floraachy/OpenBLAS
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
4,456 Commits 47 Branches 64 Tags
06208c8d015d2429645b26c19e74909a861fbfd2
Commit Graph

4456 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Martin Kroeker
06208c8d01 Limit this fix to ELFv2 builds 2020-04-22 14:16:40 +02:00
Martin Kroeker
c90b28dee6 Export ELF_VERSION for use in powerpc kernel configurations 2020-04-22 14:14:20 +02:00
Martin Kroeker
6275b43918 Avoid duplicate printout of byte order and report ELF_VERSION 2020-04-22 14:12:27 +02:00
Martin Kroeker
f5c4c28b98 Work around POWER8BE bugs on FreeBSD (ELFv2) 
for #2299
 2020-04-21 17:17:17 +02:00
Martin Kroeker
568674477c Merge pull request #48 from xianyi/develop 
rebase
 2020-04-20 21:51:59 +02:00
Martin Kroeker
fa42588e1f Merge pull request #2565 from martin-frbg/mips24k 
Support MIPS32 24K family as P5600
 2020-04-20 17:13:53 +02:00
Martin Kroeker
8a6d26458b Merge pull request #2559 from RajalakshmiSR/shgemm 
Add half precision gemm for bfloat16 in OpenBLAS
 2020-04-19 22:09:55 +02:00
Martin Kroeker
db86f516b9 Merge pull request #2568 from martin-frbg/azure-win 
Add a Windows/CL build job to the Azure CI
 2020-04-19 19:06:33 +02:00
Martin Kroeker
aec353b5a7 Add a Windows/CL build to the Azure Ci configuration 2020-04-19 19:04:33 +02:00
Martin Kroeker
c62fbefad4 Merge pull request #2567 from xianyi/revert-2566-azurewin 
Revert "Add Windows build job on Azure CI"
 2020-04-19 19:01:58 +02:00
Martin Kroeker
04706e760d Revert "Add Windows build job on Azure CI (#2566)" 
This reverts commit e1e543b145.
 2020-04-19 19:00:37 +02:00
Martin Kroeker
e1e543b145 Add Windows build job on Azure CI (#2566) 
* Add Windows-CL build job on Azure
 2020-04-19 16:16:15 +02:00
Martin Kroeker
e55ec82bb9 Delete KERNEL.1004K 2020-04-19 15:44:30 +02:00
Martin Kroeker
7353ea5afc Delete KERNEL.24K 2020-04-19 15:44:19 +02:00
Martin Kroeker
6a04efb122 Rename KERNEL files to include MIPS prefix 2020-04-19 15:43:54 +02:00
Martin Kroeker
5afb66812f Update getarch.c 2020-04-19 14:55:31 +02:00
Martin Kroeker
0d18f231fc Update getarch.c 2020-04-19 13:52:58 +02:00
Martin Kroeker
2f4a8e5bc4 Rename the FORCE entries for 24K and 1004K to include the MIPS prefix 2020-04-19 13:22:19 +02:00
Martin Kroeker
4f70512b97 Update kernel.cmake 2020-04-19 08:10:26 +02:00
Martin Kroeker
8792fc4d5f Disable RPCC macro on MIPS24K 2020-04-19 07:21:48 +02:00
Martin Kroeker
577c5d9f8f Update README.md 2020-04-19 06:54:52 +02:00
Martin Kroeker
6721f2750e Update TargetList.txt 2020-04-19 06:51:57 +02:00
Martin Kroeker
b0b02a080d Add compiler options for MIPS32 24K/1004K 2020-04-19 06:50:51 +02:00
Martin Kroeker
a1fc98dc57 rename 1004K, 24K to MIPS1004K, MIPS24K to avoid identifier naming problem 2020-04-18 23:50:23 +02:00
Martin Kroeker
d0737b0142 Update kernel.cmake 2020-04-18 21:36:28 +02:00
Martin Kroeker
7dbb59b256 Update common_macro.h 2020-04-18 21:34:14 +02:00
Martin Kroeker
00172d440b Typo fix in MIPS24K addition 2020-04-18 21:16:49 +02:00
Martin Kroeker
d712ea724c Add MIPS24K support 2020-04-18 21:10:18 +02:00
Martin Kroeker
61bbae3ac1 Handle MIPS24K like P5600 
and allow enforcing TARGET=1004K as well (omission from earlier 1004K merge and later introduction of TARGET check)
 2020-04-18 21:09:32 +02:00
