diff options
| -rw-r--r-- | libgomp/ChangeLog | 7 | ||||
| -rw-r--r-- | libgomp/plugin/plugin-nvptx.c | 7 |
2 files changed, 12 insertions, 2 deletions
diff --git a/libgomp/ChangeLog b/libgomp/ChangeLog index f674b5e..c425f68 100644 --- a/libgomp/ChangeLog +++ b/libgomp/ChangeLog @@ -1,5 +1,12 @@ 2018-08-08 Tom de Vries <tdevries@suse.de> + * plugin/plugin-nvptx.c + (CU_DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR): Define. + (nvptx_open_device): Use + CU_DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR. + +2018-08-08 Tom de Vries <tdevries@suse.de> + * plugin/plugin-nvptx.c (cuda_error): Move declaration of cuGetErrorString ... (cuGetErrorString): ... here. Guard with CUDA_VERSION < 6000. diff --git a/libgomp/plugin/plugin-nvptx.c b/libgomp/plugin/plugin-nvptx.c index e2ea542..589d659 100644 --- a/libgomp/plugin/plugin-nvptx.c +++ b/libgomp/plugin/plugin-nvptx.c @@ -51,6 +51,7 @@ #if CUDA_VERSION < 6000 extern CUresult cuGetErrorString (CUresult, const char **); +#define CU_DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR 82 #endif #define DO_PRAGMA(x) _Pragma (#x) @@ -741,9 +742,11 @@ nvptx_open_device (int n) &pi, CU_DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK, dev); ptx_dev->regs_per_block = pi; - /* CU_DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR = 82 is defined only + /* CU_DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR is defined only in CUDA 6.0 and newer. */ - r = CUDA_CALL_NOCHECK (cuDeviceGetAttribute, &pi, 82, dev); + r = CUDA_CALL_NOCHECK (cuDeviceGetAttribute, &pi, + CU_DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR, + dev); /* Fallback: use limit of registers per block, which is usually equal. */ if (r == CUDA_ERROR_INVALID_VALUE) pi = ptx_dev->regs_per_block; |