Add support for converstion of intrinsic @llvm.fptosi.sat.* and @llvm.fptoui.sat.* #125472
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Contributor
Vishakh2012
commented
Feb 3, 2025
Vishakh2012
commented
- add legalizer for the Generic MIR G_FPTOSI_SAT and G_FPTOUI_SAT
- add function to add saturatedConversion on these instructions
- add InstructionSelector for both of the gMIR
Member
|
@llvm/pr-subscribers-backend-spir-v Author: Vishakh Prakash (Vishakh2012) Changes
Full diff: https://github.com/llvm/llvm-project/pull/125472.diff 4 Files Affected:
diff --git a/llvm/lib/Target/SPIRV/SPIRVEmitIntrinsics.cpp b/llvm/lib/Target/SPIRV/SPIRVEmitIntrinsics.cpp
index 702206b8e0dc56..cec3e2dba14e06 100644
--- a/llvm/lib/Target/SPIRV/SPIRVEmitIntrinsics.cpp
+++ b/llvm/lib/Target/SPIRV/SPIRVEmitIntrinsics.cpp
@@ -18,12 +18,15 @@
#include "SPIRVTargetMachine.h"
#include "SPIRVUtils.h"
#include "llvm/ADT/DenseSet.h"
+#include "llvm/ADT/STLExtras.h"
#include "llvm/IR/IRBuilder.h"
#include "llvm/IR/InstIterator.h"
#include "llvm/IR/InstVisitor.h"
#include "llvm/IR/IntrinsicsSPIRV.h"
#include "llvm/IR/TypedPointerType.h"
+#include "llvm/Support/Casting.h"
+#include <iostream>
#include <queue>
#include <unordered_set>
@@ -1337,6 +1340,24 @@ static void createSaturatedConversionDecoration(Instruction *I,
createDecorationIntrinsic(I, SaturatedConversionNode, B);
}
+static void addSaturatedDecorationToIntrinsic(Instruction *I, IRBuilder<> &B) {
+ // llvm::errs() << "this function is running successfully";
+ if (auto *CI = dyn_cast<CallInst>(I)) {
+ Function *F = CI->getCalledFunction();
+ if (F->isIntrinsic()) {
+ StringRef S = F->getName();
+ SmallVector<StringRef, 8> Parts;
+ S.split(Parts, ".", -1, false);
+
+ if (Parts.size() > 1) {
+ if (std::find(Parts.begin(), Parts.end(), "sat") != Parts.end()) {
+ createSaturatedConversionDecoration(I, B);
+ }
+ }
+ }
+ }
+}
+
Instruction *SPIRVEmitIntrinsics::visitCallInst(CallInst &Call) {
if (!Call.isInlineAsm())
return &Call;
@@ -2400,6 +2421,7 @@ bool SPIRVEmitIntrinsics::runOnFunction(Function &Func) {
if (isConvergenceIntrinsic(I))
continue;
+ addSaturatedDecorationToIntrinsic(I, B);
processInstrAfterVisit(I, B);
}
diff --git a/llvm/lib/Target/SPIRV/SPIRVInstructionSelector.cpp b/llvm/lib/Target/SPIRV/SPIRVInstructionSelector.cpp
index e7d8fe5bd8015b..49642126d34cfd 100644
--- a/llvm/lib/Target/SPIRV/SPIRVInstructionSelector.cpp
+++ b/llvm/lib/Target/SPIRV/SPIRVInstructionSelector.cpp
@@ -602,6 +602,10 @@ bool SPIRVInstructionSelector::spvSelect(Register ResVReg,
return selectUnOp(ResVReg, ResType, I, SPIRV::OpConvertFToS);
case TargetOpcode::G_FPTOUI:
return selectUnOp(ResVReg, ResType, I, SPIRV::OpConvertFToU);
+ case TargetOpcode::G_FPTOSI_SAT:
+ return selectUnOp(ResVReg, ResType, I, SPIRV::OpConvertFToS);
+ case TargetOpcode::G_FPTOUI_SAT:
+ return selectUnOp(ResVReg, ResType, I, SPIRV::OpConvertFToU);
case TargetOpcode::G_SITOFP:
return selectIToF(ResVReg, ResType, I, true, SPIRV::OpConvertSToF);
diff --git a/llvm/lib/Target/SPIRV/SPIRVLegalizerInfo.cpp b/llvm/lib/Target/SPIRV/SPIRVLegalizerInfo.cpp
index fa5e0a80576d01..694d584c26e04e 100644
--- a/llvm/lib/Target/SPIRV/SPIRVLegalizerInfo.cpp
+++ b/llvm/lib/Target/SPIRV/SPIRVLegalizerInfo.cpp
@@ -236,6 +236,10 @@ SPIRVLegalizerInfo::SPIRVLegalizerInfo(const SPIRVSubtarget &ST) {
.legalForCartesianProduct(allIntScalarsAndVectors,
allFloatScalarsAndVectors);
+ getActionDefinitionsBuilder({G_FPTOSI_SAT, G_FPTOUI_SAT})
+ .legalForCartesianProduct(allIntScalarsAndVectors,
+ allFloatScalarsAndVectors);
+
getActionDefinitionsBuilder({G_SITOFP, G_UITOFP})
