|
2d676313
|
2017-01-04T10:44:36
|
|
Refactor common functionality out of draw call perf tests
Common functionality across some perf tests is moved to a separate
utility file, draw_call_perf_utils.
This will make it simpler to add more perf tests, such as tests for
multiview drawing.
BUG=angleproject:1669
TEST=angle_perftests
Change-Id: I2108d7425f7d8f43f333ea9daa6779e42862350b
Reviewed-on: https://chromium-review.googlesource.com/422332
Commit-Queue: Olli Etuaho <oetuaho@nvidia.com>
Reviewed-by: Jamie Madill <jmadill@chromium.org>
|
|
cd1b1226
|
2016-06-16T13:58:54
|
|
perf_tests: Work around stalls in gl_null test teardown.
The Clear command in the draw call benchmark was not being properly
no-op'ed. This would cause the driver to get a huge queue of GL
command, which it would only flush when the test was torn down. This
manifested as a 5+ second stall on test teardown.
Looking at the clear command, it does some work with binding
and then calling GL functions, so properly filtering out the driver
commands would be a bit more complicated. For now, we can hack in a
workaround for the draw call test (the only one that uses the GL
NULL renderer at the moment) to not call clear when it would give
us problems.
BUG=620687
Change-Id: I64a2ed1883e8d3bf0d4c423c8bce0902ae9bf8df
Reviewed-on: https://chromium-review.googlesource.com/352828
Reviewed-by: Geoff Lang <geofflang@chromium.org>
|
|
|
193c671d
|
2016-06-09T07:09:58
|
|
Add a perf test for render-to-texture.
This perf test focuses on the hotspot we have in Framebuffer::
checkStatus. It's exactly the same as the standard draw call
benchmark, but binds a Framebuffer before rendering.
BUG=angleproject:1388
Change-Id: Icc7a99e399f469d765bf1ac6abe0562977b9a39d
Reviewed-on: https://chromium-review.googlesource.com/348956
Reviewed-by: Geoff Lang <geofflang@chromium.org>
Reviewed-by: Corentin Wallez <cwallez@chromium.org>
Commit-Queue: Jamie Madill <jmadill@chromium.org>
|
|
|
8047f065
|
2015-12-15T17:54:42
|
|
Improve perf testing framework
The ANGLERenderTest subclasses have a parameter "iterations". Previously
most of these tests would perform iterations^2 iterations, since the
looping was done both in ANGLERenderTest and in the individual test
classes. Do the looping only in the individual test classes instead.
This enables getting rid of separate beginDrawBenchmark() and
endDrawBenchmark() functions.
Some other unused code is also removed:
1. stepBenchmark function
2. unused parameters to step()
This makes the core loop of running tests simpler.
The perf testing framework also now has shared logic for deciding when
to end a given test.
The score calculation for tests is also changed. Instead of reporting
just the number of operations done, it is reported relative to the actual
run time of the test. This should make the test results more accurate,
since run time of the tests may have some variation. It also enables
changing the run time of the tests without rebaselining them.
In the tests that use GPU, GPU operations are also waited to finish
before stopping the timer.
BUG=angleproject:1261
TEST=angle_perftests
Change-Id: I69e9aad8afd2d9dedd60e144f0a5d4203618feef
Reviewed-on: https://chromium-review.googlesource.com/319381
Tryjob-Request: Olli Etuaho <oetuaho@nvidia.com>
Tested-by: Olli Etuaho <oetuaho@nvidia.com>
Reviewed-by: Jamie Madill <jmadill@chromium.org>
Reviewed-by: Zhenyao Mo <zmo@chromium.org>
|
|
|
fecbed9f
|
2015-12-17T12:01:12
|
|
Fix code style in perf tests
1) Format switch/case with git cl format
2) Change NULL -> nullptr
3) Change int to GLint where appropriate
4) Use more appropriate variants of asserts
BUG=angleproject:1261
TEST=angle_perftests
Change-Id: I97d6260dbd72ef3897fff145682b7043bf323b76
Reviewed-on: https://chromium-review.googlesource.com/319380
Tryjob-Request: Olli Etuaho <oetuaho@nvidia.com>
Tested-by: Olli Etuaho <oetuaho@nvidia.com>
Reviewed-by: Jamie Madill <jmadill@chromium.org>
|
|
84b0c3b7
|
2015-11-05T15:15:28
|
|
Re-land "In D3D, cache static vertex buffers to prevent wasteful recreation"
BUG=angleproject:197
Changes since first failed patch:
- Optimized BufferD3D::getStaticVertexBuffer()
- Removed loop to commit static buffers
- Out-of-date static buffers (which are much rarer anyway after this patch)
are marked for deletion at the *next* draw call, rather than searched for
before each draw call. That search was expensive.
