maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity
llvm-project/clang/test/OpenMP/nvptx_parallel_for_codegen.cpp

Ignoring revisions in .git-blame-ignore-revs. Click here to bypass and see the normal blame view.

135 lines
5.5 KiB
C++
Raw Normal View History

[NFC][OpenMP] Add new test for parallel for code generation. Summary: This is a simple test of the parallel for code generation. It will be used to showcase the change introduced by patch D53443. Reviewers: ABataev, caomhin Reviewed By: ABataev Subscribers: guansong, cfe-commits Differential Revision: https://reviews.llvm.org/D53772 llvm-svn: 345417
2018-10-27 02:59:52 +08:00
// Test target codegen - host bc file has to be created first.
// 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
[OPENMP][NVPTX]Mark more functions as always_inline for better performance. Internally generated functions must be marked as always_inlines in most cases. Patch marks some extra reduction function + outlined parallel functions as always_inline for better performance, but only if the optimization is requested. llvm-svn: 361269
2019-05-21 23:11:58 +08:00
// RUN: %clang_cc1 -verify -fopenmp -x c++ -triple nvptx64-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-ppc-host.bc -o - -disable-llvm-optzns | FileCheck %s --check-prefix CHECK --check-prefix CHECK-64
[NFC][OpenMP] Add new test for parallel for code generation. Summary: This is a simple test of the parallel for code generation. It will be used to showcase the change introduced by patch D53443. Reviewers: ABataev, caomhin Reviewed By: ABataev Subscribers: guansong, cfe-commits Differential Revision: https://reviews.llvm.org/D53772 llvm-svn: 345417
2018-10-27 02:59:52 +08:00
// expected-no-diagnostics
#ifndef HEADER
#define HEADER
template<typename tx>
tx ftemplate(int n) {
tx b[10];
#pragma omp target
{
tx d = n;
#pragma omp parallel for
for(int i=0; i<10; i++) {
b[i] += d;
}
b[3] += 1;
}
return b[3];
}
int bar(int n){
int a = 0;
a += ftemplate<int>(n);
return a;
}
[OPENMP][NVPTX]Emit shared memory buffer for reduction as 128 bytes buffer. Seems to me, nvlink has a bug with the proper support of the weakly linked symbols. It does not allow to define several shared memory buffer with the different sizes even with the weak linkage. Instead we always use 128 bytes buffer to prevent nvlink from the error message emission. llvm-svn: 349540
2018-12-19 05:01:42 +08:00
// CHECK: [[MEM_TY:%.+]] = type { [128 x i8] }
[OPENMP][NVPTX]Emit correct reduction code for teams/parallel reductions. Fixed previously committed code for the reduction support in teams/parallel constructs taking into account new design of the NVPTX support in the compiler. Teams reduction are not fully functional yet, it is going to be fixed in the following patches. llvm-svn: 347081
2018-11-17 03:38:21 +08:00
// CHECK-DAG: [[SHARED_GLOBAL_RD:@.+]] = common addrspace(3) global [[MEM_TY]] zeroinitializer
[OPENMP][NVPTX]Improve emission of the globalized variables for target/teams/distribute regions. Target/teams/distribute regions exist for all the time the kernel is executed. Thus, if the variable is declared in their context and then escape it, we can allocate global memory statically instead of allocating it dynamically. Patch captures all the globalized variables in target/teams/distribute contexts, merges them into the records, one per each target region. Those records are then joined into the union, one per compilation unit (to save the global memory). Those units are organized into 2 x dimensional arrays, where the first dimension is the number of blocks per SM and the second one is the number of SMs. Runtime functions manage this global memory space between the executing teams. llvm-svn: 345978