.legalForCartesianProduct(allFloatScalarsAndVectors,
allScalarsAndVectors);
diff --git a/llvm/test/CodeGen/SPIRV/llvm-intrinsics/fp_to_int_intrinsic.ll b/llvm/test/CodeGen/SPIRV/llvm-intrinsics/fp_to_int_intrinsic.ll
new file mode 100644
index 00000000000000..1f0feee1d914cd
--- /dev/null
+++ b/llvm/test/CodeGen/SPIRV/llvm-intrinsics/fp_to_int_intrinsic.ll
@@ -0,0 +1,220 @@
+; RUN: llc -O0 -verify-machineinstrs -mtriple=spirv64-unkown-unknown %s -o - | FileCheck %s
+; RUN: %if spirv-tools %{ llc -O0 -mtriple=spirv64-unkown-unknown %s -o - -filetype=obj | spirv-val %}
+
+; CHECK: OpDecorate %[[#SAT1:]] SaturatedConversion
+; CHECK: OpDecorate %[[#SAT2:]] SaturatedConversion
+; CHECK: OpDecorate %[[#SAT3:]] SaturatedConversion
+; CHECK: OpDecorate %[[#SAT4:]] SaturatedConversion
+; CHECK: OpDecorate %[[#SAT5:]] SaturatedConversion
+; CHECK: OpDecorate %[[#SAT6:]] SaturatedConversion
+; CHECK: OpDecorate %[[#SAT7:]] SaturatedConversion
+; CHECK: OpDecorate %[[#SAT8:]] SaturatedConversion
+; CHECK: OpDecorate %[[#SAT9:]] SaturatedConversion
+; CHECK: OpDecorate %[[#SAT10:]] SaturatedConversion
+; CHECK: OpDecorate %[[#SAT11:]] SaturatedConversion
+; CHECK: OpDecorate %[[#SAT12:]] SaturatedConversion
+; CHECK: OpDecorate %[[#SAT13:]] SaturatedConversion
+; CHECK: OpDecorate %[[#SAT14:]] SaturatedConversion
+; CHECK: OpDecorate %[[#SAT15:]] SaturatedConversion
+
+
+; CHECK: %[[#SAT1:]] = OpConvertFToS %{{[0-9]+}} %[[#]]
+define spir_kernel void @testfunction_float_to_signed_i8(float %input) {
+entry:
+ %ptr = alloca i8
+ %0 = call i8 @llvm.fptosi.sat.i8.f32(float %input)
+ store i8 %0, i8* %ptr
+ ret void
+}
+declare i8 @llvm.fptosi.sat.i8.f32(float)
+
+
+; CHECK: %[[#SAT2:]] = OpConvertFToS %{{[0-9]+}} %[[#]]
+define spir_kernel void @testfunction_float_to_signed_i16(float %input) {
+entry:
+ %ptr = alloca i16
+ %0 = call i16 @llvm.fptosi.sat.i16.f32(float %input)
+ store i16 %0, i16* %ptr
+ ret void
+}
+declare i16 @llvm.fptosi.sat.i16.f32(float)
+
+;;;;;;; output i32
+
+; CHECK: %[[#SAT3:]] = OpConvertFToS %{{[0-9]+}} %[[#]]
+define spir_kernel void @testfunction_float_to_signed_i32(float %input) {
+entry:
+ %ptr = alloca i32
+ %0 = call i32 @llvm.fptosi.sat.i32.f32(float %input)
+ store i32 %0, i32* %ptr
+ ret void
+}
+declare i32 @llvm.fptosi.sat.i32.f32(float)
+
+;;;;;;; output i64
+; CHECK: %[[#SAT4:]] = OpConvertFToS %{{[0-9]+}} %[[#]]
+define spir_kernel void @testfunction_float_to_signed_i64(float %input) {
+entry:
+ %ptr = alloca i64
+ %0 = call i64 @llvm.fptosi.sat.i64.f32(float %input)
+ store i64 %0, i64* %ptr
+ ret void
+}
+declare i64 @llvm.fptosi.sat.i64.f32(float)
+
+;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
+; double input
+;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
+
+;;;;;;; output i8
+; CHECK: %[[#SAT5:]] = OpConvertFToS %{{[0-9]+}} %[[#]]
+define spir_kernel void @testfunction_double_to_signed_i8(double %input) {
+entry:
+ %ptr = alloca i8
+ %0 = call i8 @llvm.fptosi.sat.i8.f64(double %input)
+ store i8 %0, i8* %ptr
+ ret void
+}
+declare i8 @llvm.fptosi.sat.i8.f64(double)
+
+
+; CHECK: %[[#SAT6:]] = OpConvertFToS %{{[0-9]+}} %[[#]]
+define spir_kernel void @testfunction_double_to_signed_i16(double %input) {
+entry:
+ %ptr = alloca i16
+ %0 = call i16 @llvm.fptosi.sat.i16.f64(double %input)
+ store i16 %0, i16* %ptr
+ ret void
+}
+declare i16 @llvm.fptosi.sat.i16.f64(double)
+
+
+; CHECK: %[[#SAT7:]] = OpConvertFToS %{{[0-9]+}} %[[#]]
+define spir_kernel void @testfunction_double_to_signed_i32(double %input) {
+entry:
+ %ptr = alloca i32
+ %0 = call i32 @llvm.fptosi.sat.i32.f64(double %input)