The change should see a net improvement to DrawCallPerfBenchmark for D3D null.
Change-Id: If4942e0afd9e8fefadce8820a1305e13636547ef
Reviewed-on: https://chromium-review.googlesource.com/311115
Tested-by: Austin Kinross <aukinros@microsoft.com>
Tryjob-Request: Jamie Madill <jmadill@chromium.org>
Reviewed-by: Jamie Madill <jmadill@chromium.org>
Reviewed-by: Geoff Lang <geofflang@chromium.org>
|
|
|
5b58cae2
|
2015-11-05T14:51:47
|
|
Revert "In D3D, cache static vertex buffers to prevent wasteful recreation"
Perf bisect traced performance regression to this CL:
8.1% regression in angle_perftests/DrawCallPerf_d3d9_null/score
6.2% regression in angle_perftests/DrawCallPerf_d3d11_null/score
BUG=angleproject:197
This reverts commit 868651d334d060458af13c7ff9211c2f72be0cad.
Change-Id: Iaba7eb4e574eb886496361e61fd5fe78ca14dcb8
Reviewed-on: https://chromium-review.googlesource.com/311150
Tryjob-Request: Jamie Madill <jmadill@chromium.org>
Reviewed-by: Jamie Madill <jmadill@chromium.org>
Tested-by: Jamie Madill <jmadill@chromium.org>
|
|
|
868651d3
|
2015-08-31T15:31:18
|
|
In D3D, cache static vertex buffers to prevent wasteful recreation
BUG=angleproject:197
Change-Id: I66cd10609b2edbcf12b99530eafe1727511fe515
Reviewed-on: https://chromium-review.googlesource.com/296503
Reviewed-by: Jamie Madill <jmadill@chromium.org>
Tested-by: Austin Kinross <aukinros@microsoft.com>
Tested-by: Jamie Madill <jmadill@chromium.org>
|
|
f3357ee2
|
2015-07-22T14:10:19
|
|
EGLWindow: remove the unused width and height
EGLWindow does nothing with it per se, but some code was relying on it
to store it. Add width and height to ANGLETest and SampleApplication
instead. Also fix a typo in PerfTestParams, widowWidth -> windowWidth.
BUG=angleproject:1105
Change-Id: I26da607a2e6342864b508a50ee3cf8944608f868
Reviewed-on: https://chromium-review.googlesource.com/287379
Reviewed-by: Jamie Madill <jmadill@chromium.org>
Reviewed-by: Geoff Lang <geofflang@chromium.org>
Tested-by: Corentin Wallez <cwallez@chromium.org>
|
|
|
b76e350f
|
2015-06-11T16:01:45
|
|
Fix the broken draw call perf test.
This was broken by the angle test platforms refactor patch,
https://chromium-review.googlesource.com/#/c/276460/. It was
leading to the wrong tests be executed for the perf tests, and
also had bugs with supporting a default platform.
BUG=None
TEST=angle_perftests
Change-Id: Ib99342d4189fd98bf93dce088d15afcecc4a7e37
Reviewed-on: https://chromium-review.googlesource.com/277036
Tested-by: Jamie Madill <jmadill@chromium.org>
Reviewed-by: Zhenyao Mo <zmo@chromium.org>
|
|
dd323e95
|
2015-06-09T15:16:31
|
|
Only run tests that the current hardware can support.
For each config, determine if a context can be created at test
instantiation time. This allows skipping of ES3 tests when the hardware
does not support ES3.
Updated the perf_tests to use the EGLPlatformParameters struct so that
they can be filtered in the same way.
Change-Id: If664604b057cec4005eb4b63bebd83cd4964b7b2
Reviewed-on: https://chromium-review.googlesource.com/276460
Reviewed-by: Corentin Wallez <cwallez@chromium.org>
Tested-by: Geoff Lang <geofflang@chromium.org>
|
|
|
39fcf263
|
2015-06-08T14:39:07
|
|
Use both null and real renders for draw call perf.
