[OPENMP][NVPTX]Add __kmpc_syncwarp(int32_t) function.
Summary:
Added function void __kmpc_syncwarp(int32_t) to expose it to the
compiler. It is required to fix the problem with the critical regions in
Cuda9.0+. We cannot use barrier in the critical region, but still need
to reconverge the threads in the warp after. This function allows to do
this.
Reviewers: grokos, jdoerfert
Subscribers: guansong, openmp-commits, kkwli0, caomhin
Tags: #openmp
Differential Revision: https://reviews.llvm.org/D66672
git-svn-id: https://llvm.org/svn/llvm-project/openmp/trunk@369933 91177308-0d34-0410-b5e6-96231b3b80d8
diff --git a/libomptarget/deviceRTLs/nvptx/src/interface.h b/libomptarget/deviceRTLs/nvptx/src/interface.h
index b2a13a4..ab57715 100644
--- a/libomptarget/deviceRTLs/nvptx/src/interface.h
+++ b/libomptarget/deviceRTLs/nvptx/src/interface.h
@@ -423,6 +423,8 @@
// vote
EXTERN int32_t __kmpc_warp_active_thread_mask();
+// syncwarp
+EXTERN void __kmpc_syncwarp(int32_t);
// tasks
EXTERN kmp_TaskDescr *__kmpc_omp_task_alloc(kmp_Ident *loc,
diff --git a/libomptarget/deviceRTLs/nvptx/src/sync.cu b/libomptarget/deviceRTLs/nvptx/src/sync.cu
index 4607d6a..fcfe272 100644
--- a/libomptarget/deviceRTLs/nvptx/src/sync.cu
+++ b/libomptarget/deviceRTLs/nvptx/src/sync.cu
@@ -11,6 +11,7 @@
//===----------------------------------------------------------------------===//
#include "omptarget-nvptx.h"
+#include "target_impl.h"
////////////////////////////////////////////////////////////////////////////////
// KMP Ordered calls
@@ -144,3 +145,12 @@
PRINT0(LD_IO, "call __kmpc_warp_active_thread_mask\n");
return __ACTIVEMASK();
}
+
+////////////////////////////////////////////////////////////////////////////////
+// Syncwarp
+////////////////////////////////////////////////////////////////////////////////
+
+EXTERN void __kmpc_syncwarp(int32_t Mask) {
+ PRINT0(LD_IO, "call __kmpc_syncwarp\n");
+ __kmpc_impl_syncwarp(Mask);
+}
diff --git a/libomptarget/deviceRTLs/nvptx/src/target_impl.h b/libomptarget/deviceRTLs/nvptx/src/target_impl.h
index 6104695..a1b4c20 100644
--- a/libomptarget/deviceRTLs/nvptx/src/target_impl.h
+++ b/libomptarget/deviceRTLs/nvptx/src/target_impl.h
@@ -38,4 +38,6 @@
INLINE int __kmpc_impl_popc(uint32_t x) { return __popc(x); }
+INLINE void __kmpc_impl_syncwarp(int32_t Mask) { __SYNCWARP(Mask); }
+
#endif
