Commit Graph

244 Commits

Author SHA1 Message Date
Martin Kroeker d92bd5be24
Update KERNEL.POWER8 2020-02-15 23:07:50 +01:00
Martin Kroeker 46e4b12946
Update KERNEL.POWER8 2020-02-15 23:06:51 +01:00
Martin Kroeker cafdd999b8
Update caxpy_power8.S 2020-02-13 22:44:09 +01:00
Martin Kroeker 92ca92a46c
Update caxpy_power8.S 2020-02-13 21:24:54 +01:00
Martin Kroeker 486c35c5dc
Update icamin_power8.S 2020-02-13 18:38:43 +01:00
Martin Kroeker 5ba3699f41
Update isamin_power8.S 2020-02-13 00:00:32 +01:00
Martin Kroeker 8eefa530cd
Update isamax_power8.S 2020-02-12 23:59:50 +01:00
Martin Kroeker de40d47edf
Update isamin_power8.S 2020-02-12 23:57:48 +01:00
Martin Kroeker 7c162b8a21
Update isamax_power8.S 2020-02-12 23:56:57 +01:00
Martin Kroeker 0544cbc806
Fix syntax of endianness conditional 2020-02-12 20:00:29 +01:00
Martin Kroeker 120d20731f
Fix syntax of endianness conditional 2020-02-12 19:58:42 +01:00
Martin Kroeker dc345d84df
Fix syntax of endianness conditional and add gcc version check for workaround 2020-02-12 19:56:52 +01:00
Martin Kroeker 1a6ea8ee6d
Merge pull request #2338 from kavanabhat/aix_mod
Changes to build on AIX in POWER8 mode
2019-12-09 17:54:49 +01:00
Martin Kroeker dd04143d4a
Merge pull request #2328 from martin-frbg/ppc9
Fix precompiled kernels on POWER9 and make their use conditional on (old) gcc version
2019-11-30 12:23:57 +01:00
Martin Kroeker dedd822d1a
Fix caxpy/caxpyc naming in localentry 2019-11-29 23:56:57 +01:00
Martin Kroeker 2181fb7047
Fix caxpy/caxpyc naming in localentry 2019-11-29 23:54:15 +01:00
Martin Kroeker a9b62c03f8
Substitute precompiled gcc7 codes only when gcc is older than 9.x 2019-11-29 23:49:50 +01:00
Anton Blanchard cf2a8e410c Fix SEGV in cdot_power9
We were corrupting r2 because the local entry wasn't being
setup correctly.
2019-11-26 21:55:04 -07:00
Martin Kroeker 08fa83aba2
Merge pull request #2312 from martin-frbg/power8be
Further Power8 big-endian corrections
2019-11-20 15:12:06 +01:00
Martin Kroeker cad0d150db
Define alternate kernels for big-endian POWER8 2019-11-17 23:12:10 +01:00
Martin Kroeker eba0aeb7cd
Fix compilation for big-endian POWER8 2019-11-17 22:58:32 +01:00
Martin Kroeker 0c07c356c1
Define alternate kernels for big-endian PPC440 2019-11-17 19:25:08 +01:00
Martin Kroeker b3ac6ee222
Define alternate kernels for big-endian PPC970
The altivec versions of SGEMM and CGEMM fail most test in LAPACK-TESTING when compiled for big endian, STRSM/CTRSM even cause segfaults. The rot kernels either fail the corresponding utest or lead to failures in LAPACK-TESTING.
2019-11-17 15:19:39 +01:00
Martin Kroeker 68597002ea
The assembly microkernel is not safe to use on ELFv1 2019-11-03 22:42:46 +01:00
Martin Kroeker d2a6285549
The assembly microkernel is not safe to use on ELFv1 2019-11-03 22:41:19 +01:00
Martin Kroeker d999688d1a
The assembly microkernel is not safe to use on ELFv1 2019-11-03 22:39:06 +01:00
Martin Kroeker 928fe1b28e
The assembly microkernel is not safe to use on ELFv1 2019-11-03 22:37:27 +01:00
Martin Kroeker 5e244d80f2
Merge pull request #2271 from quickwritereader/strmm_fix
fixed bug power9 strmm . BLAS-TESTER passes
2019-09-29 13:53:45 +02:00
AbdelRauf ede5efebab trmm fix 2019-09-29 02:28:34 +00:00
Martin Kroeker 596a22325a
Fix prologue of power9 assembly cdot(c) kernel to provide cdotc 2019-09-27 00:47:18 +02:00
Martin Kroeker 7f58f3ad0e
Fix mis-edits in the gcc-derived power8 caxpy kernel 2019-09-27 00:44:26 +02:00
Martin Kroeker 673e5a0495
Replace several POWER8/9 C kernels with their gcc7-generated assembly versions (#2263)
* Add gcc7-generated assembly files for POWER8/9 isa/ica-min/max and POWER9 caxpy

