OpenBLAS

78 MB

Tree: b329e45288

Author	SHA1	Message	Date
Martin Kroeker	330044d821	Fix potentiol domain error in sqrt	5 years ago
Martin Kroeker	ce45af8151	Update conditional for atomics to use HAVE_C11	5 years ago
Zhiyong Dang	3716267124	Change _STDC_VERSION__ to __STDC_VERSION__ Change-Id: Id3fa4e8d9eedd4ef7230df69b611e7f397301a42	7 years ago
Martin Kroeker	6a99fcce94	Use _Atomic instead of volatile for thread safety where C11 is supported Suggested by dodomorandi in #660	8 years ago
Andrew	11a627c54e	remove surplus parentheses to silence clang5	8 years ago
Werner Saar	a2672d5589	prepared driver/level3 functions for UNROLL values, that are not a power of two	9 years ago
wernsaar	125610d23b	allow to set custom value for ?GEMM_DEFAULT_UNROLL_MN, optimizations for syrk	11 years ago
Timothy Gu	6c2ead30f0	Remove all trailing whitespace except lapack-netlib Signed-off-by: Timothy Gu <timothygu99@gmail.com>	11 years ago
Zhang Xianyi	32d2ca3035	Refs #214 , #221 , #246 . Fixed the getrf overflow bug on Windows. I used a smaller threshold since the stack size is 1MB on windows.	12 years ago
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.	12 years ago
Xianyi Zhang	342bbc3871	Import GotoBLAS2 1.13 BSD version codes.	15 years ago