82e80fa82b
initial strmm(sgemm). not tuned yet
2017-03-06 04:27:40 +04:00
d1fe040d9b
Merge pull request #1110 from quickwritereader/develop
...
Conventional usage of the register save area.
2017-03-01 23:08:07 +01:00
411982715c
conventional usage of the register save area
2017-03-01 20:39:39 +04:00
e831d6924e
changed to conventional register save area
2017-03-01 03:13:21 +04:00
ffc1d6c468
Merge pull request #1108 from ashwinyes/develop_20170203_thunderx2t99
...
Optimized Implementations for ThunderX2T99
2017-02-28 16:02:19 +01:00
67473d09dd
THUNDERX2T99: Bug Fixes in D/Z NRM2 and ZGEMM
2017-02-28 01:11:38 -08:00
19ba133383
THUNDERX2T99: Add Optimized ZGEMM Implementation
2017-02-28 05:31:41 +00:00
0d96b0e2a7
Merge branch 'z13' into develop
2017-02-26 06:17:33 +04:00
848cb27b1e
ztrmm kernel.
2017-02-26 06:14:12 +04:00
dc34a0da96
Merge pull request #915 from mdong/small_fix_for_icc
...
remove input from clobbered list
2017-02-23 20:00:22 +01:00
a3935f0dfb
THUNDERX2T99: Add Optimized D/Z NRM2 Implementation
2017-02-23 10:02:15 -08:00
738628e9a8
ARM64: Remove unused code
2017-02-21 21:42:32 -08:00
ab3ffab96a
THUNDERX2T99: Add Optimized C/Z DOT Implementation
2017-02-21 03:40:59 -08:00
f036be9ce2
THUNDERX2T99: Add Optimized SDOT Implementation
2017-02-21 03:24:32 -08:00
faba876fda
THUNDERX2T99: Bug fix in C/Z IAMAX
2017-02-19 23:11:50 -08:00
172a62d73e
THUNDERX2T99: Add Optimized C/Z IAMAX Implementation
2017-02-17 03:06:32 -08:00
228c75a69c
THUNDERX2T99: Add parallel SCNRM2 Implementation
2017-02-14 04:10:06 -08:00
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
2017-02-13 23:38:50 +01:00
8e89668f62
THUNDERX2T99: Fix bug in SNRM2
2017-02-07 02:14:33 -08:00
f63deae9de
THUNDERX2T99: Add Optimized S/D IAMAX Implementation
2017-02-07 01:35:55 -08:00
60eea75409
Merge pull request #1076 from ashwinyes/develop_20170130_thunderx2t99
...
More optimized implementations for ThunderX2T99
2017-02-04 17:25:43 +01:00
071a830e8b
THUNDERX2T99: Add optimized S/D/C/Z SWAP Implementations
2017-02-03 03:55:06 -08:00
d09f88192c
THUNDERX2T99: Add optimized S/D/C/Z COPY Implementations
2017-02-02 15:26:38 +05:30
e58233460a
THUDNERX2T99: Add optimized D/C/Z ASUM Implementations
2017-02-02 15:26:22 +05:30
99bd2892bf
THUNDERX2T99: Add optimized CASUM Implementation
2017-01-30 17:44:32 +05:30
ff6f572f2e
THUNDERX2T99: Rename labels in for DDOT and SNRM2
2017-01-30 17:44:32 +05:30
e0dc5f58c5
THUNDERX2T99: Remove Duplicate Code
2017-01-30 17:44:32 +05:30
2757b49767
THUNDERX2T99: Add Optimized CGEMM Implementation
2017-01-30 17:44:26 +05:30
ff41e13385
Merge pull request #1074 from ashwinyes/develop_20170116_thunderx2t99_sgemm
...
Add more THUNDERX2T99 Optimized APIs
2017-01-25 22:17:05 +08:00
907e286eb6
THUNDERX2T99: Add threaded SNRM2 Implementation
2017-01-24 21:39:29 +05:30
cde3aee08b
ARM64: Rename kernel files to have consistent naming
2017-01-24 14:53:34 +05:30
ee6ea7e988
THUNDERX2T99: Add Optimized CNRM2 Implementation
2017-01-24 10:23:32 +05:30
ca0b36b012
THUNDERX2T99: Add Optimized SNRM2 Implementation
2017-01-24 10:23:21 +05:30
d0a79ca6e0
THUNDERX2T99: Add threaded DDOT Implementation
2017-01-19 11:11:42 +05:30
0c07003ccf
THUNDERX2T99: Add Optimized DDOT Implementation
2017-01-19 11:11:07 +05:30
f33fcedb30
THUNDERX2T99: Improve SGEMM
2017-01-19 11:11:07 +05:30
0f1d6e8b39
THUNDERX2T99: Improve DGEMM
2017-01-19 11:11:07 +05:30
981064acc6
THUNDERX2T99: Add Optimized DAXPY Implementation
2017-01-19 11:10:57 +05:30
a4d97d980f
Added rot functions.
...
Signed-off-by: Shivraj Patil <shivraj.patil@imgtec.com>
2017-01-17 12:15:07 +05:30
f279ff4789
THUNDERX2T99: Add Optimized SGEMM Implementation
2017-01-16 21:44:33 +05:30
759f37feba
ARM64: Let target VULCAN inherit THUNDERX2T99 properties
2017-01-16 21:44:19 +05:30
0863a0d4b4
Merge pull request #1061 from ashwinyes/develop_aarch64_vulcan_thunderx_patch
...
Add new targets for ARM64
2017-01-16 13:20:10 +08:00
28e2fab33e
prepared kernel/setparam-ref.c for UNROLL values, that are not a power of two
2017-01-11 11:56:50 +01:00
4b55fae337
ARM64: Add Cavium THUNDERX2T99 Target
2017-01-11 11:18:40 +05:30
95649dee28
THUNDERX: Add optimized version of daxpy
...