To work around internal compiler errors encountered when compiling the original C source with gcc 4 and 5, and wrong code generated by gcc 8.3.0

* Use gcc-generated assembly instead of original C sources

to work around internal compiler errors encountered with gcc 4.8/5.4 and wrong code generation by gcc 8.3

* Use gcc-generated assembly instead of the original C source

to work around internal compiler errors encountered with gcc 4.8 and 5.4, and wrong code generation by gcc 8.3

* Add gcc7-generated assembler version of caxpy for power8

to work around wrong code generated by gcc 8.3

* Handle CONJ define for caxpyc

* Handle CONJ define for caxpyc

* Add gcc7-generated assembly cdot for POWER9

* Use prebuilt assembly for POWER9 cdot

created with gcc 7.3.1 to work around ICE in older gcc versions

* Exclude POWER9 from DYNAMIC_ARCH when gcc versions is lower than 6

* Update Makefile.system

* Use PROLOGUE macro to ensure correct function name for DYNAMIC_ARCH

* Disable POWER9 with old gcc versions
2019-09-22 22:35:22 +02:00
Martin Kroeker f3c314550c
Merge pull request #2243 from quickwritereader/develop
possible cgemv,caxpy,cdot fix
2019-08-30 23:06:23 +02:00
AbdelRauf 847c20c9b7 fix uninitialized variables i 2019-08-30 11:14:55 +00:00
AbdelRauf 4c22828812 caxpy and cdot are using vec_vsx_ld 2019-08-30 04:09:15 +00:00
AbdelRauf e79712d969 cgemv using vec_vsx_ld instead of letting gcc to decide 2019-08-30 02:52:04 +00:00
AbdelRauf be09551cdf aligned 2019-08-29 23:22:23 +00:00
Kavana Bhat 3dc6b26eff AIX changes for Power8 2019-08-20 06:51:35 -05:00
Martin Kroeker 6b6c9b1441
Merge pull request #2172 from quickwritereader/develop
power9 cgemm/ctrmm. new sgemm 8x16
2019-07-01 21:06:02 +02:00
AbdelRauf a97b301aaa cgemm/ctrmm power9 2019-07-01 14:07:54 +00:00
Piotr Kubaj eebfeba768 Fix build on FreeBSD/powerpc64.
Signed-off-by: Piotr Kubaj <pkubaj@anongoth.pl>
2019-06-25 10:58:56 +02:00
kavanabhat a575f1e4c7
Update dtrmm_kernel_16x4_power8.S 2019-06-19 15:27:14 +05:30
AbdelRauf cdbfb891da new sgemm 8x16 2019-06-17 15:33:38 +00:00
Martin Kroeker a17cf36225
Merge pull request #2153 from quickwritereader/develop
improved power9 zgemm,sgemm
2019-06-06 07:42:56 +02:00
AbdelRauf 148c4cc5fd conflict resolve 2019-06-05 20:50:50 +00:00
AbdelRauf d0c3543c3f power9 zgemm ztrmm optimized 2019-06-05 20:07:16 +00:00
AbdelRauf a469b32cf4 sgemm pipeline improved, zgemm rewritten without inner packs, ABI lxvx v20 fixed with vs52 2019-06-04 07:11:30 +00:00
AbdelRauf 8fe794f059 improved zgemm power9 based on power8 2019-05-30 15:31:25 +00:00
Martin Kroeker 3f427c0cf9
Merge pull request #2107 from quickwritereader/develop
sgemm/strmm kernel for power9
2019-05-02 07:56:57 +02:00
AbdelRauf 47f892198c conflict resolve 2019-05-01 19:36:22 +00:00
AbdelRauf 628b335e83 Merge branch 'develop' of https://github.com/quickwritereader/OpenBLAS into develop 2019-04-29 08:57:44 +00:00
AbdelRauf 0f105dd8a5 sgemm/strmm 2019-04-29 08:49:50 +00:00
Martin Kroeker ccfb7ead15
Merge pull request #2072 from martin-frbg/sum
Add (C)BLAS extension ?sum
2019-04-23 20:11:36 +02:00
Rashmica Gupta bcdf1d4917 Add in runtime CPU detection for POWER. 2019-04-09 14:20:16 +10:00
Martin Kroeker 706dfe263b
Add POWER implementation of ?sum
as trivial copy of ?asum with the fabs replaced by fmr to preserve code structure
2019-03-30 22:23:42 +01:00
Martin Kroeker 7c51cc8527
Merge branch 'develop' into develop 2019-03-29 19:36:29 +01:00
AbdelRauf 853a18bc17 power9 makefile. dgemm based on power8 kernel with following changes : 32x unrolled 16x4 kernel and 8x4 kernel using (lxv stxv butterfly rank1 update). improvement from 17 to 22-23gflops. dtrmm cases were added into dgemm itself 2019-03-29 15:49:40 +00:00
