b8cbc5c02c
The KernelEnvironment is for compile time information about a kernel. It allows the compiler to feed information to the runtime. The KernelLaunchEnvironment is for dynamic information *per* kernel launch. It allows the rutime to feed information to the kernel that is not shared with other invocations of the kernel. The first use case is to replace the globals that synchronize teams reductions with per-launch versions. This allows concurrent teams reductions. More uses cases will follow, e.g., per launch memory pools. Fixes: https://github.com/llvm/llvm-project/issues/70249
29 lines
1.2 KiB
C++
29 lines
1.2 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 %s
|
|
// expected-no-diagnostics
|
|
|
|
#define N 100
|
|
|
|
int test_amdgcn_target_temp_alloca() {
|
|
// CHECK-LABEL: test_amdgcn_target_temp_alloca
|
|
|
|
int arr[N];
|
|
|
|
// CHECK: [[DYN_PTR_ADDR:%.+]] = alloca ptr, align 8, addrspace(5)
|
|
// CHECK: [[VAR_ADDR:%.+]] = alloca ptr, align 8, addrspace(5)
|
|
// CHECK-NEXT: [[VAR2_ADDR:%.+]] = alloca i32, align 4, addrspace(5)
|
|
// CHECK-NEXT: [[DYN_PTR_ADDR_CAST:%.+]] = addrspacecast ptr addrspace(5) [[DYN_PTR_ADDR]] to ptr
|
|
// CHECK-NEXT: [[VAR_ADDR_CAST:%.+]] = addrspacecast ptr addrspace(5) [[VAR_ADDR]] to ptr
|
|
// CHECK-NEXT: [[VAR2_ADDR_CAST:%.+]] = addrspacecast ptr addrspace(5) [[VAR2_ADDR]] to ptr
|
|
// CHECK: store ptr [[VAR:%.+]], ptr [[VAR_ADDR_CAST]], align 8
|
|
|
|
#pragma omp target
|
|
for (int i = 0; i < N; i++) {
|
|
arr[i] = 1;
|
|
}
|
|
|
|
return arr[0];
|
|
}
|