amd/blis
1
0
Fork 0
mirror of https://github.com/amd/blis.git synced 2026-05-11 09:39:59 +00:00
Code Issues Packages Projects Releases Wiki Activity

Imported skx dgemm ukernel from skx-redux branch.

Browse Source 
Details:
- Added the new bli_dgemm_skx_asm_16x14.c microkernel from the skx-redux
  branch, along with appropriate blocksizes in bli_cntx_init_skx.c and
  a prototype in bli_kernels_skx.h. (Devin has not yet written the
  sgemm analague, so for now we will continue using the older sgemm
  ukernel.)
- Updated frame/include/bli_x86_asm_macros.h with a minor change that
  was present within the skx-redux branch.
This commit is contained in:
Field G. Van Zee
2018-09-10 16:48:35 -05:00
parent e93b01ff60
commit e249a00a82
4 changed files with 468 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
frame/include/bli_x86_asm_macros.h
View File

@@ -647,6 +647,7 @@
#define SAR(...) INSTR_(sar, __VA_ARGS__)
#define SHLX(_0, _1, _2) INSTR_(shlx, _0, _1, _2)
#define SHRX(_0, _1, _2) INSTR_(shrx, _0, _1, _2)
#define RORX(_0, _1, _2) INSTR_(rorx, _0, _1, _2)
#define DEC(_0) INSTR_(dec, _0)
#define INC(_0) INSTR_(inc, _0)
@@ -659,6 +660,7 @@
#define sar(...) SAR(__VA_ARGS__)
#define shlx(_0, _1, _2) SHLX(_0, _1, _2)
#define shrx(_0, _1, _2) SHRX(_0, _1, _2)
#define rorx(_0, _1, _2) RORX(_0, _1, _2)
#define dec(_0) DEC(_0)
#define inc(_0) INC(_0)