forked from OSchip/llvm-project
[OPENMP][NVPTX]Fix parallel level counter in non-SPMD mode.
Summary: In non-SPMD mode we may end up with the divergent threads when trying to increment/decrement parallel level counter. It may lead to incorrect calculations of the parallel level and wrong results when threads are divergent. We need to reconverge the threads before trying to modify the parallel level counter. Reviewers: grokos, jdoerfert Subscribers: guansong, openmp-commits, caomhin, kkwli0 Tags: #openmp Differential Revision: https://reviews.llvm.org/D66802 llvm-svn: 370803
This commit is contained in:
parent
b187eef616
commit
4812941776
|
@ -311,7 +311,16 @@ EXTERN bool __kmpc_kernel_parallel(void **WorkFn,
|
||||||
(int)newTaskDescr->ThreadId(), (int)nThreads);
|
(int)newTaskDescr->ThreadId(), (int)nThreads);
|
||||||
|
|
||||||
isActive = true;
|
isActive = true;
|
||||||
IncParallelLevel(threadsInTeam != 1);
|
// Reconverge the threads at the end of the parallel region to correctly
|
||||||
|
// handle parallel levels.
|
||||||
|
// In Cuda9+ in non-SPMD mode we have either 1 worker thread or the whole
|
||||||
|
// warp. If only 1 thread is active, not need to reconverge the threads.
|
||||||
|
// If we have the whole warp, reconverge all the threads in the warp before
|
||||||
|
// actually trying to change the parallel level. Otherwise, parallel level
|
||||||
|
// can be changed incorrectly because of threads divergence.
|
||||||
|
bool IsActiveParallelRegion = threadsInTeam != 1;
|
||||||
|
IncParallelLevel(IsActiveParallelRegion,
|
||||||
|
IsActiveParallelRegion ? 0xFFFFFFFF : 1u);
|
||||||
}
|
}
|
||||||
|
|
||||||
return isActive;
|
return isActive;
|
||||||
|
@ -329,7 +338,16 @@ EXTERN void __kmpc_kernel_end_parallel() {
|
||||||
omptarget_nvptx_threadPrivateContext->SetTopLevelTaskDescr(
|
omptarget_nvptx_threadPrivateContext->SetTopLevelTaskDescr(
|
||||||
threadId, currTaskDescr->GetPrevTaskDescr());
|
threadId, currTaskDescr->GetPrevTaskDescr());
|
||||||
|
|
||||||
DecParallelLevel(threadsInTeam != 1);
|
// Reconverge the threads at the end of the parallel region to correctly
|
||||||
|
// handle parallel levels.
|
||||||
|
// In Cuda9+ in non-SPMD mode we have either 1 worker thread or the whole
|
||||||
|
// warp. If only 1 thread is active, not need to reconverge the threads.
|
||||||
|
// If we have the whole warp, reconverge all the threads in the warp before
|
||||||
|
// actually trying to change the parallel level. Otherwise, parallel level can
|
||||||
|
// be changed incorrectly because of threads divergence.
|
||||||
|
bool IsActiveParallelRegion = threadsInTeam != 1;
|
||||||
|
DecParallelLevel(IsActiveParallelRegion,
|
||||||
|
IsActiveParallelRegion ? 0xFFFFFFFF : 1u);
|
||||||
}
|
}
|
||||||
|
|
||||||
////////////////////////////////////////////////////////////////////////////////
|
////////////////////////////////////////////////////////////////////////////////
|
||||||
|
@ -339,7 +357,7 @@ EXTERN void __kmpc_kernel_end_parallel() {
|
||||||
EXTERN void __kmpc_serialized_parallel(kmp_Ident *loc, uint32_t global_tid) {
|
EXTERN void __kmpc_serialized_parallel(kmp_Ident *loc, uint32_t global_tid) {
|
||||||
PRINT0(LD_IO, "call to __kmpc_serialized_parallel\n");
|
PRINT0(LD_IO, "call to __kmpc_serialized_parallel\n");
|
||||||
|
|
||||||
IncParallelLevel(/*ActiveParallel=*/false);
|
IncParallelLevel(/*ActiveParallel=*/false, __kmpc_impl_activemask());
|
||||||
|
|
||||||
if (checkRuntimeUninitialized(loc)) {
|
if (checkRuntimeUninitialized(loc)) {
|
||||||
ASSERT0(LT_FUSSY, checkSPMDMode(loc),
|
ASSERT0(LT_FUSSY, checkSPMDMode(loc),
|
||||||
|
@ -378,7 +396,7 @@ EXTERN void __kmpc_end_serialized_parallel(kmp_Ident *loc,
|
||||||
uint32_t global_tid) {
|
uint32_t global_tid) {
|
||||||
PRINT0(LD_IO, "call to __kmpc_end_serialized_parallel\n");
|
PRINT0(LD_IO, "call to __kmpc_end_serialized_parallel\n");
|
||||||
|
|
||||||
DecParallelLevel(/*ActiveParallel=*/false);
|
DecParallelLevel(/*ActiveParallel=*/false, __kmpc_impl_activemask());
|
||||||
|
|
||||||
if (checkRuntimeUninitialized(loc)) {
|
if (checkRuntimeUninitialized(loc)) {
|
||||||
ASSERT0(LT_FUSSY, checkSPMDMode(loc),
|
ASSERT0(LT_FUSSY, checkSPMDMode(loc),
|
||||||
|
|
|
@ -10,6 +10,7 @@
|
||||||
//
|
//
|
||||||
//===----------------------------------------------------------------------===//
|
