OSchip
/
OpenBLAS
Not watched
1
0
Fork 0
Code
Releases 66 Wiki evaluate Activity
Issues 0 Pull Requests 0 Datasets Model Cloudbrain HPC
7452 Commits
51 Branches
78 MB
0 Download
Tree: 2d0b233425
Branches Tags
${ item.name }
Create branch ${ searchTerm }
from '2d0b233425'
${ noResults }
Commit Graph

2023 Commits (2d0b2334259d41c2003b51a07580dbd25cfe267c)

Author SHA1 Message Date
  Xianyi Zhang b95ad4cfaf Support detecting ICT Loongson-3B CPU. 14 years ago
  Xianyi Zhang 3bbe3ddb31 Merge branch 'develop' of github.com:xianyi/OpenBLAS into loongson3b 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
  traits 19f5b5c132 Fixed #66 the bug in zgemv kernel with transpose matrix on 64-bit MingW (Windows). 14 years ago
  traits c852ce3981 Ref #65. Fixed 64-bit Windows calling convention bug in cdot and zdot. 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
  Zhang Xiianyi 7b410b7f0e Fixed #58 zdot SEGFAULT bug with GCC-4.6. Thank Mr. John for this patch. 14 years ago
  traz d238a768ab Use ps instructions in cgemm. 14 years ago
  traits b1fe26c45a refs #55. Changed DTB_ENTRIES to DTB_DEFAULT_ENTRIES in x86 gemv_n kernel codes. 14 years ago
  traits 9fc6764fa7 refs #55. Added DTB_ENTRIES into dynamic arch setting parameters. Now, it can read DTB_ENTRIES on runtime. 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
  traz 68532fa9ec Merge branch 'loongson3a' of github.com:xianyi/OpenBLAS into loongson3a 14 years ago
  traz 708d2b6255 Fix compute error in ztrmm. 14 years ago
  traz e72113f06a Add ztrmm and ztrsm part on loongson3a. The average performance is 2.2G. 14 years ago
  traz 14f81da375 Change prefetch length of A and B, the performance is 2.1G now. 14 years ago
  Xianyi Zhang fc21f7ad28 Merge branch 'release-v0.1alpha2' into loongson3a 14 years ago
  traz 1c96d345e2 Improve zgemm performance from 1G to 1.8G, change block size in param.h. 14 years ago
  Xianyi Zhang c4efde7713 Merge branch 'loongson3a' into release-v0.1alpha2 14 years ago
  Xianyi Zhang 32353a9d30 Refs #20. Fixed the installation bug with DYNAMIC_ARCH=1. 14 years ago
  Xianyi Zhang b3d1887745 Fixed #35 a build bug with NO_LAPACK=1 DYNAMIC_ARCH=1 FC=gfortran. I forgot to test it with gfortran in last bug fixed commit. 14 years ago
  Xianyi Zhang 8d50a9fd1a Fixed #35 a build bug with NO_LAPACK=1 & DYNAMIC_ARCH=1. 14 years ago
  Wang Qian 4335bca2f7 Fixed #33 ztrmm bug on Nehalem. 14 years ago
  Xianyi 31040e4d80 Fixed #32 a SEGFAULT bug with gcc-4.6. According to i386 calling convention, The called funtion should remove the hidden return value address from the stack. 14 years ago
  traz 88d94d0ec8 Fixed #30 strmm computational error on Loongson3A. 14 years ago
  traz fc84909115 Modify single precision compiler conditions, increasing single precision kernel code on Loongson3a. 14 years ago
  traz 5ca4e51df0 Remove the useless code, modify code comments and format. 14 years ago
  Xianyi Zhang fcb5ce011b Fixed #28. Convert the result to double precision in MIPS64 dsdot_k kernel. 14 years ago
  traz a9320f896e Fixed #25 dtrmm and dtrsm computational error on Loongson3A. 14 years ago
  Xianyi Zhang b206fc7075 Fixed #28. Convert the result to double precision in the end of dsdot kernel. 14 years ago
  traz 29dce62b8f Finish dtrsm_kernel_Rx.S on Loongson3A. 14 years ago
  traz 432c309f63 Finish dtrsm_kernel_Lx.S on Loongson3A. 14 years ago
  traz d2f351d819 Modify dtrsm compiler options 14 years ago
  traz 5a991b7149 Fixed #24 drmm error on Loongson3A 14 years ago
  traz 9320933520 Completely dtrmm function. 14 years ago
  traz 921caefa56 Increased handling trmm part, no edge handling. Test size(M and N) must be a multiple of 4 . 14 years ago
  traz ecd4c1f3d9 Modify prefetching C. 14 years ago
  traz ab9e4ce351 Adjust kc size from 112 to 116 . 14 years ago