Martin Kroeker 718efcec6f
Fix out-of-bounds memory access in gemm_beta
Fixes #2011 (as suggested by davemq), assuming typo by K.Goto
2019-02-13 22:08:37 +01:00
Martin Kroeker f9d67bb5e8
Fix out-of-bounds memory access in gemm_beta
Fixes #2011 (as suggested by davemq) presuming typo by K.Goto
2019-02-13 22:06:41 +01:00
Ubuntu 498ac98581 Note for unused kernels 2019-02-04 15:41:56 +00:00
Ubuntu cd9ea45463 NBMAX=4096 for gemvn, added sgemvn 8x8 for future 2019-02-04 06:57:11 +00:00
Ubuntu 4abc375a91 sgemv cgemv pairs 2019-02-01 13:45:00 +00:00
Ubuntu 43a4572038 crot fix 2019-01-17 14:45:31 +00:00
Abdelrauf a034e65512
Merge branch 'develop' into develop 2019-01-16 19:25:13 +04:00
Ubuntu 8c3386be87 Added missing Blas1 single fp {saxpy, caxpy, cdot, crot(refactored version of srot),isamax ,isamin, icamax, icamin},
Fixed idamin,icamin choosing the first occurance index of equal minimals
2019-01-16 15:16:21 +00:00
Martin Kroeker 961d25e9c7
Use the new zrot.c on POWER8 for crot as well
fixes #1571 (the old zrot.S assembly does not handle incx=0 correctly)
2018-05-23 22:54:39 +02:00
Martin Kroeker 8a3b6fa108
Use generic zrot.c on ppc64/POWER6 to work around utest failure from … (#1535)
* Use generic C implementation of zrot on ppc64/POWER6 to work around utest failure from #1469
2018-04-23 19:05:49 +02:00
QWR QWR 28ca97015d power8:Added initial zgemv_(t|n) ,i(d|z)amax,i(d|z)amin,dgemv_t(transposed),zrot
z13: improved zgemv_(t|n)_4,zscal,zaxpy
2018-03-27 14:54:41 +00:00
the mslm 2c0a008281 dgemm_ncopy_4_ save/restore 2018-02-18 01:30:17 +00:00
the mslm c5425daa6b power8 ?gemm_tcopy save/restore 2018-02-16 23:36:46 +00:00
martin 7a4b3cfbf8 Add trivially optimized DSDOT for POWER8 2017-11-28 18:38:07 +01:00
Martin Kroeker 9c017a2218 Save and restore VSX registers 2017-09-28 12:17:09 +02:00
Matt Brown bd831a03a8 Optimise sscal for POWER9
Use lxvd2x instruction instead of lxvw4x.
lxvd2x performs far better on the new POWER architecture than lxvw4x.
2017-06-14 17:02:46 +10:00
Matt Brown edc97918f8 Optimise srot for POWER9
Use lxvd2x instruction instead of lxvw4x.
lxvd2x performs far better on the new POWER architecture than lxvw4x.
2017-06-14 17:02:35 +10:00
Matt Brown e0034de22d Optimise sdot for POWER9
Use lxvd2x instruction instead of lxvw4x.
lxvd2x performs far better on the new POWER architecture than lxvw4x.
2017-06-14 17:02:19 +10:00
Matt Brown 32c7fe6bff Optimise sasum for POWER9
Use lxvd2x instruction instead of lxvw4x.
lxvd2x performs far better on the new POWER architecture than lxvw4x.
2017-06-14 17:02:10 +10:00
Matt Brown 19bdf9d52b Optimise casum for POWER9
Use lxvd2x instruction instead of lxvw4x.
lxvd2x performs far better on the new POWER architecture than lxvw4x.
2017-06-14 17:00:07 +10:00
Matt Brown 4f09030fdc Optimise cswap for POWER9
Use lxvd2x instruction instead of lxvw4x.
lxvd2x performs far better on the new POWER architecture than lxvw4x.
2017-06-14 16:59:53 +10:00
Matt Brown 6f4eca5ea4 Optimise sswap for POWER9
Use lxvd2x instruction instead of lxvw4x.
lxvd2x performs far better on the new POWER architecture than lxvw4x.
2017-06-14 16:59:13 +10:00
Matt Brown be55f96cbd Optimise scopy for POWER9
Use lxvd2x instruction instead of lxvw4x.
lxvd2x performs far better on the new POWER architecture than lxvw4x.
2017-06-14 16:59:13 +10:00
Matt Brown 96dd0ef4f7 Optimise ccopy for POWER9
Use lxvd2x instruction instead of lxvw4x.
lxvd2x performs far better on the new POWER architecture than lxvw4x.
2017-06-14 16:58:59 +10:00
Alan Modra dc40bc7368 Power8 inline assembly tweaks
Further fixes on top of 9e2f316ed.  Writing some doco for gcc on
inline assembly woke me up to some more errors.

