[VL] Add concurrency control to GpuLock#12090
Open
marin-ma wants to merge 2 commits into
Open
Conversation
|
Run Gluten Clickhouse CI on x86 |
|
Run Gluten Clickhouse CI on x86 |
1 similar comment
|
Run Gluten Clickhouse CI on x86 |
marin-ma
force-pushed
the
support-gpu-concurrency
branch
from
795e48f to
a3d9726
Compare
marin-ma
force-pushed
the
support-gpu-concurrency
branch
from
bd9eda7 to
b851138
Compare
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Currently, GPULock allows only one Spark task to acquire GPU resources at a time, which effectively makes GPU offloading run in single-threaded mode within a Spark executor. However, when testing the TPCDS queries, we observed that GPU utilization and memory usage can be very low (< 20%), meaning GPU resources are underutilized.
To improve GPU utilization, this PR adds support for running multiple GPU tasks concurrently through the configuration
spark.gluten.sql.columnar.backend.velox.cudf.concurrentGpuTasks. The default value is 1.