OSchip
/
OpenBLAS
Not watched
1
0
Fork 0
Code
Releases 66 Wiki evaluate Activity
Issues 0 Pull Requests 0 Datasets Model Cloudbrain HPC
Browse Source

enabled optimized sgemv kernels for nehalem, sandybridge and bulldozer

tags/v0.2.10.rc1^2
wernsaar 12 years ago
parent
15d5dfa92c
commit
0517672dd0
3 changed files with 11 additions and 0 deletions
Split View
Diff Options
Show Stats Download Patch File Download Diff File
  1. +3
    -0
      kernel/x86_64/KERNEL.BULLDOZER
  2. +4
    -0
      kernel/x86_64/KERNEL.NEHALEM
  3. +4
    -0
      kernel/x86_64/KERNEL.SANDYBRIDGE

+ 3
- 0
kernel/x86_64/KERNEL.BULLDOZER View File

@@ -1,3 +1,6 @@
SGEMVNKERNEL = sgemv_n.S
SGEMVTKERNEL = sgemv_t.S

ZGEMVNKERNEL = zgemv_n_dup.S
ZGEMVTKERNEL = zgemv_t_dup.S



+ 4
- 0
kernel/x86_64/KERNEL.NEHALEM View File

@@ -1,3 +1,7 @@
SGEMVNKERNEL = sgemv_n.S
SGEMVTKERNEL = sgemv_t.S


SGEMMKERNEL = gemm_kernel_4x8_nehalem.S
SGEMMINCOPY = gemm_ncopy_4.S
SGEMMITCOPY = gemm_tcopy_4.S


+ 4
- 0
kernel/x86_64/KERNEL.SANDYBRIDGE View File

@@ -1,3 +1,7 @@
SGEMVNKERNEL = sgemv_n.S
SGEMVTKERNEL = sgemv_t.S


SGEMMKERNEL = gemm_kernel_4x8_nehalem.S
SGEMMINCOPY = gemm_ncopy_4.S
SGEMMITCOPY = gemm_tcopy_4.S


Write Preview
Loading…
Cancel
Save