f3a674a2ef
Currently, AMDGPU functions have `target-features` attribute populated with all default features for the target GPU. This is redundant because the backend can derive these defaults from the `target-cpu` attribute via `AMDGPUTargetMachine::getFeatureString()`. In this PR, for AMDGPU targets only: - Functions without explicit target attributes no longer emit `target-features` - Functions with `__attribute__((target(...)))` or `-target-feature` emit only features that differ from the target's defaults (delta) The backend already handles missing `target-features` correctly by falling back to the TargetMachine's defaults. A new cc1 flag `-famdgpu-emit-full-target-features` is added to emit full features when needed. Example: Before: ```llvm attributes #0 = { "target-cpu"="gfx90a" "target-features"="+16-bit-insts,+atomic-buffer-global-pk-add-f16-insts,+atomic-fadd-rtn-insts,+ci-insts,+dl-insts,+dot1-insts,+dot2-insts,..." } ``` After (default): ```llvm attributes #0 = { "target-cpu"="gfx90a" } ``` After (with explicit `+wavefrontsize32` override): ```llvm attributes #0 = { "target-cpu"="gfx90a" "target-features"="+wavefrontsize32" } ```
41 lines
2.7 KiB
C++
41 lines
2.7 KiB
C++
// REQUIRES: amdgpu-registered-target
|
|
|
|
// RUN: %clang_cc1 -fopenmp -x c++ -std=c++11 -triple x86_64-unknown-unknown -fopenmp-targets=amdgcn-amd-amdhsa -emit-llvm-bc %s -o %t-ppc-host.bc
|
|
// RUN: %clang_cc1 -fopenmp -x c++ -std=c++11 -triple amdgcn-amd-amdhsa -fopenmp-targets=amdgcn-amd-amdhsa -emit-llvm %s -fopenmp-is-target-device -fopenmp-host-ir-file-path %t-ppc-host.bc -o - | FileCheck -check-prefixes=DEFAULT,ALL %s
|
|
// RUN: %clang_cc1 -target-cpu gfx900 -fopenmp -x c++ -std=c++11 -triple amdgcn-amd-amdhsa -fopenmp-targets=amdgcn-amd-amdhsa -emit-llvm %s -fopenmp-is-target-device -fopenmp-host-ir-file-path %t-ppc-host.bc -o - | FileCheck -check-prefixes=CPU,ALL %s
|
|
|
|
// RUN: %clang_cc1 -menable-no-nans -mno-amdgpu-ieee -fopenmp -x c++ -std=c++11 -triple amdgcn-amd-amdhsa -fopenmp-targets=amdgcn-amd-amdhsa -emit-llvm %s -fopenmp-is-target-device -fopenmp-host-ir-file-path %t-ppc-host.bc -o - | FileCheck -check-prefixes=NOIEEE,ALL %s
|
|
|
|
// expected-no-diagnostics
|
|
|
|
#define N 100
|
|
|
|
int callable(int);
|
|
|
|
// Check that the target attributes are set on the generated kernel
|
|
int func() {
|
|
// ALL-LABEL: amdgpu_kernel void @__omp_offloading{{.*}} #0
|
|
|
|
int arr[N];
|
|
|
|
#pragma omp target teams thread_limit(42)
|
|
for (int i = 0; i < N; i++) {
|
|
arr[i] = callable(arr[i]);
|
|
}
|
|
|
|
return arr[0];
|
|
}
|
|
|
|
int callable(int x) {
|
|
// ALL-LABEL: @_Z8callablei(i32 noundef %x) #2
|
|
return x + 1;
|
|
}
|
|
|
|
// DEFAULT: attributes #0 = { convergent mustprogress noinline norecurse nounwind optnone "amdgpu-flat-work-group-size"="1,42" "kernel" "no-trapping-math"="true" "omp_target_thread_limit"="42" "stack-protector-buffer-size"="8" "uniform-work-group-size"="true" }
|
|
// CPU: attributes #0 = { convergent mustprogress noinline norecurse nounwind optnone "amdgpu-flat-work-group-size"="1,42" "kernel" "no-trapping-math"="true" "omp_target_thread_limit"="42" "stack-protector-buffer-size"="8" "target-cpu"="gfx900" "uniform-work-group-size"="true" }
|
|
// NOIEEE: attributes #0 = { convergent mustprogress noinline norecurse nounwind optnone "amdgpu-flat-work-group-size"="1,42" "amdgpu-ieee"="false" "kernel" "no-nans-fp-math"="true" "no-trapping-math"="true" "omp_target_thread_limit"="42" "stack-protector-buffer-size"="8" "uniform-work-group-size"="true" }
|
|
|
|
// DEFAULT: attributes #2 = { convergent mustprogress noinline nounwind optnone "no-trapping-math"="true" "stack-protector-buffer-size"="8" }
|
|
// CPU: attributes #2 = { convergent mustprogress noinline nounwind optnone "no-trapping-math"="true" "stack-protector-buffer-size"="8" "target-cpu"="gfx900" }
|
|
// NOIEEE: attributes #2 = { convergent mustprogress noinline nounwind optnone "amdgpu-ieee"="false" "no-nans-fp-math"="true" "no-trapping-math"="true" "stack-protector-buffer-size"="8" }
|