shylie/llvm-project
1
0
Fork 0
Code Issues Pull Requests Actions 7 Packages Projects Releases Wiki Activity
llvm-project/clang/test/OpenMP/nvptx_data_sharing.cpp
Shilei Tian 10068cd654 [OpenMP] Introduce kernel environment 
This patch introduces per kernel environment. Previously, flags such as execution mode are set through global variables with name like `__kernel_name_exec_mode`. They are accessible on the host by reading the corresponding global variable, but not from the device. Besides, some assumptions, such as no nested parallelism, are not per kernel basis, preventing us applying per kernel optimization in the device runtime.

This is a combination and refinement of patch series D116908, D116909, and D116910.

Depend on D155886.

Reviewed By: jdoerfert

Differential Revision: https://reviews.llvm.org/D142569
2023-07-26 13:35:14 -04:00

138 lines
8.1 KiB
C++
Raw Blame History

// NOTE: Assertions have been autogenerated by utils/update_cc_test_checks.py UTC_ARGS: --function-signature --include-generated-funcs --replace-value-regex "__omp_offloading_[0-9a-z]+_[0-9a-z]+" "reduction_size[.].+[.]" "pl_cond[.].+[.|,]" --prefix-filecheck-ir-name _
// Test device global memory data sharing codegen.
///==========================================================================///
// RUN: %clang_cc1 -verify -fopenmp -x c++ -triple powerpc64le-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm-bc %s -o %t-ppc-host.bc
// RUN: %clang_cc1 -verify -fopenmp -x c++ -triple nvptx64-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm %s -fopenmp-is-target-device -fopenmp-host-ir-file-path %t-ppc-host.bc -o - -disable-llvm-optzns | FileCheck %s --check-prefix=CHECK
// expected-no-diagnostics
#ifndef HEADER
#define HEADER
void test_ds(){
#pragma omp target
{
int a = 10;
#pragma omp parallel
{
a = 1000;
}
int b = 100;
int c = 1000;
#pragma omp parallel private(c)
{
int *c1 = &c;
b = a + 10000;
}
}
}
#endif
// CHECK-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z7test_dsv_l14
// CHECK-SAME: () #[[ATTR0:[0-9]+]] {
// CHECK-NEXT: entry:
// CHECK-NEXT: [[CAPTURED_VARS_ADDRS:%.*]] = alloca [1 x ptr], align 8
// CHECK-NEXT: [[C:%.*]] = alloca i32, align 4
// CHECK-NEXT: [[CAPTURED_VARS_ADDRS1:%.*]] = alloca [2 x ptr], align 8
// CHECK-NEXT: [[TMP0:%.*]] = call i32 @__kmpc_target_init(ptr @{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z7test_dsv_l14_kernel_environment)
// CHECK-NEXT: [[EXEC_USER_CODE:%.*]] = icmp eq i32 [[TMP0]], -1
// CHECK-NEXT: br i1 [[EXEC_USER_CODE]], label [[USER_CODE_ENTRY:%.*]], label [[WORKER_EXIT:%.*]]
// CHECK: user_code.entry:
// CHECK-NEXT: [[A:%.*]] = call align 8 ptr @__kmpc_alloc_shared(i64 4)
// CHECK-NEXT: [[B:%.*]] = call align 8 ptr @__kmpc_alloc_shared(i64 4)
// CHECK-NEXT: [[TMP1:%.*]] = call i32 @__kmpc_global_thread_num(ptr @[[GLOB1:[0-9]+]])
// CHECK-NEXT: store i32 10, ptr [[A]], align 4
// CHECK-NEXT: [[TMP2:%.*]] = getelementptr inbounds [1 x ptr], ptr [[CAPTURED_VARS_ADDRS]], i64 0, i64 0