2018-11-02 22:54:07 +08:00
// CHECK-DAG: [[KERNEL_PTR:@.+]] = internal addrspace(3) global i8* null
// CHECK-DAG: [[KERNEL_SIZE:@.+]] = internal unnamed_addr constant i{{64|32}} 4
[OPENMP][NVPTX]Allow to use shared memory for the target|teams|distribute variables. If the total size of the variables, declared in target|teams|distribute regions, is less than the maximal size of shared memory available, the buffer is allocated in the shared memory. llvm-svn: 346507
2018-11-10 00:18:04 +08:00
// CHECK-DAG: [[KERNEL_SHARED:@.+]] = internal unnamed_addr constant i16 1
[OPENMP][NVPTX]Improve emission of the globalized variables for target/teams/distribute regions. Target/teams/distribute regions exist for all the time the kernel is executed. Thus, if the variable is declared in their context and then escape it, we can allocate global memory statically instead of allocating it dynamically. Patch captures all the globalized variables in target/teams/distribute contexts, merges them into the records, one per each target region. Those records are then joined into the union, one per compilation unit (to save the global memory). Those units are organized into 2 x dimensional arrays, where the first dimension is the number of blocks per SM and the second one is the number of SMs. Runtime functions manage this global memory space between the executing teams. llvm-svn: 345978
2018-11-02 22:54:07 +08:00
[NFC][OpenMP] Add new test for parallel for code generation. Summary: This is a simple test of the parallel for code generation. It will be used to showcase the change introduced by patch D53443. Reviewers: ABataev, caomhin Reviewed By: ABataev Subscribers: guansong, cfe-commits Differential Revision: https://reviews.llvm.org/D53772 llvm-svn: 345417
2018-10-27 02:59:52 +08:00
// CHECK-LABEL: define {{.*}}void {{@__omp_offloading_.+template.+l12}}_worker()
[OPENMP][NVPTX]Use __kmpc_barrier_simple_spmd(nullptr, 0) instead of nvvm_barrier0. Use runtime functions instead of the direct call to the nvvm intrinsics. It allows to prevent some dangerous LLVM optimizations, that breaks the code for the NVPTX target. llvm-svn: 350328
2019-01-04 00:25:35 +08:00
// CHECK: call void @__kmpc_barrier_simple_spmd(%struct.ident_t* null, i32 0)
[NFC][OpenMP] Add new test for parallel for code generation. Summary: This is a simple test of the parallel for code generation. It will be used to showcase the change introduced by patch D53443. Reviewers: ABataev, caomhin Reviewed By: ABataev Subscribers: guansong, cfe-commits Differential Revision: https://reviews.llvm.org/D53772 llvm-svn: 345417
2018-10-27 02:59:52 +08:00
// CHECK: call i1 @__kmpc_kernel_parallel(
// CHECK: call void @__omp_outlined___wrapper(
// CHECK: define weak void @__omp_offloading_{{.*}}l12(
// CHECK: call void @__omp_offloading_{{.*}}l12_worker()
// CHECK: call void @__kmpc_kernel_init(
// CHECK: call void @__kmpc_data_sharing_init_stack()