Introduce a "null" GL renderer for this specific benchmark, which
does not do any work on drawArrays and drawElements. We could use
the same kind of trick for buffer and texture updates, if we need
it. This gives us a good baseline for comparing GL and D3D perf.
BUG=angleproject:1040
Change-Id: I4bf7c75df01932de45ddd0a4e42e8fc82f15e37e
Reviewed-on: https://chromium-review.googlesource.com/276192
Tested-by: Jamie Madill <jmadill@chromium.org>
Reviewed-by: Kenneth Russell <kbr@chromium.org>
Reviewed-by: Geoff Lang <geofflang@chromium.org>
|
|
|
80a50949
|
2015-05-21T10:54:14
|
|
Add perftest parameters for OpenGL
BUG=angleproject:892
Change-Id: Ia22b8ab48456d6fbccb159404e943f9ef2650bdc
Reviewed-on: https://chromium-review.googlesource.com/272610
Reviewed-by: Geoff Lang <geofflang@chromium.org>
Tested-by: Corentin Wallez <cwallez@chromium.org>
|
|
|
b45a80db
|
2015-05-21T10:39:43
|
|
Make perftests use ANGLE_INSTANTIATE_TEST
This also moves ANGLE_INSTANTIATE_TEST to its own header and makes it
generic over the type of test parameter.
BUG=angleproject:892
Change-Id: Id4e3929d7ad06964b3259015915be84a8ee414f9
Reviewed-on: https://chromium-review.googlesource.com/272553
Reviewed-by: Geoff Lang <geofflang@chromium.org>
Tested-by: Corentin Wallez <cwallez@chromium.org>
|
|
|
304dcde8
|
2015-04-15T14:26:36
|
|
perftests: Use gtest asserts macro helpers.
We still were using the old cassert code, with a boolean return
value on our initialization code. We can make use of the gtest
macros and helpers to check for a successful init or GL errors.
BUG=476658
Change-Id: I09cbb3d40748cbeaf530ae8f23fb8a1b07e7611f
Reviewed-on: https://chromium-review.googlesource.com/265837
Tested-by: Jamie Madill <jmadill@chromium.org>
Reviewed-by: Geoff Lang <geofflang@chromium.org>
Reviewed-by: Brandon Jones <bajones@chromium.org>
|
|
|
4a1858b8
|
2015-04-14T16:16:30
|
|
perftests: Fix simple draw call benchmark.
Previously the code was only testing the validation logic. Fix this
by testing validation-only and a simple single quad draw benchmark.
BUG=468852
Change-Id: I510deea08fee5932f51ea39883ed91652be476df
Reviewed-on: https://chromium-review.googlesource.com/265751
Reviewed-by: Brandon Jones <bajones@chromium.org>
Reviewed-by: Geoff Lang <geofflang@chromium.org>
Tested-by: Jamie Madill <jmadill@chromium.org>
|
|
|
835be965
|
2015-04-13T14:17:49
|
|
perf_tests: Only print final score result.
Don't print all the other measurements and values, since they'll
just add noise to the perf bot dashboards. Also increase the
run time of the DrawCallPerfTest to 10.0 seconds.
BUG=angleproject:744
BUG=468852
Change-Id: If076055ad46b4e6923f39687edcaa25930b188a7
Reviewed-on: https://chromium-review.googlesource.com/265464
Tested-by: Jamie Madill <jmadill@chromium.org>
Reviewed-by: Geoff Lang <geofflang@chromium.org>
|
|
|
99f075da
|
2015-04-01T15:48:07
|
|
Split DrawCallPerf test from BufferSubData test.
This will give us better dashboard encapsulation when we're
running on the Chromium bots. It also paves the way for more
specialized draw call tests, like for indexed draw, with uniform
updates, instancing, etc.
BUG=angleproject:744
Change-Id: I396de28c027f99da18a0904f959d23b59cac2010
Reviewed-on: https://chromium-review.googlesource.com/263505
Reviewed-by: Geoff Lang <geofflang@chromium.org>
Tested-by: Jamie Madill <jmadill@chromium.org>
|