Index: clang/lib/CodeGen/TargetInfo.cpp =================================================================== --- clang/lib/CodeGen/TargetInfo.cpp +++ clang/lib/CodeGen/TargetInfo.cpp @@ -9303,16 +9303,9 @@ if (FD) setFunctionDeclAttributes(FD, F, M); - const bool IsOpenCLKernel = - M.getLangOpts().OpenCL && FD && FD->hasAttr(); const bool IsHIPKernel = M.getLangOpts().HIP && FD && FD->hasAttr(); - const bool IsOpenMP = M.getLangOpts().OpenMP && !FD; - if ((IsOpenCLKernel || IsHIPKernel || IsOpenMP) && - (M.getTriple().getOS() == llvm::Triple::AMDHSA)) - F->addFnAttr("amdgpu-implicitarg-num-bytes", "56"); - if (IsHIPKernel) F->addFnAttr("uniform-work-group-size", "true"); Index: clang/test/CodeGenCUDA/amdgpu-hip-implicit-kernarg.cu =================================================================== --- clang/test/CodeGenCUDA/amdgpu-hip-implicit-kernarg.cu +++ /dev/null @@ -1,8 +0,0 @@ -// REQUIRES: amdgpu-registered-target -// RUN: %clang_cc1 -triple amdgcn-amd-amdhsa -fcuda-is-device -emit-llvm -x hip -o - %s | FileCheck %s -#include "Inputs/cuda.h" - -__global__ void hip_kernel_temp() { -} - -// CHECK: attributes {{.*}} = {{.*}} "amdgpu-implicitarg-num-bytes"="56" Index: clang/test/CodeGenOpenCL/amdgpu-attrs.cl =================================================================== --- clang/test/CodeGenOpenCL/amdgpu-attrs.cl +++ clang/test/CodeGenOpenCL/amdgpu-attrs.cl @@ -153,8 +153,7 @@ // X86-NOT: "amdgpu-waves-per-eu" // X86-NOT: "amdgpu-num-vgpr" // X86-NOT: "amdgpu-num-sgpr" -// X86-NOT: "amdgpu-implicitarg-num-bytes" -// NONAMDHSA-NOT: "amdgpu-implicitarg-num-bytes" +// CHECK-NOT: "amdgpu-implicitarg-num-bytes" // CHECK-NOT: "amdgpu-flat-work-group-size"="0,0" // CHECK-NOT: "amdgpu-waves-per-eu"="0" @@ -162,33 +161,33 @@ // CHECK-NOT: "amdgpu-num-sgpr"="0" // CHECK-NOT: "amdgpu-num-vgpr"="0" -// CHECK-DAG: attributes [[FLAT_WORK_GROUP_SIZE_32_64]] = {{.*}} "amdgpu-flat-work-group-size"="32,64" "amdgpu-implicitarg-num-bytes"="56" -// CHECK-DAG: attributes [[FLAT_WORK_GROUP_SIZE_64_64]] = {{.*}} "amdgpu-flat-work-group-size"="64,64" "amdgpu-implicitarg-num-bytes"="56" -// CHECK-DAG: attributes [[FLAT_WORK_GROUP_SIZE_16_128]] = {{.*}} "amdgpu-flat-work-group-size"="16,128" "amdgpu-implicitarg-num-bytes"="56" +// CHECK-DAG: attributes [[FLAT_WORK_GROUP_SIZE_32_64]] = {{.*}} "amdgpu-flat-work-group-size"="32,64" +// CHECK-DAG: attributes [[FLAT_WORK_GROUP_SIZE_64_64]] = {{.*}} "amdgpu-flat-work-group-size"="64,64" +// CHECK-DAG: attributes [[FLAT_WORK_GROUP_SIZE_16_128]] = {{.*}} "amdgpu-flat-work-group-size"="16,128" -// CHECK-DAG: attributes [[WAVES_PER_EU_2]] = {{.*}} "amdgpu-flat-work-group-size"="1,256" "amdgpu-implicitarg-num-bytes"="56" "amdgpu-waves-per-eu"="2" +// CHECK-DAG: attributes [[WAVES_PER_EU_2]] = {{.*}} "amdgpu-flat-work-group-size"="1,256" "amdgpu-waves-per-eu"="2" -// CHECK-DAG: attributes [[WAVES_PER_EU_2_4]] = {{.*}} "amdgpu-flat-work-group-size"="1,256" "amdgpu-implicitarg-num-bytes"="56" "amdgpu-waves-per-eu"="2,4" -// CHECK-DAG: attributes [[NUM_SGPR_32]] = {{.