[OPENMP][NVPTX]Allow to use shared memory for the target|teams|distribute variables. If the total size of the variables, declared in target|teams|distribute regions, is less than the maximal size of shared memory available, the buffer is allocated in the shared memory. llvm-svn: 346507
2018-11-10 00:18:04 +08:00
// CHECK: [[IS_SHARED:%.+]] = load i16, i16* [[KERNEL_SHARED]],
[OPENMP][NVPTX]Improve emission of the globalized variables for target/teams/distribute regions. Target/teams/distribute regions exist for all the time the kernel is executed. Thus, if the variable is declared in their context and then escape it, we can allocate global memory statically instead of allocating it dynamically. Patch captures all the globalized variables in target/teams/distribute contexts, merges them into the records, one per each target region. Those records are then joined into the union, one per compilation unit (to save the global memory). Those units are organized into 2 x dimensional arrays, where the first dimension is the number of blocks per SM and the second one is the number of SMs. Runtime functions manage this global memory space between the executing teams. llvm-svn: 345978
2018-11-02 22:54:07 +08:00
// CHECK: [[SIZE:%.+]] = load i{{64|32}}, i{{64|32}}* [[KERNEL_SIZE]],
[OPENMP][NVPTX]Use new functions from the runtime library. Updated codegen to use the new functions from the runtime library. llvm-svn: 350415
2019-01-05 01:25:09 +08:00
// CHECK: call void @__kmpc_get_team_static_memory(i16 0, i8* addrspacecast (i8 addrspace(3)* getelementptr inbounds ([[MEM_TY]], [[MEM_TY]] addrspace(3)* [[SHARED_GLOBAL_RD]], i32 0, i32 0, i32 0) to i8*), i64 %7, i16 %6, i8** addrspacecast (i8* addrspace(3)* [[KERNEL_PTR]] to i8**))
[OPENMP][NVPTX]Improve emission of the globalized variables for target/teams/distribute regions. Target/teams/distribute regions exist for all the time the kernel is executed. Thus, if the variable is declared in their context and then escape it, we can allocate global memory statically instead of allocating it dynamically. Patch captures all the globalized variables in target/teams/distribute contexts, merges them into the records, one per each target region. Those records are then joined into the union, one per compilation unit (to save the global memory). Those units are organized into 2 x dimensional arrays, where the first dimension is the number of blocks per SM and the second one is the number of SMs. Runtime functions manage this global memory space between the executing teams. llvm-svn: 345978
2018-11-02 22:54:07 +08:00
// CHECK: [[KERNEL_RD:%.+]] = load i8*, i8* addrspace(3)* [[KERNEL_PTR]],
// CHECK: [[STACK:%.+]] = getelementptr inbounds i8, i8* [[KERNEL_RD]], i{{64|32}} 0
[NFC][OpenMP] Add new test for parallel for code generation. Summary: This is a simple test of the parallel for code generation. It will be used to showcase the change introduced by patch D53443. Reviewers: ABataev, caomhin Reviewed By: ABataev Subscribers: guansong, cfe-commits Differential Revision: https://reviews.llvm.org/D53772 llvm-svn: 345417
2018-10-27 02:59:52 +08:00
// CHECK: call void @__kmpc_kernel_prepare_parallel(
// CHECK: call void @__kmpc_begin_sharing_variables({{.*}}, i64 2)
[OPENMP][NVPTX]Use __kmpc_barrier_simple_spmd(nullptr, 0) instead of nvvm_barrier0. Use runtime functions instead of the direct call to the nvvm intrinsics. It allows to prevent some dangerous LLVM optimizations, that breaks the code for the NVPTX target. llvm-svn: 350328
