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

optimized dtrsm_logic_LT_16x4_power8.S and dtrsm_macros_LT_16x4_power8.S

tags/v0.2.19^2
Werner Saar 10 years ago
parent
bd06b246cc
commit
412bcd187a
2 changed files with 375 additions and 342 deletions
Split View
Diff Options
Show Stats Download Patch File Download Diff File
  1. +5
    -8
      kernel/power/dtrsm_logic_LT_16x4_power8.S
  2. +370
    -334
      kernel/power/dtrsm_macros_LT_16x4_power8.S

+ 5
- 8
kernel/power/dtrsm_logic_LT_16x4_power8.S View File

@@ -54,29 +54,26 @@ DSTRM_LT_L4x16_LOOP_START:

addic. L, KK, 0
ble- DSTRM_LT_L4x16_SAVE
mtctr L

DSTRM_LT_L4x16_LOOP:

dcbt AO, PRE
dcbt BO, PRE
KERNEL_16x4
addic. L, L, -1
ble- DSTRM_LT_L4x16_SAVE
bdz- DSTRM_LT_L4x16_SAVE

dcbt AO, PRE
KERNEL_16x4
addic. L, L, -1
ble- DSTRM_LT_L4x16_SAVE
bdz- DSTRM_LT_L4x16_SAVE

dcbt AO, PRE
KERNEL_16x4
addic. L, L, -1
ble- DSTRM_LT_L4x16_SAVE
bdz- DSTRM_LT_L4x16_SAVE

dcbt AO, PRE
KERNEL_16x4
addic. L, L, -1
bgt+ DSTRM_LT_L4x16_LOOP
bdnz+ DSTRM_LT_L4x16_LOOP


DSTRM_LT_L4x16_SAVE:


+ 370
- 334
kernel/power/dtrsm_macros_LT_16x4_power8.S
File diff suppressed because it is too large
View File


Write Preview
Loading…
Cancel
Save