OpenBLAS

Commit Graph

Author	SHA1	Message	Date
Jerome Robert	b17ccb4c5c	Fix a segfault in gemv when MAX_STACK_ALLOC is set * stack_alloc_size is needed after the implementation call but it may be overwritten if it's optimized to a register, because some gemv implementation (ex: dgemv_n.S) do not restore all register (ex: r10). * do the same in ger.c for the same reasons even if the bug has not been observed.	10 years ago
Hank Anderson	5eefe18ae4	Added CMakeLists.txt for the first of the BLAS folders. It only does the double precision compile currently. I realized I didn't finish converting Makefile.system yet, so I made a note of that.	10 years ago
Jerome Robert	e9d9a8eae3	Allow to do gemv and ger buffer allocation on the stack ger and gemv call blas_memory_alloc/free which in their turn call blas_lock. blas_lock create thread contention when matrices are small and the number of thread is high enough. We avoid call blas_memory_alloc by replacing it with stack allocation. This can be enabled with: make -DMAX_STACK_ALLOC=2048 The given size (in byte) must be high enough to avoid thread contention and small enough to avoid stack overflow. Fix #478	10 years ago
wernsaar	9e829ce98f	enabled cblas gemm3m functions	11 years ago
wernsaar	d49fd33885	disabled SYMM3M and HEMM3M functions because segment violations	11 years ago
wernsaar	7aae4a62e7	enabled use of GEMM3M functions	11 years ago
wernsaar	3300f5ebff	optimized multithreading lower limits	11 years ago
wernsaar	fd2478c9e2	optimized interface/zgemv.c for multithreading	11 years ago
Zhang Xianyi	1cba8e7b11	Merge pull request #446 from grisuthedragon/cblas_matcopy Add a CBLAS interface for the BLAS extension s/d/c/z*matcopy routines.	11 years ago
Martin Koehler	a057e5434d	add CBLAS interface for s/d/c/zimatcopy	11 years ago
Martin Köhler	7794766d3c	Add cblas_(s/d/c/z)omatcopy in order to have cblas interface for them.	11 years ago
wernsaar	f511807fc0	modified multithreading threshold	11 years ago
wernsaar	d1800397f5	optimized interface/gemv.c for multithreading	11 years ago
wernsaar	f4ff889491	updated interface/gemv.c for multithreading	11 years ago
wernsaar	51413925bd	adjust number of threads for small size in cgemv and zgemv	11 years ago
wernsaar	b985cea65d	adjust number of threads for sgemv and dgemv	11 years ago
wernsaar	d286daa2ba	adjusted number of threads for small size	11 years ago
wernsaar	cedc1f4b14	Ref #410 : disabled optimized potri functions ( single threading bug)	11 years ago
wernsaar	02a504c0b8	fixed my bug in ger.c	11 years ago
wernsaar	be94db096c	disabled *3M functions for x86_64 platforms	11 years ago
wernsaar	aee61456a4	disabled SMP for sbmv and zsbmv again	11 years ago
wernsaar	01a119abfc	enabled SMP for sbmv and zsbmv, but only for 64bit binaries	11 years ago
wernsaar	1fad2b759f	enabled smp for ger.c and zger.c, but only for 64bit binaries	11 years ago
Timothy Gu	6c2ead30f0	Remove all trailing whitespace except lapack-netlib Signed-off-by: Timothy Gu <timothygu99@gmail.com>	11 years ago
wernsaar	15d5dfa92c	fixed compiler warnings	11 years ago
wernsaar	86d8c8978b	Ref #391 : disabled SMP in ger.c and zger.c	11 years ago
wernsaar	a19d209005	Ref #103 : enhancement for small matrix dimensions	11 years ago
wernsaar	faeab93df0	Ref #51 : added blas extensions simatcopy, dimatcopy, cimatcopy, zimatcopy	11 years ago
wernsaar	cee257f384	Ref #51 : added blas extensions zomatcopy and comatcopy	11 years ago
wernsaar	7bfb3011e8	Ref #51 : added blas extension somatcopy	11 years ago
wernsaar	8c8f596238	Ref #51 : added blas extension domatcopy as not opimized reference	11 years ago
wernsaar	bff575d0b1	Ref #375 : added workaround for small sizes to scal.c and zscal.c	11 years ago
wernsaar	faf3ac0aad	Ref #285 : added axpby kernels	11 years ago
Zhang Xianyi	b31ec99372	Fixed #374 . Merge branch 'TimothyGu-develop' into develop	11 years ago
wernsaar	25e899b60b	fixed function profile in zpotri.c	11 years ago
wernsaar	89da450800	enabled and tested optimized potri lapack functions	11 years ago
wernsaar	c26bbee489	enabled abd tested optimized trtri lapack functions	11 years ago
Timothy Gu	ced13574a0	Random "walk (a)round" --> "work-around" typo fixes Signed-off-by: Timothy Gu <timothygu99@gmail.com>	11 years ago
wernsaar	a748d3a75d	enabled optimized trti2 lapack functions again	11 years ago
wernsaar	a5ab231ad4	enabled optimized complex lauum lapack functions again	11 years ago
wernsaar	dbaeea7b59	enabled lauu2 and lauum lapack functions again	11 years ago
wernsaar	0d75f3b6a2	enabled and tested optimized gesv lapack functions	11 years ago
wernsaar	abad6f66d6	marked trti2.c and ztrti2.c as bad	11 years ago
wernsaar	2ff66e661d	enabled and tested optimized laswp lapack function	11 years ago
wernsaar	5e55034922	marked zlauu2.c and zlauum.c as bad	11 years ago
wernsaar	9a9e810239	marked trtri.c and ztrtri as bad	11 years ago
wernsaar	45be9ac111	moved trtri.c and ztrtri.c to the directory lapack	11 years ago
wernsaar	9f201558c9	marked lauu2.c and lauum.c as bad	11 years ago
wernsaar	d4237cb7f3	marked larf.c as obsolete	11 years ago
wernsaar	aaa9d7fbf8	marked potri functions as bad because a lot of errors	11 years ago

... 3 4 5 6 7

315 Commits (v0.3.23)