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!
This commit is contained in:
parent
bfaaa975e6
commit
f19af5ecc0
|
@ -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
|
||||
|
|
File diff suppressed because it is too large
Load Diff
Loading…
Reference in New Issue