[async] [cuda] AsyncEngine now supports CUDA #1687
Merged
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
yuanming-hu
commented
Aug 12, 2020
| @@ -673,8 +673,6 @@ def to_numpy(self, keep_dims=False, as_vector=None): | |||
| ret = np.zeros(self.shape + shape_ext, dtype=to_numpy_type(self.dtype)) | |||
| from .meta import matrix_to_ext_arr | |||
| matrix_to_ext_arr(self, ret, as_vector) | |||
| import taichi as ti | |||
| ti.sync() | |||
There was a problem hiding this comment.
Not needed since we already synchronize in Kernel.__call__
Comment on lines
-99
to
+100
| static std::unordered_map<std::thread::id, CUDAContext *> instances; | ||
| static std::mutex mut; | ||
| { | ||
| // critical section | ||
| auto _ = std::lock_guard<std::mutex>(mut); | ||
|
|
||
| auto tid = std::this_thread::get_id(); | ||
| if (instances.find(tid) == instances.end()) { | ||
| instances[tid] = new CUDAContext(); | ||
| // We expect CUDAContext to live until the process ends, thus the raw | ||
| // pointers and `new`s. | ||
| } | ||
| return *instances[tid]; | ||
| } | ||
| static auto context = new CUDAContext(); | ||
| return *context; |
There was a problem hiding this comment.
I don't exactly remember why I had to create a standalone CUDAContext for each thread.
Creating a single context seems to work well.
| @@ -1,5 +1,7 @@ | |||
| #pragma once | |||
There was a problem hiding this comment.
Since now we have one CUDAContext shared by all threads, I add mutex to serialize the driver API calls.
Codecov Report
@@ Coverage Diff @@
## master #1687 +/- ##
==========================================
+ Coverage 43.78% 43.82% +0.03%
==========================================
Files 42 42
Lines 5940 5940
Branches 1023 1024 +1
==========================================
+ Hits 2601 2603 +2
+ Misses 3189 3187 -2
Partials 150 150
Continue to review full report at Codecov.
|
Merged
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Related issue = #742
[Click here for the format server]