// CHECK-NEXT: store ptr [[A]], ptr [[TMP2]], align 8
// CHECK-NEXT: call void @__kmpc_parallel_51(ptr @[[GLOB1]], i32 [[TMP1]], i32 1, i32 -1, i32 -1, ptr @{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z7test_dsv_l14_omp_outlined, ptr @{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z7test_dsv_l14_omp_outlined_wrapper, ptr [[CAPTURED_VARS_ADDRS]], i64 1)
// CHECK-NEXT: store i32 100, ptr [[B]], align 4
// CHECK-NEXT: store i32 1000, ptr [[C]], align 4
// CHECK-NEXT: [[TMP3:%.*]] = getelementptr inbounds [2 x ptr], ptr [[CAPTURED_VARS_ADDRS1]], i64 0, i64 0
// CHECK-NEXT: store ptr [[B]], ptr [[TMP3]], align 8
// CHECK-NEXT: [[TMP4:%.*]] = getelementptr inbounds [2 x ptr], ptr [[CAPTURED_VARS_ADDRS1]], i64 0, i64 1
// CHECK-NEXT: store ptr [[A]], ptr [[TMP4]], align 8
// CHECK-NEXT: call void @__kmpc_parallel_51(ptr @[[GLOB1]], i32 [[TMP1]], i32 1, i32 -1, i32 -1, ptr @{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z7test_dsv_l14_omp_outlined1, ptr @{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z7test_dsv_l14_omp_outlined1_wrapper, ptr [[CAPTURED_VARS_ADDRS1]], i64 2)
// CHECK-NEXT: call void @__kmpc_free_shared(ptr [[B]], i64 4)
// CHECK-NEXT: call void @__kmpc_free_shared(ptr [[A]], i64 4)
// CHECK-NEXT: call void @__kmpc_target_deinit()
// CHECK-NEXT: ret void
// CHECK: worker.exit:
// CHECK-NEXT: ret void
//
//
// CHECK-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z7test_dsv_l14_omp_outlined
// CHECK-SAME: (ptr noalias noundef [[DOTGLOBAL_TID_:%.*]], ptr noalias noundef [[DOTBOUND_TID_:%.*]], ptr noundef nonnull align 4 dereferenceable(4) [[A:%.*]]) #[[ATTR2:[0-9]+]] {
// CHECK-NEXT: entry:
// CHECK-NEXT: [[DOTGLOBAL_TID__ADDR:%.*]] = alloca ptr, align 8
// CHECK-NEXT: [[DOTBOUND_TID__ADDR:%.*]] = alloca ptr, align 8
// CHECK-NEXT: [[A_ADDR:%.*]] = alloca ptr, align 8
// CHECK-NEXT: store ptr [[DOTGLOBAL_TID_]], ptr [[DOTGLOBAL_TID__ADDR]], align 8
// CHECK-NEXT: store ptr [[DOTBOUND_TID_]], ptr [[DOTBOUND_TID__ADDR]], align 8
// CHECK-NEXT: store ptr [[A]], ptr [[A_ADDR]], align 8
// CHECK-NEXT: [[TMP0:%.*]] = load ptr, ptr [[A_ADDR]], align 8
// CHECK-NEXT: store i32 1000, ptr [[TMP0]], align 4
// CHECK-NEXT: ret void
//
//
// CHECK-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z7test_dsv_l14_omp_outlined_wrapper
// CHECK-SAME: (i16 noundef zeroext [[TMP0:%.*]], i32 noundef [[TMP1:%.*]]) #[[ATTR3:[0-9]+]] {
// CHECK-NEXT: entry:
// CHECK-NEXT: [[DOTADDR:%.*]] = alloca i16, align 2
// CHECK-NEXT: [[DOTADDR1:%.*]] = alloca i32, align 4
// CHECK-NEXT: [[DOTZERO_ADDR:%.*]] = alloca i32, align 4
// CHECK-NEXT: [[GLOBAL_ARGS:%.*]] = alloca ptr, align 8
// CHECK-NEXT: store i16 [[TMP0]], ptr [[DOTADDR]], align 2
// CHECK-NEXT: store i32 [[TMP1]], ptr [[DOTADDR1]], align 4
// CHECK-NEXT: store i32 0, ptr [[DOTZERO_ADDR]], align 4
// CHECK-NEXT: call void @__kmpc_get_shared_variables(ptr [[GLOBAL_ARGS]])
// CHECK-NEXT: [[TMP2:%.*]] = load ptr, ptr [[GLOBAL_ARGS]], align 8
