Optimized PTX IntrinsicMath implementation to use LibDevice. #1189
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
MoFtZ
force-pushed
the
feature/xmath-libdevice
branch
2 times, most recently
from
46efee6 to
7454a8b
Compare
MoFtZ
force-pushed
the
feature/xmath-libdevice
branch
from
7454a8b to
152a938
Compare
m4rs-mt
reviewed
Apr 9, 2024
m4rs-mt
approved these changes
Apr 9, 2024
m4rs-mt
approved these changes
Apr 10, 2024
MoFtZ
added a commit
to MoFtZ/ILGPU
that referenced
this pull request
Apr 18, 2024
MoFtZ
added a commit
to MoFtZ/ILGPU
that referenced
this pull request
Apr 18, 2024
MoFtZ
added a commit
to MoFtZ/ILGPU
that referenced
this pull request
Apr 18, 2024
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Outdated suggestions cannot be applied.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.
Extracted from #1148.
Depends on #1187 and #1185.
PTXMath in ILGPU.Algorithms provides a number of math functions using Cordic implemenentations. However, these are considerably slower compared to LibDevice.
Currently, LibDevice methods need to be explicitly called.
This PR automatically tries to initialize LibDevice when the Context is being configured. If found, all the Math intrinsics are redirected to using LibDevice. The Cordic implementation in ILGPU.Algorithms will only activate itself if LibDevice is not available.