector element-wise cosine value.
-    %f = cos %g : vector<4xf32>
-
-    // Tensor element-wise cosine value.
-    %x = cos %y : tensor<4x?xf8>
-    ```
-  }];
-}
-
-//===----------------------------------------------------------------------===//
-// SinOp
-//===----------------------------------------------------------------------===//
-
-def SinOp : FloatUnaryOp<"sin"> {
-  let summary = "sine of the specified value";
-  let description = [{
-    Syntax:
-
-    ```
-    operation ::= ssa-id `=` `std.sin` ssa-use `:` type
-    ```
-
-    The `sin` operation computes the sine of a given value. It takes one
-    operand and returns one result of the same type. This type may be a float
-    scalar type, a vector whose element type is float, or a tensor of floats.
-    It has no standard attributes.
-
-    Example:
-
-    ```mlir
-    // Scalar sine value.
-    %a = sin %b : f64
-
-    // SIMD vector element-wise sine value.
-    %f = sin %g : vector<4xf32>
-
-    // Tensor element-wise sine value.
-    %x = sin %y : tensor<4x?xf8>
-    ```
-  }];
-}
-
-//===----------------------------------------------------------------------===//
 // DeallocOp
 //===----------------------------------------------------------------------===//
 
 def DeallocOp : Std_Op<"dealloc", [MemRefsNormalizable]> {
   let summary = "memory deallocation operation";
   let description = [{
     The `dealloc` operation frees the region of memory referenced by a memref
     which was originally created by the `alloc` operation.

 //===----------------------------------------------------------------------===//
 
 def DivFOp : FloatArithmeticOp<"divf"> {
   let summary = "floating point division operation";
   let hasFolder = 1;
 }
 
 //===----------------------------------------------------------------------===//
-// ExpOp
-//===----------------------------------------------------------------------===//
-
-def ExpOp : FloatUnaryOp<"exp"> {
-  let summary = "base-e exponential of the specified value";
-  let description = [{
-    Syntax:
-
-    ```
-    operation ::= ssa-id `=` `std.exp` ssa-use `:` type
-    ```
-
-    The `exp` operation takes one operand and returns one result of the same
-    type. This type may be a float scalar type, a vector whose element type is
-    float, or a tensor of floats. It has no standard attributes.
-
-    Example:
-
-    ```mlir
-    // Scalar natural exponential.
-    %a = exp %b : f64
-
-    // SIMD vector element-wise natural exponential.
-    %f = exp %g : vector<4xf32>
-
-    // Tensor element-wise natural exponential.
-    %x = exp %y : tensor<4x?xf8>
-    ```
-  }];
-}
-
-//===----------------------------------------------------------------------===//
-// ExpOp
-//===----------------------------------------------------------------------===//
-
-def Exp2Op : FloatUnaryOp<"exp2"> {
-  let summary = "base-2 exponential of the specified value";
-}
-
-//===----------------------------------------------------------------------===//
 // FPExtOp
 //===----------------------------------------------------------------------===//
 
 def FPExtOp : ArithmeticCastOp<"fpext">, Arguments<(ins AnyType:$in)> {
   let summary = "cast from floating-point to wider floating-point";
   let description = [{
     Cast a floating-point value to a larger floating-point-typed value.
     The destination type must to be strictly wider than the source type.
def LoadOp : Std_Op<"load",
 
   let hasCanonicalizer = 1;
   let hasFolder = 1;
 
   let assemblyFormat = "$memref `[` $indices `]` attr-dict `:` type($memref)";
 }
 
 //===----------------------------------------------------------------------===//
-// LogOp
-//===----------------------------------------------------------------------===//
-
-def LogOp : FloatUnaryOp<"log"> {
-  let summary = "base-e logarithm of the specified value";
-}
-
-//===----------------------------------------------------------------------===//
-// Log10Op
-//===----------------------------------------------------------------------===//
-
-def Log10Op : FloatUnaryOp<"log10"> {
-  let summary = "base-10 logarithm of the specified value";
-}
-
-//===----------------------------------------------------------------------===//
-// Log1pOp
-//===----------------------------------------------------------------------===//
-
-def Log1pOp : FloatUnaryOp<"log1p"> {
-  let summary = "Computes the natural logarithm of one plus the given value";
-
-  let description = [{
-    Computes the base-e logarithm of one plus the given value. It takes one
-    operand and returns one result of the same type.
-
-    log1p(x) := log(1 + x)
-
-    Example:
-
-    ```mlir
-    %y = log1p %x : f64
-    ```
-  }];
-}
-
-//===----------------------------------------------------------------------===//
-// Log2Op
-//===----------------------------------------------------------------------===//
-
-def Log2Op : FloatUnaryOp<"log2"> {
-  let summary = "base-2 logarithm of the specified value";
-}
-
-//===----------------------------------------------------------------------===//
 // MemRefCastOp
 //===----------------------------------------------------------------------===//
 
 def MemRefCastOp : CastOp<"memref_cast", [
     DeclareOpInterfaceMethods<ViewLikeOpInterface>
   ]> {
   let summary = "memref cast operation";
   let description = [{
let description = [{
     // Tensor element-wise bitwise integer or.
     %x = or %y, %z : tensor<4x?xi8>
     ```
   }];
   let hasFolder = 1;
 }
 
 //===----------------------------------------------------------------------===//
-// PowFOp
-//===----------------------------------------------------------------------===//
-
-def PowFOp : FloatArithmeticOp<"powf"> {
-  let summary = "floating point raised to the power of operation";
-  let description = [{
-    Syntax:
-
-    ```
-    operation ::= ssa-id `=` `std.powf` ssa-use `,` ssa-use `:` type
-    ```
-
-    The `powf` operation takes two operands and returns one result, each of
-    these is required to be the same type. This type may be a floating point
-    scalar type, a vector whose element type is a floating point type, or a
-    floating point tensor.
-
-    Example:
-
-    ```mlir
-    // Scalar exponentiation.
-    %a = powf %b, %c : f64
-
-    // SIMD pointwise vector exponentiation
-    %f = powf %g, %h : vector<4xf32>
-
-    // Tensor pointwise exponentiation.
-    %x = powf %y, %z : tensor<4x?xbf16>
-    ```
-  }];
-}
-
-//===----------------------------------------------------------------------===//
 // PrefetchOp
 //===----------------------------------------------------------------------===//
 
 def PrefetchOp : Std_Op<"prefetch"> {
   let summary = "prefetch operation";
   let description = [{
     The "prefetch" op prefetches data from a memref location described with
     subscript indices similar to std.load, and with three attributes: a
def ReturnOp : Std_Op<"return", [NoSideEffect, HasParent<"FuncOp">,
   let builders = [
     OpBuilderDAG<(ins),
     [{ build($_builder, $_state, llvm::None); }]>];
 
   let assemblyFormat = "attr-dict ($operands^ `:` type($operands))?";
 }
 
 //===----------------------------------------------------------------------===//
-// RsqrtOp
-//===----------------------------------------------------------------------===//
-
-def RsqrtOp : FloatUnaryOp<"rsqrt"> {
-  let summary = "reciprocal of sqrt (1 / sqrt of the specified value)";
-  let description = [{
-    The `rsqrt` operation computes the reciprocal of the square root. It takes
-    one operand and returns one result of the same type. This type may be a
-    float scalar type, a vector whose element type is float, or a tensor of
-    floats. It has no standard attributes.
-  }];
-}
-
-//===----------------------------------------------------------------------===//
 // SelectOp
 //===----------------------------------------------------------------------===//
 
 def SelectOp : Std_Op<"select", [NoSideEffect,
      AllTypesMatch<["true_value", "false_value", "result"]>,
      ElementwiseMappable, DeclareOpInterfaceMethods<VectorUnrollOpInterface>]> {
   let summary = "select operation";
   let description = [{
let builders = [
     [{ build($_builder, $_state, aggregateType, element); }]>];
 
   let hasFolder = 1;
 
   let assemblyFormat = "$input attr-dict `:` type($aggregate)";
 }
 
 //===----------------------------------------------------------------------===//
-// SqrtOp
-//===----------------------------------------------------------------------===//
-
-def SqrtOp : FloatUnaryOp<"sqrt"> {
-  let summary = "sqrt of the specified value";
-  let description = [{
-    The `sqrt` operation computes the square root. It takes one operand and
-    returns one result of the same type. This type may be a float scalar type, a
-    vector whose element type is float, or a tensor of floats. It has no standard
-    attributes.
-
-    Example:
-
-    ```mlir
-    // Scalar square root value.
-    %a = sqrt %b : f64
-    // SIMD vector element-wise square root value.
-    %f = sqrt %g : vector<4xf32>
-    // Tensor element-wise square root value.
-    %x = sqrt %y : tensor<4x?xf32>
-    ```
-  }];
-}
-
-//===----------------------------------------------------------------------===//
 // StoreOp
 //===----------------------------------------------------------------------===//
 
 def StoreOp : Std_Op<"store",
      [TypesMatchWith<"type of 'value' matches element type of 'memref'",
                      "memref", "value",
                      "$_self.cast<MemRefType>().getElementType()">,
                      MemRefsNormalizable]> {
let extraClassDeclaration = extraBaseClassDeclaration # [{
 
     /// Return the number of leading operands before the `offsets`, `sizes` and
     /// and `strides` operands.
     static unsigned getOffsetSizeAndStrideStartOperandIndex() { return 2; }
   }];
 }
 
 //===----------------------------------------------------------------------===//
-// TanhOp
-//===----------------------------------------------------------------------===//
-
-def TanhOp : FloatUnaryOp<"tanh"> {
-  let summary = "hyperbolic tangent of the specified value";
-  let description = [{
-    Syntax:
-
-    ```
-    operation ::= ssa-id `=` `std.tanh` ssa-use `:` type
-    ```
-
-    The `tanh` operation computes the hyperbolic tangent. It takes one operand
-    and returns one result of the same type. This type may be a float scalar
-    type, a vector whose element type is float, or a tensor of floats. It has
-    no standard attributes.
-
-    Example:
-
-    ```mlir
-    // Scalar hyperbolic tangent value.
-    %a = tanh %b : f64
-
-    // SIMD vector element-wise hyperbolic tangent value.
-    %f = tanh %g : vector<4xf32>
-
-    // Tensor element-wise hyperbolic tangent value.
-    %x = tanh %y : tensor<4x?xf8>
-    ```
-  }];
-}
-
-//===----------------------------------------------------------------------===//
 // TensorLoadOp
 //===----------------------------------------------------------------------===//
 
 def TensorLoadOp : Std_Op<"tensor_load",
     [SameOperandsAndResultShape, SameOperandsAndResultElementType,
      TypesMatchWith<"result type matches tensor equivalent of 'memref'",
                     "memref", "result",
                     "getTensorTypeFromMemRefType($_self)">]> {

mlir/include/mlir/Dialect/StandardOps/Transforms/Passes.h

-
 //===- Passes.h - Pass Entrypoints ------------------------------*- C++ -*-===//
 //
 // 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-2.0 WITH LLVM-exception
 //
 //===----------------------------------------------------------------------===//
 //
 // This header file defines prototypes that expose pass constructors in the loop
 // transformation library.
 //
 //===----------------------------------------------------------------------===//
 
 #ifndef MLIR_DIALECT_STANDARD_TRANSFORMS_PASSES_H_
 #define MLIR_DIALECT_STANDARD_TRANSFORMS_PASSES_H_
 
 #include "mlir/Pass/Pass.h"
 #include "mlir/Transforms/Bufferize.h"
 
 namespace mlir {
 
 class OwningRewritePatternList;
 
-void populateExpandTanhPattern(OwningRewritePatternList &patterns,
-                               MLIRContext *ctx);
-
 void populateStdBufferizePatterns(MLIRContext *context,
                                   BufferizeTypeConverter &typeConverter,
                                   OwningRewritePatternList &patterns);
 
 /// Creates an instance of std bufferization pass.
 std::unique_ptr<Pass> createStdBufferizePass();
 
 /// Creates an instance of func bufferization pass.

mlir/include/mlir/InitAllDialects.h

 #include "mlir/Dialect/GPU/GPUDialect.h"
 #include "mlir/Dialect/LLVMIR/LLVMAVX512Dialect.h"
 #include "mlir/Dialect/LLVMIR/LLVMArmNeonDialect.h"
 #include "mlir/Dialect/LLVMIR/LLVMArmSVEDialect.h"
 #include "mlir/Dialect/LLVMIR/LLVMDialect.h"
 #include "mlir/Dialect/LLVMIR/NVVMDialect.h"
 #include "mlir/Dialect/LLVMIR/ROCDLDialect.h"
 #include "mlir/Dialect/Linalg/IR/LinalgOps.h"
+#include "mlir/Dialect/Math/IR/Math.h"
 #include "mlir/Dialect/OpenACC/OpenACC.h"
 #include "mlir/Dialect/OpenMP/OpenMPDialect.h"
 #include "mlir/Dialect/PDL/IR/PDL.h"
 #include "mlir/Dialect/PDLInterp/IR/PDLInterp.h"
 #include "mlir/Dialect/Quant/QuantOps.h"
 #include "mlir/Dialect/SCF/SCF.h"
 #include "mlir/Dialect/SDBM/SDBMDialect.h"
 #include "mlir/Dialect/SPIRV/IR/SPIRVDialect.h"
registry.insert<acc::OpenACCDialect,
                   avx512::AVX512Dialect,
                   complex::ComplexDialect,
                   gpu::GPUDialect,
                   LLVM::LLVMAVX512Dialect,
                   LLVM::LLVMDialect,
                   LLVM::LLVMArmNeonDialect,
                   LLVM::LLVMArmSVEDialect,
                   linalg::LinalgDialect,
+                  math::MathDialect,
                   scf::SCFDialect,
                   omp::OpenMPDialect,
                   pdl::PDLDialect,
                   pdl_interp::PDLInterpDialect,
                   quant::QuantizationDialect,
                   spirv::SPIRVDialect,
                   StandardOpsDialect,
                   arm_sve::ArmSVEDialect,

mlir/lib/Conversion/GPUToNVVM/LowerGpuOpsToNVVMOps.cpp

 //===----------------------------------------------------------------------===//
 
 #include "mlir/Conversion/GPUToNVVM/GPUToNVVMPass.h"
 
 #include "mlir/Conversion/StandardToLLVM/ConvertStandardToLLVMPass.h"
 #include "mlir/Dialect/GPU/GPUDialect.h"
 #include "mlir/Dialect/GPU/Passes.h"
 #include "mlir/Dialect/LLVMIR/NVVMDialect.h"
+#include "mlir/Dialect/Math/IR/Math.h"
 #include "mlir/IR/BlockAndValueMapping.h"
 #include "mlir/Transforms/DialectConversion.h"
 #include "mlir/Transforms/GreedyPatternRewriteDriver.h"
 #include "llvm/Support/FormatVariadic.h"
 
 #include "../GPUCommon/GPUOpsLowering.h"
 #include "../GPUCommon/IndexIntrinsicsOpLowering.h"
 #include "../GPUCommon/OpToFuncCallLowering.h"
patterns
                                           NVVM::GridDimYOp, NVVM::GridDimZOp>,
               GPUShuffleOpLowering, GPUReturnOpLowering,
               // Explicitly drop memory space when lowering private memory
               // attributions since NVVM models it as `alloca`s in the default
               // memory space and does not support `alloca`s with addrspace(5).