This is better for single core but does not change anything for multiple cores
2017-01-11 11:18:36 +05:30
8fdb0655e9
THUNDERX: Add an optimized version of ddot
2017-01-10 15:01:37 +05:30
fb200c7245
ARM64: Add Cavium THUNDERX Target
2017-01-10 15:01:37 +05:30
0b8e876d89
VULCAN: Add optimized DGEMM implementation
2017-01-10 15:01:37 +05:30
4713e7c47f
ARM64: Add the VULCAN Target
2017-01-10 15:01:17 +05:30
6085386b10
CORTEXA57: Add assembly kernels for copy routines
2017-01-10 15:01:05 +05:30
1480f3df71
Add msa optimization for AXPY, COPY, SCALE, SWAP
...
Signed-off-by: kaustubh <kaustubh.raste@imgtec.com>
2017-01-09 18:27:23 +05:30
88afb3bc94
Add msa optimization for AXPY, COPY, SCALE, SWAP
...
Signed-off-by: kaustubh <kaustubh.raste@imgtec.com>
2017-01-09 18:22:09 +05:30
b678471d65
Merge branch 'z13' into develop
...
Conflicts:
CONTRIBUTORS.md
2017-01-09 05:52:42 -05:00
864e202afd
Add USE_TRMM=1 for IBM z13 in kernel/Makefile.L3
2017-01-09 05:48:09 -05:00
6418667818
dtrmm and dgemm for z13
2017-01-04 19:32:33 +04:00
a9bf8a781a
Added prefetch to CGEMV and ZGEMV.
...
Signed-off-by: Shivraj Patil <shivraj.patil@imgtec.com>
2016-12-27 11:33:51 +05:30
5f93aa5f87
Updated data prefetch in TRSM, ASUM, DOT functions
...
Signed-off-by: kaustubh <kaustubh.raste@imgtec.com>
2016-12-14 14:05:11 +05:30
9db451acd0
Updated data prefetch in TRSM, ASUM, DOT functions
...
Signed-off-by: kaustubh <kaustubh.raste@imgtec.com>
2016-12-13 14:02:14 +05:30
3eaff85191
Updated data prefetch in TRSM, ASUM, DOT functions
...
Signed-off-by: kaustubh <kaustubh.raste@imgtec.com>
2016-12-13 11:41:17 +05:30
00abce3b93
Add data prefetch in DOT and ASUM functions
...
Signed-off-by: kaustubh <kaustubh.raste@imgtec.com>
2016-11-22 11:21:03 +05:30
becf8bc7a0
remove dead code
2016-10-31 12:46:56 +01:00
f3419e634c
SGEMM, DGEMM, CGEMM, ZGEMM functions data prefetch
...
Signed-off-by: kaustubh <kaustubh.raste@imgtec.com>
2016-10-17 18:29:38 +05:30
7472c79ea6
Merge pull request #984 from ksraste/develop
...
STRSM, DTRSM functions data prefetch
2016-10-17 11:33:16 +08:00
90e2321ac3
STRSM, DTRSM functions data prefetch
...
Signed-off-by: kaustubh <kaustubh.raste@imgtec.com>
2016-10-14 16:41:28 +05:30
4998e19869
Change file comments to work around clang 3.9 assembler bug
2016-10-13 16:51:08 +02:00
91610f3835
Update zdot_msa.c
2016-10-05 18:59:09 +02:00
6e22ecf102
Update zdot.c
2016-10-05 18:58:03 +02:00
6221d6df5f
Update zdot.c
2016-10-05 18:57:14 +02:00
16446d1d23
Remove explicit include of complex.h
2016-09-29 23:45:56 +02:00
a6e9e0b94b
Remove explicit include of complex.h
2016-09-29 23:43:28 +02:00
3178e4fea0
Remove explicit include of complex.h
2016-09-29 23:41:43 +02:00
95c245ddb0
Remove explicit include of complex.h
2016-09-29 23:40:36 +02:00
4b1b27347f
Remove explicit include of complex.h
2016-09-29 23:39:35 +02:00
54747fe24a
DGEMM function split and data prefech
...
Signed-off-by: Shivraj Patil <shivraj.patil@imgtec.com>
2016-09-22 17:25:46 +05:30
515bc56ea9
Refs #946 . Use nrm2 reference implementation for Power8.
2016-08-18 18:59:43 -07:00
ae70b916f4
Refs #929 . Deal with zero and NaNs for scale.
2016-08-18 10:24:42 -07:00
9687437928
MIPS n32 ABI and build time mips simd support check
...
Signed-off-by: Shivraj Patil <shivraj.patil@imgtec.com>
2016-08-10 17:44:22 +05:30
d1c6469283
MIPS n32 ABI support, MSA support detection and rename ARCH, ARCHFLAGS
...
Signed-off-by: Shivraj Patil <shivraj.patil@imgtec.com>
2016-08-08 11:58:01 +05:30
c54a29bb48
Cortex A57: Improvements to DGEMM 8x4 kernel
2016-07-26 10:58:21 +05:30
beb1d076a4
Added MSA optimization for GEMV_N, GEMV_T, ASUM, DOT functions
...
Signed-off-by: Shivraj Patil <shivraj.patil@imgtec.com>
2016-07-15 18:38:25 +05:30
8a592ee386
Merge pull request #924 from ashwinyes/develop_aarch64_improvements_20160714
...
Improvements to Aarch64 kernels
2016-07-14 15:47:55 -04:00
0a5ff9f9f9
Improvements to TRMM and GEMM kernels
2016-07-14 13:56:04 +05:30
8a40f1355e
Improvements to GEMV kernels
2016-07-14 13:50:38 +05:30
78782485b6
Improvements to COPY and IAMAX kernels
2016-07-14 13:49:34 +05:30
57df7956ee
Added CGEMM, ZGEMM, STRMM, DTRMM, CTRMM, ZTRMM. Updated macros in SGEMM, DGEMM, STRMM.
...
Signed-off-by: Shivraj Patil <shivraj.patil@imgtec.com>
2016-06-28 17:51:10 +05:30
4a30a2584a
Merge pull request #897 from ksraste/develop
...
STRSM optimized for MSA
2016-06-27 10:04:18 -04:00
098d8ec5d6
remove input from clobbered list
2016-06-24 16:37:58 -04:00
f04af36ad0
Merge pull request #898 from wernsaar/develop
...
added experimental support for optimized lapack fortran functions
2016-05-31 14:13:52 +02:00
011431b9d7
STRSM optimized for MSA
...
Signed-off-by: Kaustubh Raste <kaustubh.raste@imgtec.com>
2016-05-31 10:17:23 +05:30
c8a7860eb3
STRSM optimized
...
Signed-off-by: Kaustubh Raste <kaustubh.raste@imgtec.com>
2016-05-30 21:17:00 +05:30
2daad2bcb5
Merge pull request #893 from biddisco/develop
...
Replace CMAKE_SOURCE_DIR/CMAKE_BINARY_DIR with PROJECT_SOURCE_DIR/PRO…
2016-05-30 14:52:58 +08:00
053044ae4d
Replace CMAKE_SOURCE_DIR/CMAKE_BINARY_DIR with PROJECT_SOURCE_DIR/PROJECT_BINARY_DIR
...
If OpenBLAS is built using add_subdirectory(OpenBlas) as part of another project
then the paths set by CMAKE_XXX_DIR are relative to the parent project
and not the OpenBLAS project.
2016-05-25 09:13:28 +02:00
fca66262c4
mips64/axpy: fix error when INCY == 0
2016-05-23 13:30:27 +03:00
412bcd187a
optimized dtrsm_logic_LT_16x4_power8.S and dtrsm_macros_LT_16x4_power8.S
2016-05-23 11:20:41 +02:00
bd06b246cc
Merge pull request #890 from wernsaar/develop
...
optimized dtrsm_kernel_LT for POWER8
2016-05-22 16:01:35 +02:00
8b140220c8
optimized dtrsm_kernel_LT for POWER8
2016-05-22 15:20:04 +02:00
8fb5a1aaff
added optimized dtrsm_LT kernel for POWER8
2016-05-22 13:09:05 +02:00
ad9f317870
STRSM optimization for MIPS P5600 and I6400 using MSA
...
Signed-off-by: Kaustubh Raste <kaustubh.raste@imgtec.com>
2016-05-20 10:59:03 +05:30
c4ba40e308
SGEMM optimization for MIPS P5600 and I6400 using MSA. Unrolled k loop in DGEMM kernel function
...
Signed-off-by: Shivraj Patil <shivraj.patil@imgtec.com>
2016-05-19 11:04:42 +05:30
7a19065369
Merge pull request #878 from ksraste/develop
...
DTRSM bug fix for MIPS P5600 and I6400
2016-05-19 11:16:43 +08:00
6a2bde7a2d
optimized dgemm and dgetrf for POWER8
2016-05-17 14:45:27 +02:00
d7cbc7ac13
DTRSM bug fix for MIPS P5600 and I6400
...
Signed-off-by: Kaustubh Raste <kaustubh.raste@imgtec.com>
2016-05-17 15:48:02 +05:30
88011f625d
Merge pull request #876 from wernsaar/develop
...
optimized dgemm on power8 for 20 threads
2016-05-16 14:52:40 +02:00
8310d4d3f7
optimized dgemm for 20 threads
2016-05-16 14:14:25 +02:00
edb5980c13
DTRSM optimization for MIPS P5600 and I6400 using MSA
...
Signed-off-by: Kaustubh Raste <kaustubh.raste@imgtec.com>
2016-05-09 15:15:26 +05:30
085cf236c2
conflict resolved by syncing with 'xianyi:develop'
...
Signed-off-by: Shivraj Patil <shivraj.patil@imgtec.com>
2016-05-04 11:07:14 +05:30
b7b3d8ec8e
DGEMM optimization for MIPS P5600 and I6400 using MSA
...
Signed-off-by: Shivraj Patil <shivraj.patil@imgtec.com>
2016-05-03 14:42:26 +05:30
cd7af5260a
Merge pull request #847 from sva-img/develop
...
MIPS P5600(32 bit) and I6400(64 bit) cores support added.
2016-04-29 11:44:36 -04:00
56948dbf0f
optimized dgemm for POWER8
2016-04-29 12:52:47 +02:00
0d0c6f7d7d
optimized dgemm for POWER8
2016-04-27 14:01:08 +02:00
298b13bba4
updated some kernel files for EXCAVATOR
2016-04-25 10:36:23 +02:00
78b05f6476
bugfix for EXCAVATOR and DYNAMIC_ARCH
2016-04-25 10:13:30 +02:00
a3da10662f
added sgemm_tcopy_8_power8.S
2016-04-23 10:04:41 +02:00
d46f07bb4e
added cgemm_tcopy_8_power8.S
2016-04-23 07:37:18 +02:00
879a51165f
Optimized zgemm and tested zgemm again
2016-04-22 13:07:12 +02:00
2c3dfe2bf3
MIPS P5600(32 bit) and I6400(64 bit) cores support added.
...
Seperated mips and mips64 files.
Configurations support for mips 32 bit.
Signed-off-by: Shivraj Patil <shivraj.patil@imgtec.com>
2016-04-22 14:03:18 +05:30
9276c9012f
Optimized sgemm and dgemm and tested again.
2016-04-21 11:37:57 +02:00
6fbca2a4a1
Merge pull request #845 from wernsaar/develop
...
optimized sgemm for power8
2016-04-20 13:44:22 +02:00
0001260f4b
optimized sgemm
2016-04-20 13:06:38 +02:00
3c6294ca3d
added optimized sgemm_tcopy for power8
2016-04-19 16:08:54 +02:00
dd43661cfd
Init IBM z system (s390x) porting.