*}} "amdgpu-flat-work-group-size"="1,256" "amdgpu-implicitarg-num-bytes"="56" "amdgpu-num-sgpr"="32" -// CHECK-DAG: attributes [[NUM_VGPR_64]] = {{.*}} "amdgpu-flat-work-group-size"="1,256" "amdgpu-implicitarg-num-bytes"="56" "amdgpu-num-vgpr"="64" +// CHECK-DAG: attributes [[WAVES_PER_EU_2_4]] = {{.*}} "amdgpu-flat-work-group-size"="1,256" "amdgpu-waves-per-eu"="2,4" +// CHECK-DAG: attributes [[NUM_SGPR_32]] = {{.*}} "amdgpu-flat-work-group-size"="1,256" "amdgpu-num-sgpr"="32" +// CHECK-DAG: attributes [[NUM_VGPR_64]] = {{.*}} "amdgpu-flat-work-group-size"="1,256" "amdgpu-num-vgpr"="64" -// CHECK-DAG: attributes [[FLAT_WORK_GROUP_SIZE_32_64_WAVES_PER_EU_2]] = {{.*}} "amdgpu-flat-work-group-size"="32,64" "amdgpu-implicitarg-num-bytes"="56" "amdgpu-waves-per-eu"="2" -// CHECK-DAG: attributes [[FLAT_WORK_GROUP_SIZE_32_64_WAVES_PER_EU_2_4]] = {{.*}} "amdgpu-flat-work-group-size"="32,64" "amdgpu-implicitarg-num-bytes"="56" "amdgpu-waves-per-eu"="2,4" -// CHECK-DAG: attributes [[FLAT_WORK_GROUP_SIZE_32_64_NUM_SGPR_32]] = {{.*}} "amdgpu-flat-work-group-size"="32,64" "amdgpu-implicitarg-num-bytes"="56" "amdgpu-num-sgpr"="32" -// CHECK-DAG: attributes [[FLAT_WORK_GROUP_SIZE_32_64_NUM_VGPR_64]] = {{.*}} "amdgpu-flat-work-group-size"="32,64" "amdgpu-implicitarg-num-bytes"="56" "amdgpu-num-vgpr"="64" -// CHECK-DAG: attributes [[WAVES_PER_EU_2_NUM_SGPR_32]] = {{.*}} "amdgpu-flat-work-group-size"="1,256" "amdgpu-implicitarg-num-bytes"="56" "amdgpu-num-sgpr"="32" "amdgpu-waves-per-eu"="2" -// CHECK-DAG: attributes [[WAVES_PER_EU_2_NUM_VGPR_64]] = {{.*}} "amdgpu-flat-work-group-size"="1,256" "amdgpu-implicitarg-num-bytes"="56" "amdgpu-num-vgpr"="64" "amdgpu-waves-per-eu"="2" -// CHECK-DAG: attributes [[WAVES_PER_EU_2_4_NUM_SGPR_32]] = {{.*}} "amdgpu-flat-work-group-size"="1,256" "amdgpu-implicitarg-num-bytes"="56" "amdgpu-num-sgpr"="32" "amdgpu-waves-per-eu"="2,4" -// CHECK-DAG: attributes [[WAVES_PER_EU_2_4_NUM_VGPR_64]] = {{.*}} "amdgpu-flat-work-group-size"="1,256" "amdgpu-implicitarg-num-bytes"="56" "amdgpu-num-vgpr"="64" "amdgpu-waves-per-eu"="2,4" -// CHECK-DAG: attributes [[NUM_SGPR_32_NUM_VGPR_64]] = {{.*}} "amdgpu-flat-work-group-size"="1,256" "amdgpu-implicitarg-num-bytes"="56" "amdgpu-num-sgpr"="32" "amdgpu-num-vgpr"="64" +// CHECK-DAG: attributes [[FLAT_WORK_GROUP_SIZE_32_64_WAVES_PER_EU_2]] = {{.*}} "amdgpu-flat-work-group-size"="32,64" "amdgpu-waves-per-eu"="2" +// CHECK-DAG: attributes [[FLAT_WORK_GROUP_SIZE_32_64_WAVES_PER_EU_2_4]] = {{.*}} "amdgpu-flat-work-group-size"="32,64" "amdgpu-waves-per-eu"="2,4" +// CHECK-DAG: attributes [[FLAT_WORK_GROUP_SIZE_32_64_NUM_SGPR_32]] = {{.*}} "amdgpu-flat-work-group-size"="32,64" "amdgpu-num-sgpr"="32" +// CHECK-DAG: attributes [[FLAT_WORK_GROUP_SIZE_32_64_NUM_VGPR_64]] = {{.*}} "amdgpu-flat-work-group-size"="32,64" "amdgpu-num-vgpr"="64" +// CHECK-DAG: attributes [[WAVES_PER_EU_2_NUM_SGPR_32]] = {{.*}} "amdgpu-flat-work-group-size"="1,256" "amdgpu-num-sgpr"="32" "amdgpu-waves-per-eu"="2" +// CHECK-DAG: attributes [[WAVES_PER_EU_2_NUM_VGPR_64]] = {{.*}} "amdgpu-flat-work-group-size"="1,256" "amdgpu-num-vgpr"="64" "amdgpu-waves-per-eu"="2" +// CHECK-DAG: attributes [[WAVES_PER_EU_2_4_NUM_SGPR_32]] = {{.