               GPUFuncOpLowering<0>>(converter);
   patterns.insert<OpToFuncCallLowering<AbsFOp>>(converter, "__nv_fabsf",
                                                 "__nv_fabs");
-  patterns.insert<OpToFuncCallLowering<AtanOp>>(converter, "__nv_atanf",
+  patterns.insert<OpToFuncCallLowering<math::AtanOp>>(converter, "__nv_atanf",
                                                       "__nv_atan");
-  patterns.insert<OpToFuncCallLowering<Atan2Op>>(converter, "__nv_atan2f",
+  patterns.insert<OpToFuncCallLowering<math::Atan2Op>>(converter, "__nv_atan2f",
                                                        "__nv_atan2");
   patterns.insert<OpToFuncCallLowering<CeilFOp>>(converter, "__nv_ceilf",
                                                  "__nv_ceil");
-  patterns.insert<OpToFuncCallLowering<CosOp>>(converter, "__nv_cosf",
+  patterns.insert<OpToFuncCallLowering<math::CosOp>>(converter, "__nv_cosf",
                                                      "__nv_cos");
-  patterns.insert<OpToFuncCallLowering<ExpOp>>(converter, "__nv_expf",
+  patterns.insert<OpToFuncCallLowering<math::ExpOp>>(converter, "__nv_expf",
                                                      "__nv_exp");
   patterns.insert<OpToFuncCallLowering<FloorFOp>>(converter, "__nv_floorf",
                                                   "__nv_floor");
-  patterns.insert<OpToFuncCallLowering<LogOp>>(converter, "__nv_logf",
+  patterns.insert<OpToFuncCallLowering<math::LogOp>>(converter, "__nv_logf",
                                                      "__nv_log");
-  patterns.insert<OpToFuncCallLowering<Log1pOp>>(converter, "__nv_log1pf",
+  patterns.insert<OpToFuncCallLowering<math::Log1pOp>>(converter, "__nv_log1pf",
                                                        "__nv_log1p");
-  patterns.insert<OpToFuncCallLowering<Log10Op>>(converter, "__nv_log10f",
+  patterns.insert<OpToFuncCallLowering<math::Log10Op>>(converter, "__nv_log10f",
                                                        "__nv_log10");
-  patterns.insert<OpToFuncCallLowering<Log2Op>>(converter, "__nv_log2f",
+  patterns.insert<OpToFuncCallLowering<math::Log2Op>>(converter, "__nv_log2f",
                                                       "__nv_log2");
-  patterns.insert<OpToFuncCallLowering<PowFOp>>(converter, "__nv_powf",
+  patterns.insert<OpToFuncCallLowering<math::PowFOp>>(converter, "__nv_powf",
                                                       "__nv_pow");
-  patterns.insert<OpToFuncCallLowering<RsqrtOp>>(converter, "__nv_rsqrtf",
+  patterns.insert<OpToFuncCallLowering<math::RsqrtOp>>(converter, "__nv_rsqrtf",
                                                        "__nv_rsqrt");
-  patterns.insert<OpToFuncCallLowering<SinOp>>(converter, "__nv_sinf",
+  patterns.insert<OpToFuncCallLowering<math::SinOp>>(converter, "__nv_sinf",
                                                      "__nv_sin");
-  patterns.insert<OpToFuncCallLowering<SqrtOp>>(converter, "__nv_sqrtf",
+  patterns.insert<OpToFuncCallLowering<math::SqrtOp>>(converter, "__nv_sqrtf",
                                                       "__nv_sqrt");
-  patterns.insert<OpToFuncCallLowering<TanhOp>>(converter, "__nv_tanhf",
+  patterns.insert<OpToFuncCallLowering<math::TanhOp>>(converter, "__nv_tanhf",
                                                       "__nv_tanh");
 }
 
 std::unique_ptr<OperationPass<gpu::GPUModuleOp>>
 mlir::createLowerGpuOpsToNVVMOpsPass(unsigned indexBitwidth) {
   return std::make_unique<LowerGpuOpsToNVVMOpsPass>(indexBitwidth);
 }

mlir/lib/Conversion/GPUToROCDL/LowerGpuOpsToROCDLOps.cpp

 #include "mlir/Conversion/GPUToROCDL/GPUToROCDLPass.h"
 
 #include "mlir/Conversion/StandardToLLVM/ConvertStandardToLLVMPass.h"
 #include "mlir/Conversion/VectorToLLVM/ConvertVectorToLLVM.h"
 #include "mlir/Conversion/VectorToROCDL/VectorToROCDL.h"
 #include "mlir/Dialect/GPU/GPUDialect.h"
 #include "mlir/Dialect/GPU/Passes.h"
 #include "mlir/Dialect/LLVMIR/ROCDLDialect.h"
+#include "mlir/Dialect/Math/IR/Math.h"
 #include "mlir/Dialect/Vector/VectorOps.h"
 #include "mlir/Pass/Pass.h"
 #include "mlir/Transforms/DialectConversion.h"
 #include "mlir/Transforms/GreedyPatternRewriteDriver.h"
 #include "llvm/Support/FormatVariadic.h"
 
 #include "../GPUCommon/GPUOpsLowering.h"
 #include "../GPUCommon/IndexIntrinsicsOpLowering.h"
patterns.insert<
                                   ROCDL::BlockDimYOp, ROCDL::BlockDimZOp>,
       GPUIndexIntrinsicOpLowering<gpu::BlockIdOp, ROCDL::BlockIdXOp,
                                   ROCDL::BlockIdYOp, ROCDL::BlockIdZOp>,
       GPUIndexIntrinsicOpLowering<gpu::GridDimOp, ROCDL::GridDimXOp,
                                   ROCDL::GridDimYOp, ROCDL::GridDimZOp>,
       GPUFuncOpLowering<5>, GPUReturnOpLowering>(converter);
   patterns.insert<OpToFuncCallLowering<AbsFOp>>(converter, "__ocml_fabs_f32",
                                                 "__ocml_fabs_f64");
-  patterns.insert<OpToFuncCallLowering<AtanOp>>(converter, "__ocml_atan_f32",
-                                                "__ocml_atan_f64");
-  patterns.insert<OpToFuncCallLowering<Atan2Op>>(converter, "__ocml_atan2_f32",
-                                                 "__ocml_atan2_f64");
+  patterns.insert<OpToFuncCallLowering<math::AtanOp>>(
+      converter, "__ocml_atan_f32", "__ocml_atan_f64");
+  patterns.insert<OpToFuncCallLowering<math::Atan2Op>>(
+      converter, "__ocml_atan2_f32", "__ocml_atan2_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<math::CosOp>>(
+      converter, "__ocml_cos_f32", "__ocml_cos_f64");
+  patterns.insert<OpToFuncCallLowering<math::ExpOp>>(
+      converter, "__ocml_exp_f32", "__ocml_exp_f64");
   patterns.insert<OpToFuncCallLowering<FloorFOp>>(converter, "__ocml_floor_f32",
                                                   "__ocml_floor_f64");
-  patterns.insert<OpToFuncCallLowering<LogOp>>(converter, "__ocml_log_f32",
-                                               "__ocml_log_f64");
-  patterns.insert<OpToFuncCallLowering<Log10Op>>(converter, "__ocml_log10_f32",
-                                                 "__ocml_log10_f64");
-  patterns.insert<OpToFuncCallLowering<Log1pOp>>(converter, "__ocml_log1p_f32",
-                                                 "__ocml_log1p_f64");
-  patterns.insert<OpToFuncCallLowering<Log2Op>>(converter, "__ocml_log2_f32",
-                                                "__ocml_log2_f64");
-  patterns.insert<OpToFuncCallLowering<PowFOp>>(converter, "__ocml_pow_f32",
-                                                "__ocml_pow_f64");
-  patterns.insert<OpToFuncCallLowering<RsqrtOp>>(converter, "__ocml_rsqrt_f32",
-                                                 "__ocml_rsqrt_f64");
-  patterns.insert<OpToFuncCallLowering<SinOp>>(converter, "__ocml_sin_f32",
-                                               "__ocml_sin_f64");
-  patterns.insert<OpToFuncCallLowering<SqrtOp>>(converter, "__ocml_sqrt_f32",
-                                                "__ocml_sqrt_f64");
-  patterns.insert<OpToFuncCallLowering<TanhOp>>(converter, "__ocml_tanh_f32",
-                                                "__ocml_tanh_f64");
+  patterns.insert<OpToFuncCallLowering<math::LogOp>>(
+      converter, "__ocml_log_f32", "__ocml_log_f64");
+  patterns.insert<OpToFuncCallLowering<math::Log10Op>>(
+      converter, "__ocml_log10_f32", "__ocml_log10_f64");
+  patterns.insert<OpToFuncCallLowering<math::Log1pOp>>(
+      converter, "__ocml_log1p_f32", "__ocml_log1p_f64");
+  patterns.insert<OpToFuncCallLowering<math::Log2Op>>(
+      converter, "__ocml_log2_f32", "__ocml_log2_f64");
+  patterns.insert<OpToFuncCallLowering<math::PowFOp>>(
+      converter, "__ocml_pow_f32", "__ocml_pow_f64");
+  patterns.insert<OpToFuncCallLowering<math::RsqrtOp>>(
+      converter, "__ocml_rsqrt_f32", "__ocml_rsqrt_f64");
+  patterns.insert<OpToFuncCallLowering<math::SinOp>>(
+      converter, "__ocml_sin_f32", "__ocml_sin_f64");
+  patterns.insert<OpToFuncCallLowering<math::SqrtOp>>(
+      converter, "__ocml_sqrt_f32", "__ocml_sqrt_f64");
+  patterns.insert<OpToFuncCallLowering<math::TanhOp>>(
+      converter, "__ocml_tanh_f32", "__ocml_tanh_f64");
 }
 
 std::unique_ptr<OperationPass<gpu::GPUModuleOp>>
 mlir::createLowerGpuOpsToROCDLOpsPass(unsigned indexBitwidth) {
   return std::make_unique<LowerGpuOpsToROCDLOpsPass>(indexBitwidth);
 }

mlir/lib/Conversion/StandardToLLVM/CMakeLists.txt

 add_mlir_conversion_library(MLIRStandardToLLVM
   StandardToLLVM.cpp
 
   ADDITIONAL_HEADER_DIRS
   ${MLIR_MAIN_INCLUDE_DIR}/mlir/Conversion/StandardToLLVM
 
   DEPENDS
   MLIRConversionPassIncGen
   intrinsics_gen
 
   LINK_COMPONENTS
   Core
 
   LINK_LIBS PUBLIC
   MLIRLLVMIR
+  MLIRMath
   MLIRTransforms
   )

mlir/lib/Conversion/StandardToLLVM/StandardToLLVM.cpp

 // into the LLVM IR dialect.
 //
 //===----------------------------------------------------------------------===//
 
 #include "../PassDetail.h"
 #include "mlir/Conversion/StandardToLLVM/ConvertStandardToLLVM.h"
 #include "mlir/Conversion/StandardToLLVM/ConvertStandardToLLVMPass.h"
 #include "mlir/Dialect/LLVMIR/LLVMDialect.h"
+#include "mlir/Dialect/Math/IR/Math.h"
 #include "mlir/Dialect/StandardOps/IR/Ops.h"
 #include "mlir/IR/Attributes.h"
 #include "mlir/IR/BlockAndValueMapping.h"
 #include "mlir/IR/Builders.h"
 #include "mlir/IR/BuiltinOps.h"
 #include "mlir/IR/MLIRContext.h"
 #include "mlir/IR/PatternMatch.h"
 #include "mlir/IR/TypeUtilities.h"

 // Straightforward lowerings.
 using AbsFOpLowering = VectorConvertToLLVMPattern<AbsFOp, LLVM::FAbsOp>;
 using AddFOpLowering = VectorConvertToLLVMPattern<AddFOp, LLVM::FAddOp>;
 using AddIOpLowering = VectorConvertToLLVMPattern<AddIOp, LLVM::AddOp>;
 using AndOpLowering = VectorConvertToLLVMPattern<AndOp, LLVM::AndOp>;
 using CeilFOpLowering = VectorConvertToLLVMPattern<CeilFOp, LLVM::FCeilOp>;
 using CopySignOpLowering =
     VectorConvertToLLVMPattern<CopySignOp, LLVM::CopySignOp>;
-using CosOpLowering = VectorConvertToLLVMPattern<CosOp, LLVM::CosOp>;
+using CosOpLowering = VectorConvertToLLVMPattern<math::CosOp, LLVM::CosOp>;
 using DivFOpLowering = VectorConvertToLLVMPattern<DivFOp, LLVM::FDivOp>;
-using ExpOpLowering = VectorConvertToLLVMPattern<ExpOp, LLVM::ExpOp>;
-using Exp2OpLowering = VectorConvertToLLVMPattern<Exp2Op, LLVM::Exp2Op>;
+using ExpOpLowering = VectorConvertToLLVMPattern<math::ExpOp, LLVM::ExpOp>;
+using Exp2OpLowering = VectorConvertToLLVMPattern<math::Exp2Op, LLVM::Exp2Op>;
 using FloorFOpLowering = VectorConvertToLLVMPattern<FloorFOp, LLVM::FFloorOp>;
-using Log10OpLowering = VectorConvertToLLVMPattern<Log10Op, LLVM::Log10Op>;
-using Log2OpLowering = VectorConvertToLLVMPattern<Log2Op, LLVM::Log2Op>;
-using LogOpLowering = VectorConvertToLLVMPattern<LogOp, LLVM::LogOp>;
+using Log10OpLowering =
+    VectorConvertToLLVMPattern<math::Log10Op, LLVM::Log10Op>;
+using Log2OpLowering = VectorConvertToLLVMPattern<math::Log2Op, LLVM::Log2Op>;
+using LogOpLowering = VectorConvertToLLVMPattern<math::LogOp, LLVM::LogOp>;
 using MulFOpLowering = VectorConvertToLLVMPattern<MulFOp, LLVM::FMulOp>;
 using MulIOpLowering = VectorConvertToLLVMPattern<MulIOp, LLVM::MulOp>;
 using NegFOpLowering = VectorConvertToLLVMPattern<NegFOp, LLVM::FNegOp>;
 using OrOpLowering = VectorConvertToLLVMPattern<OrOp, LLVM::OrOp>;
-using PowFOpLowering = VectorConvertToLLVMPattern<PowFOp, LLVM::PowOp>;
+using PowFOpLowering = VectorConvertToLLVMPattern<math::PowFOp, LLVM::PowOp>;
 using RemFOpLowering = VectorConvertToLLVMPattern<RemFOp, LLVM::FRemOp>;
 using SelectOpLowering = OneToOneConvertToLLVMPattern<SelectOp, LLVM::SelectOp>;
 using SignExtendIOpLowering =
     VectorConvertToLLVMPattern<SignExtendIOp, LLVM::SExtOp>;
 using ShiftLeftOpLowering =
     OneToOneConvertToLLVMPattern<ShiftLeftOp, LLVM::ShlOp>;
 using SignedDivIOpLowering =
     VectorConvertToLLVMPattern<SignedDivIOp, LLVM::SDivOp>;
 using SignedRemIOpLowering =
     VectorConvertToLLVMPattern<SignedRemIOp, LLVM::SRemOp>;
 using SignedShiftRightOpLowering =
     OneToOneConvertToLLVMPattern<SignedShiftRightOp, LLVM::AShrOp>;
-using SinOpLowering = VectorConvertToLLVMPattern<SinOp, LLVM::SinOp>;
-using SqrtOpLowering = VectorConvertToLLVMPattern<SqrtOp, LLVM::SqrtOp>;
+using SinOpLowering = VectorConvertToLLVMPattern<math::SinOp, LLVM::SinOp>;
+using SqrtOpLowering = VectorConvertToLLVMPattern<math::SqrtOp, LLVM::SqrtOp>;
 using SubFOpLowering = VectorConvertToLLVMPattern<SubFOp, LLVM::FSubOp>;
 using SubIOpLowering = VectorConvertToLLVMPattern<SubIOp, LLVM::SubOp>;
 using UnsignedDivIOpLowering =
     VectorConvertToLLVMPattern<UnsignedDivIOp, LLVM::UDivOp>;
 using UnsignedRemIOpLowering =
     VectorConvertToLLVMPattern<UnsignedRemIOp, LLVM::URemOp>;
 using UnsignedShiftRightOpLowering =
     OneToOneConvertToLLVMPattern<UnsignedShiftRightOp, LLVM::LShrOp>;
std::tuple<Value, Value> allocateBuffer(ConversionPatternRewriter &rewriter,
 
     // Both allocated and aligned pointers are same. We could potentially stash
     // a nullptr for the allocated pointer since we do not expect any dealloc.
     return std::make_tuple(deadBeefPtr, gep);
   }
 };
 
 // A `rsqrt` is converted into `1 / sqrt`.
-struct RsqrtOpLowering : public ConvertOpToLLVMPattern<RsqrtOp> {
-  using ConvertOpToLLVMPattern<RsqrtOp>::ConvertOpToLLVMPattern;
+struct RsqrtOpLowering : public ConvertOpToLLVMPattern<math::RsqrtOp> {
+  using ConvertOpToLLVMPattern<math::RsqrtOp>::ConvertOpToLLVMPattern;
 
   LogicalResult
-  matchAndRewrite(RsqrtOp op, ArrayRef<Value> operands,
+  matchAndRewrite(math::RsqrtOp op, ArrayRef<Value> operands,
                   ConversionPatternRewriter &rewriter) const override {
-    RsqrtOp::Adaptor transformed(operands);
+    math::RsqrtOp::Adaptor transformed(operands);
     auto operandType = transformed.operand().getType();
 
     if (!operandType || !LLVM::isCompatibleType(operandType))
       return failure();
 
     auto loc = op.getLoc();
     auto resultType = op.getResult().getType();
     auto floatType = getElementTypeOrSelf(resultType).cast<FloatType>();
struct LLVMLoweringPass : public ConvertStandardToLLVMBase<LLVMLoweringPass> {
   }
 };
 } // end namespace
 
 mlir::LLVMConversionTarget::LLVMConversionTarget(MLIRContext &ctx)
     : ConversionTarget(ctx) {
   this->addLegalDialect<LLVM::LLVMDialect>();
   this->addIllegalOp<LLVM::DialectCastOp>();
-  this->addIllegalOp<TanhOp>();
+  this->addIllegalOp<math::TanhOp>();
 }
 
 std::unique_ptr<OperationPass<ModuleOp>>
 mlir::createLowerToLLVMPass(const LowerToLLVMOptions &options) {
   return std::make_unique<LLVMLoweringPass>(
       options.useBarePtrCallConv, options.emitCWrappers, options.indexBitwidth,
       options.useAlignedAlloc, options.dataLayout);
 }

mlir/lib/Conversion/StandardToSPIRV/CMakeLists.txt

 add_mlir_conversion_library(MLIRStandardToSPIRV
   LegalizeStandardForSPIRV.cpp
   StandardToSPIRV.cpp
   StandardToSPIRVPass.cpp
 
   ADDITIONAL_HEADER_DIRS
   ${MLIR_MAIN_INCLUDE_DIR}/mlir/Dialect/SPIRV
   ${MLIR_MAIN_INCLUDE_DIR}/mlir/IR
 
   DEPENDS
   MLIRConversionPassIncGen
 
   LINK_LIBS PUBLIC
   MLIRIR
+  MLIRMath
   MLIRPass
   MLIRSPIRV
   MLIRSPIRVConversion
   MLIRSupport
   MLIRTransformUtils
   MLIRStandard
   )

mlir/lib/Conversion/StandardToSPIRV/StandardToSPIRV.cpp

 //===- StandardToSPIRV.cpp - Standard to SPIR-V Patterns ------------------===//
 //
 // 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-2.0 WITH LLVM-exception
 //
 //===----------------------------------------------------------------------===//
 //
 // This file implements patterns to convert standard dialect to SPIR-V dialect.
 //
 //===----------------------------------------------------------------------===//
 
+#include "mlir/Dialect/Math/IR/Math.h"
 #include "mlir/Dialect/SPIRV/IR/SPIRVDialect.h"
 #include "mlir/Dialect/SPIRV/IR/SPIRVOps.h"
 #include "mlir/Dialect/SPIRV/Transforms/SPIRVConversion.h"
 #include "mlir/Dialect/SPIRV/Utils/LayoutUtils.h"
 #include "mlir/Dialect/StandardOps/IR/Ops.h"
 #include "mlir/IR/AffineMap.h"
 #include "mlir/Support/LogicalResult.h"
 #include "llvm/ADT/SetVector.h"

 // Pattern population
 //===----------------------------------------------------------------------===//
 
 namespace mlir {
 void populateStandardToSPIRVPatterns(MLIRContext *context,
                                      SPIRVTypeConverter &typeConverter,
                                      OwningRewritePatternList &patterns) {
   patterns.insert<
+      // Math dialect operations.
+      // TODO: Move to separate pass.