- dgemv_kernel_4x4 asm did not mention *ap as a memory input, and
  *y is both read and write.
- sasum_kernel_32 and casum_kernel_16 did not use %x for a vsx insn
  operand, a problem if the "=f" sum output was ever allocated a vsx
  reg in the altivec set.  This might be possible with inlining and
  future gcc optimisation.
2017-04-04 23:13:54 +09:30
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
2017-02-13 23:38:50 +01:00
Martin Kroeker a6e9e0b94b Remove explicit include of complex.h 2016-09-29 23:43:28 +02:00
Zhang Xianyi 515bc56ea9 Refs #946. Use nrm2 reference implementation for Power8. 2016-08-18 18:59:43 -07:00
Zhang Xianyi ae70b916f4 Refs #929. Deal with zero and NaNs for scale. 2016-08-18 10:24:42 -07:00
Werner Saar 412bcd187a optimized dtrsm_logic_LT_16x4_power8.S and dtrsm_macros_LT_16x4_power8.S 2016-05-23 11:20:41 +02:00
Werner Saar 8b140220c8 optimized dtrsm_kernel_LT for POWER8 2016-05-22 15:20:04 +02:00
Werner Saar 8fb5a1aaff added optimized dtrsm_LT kernel for POWER8 2016-05-22 13:09:05 +02:00
Werner Saar 6a2bde7a2d optimized dgemm and dgetrf for POWER8 2016-05-17 14:45:27 +02:00
Werner Saar 8310d4d3f7 optimized dgemm for 20 threads 2016-05-16 14:14:25 +02:00
Werner Saar 56948dbf0f optimized dgemm for POWER8 2016-04-29 12:52:47 +02:00
Werner Saar 0d0c6f7d7d optimized dgemm for POWER8 2016-04-27 14:01:08 +02:00
Werner Saar a3da10662f added sgemm_tcopy_8_power8.S 2016-04-23 10:04:41 +02:00
Werner Saar d46f07bb4e added cgemm_tcopy_8_power8.S 2016-04-23 07:37:18 +02:00
Werner Saar 879a51165f Optimized zgemm and tested zgemm again 2016-04-22 13:07:12 +02:00
Werner Saar 9276c9012f Optimized sgemm and dgemm and tested again. 2016-04-21 11:37:57 +02:00
Werner Saar 0001260f4b optimized sgemm 2016-04-20 13:06:38 +02:00
Werner Saar 3c6294ca3d added optimized sgemm_tcopy for power8 2016-04-19 16:08:54 +02:00
Werner Saar e173c51c04 updated zgemm- and ztrmm-kernel for POWER8 2016-04-08 09:05:37 +02:00
Werner Saar 9c42f0374a Updated cgemm- and sgemm-kernel for POWER8 SMP 2016-04-07 15:08:15 +02:00
Werner Saar a51102e9b7 bugfixes for sgemm- and cgemm-kernel 2016-04-06 11:15:21 +02:00
Werner Saar c5b1fbcb2e updated optimized cgemm- and ctrmm-kernel for POWER8 2016-04-04 09:12:08 +02:00
Werner Saar d4c0330967 updated cgemm- and ctrmm-kernel for POWER8 2016-04-03 14:30:49 +02:00
Werner Saar 6a9bbfc227 updated sgemm- and strmm-kernel for POWER8 2016-04-02 17:16:36 +02:00
Werner Saar 68a69c5b50 added optimized dgemv_n kernel for POWER8 2016-03-30 11:10:53 +02:00
Werner Saar c2464a7c4a added optimized casum kernel for POWER8 2016-03-28 14:12:08 +02:00
Werner Saar 294f933869 added optimized zasum kernel for POWER8 2016-03-28 13:37:32 +02:00
Werner Saar f59c9bd6ef added optimized sasum kernel for POWER8 2016-03-28 12:44:25 +02:00
Werner Saar c53be46d78 added optimized dasum kernel for POWER8 2016-03-28 12:17:15 +02:00
Werner Saar 659ed16591 added otimized cswap and zswap kernels for POWER8 2016-03-27 18:31:37 +02:00
Werner Saar 35c98a3556 added optimized zscal kernel for POWER8 2016-03-27 16:31:50 +02:00