*}} "amdgpu-flat-work-group-size"="1,256" "amdgpu-num-sgpr"="32" "amdgpu-waves-per-eu"="2,4" +// CHECK-DAG: attributes [[WAVES_PER_EU_2_4_NUM_VGPR_64]] = {{.*}} "amdgpu-flat-work-group-size"="1,256" "amdgpu-num-vgpr"="64" "amdgpu-waves-per-eu"="2,4" +// CHECK-DAG: attributes [[NUM_SGPR_32_NUM_VGPR_64]] = {{.*}} "amdgpu-flat-work-group-size"="1,256" "amdgpu-num-sgpr"="32" "amdgpu-num-vgpr"="64" -// CHECK-DAG: attributes [[FLAT_WORK_GROUP_SIZE_32_64_WAVES_PER_EU_2_NUM_SGPR_32]] = {{.*}} "amdgpu-flat-work-group-size"="32,64" "amdgpu-implicitarg-num-bytes"="56" "amdgpu-num-sgpr"="32" "amdgpu-waves-per-eu"="2" -// CHECK-DAG: attributes [[FLAT_WORK_GROUP_SIZE_32_64_WAVES_PER_EU_2_NUM_VGPR_64]] = {{.*}} "amdgpu-flat-work-group-size"="32,64" "amdgpu-implicitarg-num-bytes"="56" "amdgpu-num-vgpr"="64" "amdgpu-waves-per-eu"="2" -// CHECK-DAG: attributes [[FLAT_WORK_GROUP_SIZE_32_64_WAVES_PER_EU_2_4_NUM_SGPR_32]] = {{.*}} "amdgpu-flat-work-group-size"="32,64" "amdgpu-implicitarg-num-bytes"="56" "amdgpu-num-sgpr"="32" "amdgpu-waves-per-eu"="2,4" -// CHECK-DAG: attributes [[FLAT_WORK_GROUP_SIZE_32_64_WAVES_PER_EU_2_4_NUM_VGPR_64]] = {{.*}} "amdgpu-flat-work-group-size"="32,64" "amdgpu-implicitarg-num-bytes"="56" "amdgpu-num-vgpr"="64" "amdgpu-waves-per-eu"="2,4" +// CHECK-DAG: attributes [[FLAT_WORK_GROUP_SIZE_32_64_WAVES_PER_EU_2_NUM_SGPR_32]] = {{.*}} "amdgpu-flat-work-group-size"="32,64" "amdgpu-num-sgpr"="32" "amdgpu-waves-per-eu"="2" +// CHECK-DAG: attributes [[FLAT_WORK_GROUP_SIZE_32_64_WAVES_PER_EU_2_NUM_VGPR_64]] = {{.*}} "amdgpu-flat-work-group-size"="32,64" "amdgpu-num-vgpr"="64" "amdgpu-waves-per-eu"="2" +// CHECK-DAG: attributes [[FLAT_WORK_GROUP_SIZE_32_64_WAVES_PER_EU_2_4_NUM_SGPR_32]] = {{.*}} "amdgpu-flat-work-group-size"="32,64" "amdgpu-num-sgpr"="32" "amdgpu-waves-per-eu"="2,4" +// CHECK-DAG: attributes [[FLAT_WORK_GROUP_SIZE_32_64_WAVES_PER_EU_2_4_NUM_VGPR_64]] = {{.*}} "amdgpu-flat-work-group-size"="32,64" "amdgpu-num-vgpr"="64" "amdgpu-waves-per-eu"="2,4" -// CHECK-DAG: attributes [[FLAT_WORK_GROUP_SIZE_32_64_WAVES_PER_EU_2_NUM_SGPR_32_NUM_VGPR_64]] = {{.*}} "amdgpu-flat-work-group-size"="32,64" "amdgpu-implicitarg-num-bytes"="56" "amdgpu-num-sgpr"="32" "amdgpu-num-vgpr"="64" "amdgpu-waves-per-eu"="2" -// CHECK-DAG: attributes [[FLAT_WORK_GROUP_SIZE_32_64_WAVES_PER_EU_2_4_NUM_SGPR_32_NUM_VGPR_64]] = {{.*}} "amdgpu-flat-work-group-size"="32,64" "amdgpu-implicitarg-num-bytes"="56" "amdgpu-num-sgpr"="32" "amdgpu-num-vgpr"="64" "amdgpu-waves-per-eu"="2,4" +// CHECK-DAG: attributes [[FLAT_WORK_GROUP_SIZE_32_64_WAVES_PER_EU_2_NUM_SGPR_32_NUM_VGPR_64]] = {{.*}} "amdgpu-flat-work-group-size"="32,64" "amdgpu-num-sgpr"="32" "amdgpu-num-vgpr"="64" "amdgpu-waves-per-eu"="2" +// CHECK-DAG: attributes [[FLAT_WORK_GROUP_SIZE_32_64_WAVES_PER_EU_2_4_NUM_SGPR_32_NUM_VGPR_64]] = {{.*}} "amdgpu-flat-work-group-size"="32,64" "amdgpu-num-sgpr"="32" "amdgpu-num-vgpr"="64" "amdgpu-waves-per-eu"="2,4" // CHECK-DAG: attributes [[A_FUNCTION]] = {{.*}} -// CHECK-DAG: attributes [[DEFAULT_KERNEL_ATTRS]] = {{.