+      UnaryAndBinaryOpPattern<math::CosOp, spirv::GLSLCosOp>,
+      UnaryAndBinaryOpPattern<math::ExpOp, spirv::GLSLExpOp>,
+      UnaryAndBinaryOpPattern<math::LogOp, spirv::GLSLLogOp>,
+      UnaryAndBinaryOpPattern<math::RsqrtOp, spirv::GLSLInverseSqrtOp>,
+      UnaryAndBinaryOpPattern<math::SinOp, spirv::GLSLSinOp>,
+      UnaryAndBinaryOpPattern<math::SqrtOp, spirv::GLSLSqrtOp>,
+      UnaryAndBinaryOpPattern<math::TanhOp, spirv::GLSLTanhOp>,
       // Unary and binary patterns
       BitwiseOpPattern<AndOp, spirv::LogicalAndOp, spirv::BitwiseAndOp>,
       BitwiseOpPattern<OrOp, spirv::LogicalOrOp, spirv::BitwiseOrOp>,
       UnaryAndBinaryOpPattern<AbsFOp, spirv::GLSLFAbsOp>,
       UnaryAndBinaryOpPattern<AddFOp, spirv::FAddOp>,
       UnaryAndBinaryOpPattern<AddIOp, spirv::IAddOp>,
       UnaryAndBinaryOpPattern<CeilFOp, spirv::GLSLCeilOp>,
-      UnaryAndBinaryOpPattern<CosOp, spirv::GLSLCosOp>,
       UnaryAndBinaryOpPattern<DivFOp, spirv::FDivOp>,
-      UnaryAndBinaryOpPattern<ExpOp, spirv::GLSLExpOp>,
       UnaryAndBinaryOpPattern<FloorFOp, spirv::GLSLFloorOp>,
-      UnaryAndBinaryOpPattern<LogOp, spirv::GLSLLogOp>,
       UnaryAndBinaryOpPattern<MulFOp, spirv::FMulOp>,
       UnaryAndBinaryOpPattern<MulIOp, spirv::IMulOp>,
       UnaryAndBinaryOpPattern<NegFOp, spirv::FNegateOp>,
       UnaryAndBinaryOpPattern<RemFOp, spirv::FRemOp>,
-      UnaryAndBinaryOpPattern<RsqrtOp, spirv::GLSLInverseSqrtOp>,
       UnaryAndBinaryOpPattern<ShiftLeftOp, spirv::ShiftLeftLogicalOp>,
       UnaryAndBinaryOpPattern<SignedDivIOp, spirv::SDivOp>,
       UnaryAndBinaryOpPattern<SignedShiftRightOp,
                               spirv::ShiftRightArithmeticOp>,
-      UnaryAndBinaryOpPattern<SinOp, spirv::GLSLSinOp>,
-      UnaryAndBinaryOpPattern<SqrtOp, spirv::GLSLSqrtOp>,
-      UnaryAndBinaryOpPattern<SubFOp, spirv::FSubOp>,
       UnaryAndBinaryOpPattern<SubIOp, spirv::ISubOp>,
-      UnaryAndBinaryOpPattern<TanhOp, spirv::GLSLTanhOp>,
+      UnaryAndBinaryOpPattern<SubFOp, spirv::FSubOp>,
       UnaryAndBinaryOpPattern<UnsignedDivIOp, spirv::UDivOp>,
       UnaryAndBinaryOpPattern<UnsignedRemIOp, spirv::UModOp>,
       UnaryAndBinaryOpPattern<UnsignedShiftRightOp, spirv::ShiftRightLogicalOp>,
       SignedRemIOpPattern, XOrOpPattern,
 
       // Comparison patterns
       BoolCmpIOpPattern, CmpFOpPattern, CmpFOpNanNonePattern, CmpIOpPattern,
 

mlir/lib/Conversion/TosaToLinalg/CMakeLists.txt

 add_mlir_conversion_library(MLIRTosaToLinalg
   TosaToLinalg.cpp
   TosaToLinalgPass.cpp
 
   ADDITIONAL_HEADER_DIRS
   ${MLIR_MAIN_INCLUDE_DIR}/mlir/Dialect/Tosa
   ${MLIR_MAIN_INCLUDE_DIR}/mlir/IR
 
   DEPENDS
   MLIRConversionPassIncGen
 
   LINK_LIBS PUBLIC
   MLIRIR
   MLIRLinalg
   MLIRLinalgUtils
+  MLIRMath
   MLIRPass
   MLIRTosa
   MLIRTosaTransforms
   MLIRSupport
   )

mlir/lib/Conversion/TosaToLinalg/TosaToLinalg.cpp

 //===- TosaToLinalg.cpp - Lowering Tosa to Linalg Dialect -----------------===//
 //
 // 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-2.0 WITH LLVM-exception
 //
 //===----------------------------------------------------------------------===//
 //
 // These rewriters lower from the Tosa to the Linalg dialect.
 //
 //===----------------------------------------------------------------------===//
 
 #include "mlir/Conversion/TosaToLinalg/TosaToLinalg.h"
 #include "mlir/Dialect/Linalg/IR/LinalgOps.h"
+#include "mlir/Dialect/Math/IR/Math.h"
 #include "mlir/Dialect/StandardOps/IR/Ops.h"
 #include "mlir/Dialect/Tosa/IR/TosaOps.h"
 #include "mlir/IR/PatternMatch.h"
 #include "mlir/Transforms/GreedyPatternRewriteDriver.h"
 
 using namespace mlir;
 
 static SmallVector<StringRef> getNParallelLoopsAttrs(unsigned nParallelLoops) {
if (isa<tosa::LogicalLeftShiftOp>(op) && elementTy.isa<IntegerType>())
     return rewriter.create<mlir::ShiftLeftOp>(loc, resultTypes, args);
 
   // tosa::LogicalrightShiftOp
   if (isa<tosa::LogicalRightShiftOp>(op) && elementTy.isa<IntegerType>())
     return rewriter.create<mlir::UnsignedShiftRightOp>(loc, resultTypes, args);
 
   // tosa::PowOp
   if (isa<tosa::PowOp>(op) && elementTy.isa<FloatType>())
-    return rewriter.create<mlir::PowFOp>(loc, resultTypes, args);
+    return rewriter.create<mlir::math::PowFOp>(loc, resultTypes, args);
 
   // tosa::LogOp
   if (isa<tosa::LogOp>(op) && elementTy.isa<FloatType>())
-    return rewriter.create<mlir::LogOp>(loc, resultTypes, args);
+    return rewriter.create<mlir::math::LogOp>(loc, resultTypes, args);
 
   // tosa::ExpOp
   if (isa<tosa::ExpOp>(op) && elementTy.isa<FloatType>())
-    return rewriter.create<mlir::ExpOp>(loc, resultTypes, args);
+    return rewriter.create<mlir::math::ExpOp>(loc, resultTypes, args);
 
   // tosa::SubOp
   if (isa<tosa::SubOp>(op) && elementTy.isa<FloatType>())
     return rewriter.create<mlir::SubFOp>(loc, resultTypes, args);
 
   if (isa<tosa::SubOp>(op) && elementTy.isa<IntegerType>())
     return rewriter.create<mlir::SubIOp>(loc, resultTypes, args);
 
   // tosa::TanhOp
   if (isa<tosa::TanhOp>(op) && elementTy.isa<FloatType>())
-    return rewriter.create<mlir::TanhOp>(loc, resultTypes, args);
+    return rewriter.create<mlir::math::TanhOp>(loc, resultTypes, args);
 
   // tosa::GreaterOp
   if (isa<tosa::GreaterOp>(op) && elementTy.isa<FloatType>())
     return rewriter.create<mlir::CmpFOp>(loc, CmpFPredicate::OGT, args[0],
                                          args[1]);
 
   if (isa<tosa::GreaterOp>(op) && elementTy.isSignlessInteger())
     return rewriter.create<mlir::CmpIOp>(loc, CmpIPredicate::sgt, args[0],

mlir/lib/Conversion/TosaToLinalg/TosaToLinalgPass.cpp

 //===- TosaToLinalgPass.cpp - Lowering Tosa to Linalg Dialect -------------===//
 //
 // 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-2.0 WITH LLVM-exception
 //
 //===----------------------------------------------------------------------===//
 //
 // This transformation pass legalizes Tosa operations to the Linalg dialect.
 //
 //===----------------------------------------------------------------------===//
 
 #include "../PassDetail.h"
 #include "mlir/Conversion/TosaToLinalg/TosaToLinalg.h"
 #include "mlir/Dialect/Linalg/IR/LinalgOps.h"
+#include "mlir/Dialect/Math/IR/Math.h"
 #include "mlir/Dialect/StandardOps/IR/Ops.h"
 #include "mlir/Dialect/Tosa/IR/TosaOps.h"
 #include "mlir/Dialect/Tosa/Transforms/PassDetail.h"
 #include "mlir/Dialect/Tosa/Transforms/Passes.h"
 #include "mlir/Dialect/Tosa/Utils/QuantUtils.h"
 #include "mlir/IR/PatternMatch.h"
 #include "mlir/Pass/PassManager.h"
 #include "mlir/Transforms/DialectConversion.h"
 #include "mlir/Transforms/GreedyPatternRewriteDriver.h"
 
 using namespace mlir;
 
 namespace {
 struct TosaToLinalgOnTensors
     : public TosaToLinalgOnTensorsBase<TosaToLinalgOnTensors> {
 public:
   void getDependentDialects(DialectRegistry &registry) const override {
-    registry.insert<linalg::LinalgDialect, StandardOpsDialect>();
+    registry
+        .insert<linalg::LinalgDialect, math::MathDialect, StandardOpsDialect>();
   }
 
   void runOnFunction() override {
     OwningRewritePatternList patterns;
     ConversionTarget target(getContext());
     target.addLegalDialect<linalg::LinalgDialect, StandardOpsDialect>();
     target.addIllegalDialect<tosa::TosaDialect>();
     target.markUnknownOpDynamicallyLegal([](Operation *) { return true; });

mlir/lib/Dialect/CMakeLists.txt

 add_subdirectory(Affine)
 add_subdirectory(ArmNeon)
 add_subdirectory(ArmSVE)
 add_subdirectory(Async)
 add_subdirectory(AVX512)
 add_subdirectory(Complex)
 add_subdirectory(GPU)
 add_subdirectory(Linalg)
 add_subdirectory(LLVMIR)
+add_subdirectory(Math)
 add_subdirectory(OpenACC)
 add_subdirectory(OpenMP)
 add_subdirectory(PDL)
 add_subdirectory(PDLInterp)
 add_subdirectory(Quant)
 add_subdirectory(SCF)
 add_subdirectory(SDBM)
 add_subdirectory(Shape)

mlir/lib/Dialect/Linalg/EDSC/Builders.cpp

 //===- Builders.cpp - MLIR Declarative Linalg Builders --------------------===//
 //
 // 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-2.0 WITH LLVM-exception
 //
 //===----------------------------------------------------------------------===//
 
 #include "mlir/IR/Builders.h"
 #include "mlir/Dialect/Affine/EDSC/Intrinsics.h"
 #include "mlir/Dialect/Linalg/EDSC/Builders.h"
 #include "mlir/Dialect/Linalg/EDSC/Intrinsics.h"
+#include "mlir/Dialect/Math/EDSC/Intrinsics.h"
 #include "mlir/Dialect/SCF/EDSC/Builders.h"
 #include "mlir/Dialect/StandardOps/EDSC/Intrinsics.h"
 #include "mlir/Dialect/Utils/StructuredOpsUtils.h"
 #include "mlir/IR/AffineExpr.h"
 
 using namespace mlir;
 using namespace mlir::edsc;
 using namespace mlir::edsc::intrinsics;
if (O.getType().isa<RankedTensorType>())
     return makeGenericLinalgOp(iterTypes, /*inputs=*/{I}, /*outputs=*/{O},
                                /*resultTensorTypes=*/{O}, fun);
   return makeGenericLinalgOp(iterTypes, /*inputs=*/{I}, /*outputs=*/{O},
                              /*resultTensorTypes=*/{}, fun);
 }
 
 Operation *mlir::edsc::ops::linalg_generic_pointwise_tanh(StructuredIndexed I,
                                                           StructuredIndexed O) {
-  UnaryPointwiseOpBuilder unOp([](Value a) -> Value { return std_tanh(a); });
+  UnaryPointwiseOpBuilder unOp([](Value a) -> Value { return math_tanh(a); });
   return linalg_generic_pointwise(unOp, I, O);
 }
 
 /// Binary pointwise operation (with broadcast) entry point.
 Operation *mlir::edsc::ops::linalg_generic_pointwise(
     BinaryPointwiseOpBuilder binaryOp, StructuredIndexed I1,
     StructuredIndexed I2, StructuredIndexed O) {
   SmallVector<IteratorType, 4> iterTypes(O.getExprs().size(),

mlir/lib/Dialect/Linalg/EDSC/CMakeLists.txt

 add_mlir_dialect_library(MLIRLinalgEDSC
   Builders.cpp
 
   ADDITIONAL_HEADER_DIRS
   ${MLIR_MAIN_INCLUDE_DIR}/mlir/Dialect/Linalg
 
   LINK_LIBS PUBLIC
   MLIREDSC
   MLIRIR
   MLIRAffine
   MLIRAffineEDSC
   MLIRLinalg
+  MLIRMath
   MLIRSCF
   MLIRStandard
   )

mlir/lib/Dialect/Linalg/Transforms/Bufferize.cpp

 //===- Bufferize.cpp - Bufferization of linalg ops ------------------===//
 //
 // 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-2.0 WITH LLVM-exception
 //
 //===----------------------------------------------------------------------===//
 
 #include "mlir/Transforms/Bufferize.h"
 #include "PassDetail.h"
 #include "mlir/Dialect/Linalg/IR/LinalgOps.h"
 #include "mlir/Dialect/Linalg/Passes.h"
 #include "mlir/Dialect/Linalg/Transforms/Transforms.h"
 #include "mlir/Dialect/Linalg/Utils/Utils.h"
+#include "mlir/Dialect/Math/IR/Math.h"
 #include "mlir/Dialect/StandardOps/Transforms/Passes.h"
 #include "mlir/Dialect/StandardOps/Utils/Utils.h"
 #include "mlir/Dialect/Vector/VectorOps.h"
 #include "mlir/IR/BuiltinDialect.h"
 #include "mlir/IR/Operation.h"
 #include "mlir/Pass/Pass.h"
 
 using namespace ::mlir;

 /// work on buffers.
 struct LinalgBufferizePass : public LinalgBufferizeBase<LinalgBufferizePass> {
   void runOnOperation() override {
     MLIRContext &context = getContext();
     ConversionTarget target(context);
     BufferizeTypeConverter typeConverter;
 
     // Mark all Standard operations legal.
-    target.addLegalDialect<AffineDialect, StandardOpsDialect>();
+    target.addLegalDialect<AffineDialect, math::MathDialect,
+                           StandardOpsDialect>();
     target.addIllegalOp<InitTensorOp, SubTensorOp, SubTensorInsertOp>();
 
     // Mark all Linalg operations illegal as long as they work on tensors.
     auto isLegalOperation = [&](Operation *op) {
       return typeConverter.isLegal(op);
     };
     target.addDynamicallyLegalDialect<linalg::LinalgDialect>(isLegalOperation);
     target.addDynamicallyLegalOp<ConstantOp>(isLegalOperation);

mlir/lib/Dialect/Math/CMakeLists.txt

+add_subdirectory(IR)
+add_subdirectory(Transforms)

mlir/lib/Dialect/Math/IR/CMakeLists.txt

+add_mlir_dialect_library(MLIRMath
+  MathOps.cpp
+  MathDialect.cpp
+
+  ADDITIONAL_HEADER_DIRS
+  ${MLIR_MAIN_INCLUDE_DIR}/mlir/Dialect/Math
+
+  DEPENDS
+  MLIRMathOpsIncGen
+
+  LINK_LIBS PUBLIC
+  MLIRDialect
+  MLIRIR
+  )

mlir/lib/Dialect/Math/IR/MathDialect.cpp

+//===- MathDialect.cpp - MLIR dialect for Math implementation -------------===//
+//
+// 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-2.0 WITH LLVM-exception
+//
+//===----------------------------------------------------------------------===//
+
+#include "mlir/Dialect/Math/IR/Math.h"
+
+void mlir::math::MathDialect::initialize() {
+  addOperations<
+#define GET_OP_LIST
+#include "mlir/Dialect/Math/IR/MathOps.cpp.inc"
+      >();
+}

mlir/lib/Dialect/Math/IR/MathOps.cpp

+//===- MathOps.cpp - MLIR operations for math implementation --------------===//
+//
+// 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-2.0 WITH LLVM-exception
+//
+//===----------------------------------------------------------------------===//
+
+#include "mlir/Dialect/Math/IR/Math.h"
+
+using namespace mlir;
+using namespace mlir::math;
+
+//===----------------------------------------------------------------------===//
+// TableGen'd op method definitions
+//===----------------------------------------------------------------------===//
+
+#define GET_OP_CLASSES
+#include "mlir/Dialect/Math/IR/MathOps.cpp.inc"

mlir/lib/Dialect/Math/Transforms/CMakeLists.txt

+add_mlir_dialect_library(MLIRMathTransforms
+  ExpandTanh.cpp
+
+  ADDITIONAL_HEADER_DIRS
+  ${MLIR_MAIN_INCLUDE_DIR}/mlir/Dialect/Math/Transforms
+
+  LINK_LIBS PUBLIC
+  MLIRIR
+  MLIRPass
+  MLIRStandard
+  MLIRTransforms
+  )

mlir/lib/Dialect/Math/Transforms/ExpandTanh.cpp

 //===- ExpandTanh.cpp - Code to perform expanding tanh op -----------------===//
 //
 // 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-2.0 WITH LLVM-exception
 //
 //===----------------------------------------------------------------------===//
 //
 // This file implements expansion of tanh op.