2019-01-04 00:25:35 +08:00
// CHECK: call void @__kmpc_barrier_simple_spmd(%struct.ident_t* null, i32 0)
// CHECK: call void @__kmpc_barrier_simple_spmd(%struct.ident_t* null, i32 0)
[NFC][OpenMP] Add new test for parallel for code generation. Summary: This is a simple test of the parallel for code generation. It will be used to showcase the change introduced by patch D53443. Reviewers: ABataev, caomhin Reviewed By: ABataev Subscribers: guansong, cfe-commits Differential Revision: https://reviews.llvm.org/D53772 llvm-svn: 345417
2018-10-27 02:59:52 +08:00
// CHECK: call void @__kmpc_end_sharing_variables()
[OPENMP][NVPTX]Allow to use shared memory for the target|teams|distribute variables. If the total size of the variables, declared in target|teams|distribute regions, is less than the maximal size of shared memory available, the buffer is allocated in the shared memory. llvm-svn: 346507
2018-11-10 00:18:04 +08:00
// CHECK: [[IS_SHARED:%.+]] = load i16, i16* [[KERNEL_SHARED]],
[OPENMP][NVPTX]Use new functions from the runtime library. Updated codegen to use the new functions from the runtime library. llvm-svn: 350415
2019-01-05 01:25:09 +08:00
// CHECK: call void @__kmpc_restore_team_static_memory(i16 0, i16 [[IS_SHARED]])
[NFC][OpenMP] Add new test for parallel for code generation. Summary: This is a simple test of the parallel for code generation. It will be used to showcase the change introduced by patch D53443. Reviewers: ABataev, caomhin Reviewed By: ABataev Subscribers: guansong, cfe-commits Differential Revision: https://reviews.llvm.org/D53772 llvm-svn: 345417
2018-10-27 02:59:52 +08:00
// CHECK: call void @__kmpc_kernel_deinit(i16 1)
// CHECK: define internal void @__omp_outlined__(
// CHECK: alloca
// CHECK: alloca
// CHECK: alloca
// CHECK: alloca
// CHECK: [[OMP_IV:%.*]] = alloca i32
// CHECK: store i32 0, {{.*}} [[OMP_LB:%.+]],
// CHECK: store i32 9, {{.*}} [[OMP_UB:%.+]],
// CHECK: store i32 1, {{.*}} [[OMP_ST:%.+]],
[OpenMP][NVPTX] Enable default scheduling for parallel for in non-SPMD cases. Summary: This patch enables the choosing of the default schedule for parallel for loops even in non-SPMD cases. Reviewers: ABataev, caomhin Reviewed By: ABataev Subscribers: jholewinski, guansong, cfe-commits Differential Revision: https://reviews.llvm.org/D53443 llvm-svn: 345507
2018-10-29 23:23:23 +08:00
// CHECK: call void @__kmpc_for_static_init_4({{.*}} i32 33, {{.*}} [[OMP_LB]], {{.*}} [[OMP_UB]], {{.*}} [[OMP_ST]], i32 1, i32 1)
// CHECK: br label %[[OMP_DISPATCH_COND:.+]]
// CHECK: [[OMP_DISPATCH_COND]]
[NFC][OpenMP] Add new test for parallel for code generation. Summary: This is a simple test of the parallel for code generation. It will be used to showcase the change introduced by patch D53443. Reviewers: ABataev, caomhin Reviewed By: ABataev Subscribers: guansong, cfe-commits Differential Revision: https://reviews.llvm.org/D53772 llvm-svn: 345417
2018-10-27 02:59:52 +08:00
// CHECK: [[OMP_UB_1:%.+]] = load {{.*}} [[OMP_UB]]
// CHECK: [[COMP_1:%.+]] = icmp sgt {{.*}} [[OMP_UB_1]]
// CHECK: br i1 [[COMP_1]], label %[[COND_TRUE:.+]], label %[[COND_FALSE:.+]]
// CHECK: [[COND_TRUE]]
// CHECK: br label %[[COND_END:.+]]
// CHECK: [[COND_FALSE]]
// CHECK: [[OMP_UB_2:%.+]] = load {{.*}}* [[OMP_UB]]
// CHECK: br label %[[COND_END]]
// CHECK: [[COND_END]]
// CHECK: [[COND_RES:%.+]] = phi i32 [ 9, %[[COND_TRUE]] ], [ [[OMP_UB_2]], %[[COND_FALSE]] ]
