Adding Radeon support by controlling wave size #1729
+16
−8
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
seanofthemillers
force-pushed
the
feature/seanofthemillers/adding_radeon_support
branch
from
480d181
to
95de1dc
Compare
MrBurmark
reviewed
Sep 3, 2024
seanofthemillers
force-pushed
the
feature/seanofthemillers/adding_radeon_support
branch
from
95de1dc
to
8ca1d56
Compare
MrBurmark
reviewed
Oct 1, 2024
Comment on lines
80
to
87
| #ifdef RAJA_COMPILER_MSVC | ||
| // MSVC doesn't like taking a pointer to stack allocated data?!?! | ||
| varType *ptr = new varType[camp::get<Pos>(data.param_tuple).size()]; | ||
| camp::get<Pos>(data.param_tuple).set_data(ptr); | ||
| #else | ||
| varType Array[camp::get<Pos>(data.param_tuple).size()]; | ||
| camp::get<Pos>(data.param_tuple).set_data(&Array[0]); | ||
| #endif |
There was a problem hiding this comment.
This was to address a warning that pops up in clang 18 for dynamic stack variables. I can move to a separate issue, but it was small enough I thought I would just throw it in here.
There was a problem hiding this comment.
I was wondering if anyone knew if we'd gotten past the MSVC problem from the comment.
There was a problem hiding this comment.
Thinking about this a bit more are we really declaring a dynamically sized array in c++ or is our function to get the size just not constexpr?
There was a problem hiding this comment.
It would appear that the compiler is not treating it as compile time knowledge - I'm not sure why. Should I remove this change from this branch to be worked on separately?
MrBurmark
reviewed
Oct 1, 2024
MrBurmark
reviewed
Oct 1, 2024
seanofthemillers
force-pushed
the
feature/seanofthemillers/adding_radeon_support
branch
from
8ca1d56
to
314466a
Compare
seanofthemillers
force-pushed
the
feature/seanofthemillers/adding_radeon_support
branch
from
1aa7b05
to
f352a5f
Compare
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.
Summary
This is a feature. It adds a configuration time control parameter for the default wave size. On AMD MI cards this is generally 64, however on Radeon (gaming) cards this is usually 32. These changes will require the user to know if the card is setup for Wave32 or Wave64.
I also added a fix for the dynamically sized memory allocation which seems to trigger a lot of warnings for ROCm 6.2.
Design review (for API changes or additions---delete if unneeded)
On (date), we reviewed this PR. We discussed the design ideas:
This PR implements 1. and 3. It leaves out 2. for the following reasons