 //
 //===----------------------------------------------------------------------===//
 
-#include "PassDetail.h"
+#include "mlir/Dialect/Math/IR/Math.h"
+#include "mlir/Dialect/Math/Transforms/Passes.h"
 #include "mlir/Dialect/StandardOps/IR/Ops.h"
-#include "mlir/Dialect/StandardOps/Transforms/Passes.h"
 #include "mlir/IR/Builders.h"
-#include "mlir/IR/PatternMatch.h"
-#include "mlir/IR/TypeUtilities.h"
-#include "mlir/Pass/Pass.h"
 #include "mlir/Transforms/DialectConversion.h"
 
 using namespace mlir;
 
 namespace {
-
 /// Expands tanh op into
 ///   1) 1-exp^{-2x} / 1+exp^{-2x}, if x => 0
 ///   2) exp^{2x}-1 / exp^{2x}+1  , if x < 0
-struct TanhOpConverter : public OpRewritePattern<TanhOp> {
+struct TanhOpConverter : public OpRewritePattern<math::TanhOp> {
 public:
   using OpRewritePattern::OpRewritePattern;
 
-  LogicalResult matchAndRewrite(TanhOp op,
+  LogicalResult matchAndRewrite(math::TanhOp op,
                                 PatternRewriter &rewriter) const final {
     auto floatType = op.operand().getType();
     Location loc = op.getLoc();
     auto floatOne = rewriter.getFloatAttr(floatType, 1.0);
     auto floatTwo = rewriter.getFloatAttr(floatType, 2.0);
     Value one = rewriter.create<ConstantOp>(loc, floatOne);
     Value two = rewriter.create<ConstantOp>(loc, floatTwo);
     Value doubledX = rewriter.create<MulFOp>(loc, op.operand(), two);
 
     // Case 1: tanh(x) = 1-exp^{-2x} / 1+exp^{-2x}
     Value negDoubledX = rewriter.create<NegFOp>(loc, doubledX);
-    Value exp2x = rewriter.create<ExpOp>(loc, negDoubledX);
+    Value exp2x = rewriter.create<math::ExpOp>(loc, negDoubledX);
     Value dividend = rewriter.create<SubFOp>(loc, one, exp2x);
     Value divisor = rewriter.create<AddFOp>(loc, one, exp2x);
     Value positiveRes = rewriter.create<DivFOp>(loc, dividend, divisor);
 
     // Case 2: tanh(x) = exp^{2x}-1 / exp^{2x}+1
-    exp2x = rewriter.create<ExpOp>(loc, doubledX);
+    exp2x = rewriter.create<math::ExpOp>(loc, doubledX);
     dividend = rewriter.create<SubFOp>(loc, exp2x, one);
     divisor = rewriter.create<AddFOp>(loc, exp2x, one);
     Value negativeRes = rewriter.create<DivFOp>(loc, dividend, divisor);
 
     // tanh(x) = x >= 0 ? positiveRes : negativeRes
     auto floatZero = rewriter.getFloatAttr(floatType, 0.0);
     Value zero = rewriter.create<ConstantOp>(loc, floatZero);
     Value cmpRes =

mlir/lib/Dialect/StandardOps/Transforms/CMakeLists.txt

 add_mlir_dialect_library(MLIRStandardOpsTransforms
   Bufferize.cpp
   DecomposeCallGraphTypes.cpp
   ExpandOps.cpp
-  ExpandTanh.cpp
   FuncBufferize.cpp
   FuncConversions.cpp
   TensorConstantBufferize.cpp
 
   ADDITIONAL_HEADER_DIRS
   ${MLIR_MAIN_INCLUDE_DIR}/mlir/Dialect/StandardOps/Transforms
 
   DEPENDS

mlir/test/Analysis/test-shape-fn-report.mlir

 // RUN: mlir-opt %s --test-shape-function-report -verify-diagnostics
 
 module attributes {shape.lib = [@shape_lib]} {
 
 // expected-remark@+1 {{associated shape function: same_result_shape}}
 func @tanh(%arg: tensor<10x20xf32>) -> tensor<10x20xf32>
     attributes {shape.function = @shape_lib::@same_result_shape} {
   // expected-remark@+1 {{no associated way}}
-  %0 = tanh %arg : tensor<10x20xf32>
+  %0 = math.tanh %arg : tensor<10x20xf32>
   // expected-remark@+1 {{associated shape function: same_result_shape}}
   %1 = "test.same_operand_result_type"(%0) : (tensor<10x20xf32>) -> tensor<10x20xf32>
   return %1 : tensor<10x20xf32>
 }
 
 // The shape function library with some local functions.
 shape.function_library @shape_lib {
   // Test shape function that returns the shape of input arg as result shape.

mlir/test/Bindings/Python/pass_manager.py

 # RUN: %PYTHON %s 2>&1 | FileCheck %s
 
 import gc, sys
 from mlir.ir import *
 from mlir.passmanager import *
 
-# Log everything to stderr and flush so that we have a unified stream to match
+
+# math.log everything to stderr and flush so that we have a unified stream to match
 # errors/info emitted by MLIR to stderr.
 def log(*args):
   print(*args, file=sys.stderr)
   sys.stderr.flush()
 
+
 def run(f):
   log("\nTEST:", f.__name__)
   f()
   gc.collect()
   assert Context._get_live_count() == 0
 
+
 # Verify capsule interop.
 # CHECK-LABEL: TEST: testCapsule
 def testCapsule():
   with Context():
     pm = PassManager()
     pm_capsule = pm._CAPIPtr
     assert '"mlir.passmanager.PassManager._CAPIPtr"' in repr(pm_capsule)
     pm._testing_release()
     pm1 = PassManager._CAPICreate(pm_capsule)
     assert pm1 is not None  # And does not crash.
+
+
 run(testCapsule)
 
 
 # Verify successful round-trip.
 # CHECK-LABEL: TEST: testParseSuccess
 def testParseSuccess():
   with Context():
     # A first import is expected to fail because the pass isn't registered
     # until we import mlir.transforms
     try:
       pm = PassManager.parse("module(func(print-op-stats))")
       # TODO: this error should be propagate to Python but the C API does not help right now.
       # CHECK: error: 'print-op-stats' does not refer to a registered pass or pass pipeline
     except ValueError as e:
       # CHECK: ValueError exception: invalid pass pipeline 'module(func(print-op-stats))'.
       log("ValueError exception:", e)
     else:
       log("Exception not produced")
 
     # This will register the pass and round-trip should be possible now.
     import mlir.transforms
     pm = PassManager.parse("module(func(print-op-stats))")
     # CHECK: Roundtrip: module(func(print-op-stats))
     log("Roundtrip: ", pm)
+
+
 run(testParseSuccess)
 
+
 # Verify failure on unregistered pass.
 # CHECK-LABEL: TEST: testParseFail
 def testParseFail():
   with Context():
     try:
       pm = PassManager.parse("unknown-pass")
     except ValueError as e:
       # CHECK: ValueError exception: invalid pass pipeline 'unknown-pass'.
       log("ValueError exception:", e)
     else:
       log("Exception not produced")
+
+
 run(testParseFail)
 
 
 # Verify failure on incorrect level of nesting.
 # CHECK-LABEL: TEST: testInvalidNesting
 def testInvalidNesting():
   with Context():
     try:
       pm = PassManager.parse("func(print-op-graph)")
     except ValueError as e:
       # CHECK: Can't add pass 'PrintOp' restricted to 'module' on a PassManager intended to run on 'func', did you intend to nest?
       # CHECK: ValueError exception: invalid pass pipeline 'func(print-op-graph)'.
       log("ValueError exception:", e)
     else:
       log("Exception not produced")
+
+
 run(testInvalidNesting)
 
 
 # Verify that a pass manager can execute on IR
 # CHECK-LABEL: TEST: testRun
 def testRunPipeline():
   with Context():
     pm = PassManager.parse("print-op-stats")
     module = Module.parse(r"""func @successfulParse() { return }""")
     pm.run(module)
+
+
 # CHECK: Operations encountered:
 # CHECK: func              , 1
 # CHECK: module            , 1
 # CHECK: module_terminator , 1
 # CHECK: std.return        , 1
 run(testRunPipeline)

mlir/test/Conversion/GPUToNVVM/gpu-to-nvvm.mlir

 
 // -----
 
 gpu.module @test_module {
   // CHECK: llvm.func @__nv_cosf(f32) -> f32
   // CHECK: llvm.func @__nv_cos(f64) -> f64
   // CHECK-LABEL: func @gpu_cos
   func @gpu_cos(%arg_f32 : f32, %arg_f64 : f64) -> (f32, f64) {
-    %result32 = std.cos %arg_f32 : f32
+    %result32 = math.cos %arg_f32 : f32
     // CHECK: llvm.call @__nv_cosf(%{{.*}}) : (f32) -> f32
-    %result64 = std.cos %arg_f64 : f64
+    %result64 = math.cos %arg_f64 : f64
     // CHECK: llvm.call @__nv_cos(%{{.*}}) : (f64) -> f64
     std.return %result32, %result64 : f32, f64
   }
 }
 
 // -----
 gpu.module @test_module {
   // CHECK: llvm.func @__nv_expf(f32) -> f32
   // CHECK: llvm.func @__nv_exp(f64) -> f64
   // CHECK-LABEL: func @gpu_exp
   func @gpu_exp(%arg_f32 : f32, %arg_f64 : f64) -> (f32, f64) {
-    %result32 = std.exp %arg_f32 : f32
+    %result32 = math.exp %arg_f32 : f32
     // CHECK: llvm.call @__nv_expf(%{{.*}}) : (f32) -> f32
-    %result64 = std.exp %arg_f64 : f64
+    %result64 = math.exp %arg_f64 : f64
     // CHECK: llvm.call @__nv_exp(%{{.*}}) : (f64) -> f64
     std.return %result32, %result64 : f32, f64
   }
 }
 
 // -----
 
 gpu.module @test_module {
   // CHECK: llvm.func @__nv_logf(f32) -> f32
   // CHECK: llvm.func @__nv_log(f64) -> f64
   // CHECK-LABEL: func @gpu_log
   func @gpu_log(%arg_f32 : f32, %arg_f64 : f64) -> (f32, f64) {
-    %result32 = std.log %arg_f32 : f32
+    %result32 = math.log %arg_f32 : f32
     // CHECK: llvm.call @__nv_logf(%{{.*}}) : (f32) -> f32
-    %result64 = std.log %arg_f64 : f64
+    %result64 = math.log %arg_f64 : f64
     // CHECK: llvm.call @__nv_log(%{{.*}}) : (f64) -> f64
     std.return %result32, %result64 : f32, f64
   }
 }
 
 // -----
 
 gpu.module @test_module {
   // CHECK: llvm.func @__nv_log10f(f32) -> f32
   // CHECK: llvm.func @__nv_log10(f64) -> f64
   // CHECK-LABEL: func @gpu_log10
   func @gpu_log10(%arg_f32 : f32, %arg_f64 : f64) -> (f32, f64) {
-    %result32 = std.log10 %arg_f32 : f32
+    %result32 = math.log10 %arg_f32 : f32
     // CHECK: llvm.call @__nv_log10f(%{{.*}}) : (f32) -> f32
-    %result64 = std.log10 %arg_f64 : f64
+    %result64 = math.log10 %arg_f64 : f64
     // CHECK: llvm.call @__nv_log10(%{{.*}}) : (f64) -> f64
     std.return %result32, %result64 : f32, f64
   }
 }
 
 // -----
 
 gpu.module @test_module {
   // CHECK: llvm.func @__nv_log1pf(f32) -> f32
   // CHECK: llvm.func @__nv_log1p(f64) -> f64
   // CHECK-LABEL: func @gpu_log1p
   func @gpu_log1p(%arg_f32 : f32, %arg_f64 : f64) -> (f32, f64) {
-    %result32 = std.log1p %arg_f32 : f32
+    %result32 = math.log1p %arg_f32 : f32
     // CHECK: llvm.call @__nv_log1pf(%{{.*}}) : (f32) -> f32
-    %result64 = std.log1p %arg_f64 : f64
+    %result64 = math.log1p %arg_f64 : f64
     // CHECK: llvm.call @__nv_log1p(%{{.*}}) : (f64) -> f64
     std.return %result32, %result64 : f32, f64
   }
 }
 
 // -----
 
 gpu.module @test_module {
   // CHECK: llvm.func @__nv_log2f(f32) -> f32
   // CHECK: llvm.func @__nv_log2(f64) -> f64
   // CHECK-LABEL: func @gpu_log2
   func @gpu_log2(%arg_f32 : f32, %arg_f64 : f64) -> (f32, f64) {
-    %result32 = std.log2 %arg_f32 : f32
+    %result32 = math.log2 %arg_f32 : f32
     // CHECK: llvm.call @__nv_log2f(%{{.*}}) : (f32) -> f32
-    %result64 = std.log2 %arg_f64 : f64
+    %result64 = math.log2 %arg_f64 : f64
     // CHECK: llvm.call @__nv_log2(%{{.*}}) : (f64) -> f64
     std.return %result32, %result64 : f32, f64
   }
 }
 
 // -----
 
 gpu.module @test_module {
   // CHECK: llvm.func @__nv_sinf(f32) -> f32
   // CHECK: llvm.func @__nv_sin(f64) -> f64
   // CHECK-LABEL: func @gpu_sin
   func @gpu_sin(%arg_f32 : f32, %arg_f64 : f64) -> (f32, f64) {
-    %result32 = std.sin %arg_f32 : f32
+    %result32 = math.sin %arg_f32 : f32
     // CHECK: llvm.call @__nv_sinf(%{{.*}}) : (f32) -> f32
-    %result64 = std.sin %arg_f64 : f64
+    %result64 = math.sin %arg_f64 : f64
     // CHECK: llvm.call @__nv_sin(%{{.*}}) : (f64) -> f64
     std.return %result32, %result64 : f32, f64
   }
 }
 
 // -----
 
 gpu.module @test_module {
   // CHECK: llvm.func @__nv_tanhf(f32) -> f32
   // CHECK: llvm.func @__nv_tanh(f64) -> f64
   // CHECK-LABEL: func @gpu_tanh
   func @gpu_tanh(%arg_f16 : f16, %arg_f32 : f32, %arg_f64 : f64) -> (f16, f32, f64) {
-    %result16 = std.tanh %arg_f16 : f16
+    %result16 = math.tanh %arg_f16 : f16
     // CHECK: llvm.fpext %{{.*}} : f16 to f32
     // CHECK-NEXT: llvm.call @__nv_tanhf(%{{.*}}) : (f32) -> f32
     // CHECK-NEXT: llvm.fptrunc %{{.*}} : f32 to f16
-    %result32 = std.tanh %arg_f32 : f32
+    %result32 = math.tanh %arg_f32 : f32
     // CHECK: llvm.call @__nv_tanhf(%{{.*}}) : (f32) -> f32
-    %result64 = std.tanh %arg_f64 : f64
+    %result64 = math.tanh %arg_f64 : f64
     // CHECK: llvm.call @__nv_tanh(%{{.*}}) : (f64) -> f64
     std.return %result16, %result32, %result64 : f16, f32, f64
   }
 }
 
 // -----
 
 gpu.module @test_module {
   // CHECK: llvm.func @__nv_rsqrtf(f32) -> f32
   // CHECK: llvm.func @__nv_rsqrt(f64) -> f64
   // CHECK-LABEL: func @gpu_rsqrt
   func @gpu_rsqrt(%arg_f16 : f16, %arg_f32 : f32, %arg_f64 : f64)
       -> (f16, f32, f64) {
-    %result16 = std.rsqrt %arg_f16 : f16
+    %result16 = math.rsqrt %arg_f16 : f16
     // CHECK: llvm.fpext %{{.*}} : f16 to f32
     // CHECK-NEXT: llvm.call @__nv_rsqrtf(%{{.*}}) : (f32) -> f32
     // CHECK-NEXT: llvm.fptrunc %{{.*}} : f32 to f16
-    %result32 = std.rsqrt %arg_f32 : f32
+    %result32 = math.rsqrt %arg_f32 : f32
     // CHECK: llvm.call @__nv_rsqrtf(%{{.*}}) : (f32) -> f32
-    %result64 = std.rsqrt %arg_f64 : f64
+    %result64 = math.rsqrt %arg_f64 : f64
     // CHECK: llvm.call @__nv_rsqrt(%{{.*}}) : (f64) -> f64
     std.return %result16, %result32, %result64 : f16, f32, f64
   }
 }
 
 // -----
 
 gpu.module @test_module {
   // CHECK: llvm.func @__nv_sqrtf(f32) -> f32
   // CHECK: llvm.func @__nv_sqrt(f64) -> f64
   // CHECK-LABEL: func @gpu_sqrt
   func @gpu_sqrt(%arg_f16 : f16, %arg_f32 : f32, %arg_f64 : f64)
       -> (f16, f32, f64) {
-    %result16 = std.sqrt %arg_f16 : f16
+    %result16 = math.sqrt %arg_f16 : f16
     // CHECK: llvm.fpext %{{.*}} : f16 to f32
     // CHECK-NEXT: llvm.call @__nv_sqrtf(%{{.*}}) : (f32) -> f32
     // CHECK-NEXT: llvm.fptrunc %{{.*}} : f32 to f16
-    %result32 = std.sqrt %arg_f32 : f32
+    %result32 = math.sqrt %arg_f32 : f32
     // CHECK: llvm.call @__nv_sqrtf(%{{.*}}) : (f32) -> f32
-    %result64 = std.sqrt %arg_f64 : f64
+    %result64 = math.sqrt %arg_f64 : f64
     // CHECK: llvm.call @__nv_sqrt(%{{.*}}) : (f64) -> f64
     std.return %result16, %result32, %result64 : f16, f32, f64
   }
 }
 
 // -----
 
 gpu.module @test_module {
   // CHECK: llvm.func @__nv_atanf(f32) -> f32
   // CHECK: llvm.func @__nv_atan(f64) -> f64
   // CHECK-LABEL: func @gpu_atan
