diff options
| author | ericrk <ericrk@chromium.org> | 2015-12-16 14:39:37 -0800 |
|---|---|---|
| committer | Commit bot <commit-bot@chromium.org> | 2015-12-16 22:40:46 +0000 |
| commit | 3b4338fc32cf20703baa8066bdad7ce07c5ae696 (patch) | |
| tree | 32a7cc1a202d3c68836bc5902b70b92ae525c1f0 /cc/cc.gyp | |
| parent | b8207ad6c963446716e84d265c03c8d7e90508d9 (diff) | |
| download | chromium_src-3b4338fc32cf20703baa8066bdad7ce07c5ae696.zip chromium_src-3b4338fc32cf20703baa8066bdad7ce07c5ae696.tar.gz chromium_src-3b4338fc32cf20703baa8066bdad7ce07c5ae696.tar.bz2 | |
TaskGraphRunner Group support
Adds a group to TaskGraphRunner, this can be used by an
implementation along with priority in order to decide how to execute
tasks.
This is a prerequisite patch for thread affinity changes which are
coming in a follow-up.
This patch causes a moderate (~15%) regression in cc_perftests for TaskGraphRunner.
The main regressions I'm seeing are:
In ScheduleTasks, we're seeing an additional 3% time spent in operator[] for the two new maps vs ToT.
We're also seeing an additional 5.5% of time spent in test code which builds the task graph.
Other regressions are less clear, but probably have to do with the additional cost of ScheduleTasks in the function body itself (inlined looping).
BUG=
CQ_INCLUDE_TRYBOTS=tryserver.blink:linux_blink_rel
Committed: https://crrev.com/05ca4bc9df381e6345f9cf7ee29cdfa075be30c4
Cr-Commit-Position: refs/heads/master@{#365140}
Review URL: https://codereview.chromium.org/1489233003
Cr-Commit-Position: refs/heads/master@{#365646}
Diffstat (limited to 'cc/cc.gyp')
| -rw-r--r-- | cc/cc.gyp | 1 |
1 files changed, 1 insertions, 0 deletions
@@ -435,6 +435,7 @@ 'raster/single_thread_task_graph_runner.h', 'raster/synchronous_task_graph_runner.cc', 'raster/synchronous_task_graph_runner.h', + 'raster/task_category.h', 'raster/task_graph_runner.cc', 'raster/task_graph_runner.h', 'raster/task_graph_work_queue.cc', |