Werner Saar f1a5dd06c5 added optimized sscal kernel for POWER8 2016-03-27 11:05:56 +02:00
Werner Saar 35f1f21a7f added drot- and srot-kernel optimimized for POWER8 2016-03-27 08:57:11 +02:00
Werner Saar 3d9a50e841 added optimized sswap kernel for POWER8 2016-03-25 17:34:55 +01:00
Werner Saar 828c849b44 added optimized ccopy kernel for POWER8 2016-03-25 16:54:25 +01:00
Werner Saar ecc0bc9813 added optimized scopy kernel for POWER8 2016-03-25 16:06:56 +01:00
Werner Saar 12f209b7b0 added optimized zswap kernel for POWER8 2016-03-25 15:27:34 +01:00
Werner Saar 7316a87930 added optimized dswap kernel for POWER8 2016-03-25 14:35:43 +01:00
Werner Saar 0bff057a87 added optimized dcopy kernel for POWER8 2016-03-25 13:03:02 +01:00
Werner Saar 1e6cf9808c added optimized dscal kernel for POWER8 2016-03-25 09:42:08 +01:00
Werner Saar 55eda3813b added optimized zaxpy kernel for POWER8 2016-03-23 11:20:23 +01:00
Werner Saar 0664ba4c97 added optimized daxpy kernel for POWER8 2016-03-22 14:50:03 +01:00
Werner Saar 11c44dede1 added optimized sdot kernel for POWER8 2016-03-21 13:18:23 +01:00
Werner Saar 9e4584d069 added optimized zdot kernel for POWER8 2016-03-21 10:12:07 +01:00
Werner Saar cd9fafc054 ddot for POWER8: updated licence information 2016-03-20 11:19:27 +01:00
Werner Saar 84b92e6373 added optimized ddot kernel for POWER8 2016-03-20 11:06:06 +01:00
Werner Saar e1df5a6e23 fixed sgemm- and strmm-kernel 2016-03-18 12:12:03 +01:00
Werner Saar 5c658f8746 add optimized cgemm- and ctrmm-kernel for POWER8 2016-03-18 08:17:25 +01:00
Werner Saar dcd15b546c BUGFIX: KERNEL.POWER8 2016-03-14 14:36:59 +01:00
Werner Saar 96284ab295 added sgemm- and strmm-kernel for POWER8 2016-03-14 13:52:44 +01:00
Werner Saar cd5241d0cf modified KERNEL for power, to use the generic DSDOT-KERNEL 2016-03-06 09:07:24 +01:00
Werner Saar 085f215257 Modified assembly label name, so that they are hidden.
Added license informations.
2016-03-05 10:27:27 +01:00
Werner Saar 0afc76fd65 enabled gemm_beta assembly kernels 2016-03-04 15:01:15 +01:00
Werner Saar 91e1c5080c modified configuration, to use power6 sgemm kernel for power8 2016-03-04 13:38:57 +01:00
Werner Saar 73f04c2c72 enabled hemv assemly function for power8 2016-03-04 13:20:50 +01:00
Werner Saar 3e633152c6 enabled symv assembly kernels on power8 2016-03-04 13:08:18 +01:00
Werner Saar d5130ce7e3 enabled gemv assembly on power8 2016-03-04 12:53:31 +01:00
Werner Saar 4824b88fcb enabled all level1 assembly kernels for power8 2016-03-04 12:35:25 +01:00
Werner Saar b752858d6c added dgemm-, dtrmm-, zgemm- and ztrmm-kernel for power8 2016-03-01 07:33:56 +01:00
Zhang Xianyi 3e8d6ea74f Init POWER8 kernels by POWER6. 2015-11-03 12:34:23 +08:00
Matthew Brandyberry 7ba4fe5afb ppc64le platform support (ELF ABI v2) 2015-07-21 22:20:19 -05:00
Timothy Gu 6c2ead30f0 Remove all trailing whitespace except lapack-netlib
Signed-off-by: Timothy Gu <timothygu99@gmail.com>
2014-06-27 12:05:18 -07:00
Xianyi Zhang 342bbc3871 Import GotoBLAS2 1.13 BSD version codes. 2011-01-24 14:54:24 +00:00