+ store i32 %0, i32* %ptr
+ ret void
+}
+declare i32 @llvm.fptosi.sat.i32.f64(double)
+
+
+; CHECK: %[[#SAT8:]] = OpConvertFToS %{{[0-9]+}} %[[#]]
+define spir_kernel void @testfunction_double_to_signed_i64(double %input) {
+entry:
+ %ptr = alloca i64
+ %0 = call i64 @llvm.fptosi.sat.i64.f64(double %input)
+ store i64 %0, i64* %ptr
+ ret void
+}
+declare i64 @llvm.fptosi.sat.i64.f64(double)
+
+
+
+
+;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
+;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
+; unsigned output
+;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
+;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
+
+;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
+; float input
+;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
+
+;;;;;;; output i8
+; CHECK: %[[#SAT8:]] = OpConvertFToU %{{[0-9]+}} %[[#]]
+define spir_kernel void @testfunction_float_to_unsigned_i8(float %input) {
+entry:
+ %ptr = alloca i8
+ %0 = call i8 @llvm.fptoui.sat.i8.f32(float %input)
+ store i8 %0, i8* %ptr
+ ret void
+}
+declare i8 @llvm.fptoui.sat.i8.f32(float)
+
+;;;;;;; output i16
+; CHECK: %[[#SAT9:]] = OpConvertFToU %{{[0-9]+}} %[[#]]
+define spir_kernel void @testfunction_float_to_unsigned_i16(float %input) {
+entry:
+ %ptr = alloca i16
+ %0 = call i16 @llvm.fptoui.sat.i16.f32(float %input)
+ store i16 %0, i16* %ptr
+ ret void
+}
+declare i16 @llvm.fptoui.sat.i16.f32(float)
+
+;;;;;;; output i32
+; CHECK: %[[#SAT10:]] = OpConvertFToU %{{[0-9]+}} %[[#]]
+define spir_kernel void @testfunction_float_to_unsigned_i32(float %input) {
+entry:
+ %ptr = alloca i32
+ %0 = call i32 @llvm.fptoui.sat.i32.f32(float %input)
+ store i32 %0, i32* %ptr
+ ret void
+}
+declare i32 @llvm.fptoui.sat.i32.f32(float)
+
+;;;;;;; output i64
+; CHECK: %[[#SAT11:]] = OpConvertFToU %{{[0-9]+}} %[[#]]
+define spir_kernel void @testfunction_float_to_unsigned_i64(float %input) {
+entry:
+ %ptr = alloca i64
+ %0 = call i64 @llvm.fptoui.sat.i64.f32(float %input)
+ store i64 %0, i64* %ptr
+ ret void
+}
+declare i64 @llvm.fptoui.sat.i64.f32(float)
+
+;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
+; double input
+;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
+
+;;;;;;; output i8
+; CHECK: %[[#SAT12:]] = OpConvertFToU %{{[0-9]+}} %[[#]]
+define spir_kernel void @testfunction_double_to_unsigned_i8(double %input) {
+entry:
+ %ptr = alloca i8
+ %0 = call i8 @llvm.fptoui.sat.i8.f64(double %input)
+ store i8 %0, i8* %ptr
+ ret void
+}
+declare i8 @llvm.fptoui.sat.i8.f64(double)
+
+;;;;;;; output i16
+; CHECK: %[[#SAT13:]] = OpConvertFToU %{{[0-9]+}} %[[#]]
+define spir_kernel void @testfunction_double_to_unsigned_i16(double %input) {
+entry:
+ %ptr = alloca i16
+ %0 = call i16 @llvm.fptoui.sat.i16.f64(double %input)
+ store i16 %0, i16* %ptr
+ ret void
+}
+declare i16 @llvm.fptoui.sat.i16.f64(double)
+
+;;;;;;; output i32
+; CHECK: %[[#SAT14:]] = OpConvertFToU %{{[0-9]+}} %[[#]]
+define spir_kernel void @testfunction_double_to_unsigned_i32(double %input) {
+entry:
+ %ptr = alloca i32
+ %0 = call i32 @llvm.fptoui.sat.i32.f64(double %input)
+ store i32 %0, i32* %ptr
+ ret void
+}
+declare i32 @llvm.fptoui.sat.i32.f64(double)
+
+;;;;;;; output i64
+; CHECK: %[[#SAT15:]] = OpConvertFToU %{{[0-9]+}} %[[#]]
+define spir_kernel void @testfunction_double_to_unsigned_i64(double %input) {
+entry:
+ %ptr = alloca i64
+ %0 = call i64 @llvm.fptoui.sat.i64.f64(double %input)
+ store i64 %0, i64* %ptr
+ ret void
+}
+declare i64 @llvm.fptoui.sat.i64.f64(double)
+
+
+
+
|
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.