Conversation
Collaborator
Author
|
@theodegeest might be interested as well |
Add a new-API benchmark for SPLASH-4, the m4/make-built suite of parallel kernels (FFT, LU, RADIX, OCEAN, BARNES, WATER, ...). The benchmark implements fetch/build/run/collect and covers all 15 kernels via a keyword-only Splash4Kernel registry. The kernel is a build-time variable: build() selects and compiles it and carries the resolved recipe to run() via BuildResult.other, so run() only declares the true run-time variables (nb_threads, input_size). Kernels differ in invocation (flag args, leading-positional threads, and stdin-fed inputs), so run() assembles the command from the registry and executes it via `bash -lc` where stdin redirection is needed. collect() returns a uniform schema (primary_time_us plus the with/without initialization times) so heterogeneous timing output aggregates into a non-ragged CSV; kernels without a single total (volrend) report None rather than failing the campaign point. Add run-once and explicit-workflow tests plus small and full Cartesian campaigns (all kernels x thread-count sweep). Signed-off-by: Antonio Paolillo <apaolill@gmail.com>
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
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Add a new-API benchmark for SPLASH-4, the m4/make-built suite of parallel kernels (FFT, LU, RADIX, OCEAN, BARNES, WATER, ...). The benchmark implements fetch/build/run/collect and covers all 15 kernels via a keyword-only Splash4Kernel registry.
The kernel is a build-time variable: build() selects and compiles it and carries the resolved recipe to run() via BuildResult.other, so run() only declares the true run-time variables (nb_threads, input_size). Kernels differ in invocation (flag args, leading-positional threads, and stdin-fed inputs), so run() assembles the command from the registry and executes it via
bash -lcwhere stdin redirection is needed.collect() returns a uniform schema (primary_time_us plus the with/without initialization times) so heterogeneous timing output aggregates into a non-ragged CSV; kernels without a single total (volrend) report None rather than failing the campaign point.
Add run-once and explicit-workflow tests plus small and full Cartesian campaigns (all kernels x thread-count sweep).