floraachy
/
OpenBLAS
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
OpenBLAS/lapack
History
Zhang Xianyi 5d3312142a Refs #221 #246. Fixed the overflowing stack bug in mutlithreading BLAS3. 
When NUM_THREADS(MAX_CPU_NUNBERS) is very large ,e.g. 256.

typedef struct {
  volatile BLASLONG working[MAX_CPU_NUMBER][CACHE_LINE_SIZE * DIVIDE_RATE];
} job_t;

job_t          job[MAX_CPU_NUMBER];

The job array is equal 8MB.

Thus, We use malloc instead of stack allocation.
 		2013-07-08 01:07:05 +08:00
..
getf2 Import GotoBLAS2 1.13 BSD version codes. 2011-01-24 14:54:24 +00:00
getrf Refs #221 #246. Fixed the overflowing stack bug in mutlithreading BLAS3. 2013-07-08 01:07:05 +08:00
getri Import GotoBLAS2 1.13 BSD version codes. 2011-01-24 14:54:24 +00:00
getrs Import GotoBLAS2 1.13 BSD version codes. 2011-01-24 14:54:24 +00:00
laswp Refs #130 Fixed laswp building bug with DYNAMIC_ARCH=1. 2012-08-09 20:36:29 +08:00
lauu2 Import GotoBLAS2 1.13 BSD version codes. 2011-01-24 14:54:24 +00:00
lauum Import GotoBLAS2 1.13 BSD version codes. 2011-01-24 14:54:24 +00:00
potf2 Import GotoBLAS2 1.13 BSD version codes. 2011-01-24 14:54:24 +00:00
potrf Refs #221 #246. Fixed the overflowing stack bug in mutlithreading BLAS3. 2013-07-08 01:07:05 +08:00
trti2 Import GotoBLAS2 1.13 BSD version codes. 2011-01-24 14:54:24 +00:00
trtri Import GotoBLAS2 1.13 BSD version codes. 2011-01-24 14:54:24 +00:00
Makefile Import GotoBLAS2 1.13 BSD version codes. 2011-01-24 14:54:24 +00:00