2016-04-15 18:02:24 -04:00
f24d5307cf
Refs #834 . Fix zgemv config bug on Steamroller.
2016-04-12 22:26:11 +08:00
8037d78eed
bugfix for arm scal.c and zscal.c
2016-04-11 11:21:36 +02:00
0a4276bc2f
Merge pull request #837 from wernsaar/develop
...
updated zgemm- and ztrmm-kernel for POWER8
2016-04-08 11:13:27 +02:00
e173c51c04
updated zgemm- and ztrmm-kernel for POWER8
2016-04-08 09:05:37 +02:00
9c42f0374a
Updated cgemm- and sgemm-kernel for POWER8 SMP
2016-04-07 15:08:15 +02:00
d4380c1fe4
Refs xianyi/OpenBLAS-CI#10 , Fix sdot for scipy test_iterative.test_convergence test failure on AMD bulldozer and piledriver.
2016-04-07 01:44:18 +08:00
a51102e9b7
bugfixes for sgemm- and cgemm-kernel
2016-04-06 11:15:21 +02:00
c5b1fbcb2e
updated optimized cgemm- and ctrmm-kernel for POWER8
2016-04-04 09:12:08 +02:00
d4c0330967
updated cgemm- and ctrmm-kernel for POWER8
2016-04-03 14:30:49 +02:00
6a9bbfc227
updated sgemm- and strmm-kernel for POWER8
2016-04-02 17:16:36 +02:00
68a69c5b50
added optimized dgemv_n kernel for POWER8
2016-03-30 11:10:53 +02:00
c2464a7c4a
added optimized casum kernel for POWER8
2016-03-28 14:12:08 +02:00
294f933869
added optimized zasum kernel for POWER8
2016-03-28 13:37:32 +02:00
f59c9bd6ef
added optimized sasum kernel for POWER8
2016-03-28 12:44:25 +02:00
c53be46d78
added optimized dasum kernel for POWER8
2016-03-28 12:17:15 +02:00
659ed16591
added otimized cswap and zswap kernels for POWER8
2016-03-27 18:31:37 +02:00
35c98a3556
added optimized zscal kernel for POWER8
2016-03-27 16:31:50 +02:00
f1a5dd06c5
added optimized sscal kernel for POWER8
2016-03-27 11:05:56 +02:00
e125a3dc33
Merge pull request #824 from wernsaar/develop
...
added optimized drot-kernel and srot-kernel for POWER8
2016-03-27 10:43:17 +02:00
35f1f21a7f
added drot- and srot-kernel optimimized for POWER8
2016-03-27 08:57:11 +02:00
7b4b7179ba
Merge pull request #819 from ashwinyes/develop_20160324_fixes_optimizations
...
Cortex-A57: Fixes and Optimizations
2016-03-27 00:04:20 -04:00
3d9a50e841
added optimized sswap kernel for POWER8
2016-03-25 17:34:55 +01:00
828c849b44
added optimized ccopy kernel for POWER8
2016-03-25 16:54:25 +01:00
ecc0bc9813
added optimized scopy kernel for POWER8
2016-03-25 16:06:56 +01:00
12f209b7b0
added optimized zswap kernel for POWER8
2016-03-25 15:27:34 +01:00
7316a87930
added optimized dswap kernel for POWER8
2016-03-25 14:35:43 +01:00
0bff057a87
added optimized dcopy kernel for POWER8
2016-03-25 13:03:02 +01:00
1e6cf9808c
added optimized dscal kernel for POWER8
2016-03-25 09:42:08 +01:00
278511ad2d
Cortex-A57: Fix clang compilation errors
2016-03-24 10:42:04 +05:30
3b5ffb49d3
Cortex-A57: Improve DGEMM 8x4 Implementation
2016-03-24 10:25:18 +05:30
55eda3813b
added optimized zaxpy kernel for POWER8
2016-03-23 11:20:23 +01:00
0664ba4c97
added optimized daxpy kernel for POWER8
2016-03-22 14:50:03 +01:00
11c44dede1
added optimized sdot kernel for POWER8
2016-03-21 13:18:23 +01:00
9e4584d069
added optimized zdot kernel for POWER8
2016-03-21 10:12:07 +01:00
cd9fafc054
ddot for POWER8: updated licence information
2016-03-20 11:19:27 +01:00
84b92e6373
added optimized ddot kernel for POWER8
2016-03-20 11:06:06 +01:00
c279a53ed8
Merge pull request #806 from wernsaar/develop
...
adding optimized single precision blas level3 kernels for POWER8
2016-03-18 12:46:16 +01:00
e1df5a6e23
fixed sgemm- and strmm-kernel
2016-03-18 12:12:03 +01:00
5c658f8746
add optimized cgemm- and ctrmm-kernel for POWER8
2016-03-18 08:17:25 +01:00
5ac02f6dc7
Optimize Dgemm 4x4 for Cortex A57
2016-03-14 19:35:23 +05:30
7aa1ad4923
Functional Assembly Kernels for CortexA57
...
Adding functional (non-optimized) kernels for Cortex-A57
with the following layouts.
SGEMM - 16x4, 8x8
CGEMM - 8x4
DGEMM - 8x4, 4x8
2016-03-14 19:33:21 +05:30
dcd15b546c
BUGFIX: KERNEL.POWER8
2016-03-14 14:36:59 +01:00
96284ab295
added sgemm- and strmm-kernel for POWER8
2016-03-14 13:52:44 +01:00
faa5e2e5e3
FIX: forgot the add the files cgemv_n_4.c and cgemv_t_4.c
2016-03-10 11:10:38 +01:00
fdf291be30
Added optimized cgemv_n and cgemv_t kernels for bulldozer, piledriver and steamroller
2016-03-10 09:42:07 +01:00
c99cc41cbd
Added optimized zgemv_n kernel for bulldozer, piledriver and steamroller
2016-03-09 14:02:03 +01:00
acdff55a6a
Bugfix for ztrmv
2016-03-07 09:39:34 +01:00
7d6b68eb4a
Refs #786 . Revert to default assembly kernel.
