Hank Anderson
2416d9dbac
Fixed TRANSA defines for complex sources in driver/level2.
11 years ago
Hank Anderson
0d8e227ea7
Changed strategy for setting preprocessor definitions.
Instead of generating separate object files for each permutation of
defines for a source file, GenerateNamedObjects now writes an entirely
new source file and inserts the defines as #define c statements.
This solves a problem I ran into with ar.exe where it was refusing to
link objects that had the same filename despite having different paths.
11 years ago
Hank Anderson
1b7f427401
Added conj gemv objects for complex build.
11 years ago
Hank Anderson
fb5d5bb971
Added defines for complex trmv.
11 years ago
Hank Anderson
371071d461
Added CONJ defines for trmm/trsm.
11 years ago
Hank Anderson
8a143516e3
Added alternate_name to a couple of the name mangling schemes.
Added zherk_k sources to driver/level3.
11 years ago
Hank Anderson
e5897ecb9b
Added zherk_kernel.c objects to driver/level3.
11 years ago
Hank Anderson
33c5e8db7f
Added a helper function for setting the L1 kernel defaults.
Added loop to build objects with different KERNEL defines.
11 years ago
Hank Anderson
4662a0b13a
Changed generate functions to iterate through a list of float types.
This will generate obj files for SINGLE/DOUBLE/COMPLEX/DOUBLE COMPLEX.
11 years ago
Hank Anderson
e74462a3f5
Moved declarations to start of functions to satisfy MSVC C89 implementation.
11 years ago
Hank Anderson
056ba26755
Changed a number of inline calls to use __inline.
MSVC doesn't inmplement C99, so can't use the inline keyword. __inline
appears to work in MSVC and GCC.
11 years ago
Hank Anderson
c94fe71278
Removed incoming-stack-boundary for MSVC.
Made float type optional for GenerateNamedObjects.
Called GenerateNamedObjects for a couple of driver/others files that
needed NAME/CNAME set.
11 years ago
Hank Anderson
e8c39138c6
Removed return value from GenerateNamedObjects.
It sets DBLAS_OBJS directly to save a bunch of list appending in the
CMakeLists.txt files.
11 years ago
Hank Anderson
7fa5c4e2fd
Fixed some case issues with ARCH.
Added some kernel and driver/others objects.
11 years ago
Zhang Xianyi
cfa9392ffa
Fix openblas_get_num_threads and openblas_get_num_procs bug with single thread.
11 years ago
Hank Anderson
2f59135eb6
Added gemv to level2 CMakeLists.txt.
11 years ago
Hank Anderson
6b5d26e07b
Added SMP sources to level2 CMakeLists.txt.
11 years ago
Hank Anderson
627d5e7401
Added SMP objects to driver/level3.
11 years ago
Hank Anderson
943fa2fb58
Fixed object names in level2.
11 years ago
Hank Anderson
461e691127
Codes when define is absent are now a parameter to AllCombinations.
The level3 object names should now be correct.
11 years ago
Hank Anderson
cfaf1c678f
Added option to append define codes with an underscore.
Fixed the code array not getting reset on subsequent AllCombinations
calls.
11 years ago
Hank Anderson
0d7bad1f35
Changed GenerateObjects to append combination codes (e.g. dtrmm_TU).
11 years ago
Hank Anderson
2828f6630c
Added SMP sources to COMMONOBJS.
11 years ago
Erik Schnetter
65a847cd36
Introduce openblas_get_num_threads and openblas_get_num_procs
11 years ago
Hank Anderson
7194424fef
Added missing common objects to the library.
11 years ago
Hank Anderson
d11bde60d0
DOUBLE define for DBLAS objects is now set in main CMakeLists.txt.
Since the objects are the same, could generate SINGLE/COMPLEX/etc here
without having to rewrite all the object enumeration code again.
11 years ago
Hank Anderson
5057a4b4df
Added openblas add_library call that uses DBLAS_OBJS ojbects.
11 years ago
Hank Anderson
3e8ea7a351
Added COMMONOBJS to driver/others CMakeLists.txt.
11 years ago
Hank Anderson
d3dcdddf75
Moved functions into util cmake file.
11 years ago
Hank Anderson
e5e7595bf9
Added paramater to GenerateObjects for defines that affect all sources.
11 years ago
Hank Anderson
7693887d61
Added empty set to the combinations generated by AllCombinations.
11 years ago
Hank Anderson
8d9b196e0d
Moved loop over define combos into a function.
This function takes a set of sources and a set of preprocessor
definitions. It will iterate over the sources and build an object
file for each combination of preprocessor definitions for each
source file.
11 years ago
Hank Anderson
a6cf8aafc0
Updated level3/CMakeLists with correct defines using all combos.
11 years ago
Hank Anderson
dbdca7bf0c
Added first pass at driver/level3 Makefile conversion.
Added a rather convoluted CMake function to find all combinations
of a given list. This will be useful for the object files that are
compiled multiple times with different combinations of preprocessor
definitions.
11 years ago
Hank Anderson
8c23965da3
prebuild.cmake now reads the output from getarch into CMake vars.
11 years ago
Hank Anderson
8ede4a8da4
getarch now compiles and sets config.h defines properly.
Still isn't parsed into CMake variables, and getarch_2 needs to
get the same treatment.
11 years ago
Hank Anderson
1c5b6bb4f7
Added CORE define to config.h in prebuild.cmake (temporarily).
11 years ago
Hank Anderson
9a508abdc7
Added first pass at driver/level2 makefile conversion.
11 years ago
Werner Saar
0dc559ed30
bugfix in dynamic.c
11 years ago
Werner Saar
4319769b79
added target processor STEAMROLLER
11 years ago
Zhang Xianyi
2fb02626da
Update organization info.
11 years ago
Zhang Xianyi
695e0fa649
#463 fixed a compiling bug on AIX.
11 years ago
wernsaar
7aae4a62e7
enabled use of GEMM3M functions
11 years ago
wernsaar
a64fe9bcc9
added optimized sgemv_n kernel for sandybridge
11 years ago
wernsaar
2021d0f9d6
experimentally removed expensive function calls
11 years ago
Isaac Dunham
f7eb81a846
Fix link error on Linux/musl.
get_nprocs() is a GNU convenience function equivalent to POSIX2008
sysconf(_SC_NPROCESSORS_ONLN); the latter should be available in unistd.h
on any current *nix. (OS X supports this call since 10.5, and FreeBSD
currently supports it. But this commit does not change FreeBSD or OS X
versions.)
11 years ago
wernsaar
793175be3a
added experimental support for big numa machines
11 years ago
wernsaar
1d33547222
optimized zgemm kernel for haswell
11 years ago
wernsaar
3ea4dadd30
optimizations for trsm
11 years ago
wernsaar
1b10ff129a
optimizations for trmm
11 years ago