libgomp: cuda.h and omp_target_memcpy_rect cleanup

Fixes for commit r14-2792-g25072a477a56a727b369bf9b20f4d18198ff5894
"OpenMP: Call cuMemcpy2D/cuMemcpy3D for nvptx for omp_target_memcpy_rect",
namely:

In that commit, the code was changed to handle shared-memory devices;
however, as pointed out, omp_target_memcpy_check already set the pointer
to NULL in that case.  Hence, this commit reverts to the prior version.

In cuda.h, it adds cuMemcpyPeer{,Async} for symmetry for cuMemcpy3DPeer
(all currently unused) and in three structs, fixes reserved-member names
and remove a bogus 'const' in three structs.

And it changes a DLSYM to DLSYM_OPT as not all plugins support the new
functions, yet.

include/ChangeLog:

	* cuda/cuda.h (CUDA_MEMCPY2D, CUDA_MEMCPY3D, CUDA_MEMCPY3D_PEER):
	Remove bogus 'const' from 'const void *dst' and fix reserved-name
	name in those structs.
	(cuMemcpyPeer, cuMemcpyPeerAsync): Add.

libgomp/ChangeLog:

	* target.c (omp_target_memcpy_rect_worker): Undo dim=1 change for
	GOMP_OFFLOAD_CAP_SHARED_MEM.
	(omp_target_memcpy_rect_copy): Likewise for lock condition.
	(gomp_load_plugin_for_device): Use DLSYM_OPT not DLSYM for
	memcpy3d/memcpy2d.
	* plugin/plugin-nvptx.c (GOMP_OFFLOAD_memcpy2d,
	GOMP_OFFLOAD_memcpy3d): Use memset 0 to nullify reserved and
	unused src/dst fields for that mem type; remove '{src,dst}LOD = 0'.

1 files changed, 7 insertions, 5 deletions

diff --git a/include/cuda/cuda.h b/include/cuda/cuda.h
index 09c3c2b..94fc64a 100644
--- a/include/cuda/cuda.h
+++ b/include/cuda/cuda.h
@@ -147,7 +147,7 @@ typedef struct {
 
   size_t dstXInBytes, dstY;
   CUmemorytype dstMemoryType;
-  const void *dstHost;
+  void *dstHost;
   CUdeviceptr dstDevice;
   CUarray dstArray;
   size_t dstPitch;
@@ -162,16 +162,16 @@ typedef struct {
   const void *srcHost;
   CUdeviceptr srcDevice;
   CUarray srcArray;
-  void *dummy;
+  void *reserved0;
   size_t srcPitch, srcHeight;
 
   size_t dstXInBytes, dstY, dstZ;
   size_t dstLOD;
   CUmemorytype dstMemoryType;
-  const void *dstHost;
+  void *dstHost;
   CUdeviceptr dstDevice;
   CUarray dstArray;
-  void *dummy2;
+  void *reserved1;
   size_t dstPitch, dstHeight;
 
   size_t WidthInBytes, Height, Depth;
@@ -190,7 +190,7 @@ typedef struct {
   size_t dstXInBytes, dstY, dstZ;
   size_t dstLOD;
   CUmemorytype dstMemoryType;
-  const void *dstHost;
+  void *dstHost;
   CUdeviceptr dstDevice;
   CUarray dstArray;
   CUcontext dstContext;
@@ -246,6 +246,8 @@ CUresult cuMemAlloc (CUdeviceptr *, size_t);
 CUresult cuMemAllocHost (void **, size_t);
 CUresult cuMemHostAlloc (void **, size_t, unsigned int);
 CUresult cuMemcpy (CUdeviceptr, CUdeviceptr, size_t);
+CUresult cuMemcpyPeer (CUdeviceptr, CUcontext, CUdeviceptr, CUcontext, size_t);
+CUresult cuMemcpyPeerAsync (CUdeviceptr, CUcontext, CUdeviceptr, CUcontext, size_t, CUstream);
 #define cuMemcpyDtoDAsync cuMemcpyDtoDAsync_v2
 CUresult cuMemcpyDtoDAsync (CUdeviceptr, CUdeviceptr, size_t, CUstream);
 #define cuMemcpyDtoH cuMemcpyDtoH_v2