intel/llvm
1
0
Fork 0
mirror of https://github.com/intel/llvm.git synced 2026-01-24 08:30:34 +08:00
Code Issues Packages Projects Releases Wiki Activity

[mlir] Add math to LLVM lowering support for missing trigonometric & hyperbolic ops (#125753)

Browse Source 
The patch adds support for math -> LLVM dialect lowering for TanOp,
Sinh, Cosh, Tanh
This commit is contained in:
Paul Carabas
2025-02-06 02:02:29 +02:00
committed by GitHub
parent 88f55d16c4
commit df1bee03de
3 changed files with 43 additions and 13 deletions
Download Patch File Download Diff File Expand all files Collapse all files

16
flang/test/Intrinsics/math-codegen.fir
View File

@@ -1803,10 +1803,10 @@ func.func private @sinh(f64) -> f64
//--- tanh_fast.fir
// RUN: fir-opt %t/tanh_fast.fir --fir-to-llvm-ir="target=x86_64-unknown-linux-gnu" | FileCheck %t/tanh_fast.fir
// CHECK: @_QPtest_real4
// CHECK: {{%[A-Za-z0-9._]+}} = llvm.call @tanhf({{%[A-Za-z0-9._]+}}) : (f32) -> f32
// CHECK: {{%[A-Za-z0-9._]+}} = llvm.intr.tanh({{%[A-Za-z0-9._]+}}) : (f32) -> f32
// CHECK: @_QPtest_real8
// CHECK: {{%[A-Za-z0-9._]+}} = llvm.call @tanh({{%[A-Za-z0-9._]+}}) : (f64) -> f64
// CHECK: {{%[A-Za-z0-9._]+}} = llvm.intr.tanh({{%[A-Za-z0-9._]+}}) : (f64) -> f64
func.func @_QPtest_real4(%arg0: !fir.ref<f32> {fir.bindc_name = "x"}) -> f32 {
%0 = fir.alloca f32 {bindc_name = "test_real4", uniq_name = "_QFtest_real4Etest_real4"}
@@ -1828,10 +1828,10 @@ func.func @_QPtest_real8(%arg0: !fir.ref<f64> {fir.bindc_name = "x"}) -> f64 {
//--- tanh_relaxed.fir
// RUN: fir-opt %t/tanh_relaxed.fir --fir-to-llvm-ir="target=x86_64-unknown-linux-gnu" | FileCheck %t/tanh_relaxed.fir
// CHECK: @_QPtest_real4
// CHECK: {{%[A-Za-z0-9._]+}} = llvm.call @tanhf({{%[A-Za-z0-9._]+}}) : (f32) -> f32
// CHECK: {{%[A-Za-z0-9._]+}} = llvm.intr.tanh({{%[A-Za-z0-9._]+}}) : (f32) -> f32
// CHECK: @_QPtest_real8
// CHECK: {{%[A-Za-z0-9._]+}} = llvm.call @tanh({{%[A-Za-z0-9._]+}}) : (f64) -> f64
// CHECK: {{%[A-Za-z0-9._]+}} = llvm.intr.tanh({{%[A-Za-z0-9._]+}}) : (f64) -> f64
func.func @_QPtest_real4(%arg0: !fir.ref<f32> {fir.bindc_name = "x"}) -> f32 {
%0 = fir.alloca f32 {bindc_name = "test_real4", uniq_name = "_QFtest_real4Etest_real4"}
@@ -1880,10 +1880,10 @@ func.func private @tanh(f64) -> f64
//--- tan_fast.fir
// RUN: fir-opt %t/tan_fast.fir --fir-to-llvm-ir="target=x86_64-unknown-linux-gnu" | FileCheck %t/tan_fast.fir
// CHECK: @_QPtest_real4
// CHECK: {{%[A-Za-z0-9._]+}} = llvm.call @tanf({{%[A-Za-z0-9._]+}}) : (f32) -> f32
// CHECK: {{%[A-Za-z0-9._]+}} = llvm.intr.tan({{%[A-Za-z0-9._]+}}) : (f32) -> f32
// CHECK: @_QPtest_real8
// CHECK: {{%[A-Za-z0-9._]+}} = llvm.call @tan({{%[A-Za-z0-9._]+}}) : (f64) -> f64
// CHECK: {{%[A-Za-z0-9._]+}} = llvm.intr.tan({{%[A-Za-z0-9._]+}}) : (f64) -> f64
func.func @_QPtest_real4(%arg0: !fir.ref<f32> {fir.bindc_name = "x"}) -> f32 {
%0 = fir.alloca f32 {bindc_name = "test_real4", uniq_name = "_QFtest_real4Etest_real4"}
@@ -1905,10 +1905,10 @@ func.func @_QPtest_real8(%arg0: !fir.ref<f64> {fir.bindc_name = "x"}) -> f64 {
//--- tan_relaxed.fir
// RUN: fir-opt %t/tan_relaxed.fir --fir-to-llvm-ir="target=x86_64-unknown-linux-gnu" | FileCheck %t/tan_relaxed.fir
// CHECK: @_QPtest_real4
// CHECK: {{%[A-Za-z0-9._]+}} = llvm.call @tanf({{%[A-Za-z0-9._]+}}) : (f32) -> f32
// CHECK: {{%[A-Za-z0-9._]+}} = llvm.intr.tan({{%[A-Za-z0-9._]+}}) : (f32) -> f32
// CHECK: @_QPtest_real8
// CHECK: {{%[A-Za-z0-9._]+}} = llvm.call @tan({{%[A-Za-z0-9._]+}}) : (f64) -> f64
// CHECK: {{%[A-Za-z0-9._]+}} = llvm.intr.tan({{%[A-Za-z0-9._]+}}) : (f64) -> f64
func.func @_QPtest_real4(%arg0: !fir.ref<f32> {fir.bindc_name = "x"}) -> f32 {
%0 = fir.alloca f32 {bindc_name = "test_real4", uniq_name = "_QFtest_real4Etest_real4"}