Martin Kroeker
1c1ca2bc0a Merge pull request #47 from xianyi/develop 
rebase
 2020-04-18 21:07:14 +02:00
Martin Kroeker
c7d668c248 Update common_macro.h 2020-04-18 16:04:38 +02:00
Martin Kroeker
a83a59b038 Use generic kernels for ishama,shasum,shdot,shrot 2020-04-18 15:53:51 +02:00
Martin Kroeker
0a19bd813c Use generic codes for shamax and shcopy 2020-04-18 12:52:51 +02:00
Martin Kroeker
e7afe8a969 Define AXPBY_K fallback for float16 2020-04-18 11:10:15 +02:00
Martin Kroeker
f361de30a3 Use generic axpy.c for SHAXPY as x86 lacks saxpy.c 2020-04-18 11:07:16 +02:00
Martin Kroeker
9f6d6f6cb6 use saxpy.c instead of axpy.S for SHAXPY 2020-04-17 22:27:58 +02:00
Rajalakshmi Srinivasaraghavan
22bb50fb81 cmake fixes 2020-04-17 13:35:17 -05:00
Martin Kroeker
236a3d8ce6 Merge pull request #2563 from zelong-1024/develop 
[OpenBLAS]: benchmark error of potrf
 2020-04-16 11:45:32 +02:00
l00536773
6b7ef6543a [OpenBLAS]: benchmark error of potrf 
[description]: when the matrix size goes higher than 5800 during the cpotrf test, error info, such as "Potrf info = 5679", will be returned on ARM64 and x86 machines. Uplo = L & F.
[solution]: changed the func for building the matrix so that the complex Hermitian matrix can stay positive definite during the computation.
[dts]:
 2020-04-16 10:55:10 +08:00
Rajalakshmi Srinivasaraghavan
67cc4b9e16 Fix warnings in clang and export symbol 2020-04-15 19:15:23 -05:00
Martin Kroeker
250e6f8039 Merge pull request #2557 from martin-frbg/dronebadge 
Update and reformat README
 2020-04-15 20:23:43 +02:00
Martin Kroeker
7a6d0016b0 Merge pull request #2556 from martin-frbg/epicdrone 
Add a drone.io multithread test for x86_64
 2020-04-15 20:23:17 +02:00
Martin Kroeker
e8e8a6e608 Restore USE_OPENMP in the x86 thread test 2020-04-15 19:26:12 +02:00
Martin Kroeker
579811fb6a Move all 19.04-based jobs back to ubuntu 18.04 2020-04-15 17:38:33 +02:00
Rajalakshmi Srinivasaraghavan
a87793e03c Fix DYNAMIC_ARCH compilation errors 2020-04-15 09:09:50 -05:00
Rajalakshmi Srinivasaraghavan
ac6a22ae78 Update header 2020-04-14 22:58:39 -05:00
Rajalakshmi Srinivasaraghavan
ff010f496e Build shgemm for all architecture 2020-04-14 20:38:53 -05:00
Rajalakshmi Srinivasaraghavan
7eb55504b1 RFC : Add half precision gemm for bfloat16 in OpenBLAS 
This patch adds support for bfloat16 data type matrix multiplication kernel.
For architectures that don't support bfloat16, it is defined as unsigned short
(2 bytes).  Default unroll sizes can be changed as per architecture as done for
SGEMM and for now 8 and 4 are used for M and N.  Size of ncopy/tcopy can be
changed as per architecture requirement and for now, size 2 is used.

Added shgemm in kernel/power/KERNEL.POWER9 and tested in powerpc64le and
powerpc64.  For reference, added a small test compare_sgemm_shgemm.c to compare
sgemm and shgemm output.

This patch does not cover OpenBLAS test, benchmark and lapack tests for shgemm.
Complex type implementation can be discussed and added once this is approved.
 2020-04-14 14:55:08 -05:00
Martin Kroeker
84a9614345 try x86_64 test without openmp 2020-04-14 19:18:35 +02:00
Martin Kroeker
b969533703 Add drone.io badge, mention EMAG8180 support, reformat the DYNAMIC_ARCH paragraph 2020-04-14 10:53:28 +02:00