2016-03-07 11:34:58 +08:00
cd5241d0cf
modified KERNEL for power, to use the generic DSDOT-KERNEL
2016-03-06 09:07:24 +01:00
8c43d7fa5f
Merge remote-tracking branch 'origin/power8' into develop
...
Refs #774
2016-03-05 06:03:19 -05:00
085f215257
Modified assembly label name, so that they are hidden.
...
Added license informations.
2016-03-05 10:27:27 +01:00
8f758eeff9
Refs #786 . avoid old assembly c/zgemv kernels.
2016-03-05 08:32:03 +08:00
0afc76fd65
enabled gemm_beta assembly kernels
2016-03-04 15:01:15 +01:00
91e1c5080c
modified configuration, to use power6 sgemm kernel for power8
2016-03-04 13:38:57 +01:00
73f04c2c72
enabled hemv assemly function for power8
2016-03-04 13:20:50 +01:00
3e633152c6
enabled symv assembly kernels on power8
2016-03-04 13:08:18 +01:00
d5130ce7e3
enabled gemv assembly on power8
2016-03-04 12:53:31 +01:00
4824b88fcb
enabled all level1 assembly kernels for power8
2016-03-04 12:35:25 +01:00
b752858d6c
added dgemm-, dtrmm-, zgemm- and ztrmm-kernel for power8
2016-03-01 07:33:56 +01:00
efa4f5c936
Refs #695 #783 . Replace default x86_64 cgemv_t
...
asm kernel by C kernel.
2016-03-01 11:18:56 +08:00
74b0672223
Fix c/zaxpyc kernel bug on Cortex-A57.
2016-02-23 22:47:53 +00:00
6e7be06e07
Refs JuliaLang/julia#5728 . Fix gemv performance bug on Haswell Mac OSX.
...
On Mac OS X, it should use .align 4 (equal to .align 16 on Linux).
I didn't get the performance benefit from .align. Thus, I deleted it.
2016-02-19 17:56:07 -05:00
d06b92906a
Add gemm3m building for CMake.
2016-02-12 05:02:51 +08:00
962376664d
Refs #768 . Swap the result of zdot x87 fp kernel.
2016-02-02 09:15:02 +08:00
c44ff4d648
Refs #714 . avoid compiling warnings.
2016-01-28 04:38:07 +08:00
63a7d7fb24
updated gemv_n_vfpv3.S for armv7
2016-01-25 15:00:13 +01:00
b4ede558a5
updated nrm2 kernel for armv7
2016-01-25 11:55:25 +01:00
de3e2d4349
updated trmm kernels for armv7
2016-01-25 11:08:56 +01:00
a0e51e96f1
updated gemm kernels for armv7
2016-01-25 10:46:10 +01:00
c2891330bc
updated KERNEL.ARMV6
2016-01-24 17:12:07 +01:00
ceaa931e48
updated gemv kernel for armv6
2016-01-24 16:31:19 +01:00
eaa63165df
updated cgemv and zgemv kernels for armv6
2016-01-24 14:42:38 +01:00
c65357c566
updated trmm_kernels for armv6
2016-01-24 13:03:33 +01:00
e63e9f9f26
updated gemm_kernels for armv6
2016-01-24 11:55:50 +01:00
aafd3ab60e
updated cdot and zdot on arm
2016-01-24 10:56:49 +01:00
d2f84c9c8a
Ref #740 : updated nrm2_vfp.S
2016-01-23 17:47:58 +01:00
ca32253f32
Ref #740 : updated asum_vfp.S and iamax_vfp.S
2016-01-23 14:44:34 +01:00
9066d1f982
Ref #750 and Ref #740 : bugfix for sdot, dsdot and ddot on arm
2016-01-23 11:59:51 +01:00
692d9c881c
Ref #740 : simple solution to clear floating point register on arm
2016-01-17 15:37:12 +01:00
3602a2cd1f
#736 Revert #733 patch to fix bus error on ARM.
2016-01-12 22:19:58 +00:00
e3e20e2242
Merge pull request #733 from yuyichao/arm-asm
...
Do not use vsub to clear the register values
2016-01-05 19:35:12 -06:00
594b9f4c73
Do not use vsub to clear the register values since it doesn't work with non-normal numbers.
2016-01-05 16:54:05 +00:00
c8f2c5d636
added optimized trsm_kernels
2016-01-05 13:05:05 +01:00
318f0949c3
lapack-test fixes in nrm2 kernels for Cortex A57
2015-11-23 13:43:36 +05:30
98965da2e8
lapack-test fixes for Cortex A57
2015-11-20 01:15:04 +05:30
c99c43d51e
Optimized trmm kernels for CORTEXA57
2015-11-09 14:15:54 +05:30
1397b47197
Optimized zgemm kernel for CORTEXA57
2015-11-09 14:15:53 +05:30
45f78963ac
Optimized cgemm kernel for CORTEXA57
...
Also, add a generic ztrmm 4x4 kernel
2015-11-09 14:15:53 +05:30
402443bf9c
Optimized dgemm kernel for CORTEXA57
2015-11-09 14:15:53 +05:30
19fdbee291
Improve the sgemm kernel for CORTEXA57
2015-11-09 14:15:53 +05:30
3b0cdfab1e
Optimized gemv kernels for CORTEXA57
...
Co-Authored-By: Ralph Campbell <ralph.campbell@broadcom.com>
2015-11-09 14:15:52 +05:30
46efa6a1da
Optimized swap kernels for CORTEXA57
...
Co-Authored-By: Ralph Campbell <ralph.campbell@broadcom.com>
2015-11-09 14:15:52 +05:30
ea1465cdf8
Optimized scal kernels for CORTEXA57
...
