diff options
| -rw-r--r-- | gcc/ChangeLog | 4 | ||||
| -rw-r--r-- | gcc/config/nvptx/nvptx.c | 11 |
2 files changed, 10 insertions, 5 deletions
diff --git a/gcc/ChangeLog b/gcc/ChangeLog index 0808254..5495b9a 100644 --- a/gcc/ChangeLog +++ b/gcc/ChangeLog @@ -1,3 +1,7 @@ +2019-01-11 Tom de Vries <tdevries@suse.de> + + * config/nvptx/nvptx.c (PTX_CTA_SIZE): Move up. + 2019-01-11 Jan Beulich <jbeulich@suse.com> * config/i386/i386.md (rex64suffix): Add L suffix for SI. diff --git a/gcc/config/nvptx/nvptx.c b/gcc/config/nvptx/nvptx.c index 7fdc285..643f5e8 100644 --- a/gcc/config/nvptx/nvptx.c +++ b/gcc/config/nvptx/nvptx.c @@ -82,17 +82,18 @@ #define WORKAROUND_PTXJIT_BUG_2 1 #define WORKAROUND_PTXJIT_BUG_3 1 +/* The PTX concept CTA (Concurrent Thread Array) maps on the CUDA concept thread + block, which has had a maximum number of threads of 1024 since CUDA version + 2.x. */ +#define PTX_CTA_SIZE 1024 + #define PTX_WARP_SIZE 32 + #define PTX_DEFAULT_VECTOR_LENGTH PTX_WARP_SIZE #define PTX_MAX_VECTOR_LENGTH PTX_WARP_SIZE #define PTX_WORKER_LENGTH 32 #define PTX_DEFAULT_RUNTIME_DIM 0 /* Defer to runtime. */ -/* The PTX concept CTA (Concurrent Thread Array) maps on the CUDA concept thread - block, which has had a maximum number of threads of 1024 since CUDA version - 2.x. */ -#define PTX_CTA_SIZE 1024 - /* The various PTX memory areas an object might reside in. */ enum nvptx_data_area { |