10
mlir/lib/Conversion/MathToLLVM/MathToLLVM.cpp
View File

@@ -39,6 +39,7 @@ using CeilOpLowering = ConvertFMFMathToLLVMPattern<math::CeilOp, LLVM::FCeilOp>;
using CopySignOpLowering =
ConvertFMFMathToLLVMPattern<math::CopySignOp, LLVM::CopySignOp>;
using CosOpLowering = ConvertFMFMathToLLVMPattern<math::CosOp, LLVM::CosOp>;
using CoshOpLowering = ConvertFMFMathToLLVMPattern<math::CoshOp, LLVM::CoshOp>;
using CtPopFOpLowering =
VectorConvertToLLVMPattern<math::CtPopOp, LLVM::CtPopOp>;
using Exp2OpLowering = ConvertFMFMathToLLVMPattern<math::Exp2Op, LLVM::Exp2Op>;
@@ -58,9 +59,12 @@ using RoundEvenOpLowering =
using RoundOpLowering =
ConvertFMFMathToLLVMPattern<math::RoundOp, LLVM::RoundOp>;
using SinOpLowering = ConvertFMFMathToLLVMPattern<math::SinOp, LLVM::SinOp>;
using SinhOpLowering = ConvertFMFMathToLLVMPattern<math::SinhOp, LLVM::SinhOp>;
using SqrtOpLowering = ConvertFMFMathToLLVMPattern<math::SqrtOp, LLVM::SqrtOp>;
using FTruncOpLowering =
ConvertFMFMathToLLVMPattern<math::TruncOp, LLVM::FTruncOp>;
using TanOpLowering = ConvertFMFMathToLLVMPattern<math::TanOp, LLVM::TanOp>;
using TanhOpLowering = ConvertFMFMathToLLVMPattern<math::TanhOp, LLVM::TanhOp>;
// A `CtLz/CtTz/absi(a)` is converted into `CtLz/CtTz/absi(a, false)`.
template <typename MathOp, typename LLVMOp>
@@ -310,6 +314,7 @@ void mlir::populateMathToLLVMConversionPatterns(
CeilOpLowering,
CopySignOpLowering,
CosOpLowering,
CoshOpLowering,
CountLeadingZerosOpLowering,
CountTrailingZerosOpLowering,
CtPopFOpLowering,
@@ -327,8 +332,11 @@ void mlir::populateMathToLLVMConversionPatterns(
RoundOpLowering,
RsqrtOpLowering,
SinOpLowering,
SinhOpLowering,
SqrtOpLowering,
FTruncOpLowering
FTruncOpLowering,
TanOpLowering,
TanhOpLowering
>(converter);
// clang-format on
}

30
mlir/test/Conversion/MathToLLVM/math-to-llvm.mlir
View File

@@ -161,11 +161,33 @@ func.func @rsqrt(%arg0 : f32) {
// -----
// CHECK-LABEL: func @sine(
// CHECK-SAME: f32
func.func @sine(%arg0 : f32) {
// CHECK: llvm.intr.sin(%arg0) : (f32) -> f32
// CHECK-LABEL: func @trigonometrics
// CHECK-SAME: [[ARG0:%.+]]: f32
func.func @trigonometrics(%arg0: f32) {
// CHECK: llvm.intr.sin([[ARG0]]) : (f32) -> f32
%0 = math.sin %arg0 : f32
// CHECK: llvm.intr.cos([[ARG0]]) : (f32) -> f32
%1 = math.cos %arg0 : f32
// CHECK: llvm.intr.tan([[ARG0]]) : (f32) -> f32
%2 = math.tan %arg0 : f32
func.return
}
// -----
// CHECK-LABEL: func @hyperbolics
// CHECK-SAME: [[ARG0:%.+]]: f32
func.func @hyperbolics(%arg0: f32) {
// CHECK: llvm.intr.sinh([[ARG0]]) : (f32) -> f32
%0 = math.sinh %arg0 : f32
// CHECK: llvm.intr.cosh([[ARG0]]) : (f32) -> f32
%1 = math.cosh %arg0 : f32
// CHECK: llvm.intr.tanh([[ARG0]]) : (f32) -> f32
%2 = math.tanh %arg0 : f32
func.return
}