Issue metadata
Sign in to add a comment
|
12.4%-13.5% regression in angle_perftests at 548306:548369 |
||||||||||||||||||||||
Issue descriptionSee the link to graphs below.
,
Apr 6 2018
📍 Pinpoint job started. https://pinpoint-dot-chromeperf.appspot.com/job/11cdb4f8c40000
,
Apr 6 2018
😿 Pinpoint job stopped with an error. https://pinpoint-dot-chromeperf.appspot.com/job/11cdb4f8c40000
,
Apr 6 2018
Dale, any ideas why the job failed?
,
Apr 6 2018
,
Apr 7 2018
We were overloaded with Gitiles requests due to a data migration earlier today. It cleared up around noon PDT, so I'll re-run now.
,
Apr 7 2018
📍 Pinpoint job started. https://pinpoint-dot-chromeperf.appspot.com/job/158079f8c40000
,
Apr 7 2018
📍 Found significant differences after each of 2 commits. https://pinpoint-dot-chromeperf.appspot.com/job/158079f8c40000 Move Buffer Subject/Observer to front end. by jmadill@chromium.org https://chromium.googlesource.com/angle/angle/+/0946393dfd115f5d74abfc8ad4b8ef7b4d363503 Vulkan: Implement stencil test support by lucferron@chromium.org https://chromium.googlesource.com/angle/angle/+/364a95571eeb2829669c1abafc93808ab67b0b8b Understanding performance regressions: http://g.co/ChromePerformanceRegressions
,
Apr 9 2018
Unsure why pinpoint decided two CLs were possibly suspect. This is clearly because of Move Buffer Subject/Observer to front end. by jmadill@chromium.org https://chromium.googlesource.com/angle/angle/+/0946393dfd115f5d74abfc8ad4b8ef7b4d363503 Will investigate. Removing unrelated folks from cc.
,
Apr 9 2018
,
Apr 9 2018
The following revision refers to this bug: https://chromium.googlesource.com/angle/angle/+/0ce016c1bd12916c0d30c0ded96b29681a9e4d09 commit 0ce016c1bd12916c0d30c0ded96b29681a9e4d09 Author: Jamie Madill <jmadill@chromium.org> Date: Mon Apr 09 17:42:55 2018 FixedVector: Add "full" method. Will be useful for an optimization to the Buffer Subject/Observer pattern. Also cleans up an ASSERT. Bug: angleproject:2389 Bug: chromium:829906 Change-Id: I2f8313ab531bca61947a51cc2396c04fb5d4bb1d Reviewed-on: https://chromium-review.googlesource.com/1002883 Reviewed-by: Luc Ferron <lucferron@chromium.org> Reviewed-by: Lingfeng Yang <lfy@google.com> Reviewed-by: Jamie Madill <jmadill@chromium.org> Commit-Queue: Jamie Madill <jmadill@chromium.org> [modify] https://crrev.com/0ce016c1bd12916c0d30c0ded96b29681a9e4d09/src/common/FixedVector.h [modify] https://crrev.com/0ce016c1bd12916c0d30c0ded96b29681a9e4d09/src/common/FixedVector_unittest.cpp
,
Apr 10 2018
The following revision refers to this bug: https://chromium.googlesource.com/chromium/src.git/+/afadafa5a61f1166e24115e6e7c7ba5b7618a378 commit afadafa5a61f1166e24115e6e7c7ba5b7618a378 Author: angle-chromium-autoroll@skia-buildbots.google.com.iam.gserviceaccount.com <angle-chromium-autoroll@skia-buildbots.google.com.iam.gserviceaccount.com> Date: Tue Apr 10 01:02:21 2018 Roll src/third_party/angle/ bb52c5235..0ce016c1b (1 commit) https://chromium.googlesource.com/angle/angle.git/+log/bb52c523556e..0ce016c1bd12 $ git log bb52c5235..0ce016c1b --date=short --no-merges --format='%ad %ae %s' 2018-04-09 jmadill FixedVector: Add "full" method. Created with: roll-dep src/third_party/angle BUG= chromium:829906 The AutoRoll server is located here: https://angle-chromium-roll.skia.org Documentation for the AutoRoller is here: https://skia.googlesource.com/buildbot/+/master/autoroll/README.md If the roll is causing failures, please contact the current sheriff, who should be CC'd on the roll, and stop the roller if necessary. CQ_INCLUDE_TRYBOTS=luci.chromium.try:android_optional_gpu_tests_rel;luci.chromium.try:linux_optional_gpu_tests_rel;luci.chromium.try:mac_optional_gpu_tests_rel;master.tryserver.chromium.win:win_optional_gpu_tests_rel