summaryrefslogtreecommitdiff
path: root/kernel/power
AgeCommit message (Expand)AuthorFilesLines
2019-07-01Merge pull request #2172 from quickwritereader/developMartin Kroeker7-251/+6416
2019-07-01cgemm/ctrmm power9AbdelRauf5-4/+6132
2019-06-25Fix build on FreeBSD/powerpc64.Piotr Kubaj86-190/+190
2019-06-19Update dtrmm_kernel_16x4_power8.Skavanabhat1-2/+0
2019-06-17new sgemm 8x16AbdelRauf2-247/+284
2019-06-06Merge pull request #2153 from quickwritereader/developMartin Kroeker8-744/+4460
2019-06-05conflict resolveAbdelRauf1-1/+1
2019-06-05power9 zgemm ztrmm optimizedAbdelRauf4-1305/+2597
2019-06-04sgemm pipeline improved, zgemm rewritten without inner packs, ABI lxvx v20 fi...AbdelRauf8-2416/+2062
2019-05-30improved zgemm power9 based on power8AbdelRauf6-22/+2800
2019-05-02Merge pull request #2107 from quickwritereader/developMartin Kroeker6-4/+8251
2019-05-01conflict resolveAbdelRauf3-7/+7
2019-04-29Merge branch 'develop' of https://github.com/quickwritereader/OpenBLAS into d...AbdelRauf2-2/+2
2019-04-29sgemm/strmmAbdelRauf4-3/+8250
2019-04-23Merge pull request #2072 from martin-frbg/sumMartin Kroeker2-0/+898
2019-04-09Add in runtime CPU detection for POWER.Rashmica Gupta2-32/+32
2019-03-30Add POWER implementation of ?sumMartin Kroeker2-0/+898
2019-03-29Merge branch 'develop' into developMartin Kroeker2-2/+2
2019-03-29power9 makefile. dgemm based on power8 kernel with following changes : 32x un...AbdelRauf28-27/+6063
2019-02-13Fix out-of-bounds memory access in gemm_betaMartin Kroeker1-1/+1
2019-02-13Fix out-of-bounds memory access in gemm_betaMartin Kroeker1-1/+1
2019-02-04Note for unused kernelsUbuntu2-0/+13
2019-02-04NBMAX=4096 for gemvn, added sgemvn 8x8 for futureUbuntu3-2/+509
2019-02-01sgemv cgemv pairsUbuntu10-32/+2691
2019-01-17crot fixUbuntu1-36/+54
2019-01-16Merge branch 'develop' into developAbdelrauf1-0/+3
2019-01-16Added missing Blas1 single fp {saxpy, caxpy, cdot, crot(refactored version of...Ubuntu11-48/+1802
2018-05-23Use the new zrot.c on POWER8 for crot as wellMartin Kroeker1-1/+1
2018-04-23Use generic zrot.c on ppc64/POWER6 to work around utest failure from … (#1535)Martin Kroeker1-0/+3
2018-03-27power8:Added initial zgemv_(t|n) ,i(d|z)amax,i(d|z)amin,dgemv_t(transposed),zrotQWR QWR9-8/+4454
2018-02-18dgemm_ncopy_4_ save/restorethe mslm2-249/+160
2018-02-16power8 ?gemm_tcopy save/restorethe mslm7-495/+238
2017-11-28Add trivially optimized DSDOT for POWER8martin2-9/+47
2017-09-28Save and restore VSX registersMartin Kroeker15-89/+884
2017-06-14Optimise sscal for POWER9Matt Brown1-40/+40
2017-06-14Optimise srot for POWER9Matt Brown1-32/+32
2017-06-14Optimise sdot for POWER9Matt Brown1-32/+32
2017-06-14Optimise sasum for POWER9Matt Brown1-16/+16
2017-06-14Optimise casum for POWER9Matt Brown1-16/+16
2017-06-14Optimise cswap for POWER9Matt Brown1-64/+64
2017-06-14Optimise sswap for POWER9Matt Brown1-32/+32
2017-06-14Optimise scopy for POWER9Matt Brown1-32/+32
2017-06-14Optimise ccopy for POWER9Matt Brown1-64/+64
2017-04-04Power8 inline assembly tweaksAlan Modra3-44/+45
2017-02-13Power8 inline assembly fixesMartin Kroeker38-3640/+3314
2016-09-29Remove explicit include of complex.hMartin Kroeker1-1/+0
2016-08-18Refs #946. Use nrm2 reference implementation for Power8.Zhang Xianyi1-4/+4
2016-08-18Refs #929. Deal with zero and NaNs for scale.Zhang Xianyi2-1/+18
2016-05-23optimized dtrsm_logic_LT_16x4_power8.S and dtrsm_macros_LT_16x4_power8.SWerner Saar2-338/+371
2016-05-22optimized dtrsm_kernel_LT for POWER8Werner Saar2-2/+45
generated by cgit v1.2.3 (git 2.25.1) at 2024-11-25 13:49:11 +0000