Commit 69b09a58 by Tom de Vries Committed by Tom de Vries

[nvptx] Move PTX_CTA_SIZE up

Move the defition of PTX_CTA_SIZE up in nvptx.c.

2019-01-11  Tom de Vries  <tdevries@suse.de>

	* config/nvptx/nvptx.c (PTX_CTA_SIZE): Move up.

From-SVN: r267837
parent 9390f916
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> 2019-01-11 Jan Beulich <jbeulich@suse.com>
* config/i386/i386.md (rex64suffix): Add L suffix for SI. * config/i386/i386.md (rex64suffix): Add L suffix for SI.
......
...@@ -82,17 +82,18 @@ ...@@ -82,17 +82,18 @@
#define WORKAROUND_PTXJIT_BUG_2 1 #define WORKAROUND_PTXJIT_BUG_2 1
#define WORKAROUND_PTXJIT_BUG_3 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_WARP_SIZE 32
#define PTX_DEFAULT_VECTOR_LENGTH PTX_WARP_SIZE #define PTX_DEFAULT_VECTOR_LENGTH PTX_WARP_SIZE
#define PTX_MAX_VECTOR_LENGTH PTX_WARP_SIZE #define PTX_MAX_VECTOR_LENGTH PTX_WARP_SIZE
#define PTX_WORKER_LENGTH 32 #define PTX_WORKER_LENGTH 32
#define PTX_DEFAULT_RUNTIME_DIM 0 /* Defer to runtime. */ #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. */ /* The various PTX memory areas an object might reside in. */
enum nvptx_data_area enum nvptx_data_area
{ {
......
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment