diff options
| -rw-r--r-- | clang/docs/UsersManual.rst | 4 | ||||
| -rw-r--r-- | clang/lib/CodeGen/TargetInfo.cpp | 5 | ||||
| -rw-r--r-- | clang/test/CodeGenOpenCL/amdgpu-attrs.cl | 61 |
3 files changed, 42 insertions, 28 deletions
diff --git a/clang/docs/UsersManual.rst b/clang/docs/UsersManual.rst index 1e46ebe03f8..25f99cf1531 100644 --- a/clang/docs/UsersManual.rst +++ b/clang/docs/UsersManual.rst @@ -2180,7 +2180,7 @@ to the target, for example: .. code-block:: console $ clang -target nvptx64-unknown-unknown test.cl - $ clang -target amdgcn-amd-amdhsa-opencl test.cl + $ clang -target amdgcn-amd-amdhsa -mcpu=gfx900 test.cl Compiling to bitcode can be done as follows: @@ -2288,7 +2288,7 @@ There is a set of concrete HW architectures that OpenCL can be compiled for. .. code-block:: console - $ clang -target amdgcn-amd-amdhsa-opencl test.cl + $ clang -target amdgcn-amd-amdhsa -mcpu=gfx900 test.cl - For Nvidia architectures: diff --git a/clang/lib/CodeGen/TargetInfo.cpp b/clang/lib/CodeGen/TargetInfo.cpp index 01eb6ead163..435565dce3f 100644 --- a/clang/lib/CodeGen/TargetInfo.cpp +++ b/clang/lib/CodeGen/TargetInfo.cpp @@ -7661,6 +7661,11 @@ void AMDGPUTargetCodeGenInfo::setTargetAttributes( const auto *ReqdWGS = M.getLangOpts().OpenCL ? FD->getAttr<ReqdWorkGroupSizeAttr>() : nullptr; + + if (M.getLangOpts().OpenCL && FD->hasAttr<OpenCLKernelAttr>() && + (M.getTriple().getOS() == llvm::Triple::AMDHSA)) + F->addFnAttr("amdgpu-implicitarg-num-bytes", "32"); + const auto *FlatWGS = FD->getAttr<AMDGPUFlatWorkGroupSizeAttr>(); if (ReqdWGS || FlatWGS) { unsigned Min = FlatWGS ? FlatWGS->getMin() : 0; diff --git a/clang/test/CodeGenOpenCL/amdgpu-attrs.cl b/clang/test/CodeGenOpenCL/amdgpu-attrs.cl index 2696123f143..2cd0c2e9edc 100644 --- a/clang/test/CodeGenOpenCL/amdgpu-attrs.cl +++ b/clang/test/CodeGenOpenCL/amdgpu-attrs.cl @@ -1,4 +1,5 @@ -// RUN: %clang_cc1 -triple amdgcn-- -target-cpu tahiti -O0 -emit-llvm -o - %s | FileCheck %s +// RUN: %clang_cc1 -triple amdgcn-amd-amdhsa -target-cpu tahiti -O0 -emit-llvm -o - %s | FileCheck %s +// RUN: %clang_cc1 -triple amdgcn-- -target-cpu tahiti -O0 -emit-llvm -o - %s | FileCheck %s -check-prefix=NONAMDHSA // RUN: %clang_cc1 -triple x86_64-unknown-linux-gnu -O0 -emit-llvm -verify -o - %s | FileCheck -check-prefix=X86 %s __attribute__((amdgpu_flat_work_group_size(0, 0))) // expected-no-diagnostics @@ -138,12 +139,18 @@ kernel void reqd_work_group_size_32_2_1_flat_work_group_size_16_128() { // CHECK: define amdgpu_kernel void @reqd_work_group_size_32_2_1_flat_work_group_size_16_128() [[FLAT_WORK_GROUP_SIZE_16_128:#[0-9]+]] } +void a_function() { +// CHECK: define void @a_function() [[A_FUNCTION:#[0-9]+]] +} + // Make sure this is silently accepted on other targets. // X86-NOT: "amdgpu-flat-work-group-size" // 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-flat-work-group-size"="0,0" // CHECK-NOT: "amdgpu-waves-per-eu"="0" @@ -151,28 +158,30 @@ kernel void reqd_work_group_size_32_2_1_flat_work_group_size_16_128() { // CHECK-NOT: "amdgpu-num-sgpr"="0" // CHECK-NOT: "amdgpu-num-vgpr"="0" -// CHECK-DAG: attributes [[FLAT_WORK_GROUP_SIZE_32_64]] = { convergent noinline nounwind optnone "amdgpu-flat-work-group-size"="32,64" -// CHECK-DAG: attributes [[FLAT_WORK_GROUP_SIZE_64_64]] = { convergent noinline nounwind optnone "amdgpu-flat-work-group-size"="64,64" -// CHECK-DAG: