Add support for the intrinsic @llvm.fptosi.sat.* and @llvm.fptoui.sat.* lowering #126214
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
Member
|
@llvm/pr-subscribers-backend-spir-v Author: Vishakh Prakash (Vishakh2012) Changes
currently does not support arbitrary size integer because of the constraints placed by the prelegalizer Full diff: https://github.com/llvm/llvm-project/pull/126214.diff 4 Files Affected:
diff --git a/llvm/lib/Target/SPIRV/SPIRVEmitIntrinsics.cpp b/llvm/lib/Target/SPIRV/SPIRVEmitIntrinsics.cpp
index 702206b8e0dc56e..d67d3521728e3fc 100644
--- a/llvm/lib/Target/SPIRV/SPIRVEmitIntrinsics.cpp
+++ b/llvm/lib/Target/SPIRV/SPIRVEmitIntrinsics.cpp
@@ -21,6 +21,7 @@
#include "llvm/IR/IRBuilder.h"
#include "llvm/IR/InstIterator.h"
#include "llvm/IR/InstVisitor.h"
+#include "llvm/IR/Intrinsics.h"
#include "llvm/IR/IntrinsicsSPIRV.h"
#include "llvm/IR/TypedPointerType.h"
@@ -1337,6 +1338,24 @@ static void createSaturatedConversionDecoration(Instruction *I,
createDecorationIntrinsic(I, SaturatedConversionNode, B);
}
+static void addSaturatedDecorationToIntrinsic(Instruction *I, IRBuilder<> &B) {
+ if (auto *CI = dyn_cast<CallInst>(I)) {
+ if (Function *Fu = CI->getCalledFunction()) {
+ if (Fu->isIntrinsic()) {
+ unsigned const int IntrinsicId = Fu->getIntrinsicID();
+ switch (IntrinsicId) {
+ case Intrinsic::fptosi_sat:
+ case Intrinsic::fptoui_sat:
+ createSaturatedConversionDecoration(I, B);
+ break;
+ default:
+ break;
+ }
+ }
+ }
+ }
+}
+
Instruction *SPIRVEmitIntrinsics::visitCallInst(CallInst &Call) {
if (!Call.isInlineAsm())
return &Call;
@@ -2400,6 +2419,7 @@ 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 e7d8fe5bd8015b1..2aea5189f46ad15 100644
--- a/llvm/lib/Target/SPIRV/SPIRVInstructionSelector.cpp
+++ b/llvm/lib/Target/SPIRV/SPIRVInstructionSelector.cpp
@@ -603,6 +603,11 @@ bool SPIRVInstructionSelector::spvSelect(Register ResVReg,
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);
case TargetOpcode::G_UITOFP:
diff --git a/llvm/lib/Target/SPIRV/SPIRVLegalizerInfo.cpp b/llvm/lib/Target/SPIRV/SPIRVLegalizerInfo.cpp
index fa5e0a80576d01b..694d584c26e04eb 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_intrinsics.ll b/llvm/test/CodeGen/SPIRV/llvm-intrinsics/fp_to_int_intrinsics.ll
new file mode 100644
index 000000000000000..9f707e2b3cd173f
--- /dev/null
+++ b/llvm/test/CodeGen/SPIRV/llvm-intrinsics/fp_to_int_intrinsics.ll
@@ -0,0 +1,210 @@
+; 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)
+
+; 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)
+
+
+; 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)
+
+
+; 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
+
+;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
+
+
+; 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)
+
+
+; 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)
+
+
+; 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)
+
+
+; 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)
+
+
+; 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)
+
+
+; 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)
+
+
+; 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)
+
+
+; 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.
currently does not support arbitrary size integer because of the constraints placed by the prelegalizer