Browse Source

Refs #54. Added AMD Bulldozer x86_64 dgemm kernel developed by Werner Saar <wernsaar at googlemail.com>

Based on the dgemm kernel for AMD Barcelona, he used AVX and FMA4 instructions.
Thank Werner Saar!
tags/v0.2.6
Zhang Xianyi 13 years ago
parent
commit
f19af5ecc0
2 changed files with 1861 additions and 1 deletions
  1. +1
    -1
      kernel/x86_64/KERNEL.BULLDOZER
  2. +1860
    -0
      kernel/x86_64/dgemm_kernel_4x4_bulldozer.S

+ 1
- 1
kernel/x86_64/KERNEL.BULLDOZER View File

@@ -10,7 +10,7 @@ SGEMMINCOPYOBJ = sgemm_incopy$(TSUFFIX).$(SUFFIX)
SGEMMITCOPYOBJ = sgemm_itcopy$(TSUFFIX).$(SUFFIX)
SGEMMONCOPYOBJ = sgemm_oncopy$(TSUFFIX).$(SUFFIX)
SGEMMOTCOPYOBJ = sgemm_otcopy$(TSUFFIX).$(SUFFIX)
DGEMMKERNEL = gemm_kernel_4x4_barcelona.S
DGEMMKERNEL = dgemm_kernel_4x4_bulldozer.S
DGEMMINCOPY =
DGEMMITCOPY =
DGEMMONCOPY = gemm_ncopy_4_opteron.S


+ 1860
- 0
kernel/x86_64/dgemm_kernel_4x4_bulldozer.S
File diff suppressed because it is too large
View File


Loading…
Cancel
Save