TBR=ynovikov@chromium.org Change-Id: I65c0cb6b4fd6df9da34cd3bbad338ac9d05b8b8a Reviewed-on: https://chromium-review.googlesource.com/1003315 Reviewed-by: angle-chromium-autoroll <angle-chromium-autoroll@skia-buildbots.google.com.iam.gserviceaccount.com> Commit-Queue: angle-chromium-autoroll <angle-chromium-autoroll@skia-buildbots.google.com.iam.gserviceaccount.com> Cr-Commit-Position: refs/heads/master@{#549356} [modify] https://crrev.com/afadafa5a61f1166e24115e6e7c7ba5b7618a378/DEPS
,
Apr 10 2018
The following revision refers to this bug: https://chromium.googlesource.com/angle/angle/+/3418fe80e4e953e0b5a066ff0c5a3580376476bb commit 3418fe80e4e953e0b5a066ff0c5a3580376476bb Author: Jamie Madill <jmadill@chromium.org> Date: Tue Apr 10 11:38:55 2018 Optimize Subject's binding method. Using FixedVector, we can remove the need for dynamic allocation in most of the use cases. Only when we exceed a certain amount of fixed storage do we need to spill into the heap. Bug: angleproject:2389 Bug: chromium:829906 Change-Id: Ib5f7073b58876bfd2400bd87b743bddcee5e5dc8 Reviewed-on: https://chromium-review.googlesource.com/1002884 Reviewed-by: Yuly Novikov <ynovikov@chromium.org> Reviewed-by: Luc Ferron <lucferron@chromium.org> Commit-Queue: Jamie Madill <jmadill@chromium.org> [modify] https://crrev.com/3418fe80e4e953e0b5a066ff0c5a3580376476bb/src/libANGLE/Observer.h [modify] https://crrev.com/3418fe80e4e953e0b5a066ff0c5a3580376476bb/src/libANGLE/Observer.cpp
,
Apr 10 2018
,
Apr 10 2018
The following revision refers to this bug: https://chromium.googlesource.com/chromium/src.git/+/fcb9565683b9bb2ca6c0330fa6cbdfa9da9ce170 commit fcb9565683b9bb2ca6c0330fa6cbdfa9da9ce170 Author: angle-chromium-autoroll@skia-buildbots.google.com.iam.gserviceaccount.com <angle-chromium-autoroll@skia-buildbots.google.com.iam.gserviceaccount.com> Date: Tue Apr 10 14:52:07 2018 Roll src/third_party/angle/ fe4bbe6cb..26084d0aa (3 commits) https://chromium.googlesource.com/angle/angle.git/+log/fe4bbe6cbec6..26084d0aae38 $ git log fe4bbe6cb..26084d0aa --date=short --no-merges --format='%ad %ae %s' 2018-04-09 jmadill Vulkan: Create TextureVk's Image lazily. 2018-04-09 jmadill Optimize Subject's binding method. 2018-03-30 jiawei.shao Use ShaderBitSet for active use bits on uniforms Created with: roll-dep src/third_party/angle BUG= chromium:829906 The AutoRoll server is located here: https://angle-chromium-roll.skia.org Documentation for the AutoRoller is here: https://skia.googlesource.com/buildbot/+/master/autoroll/README.md If the roll is causing failures, please contact the current sheriff, who should be CC'd on the roll, and stop the roller if necessary. CQ_INCLUDE_TRYBOTS=luci.chromium.try:android_optional_gpu_tests_rel;luci.chromium.try:linux_optional_gpu_tests_rel;luci.chromium.try:mac_optional_gpu_tests_rel;master.tryserver.chromium.win:win_optional_gpu_tests_rel TBR=ynovikov@chromium.org Change-Id: I56fc6e687699170e99bd4d210db0b1ac88aedf48 Reviewed-on: https://chromium-review.googlesource.com/1005023 Commit-Queue: angle-chromium-autoroll <angle-chromium-autoroll@skia-buildbots.google.com.iam.gserviceaccount.com> Reviewed-by: angle-chromium-autoroll <angle-chromium-autoroll@skia-buildbots.google.com.iam.gserviceaccount.com> Cr-Commit-Position: refs/heads/master@{#549528} [modify] https://crrev.com/fcb9565683b9bb2ca6c0330fa6cbdfa9da9ce170/DEPS
,
Apr 10 2018
,
Apr 11 2018
,
Apr 11 2018
The fix improved the regression on the buffer binding tests but didn't seem to help with the multiview tests or the Chromium regression. Looking again at these other tests.