   func @gpu_atan(%arg_f16 : f16, %arg_f32 : f32, %arg_f64 : f64)
       -> (f16, f32, f64) {
-    %result16 = std.atan %arg_f16 : f16
+    %result16 = math.atan %arg_f16 : f16
     // CHECK: llvm.fpext %{{.*}} : f16 to f32
     // CHECK-NEXT: llvm.call @__nv_atanf(%{{.*}}) : (f32) -> f32
     // CHECK-NEXT: llvm.fptrunc %{{.*}} : f32 to f16
-    %result32 = std.atan %arg_f32 : f32
+    %result32 = math.atan %arg_f32 : f32
     // CHECK: llvm.call @__nv_atanf(%{{.*}}) : (f32) -> f32
-    %result64 = std.atan %arg_f64 : f64
+    %result64 = math.atan %arg_f64 : f64
     // CHECK: llvm.call @__nv_atan(%{{.*}}) : (f64) -> f64
     std.return %result16, %result32, %result64 : f16, f32, f64
   }
 }
 
 // -----
 
 gpu.module @test_module {
   // CHECK: llvm.func @__nv_atan2f(f32, f32) -> f32
   // CHECK: llvm.func @__nv_atan2(f64, f64) -> f64
   // CHECK-LABEL: func @gpu_atan2
   func @gpu_atan2(%arg_f16 : f16, %arg_f32 : f32, %arg_f64 : f64)
       -> (f16, f32, f64) {
-    %result16 = std.atan2 %arg_f16, %arg_f16 : f16
+    %result16 = math.atan2 %arg_f16, %arg_f16 : f16
     // CHECK: llvm.fpext %{{.*}} : f16 to f32
     // CHECK: llvm.fpext %{{.*}} : f16 to f32
     // CHECK-NEXT: llvm.call @__nv_atan2f(%{{.*}}) : (f32, f32) -> f32
     // CHECK-NEXT: llvm.fptrunc %{{.*}} : f32 to f16
-    %result32 = std.atan2 %arg_f32, %arg_f32 : f32
+    %result32 = math.atan2 %arg_f32, %arg_f32 : f32
     // CHECK: llvm.call @__nv_atan2f(%{{.*}}) : (f32, f32) -> f32
-    %result64 = std.atan2 %arg_f64, %arg_f64 : f64
+    %result64 = math.atan2 %arg_f64, %arg_f64 : f64
     // CHECK: llvm.call @__nv_atan2(%{{.*}}) : (f64, f64) -> f64
     std.return %result16, %result32, %result64 : f16, f32, f64
   }
 }
 
 // -----
 
 // Test that we handled properly operation with SymbolTable other than module op
 gpu.module @test_module {
   "test.symbol_scope"() ({
   // CHECK: test.symbol_scope
   // CHECK: llvm.func @__nv_expf(f32) -> f32
   // CHECK: llvm.func @__nv_exp(f64) -> f64
   // CHECK-LABEL: func @gpu_exp
     func @gpu_exp(%arg_f32 : f32, %arg_f64 : f64) -> (f32, f64) {
-      %result32 = std.exp %arg_f32 : f32
+      %result32 = math.exp %arg_f32 : f32
       // CHECK: llvm.call @__nv_expf(%{{.*}}) : (f32) -> f32
-      %result64 = std.exp %arg_f64 : f64
+      %result64 = math.exp %arg_f64 : f64
       // CHECK: llvm.call @__nv_exp(%{{.*}}) : (f64) -> f64
       std.return %result32, %result64 : f32, f64
     }
     "test.finish" () : () -> ()
   }) : () -> ()
 }
 
 // -----
 
 gpu.module @test_module {
   // CHECK: llvm.func @__nv_powf(f32, f32) -> f32
   // CHECK: llvm.func @__nv_pow(f64, f64) -> f64
   // CHECK-LABEL: func @gpu_pow
   func @gpu_pow(%arg_f32 : f32, %arg_f64 : f64) -> (f32, f64) {
-    %result32 = std.powf %arg_f32, %arg_f32 : f32
+    %result32 = math.powf %arg_f32, %arg_f32 : f32
     // CHECK: llvm.call @__nv_powf(%{{.*}}, %{{.*}}) : (f32, f32) -> f32
-    %result64 = std.powf %arg_f64, %arg_f64 : f64
+    %result64 = math.powf %arg_f64, %arg_f64 : f64
     // CHECK: llvm.call @__nv_pow(%{{.*}}, %{{.*}}) : (f64, f64) -> f64
     std.return %result32, %result64 : f32, f64
   }
 }

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

 
 // -----
 
 gpu.module @test_module {
   // CHECK: llvm.func @__ocml_cos_f32(f32) -> f32
   // CHECK: llvm.func @__ocml_cos_f64(f64) -> f64
   // CHECK-LABEL: func @gpu_cos
   func @gpu_cos(%arg_f32 : f32, %arg_f64 : f64) -> (f32, f64) {
-    %result32 = std.cos %arg_f32 : f32
+    %result32 = math.cos %arg_f32 : f32
     // CHECK: llvm.call @__ocml_cos_f32(%{{.*}}) : (f32) -> f32
-    %result64 = std.cos %arg_f64 : f64
+    %result64 = math.cos %arg_f64 : f64
     // CHECK: llvm.call @__ocml_cos_f64(%{{.*}}) : (f64) -> f64
     std.return %result32, %result64 : f32, f64
   }
 }
 
 // -----
 gpu.module @test_module {
   // CHECK: llvm.func @__ocml_exp_f32(f32) -> f32
   // CHECK: llvm.func @__ocml_exp_f64(f64) -> f64
   // CHECK-LABEL: func @gpu_exp
   func @gpu_exp(%arg_f32 : f32, %arg_f64 : f64) -> (f32, f64) {
-    %exp_f32 = std.exp %arg_f32 : f32
+    %exp_f32 = math.exp %arg_f32 : f32
     // CHECK: llvm.call @__ocml_exp_f32(%{{.*}}) : (f32) -> f32
-    %result32 = std.exp %exp_f32 : f32
+    %result32 = math.exp %exp_f32 : f32
     // CHECK: llvm.call @__ocml_exp_f32(%{{.*}}) : (f32) -> f32
-    %result64 = std.exp %arg_f64 : f64
+    %result64 = math.exp %arg_f64 : f64
     // CHECK: llvm.call @__ocml_exp_f64(%{{.*}}) : (f64) -> f64
     std.return %result32, %result64 : f32, f64
   }
 }
 
 
 // -----
 
 // Test that we handled properly operation with SymbolTable other than module op
 gpu.module @test_module {
   "test.symbol_scope"() ({
     // CHECK: test.symbol_scope
     // CHECK: llvm.func @__ocml_exp_f32(f32) -> f32
     // CHECK: llvm.func @__ocml_exp_f64(f64) -> f64
     // CHECK-LABEL: func @gpu_exp
     func @gpu_exp(%arg_f32 : f32, %arg_f64 : f64) -> (f32, f64) {
-      %exp_f32 = std.exp %arg_f32 : f32
+      %exp_f32 = math.exp %arg_f32 : f32
       // CHECK: llvm.call @__ocml_exp_f32(%{{.*}}) : (f32) -> f32
-      %result32 = std.exp %exp_f32 : f32
+      %result32 = math.exp %exp_f32 : f32
       // CHECK: llvm.call @__ocml_exp_f32(%{{.*}}) : (f32) -> f32
-      %result64 = std.exp %arg_f64 : f64
+      %result64 = math.exp %arg_f64 : f64
       // CHECK: llvm.call @__ocml_exp_f64(%{{.*}}) : (f64) -> f64
       std.return %result32, %result64 : f32, f64
     }
     "test.finish" () : () -> ()
   }) : () -> ()
 }
 
 // -----
 
 gpu.module @test_module {
   // CHECK: llvm.func @__ocml_log_f32(f32) -> f32
   // CHECK: llvm.func @__ocml_log_f64(f64) -> f64
   // CHECK-LABEL: func @gpu_log
   func @gpu_log(%arg_f32 : f32, %arg_f64 : f64) -> (f32, f64) {
-    %result32 = std.log %arg_f32 : f32
+    %result32 = math.log %arg_f32 : f32
     // CHECK: llvm.call @__ocml_log_f32(%{{.*}}) : (f32) -> f32
-    %result64 = std.log %arg_f64 : f64
+    %result64 = math.log %arg_f64 : f64
     // CHECK: llvm.call @__ocml_log_f64(%{{.*}}) : (f64) -> f64
     std.return %result32, %result64 : f32, f64
   }
 }
 
 // -----
 
 gpu.module @test_module {
   // CHECK: llvm.func @__ocml_log1p_f32(f32) -> f32
   // CHECK: llvm.func @__ocml_log1p_f64(f64) -> f64
   // CHECK-LABEL: func @gpu_log1p
   func @gpu_log1p(%arg_f32 : f32, %arg_f64 : f64) -> (f32, f64) {
-    %result32 = std.log1p %arg_f32 : f32
+    %result32 = math.log1p %arg_f32 : f32
     // CHECK: llvm.call @__ocml_log1p_f32(%{{.*}}) : (f32) -> f32
-    %result64 = std.log1p %arg_f64 : f64
+    %result64 = math.log1p %arg_f64 : f64
     // CHECK: llvm.call @__ocml_log1p_f64(%{{.*}}) : (f64) -> f64
     std.return %result32, %result64 : f32, f64
   }
 }
 
 // -----
 
 gpu.module @test_module {
   // CHECK: llvm.func @__ocml_log10_f32(f32) -> f32
   // CHECK: llvm.func @__ocml_log10_f64(f64) -> f64
   // CHECK-LABEL: func @gpu_log10
   func @gpu_log10(%arg_f32 : f32, %arg_f64 : f64) -> (f32, f64) {
-    %result32 = std.log10 %arg_f32 : f32
+    %result32 = math.log10 %arg_f32 : f32
     // CHECK: llvm.call @__ocml_log10_f32(%{{.*}}) : (f32) -> f32
-    %result64 = std.log10 %arg_f64 : f64
+    %result64 = math.log10 %arg_f64 : f64
     // CHECK: llvm.call @__ocml_log10_f64(%{{.*}}) : (f64) -> f64
     std.return %result32, %result64 : f32, f64
   }
 }
 
 // -----
 
 gpu.module @test_module {
   // CHECK: llvm.func @__ocml_log2_f32(f32) -> f32
   // CHECK: llvm.func @__ocml_log2_f64(f64) -> f64
   // CHECK-LABEL: func @gpu_log2
   func @gpu_log2(%arg_f32 : f32, %arg_f64 : f64) -> (f32, f64) {
-    %result32 = std.log2 %arg_f32 : f32
+    %result32 = math.log2 %arg_f32 : f32
     // CHECK: llvm.call @__ocml_log2_f32(%{{.*}}) : (f32) -> f32
-    %result64 = std.log2 %arg_f64 : f64
+    %result64 = math.log2 %arg_f64 : f64
     // CHECK: llvm.call @__ocml_log2_f64(%{{.*}}) : (f64) -> f64
     std.return %result32, %result64 : f32, f64
   }
 }
 
 // -----
 
 gpu.module @test_module {
   // CHECK: llvm.func @__ocml_rsqrt_f32(f32) -> f32
   // CHECK: llvm.func @__ocml_rsqrt_f64(f64) -> f64
   // CHECK-LABEL: func @gpu_rsqrt
   func @gpu_rsqrt(%arg_f16 : f16, %arg_f32 : f32, %arg_f64 : f64)
       -> (f16, f32, f64) {
-    %result16 = std.rsqrt %arg_f16 : f16
+    %result16 = math.rsqrt %arg_f16 : f16
     // CHECK: llvm.fpext %{{.*}} : f16 to f32
     // CHECK-NEXT: llvm.call @__ocml_rsqrt_f32(%{{.*}}) : (f32) -> f32
     // CHECK-NEXT: llvm.fptrunc %{{.*}} : f32 to f16
-    %result32 = std.rsqrt %arg_f32 : f32
+    %result32 = math.rsqrt %arg_f32 : f32
     // CHECK: llvm.call @__ocml_rsqrt_f32(%{{.*}}) : (f32) -> f32
-    %result64 = std.rsqrt %arg_f64 : f64
+    %result64 = math.rsqrt %arg_f64 : f64
     // CHECK: llvm.call @__ocml_rsqrt_f64(%{{.*}}) : (f64) -> f64
     std.return %result16, %result32, %result64 : f16, f32, f64
   }
 }
 
 // -----
 
 gpu.module @test_module {
   // CHECK: llvm.func @__ocml_sqrt_f32(f32) -> f32
   // CHECK: llvm.func @__ocml_sqrt_f64(f64) -> f64
   // CHECK-LABEL: func @gpu_sqrt
   func @gpu_sqrt(%arg_f16 : f16, %arg_f32 : f32, %arg_f64 : f64)
       -> (f16, f32, f64) {
-    %result16 = std.sqrt %arg_f16 : f16
+    %result16 = math.sqrt %arg_f16 : f16
     // CHECK: llvm.fpext %{{.*}} : f16 to f32
     // CHECK-NEXT: llvm.call @__ocml_sqrt_f32(%{{.*}}) : (f32) -> f32
     // CHECK-NEXT: llvm.fptrunc %{{.*}} : f32 to f16
-    %result32 = std.sqrt %arg_f32 : f32
+    %result32 = math.sqrt %arg_f32 : f32
     // CHECK: llvm.call @__ocml_sqrt_f32(%{{.*}}) : (f32) -> f32
-    %result64 = std.sqrt %arg_f64 : f64
+    %result64 = math.sqrt %arg_f64 : f64
     // CHECK: llvm.call @__ocml_sqrt_f64(%{{.*}}) : (f64) -> f64
     std.return %result16, %result32, %result64 : f16, f32, f64
   }
 }
 
 // -----
 
 gpu.module @test_module {
   // CHECK: llvm.func @__ocml_tanh_f32(f32) -> f32
   // CHECK: llvm.func @__ocml_tanh_f64(f64) -> f64
   // CHECK-LABEL: func @gpu_tanh
   func @gpu_tanh(%arg_f32 : f32, %arg_f64 : f64) -> (f32, f64) {
-    %result32 = std.tanh %arg_f32 : f32
+    %result32 = math.tanh %arg_f32 : f32
     // CHECK: llvm.call @__ocml_tanh_f32(%{{.*}}) : (f32) -> f32
-    %result64 = std.tanh %arg_f64 : f64
+    %result64 = math.tanh %arg_f64 : f64
     // CHECK: llvm.call @__ocml_tanh_f64(%{{.*}}) : (f64) -> f64
     std.return %result32, %result64 : f32, f64
   }
 }
 
 // -----
 
 gpu.module @test_module {
   // CHECK: llvm.func @__ocml_atan_f32(f32) -> f32
   // CHECK: llvm.func @__ocml_atan_f64(f64) -> f64
   // CHECK-LABEL: func @gpu_atan
   func @gpu_atan(%arg_f32 : f32, %arg_f64 : f64) -> (f32, f64) {
-    %result32 = std.atan %arg_f32 : f32
+    %result32 = math.atan %arg_f32 : f32
     // CHECK: llvm.call @__ocml_atan_f32(%{{.*}}) : (f32) -> f32
-    %result64 = std.atan %arg_f64 : f64
+    %result64 = math.atan %arg_f64 : f64
     // CHECK: llvm.call @__ocml_atan_f64(%{{.*}}) : (f64) -> f64
     std.return %result32, %result64 : f32, f64
   }
 }
 
 // -----
 
 gpu.module @test_module {
   // CHECK: llvm.func @__ocml_atan2_f32(f32, f32) -> f32
   // CHECK: llvm.func @__ocml_atan2_f64(f64, f64) -> f64
   // CHECK-LABEL: func @gpu_atan2
   func @gpu_atan2(%arg_f32 : f32, %arg_f64 : f64) -> (f32, f64) {
-    %result32 = std.atan2 %arg_f32, %arg_f32 : f32
+    %result32 = math.atan2 %arg_f32, %arg_f32 : f32
     // CHECK: llvm.call @__ocml_atan2_f32(%{{.*}}) : (f32, f32) -> f32
-    %result64 = std.atan2 %arg_f64, %arg_f64 : f64
+    %result64 = math.atan2 %arg_f64, %arg_f64 : f64
     // CHECK: llvm.call @__ocml_atan2_f64(%{{.*}}) : (f64, f64) -> f64
     std.return %result32, %result64 : f32, f64
   }
 }
 
 // -----
 
 gpu.module @test_module {
   // CHECK: llvm.func @__ocml_pow_f32(f32, f32) -> f32
   // CHECK: llvm.func @__ocml_pow_f64(f64, f64) -> f64
   // CHECK-LABEL: func @gpu_pow
   func @gpu_pow(%arg_f32 : f32, %arg_f64 : f64) -> (f32, f64) {
-    %result32 = std.powf %arg_f32, %arg_f32 : f32
+    %result32 = math.powf %arg_f32, %arg_f32 : f32
     // CHECK: llvm.call @__ocml_pow_f32(%{{.*}}, %{{.*}}) : (f32, f32) -> f32
-    %result64 = std.powf %arg_f64, %arg_f64 : f64
+    %result64 = math.powf %arg_f64, %arg_f64 : f64
     // CHECK: llvm.call @__ocml_pow_f64(%{{.*}}, %{{.*}}) : (f64, f64) -> f64
     std.return %result32, %result64 : f32, f64
   }
 }

mlir/test/Conversion/StandardToLLVM/convert-to-llvmir.mlir

// CHECK-NEXT:  %9 = llvm.frem %arg0, %arg1 : f32
   %9 = remf %arg0, %arg1 : f32
 // CHECK-NEXT: %10 = llvm.and %arg2, %arg3 : i32
   %10 = and %arg2, %arg3 : i32
 // CHECK-NEXT: %11 = llvm.or %arg2, %arg3 : i32
   %11 = or %arg2, %arg3 : i32
 // CHECK-NEXT: %12 = llvm.xor %arg2, %arg3 : i32
   %12 = xor %arg2, %arg3 : i32
 // CHECK-NEXT: %13 = "llvm.intr.exp"(%arg0) : (f32) -> f32
-  %13 = std.exp %arg0 : f32
+  %13 = math.exp %arg0 : f32
 // CHECK-NEXT: %14 = "llvm.intr.exp2"(%arg0) : (f32) -> f32
-  %14 = std.exp2 %arg0 : f32
+  %14 = math.exp2 %arg0 : f32
 // CHECK-NEXT: %15 = llvm.mlir.constant(7.900000e-01 : f64) : f64
   %15 = constant 7.9e-01 : f64
 // CHECK-NEXT: %16 = llvm.shl %arg2, %arg3 : i32
   %16 = shift_left %arg2, %arg3 : i32
 // CHECK-NEXT: %17 = llvm.ashr %arg2, %arg3 : i32
   %17 = shift_right_signed %arg2, %arg3 : i32
 // CHECK-NEXT: %18 = llvm.lshr %arg2, %arg3 : i32
   %18 = shift_right_unsigned %arg2, %arg3 : i32
 // CHECK-NEXT: %{{[0-9]+}} = "llvm.intr.sqrt"(%arg0) : (f32) -> f32
-  %19 = std.sqrt %arg0 : f32
+  %19 = math.sqrt %arg0 : f32
 // CHECK-NEXT: %{{[0-9]+}} = "llvm.intr.sqrt"(%arg4) : (f64) -> f64
-  %20 = std.sqrt %arg4 : f64
+  %20 = math.sqrt %arg4 : f64
   return %0, %4 : f32, i32
 }
 
 // Checking conversion of index types to integers using i1, assuming no target
 // system would have a 1-bit address space.  Otherwise, we would have had to
 // make this test dependent on the pointer size on the target system.