Co-Authored-By: Ralph Campbell <ralph.campbell@broadcom.com>
2015-11-09 14:15:52 +05:30
fb4be3b3eb
Optimized rot kernels for CORTEXA57
...
Co-Authored-By: Ralph Campbell <ralph.campbell@broadcom.com>
2015-11-09 14:15:52 +05:30
6c2f4ddbcd
Optimized nrm2 kernels for CORTEXA57
2015-11-09 14:15:51 +05:30
870c4d49c0
Optimized dot kernels for CORTEXA57
...
Co-Authored-By: Ralph Campbell <ralph.campbell@broadcom.com>
2015-11-09 14:15:51 +05:30
cd7684097c
Optimized copy kernels for CORTEXA57
...
Co-Authored-By: Ralph Campbell <ralph.campbell@broadcom.com>
2015-11-09 14:15:51 +05:30
2690b71b1f
Optimized axpy kernels for CORTEXA57
...
Co-Authored-By: Ralph Campbell <ralph.campbell@broadcom.com>
2015-11-09 14:15:51 +05:30
3e4acedf0e
Optimized asum kernels for CORTEXA57
...
Co-Authored-By: Ralph Campbell <ralph.campbell@broadcom.com>
2015-11-09 14:15:51 +05:30
2610752dbb
Optimized iamax kernels for CORTEXA57
...
Co-Authored-By: Ralph Campbell <ralph.campbell@broadcom.com>
2015-11-09 14:15:50 +05:30
dbb213655e
Optimized amax kernels for CORTEXA57
...
Co-Authored-By: Ralph Campbell <ralph.campbell@broadcom.com>
2015-11-09 14:15:50 +05:30
f2f8a0fe8b
Adding arm64 target CORTEXA57
...
Co-Authored-By: Ralph Campbell <ralph.campbell@broadcom.com>
2015-11-09 14:15:50 +05:30
c053559ed9
Minor C code fixes in kernel/arm
2015-11-09 14:15:49 +05:30
55e4332f00
Remove duplicate -D args in kernel/Makefile.L1
2015-11-09 14:15:48 +05:30
3e8d6ea74f
Init POWER8 kernels by POWER6.
2015-11-03 12:34:23 +08:00
69363622a8
Fix DYNAMIC_ARCH=1 bug.
2015-10-27 05:10:40 +08:00
53b6023a6c
Fix cmake bug on MSVC 32-bit.
2015-10-26 14:52:13 -05:00
309875de3c
Fix cmake bug on x86 32-bit.
...
e.g. Build 32-bit on 64-bit Linux.
cmake -DBINARY=32
2015-10-27 02:54:53 +08:00
8fade093aa
Fixed cmake bug on Visual Studio.
2015-10-20 14:37:22 -05:00
96f0bbe067
Fixed cmake bug on haswell.
2015-10-21 02:24:54 +08:00
d8392c1245
Fixe cmake config bugs.
2015-10-20 04:30:55 +08:00
94b125255f
Merge branch 'develop' into cmake
...
Conflicts:
driver/others/memory.c
2015-10-13 04:46:08 +08:00
711ca33bc6
Improved Ximatcopy when lda==ldb.
...
The Ximatcopy functions create a copy of the input matrix
although they seem to work inplace. The new routines
XIMATCOPY_K_YY perform the operations inplace if the leading
dimension does not change.
2015-09-07 14:36:16 +02:00
7df0820160
Use C kernels for s/dgemv on x86.
2015-08-19 08:07:47 -05:00
f874465bb8
Use cmake to build OpenBLAS GENERIC Target on MSVC x86 64-bit.
...
Disable CBLAS and LAPACK.
2015-08-10 14:10:44 -05:00
898fc7552a
Merge pull request #612 from ibmsoe/ppc64le
...
ppc64le platform support (ELF ABI v2)
2015-08-04 16:58:24 -05:00
ab0a0a75fc
Merge branch 'develop' into cmake
2015-08-03 23:59:01 -05:00
1cf2b10224
Use pure C generic target on x86 and x86_64.
...
make TARGET=GENERIC
?gemm3m is unimplemented on generic target.
2015-08-03 23:55:56 -05:00
7ac7e147d4
Fixed cmake building bugs on Linux. Disable LAPACK by default.
2015-08-04 04:37:05 +08:00
7ba4fe5afb
ppc64le platform support (ELF ABI v2)
2015-07-21 22:20:19 -05:00
dcd5ba4443
Merge branch 'cmake' of https://github.com/hpanderson/OpenBLAS into hpanderson_cmake
2015-07-22 04:06:39 +08:00
e7c969e164
added optimized dtrmm_kernel for haswell
2015-06-13 16:16:29 +02:00
9bd962f655
modified haswell parameter dgemm_unroll_n
2015-06-13 10:28:27 +02:00
24f58c8bb1
added optimized cscal and zscal kernels for steamroller
2015-05-18 12:40:07 +02:00
95b1faf667
added optimized cscal and zscal kernels for steamroller and piledriver
2015-05-18 10:50:57 +02:00
2d9e406050
added optimized cscal kernel for sandybridge
2015-05-18 08:46:06 +02:00
59083e3ce1
added optimized cscal kernel for bulldozer
2015-05-18 07:33:52 +02:00
685be40339
Merge pull request #571 from wernsaar/develop
...
added optimized cscal and zscal functions
2015-05-17 14:09:14 +02:00
31c9e399e9
added optimized cscal kernel for haswell
2015-05-17 13:44:09 +02:00
7de6bb9889
added optimized zscal kernel for bulldozer
2015-05-17 11:45:19 +02:00
d63034303b
added optimized zscal kernel for haswell
2015-05-16 16:41:45 +02:00
51ff17d46e
Add AMD Excavator target.
