AuroraMiddleware/skia2
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

Revert of Properly enable S32_D16_filter_DX_SSE2 optimization. (https://codereview.chromium.org/239453010/)

Browse Source 
Reason for revert:
Broke GMs in 565 mode. To repro:
out/Debug/gm --match filterbitmap_image_mandrill -w . --config 565
open filterbitmap_image_mandrill_512.png_565.png

Original issue's description:
> Properly enable S32_D16_filter_DX_SSE2 optimization.
>
> Currently, the S32_D16_filter_DX_SSE2 optimization is only used in
> configurations where the maximum SSE level is SSE2.
> This patch enables it for higher levels, as well.
> Also, refactored the function a bit, to make future modifications
> less error-prone.
>
> Author: henrik.smiding@intel.com
>
> Signed-off-by: Henrik Smiding <henrik.smiding@intel.com>
>
> Committed: http://code.google.com/p/skia/source/detail?r=14333

R=reed@google.com, mtklein@google.com, tomhudson@google.com, djsollen@google.com, joakim.landberg@intel.com, henrik.smiding@intel.com
TBR=djsollen@google.com, henrik.smiding@intel.com, joakim.landberg@intel.com, mtklein@google.com, reed@google.com, tomhudson@google.com
NOTREECHECKS=true
NOTRY=true

Author: bsalomon@google.com

Review URL: https://codereview.chromium.org/246393013

git-svn-id: http://skia.googlecode.com/svn/trunk@14336 2bbb7eff-a529-9590-31e7-b0007b416f81
This commit is contained in:
commit-bot@chromium.org 2014-04-23 20:07:19 +00:00
parent 74e608cdc1
commit c398f7156e
1 changed files with 32 additions and 40 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

72
src/opts/opts_check_SSE2.cpp
View File

@ -123,54 +123,46 @@ void SkBitmapProcState::platformConvolutionProcs(SkConvolutionProcs* procs) {
}
void SkBitmapProcState::platformProcs() {
/* Every optimization in the function requires at least SSE2 */
if (!cachedHasSSE2()) {
return;
}
/* Check fSampleProc32 */
if (fSampleProc32 == S32_opaque_D32_filter_DX) {
if (cachedHasSSSE3()) {
if (cachedHasSSSE3()) {
if (fSampleProc32 == S32_opaque_D32_filter_DX) {
fSampleProc32 = S32_opaque_D32_filter_DX_SSSE3;
} else {
fSampleProc32 = S32_opaque_D32_filter_DX_SSE2;
}
} else if (fSampleProc32 == S32_opaque_D32_filter_DXDY) {
if (cachedHasSSSE3()) {
fSampleProc32 = S32_opaque_D32_filter_DXDY_SSSE3;
}
} else if (fSampleProc32 == S32_alpha_D32_filter_DX) {
if (cachedHasSSSE3()) {
} else if (fSampleProc32 == S32_alpha_D32_filter_DX) {
fSampleProc32 = S32_alpha_D32_filter_DX_SSSE3;
} else {
fSampleProc32 = S32_alpha_D32_filter_DX_SSE2;
}
} else if (fSampleProc32 == S32_alpha_D32_filter_DXDY) {
if (cachedHasSSSE3()) {
if (fSampleProc32 == S32_opaque_D32_filter_DXDY) {
fSampleProc32 = S32_opaque_D32_filter_DXDY_SSSE3;
} else if (fSampleProc32 == S32_alpha_D32_filter_DXDY) {
fSampleProc32 = S32_alpha_D32_filter_DXDY_SSSE3;
}
} else if (cachedHasSSE2()) {
if (fSampleProc32 == S32_opaque_D32_filter_DX) {
fSampleProc32 = S32_opaque_D32_filter_DX_SSE2;
} else if (fSampleProc32 == S32_alpha_D32_filter_DX) {
fSampleProc32 = S32_alpha_D32_filter_DX_SSE2;
}
if (fSampleProc16 == S32_D16_filter_DX) {
fSampleProc16 = S32_D16_filter_DX_SSE2;
}
}
/* Check fSampleProc16 */
if (fSampleProc16 == S32_D16_filter_DX) {
fSampleProc16 = S32_D16_filter_DX_SSE2;
}
if (cachedHasSSSE3() || cachedHasSSE2()) {
if (fMatrixProc == ClampX_ClampY_filter_scale) {
fMatrixProc = ClampX_ClampY_filter_scale_SSE2;
} else if (fMatrixProc == ClampX_ClampY_nofilter_scale) {
fMatrixProc = ClampX_ClampY_nofilter_scale_SSE2;
}
/* Check fMatrixProc */
if (fMatrixProc == ClampX_ClampY_filter_scale) {
fMatrixProc = ClampX_ClampY_filter_scale_SSE2;
} else if (fMatrixProc == ClampX_ClampY_nofilter_scale) {
fMatrixProc = ClampX_ClampY_nofilter_scale_SSE2;
} else if (fMatrixProc == ClampX_ClampY_filter_affine) {
fMatrixProc = ClampX_ClampY_filter_affine_SSE2;
} else if (fMatrixProc == ClampX_ClampY_nofilter_affine) {
fMatrixProc = ClampX_ClampY_nofilter_affine_SSE2;
}
/* Check fShaderProc32 */
if (c_hqfilter_sse) {
if (fShaderProc32 == highQualityFilter32) {
fShaderProc32 = highQualityFilter_SSE2;
if (fMatrixProc == ClampX_ClampY_filter_affine) {
fMatrixProc = ClampX_ClampY_filter_affine_SSE2;
} else if (fMatrixProc == ClampX_ClampY_nofilter_affine) {
fMatrixProc = ClampX_ClampY_nofilter_affine_SSE2;
}
if (c_hqfilter_sse) {
if (fShaderProc32 == highQualityFilter32) {
fShaderProc32 = highQualityFilter_SSE2;
}
}
}
}