OpenBLAS

Tree: 9e2f316ede

History

Martin Kroeker 9e2f316ede Power8 inline assembly fixes Quoting patch author amodra from #1078 Lots of issues here. - The vsx regs weren't listed as clobbered. - Poor choice of vsx regs, which along with the lack of clobbers led to trashing v0..v21 and fr14..fr23. Ideally you'd let gcc choose all temp vsx regs, but asms currently have a limit of 30 i/o parms. - Other regs were clobbered unnecessarily, seemingly in an attempt to clobber inputs, with gcc-7 complaining about the clobber of r2. (Changed inputs should be also listed as outputs or as an i/o.) - "r" constraint used instead of "b" for gprs used in insns where the r0 encoding means zero rather than r0. - There were unused asm inputs too. - All memory was clobbered rather than hooking up memory outputs with proper memory constraints, and that and the lack of proper memory input constraints meant the asms needed to be volatile and their containing function noinline. - Some parameters were being passed unnecessarily via memory. - When a copy of a		8 years ago
..
alpha	Remove all trailing whitespace except lapack-netlib	11 years ago

arm	Update zdot.c	9 years ago

arm64	THUNDERX2T99: Add optimized S/D/C/Z COPY Implementations	8 years ago

generic	remove dead code	9 years ago

ia64	Remove all trailing whitespace except lapack-netlib	11 years ago

mips	Added rot functions.	8 years ago

mips64	Added MSA optimization for GEMV_N, GEMV_T, ASUM, DOT functions	9 years ago

power	Power8 inline assembly fixes	8 years ago

sparc	Remove all trailing whitespace except lapack-netlib	11 years ago

x86	Fix cmake bug on MSVC 32-bit.	10 years ago

x86_64	Change file comments to work around clang 3.9 assembler bug	9 years ago

zarch	dtrmm and dgemm for z13	8 years ago

CMakeLists.txt	Replace CMAKE_SOURCE_DIR/CMAKE_BINARY_DIR with PROJECT_SOURCE_DIR/PROJECT_BINARY_DIR	9 years ago

Makefile	Remove all trailing whitespace except lapack-netlib	11 years ago

Makefile.L1	Remove duplicate -D args in kernel/Makefile.L1	10 years ago

Makefile.L2	Remove all trailing whitespace except lapack-netlib	11 years ago

Makefile.L3	Merge branch 'z13' into develop	8 years ago

Makefile.LA	Support NO_LAPACK=1 to build the lib without LAPACK functions.	14 years ago

setparam-ref.c	prepared kernel/setparam-ref.c for UNROLL values, that are not a power of two	8 years ago

OpenBLAS is an optimized BLAS library based on GotoBLAS2 1.13 BSD version.

C Fortran Motorola 68K Assembly Makefile Unix Assembly other

wernsaar@googlemail.com traits.zhang@gmail.com xianyi@iscas.ac.cn hank.p.anderson@gmail.com martin@ruby.chemie.uni-freiburg.de wangqian10@iscas.ac.cn ashwin@broadcom.com ashwin.sekhar@cavium.com jeromerobert@gmx.com zaheer.chothia@gmail.com kirkhamj@janelia.hhmi.org shivraj.patil@imgtec.com koehlerm@mpi-magdeburg.mpg.de timothygu99@gmail.com notasas@gmail.com kaustubh.raste@imgtec.com lotheac@iki.fi mike@nolta.net olivier.grisel@ensta.org paul.mustiere@gmail.com sebastien@debian.org xantares09@hotmail.com bradatajs@yahoo.com schnetter@gmail.com Explorer09@gmail.com

Contributors (25+) All

Contributors (25+)
All