,
Apr 11 2018
The following revision refers to this bug: https://chromium.googlesource.com/angle/angle/+/2dadd1d08e236de0a18c6f43ddebe61308d228d1 commit 2dadd1d08e236de0a18c6f43ddebe61308d228d1 Author: Jamie Madill <jmadill@chromium.org> Date: Wed Apr 11 14:13:12 2018 D3D11: Fix inactive attrib VAO perf regression. In the case there are any dirty inactive attributes, we were continually invalidating the Vertex Buffer and Input Layout bindings. This fixes the invalidation to only happen when there are any dirty active attributes. This regressed in "Move Buffer Subject/Observer to front end." Bug: chromium:829906 Bug: angleproject:2389 Change-Id: I8ed616bb696e0be548344192037ad6cc6f9c595c Reviewed-on: https://chromium-review.googlesource.com/1006998 Reviewed-by: Luc Ferron <lucferron@chromium.org> Reviewed-by: Jamie Madill <jmadill@chromium.org> Commit-Queue: Jamie Madill <jmadill@chromium.org> [modify] https://crrev.com/2dadd1d08e236de0a18c6f43ddebe61308d228d1/src/libANGLE/renderer/d3d/d3d11/VertexArray11.cpp [modify] https://crrev.com/2dadd1d08e236de0a18c6f43ddebe61308d228d1/src/libANGLE/renderer/d3d/d3d11/VertexArray11.h
,
Apr 11 2018
,
Apr 11 2018
Issue 830775 has been merged into this issue.
,
Apr 11 2018
More alerts in duplicate issues: https://chromeperf.appspot.com/group_report?bug_id=830775 https://chromeperf.appspot.com/group_report?bug_id=830665
,
Apr 11 2018
,
Apr 11 2018
,
Apr 12 2018
The following revision refers to this bug: https://chromium.googlesource.com/chromium/src.git/+/cd2b9676d2a45d84d784da927bbd75ee0e62f0fa commit cd2b9676d2a45d84d784da927bbd75ee0e62f0fa Author: angle-chromium-autoroll@skia-buildbots.google.com.iam.gserviceaccount.com <angle-chromium-autoroll@skia-buildbots.google.com.iam.gserviceaccount.com> Date: Thu Apr 12 01:01:30 2018 Roll src/third_party/angle/ ebd6e2df2..14f4817c4 (7 commits) https://chromium.googlesource.com/angle/angle.git/+log/ebd6e2df290a..14f4817c4dad $ git log ebd6e2df2..14f4817c4 --date=short --no-merges --format='%ad %ae %s' 2018-04-11 lucferron Vulkan: Simplify viewport / scissor updates 2018-04-11 cwallez cq.cfg: equivalent_to to 100% for Windows tryservers. 2018-04-11 jmadill D3D11: Fix inactive attrib VAO perf regression. 2018-03-31 jmadill Texture: Pass ImageIndex to relevant methods. 2018-04-08 jmadill Vulkan: Rename vk::LineLoopHelper. 2018-04-10 lucferron Vulkan: Cleanup some TODOs in TextureTest.cpp 2018-04-10 jdarpinian D3D11: Fix primitive topology dirty bit tracking. Created with: roll-dep src/third_party/angle BUG=chromium:815092, chromium:829906 , chromium:696345 The AutoRoll server is located here: https://angle-chromium-roll.skia.org Documentation for the AutoRoller is here: https://skia.googlesource.com/buildbot/+/master/autoroll/README.md If the roll is causing failures, please contact the current sheriff, who should be CC'd on the roll, and stop the roller if necessary. CQ_INCLUDE_TRYBOTS=luci.chromium.try:android_optional_gpu_tests_rel;luci.chromium.try:linux_optional_gpu_tests_rel;luci.chromium.try:mac_optional_gpu_tests_rel;luci.chromium.try:win_optional_gpu_tests_rel TBR=ynovikov@chromium.org Change-Id: Ib53f6489642caaae9657a7f69d4bd28c60527e19 Reviewed-on: https://chromium-review.googlesource.com/1008728 Reviewed-by: angle-chromium-autoroll <angle-chromium-autoroll@skia-buildbots.google.com.iam.gserviceaccount.com> Commit-Queue: Jamie Madill <jmadill@chromium.org> Cr-Commit-Position: refs/heads/master@{#549981} [modify] https://crrev.com/cd2b9676d2a45d84d784da927bbd75ee0e62f0fa/DEPS
,
Apr 12 2018
Graphs have recovered and even improved the score somewhat.
,
Aug 20
|
|||||||||||||||||||||||
►
Sign in to add a comment |
|||||||||||||||||||||||
Comment 1 by 42576172...@developer.gserviceaccount.com
, Apr 6 2018