2015-05-13 16:16:30 -05:00
18e90ee2e3
bugfix: added static to functions
2015-05-13 13:31:26 +02:00
e00cccc41e
added optimized dscal kernel for piledriver
2015-05-13 13:05:35 +02:00
73f09bf64f
optimized dscal kernel for increment != 1
2015-05-13 12:14:39 +02:00
02e772c7e4
added optimized dscal kernel for haswell
2015-05-12 17:19:58 +02:00
7aee913991
added optimized dscal kernel for sandybridge
2015-05-12 16:27:43 +02:00
e50a933037
added optimized dscal kernel for bulldozer
2015-05-12 12:28:44 +02:00
133c11a156
updated dgemv_n kernel for nehalem
2015-04-30 14:38:06 +02:00
30f52d53df
optimized dgemv_n kernel for haswell
2015-04-30 12:11:39 +02:00
5e83d80725
optimized dger kernel for sandybridge
2015-04-28 16:58:11 +02:00
b2e1797dc6
added optimized sger kernel for sandybridge
2015-04-28 15:33:38 +02:00
e216f686cb
optimized saxpy and daxpy for sandybridge
2015-04-28 10:18:32 +02:00
fc0e0391f3
bugfixes: replaced int with BLASLONG
2015-04-24 14:30:44 +02:00
c22068c406
optimized sdot.c for increments != 1
2015-04-24 13:13:20 +02:00
dee100d0e4
optimized saxpy.c for increments != 1
2015-04-24 11:52:59 +02:00
0273966abb
optimized daxpy kernel for increments != 1
2015-04-24 11:39:17 +02:00
3a67daa954
optimized ddot.c for increments != 1
2015-04-24 10:56:55 +02:00
b4f2153dcd
added optimized ssymv kernels for sandybridge
2015-04-23 12:19:24 +02:00
1c4b0eeae3
added optimized ssymv kernels for haswell
2015-04-23 10:23:13 +02:00
1bec9abb9a
added optimized dsymv kernels for sandybridge
2015-04-22 12:09:43 +02:00
3814bf60d3
added optimized dsymv kernels for haswell
2015-04-22 10:42:50 +02:00
6d0db0151f
added optimized zaxpy-kernels
2015-04-16 11:19:37 +02:00
37b9033c90
Merge pull request #543 from jeromerobert/develop
...
Fix a buffer overflow with MAX_STACK_ALLOC size in dgemv_t
2015-04-15 11:18:14 -05:00
13889515b3
added optimized caxpy-kernel for sandybridge
2015-04-15 16:29:25 +02:00
248c9340c3
added optimized caxpy-kernel for haswell
2015-04-15 15:16:31 +02:00
e9f33b4ca7
added optimized caxpy-kernel for steamroller
2015-04-15 13:49:23 +02:00
f5d847122a
updated caxpy_microk_bulldozer-2.c and caxpy.c
2015-04-15 11:59:38 +02:00
a4c96eca67
Fix a buffer overflow with MAX_STACK_ALLOC size in dgemv_t
...
Refs #478 , #482 , 9798481fd9fd42
2015-04-15 11:46:48 +02:00
baa0363ea2
add optimized ddot-kernel for piledriver
2015-04-14 15:09:13 +02:00
34ba66606a
add optimized daxpy-kernel for piledriver
2015-04-14 14:23:29 +02:00
f615dc7603
added optimized saxpy kernel for steamroller
2015-04-14 09:09:39 +02:00
331c417637
optimized saxpy for piledriver
2015-04-14 08:34:11 +02:00
d7a17ad85d
optimized sdot-kernel for pilediver
2015-04-13 13:19:21 +02:00
d35f6c63c2
add optimized daxpy-kernel for steamroller
2015-04-13 12:22:43 +02:00
166d76e864
added optimized sdot-kernel for steamroller
2015-04-11 08:48:18 +02:00
f9f127d838
added optimized ddot kernel for steamroller
2015-04-10 16:18:03 +02:00
62231ab337
Merge pull request #538 from wernsaar/develop
...
Added optimized cdot- and zdot-kernels
2015-04-10 16:03:37 +02:00
3119def9a7
updated cdot and zdot
2015-04-10 11:10:31 +02:00
33b332372a
add optimized cdot- and zdot-kernel for sandybridge
2015-04-10 09:37:26 +02:00
fd838c75bc
add optimized cdot- and zdot-kernel for haswell
2015-04-09 15:13:52 +02:00
b57a60dac8
updated cdot and zdot for piledriver
2015-04-09 10:33:46 +02:00
5c51163972
added optimized cdot- and zdot-kernel for steamroller
2015-04-09 09:45:23 +02:00
9299d8cfd6
added optimized cdot- and zdot-kernels for bulldozer
2015-04-08 16:29:55 +02:00
0a3d3b945d
Refs #535 . Fix the wrong vector instruction in sgemm sandy bridge kernel.
2015-04-08 03:55:49 +08:00
60c6dec6e6
updated some lines for bulldozer
2015-04-06 18:47:16 +02:00
47898cca35
added optimized saxpy- and daxpy-kernel for sandybridge
2015-04-06 16:05:16 +02:00
53bb924287
added optimized saxpy- and daxpy-kernel for haswell
2015-04-06 12:33:16 +02:00
a901b065d3
added optimized ddot-kernel for sandybridge
2015-04-05 20:19:38 +02:00
3937e2a0a0
add optimized sdot-kernel for sandybridge
2015-04-05 19:47:05 +02:00
9707d608d5
removed double definition line
2015-04-05 18:35:34 +02:00
701b9d7556
added optimized sdot- and ddot-kernel for HASWELL
2015-04-05 17:57:53 +02:00
e5b96e55a7
Fix build bug for ARM64.
2015-03-24 15:27:17 -05:00
84d90d6ed8
Fixed some compiler errors/warnings for clang.
2015-02-25 11:52:25 -06:00
518e2424a8
Fixed bad filename for cpuid.S compile.
2015-02-25 11:51:29 -06:00
ea7f9dacf4
Refs #509 . Fixed geadd building bug with DYNAMIC_ARCH=1.