 // CHECK-LABEL: @index_cast
 func @index_cast(%arg0: index, %arg1: i1) {

mlir/test/Conversion/StandardToLLVM/standard-to-llvm.mlir

 // -----
 
 // CHECK-LABEL: func @rsqrt(
 // CHECK-SAME: f32
 func @rsqrt(%arg0 : f32) {
   // CHECK: %[[ONE:.*]] = llvm.mlir.constant(1.000000e+00 : f32) : f32
   // CHECK: %[[SQRT:.*]] = "llvm.intr.sqrt"(%arg0) : (f32) -> f32
   // CHECK: %[[DIV:.*]] = llvm.fdiv %[[ONE]], %[[SQRT]] : f32
-  %0 = rsqrt %arg0 : f32
+  %0 = math.rsqrt %arg0 : f32
   std.return
 }
 
 // -----
 
 // CHECK-LABEL: func @sine(
 // CHECK-SAME: f32
 func @sine(%arg0 : f32) {
   // CHECK: "llvm.intr.sin"(%arg0) : (f32) -> f32
-  %0 = sin %arg0 : f32
+  %0 = math.sin %arg0 : f32
   std.return
 }
 
 // -----
 
 // CHECK-LABEL: func @ceilf(
 // CHECK-SAME: f32
 func @ceilf(%arg0 : f32) {

 
 
 // CHECK-LABEL: func @rsqrt_double(
 // CHECK-SAME: f64
 func @rsqrt_double(%arg0 : f64) {
   // CHECK: %[[ONE:.*]] = llvm.mlir.constant(1.000000e+00 : f64) : f64
   // CHECK: %[[SQRT:.*]] = "llvm.intr.sqrt"(%arg0) : (f64) -> f64
   // CHECK: %[[DIV:.*]] = llvm.fdiv %[[ONE]], %[[SQRT]] : f64
-  %0 = rsqrt %arg0 : f64
+  %0 = math.rsqrt %arg0 : f64
   std.return
 }
 
 // -----
 
 // CHECK-LABEL: func @rsqrt_vector(
 // CHECK-SAME: vector<4xf32>
 func @rsqrt_vector(%arg0 : vector<4xf32>) {
   // CHECK: %[[ONE:.*]] = llvm.mlir.constant(dense<1.000000e+00> : vector<4xf32>) : vector<4xf32>
   // CHECK: %[[SQRT:.*]] = "llvm.intr.sqrt"(%arg0) : (vector<4xf32>) -> vector<4xf32>
   // CHECK: %[[DIV:.*]] = llvm.fdiv %[[ONE]], %[[SQRT]] : vector<4xf32>
-  %0 = rsqrt %arg0 : vector<4xf32>
+  %0 = math.rsqrt %arg0 : vector<4xf32>
   std.return
 }
 
 // -----
 
 // CHECK-LABEL: func @rsqrt_multidim_vector(
 // CHECK-SAME: !llvm.array<4 x vector<3xf32>>
 func @rsqrt_multidim_vector(%arg0 : vector<4x3xf32>) {
   // CHECK: %[[EXTRACT:.*]] = llvm.extractvalue %arg0[0] : !llvm.array<4 x vector<3xf32>>
   // CHECK: %[[ONE:.*]] = llvm.mlir.constant(dense<1.000000e+00> : vector<3xf32>) : vector<3xf32>
   // CHECK: %[[SQRT:.*]] = "llvm.intr.sqrt"(%[[EXTRACT]]) : (vector<3xf32>) -> vector<3xf32>
   // CHECK: %[[DIV:.*]] = llvm.fdiv %[[ONE]], %[[SQRT]] : vector<3xf32>
   // CHECK: %[[INSERT:.*]] = llvm.insertvalue %[[DIV]], %0[0] : !llvm.array<4 x vector<3xf32>>
-  %0 = rsqrt %arg0 : vector<4x3xf32>
+  %0 = math.rsqrt %arg0 : vector<4x3xf32>
   std.return
 }
 
 // -----
 
 // Lowers `assert` to a function call to `abort` if the assertion is violated.
 // CHECK: llvm.func @abort()
 // CHECK-LABEL: @assert_test_function

 func private @zero_result_func()
 
 // -----
 
 // CHECK-LABEL: func @powf(
 // CHECK-SAME: f64
 func @powf(%arg0 : f64) {
   // CHECK: %[[POWF:.*]] = "llvm.intr.pow"(%arg0, %arg0) : (f64, f64) -> f64
-  %0 = std.powf %arg0, %arg0 : f64
+  %0 = math.powf %arg0, %arg0 : f64
   std.return
 }

mlir/test/Conversion/StandardToSPIRV/std-ops-to-spirv.mlir

 // Check float unary operation conversions.
 // CHECK-LABEL: @float32_unary_scalar
 func @float32_unary_scalar(%arg0: f32) {
   // CHECK: spv.GLSL.FAbs %{{.*}}: f32
   %0 = absf %arg0 : f32
   // CHECK: spv.GLSL.Ceil %{{.*}}: f32
   %1 = ceilf %arg0 : f32
   // CHECK: spv.GLSL.Cos %{{.*}}: f32
-  %2 = cos %arg0 : f32
+  %2 = math.cos %arg0 : f32
   // CHECK: spv.GLSL.Exp %{{.*}}: f32
-  %3 = exp %arg0 : f32
+  %3 = math.exp %arg0 : f32
   // CHECK: spv.GLSL.Log %{{.*}}: f32
-  %4 = log %arg0 : f32
+  %4 = math.log %arg0 : f32
   // CHECK: spv.FNegate %{{.*}}: f32
   %5 = negf %arg0 : f32
   // CHECK: spv.GLSL.InverseSqrt %{{.*}}: f32
-  %6 = rsqrt %arg0 : f32
+  %6 = math.rsqrt %arg0 : f32
   // CHECK: spv.GLSL.Sqrt %{{.*}}: f32
-  %7 = sqrt %arg0 : f32
+  %7 = math.sqrt %arg0 : f32
   // CHECK: spv.GLSL.Tanh %{{.*}}: f32
-  %8 = tanh %arg0 : f32
+  %8 = math.tanh %arg0 : f32
   // CHECK: spv.GLSL.Sin %{{.*}}: f32
-  %9 = sin %arg0 : f32
+  %9 = math.sin %arg0 : f32
   // CHECK: spv.GLSL.Floor %{{.*}}: f32
   %10 = floorf %arg0 : f32
   return
 }
 
 // Check float binary operation conversions.
 // CHECK-LABEL: @float32_binary_scalar
 func @float32_binary_scalar(%lhs: f32, %rhs: f32) {

mlir/test/Conversion/StandardToSPIRV/subview-to-spirv.mlir

func @fold_static_stride_subview
         %arg2 : index, %arg3 : index, %arg4 : index) {
   // CHECK-DAG: %[[C2:.*]] = constant 2
   // CHECK-DAG: %[[C3:.*]] = constant 3
   //     CHECK: %[[T0:.*]] = muli %[[ARG3]], %[[C3]]
   //     CHECK: %[[T1:.*]] = addi %[[ARG1]], %[[T0]]
   //     CHECK: %[[T2:.*]] = muli %[[ARG4]], %[[ARG2]]
   //     CHECK: %[[T3:.*]] = addi %[[T2]], %[[C2]]
   //     CHECK: %[[LOADVAL:.*]] = load %[[ARG0]][%[[T1]], %[[T3]]]
-  //     CHECK: %[[STOREVAL:.*]] = sqrt %[[LOADVAL]]
+  //     CHECK: %[[STOREVAL:.*]] = math.sqrt %[[LOADVAL]]
   //     CHECK: %[[T6:.*]] = muli %[[ARG3]], %[[C3]]
   //     CHECK: %[[T7:.*]] = addi %[[ARG1]], %[[T6]]
   //     CHECK: %[[T8:.*]] = muli %[[ARG4]], %[[ARG2]]
   //     CHECK: %[[T9:.*]] = addi %[[T8]], %[[C2]]
   //     CHECK: store %[[STOREVAL]], %[[ARG0]][%[[T7]], %[[T9]]]
   %0 = subview %arg0[%arg1, 2][4, 4][3, %arg2] : memref<12x32xf32> to memref<4x4xf32, offset:?, strides: [96, ?]>
   %1 = load %0[%arg3, %arg4] : memref<4x4xf32, offset:?, strides: [96, ?]>
-  %2 = sqrt %1 : f32
+  %2 = math.sqrt %1 : f32
   store %2, %0[%arg3, %arg4] : memref<4x4xf32, offset:?, strides: [96, ?]>
   return
 }
 
 } // end module

mlir/test/Dialect/Linalg/bufferize.mlir

 // CHECK-LABEL:   func @basic(
 // CHECK-SAME:                %[[TENSOR:.*]]: tensor<4xf32>) -> tensor<4xf32> {
 // CHECK:           %[[MEMREF:.*]] = tensor_to_memref %[[TENSOR]] : memref<4xf32>
 // CHECK:           %[[RESULT_MEMREF:.*]] = alloc() : memref<4xf32>
 // CHECK:           linalg.generic {indexing_maps = [#map, #map], iterator_types = ["parallel"]}
 // CHECK-SAME:      ins(%[[MEMREF]] : memref<4xf32>)
 // CHECK-SAME:      outs(%[[RESULT_MEMREF]] : memref<4xf32>) {
 // CHECK:           ^bb0(%[[RESULT1:.*]]: f32, %[[UNUSED:.*]]: f32):
-// CHECK:             %[[DIM1:.*]] = exp %[[RESULT1]] : f32
+// CHECK:             %[[DIM1:.*]] = math.exp %[[RESULT1]] : f32
 // CHECK:             linalg.yield %[[DIM1]] : f32
 // CHECK:           }
 // CHECK:           %[[RESULT:.*]] = tensor_load %[[RESULT_MEMREF]] : memref<4xf32>
 // CHECK:           return %[[RESULT]] : tensor<4xf32>
 func @basic(%arg0: tensor<4xf32>) -> tensor<4xf32> {
     %0 = linalg.generic {
       indexing_maps = [#map0, #map0],
       iterator_types = ["parallel"]
     } ins(%arg0 : tensor<4xf32>)
       outs(%arg0 : tensor<4xf32>) {
       ^bb0(%gen_arg1: f32, %out: f32):
-        %tmp1 = exp %gen_arg1 : f32
+        %tmp1 = math.exp %gen_arg1 : f32
         linalg.yield %tmp1 : f32
     } -> tensor<4xf32>
     return %0 : tensor<4xf32>
 }
 
 
 // -----
 

 func @init_tensor(%in : tensor<?xf32>, %size: index) -> tensor<?xf32> {
   %init = linalg.init_tensor [%size] : tensor<?xf32>
   %0 = linalg.generic {
     indexing_maps = [#map0, #map0],
     iterator_types = ["parallel"]
   } ins(%in : tensor<?xf32>)
     outs(%init : tensor<?xf32>) {
     ^bb0(%gen_arg1: f32, %out: f32):
-      %tmp1 = exp %gen_arg1 : f32
+      %tmp1 = math.exp %gen_arg1 : f32
       linalg.yield %tmp1 : f32
   } -> tensor<?xf32>
   return %0 : tensor<?xf32>
 }
 
 
 // -----
 
 #map0 = affine_map<(d0) -> (d0)>
 
 // CHECK-LABEL:   func @multiple_results
 // CHECK:           %[[RESULT0:.*]] = alloc() : memref<4xf32>
 // CHECK:           %[[RESULT1:.*]] = alloc() : memref<4xf32>
 // CHECK:           linalg.generic
 // CHECK-SAME:      ins(%{{.*}} : memref<4xf32>)
 // CHECK-SAME:      outs(%[[RESULT0]], %[[RESULT1]] : memref<4xf32>, memref<4xf32>)
 // CHECK-NEXT: ^bb0(%{{.*}}: f32, %{{.*}}: f32, %{{.*}}: f32):
 func @multiple_results(%arg0: tensor<4xf32>) -> (tensor<4xf32>, tensor<4xf32>) {
     %0, %1 = linalg.generic {
       indexing_maps = [#map0, #map0, #map0],
       iterator_types = ["parallel"]
     } ins(%arg0 : tensor<4xf32>)
       outs (%arg0, %arg0 : tensor<4xf32>, tensor<4xf32>) {
       ^bb0(%gen_arg1: f32, %out1: f32, %out2: f32):
-        %tmp1 = exp %gen_arg1 : f32
+        %tmp1 = math.exp %gen_arg1 : f32
         linalg.yield %tmp1, %tmp1 : f32, f32
     } -> tensor<4xf32>, tensor<4xf32>
     return %0, %1 : tensor<4xf32>, tensor<4xf32>
 }
 
 // -----
 
 #map0 = affine_map<(d0) -> (d0)>

 func @dynamic_results(%arg0: tensor<?x?xf32>)
          -> (tensor<?x?xf32>, tensor<?x?xf32>) {
     %0, %1 = linalg.generic {
       indexing_maps = [#map_2d, #map_2d, #map_2d],
       iterator_types = ["parallel", "parallel"]
     } ins(%arg0 : tensor<?x?xf32>)
       outs (%arg0, %arg0 : tensor<?x?xf32>, tensor<?x?xf32>) {
       ^bb0(%gen_arg1: f32, %out1: f32, %out2: f32):
-        %tmp1 = exp %gen_arg1 : f32
+        %tmp1 = math.exp %gen_arg1 : f32
         linalg.yield %tmp1, %tmp1 : f32, f32
     } -> tensor<?x?xf32>, tensor<?x?xf32>
     return %0, %1 : tensor<?x?xf32>, tensor<?x?xf32>
 }
 
 // -----
 
 #accesses = [

mlir/test/Dialect/Linalg/convert-elementwise-to-linalg.mlir

 // Check a unary op.
 // CHECK-LABEL: func @exp
 //  CHECK-SAME:   %[[ARG0:[0-9a-zA-Z]*]]: tensor<f32>
 func @exp(%arg0: tensor<f32>) -> tensor<f32> {
   // CHECK: linalg.generic
   // CHECK-SAME:  ins(%[[ARG0]]
   // CHECK-SAME: outs(%[[ARG0]]
   // CHECK: ^bb0(%[[SCALAR:.*]]: f32, %{{.*}}: f32):
-  // CHECK:   %[[YIELD:.*]] = exp %[[SCALAR]] : f32
+  // CHECK:   %[[YIELD:.*]] = math.exp %[[SCALAR]] : f32
   // CHECK:   linalg.yield %[[YIELD]] : f32
-  %0 = exp %arg0 : tensor<f32>
+  %0 = math.exp %arg0 : tensor<f32>
   return %0 : tensor<f32>
 }
 
 // -----
 
 // Check a case with varying operand types.
