diff mbox series

[FFmpeg-devel,v1,1/2,GSoC,2024] libavcode/x86/vvc: change label to vvc_sad_16 to reflect block sizes

Message ID 20240528190903.40811-3-chen.stonechen@gmail.com
State Accepted
Commit 55e9c758f07de6f40489a2fc5f2b35ab368329f0
Headers show
Series [FFmpeg-devel,v1,1/2,GSoC,2024] libavcode/x86/vvc: change label to vvc_sad_16 to reflect block sizes | expand

Checks

Context Check Description
yinshiyou/make_loongarch64 success Make finished
yinshiyou/make_fate_loongarch64 success Make fate finished
andriy/make_x86 success Make finished
andriy/make_fate_x86 success Make fate finished

Commit Message

Stone Chen May 28, 2024, 7:09 p.m. UTC 
According to the VVC specification (section 8.5.1), the maximum width/height of a subblock passed for DMVR SAD is 16. This along with previous constraint requiring width * height >= 128 means that  8x16, 16x8, and 16x16 are the only allowed sizes. This re-labels vvc_sad_16_128 to vvc_sad_16 to reflect this and adds a comment about the block size constraints. There's no functionality change.
---
 libavcodec/x86/vvc/vvc_sad.asm | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)
diff mbox series

Patch

diff --git a/libavcodec/x86/vvc/vvc_sad.asm b/libavcodec/x86/vvc/vvc_sad.asm
index b468d89ac2..982951a370 100644
--- a/libavcodec/x86/vvc/vvc_sad.asm
+++ b/libavcodec/x86/vvc/vvc_sad.asm
@@ -29,6 +29,7 @@  SECTION_RODATA
 pw_1: times 2 dw 1
 
 ; DMVR SAD is only calculated on even rows to reduce complexity
+; Additionally the only valid sizes are 8x16, 16x8, and 16x16
 SECTION .text
 
 %macro MIN_MAX_SAD 3
@@ -77,7 +78,7 @@  cglobal vvc_sad, 6, 9, 5, src1, src2, dx, dy, block_w, block_h, off1, off2, row_
     vpbroadcastd       m4, [pw_1]
 
     cmp          block_wd, 16
-    jge    vvc_sad_16_128
+    je         vvc_sad_16
 
     vvc_sad_8:
         .loop_height:
@@ -100,7 +101,7 @@  cglobal vvc_sad, 6, 9, 5, src1, src2, dx, dy, block_w, block_h, off1, off2, row_
         movd          eax, xm0
     RET
 
-    vvc_sad_16_128:
+    vvc_sad_16:
         sar      block_wd, 4
         .loop_height:
         mov         off1q, src1q