Add disk caching for Water backend via object files#1093
Open
Hardcode84 wants to merge 1 commit intoiree-org:mainfrom
Open
Add disk caching for Water backend via object files#1093Hardcode84 wants to merge 1 commit intoiree-org:mainfrom
Hardcode84 wants to merge 1 commit intoiree-org:mainfrom
Conversation
Hardcode84
force-pushed
the
water-backend-caching
branch
from
3694ae0 to
9660f5d
Compare
After JIT compilation, dump the host object file (which embeds the GPU binary) to the cache directory. On cache hit, load the .o directly into the execution engine, skipping MLIR parsing, LLVM IR translation, and host code compilation entirely. - Add ExecutionEngine::loadFromObjectFile (C++ + Python binding). - Enable object cache by default so dump_to_object_file works. - Include use_water_backend in cache hash to avoid collisions. - Add testWaterBackendCache covering miss, store, hit, and correctness. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> Signed-off-by: Ivan Butygin <ivan.butygin@gmail.com>
Hardcode84
force-pushed
the
water-backend-caching
branch
from
9660f5d to
1f97430
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
After JIT compilation, dump the host object file (which embeds the GPU binary) to the cache directory. On cache hit, load the .o directly into the execution engine, skipping MLIR parsing, LLVM IR translation, and host code compilation entirely.
This was the last significant functionality gap comparing to the current wave_runtime.