// CHECK: store i32 [[COND_RES]], i32* [[OMP_UB]]
// CHECK: [[OMP_LB_1:%.+]] = load i32, i32* [[OMP_LB]]
// CHECK: store i32 [[OMP_LB_1]], i32* [[OMP_IV]]
[OpenMP][NVPTX] Enable default scheduling for parallel for in non-SPMD cases. Summary: This patch enables the choosing of the default schedule for parallel for loops even in non-SPMD cases. Reviewers: ABataev, caomhin Reviewed By: ABataev Subscribers: jholewinski, guansong, cfe-commits Differential Revision: https://reviews.llvm.org/D53443 llvm-svn: 345507
2018-10-29 23:23:23 +08:00
// CHECK: [[OMP_IV_1:%.+]] = load i32, i32* [[OMP_IV]]
// CHECK: [[OMP_UB_3:%.+]] = load i32, i32* [[OMP_UB]]
// CHECK: [[COMP_2:%.+]] = icmp sle i32 [[OMP_IV_1]], [[OMP_UB_3]]
// CHECK: br i1 [[COMP_2]], label %[[DISPATCH_BODY:.+]], label %[[DISPATCH_END:.+]]
// CHECK: [[DISPATCH_BODY]]
[NFC][OpenMP] Add new test for parallel for code generation. Summary: This is a simple test of the parallel for code generation. It will be used to showcase the change introduced by patch D53443. Reviewers: ABataev, caomhin Reviewed By: ABataev Subscribers: guansong, cfe-commits Differential Revision: https://reviews.llvm.org/D53772 llvm-svn: 345417
2018-10-27 02:59:52 +08:00
// CHECK: br label %[[OMP_INNER_FOR_COND:.+]]
// CHECK: [[OMP_INNER_FOR_COND]]
// CHECK: [[OMP_IV_2:%.+]] = load i32, i32* [[OMP_IV]]
// CHECK: [[OMP_UB_4:%.+]] = load i32, i32* [[OMP_UB]]
// CHECK: [[COMP_3:%.+]] = icmp sle i32 [[OMP_IV_2]], [[OMP_UB_4]]
// CHECK: br i1 [[COMP_3]], label %[[OMP_INNER_FOR_BODY:.+]], label %[[OMP_INNER_FOR_END:.+]]
// CHECK: [[OMP_INNER_FOR_BODY]]
// CHECK: br label %[[OMP_BODY_CONTINUE:.+]]
// CHECK: [[OMP_BODY_CONTINUE]]
// CHECK: br label %[[OMP_INNER_FOR_INC:.+]]
// CHECK: [[OMP_INNER_FOR_INC]]
// CHECK: [[OMP_IV_3:%.+]] = load i32, i32* [[OMP_IV]]
// CHECK: [[ADD_1:%.+]] = add nsw i32 [[OMP_IV_3]], 1
// CHECK: store i32 [[ADD_1]], i32* [[OMP_IV]]
// CHECK: br label %[[OMP_INNER_FOR_COND]]
[OpenMP][NVPTX] Enable default scheduling for parallel for in non-SPMD cases. Summary: This patch enables the choosing of the default schedule for parallel for loops even in non-SPMD cases. Reviewers: ABataev, caomhin Reviewed By: ABataev Subscribers: jholewinski, guansong, cfe-commits Differential Revision: https://reviews.llvm.org/D53443 llvm-svn: 345507
2018-10-29 23:23:23 +08:00
// CHECK: [[OMP_INNER_FOR_COND]]
// CHECK: br label %[[OMP_DISPATCH_INC:.+]]
// CHECK: [[OMP_DISPATCH_INC]]
// CHECK: [[OMP_LB_2:%.+]] = load i32, i32* [[OMP_LB]]
// CHECK: [[OMP_ST_1:%.+]] = load i32, i32* [[OMP_ST]]
// CHECK: [[ADD_2:%.+]] = add nsw i32 [[OMP_LB_2]], [[OMP_ST_1]]
// CHECK: store i32 [[ADD_2]], i32* [[OMP_LB]]
// CHECK: [[OMP_UB_5:%.+]] = load i32, i32* [[OMP_UB]]
// CHECK: [[OMP_ST_2:%.+]] = load i32, i32* [[OMP_ST]]
// CHECK: [[ADD_3:%.+]] = add nsw i32 [[OMP_UB_5]], [[OMP_ST_2]]
// CHECK: store i32 [[ADD_3]], i32* [[OMP_UB]]
// CHECK: [[DISPATCH_END]]
[NFC][OpenMP] Add new test for parallel for code generation. Summary: This is a simple test of the parallel for code generation. It will be used to showcase the change introduced by patch D53443. Reviewers: ABataev, caomhin Reviewed By: ABataev Subscribers: guansong, cfe-commits Differential Revision: https://reviews.llvm.org/D53772 llvm-svn: 345417
2018-10-27 02:59:52 +08:00
// CHECK: call void @__kmpc_for_static_fini(
// CHECK: ret void
#endif