 // CHECK-LABEL: func @select
 //  CHECK-SAME:   %[[ARG0:[0-9a-zA-Z]*]]: tensor<i1>

mlir/test/Dialect/Linalg/fusion.mlir

scf.for %j = %c0 to %3 step %c1 {
       %7 = std.subview %arg2[%i, %j][%c1, %c1][%c1, %c1] :
       memref<100x10xf32> to memref<?x?xf32, #map2>
       linalg.generic {
         indexing_maps = [#map1, #map1],
         iterator_types = ["parallel", "parallel"]}
         ins(%6 : memref<?x?xf32, #map2>)
        outs(%7 : memref<?x?xf32, #map2>) {
           ^bb0(%arg3: f32, %arg4: f32):     // no predecessors
-            %8 = exp %arg3 : f32
+            %8 = math.exp %arg3 : f32
             linalg.yield %8 : f32
           }
     }
   }
  dealloc %1 : memref<100x10xf32>
  return
 }
 // CHECK-LABEL: func @fusion

mlir/test/Dialect/Linalg/vectorization.mlir

func @generic_vectorize(%arg0: memref<4x256xf32>,
   //       CHECK:   %[[ADD:.*]] = addf %[[V0B]], %[[V1]] : vector<4x256xf32>
     %6 = addf %arg4, %arg6 : f32
   //       CHECK:   %[[CMP:.*]] = cmpf ogt, %[[V2]], %[[V1]] : vector<4x256xf32>
     %7 = cmpf ogt, %arg3, %arg6 : f32
   //       CHECK:   %[[ARG3B:.*]] = vector.broadcast %[[ARG3]] : f32 to vector<4x256xf32>
     %8 = constant 2.0 : f32
   //       CHECK:   %[[DIV:.*]] = divf %[[V3]], %[[ARG3B]] : vector<4x256xf32>
     %9 = divf %arg5, %i : f32
-  //       CHECK:   %[[EXP:.*]] = exp2 %[[V3]] : vector<4x256xf32>
-    %10 = exp2 %arg5 : f32
+  //       CHECK:   %[[EXP:.*]] = math.exp2 %[[V3]] : vector<4x256xf32>
+    %10 = math.exp2 %arg5 : f32
   //       CHECK:   %[[MUL:.*]] = mulf %[[V3]], %[[CST0]] : vector<4x256xf32>
     %11 = mulf %arg5, %8 : f32
-  //       CHECK:   %[[RSQRT:.*]] = rsqrt %[[V3]] : vector<4x256xf32>
-    %12 = rsqrt %arg5 : f32
+  //       CHECK:   %[[RSQRT:.*]] = math.rsqrt %[[V3]] : vector<4x256xf32>
+    %12 = math.rsqrt %arg5 : f32
   //       CHECK:   %[[SEL:.*]] = select %[[CMP]], %[[V3]], %[[V1]] : vector<4x256xi1>, vector<4x256xf32>
     %13 = select %7, %arg5, %arg6 : f32
   //       CHECK:   %[[V0B:.*]] = vector.broadcast %[[V0]] : vector<256xf32> to vector<4x256xf32>
   //       CHECK:   %[[SUB:.*]] = subf %[[V3]], %[[V0B]] : vector<4x256xf32>
     %14 = subf %arg5, %arg4 : f32
-  //       CHECK:   %[[TAN:.*]] = tanh %[[V3]] : vector<4x256xf32>
-    %15 = tanh %arg5 : f32
+  //       CHECK:   %[[TAN:.*]] = math.tanh %[[V3]] : vector<4x256xf32>
+    %15 = math.tanh %arg5 : f32
   //       CHECK:   vector.transfer_write %[[ADD]], %[[ARG0]][%[[C0]], %[[C0]]] {{.*}} : vector<4x256xf32>, memref<4x256xf32>
   //       CHECK:   vector.transfer_write %[[CST0]], %[[ARG0]][%[[C0]], %[[C0]]] {{.*}} : vector<4x256xf32>, memref<4x256xf32>
   //       CHECK:   vector.transfer_write %[[CST1]], %[[ARG0]][%[[C0]], %[[C0]]] {{.*}} : vector<4x256xf32>, memref<4x256xf32>
   //       CHECK:   vector.transfer_write %[[DIV]], %[[ARG0]][%[[C0]], %[[C0]]] {{.*}} : vector<4x256xf32>, memref<4x256xf32>
   //       CHECK:   vector.transfer_write %[[EXP]], %[[ARG0]][%[[C0]], %[[C0]]] {{.*}} : vector<4x256xf32>, memref<4x256xf32>
   //       CHECK:   vector.transfer_write %[[MUL]], %[[ARG0]][%[[C0]], %[[C0]]] {{.*}} : vector<4x256xf32>, memref<4x256xf32>
   //       CHECK:   vector.transfer_write %[[RSQRT]], %[[ARG0]][%[[C0]], %[[C0]]] {{.*}} : vector<4x256xf32>, memref<4x256xf32>
   //       CHECK:   vector.transfer_write %[[SEL]], %[[ARG0]][%[[C0]], %[[C0]]] {{.*}} : vector<4x256xf32>, memref<4x256xf32>
func @generic_vectorize_tensor(%arg0: tensor<4x256xf32>,
   //       CHECK:   %[[ADD:.*]] = addf %[[V0B]], %[[V1]] : vector<4x256xf32>
     %6 = addf %arg4, %arg6 : f32
   //       CHECK:   %[[CMP:.*]] = cmpf ogt, %[[V2]], %[[V1]] : vector<4x256xf32>
     %7 = cmpf ogt, %arg3, %arg6 : f32
   //       CHECK:   %[[ARG3B:.*]] = vector.broadcast %[[ARG3]] : f32 to vector<4x256xf32>
     %8 = constant 2.0 : f32
   //       CHECK:   %[[DIV:.*]] = divf %[[V3]], %[[ARG3B]] : vector<4x256xf32>
     %9 = divf %arg5, %i : f32
-  //       CHECK:   %[[EXP:.*]] = exp2 %[[V3]] : vector<4x256xf32>
-    %10 = exp2 %arg5 : f32
+  //       CHECK:   %[[EXP:.*]] = math.exp2 %[[V3]] : vector<4x256xf32>
+    %10 = math.exp2 %arg5 : f32
   //       CHECK:   %[[MUL:.*]] = mulf %[[V3]], %[[CST0]] : vector<4x256xf32>
     %11 = mulf %arg5, %8 : f32
-  //       CHECK:   %[[RSQRT:.*]] = rsqrt %[[V3]] : vector<4x256xf32>
-    %12 = rsqrt %arg5 : f32
+  //       CHECK:   %[[RSQRT:.*]] = math.rsqrt %[[V3]] : vector<4x256xf32>
+    %12 = math.rsqrt %arg5 : f32
   //       CHECK:   %[[SEL:.*]] = select %[[CMP]], %[[V3]], %[[V1]] : vector<4x256xi1>, vector<4x256xf32>
     %13 = select %7, %arg5, %arg6 : f32
   //       CHECK:   %[[V0B:.*]] = vector.broadcast %[[V0]] : vector<256xf32> to vector<4x256xf32>
   //       CHECK:   %[[SUB:.*]] = subf %[[V3]], %[[V0B]] : vector<4x256xf32>
     %14 = subf %arg5, %arg4 : f32
-  //       CHECK:   %[[TAN:.*]] = tanh %[[V3]] : vector<4x256xf32>
-    %15 = tanh %arg5 : f32
+  //       CHECK:   %[[TAN:.*]] = math.tanh %[[V3]] : vector<4x256xf32>
+    %15 = math.tanh %arg5 : f32
   //       CHECK:   %[[R0:.*]] = vector.transfer_write %[[ADD]], %[[ARG0]][%[[C0]], %[[C0]]] {{.*}} : vector<4x256xf32>, tensor<4x256xf32>
   //       CHECK:   %[[R1:.*]] = vector.transfer_write %[[CST0]], %[[ARG0]][%[[C0]], %[[C0]]] {{.*}} : vector<4x256xf32>, tensor<4x256xf32>
   //       CHECK:   %[[R2:.*]] = vector.transfer_write %[[CST1]], %[[ARG0]][%[[C0]], %[[C0]]] {{.*}} : vector<4x256xf32>, tensor<4x256xf32>
   //       CHECK:   %[[R3:.*]] = vector.transfer_write %[[DIV]], %[[ARG0]][%[[C0]], %[[C0]]] {{.*}} : vector<4x256xf32>, tensor<4x256xf32>
   //       CHECK:   %[[R4:.*]] = vector.transfer_write %[[EXP]], %[[ARG0]][%[[C0]], %[[C0]]] {{.*}} : vector<4x256xf32>, tensor<4x256xf32>
   //       CHECK:   %[[R5:.*]] = vector.transfer_write %[[MUL]], %[[ARG0]][%[[C0]], %[[C0]]] {{.*}} : vector<4x256xf32>, tensor<4x256xf32>
   //       CHECK:   %[[R6:.*]] = vector.transfer_write %[[RSQRT]], %[[ARG0]][%[[C0]], %[[C0]]] {{.*}} : vector<4x256xf32>, tensor<4x256xf32>
   //       CHECK:   %[[R7:.*]] = vector.transfer_write %[[SEL]], %[[ARG0]][%[[C0]], %[[C0]]] {{.*}} : vector<4x256xf32>, tensor<4x256xf32>

mlir/test/Dialect/Math/ops.mlir

+// RUN: mlir-opt %s | mlir-opt | FileCheck %s
+// RUN: mlir-opt %s --mlir-print-op-generic | mlir-opt | FileCheck %s
+
+// CHECK-LABEL: func @exp(
+// CHECK-SAME:            %[[F:.*]]: f32, %[[V:.*]]: vector<4xf32>, %[[T:.*]]: tensor<4x4x?xf32>)
+func @exp(%f: f32, %v: vector<4xf32>, %t: tensor<4x4x?xf32>) {
+  // CHECK: %{{.*}} = math.exp %[[F]] : f32
+  %0 = math.exp %f : f32
+  // CHECK: %{{.*}} = math.exp %[[V]] : vector<4xf32>
+  %1 = math.exp %v : vector<4xf32>
+  // CHECK: %{{.*}} = math.exp %[[T]] : tensor<4x4x?xf32>
+  %2 = math.exp %t : tensor<4x4x?xf32>
+  return
+}

mlir/test/Dialect/SCF/parallel-loop-fusion.mlir

scf.parallel (%i, %j) = (%c0, %c0) to (%c100, %c10) step (%c1, %c1) {
     %lhs_elem = load %lhs[%i, %j] : memref<100x10xf32>
     %broadcast_rhs_elem = load %broadcast_rhs[%i, %j] : memref<100x10xf32>
     %diff_elem = subf %lhs_elem, %broadcast_rhs_elem : f32
     store %diff_elem, %diff[%i, %j] : memref<100x10xf32>
     scf.yield
   }
   scf.parallel (%i, %j) = (%c0, %c0) to (%c100, %c10) step (%c1, %c1) {
     %diff_elem = load %diff[%i, %j] : memref<100x10xf32>
-    %exp_elem = exp %diff_elem : f32
+    %exp_elem = math.exp %diff_elem : f32
     store %exp_elem, %result[%i, %j] : memref<100x10xf32>
     scf.yield
   }
   dealloc %broadcast_rhs : memref<100x10xf32>
   dealloc %diff : memref<100x10xf32>
   return
 }
 // CHECK-LABEL: func @fuse_three

 // CHECK-SAME:     to ([[C100]], [[C10]]) step ([[C1]], [[C1]]) {
 // CHECK:        [[RHS_ELEM:%.*]] = load [[RHS]]{{\[}}[[I]]]
 // CHECK:        store [[RHS_ELEM]], [[BROADCAST_RHS]]{{\[}}[[I]], [[J]]]
 // CHECK:        [[LHS_ELEM:%.*]] = load [[LHS]]{{\[}}[[I]], [[J]]]
 // CHECK:        [[BROADCAST_RHS_ELEM:%.*]] = load [[BROADCAST_RHS]]
 // CHECK:        [[DIFF_ELEM:%.*]] = subf [[LHS_ELEM]], [[BROADCAST_RHS_ELEM]]
 // CHECK:        store [[DIFF_ELEM]], [[DIFF]]{{\[}}[[I]], [[J]]]
 // CHECK:        [[DIFF_ELEM_:%.*]] = load [[DIFF]]{{\[}}[[I]], [[J]]]
-// CHECK:        [[EXP_ELEM:%.*]] = exp [[DIFF_ELEM_]]
+// CHECK:        [[EXP_ELEM:%.*]] = math.exp [[DIFF_ELEM_]]
 // CHECK:        store [[EXP_ELEM]], [[RESULT]]{{\[}}[[I]], [[J]]]
 // CHECK:        scf.yield
 // CHECK:      }
 // CHECK:      dealloc [[BROADCAST_RHS]]
 // CHECK:      dealloc [[DIFF]]
 
 // -----
 

mlir/test/Dialect/Standard/expand-tanh.mlir

 // RUN: mlir-opt %s -test-expand-tanh | FileCheck %s
 
 // CHECK-LABEL: func @tanh
 func @tanh(%arg: f32) -> f32 {
-  %res = tanh %arg : f32
+  %res = math.tanh %arg : f32
   return %res : f32
 }
 // CHECK-DAG: %[[ZERO:.+]] = constant 0.000000e+00 : f32
 // CHECK-DAG: %[[ONE:.+]] = constant 1.000000e+00 : f32
 // CHECK-DAG: %[[TWO:.+]] = constant 2.000000e+00 : f32
 // CHECK: %[[DOUBLEDX:.+]] = mulf %arg0, %[[TWO]] : f32
 // CHECK: %[[NEGDOUBLEDX:.+]] = negf %[[DOUBLEDX]] : f32
-// CHECK: %[[EXP1:.+]] = exp %[[NEGDOUBLEDX]] : f32
+// CHECK: %[[EXP1:.+]] = math.exp %[[NEGDOUBLEDX]] : f32
 // CHECK: %[[DIVIDEND1:.+]] = subf %[[ONE]], %[[EXP1]] : f32
 // CHECK: %[[DIVISOR1:.+]] = addf %[[ONE]], %[[EXP1]] : f32
 // CHECK: %[[RES1:.+]] = divf %[[DIVIDEND1]], %[[DIVISOR1]] : f32
-// CHECK: %[[EXP2:.+]] = exp %[[DOUBLEDX]] : f32
+// CHECK: %[[EXP2:.+]] = math.exp %[[DOUBLEDX]] : f32
 // CHECK: %[[DIVIDEND2:.+]] = subf %[[EXP2]], %[[ONE]] : f32
 // CHECK: %[[DIVISOR2:.+]] = addf %[[EXP2]], %[[ONE]] : f32
 // CHECK: %[[RES2:.+]] = divf %[[DIVIDEND2]], %[[DIVISOR2]] : f32
 // CHECK: %[[COND:.+]] = cmpf oge, %arg0, %[[ZERO]] : f32
 // CHECK: %[[RESULT:.+]] = select %[[COND]], %[[RES1]], %[[RES2]] : f32
 // CHECK: return %[[RESULT]]

mlir/test/Dialect/Standard/ops.mlir

 // CHECK-LABEL: @assert
 func @assert(%arg : i1) {
   assert %arg, "Some message in case this assertion fails."
   return
 }
 
 // CHECK-LABEL: @atan
 func @atan(%arg : f32) -> f32 {
-  %result = atan %arg : f32
+  %result = math.atan %arg : f32
   return %result : f32
 }
 
 // CHECK-LABEL: @atan2
 func @atan2(%arg0 : f32, %arg1 : f32) -> f32 {
-  %result = atan2 %arg0, %arg1 : f32
+  %result = math.atan2 %arg0, %arg1 : f32
   return %result : f32
 }
 
 // CHECK-LABEL: func @memref_reinterpret_cast
 func @memref_reinterpret_cast(%in: memref<?xf32>)
     -> memref<10x?xf32, offset: ?, strides: [?, 1]> {
   %c0 = constant 0 : index
   %c10 = constant 10 : index

mlir/test/EDSC/builder-api-test.cpp

 //===- builder-api-test.cpp - Tests for Declarative Builder APIs ----------===//
 //
 // 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-2.0 WITH LLVM-exception
 //
 //===----------------------------------------------------------------------===//
 
 // RUN: mlir-edsc-builder-api-test | FileCheck %s
 
 #include "mlir/Dialect/Affine/EDSC/Intrinsics.h"
 #include "mlir/Dialect/Linalg/EDSC/Builders.h"
 #include "mlir/Dialect/Linalg/EDSC/Intrinsics.h"
+#include "mlir/Dialect/Math/IR/Math.h"
 #include "mlir/Dialect/SCF/EDSC/Intrinsics.h"
 #include "mlir/Dialect/StandardOps/EDSC/Intrinsics.h"
 #include "mlir/Dialect/Vector/EDSC/Intrinsics.h"
 #include "mlir/EDSC/Builders.h"
 #include "mlir/IR/AffineExpr.h"
 #include "mlir/IR/Builders.h"
 #include "mlir/IR/BuiltinOps.h"
 #include "mlir/IR/BuiltinTypes.h"

 
 static MLIRContext &globalContext() {
   static thread_local MLIRContext context;
   static thread_local bool initOnce = [&]() {
     // clang-format off
     context.loadDialect<AffineDialect,
                         scf::SCFDialect,
                         linalg::LinalgDialect,
+                        math::MathDialect,
                         StandardOpsDialect,
                         vector::VectorDialect>();
     // clang-format on
     return true;
   }();
   (void)initOnce;
   context.allowUnregisteredDialects();
   return context;

mlir/test/IR/core-ops.mlir

^bb42(%t: tensor<4x4x?xf32>, %f: f32, %i: i32, %idx : index, %j: i64, %half: f16):
   %i5 = subi %i4, %i4 : i32
 
   // CHECK: %[[F6:.*]] = mulf %[[F2]], %[[F2]] : f32
   %f6 = mulf %f2, %f2 : f32
 
   // CHECK: %[[I6:.*]] = muli %[[I2]], %[[I2]] : i32
   %i6 = muli %i2, %i2 : i32
 
-  // CHECK: %[[F7:.*]] = powf %[[F2]], %[[F2]] : f32
-  %f7 = powf %f2, %f2 : f32
-
   // CHECK: %c42_i32 = constant 42 : i32
   %x = "std.constant"(){value = 42 : i32} : () -> i32
 
   // CHECK: %c42_i32_0 = constant 42 : i32
   %7 = constant 42 : i32
 
   // CHECK: %c43 = constant {crazy = "std.foo"} 43 : index
   %8 = constant {crazy = "std.foo"} 43: index
^bb42(%t: tensor<4x4x?xf32>, %f: f32, %i: i32, %idx : index, %j: i64, %half: f16):
   %93 = trunci %tci32 : tensor<42 x i32> to tensor<42 x i16>
 
   // CHECK: = fpext {{.*}} : f16 to f32
   %94 = fpext %half : f16 to f32
 
   // CHECK: = fptrunc {{.*}} : f32 to f16
   %95 = fptrunc %f : f32 to f16
 
-  // CHECK: %{{[0-9]+}} = exp %arg1 : f32
-  %96 = "std.exp"(%f) : (f32) -> f32
-
-  // CHECK: %{{[0-9]+}} = exp %arg1 : f32
-  %97 = exp %f : f32
-
-  // CHECK: %{{[0-9]+}} = exp %cst_8 : vector<4xf32>
-  %98 = exp %vcf32 : vector<4xf32>
-
-  // CHECK: %{{[0-9]+}} = exp %arg0 : tensor<4x4x?xf32>
-  %99 = exp %t : tensor<4x4x?xf32>
-
   // CHECK: %{{[0-9]+}} = absf %arg1 : f32
   %100 = "std.absf"(%f) : (f32) -> f32
 
   // CHECK: %{{[0-9]+}} = absf %arg1 : f32
   %101 = absf %f : f32
 
   // CHECK: %{{[0-9]+}} = absf %cst_8 : vector<4xf32>
   %102 = absf %vcf32 : vector<4xf32>
 
   // CHECK: %{{[0-9]+}} = absf %arg0 : tensor<4x4x?xf32>
   %103 = absf %t : tensor<4x4x?xf32>
 
   // CHECK: %{{[0-9]+}} = ceilf %arg1 : f32
   %104 = "std.ceilf"(%f) : (f32) -> f32
 
   // CHECK: %{{[0-9]+}} = ceilf %arg1 : f32
   %105 = ceilf %f : f32
 
   // CHECK: %{{[0-9]+}} = ceilf %cst_8 : vector<4xf32>
   %106 = ceilf %vcf32 : vector<4xf32>
 
   // CHECK: %{{[0-9]+}} = ceilf %arg0 : tensor<4x4x?xf32>
   %107 = ceilf %t : tensor<4x4x?xf32>
 
-  // CHECK: %{{[0-9]+}} = cos %arg1 : f32
-  %108 = "std.cos"(%f) : (f32) -> f32
-
-  // CHECK: %{{[0-9]+}} = cos %arg1 : f32
-  %109 = cos %f : f32
-
-  // CHECK: %{{[0-9]+}} = cos %cst_8 : vector<4xf32>
-  %110 = cos %vcf32 : vector<4xf32>
-
