perf: increase preallocation vpmm size for halo2 - #621
Draft
Aalanli wants to merge 14 commits into
Draft
Conversation
* feat: enable cached root prover benchmark * fix: root prover bench after sdk suggestions * feat: add prove root benchmark to actions * fix: address comments * fix: add separate proof cache dir * fix: add separate proof cache dir * fix: update deps --------- Co-authored-by: Allan Lin <allanl@intrinsictech.xyz>
…rk CI sccache, cargo fingerprints, and host_cache_key all key on the literal RUSTFLAGS string, so with -Ctarget-cpu=native, artifacts built on one EC2 instance family are cache hits on another despite different machine code, causing SIGILL (e.g. AVX-512 code from g7e reused on g6e/Zen 3). Resolve "native" to the explicit host CPU name (e.g. znver3) before setting RUSTFLAGS, so the CPU identity flows into all three cache keys. Falls back to "native" if rustc cannot name the host CPU. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
The nightly toolchain was hardcoded in 5 places across the reth benchmark workflow and run.sh. Read the channel from rust-toolchain.toml instead so toolchain bumps only touch one file. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
g6e capacity has been limited; g7e is more available. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
shuklaayush
force-pushed
the
develop-v2.0.0-rc.2
branch
from
June 19, 2026 20:07
f2e1f54 to
0e19ad8
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Increases vpmm preallocation to get rid of first run warmup and page faults in halo2 prover. This makes the benchmark more representative of real-world use cases.
Default 16GB prealloc:

TODO: updated profile of 25 GB prealloc.