attributes [[FLAT_WORK_GROUP_SIZE_16_128]] = { convergent noinline nounwind optnone "amdgpu-flat-work-group-size"="16,128" -// CHECK-DAG: attributes [[WAVES_PER_EU_2]] = { convergent noinline nounwind optnone "amdgpu-waves-per-eu"="2" -// CHECK-DAG: attributes [[WAVES_PER_EU_2_4]] = { convergent noinline nounwind optnone "amdgpu-waves-per-eu"="2,4" -// CHECK-DAG: attributes [[NUM_SGPR_32]] = { convergent noinline nounwind optnone "amdgpu-num-sgpr"="32" -// CHECK-DAG: attributes [[NUM_VGPR_64]] = { convergent noinline nounwind optnone "amdgpu-num-vgpr"="64" - -// CHECK-DAG: attributes [[FLAT_WORK_GROUP_SIZE_32_64_WAVES_PER_EU_2]] = { convergent noinline nounwind optnone "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]] = { convergent noinline nounwind optnone "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]] = { convergent noinline nounwind optnone "amdgpu-flat-work-group-size"="32,64" "amdgpu-num-sgpr"="32" -// CHECK-DAG: attributes [[FLAT_WORK_GROUP_SIZE_32_64_NUM_VGPR_64]] = { convergent noinline nounwind optnone "amdgpu-flat-work-group-size"="32,64" "amdgpu-num-vgpr"="64" -// CHECK-DAG: attributes [[WAVES_PER_EU_2_NUM_SGPR_32]] = { convergent noinline nounwind optnone "amdgpu-num-sgpr"="32" "amdgpu-waves-per-eu"="2" -// CHECK-DAG: attributes [[WAVES_PER_EU_2_NUM_VGPR_64]] = { convergent noinline nounwind optnone "amdgpu-num-vgpr"="64" "amdgpu-waves-per-eu"="2" -// CHECK-DAG: attributes [[WAVES_PER_EU_2_4_NUM_SGPR_32]] = { convergent noinline nounwind optnone "amdgpu-num-sgpr"="32" "amdgpu-waves-per-eu"="2,4" -// CHECK-DAG: attributes [[WAVES_PER_EU_2_4_NUM_VGPR_64]] = { convergent noinline nounwind optnone "amdgpu-num-vgpr"="64" "amdgpu-waves-per-eu"="2,4" -// CHECK-DAG: attributes [[NUM_SGPR_32_NUM_VGPR_64]] = { convergent noinline nounwind optnone "amdgpu-num-sgpr"="32" "amdgpu-num-vgpr"="64" - -// CHECK-DAG: attributes [[FLAT_WORK_GROUP_SIZE_32_64_WAVES_PER_EU_2_NUM_SGPR_32]] = { convergent noinline nounwind optnone "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]] = { convergent noinline nounwind optnone "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]] = { convergent noinline nounwind optnone "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]] = { convergent noinline nounwind optnone "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]] = { convergent noinline nounwind optnone "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]] = { convergent noinline nounwind optnone "amdgpu-flat-work-group-size"="32,64" "amdgpu-num-sgpr"="32" "amdgpu-num-vgpr"="64" "amdgpu-waves-per-eu"="2,4" +// CHECK-DAG: attributes [[FLAT_WORK_GROUP_SIZE_32_64]] = { convergent noinline nounwind optnone "amdgpu-flat-work-group-size"="32,64" "amdgpu-implicitarg-num-bytes"="32" +// CHECK-DAG: attributes [[FLAT_WORK_GROUP_SIZE_64_64]] = { convergent noinline nounwind optnone "amdgpu-flat-work-group-size"="64,64" "amdgpu-implicitarg-num-bytes"="32" +// CHECK-DAG: attributes [[FLAT_WORK_GROUP_SIZE_16_128]] = { convergent noinline nounwind optnone "amdgpu-flat-work-group-size"="16,128" "amdgpu-implicitarg-num-bytes"="32" +// CHECK-DAG: attributes [[WAVES_PER_EU_2]] = { convergent noinline nounwind optnone "amdgpu-implicitarg-num-bytes"="32" "amdgpu-waves-per-eu"="2" +// CHECK-DAG: attributes [[WAVES_PER_EU_2_4]] = { convergent noinline nounwind optnone "amdgpu-implicitarg-num-bytes"="32" "amdgpu-waves-per-eu"="2,4" +// CHECK-DAG: attributes [[NUM_SGPR_32]] = { convergent noinline nounwind optnone "amdgpu-implicitarg-num-bytes"="32" "amdgpu-num-sgpr"="32" +// CHECK-DAG: attributes [[NUM_VGPR_64]] = { convergent noinline nounwind optnone "amdgpu-implicitarg-num-bytes"="32" "amdgpu-num-vgpr"="64" + +// CHECK-DAG: attributes [[FLAT_WORK_GROUP_SIZE_32_64_WAVES_PER_EU_2]] = { convergent noinline nounwind optnone "amdgpu-flat-work-group-size"="32,64" "amdgpu-implicitarg-num-bytes"="32" "amdgpu-waves-per-eu"="2" +// CHECK-DAG: attributes [[FLAT_WORK_GROUP_SIZE_32_64_WAVES_PER_EU_2_4]] = { convergent noinline nounwind optnone "amdgpu-flat-work-group-size"="32,64" "amdgpu-implicitarg-num-bytes"="32" "amdgpu-waves-per-eu"="2,4" +// CHECK-DAG: attributes [[FLAT_WORK_GROUP_SIZE_32_64_NUM_SGPR_32]] = { convergent noinline nounwind optnone "amdgpu-flat-work-group-size"="32,64" "amdgpu-implicitarg-num-bytes"="32" "amdgpu-num-sgpr"="32" +// CHECK-DAG: attributes [[FLAT_WORK_GROUP_SIZE_32_64_NUM_VGPR_64]] = { convergent noinline nounwind optnone "amdgpu-flat-work-group-size"="32,64" "amdgpu-implicitarg-num-bytes"="32" "amdgpu-num-vgpr"="64" +// CHECK-DAG: attributes [[WAVES_PER_EU_2_NUM_SGPR_32]] = { convergent noinline nounwind optnone "amdgpu-implicitarg-num-bytes"="32" "amdgpu-num-sgpr"="32" "amdgpu-waves-per-eu"="2" +// CHECK-DAG: attributes [[WAVES_PER_EU_2_NUM_VGPR_64]] = { convergent noinline nounwind optnone "amdgpu-implicitarg-num-bytes"="32" "amdgpu-num-vgpr"="64" "amdgpu-waves-per-eu"="2" +// CHECK-DAG: attributes [[WAVES_PER_EU_2_4_NUM_SGPR_32]] = { convergent noinline nounwind optnone "amdgpu-implicitarg-num-bytes"="32" "amdgpu-num-sgpr"="32" "amdgpu-waves-per-eu"="2,4" +// CHECK-DAG: attributes [[WAVES_PER_EU_2_4_NUM_VGPR_64]] = { convergent noinline nounwind optnone "amdgpu-implicitarg-num-bytes"="32" "amdgpu-num-vgpr"="64" "amdgpu-waves-per-eu"="2,4" +// CHECK-DAG: attributes [[NUM_SGPR_32_NUM_VGPR_64]] = { convergent noinline nounwind optnone "amdgpu-implicitarg-num-bytes"="32" "amdgpu-num-sgpr"="32" "amdgpu-num-vgpr"="64" + +// CHECK-DAG: attributes [[FLAT_WORK_GROUP_SIZE_32_64_WAVES_PER_EU_2_NUM_SGPR_32]] = { convergent noinline nounwind optnone "amdgpu-flat-work-group-size"="32,64" "amdgpu-implicitarg-num-bytes"="32" "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]] = { convergent noinline nounwind optnone "amdgpu-flat-work-group-size"="32,64" "amdgpu-implicitarg-num-bytes"="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]] = { convergent noinline nounwind optnone "amdgpu-flat-work-group-size"="32,64" "amdgpu-implicitarg-num-bytes"="32" "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]] = { convergent noinline nounwind optnone "amdgpu-flat-work-group-size"="32,64" "amdgpu-implicitarg-num-bytes"="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]] = { convergent noinline nounwind optnone "amdgpu-flat-work-group-size"="32,64" "amdgpu-implicitarg-num-bytes"="32" "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]] = { convergent noinline nounwind optnone "amdgpu-flat-work-group-size"="32,64" "amdgpu-implicitarg-num-bytes"="32" "amdgpu-num-sgpr"="32" "amdgpu-num-vgpr"="64" "amdgpu-waves-per-eu"="2,4" + +// CHECK-DAG: attributes [[A_FUNCTION]] = { convergent noinline nounwind optnone "correctly-rounded-divide-sqrt-fp-math"="false" |