// CHECK-NEXT: [[TMP3:%.*]] = getelementptr inbounds ptr, ptr [[TMP2]], i64 0
// CHECK-NEXT: [[TMP4:%.*]] = load ptr, ptr [[TMP3]], align 8
// CHECK-NEXT: call void @{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z7test_dsv_l14_omp_outlined(ptr [[DOTADDR1]], ptr [[DOTZERO_ADDR]], ptr [[TMP4]]) #[[ATTR4:[0-9]+]]
// CHECK-NEXT: ret void
//
//
// CHECK-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z7test_dsv_l14_omp_outlined1
// CHECK-SAME: (ptr noalias noundef [[DOTGLOBAL_TID_:%.*]], ptr noalias noundef [[DOTBOUND_TID_:%.*]], ptr noundef nonnull align 4 dereferenceable(4) [[B:%.*]], ptr noundef nonnull align 4 dereferenceable(4) [[A:%.*]]) #[[ATTR2]] {
// CHECK-NEXT: entry:
// CHECK-NEXT: [[DOTGLOBAL_TID__ADDR:%.*]] = alloca ptr, align 8
// CHECK-NEXT: [[DOTBOUND_TID__ADDR:%.*]] = alloca ptr, align 8
// CHECK-NEXT: [[B_ADDR:%.*]] = alloca ptr, align 8
// CHECK-NEXT: [[A_ADDR:%.*]] = alloca ptr, align 8
// CHECK-NEXT: [[C:%.*]] = alloca i32, align 4
// CHECK-NEXT: [[C1:%.*]] = alloca ptr, align 8
// CHECK-NEXT: store ptr [[DOTGLOBAL_TID_]], ptr [[DOTGLOBAL_TID__ADDR]], align 8
// CHECK-NEXT: store ptr [[DOTBOUND_TID_]], ptr [[DOTBOUND_TID__ADDR]], align 8
// CHECK-NEXT: store ptr [[B]], ptr [[B_ADDR]], align 8
// CHECK-NEXT: store ptr [[A]], ptr [[A_ADDR]], align 8
// CHECK-NEXT: [[TMP0:%.*]] = load ptr, ptr [[B_ADDR]], align 8
// CHECK-NEXT: [[TMP1:%.*]] = load ptr, ptr [[A_ADDR]], align 8
// CHECK-NEXT: store ptr [[C]], ptr [[C1]], align 8
// CHECK-NEXT: [[TMP2:%.*]] = load i32, ptr [[TMP1]], align 4
// CHECK-NEXT: [[ADD:%.*]] = add nsw i32 [[TMP2]], 10000
// CHECK-NEXT: store i32 [[ADD]], ptr [[TMP0]], align 4
// CHECK-NEXT: ret void
//
//
// CHECK-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z7test_dsv_l14_omp_outlined1_wrapper
// CHECK-SAME: (i16 noundef zeroext [[TMP0:%.*]], i32 noundef [[TMP1:%.*]]) #[[ATTR3]] {
// CHECK-NEXT: entry:
// CHECK-NEXT: [[DOTADDR:%.*]] = alloca i16, align 2
// CHECK-NEXT: [[DOTADDR1:%.*]] = alloca i32, align 4
// CHECK-NEXT: [[DOTZERO_ADDR:%.*]] = alloca i32, align 4
// CHECK-NEXT: [[GLOBAL_ARGS:%.*]] = alloca ptr, align 8
// CHECK-NEXT: store i16 [[TMP0]], ptr [[DOTADDR]], align 2
// CHECK-NEXT: store i32 [[TMP1]], ptr [[DOTADDR1]], align 4
// CHECK-NEXT: store i32 0, ptr [[DOTZERO_ADDR]], align 4
// CHECK-NEXT: call void @__kmpc_get_shared_variables(ptr [[GLOBAL_ARGS]])
// CHECK-NEXT: [[TMP2:%.*]] = load ptr, ptr [[GLOBAL_ARGS]], align 8
// CHECK-NEXT: [[TMP3:%.*]] = getelementptr inbounds ptr, ptr [[TMP2]], i64 0
// CHECK-NEXT: [[TMP4:%.*]] = load ptr, ptr [[TMP3]], align 8
// CHECK-NEXT: [[TMP5:%.*]] = getelementptr inbounds ptr, ptr [[TMP2]], i64 1
// CHECK-NEXT: [[TMP6:%.*]] = load ptr, ptr [[TMP5]], align 8
// CHECK-NEXT: call void @{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z7test_dsv_l14_omp_outlined1(ptr [[DOTADDR1]], ptr [[DOTZERO_ADDR]], ptr [[TMP4]], ptr [[TMP6]]) #[[ATTR4]]
// CHECK-NEXT: ret void
//
Reference in New Issue View Git Blame Copy Permalink