82 Commits (a1ec94c258ac4151eb69012310e0f694f7067ea2)

Author SHA1 Message Date
  Martin Kroeker e5d2725e5a
Merge pull request #4185 from XiWeiGu/mips_enable_msa 1 year ago
  Martin Kroeker 7dd441d5db
Allow negative INCX (API change from version 3.10 of the reference implementation) 2 years ago
  gxw 4d0f000db6 MIPS: Enable MSA 2 years ago
  Martin Kroeker f6f35a4288
fix copyobj declarations to work with DYNAMIC_ARCH 3 years ago
  Martin Kroeker b1d69fb3ac
Add MIPS64_GENERIC as a copy of GENERIC 3 years ago
  gxw 365936ae1b MIPS64: Using the macro MTC rather than MTC1 3 years ago
  Jiaxun Yang a50b29c540 Provide a fallback MIPS64_GENERIC target 3 years ago
  gxw cce4b1d956 MIPS64: Fix dnrm2_tiny testcase failure 3 years ago
  gxw 4b548857d6 Add msa support for loongson 4 years ago
  gxw 8d07cf9b67 Fix compilation problem on loongson platform 5 years ago
  Martin Kroeker 07454bf4d5
Add proper defaults for IxMIN/IxMAX kernels 5 years ago
  Martin Kroeker 688fa9201c
Add MIPS64 implementation of ?sum 6 years ago
  Martin Kroeker 6c7b691083
Really revert xDOT changes from 1832 6 years ago
  Martin Kroeker 5f4c550c27
Merge pull request #1892 from martin-frbg/mipsdot 6 years ago
  Martin Kroeker 95a5542e3c
Revert DOT kernel changes from #1834 6 years ago
  Martin Kroeker 7a2e1bc804
Use generic kernel for DSDOT/SDSDOT 6 years ago
  fengruilin 43bb386b10 fix dot problem on 64bit mips 6 years ago
  fengrl 2d8064174c
register push/pop command change 7 years ago
  fengruilin 6fc85a6359 test_axpy work error on LOONGSON3A platform #1777 7 years ago
  Martin Kroeker 4e103c822c
typo fix 7 years ago
  Martin Kroeker d2142760e0
Fix precision problem in DSDOT 7 years ago
  Martin Kroeker 2fbfc64da8
Use C kernels for default c/zAXPY, xROT, c/zSWAP 7 years ago
  Shivraj Patil e3d844b062 Added mips I6500 core 8 years ago
  Shivraj Patil beb1d076a4 Added MSA optimization for GEMV_N, GEMV_T, ASUM, DOT functions 9 years ago
  Aleksey Kuleshov fca66262c4 mips64/axpy: fix error when INCY == 0 9 years ago
  Shivraj Patil 2c3dfe2bf3 MIPS P5600(32 bit) and I6400(64 bit) cores support added. 9 years ago
  Zhang Xianyi 2fb02626da Update organization info. 11 years ago
  Timothy Gu 6c2ead30f0 Remove all trailing whitespace except lapack-netlib 11 years ago
  Wang Qian 8e53b57bb2 Appending gemmkernel and trmmkernel C code in kernel/generic, this code can be used to execute on a new platform which dose not have optimized assemble kernel. 13 years ago
  Wang Qian 66904fc4e8 BLAS3 used standard MIPS instructions without extensions on Loongson 3B. 14 years ago
  Xianyi Zhang 0884f6b78d Merge branch 'loongson3a' of github.com:xianyi/OpenBLAS into loongson3b 14 years ago
  traz 2d78fb05c8 Add conjugate condition to gemv. 14 years ago
  Xianyi Zhang b95ad4cfaf Support detecting ICT Loongson-3B CPU. 14 years ago
  traz a32e56500a Fix the compute error of gemv when incx and incy are negative numbers. 14 years ago
  traz c1e618ea2d Add complete gemv function on Loongson3a platform. 14 years ago
  traz e08cfaf9ca Complete all the complex single-precision functions of level3, but the performance needs further improve. 14 years ago
  traz ee4bb8bd25 Add ctrmm part in cgemm_kernel_loongson3a_4x2_ps.S. 14 years ago
  traz 7fa3d23dd9 Complete cgemm function, but no optimization. 14 years ago
  traz 9679dd077e Fix some compute error. 14 years ago
  traz d238a768ab Use ps instructions in cgemm. 14 years ago
  traz 74d4cdb81a Fix an illegal instruction for strmm_RTLU. 14 years ago
  traz 7906146836 Fix an error for strmm_LLTN. 14 years ago
  traz 3274ff47b8 Fix an error for strmm_LLTN. 14 years ago
  traz a059c553a1 Fix a compute error for strmm. 14 years ago
  traz 23e182ca7c Fix stack-pointer bug for strmm. 14 years ago
  traz a15bc95824 Add strmm part. 14 years ago
  traz 09f49fa891 Using PS instructions to improve the performance of sgemm and it is 4.2Gflops now. 14 years ago
  traz cb0214787b Modify compile options. 14 years ago
  traz 2e8cdd1542 Using ps instruction. 14 years ago
  traz c8360e3ae5 Complete all the plura single precision functions of level3 on Loongson3a, the performance is 2.3GFlops. 14 years ago