Chromium Code Reviews
chromiumcodereview-hr@appspot.gserviceaccount.com (chromiumcodereview-hr) | Please choose your nickname with Settings | Help | Chromium Project | Gerrit Changes | Sign out
(6)

Unified Diff: source/libvpx/vp8/encoder/x86/ssim_opt.asm

Issue 7671004: Update libvpx snapshot to v0.9.7-p1 (Cayuga). (Closed) Base URL: svn://chrome-svn/chrome/trunk/deps/third_party/libvpx/
Patch Set: '' Created 9 years, 4 months ago
Use n/p to move between diff chunks; N/P to move between comments. Draft comments are only viewable by you.
Jump to:
View side-by-side diff with in-line comments
Download patch
« no previous file with comments | « source/libvpx/vp8/encoder/x86/sad_ssse3.asm ('k') | source/libvpx/vp8/encoder/x86/subtract_sse2.asm » ('j') | no next file with comments »
Expand Comments ('e') | Collapse Comments ('c') | Show Comments Hide Comments ('s')
Index: source/libvpx/vp8/encoder/x86/ssim_opt.asm
===================================================================
--- source/libvpx/vp8/encoder/x86/ssim_opt.asm (revision 96967)
+++ source/libvpx/vp8/encoder/x86/ssim_opt.asm (working copy)
@@ -16,12 +16,12 @@
paddusw xmm14, xmm4 ; sum_r
movdqa xmm1, xmm3
pmaddwd xmm1, xmm1
- paddq xmm13, xmm1 ; sum_sq_s
+ paddd xmm13, xmm1 ; sum_sq_s
movdqa xmm2, xmm4
pmaddwd xmm2, xmm2
- paddq xmm12, xmm2 ; sum_sq_r
+ paddd xmm12, xmm2 ; sum_sq_r
pmaddwd xmm3, xmm4
- paddq xmm11, xmm3 ; sum_sxr
+ paddd xmm11, xmm3 ; sum_sxr
%endmacro
; Sum across the register %1 starting with q words
@@ -66,6 +66,7 @@
push rbp
mov rbp, rsp
SHADOW_ARGS_TO_STACK 9
+ SAVE_XMM 15
push rsi
push rdi
; end prolog
@@ -115,19 +116,20 @@
SUM_ACROSS_Q xmm11
mov rdi,arg(4)
- movq [rdi], xmm15;
+ movd [rdi], xmm15;
mov rdi,arg(5)
- movq [rdi], xmm14;
+ movd [rdi], xmm14;
mov rdi,arg(6)
- movq [rdi], xmm13;
+ movd [rdi], xmm13;
mov rdi,arg(7)
- movq [rdi], xmm12;
+ movd [rdi], xmm12;
mov rdi,arg(8)
- movq [rdi], xmm11;
+ movd [rdi], xmm11;
; begin epilog
pop rdi
pop rsi
+ RESTORE_XMM
UNSHADOW_ARGS
pop rbp
ret
@@ -154,6 +156,7 @@
push rbp
mov rbp, rsp
SHADOW_ARGS_TO_STACK 9
+ SAVE_XMM 15
push rsi
push rdi
; end prolog
@@ -174,11 +177,8 @@
NextRow2:
;grab source and reference pixels
- movq xmm5, [rsi]
- movq xmm6, [rdi]
-
- movdqa xmm3, xmm5
- movdqa xmm4, xmm6
+ movq xmm3, [rsi]
+ movq xmm4, [rdi]
punpcklbw xmm3, xmm0 ; low_s
punpcklbw xmm4, xmm0 ; low_r
@@ -197,19 +197,20 @@
SUM_ACROSS_Q xmm11
mov rdi,arg(4)
- movq [rdi], xmm15;
+ movd [rdi], xmm15;
mov rdi,arg(5)
- movq [rdi], xmm14;
+ movd [rdi], xmm14;
mov rdi,arg(6)
- movq [rdi], xmm13;
+ movd [rdi], xmm13;
mov rdi,arg(7)
- movq [rdi], xmm12;
+ movd [rdi], xmm12;
mov rdi,arg(8)
- movq [rdi], xmm11;
+ movd [rdi], xmm11;
; begin epilog
pop rdi
pop rsi
+ RESTORE_XMM
UNSHADOW_ARGS
pop rbp
ret
« no previous file with comments | « source/libvpx/vp8/encoder/x86/sad_ssse3.asm ('k') | source/libvpx/vp8/encoder/x86/subtract_sse2.asm » ('j') | no next file with comments »

Powered by Google App Engine
This is Rietveld 408576698