-  // CHECK: %{{[0-9]+}} = cos %arg0 : tensor<4x4x?xf32>
-  %111 = cos %t : tensor<4x4x?xf32>
-
   // CHECK: %{{[0-9]+}} = negf %arg1 : f32
   %112 = "std.negf"(%f) : (f32) -> f32
 
   // CHECK: %{{[0-9]+}} = negf %arg1 : f32
   %113 = negf %f : f32
 
   // CHECK: %{{[0-9]+}} = negf %cst_8 : vector<4xf32>
   %114 = negf %vcf32 : vector<4xf32>
 
   // CHECK: %{{[0-9]+}} = negf %arg0 : tensor<4x4x?xf32>
   %115 = negf %t : tensor<4x4x?xf32>
 
   // CHECK: %{{[0-9]+}} = copysign %arg1, %arg1 : f32
   %116 = "std.copysign"(%f, %f) : (f32, f32) -> f32
 
   // CHECK: %{{[0-9]+}} = copysign %arg1, %arg1 : f32
   %117 = copysign %f, %f : f32
 
   // CHECK: %{{[0-9]+}} = copysign %cst_8, %cst_8 : vector<4xf32>
   %118 = copysign %vcf32, %vcf32 : vector<4xf32>
 
   // CHECK: %{{[0-9]+}} = copysign %arg0, %arg0 : tensor<4x4x?xf32>
   %119 = copysign %t, %t : tensor<4x4x?xf32>
 
-  // CHECK: %{{[0-9]+}} = tanh %arg1 : f32
-  %120 = "std.tanh"(%f) : (f32) -> f32
-
-  // CHECK: %{{[0-9]+}} = tanh %arg1 : f32
-  %121 = tanh %f : f32
-
-  // CHECK: %{{[0-9]+}} = tanh %cst_8 : vector<4xf32>
-  %122 = tanh %vcf32 : vector<4xf32>
-
-  // CHECK: %{{[0-9]+}} = tanh %arg0 : tensor<4x4x?xf32>
-  %123 = tanh %t : tensor<4x4x?xf32>
-
   // CHECK: %{{[0-9]+}} = shift_left %arg2, %arg2 : i32
   %124 = "std.shift_left"(%i, %i) : (i32, i32) -> i32
 
   // CHECK:%{{[0-9]+}} = shift_left %[[I2]], %[[I2]] : i32
   %125 = shift_left %i2, %i2 : i32
 
   // CHECK: %{{[0-9]+}} = shift_left %arg3, %arg3 : index
   %126 = shift_left %idx, %idx : index
^bb42(%t: tensor<4x4x?xf32>, %f: f32, %i: i32, %idx : index, %j: i64, %half: f16):
   %136 = shift_right_unsigned %idx, %idx : index
 
   // CHECK: %{{[0-9]+}} = shift_right_unsigned %cst_5, %cst_5 : vector<42xi32>
   %137 = shift_right_unsigned %vci32, %vci32 : vector<42 x i32>
 
   // CHECK: %{{[0-9]+}} = shift_right_unsigned %cst_4, %cst_4 : tensor<42xi32>
   %138 = shift_right_unsigned %tci32, %tci32 : tensor<42 x i32>
 
-  // CHECK: %{{[0-9]+}} = sqrt %arg1 : f32
-  %139 = "std.sqrt"(%f) : (f32) -> f32
-
-  // CHECK: %{{[0-9]+}} = sqrt %arg1 : f32
-  %140 = sqrt %f : f32
-
-  // CHECK: %{{[0-9]+}} = sqrt %cst_8 : vector<4xf32>
-  %141 = sqrt %vcf32 : vector<4xf32>
-
-  // CHECK: %{{[0-9]+}} = sqrt %arg0 : tensor<4x4x?xf32>
-  %142 = sqrt %t : tensor<4x4x?xf32>
-
   // CHECK: = fpext {{.*}} : vector<4xf32> to vector<4xf64>
   %143 = fpext %vcf32 : vector<4xf32> to vector<4xf64>
 
   // CHECK: = fptrunc {{.*}} : vector<4xf32> to vector<4xf16>
   %144 = fptrunc %vcf32 : vector<4xf32> to vector<4xf16>
 
-  // CHECK: %{{[0-9]+}} = rsqrt %arg1 : f32
-  %145 = rsqrt %f : f32
-
-  // CHECK: %{{[0-9]+}} = sin %arg1 : f32
-  %146 = "std.sin"(%f) : (f32) -> f32
-
-  // CHECK: %{{[0-9]+}} = sin %arg1 : f32
-  %147 = sin %f : f32
-
-  // CHECK: %{{[0-9]+}} = sin %cst_8 : vector<4xf32>
-  %148 = sin %vcf32 : vector<4xf32>
-
-  // CHECK: %{{[0-9]+}} = sin %arg0 : tensor<4x4x?xf32>
-  %149 = sin %t : tensor<4x4x?xf32>
+  // CHECK: %{{[0-9]+}} = math.rsqrt %arg1 : f32
+  %145 = math.rsqrt %f : f32
 
   // CHECK: = fptosi {{.*}} : f32 to i32
   %159 = fptosi %f : f32 to i32
 
   // CHECK: = fptosi {{.*}} : f32 to i64
   %160 = fptosi %f : f32 to i64
 
   // CHECK: = fptosi {{.*}} : f16 to i32
^bb42(%t: tensor<4x4x?xf32>, %f: f32, %i: i32, %idx : index, %j: i64, %half: f16):
   %172 = ceildivi_signed %idx, %idx : index
 
   // CHECK: %{{[0-9]+}} = ceildivi_signed %cst_5, %cst_5 : vector<42xi32>
   %173 = ceildivi_signed %vci32, %vci32 : vector<42 x i32>
 
   // CHECK: %{{[0-9]+}} = ceildivi_signed %cst_4, %cst_4 : tensor<42xi32>
   %174 = ceildivi_signed %tci32, %tci32 : tensor<42 x i32>
 
-  // CHECK: %{{[0-9]+}} = log1p %arg1 : f32
-  %175 = log1p %f : f32
-
   return
 }
 
 // CHECK-LABEL: func @affine_apply() {
 func @affine_apply() {
   %i = "std.constant"() {value = 0: index} : () -> index
   %j = "std.constant"() {value = 1: index} : () -> index
 

mlir/test/Transforms/buffer-deallocation.mlir

 ^bb1:
   br ^bb3(%arg1 : memref<2xf32>)
 ^bb2:
   %0 = alloc() : memref<2xf32>
   test.region_buffer_based in(%arg1: memref<2xf32>) out(%0: memref<2xf32>) {
   ^bb0(%gen1_arg0: f32, %gen1_arg1: f32):
     %1 = alloc() : memref<2xf32>
     test.buffer_based in(%arg1: memref<2xf32>) out(%1: memref<2xf32>)
-    %tmp1 = exp %gen1_arg0 : f32
+    %tmp1 = math.exp %gen1_arg0 : f32
     test.region_yield %tmp1 : f32
   }
   br ^bb3(%0 : memref<2xf32>)
 ^bb3(%1: memref<2xf32>):
   test.copy(%1, %arg2) : (memref<2xf32>, memref<2xf32>)
   return
 }
 //      CHECK: (%[[cond:.*]]: {{.*}}, %[[ARG1:.*]]: {{.*}}, %{{.*}}: {{.*}})
 // CHECK-NEXT:   cond_br %[[cond]], ^[[BB1:.*]], ^[[BB2:.*]]
 //      CHECK:   %[[ALLOC0:.*]] = alloc()
 // CHECK-NEXT:   linalg.copy(%[[ARG1]], %[[ALLOC0]])
 //      CHECK: ^[[BB2]]:
 //      CHECK:   %[[ALLOC1:.*]] = alloc()
 // CHECK-NEXT:   test.region_buffer_based in(%[[ARG1]]{{.*}}out(%[[ALLOC1]]
 //      CHECK:     %[[ALLOC2:.*]] = alloc()
 // CHECK-NEXT:     test.buffer_based in(%[[ARG1]]{{.*}}out(%[[ALLOC2]]
 //      CHECK:     dealloc %[[ALLOC2]]
-// CHECK-NEXT:     %{{.*}} = exp
+// CHECK-NEXT:     %{{.*}} = math.exp
 //      CHECK:   %[[ALLOC3:.*]] = alloc()
 // CHECK-NEXT:   linalg.copy(%[[ALLOC1]], %[[ALLOC3]])
 // CHECK-NEXT:   dealloc %[[ALLOC1]]
 //      CHECK:  ^[[BB3:.*]]({{.*}}):
 //      CHECK:  test.copy
 // CHECK-NEXT:  dealloc
 
 // -----

 ^bb1:
   br ^bb3(%arg1 : memref<2xf32>)
 ^bb2:
   %0 = alloc() : memref<2xf32>
   test.region_buffer_based in(%arg1: memref<2xf32>) out(%0: memref<2xf32>) {
   ^bb0(%gen1_arg0: f32, %gen1_arg1: f32):
     %1 = alloca() : memref<2xf32>
     test.buffer_based in(%arg1: memref<2xf32>) out(%1: memref<2xf32>)
-    %tmp1 = exp %gen1_arg0 : f32
+    %tmp1 = math.exp %gen1_arg0 : f32
     test.region_yield %tmp1 : f32
   }
   br ^bb3(%0 : memref<2xf32>)
 ^bb3(%1: memref<2xf32>):
   test.copy(%1, %arg2) : (memref<2xf32>, memref<2xf32>)
   return
 }
 //      CHECK: (%[[cond:.*]]: {{.*}}, %[[ARG1:.*]]: {{.*}}, %{{.*}}: {{.*}})
 // CHECK-NEXT:   cond_br %[[cond]], ^[[BB1:.*]], ^[[BB2:.*]]
 //      CHECK: ^[[BB1]]:
 //      CHECK: %[[ALLOC0:.*]] = alloc()
 // CHECK-NEXT: linalg.copy
 //      CHECK: ^[[BB2]]:
 //      CHECK:   %[[ALLOC1:.*]] = alloc()
 // CHECK-NEXT:   test.region_buffer_based in(%[[ARG1]]{{.*}}out(%[[ALLOC1]]
 //      CHECK:     %[[ALLOCA:.*]] = alloca()
 // CHECK-NEXT:     test.buffer_based in(%[[ARG1]]{{.*}}out(%[[ALLOCA]]
-//      CHECK:     %{{.*}} = exp
+//      CHECK:     %{{.*}} = math.exp
 //      CHECK:  %[[ALLOC2:.*]] = alloc()
 // CHECK-NEXT:  linalg.copy
 // CHECK-NEXT:  dealloc %[[ALLOC1]]
 //      CHECK:  ^[[BB3:.*]]({{.*}}):
 //      CHECK:  test.copy
 // CHECK-NEXT:  dealloc
 
 // -----

mlir/test/Transforms/buffer-hoisting.mlir

 ^bb1:
   br ^bb3(%arg1 : memref<2xf32>)
 ^bb2:
   %0 = alloc() : memref<2xf32>
   test.region_buffer_based in(%arg1: memref<2xf32>) out(%0: memref<2xf32>) {
   ^bb0(%gen1_arg0: f32, %gen1_arg1: f32):
     %1 = alloc() : memref<2xf32>
     test.buffer_based in(%arg1: memref<2xf32>) out(%1: memref<2xf32>)
-    %tmp1 = exp %gen1_arg0 : f32
+    %tmp1 = math.exp %gen1_arg0 : f32
     test.region_yield %tmp1 : f32
   }
   br ^bb3(%0 : memref<2xf32>)
 ^bb3(%1: memref<2xf32>):
   test.copy(%1, %arg2) : (memref<2xf32>, memref<2xf32>)
   return
 }
 // CHECK-NEXT:   %[[ALLOC0:.*]] = alloc()

 ^bb1:
   br ^bb3(%arg1 : memref<2xf32>)
 ^bb2:
   %0 = alloc() : memref<2xf32>
   test.region_buffer_based in(%arg1: memref<2xf32>) out(%0: memref<2xf32>) {
   ^bb0(%gen1_arg0: f32, %gen1_arg1: f32):
     %1 = alloca() : memref<2xf32>
     test.buffer_based in(%arg1: memref<2xf32>) out(%1: memref<2xf32>)
-    %tmp1 = exp %gen1_arg0 : f32
+    %tmp1 = math.exp %gen1_arg0 : f32
     test.region_yield %tmp1 : f32
   }
   br ^bb3(%0 : memref<2xf32>)
 ^bb3(%1: memref<2xf32>):
   test.copy(%1, %arg2) : (memref<2xf32>, memref<2xf32>)
   return
 }
 // CHECK-NEXT:   %[[ALLOC:.*]] = alloc()

mlir/test/Transforms/buffer-loop-hoisting.mlir

 ^bb1:
   br ^bb3(%arg1 : memref<2xf32>)
 ^bb2:
   %0 = alloc() : memref<2xf32>
   test.region_buffer_based in(%arg1: memref<2xf32>) out(%0: memref<2xf32>) {
   ^bb0(%gen1_arg0: f32, %gen1_arg1: f32):
     %1 = alloc() : memref<2xf32>
     test.buffer_based in(%arg1: memref<2xf32>) out(%1: memref<2xf32>)
-    %tmp1 = exp %gen1_arg0 : f32
+    %tmp1 = math.exp %gen1_arg0 : f32
     test.region_yield %tmp1 : f32
   }
   br ^bb3(%0 : memref<2xf32>)
 ^bb3(%1: memref<2xf32>):
   test.copy(%1, %arg2) : (memref<2xf32>, memref<2xf32>)
   return
 }
 // CHECK-NEXT:   cond_br

mlir/test/Transforms/canonicalize-dce.mlir

 // CHECK:      func @f(%arg0: f32)
 // CHECK-NEXT:   br ^bb1
 // CHECK-NEXT: ^bb1:
 // CHECK-NEXT:   br ^bb1
 
 func @f(%arg0: f32) {
   br ^loop(%arg0: f32)
 ^loop(%0: f32):
-  %1 = "std.exp"(%0) : (f32) -> f32
+  %1 = "math.exp"(%0) : (f32) -> f32
   br ^loop(%1: f32)
 }
 
 // -----
 
 // Test case: Delete block arguments for cond_br.
 
 // CHECK:      func @f(%arg0: f32, %arg1: i1)
 // CHECK-NEXT:   return
 
 func @f(%arg0: f32, %pred: i1) {
-  %exp = "std.exp"(%arg0) : (f32) -> f32
+  %exp = "math.exp"(%arg0) : (f32) -> f32
   cond_br %pred, ^true(%exp: f32), ^false(%exp: f32)
 ^true(%0: f32):
   return
 ^false(%1: f32):
   return
 }
 
 // -----

 
 // Test case: Uses in nested regions are deleted correctly.
 
 // CHECK:      func @f(%arg0: f32)
 // CHECK-NEXT:   "foo.has_region"
 // CHECK-NEXT:     "foo.return"
 
 func @f(%arg0: f32) {
-  %0 = "std.exp"(%arg0) : (f32) -> f32
+  %0 = "math.exp"(%arg0) : (f32) -> f32
   "foo.has_region"() ({
-    %1 = "std.exp"(%0) : (f32) -> f32
+    %1 = "math.exp"(%0) : (f32) -> f32
     "foo.return"() : () -> ()
   }) : () -> ()
   return
 }
 
 // -----
 
 // Test case: Test the mechanics of deleting multiple block arguments.

mlir/test/Transforms/copy-removal.mlir

func @test_with_temp_usage_after_copy() -> memref<5xf32> {
   %temp = alloc() : memref<5xf32>
   linalg.copy(%ret, %temp) : memref<5xf32>, memref<5xf32>
   linalg.generic {
     indexing_maps = [#map0, #map0],
     iterator_types = ["parallel"]}
     ins(%temp : memref<5xf32>)
    outs(%res : memref<5xf32>) {
   ^bb0(%gen1_arg0: f32, %gen1_arg1: f32):
-    %tmp1 = exp %gen1_arg0 : f32
+    %tmp1 = math.exp %gen1_arg0 : f32
     linalg.yield %tmp1 : f32
   }
   dealloc %ret : memref<5xf32>
   return %temp : memref<5xf32>
 }
 // CHECK-NEXT: %[[ret:.*]] = alloc()
 // CHECK-NEXT: %[[res:.*]] = alloc()
 // CHECK-NEXT: %[[temp:.*]] = alloc()
func @test_ReuseCopyTargetAsSource(%arg0: memref<2xf32>, %result: memref<2xf32>){
   // CHECK-NOT: linalg.copy(%{{.*}}, %[[RES]])
   // CHECK-NOT: dealloc %{{.*}}
   linalg.generic {
     indexing_maps = [#map0, #map0],
     iterator_types = ["parallel"]}
     ins(%arg0 : memref<2xf32>)
    outs(%temp : memref<2xf32>) {
   ^bb0(%gen2_arg0: f32, %gen2_arg1: f32):
-    %tmp2 = exp %gen2_arg0 : f32
+    %tmp2 = math.exp %gen2_arg0 : f32
     linalg.yield %tmp2 : f32
   }
   "linalg.copy"(%temp, %result) : (memref<2xf32>, memref<2xf32>) -> ()
   dealloc %temp : memref<2xf32>
   // CHECK: return
   return
 }
 
func @test_ReuseCopyTargetAsSource(%arg0: memref<2xf32>){
   %to = alloc() : memref<2xf32>
   %temp = alloc() : memref<2xf32>
   linalg.generic {
     indexing_maps = [#map0, #map0],
     iterator_types = ["parallel"]}
     ins(%arg0 : memref<2xf32>)
    outs(%temp : memref<2xf32>) {
   ^bb0(%gen1_arg0: f32, %gen1_arg1: f32):
-    %tmp1 = exp %gen1_arg0 : f32
+    %tmp1 = math.exp %gen1_arg0 : f32
     linalg.yield %tmp1 : f32
   }
   linalg.generic {
     indexing_maps = [#map0, #map0],
     iterator_types = ["parallel"]}
     ins(%arg0 : memref<2xf32>)
    outs(%to : memref<2xf32>) {
   ^bb0(%gen2_arg0: f32, %gen2_arg1: f32):
-    %tmp2 = exp %gen2_arg0 : f32
+    %tmp2 = math.exp %gen2_arg0 : f32
     linalg.yield %tmp2 : f32
   }
   // CHECK: linalg.copy
   "linalg.copy"(%temp, %to) : (memref<2xf32>, memref<2xf32>) -> ()
   dealloc %temp : memref<2xf32>
   return
 }
 

mlir/test/Transforms/promote-buffers-to-stack.mlir

 ^bb1:
   br ^bb3(%arg1 : memref<2xf32>)
 ^bb2:
   %0 = alloc() : memref<2xf32>
   test.region_buffer_based in(%arg1: memref<2xf32>) out(%0: memref<2xf32>) {
   ^bb0(%gen1_arg0: f32, %gen1_arg1: f32):
     %1 = alloc() : memref<2xf32>
     test.buffer_based in(%arg1: memref<2xf32>) out(%1: memref<2xf32>)
-    %tmp1 = exp %gen1_arg0 : f32
+    %tmp1 = math.exp %gen1_arg0 : f32
     test.region_yield %tmp1 : f32
   }
   br ^bb3(%0 : memref<2xf32>)
 ^bb3(%1: memref<2xf32>):
   test.copy(%1, %arg2) : (memref<2xf32>, memref<2xf32>)
   return
 }
 

mlir/test/lib/Transforms/TestExpandTanh.cpp

-//===- TestExpandTanh.cpp - Test expand tanh op into exp form ------===//
+//===- TestExpandTanh.cpp - Test expand tanh op into exp form -------------===//
 //
 // 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-2.0 WITH LLVM-exception
 //
 //===----------------------------------------------------------------------===//
 //
 // This file contains test passes for expanding tanh.
 //
 //===----------------------------------------------------------------------===//
 
-#include "mlir/Dialect/StandardOps/Transforms/Passes.h"
+#include "mlir/Dialect/Math/Transforms/Passes.h"
 #include "mlir/Pass/Pass.h"
 #include "mlir/Transforms/GreedyPatternRewriteDriver.h"
 
 using namespace mlir;
 
 namespace {
 struct TestExpandTanhPass
     : public PassWrapper<TestExpandTanhPass, FunctionPass> {

mlir/test/mlir-opt/commandline.mlir

 // RUN: mlir-opt --show-dialects | FileCheck %s
 // CHECK: Available Dialects:
 // CHECK-NEXT: acc
 // CHECK-NEXT: affine
 // CHECK-NEXT: arm_neon
 // CHECK-NEXT: arm_sve
 // CHECK-NEXT: async
 // CHECK-NEXT: avx512
 // CHECK-NEXT: complex
 // CHECK-NEXT: gpu
 // CHECK-NEXT: linalg
 // CHECK-NEXT: llvm
 // CHECK-NEXT: llvm_arm_neon
 // CHECK-NEXT: llvm_arm_sve
 // CHECK-NEXT: llvm_avx512
+// CHECK-NEXT: math
 // CHECK-NEXT: nvvm
 // CHECK-NEXT: omp
 // CHECK-NEXT: pdl
 // CHECK-NEXT: pdl_interp
 // CHECK-NEXT: quant
 // CHECK-NEXT: rocdl
 // CHECK-NEXT: scf
 // CHECK-NEXT: sdbm
 // CHECK-NEXT: shape
 // CHECK-NEXT: spv
 // CHECK-NEXT: std
 // CHECK-NEXT: tensor
 // CHECK-NEXT: test
 // CHECK-NEXT: tosa
 // CHECK-NEXT: vector