Use full wave for all kernels except monolith#24
Open
doru1004 wants to merge 1 commit intoamd-integrationfrom
Open
Use full wave for all kernels except monolith#24doru1004 wants to merge 1 commit intoamd-integrationfrom
doru1004 wants to merge 1 commit intoamd-integrationfrom
Conversation
There was a problem hiding this comment.
Pull request overview
Updates constraint-solver kernel launch configuration to use a 64-thread block size (full wave on AMD GPUs) across the decomposed solver path and several core solver routines, while leaving the monolithic solver unchanged.
Changes:
- Switched multiple
ti.loop_config/qd.loop_configoccurrences fromblock_dim=32toblock_dim=64. - Kept the monolithic solve kernel at
block_dim=32(per PR intent).
Reviewed changes
Copilot reviewed 2 out of 2 changed files in this pull request and generated 1 comment.
| File | Description |
|---|---|
genesis/engine/solvers/rigid/constraint/solver_breakdown.py |
Updates decomposed-step kernels to use block_dim=64. |
genesis/engine/solvers/rigid/constraint/solver.py |
Updates several solver loops (Hessian/Cholesky + gradient update paths) to block_dim=64, leaving monolith at 32. |
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
doru1004
force-pushed
the
use-block-dim-64
branch
2 times, most recently
from
b02257a to
d4dca4e
Compare
|
Genesis tests pass locally, perf is statistically equivalent to amd-integration |
|
/run-ci |
1 similar comment
Collaborator
|
/run-ci |
Collaborator
|
This PR is not based on the latest amd-integration: use-block-dim-64...ROCm:Genesis:amd-integration |
doru1004
force-pushed
the
use-block-dim-64
branch
from
d4dca4e to
87ed791
Compare
doru1004
force-pushed
the
use-block-dim-64
branch
from
87ed791 to
7c199f2
Compare
Author
|
/run-ci |
This file contains hidden or 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
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.
On AMD GPUs the wave size is 64. Use it for all kernels except monolith (no effect).