coffee/libyuv
1
0
Fork 0
mirror of https://chromium.googlesource.com/libyuv/libyuv synced 2026-11-09 14:49:57 +08:00
Code Issues Packages Projects Releases Wiki Activity

AArch64: Avoid LD4 in ScaleRowDown4_NEON

Browse Source 
ScaleRowDown4_NEON uses LD4 to extract the third entry from each four,
however LD4 is known to be slow on some micro-architectures and implies
overhead for performing the de-interleaving even for the unused vectors
v0/v1/v3.

Replace this with a single LD1 to load the vectors without
de-interleaving and then select the bytes we want with UZP instead.

Speedup versus the existing Neon implementation (higher is better):

 Cortex-A55: 1.004
  Cortex-X4: 1.873
Cortex-A720: 1.285
    C1-Nano: 1.330
     C1-Pro: 1.246
   C1-Ultra: 1.219

Change-Id: Ib7d8633635fa149b692e433062fc4b9717a32594
Reviewed-on: https://chromium-review.googlesource.com/c/libyuv/libyuv/+/8692146
Reviewed-by: richard winterton <rrwinterton@gmail.com>
Reviewed-by: Frank Barchard <fbarchard@google.com>
This commit is contained in:
George Steed 2026-09-27 18:53:50 +01:00 committed by Frank Barchard
parent 78277c25e6
commit 9e8c1ef826
1 changed files with 4 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
source/scale_neon64.cc
View File

@ -110,8 +110,11 @@ void ScaleRowDown4_NEON(const uint8_t* src_ptr,
(void)src_stride;
asm volatile(
"1: \n"
"ld4 {v0.16b,v1.16b,v2.16b,v3.16b}, [%0], #64 \n" // src line 0
"ld1 {v0.16b, v1.16b, v2.16b, v3.16b}, [%0], #64 \n"
"subs %w2, %w2, #16 \n" // 16 processed per loop
"uzp2 v0.8h, v0.8h, v1.8h \n"
"uzp2 v2.8h, v2.8h, v3.8h \n"
"uzp1 v2.16b, v0.16b, v2.16b \n"
"prfm pldl1keep, [%0, 448] \n" // prefetch 7 lines ahead
"st1 {v2.16b}, [%1], #16 \n"
"b.gt 1b \n"