Poseidon wgpu/WASM speed-up backend #1168
Open
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Outdated suggestions cannot be applied.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.
Summary
This PR introduces an experimental
WebBackend
that off-loads the heaviest parts of Poseidon proving to the GPU viawgpu
. In early tests we observe ≈ 2 × speed-ups on Apple M3 Pro (Chrome /WASM) and up to ≈ 2.3 × on Windows 11 (Ryzen 7 7800X3D + RTX 4070 Ti, Chrome /WASM) compared with the currentSimdBackend
.more comments on hackmd : https://hackmd.io/@wiNfxgvfSc-Ln2DBfsvoqQ/SyY_THluxg
What’s in this PR
web
)extend_trace
)evaluate_constraint_quotients_on_domain
)SimdBackend
WebBackend
type lives alongside the existingSimdBackend
.constraint_framework/src/component.rs
– everything else is shared.air
.Benchmarks
Windows 11 - Ryzen 7 7800X3D + RTX 4070 Ti
Mac - Apple M3 Pro
The first pair of graphs compares the total Poseidon-prove pipeline when run on the
SimdBackend
versus the new GPU-acceleratedWebBackend
.extend_trace
andevaluate_constraint_quotients_on_domain
—to show the raw shader speed-up in isolation.How to Try It Out