//===----------------------------------------------------------------------===//
|
||||||
|
|
||||||
|
#include "target_impl.h"
|
||||||
////////////////////////////////////////////////////////////////////////////////
|
////////////////////////////////////////////////////////////////////////////////
|
||||||
// Execution Parameters
|
// Execution Parameters
|
||||||
////////////////////////////////////////////////////////////////////////////////
|
////////////////////////////////////////////////////////////////////////////////
|
||||||
|
@ -65,8 +66,8 @@ INLINE int GetNumberOfProcsInDevice(bool isSPMDExecutionMode);
|
||||||
INLINE int IsTeamMaster(int ompThreadId);
|
INLINE int IsTeamMaster(int ompThreadId);
|
||||||
|
|
||||||
// Parallel level
|
// Parallel level
|
||||||
INLINE void IncParallelLevel(bool ActiveParallel);
|
INLINE void IncParallelLevel(bool ActiveParallel, __kmpc_impl_lanemask_t Mask);
|
||||||
INLINE void DecParallelLevel(bool ActiveParallel);
|
INLINE void DecParallelLevel(bool ActiveParallel, __kmpc_impl_lanemask_t Mask);
|
||||||
|
|
||||||
////////////////////////////////////////////////////////////////////////////////
|
////////////////////////////////////////////////////////////////////////////////
|
||||||
// Memory
|
// Memory
|
||||||
|
|
|
@ -203,30 +203,28 @@ INLINE int IsTeamMaster(int ompThreadId) { return (ompThreadId == 0); }
|
||||||
////////////////////////////////////////////////////////////////////////////////
|
////////////////////////////////////////////////////////////////////////////////
|
||||||
// Parallel level
|
// Parallel level
|
||||||
|
|
||||||
INLINE void IncParallelLevel(bool ActiveParallel) {
|
INLINE void IncParallelLevel(bool ActiveParallel, __kmpc_impl_lanemask_t Mask) {
|
||||||
__kmpc_impl_lanemask_t Active = __kmpc_impl_activemask();
|
__kmpc_impl_syncwarp(Mask);
|
||||||
__kmpc_impl_syncwarp(Active);
|
|
||||||
__kmpc_impl_lanemask_t LaneMaskLt = __kmpc_impl_lanemask_lt();
|
__kmpc_impl_lanemask_t LaneMaskLt = __kmpc_impl_lanemask_lt();
|
||||||
unsigned Rank = __kmpc_impl_popc(Active & LaneMaskLt);
|
unsigned Rank = __kmpc_impl_popc(Mask & LaneMaskLt);
|
||||||
if (Rank == 0) {
|
if (Rank == 0) {
|
||||||
parallelLevel[GetWarpId()] +=
|
parallelLevel[GetWarpId()] +=
|
||||||
(1 + (ActiveParallel ? OMP_ACTIVE_PARALLEL_LEVEL : 0));
|
(1 + (ActiveParallel ? OMP_ACTIVE_PARALLEL_LEVEL : 0));
|
||||||
__threadfence();
|
__threadfence();
|
||||||
}
|
}
|
||||||
__kmpc_impl_syncwarp(Active);
|
__kmpc_impl_syncwarp(Mask);
|
||||||
}
|
}
|
||||||
|
|
||||||
INLINE void DecParallelLevel(bool ActiveParallel) {
|
INLINE void DecParallelLevel(bool ActiveParallel, __kmpc_impl_lanemask_t Mask) {
|
||||||
__kmpc_impl_lanemask_t Active = __kmpc_impl_activemask();
|
__kmpc_impl_syncwarp(Mask);
|
||||||
__kmpc_impl_syncwarp(Active);
|
|
||||||
__kmpc_impl_lanemask_t LaneMaskLt = __kmpc_impl_lanemask_lt();
|
__kmpc_impl_lanemask_t LaneMaskLt = __kmpc_impl_lanemask_lt();
|
||||||
unsigned Rank = __kmpc_impl_popc(Active & LaneMaskLt);
|
unsigned Rank = __kmpc_impl_popc(Mask & LaneMaskLt);
|
||||||
if (Rank == 0) {
|
if (Rank == 0) {
|
||||||
parallelLevel[GetWarpId()] -=
|
parallelLevel[GetWarpId()] -=
|
||||||
(1 + (ActiveParallel ? OMP_ACTIVE_PARALLEL_LEVEL : 0));
|
(1 + (ActiveParallel ? OMP_ACTIVE_PARALLEL_LEVEL : 0));
|
||||||
__threadfence();
|
__threadfence();
|
||||||
}
|
}
|
||||||
__kmpc_impl_syncwarp(Active);
|
__kmpc_impl_syncwarp(Mask);
|
||||||
}
|
}
|
||||||
|
|
||||||
////////////////////////////////////////////////////////////////////////////////
|
////////////////////////////////////////////////////////////////////////////////
|
||||||
|
|
|
@ -135,5 +135,17 @@ int main(int argc, char *argv[]) {
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
|
||||||
|
// Check for paraller level in non-SPMD kernels.
|
||||||
|
level = 0;
|
||||||
|
#pragma omp target teams distribute num_teams(1) thread_limit(32) reduction(+:level)
|
||||||
|
for (int i=0; i<5032; i+=32) {
|
||||||
|
int ub = (i+32 > 5032) ? 5032 : i+32;
|
||||||
|
#pragma omp parallel for schedule(dynamic)
|
||||||
|
for (int j=i ; j < ub; j++) ;
|
||||||
|
level += omp_get_level();
|
||||||
|
}
|
||||||
|
// CHECK: Integral level = 0.
|
||||||
|
printf("Integral level = %d.\n", level);
|
||||||
|
|
||||||
return 0;
|
return 0;
|
||||||
}
|
}
|
||||||
|
|
Loading…
Reference in New Issue