aboutsummaryrefslogtreecommitdiffhomepage
path: root/bench/QuickRejectBench.cpp
Commit message (Collapse)AuthorAge
* Optimized implementation of quickReject()Gravatar msarett2016-08-12
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Impl Overview (1) Keep the device clip bounds up to date. This requires minimal additional work in a few places throughout canvas. (2) Keep track of if the ctm isScaleTranslate. Yes, there's a function that does this, but it's slow to call. (3) Perform the src->device transform in quick reject, then check intersection/nan. Other Notes: (1) NaN and intersection checks are performed simultaneously. (2) We no longer quick reject infinity. (3) Affine and perspective are both handled in the slow case. (4) SkRasterClip::isEmpty() is handled by the intersection check. Performance on Nexus 6P: 93.2ms -> 59.8ms Overall Android Jank Tests Performance Impact: Should gain us a ms or two on some tests. BUG=skia: GOLD_TRYBOT_URL= https://gold.skia.org/search?issue=2225393002 Committed: https://skia.googlesource.com/skia/+/d22a817ff57986407facd16af36320fc86ce02da Review-Url: https://codereview.chromium.org/2225393002
* Revert of Optimized implementation of quickReject() (patchset #12 id:260001 ↵Gravatar mtklein2016-08-12
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | of https://codereview.chromium.org/2225393002/ ) Reason for revert: New assert triggering in the Chrome roll, https://build.chromium.org/p/tryserver.chromium.linux/builders/linux_chromium_asan_rel_ng/builds/208750/steps/webkit_unit_tests%20%28with%20patch%29%20on%20Ubuntu-12.04/logs/FrameThrottlingTest.SynchronousLayoutInAnimationFrameCallback and breaks the SKNX_NO_SIMD bot, https://codereview.chromium.org/2236363004 Original issue's description: > Optimized implementation of quickReject() > > Impl Overview > (1) Keep the device clip bounds up to date. This > requires minimal additional work in a few places > throughout canvas. > (2) Keep track of if the ctm isScaleTranslate. Yes, > there's a function that does this, but it's slow > to call. > (3) Perform the src->device transform in quick reject, > then check intersection/nan. > > Other Notes: > (1) NaN and intersection checks are performed > simultaneously. > (2) We no longer quick reject infinity. > (3) Affine and perspective are both handled in the slow > case. > (4) SkRasterClip::isEmpty() is handled by the intersection > check. > > Performance on Nexus 6P: > 93.2ms -> 59.8ms > > Overall Android Jank Tests Performance Impact: > Should gain us a ms or two on some tests. > > BUG=skia: > GOLD_TRYBOT_URL= https://gold.skia.org/search?issue=2225393002 > > Committed: https://skia.googlesource.com/skia/+/d22a817ff57986407facd16af36320fc86ce02da TBR=reed@google.com,herb@google.com,msarett@google.com # Skipping CQ checks because original CL landed less than 1 days ago. NOPRESUBMIT=true NOTREECHECKS=true NOTRY=true BUG=skia: Review-Url: https://codereview.chromium.org/2231393003
* Optimized implementation of quickReject()Gravatar msarett2016-08-11
Impl Overview (1) Keep the device clip bounds up to date. This requires minimal additional work in a few places throughout canvas. (2) Keep track of if the ctm isScaleTranslate. Yes, there's a function that does this, but it's slow to call. (3) Perform the src->device transform in quick reject, then check intersection/nan. Other Notes: (1) NaN and intersection checks are performed simultaneously. (2) We no longer quick reject infinity. (3) Affine and perspective are both handled in the slow case. (4) SkRasterClip::isEmpty() is handled by the intersection check. Performance on Nexus 6P: 93.2ms -> 59.8ms Overall Android Jank Tests Performance Impact: Should gain us a ms or two on some tests. BUG=skia: GOLD_TRYBOT_URL= https://gold.skia.org/search?issue=2225393002 Review-Url: https://codereview.chromium.org/2225393002