*}} "amdgpu-flat-work-group-size"="1,256" "amdgpu-implicitarg-num-bytes"="56" +// CHECK-DAG: attributes [[DEFAULT_KERNEL_ATTRS]] = {{.*}} "amdgpu-flat-work-group-size"="1,256" Index: clang/test/OpenMP/amdgcn-attributes.cpp =================================================================== --- clang/test/OpenMP/amdgcn-attributes.cpp +++ clang/test/OpenMP/amdgcn-attributes.cpp @@ -32,10 +32,10 @@ return x + 1; } - // DEFAULT: attributes #0 = { convergent noinline norecurse nounwind optnone "amdgpu-implicitarg-num-bytes"="56" "frame-pointer"="none" "min-legal-vector-width"="0" "no-trapping-math"="true" "stack-protector-buffer-size"="8" } - // CPU: attributes #0 = { convergent noinline norecurse nounwind optnone "amdgpu-implicitarg-num-bytes"="56" "frame-pointer"="none" "min-legal-vector-width"="0" "no-trapping-math"="true" "stack-protector-buffer-size"="8" "target-cpu"="gfx900" "target-features"="+16-bit-insts,+ci-insts,+dpp,+flat-address-space,+gfx8-insts,+gfx9-insts,+s-memrealtime,+s-memtime-inst" } - // NOIEEE: attributes #0 = { convergent noinline norecurse nounwind optnone "amdgpu-ieee"="false" "amdgpu-implicitarg-num-bytes"="56" "frame-pointer"="none" "min-legal-vector-width"="0" "no-nans-fp-math"="true" "no-trapping-math"="true" "stack-protector-buffer-size"="8" } - // UNSAFEATOMIC: attributes #0 = { convergent noinline norecurse nounwind optnone "amdgpu-implicitarg-num-bytes"="56" "amdgpu-unsafe-fp-atomics"="true" "frame-pointer"="none" "min-legal-vector-width"="0" "no-trapping-math"="true" "stack-protector-buffer-size"="8" } + // DEFAULT: attributes #0 = { convergent noinline norecurse nounwind optnone "frame-pointer"="none" "min-legal-vector-width"="0" "no-trapping-math"="true" "stack-protector-buffer-size"="8" } + // CPU: attributes #0 = { convergent noinline norecurse nounwind optnone "frame-pointer"="none" "min-legal-vector-width"="0" "no-trapping-math"="true" "stack-protector-buffer-size"="8" "target-cpu"="gfx900" "target-features"="+16-bit-insts,+ci-insts,+dpp,+flat-address-space,+gfx8-insts,+gfx9-insts,+s-memrealtime,+s-memtime-inst" } + // NOIEEE: attributes #0 = { convergent noinline norecurse nounwind optnone "amdgpu-ieee"="false" "frame-pointer"="none" "min-legal-vector-width"="0" "no-nans-fp-math"="true" "no-trapping-math"="true" "stack-protector-buffer-size"="8" } + // UNSAFEATOMIC: attributes #0 = { convergent noinline norecurse nounwind optnone "amdgpu-unsafe-fp-atomics"="true" "frame-pointer"="none" "min-legal-vector-width"="0" "no-trapping-math"="true" "stack-protector-buffer-size"="8" } // DEFAULT: attributes #1 = { convergent mustprogress noinline nounwind optnone "frame-pointer"="none" "min-legal-vector-width"="0" "no-trapping-math"="true" "stack-protector-buffer-size"="8" } // CPU: attributes #1 = { convergent mustprogress noinline nounwind optnone "frame-pointer"="none" "min-legal-vector-width"="0" "no-trapping-math"="true" "stack-protector-buffer-size"="8" "target-cpu"="gfx900" "target-features"="+16-bit-insts,+ci-insts,+dpp,+flat-address-space,+gfx8-insts,+gfx9-insts,+s-memrealtime,+s-memtime-inst" }