2015-02-26 01:47:11 +08:00
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.
2015-02-24 12:26:33 -06:00
12d1fb2e40
Fixed incorrect object name in kernel CMakeLists.txt
2015-02-24 10:30:16 -06:00
1b7f427401
Added conj gemv objects for complex build.
2015-02-23 10:24:31 -06:00
b2284647a3
More complex objects.
2015-02-23 07:51:05 -06:00
a6116e5859
Added some more complex-only objects.
2015-02-22 17:49:28 -06:00
714638c187
Added some TRMM objects for complex types.
2015-02-19 16:11:51 -06:00
e27c372e53
Fixed reuse of float_char from parent loop.
...
Fixed in/it/on/otcopy names.
2015-02-19 13:53:29 -06:00
f3f2b3d768
Added complex and single netlib-lapack fortran sources to lapack.cmake.
2015-02-19 12:26:11 -06:00
9492298048
Added other float types to Makefile.L3.
2015-02-18 13:01:05 -06:00
14fd3d35de
Added checks for missing defines in kernel.
2015-02-18 10:25:01 -06:00
cebc07cebd
ParseMakefileVars now recursively parses included makefiles.
2015-02-17 22:09:41 -06:00
33c5e8db7f
Added a helper function for setting the L1 kernel defaults.
...
Added loop to build objects with different KERNEL defines.
2015-02-17 21:36:23 -06:00
39cc6b21d3
Add ATLAS-style ?geadd function
2015-02-16 13:46:20 +01:00
4662a0b13a
Changed generate functions to iterate through a list of float types.
...
This will generate obj files for SINGLE/DOUBLE/COMPLEX/DOUBLE COMPLEX.
2015-02-15 17:44:37 -06:00
162791e30e
Added common objects from kernel Makefile.
2015-02-10 12:42:05 -06:00
c0624a26be
Fixed some dgemm_copy function names.
2015-02-09 14:34:29 -06:00
4bfaf1ce66
Removed some list appends I missed.
2015-02-09 12:56:55 -06:00
e8c39138c6
Removed return value from GenerateNamedObjects.
...
It sets DBLAS_OBJS directly to save a bunch of list appending in the
CMakeLists.txt files.
2015-02-09 12:28:09 -06:00
f992799226
Added the rest of Makefile.L3.
2015-02-09 10:47:35 -06:00
4c65afcce1
Changed kernel filenames to vars. These will need to be read from KERNEL.
...
Added some kernel/L3 objects.
2015-02-09 09:52:14 -06:00
7fa5c4e2fd
Fixed some case issues with ARCH.
...
Added some kernel and driver/others objects.
2015-02-08 15:29:18 -06:00
fa0e6a6c93
Added the rest of the L1 kernel makefile.
2015-02-07 21:37:46 -06:00
38681fb1c6
Added more kernel files.
2015-02-07 12:54:30 -06:00
189fadfde0
Started implementing kernel/Makefile in cmake.
2015-02-05 21:05:11 -06:00
229ce2ccd1
Add cortex-a9 and cortex-a15 targets.
2015-01-12 08:55:29 +00:00
41aad0407f
Merge pull request #482 from jeromerobert/develop
...
Allow to do gemv and ger buffer allocation on the stack
2015-01-02 02:26:17 +08:00
ddf983d643
added optimizations for steamroller
2014-12-30 20:14:45 +08:00
4319769b79
added target processor STEAMROLLER
2014-12-28 20:16:46 +08:00
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
2014-12-27 14:33:12 +01:00
587e16fba3
Ref #458 : Backport, sandybrigde uses nehalem zgemm kernel
2014-12-22 17:01:18 +01:00
6261342de3
small optimization on dgemm_kernel for N=1
2014-12-18 20:35:51 +01:00
bc5fff7085
changed inline assembler labels to short form
2014-12-07 12:38:54 +01:00
0cf29ba6d2
Fixed a bug of sgemm sandy bridge kernel.
...
Reported by Julia project. JuliaLang/julia#9084
2014-12-03 17:38:41 +08:00
2fb02626da
Update organization info.
2014-11-25 15:28:58 +08:00
a85c2785ae
Refs #467 . Added generic kernel file for x86_64.
2014-11-24 15:34:48 +08:00
58c90d5937
# The first commit's message is:
...
Optimizations for APM's xgene-1 (aarch64).
1) general system updates to support armv8 better. Make all did not work, one needed to supply TARGET=ARMV8.
2) sgem 4x4 kernel in assembler using SIMD, and configuration changes to use it.
3) strmm 4x4 kernel in C. Since the sgem kernel does 4x4, the trmm kernel must also do 4xN.
Added Dave Nuechterlein to the contributors list.
2014-11-11 22:19:23 +08:00
7aae4a62e7
enabled use of GEMM3M functions
2014-09-20 14:27:10 +02:00
b7c9566eea
removed obsolete gemv kernel files
2014-09-14 11:00:53 +02:00
6df1b0be81
optimized zgemv_n_microk_sandy-4.c
2014-09-14 10:21:22 +02:00
2ac1e076c1
added optimized zgemv_n kernel for sandybridge
2014-09-14 09:02:05 +02:00
9908b6031c
bugfix in KERNEL.PILEDRIVER
2014-09-13 16:26:53 +02:00
8f100a14f2
optimized cgemv_t kernel for haswell
2014-09-13 16:13:27 +02:00
53b5726b04
added optimized cgemv_t kernel for haswell
2014-09-13 15:14:12 +02:00
Abdurrauf
Martin Kroeker
Ashwin Sekhar T K
Zhang Xianyi
Shivraj Patil
Werner Saar
Andrew Pinski
kaustubh
Andrew
Ashwin Sekhar T K
mdong
John Biddiscombe
Aleksey Kuleshov
Yichao Yu
Ralph Campbell
Martin Koehler
Matthew Brandyberry
Jerome Robert
Hank Anderson
Jerome Robert
Benedikt Huber