perf(vm): skip coverage and limit polls on production dispatch - #1216
Open
frostney wants to merge 2 commits into
Open
perf(vm): skip coverage and limit polls on production dispatch#1216frostney wants to merge 2 commits into
frostney wants to merge 2 commits into
Conversation
Prod bytecode dispatch now uses a dedicated loop head that skips stop-IP, coverage, opcode profiling, and instruction-limit polling, sharing one opcode case with the instrumented path. Co-authored-by: Cursor <cursoragent@cursor.com>
Accepted isolated lane on optimize/w2-prod-dispatch. Prod ExecuteRegisters skips stop-IP, coverage, profiler, and inactive instruction-limit polls while sharing one opcode case with the instrumented path.
Contributor
|
No actionable comments were generated in the recent review. 🎉 ℹ️ Recent review info⚙️ Run configurationConfiguration used: Organization UI Review profile: CHILL Plan: Pro Plus Run ID: 📒 Files selected for processing (8)
Included review availability: 3 reviews are currently available. Your included PR review attempts over the past 7 days set your current allowance at 5 reviews per hour. 📝 WalkthroughWalkthroughChangesInstruction-limit dispatch behavior
Estimated code review effort: 1 (Trivial) | ~5 minutes Merge Risk: ⚪ Minimal · up to The production dispatch path removes inactive instrumentation polls while preserving the shared opcode behavior; no actionable merge-blocking risk remains after normal checks and review. 🚥 Pre-merge checks | ✅ 5✅ Passed checks (5 passed)
Full details: Description checkExplanation The description includes the required Summary and Testing sections. It explains the implementation, constraints, non-goals, related stack references, test coverage, documentation updates, and benchmark results. Full details: Docstring CoverageExplanation No functions found in the changed files to evaluate docstring coverage. Skipping docstring coverage check. Docstring coverage is scoped to functions touched by this diff. Analyzed 0 functions across 0 files. (6 skipped: 6 unsupported.) Comment |
|
The latest updates on your projects. Learn more about Vercel for GitHub.
|
frostney
changed the title
Contributor
Web Tooling Benchmark
18 pinned Web Tooling workloads; 18 workloads produced at least one Goccia sample. Raw results from 1 sample per workload; full stdout/stderr for failures and min/max/CV stay in the |
Contributor
Suite TimingTest Runner (interpreted: 12,813 passed; bytecode: 12,813 passed)
MemoryGC rows aggregate the main thread plus all worker thread-local GCs. Test runner worker shutdown frees thread-local heaps in bulk; that shutdown reclamation is not counted as GC collections or collected objects.
Benchmarks (interpreted: 440; bytecode: 440)
MemoryGC rows aggregate the main thread plus all worker thread-local GCs. Benchmark runner performs explicit between-file collections, so collection and collected-object counts can be much higher than the test runner.
Boot
Empty-script ( Measured on ubuntu-latest x64. |
Contributor
Benchmark Results440 benchmarks · PR vs same-runner Interpreted: 🟢 22 improved · 🔴 34 regressed · 384 unchanged · avg +0.2% Typical per-run noise (median variance): interpreted ±1.7%, bytecode ±1.4%. Deltas within noise overlap and read as unchanged. arraybuffer.js — Interp: 🟢 3, 🔴 2, 9 unch. · avg +0.4% · Bytecode: 🟢 1, 13 unch. · avg +0.5%
arrays.js — Interp: 19 unch. · avg +0.3% · Bytecode: 🟢 4, 15 unch. · avg +1.1%
async-await.js — Interp: 6 unch. · avg -2.1% · Bytecode: 6 unch. · avg +1.8%
async-generators.js — Interp: 2 unch. · avg -1.8% · Bytecode: 2 unch. · avg -0.7%
atomics.js — Interp: 6 unch. · avg -2.1% · Bytecode: 🟢 3, 3 unch. · avg +2.6%
base64.js — Interp: 🔴 2, 8 unch. · avg -0.2% · Bytecode: 🟢 4, 6 unch. · avg +1.7%
classes.js — Interp: 🟢 1, 🔴 2, 28 unch. · avg +0.2% · Bytecode: 🟢 4, 27 unch. · avg +1.6%
closures.js — Interp: 🔴 1, 10 unch. · avg -0.4% · Bytecode: 🟢 3, 8 unch. · avg +2.2%
collections.js — Interp: 🟢 2, 10 unch. · avg +2.2% · Bytecode: 🟢 1, 11 unch. · avg +2.3%
csv.js — Interp: 13 unch. · avg +0.0% · Bytecode: 🟢 1, 12 unch. · avg +0.6%
destructuring.js — Interp: 🔴 1, 21 unch. · avg -1.6% · Bytecode: 🟢 3, 🔴 1, 18 unch. · avg +1.0%
fibonacci.js — Interp: 🔴 1, 7 unch. · avg -0.8% · Bytecode: 🟢 1, 7 unch. · avg +3.8%
float16array.js — Interp: 🟢 2, 30 unch. · avg +0.4% · Bytecode: 🟢 5, 27 unch. · avg +2.9%
for-in/for-in.js — Interp: 3 unch. · avg +0.8% · Bytecode: 3 unch. · avg -0.1%
for-of.js — Interp: 🟢 1, 6 unch. · avg -0.6% · Bytecode: 🟢 1, 6 unch. · avg +5.2%
generators.js — Interp: 4 unch. · avg +0.1% · Bytecode: 4 unch. · avg +0.1%
intl.js — Interp: 🔴 2, 4 unch. · avg -2.6% · Bytecode: 🟢 1, 5 unch. · avg -0.2%
iterators.js — Interp: 🔴 4, 38 unch. · avg -1.7% · Bytecode: 🟢 13, 29 unch. · avg +2.4%
json.js — Interp: 🟢 2, 🔴 1, 20 unch. · avg -0.0% · Bytecode: 🔴 2, 21 unch. · avg -0.7%
jsx.jsx — Interp: 🔴 1, 20 unch. · avg -1.0% · Bytecode: 🟢 4, 🔴 1, 16 unch. · avg +1.5%
modules.js — Interp: 9 unch. · avg +2.8% · Bytecode: 🟢 1, 8 unch. · avg -1.2%
numbers.js — Interp: 🟢 1, 11 unch. · avg +0.4% · Bytecode: 🟢 2, 10 unch. · avg +0.4%
objects.js — Interp: 8 unch. · avg +1.5% · Bytecode: 8 unch. · avg +0.3%
promises.js — Interp: 🔴 1, 11 unch. · avg -1.1% · Bytecode: 12 unch. · avg +0.4%
property-access.js — Interp: 5 unch. · avg +2.1% · Bytecode: 5 unch. · avg +5.8%
regexp.js — Interp: 🔴 1, 12 unch. · avg +0.3% · Bytecode: 🟢 1, 🔴 1, 11 unch. · avg -2.0%
strings.js — Interp: 🔴 2, 17 unch. · avg -0.8% · Bytecode: 🟢 1, 🔴 1, 17 unch. · avg +0.2%
temporal.js — Interp: 🔴 1, 5 unch. · avg -1.2% · Bytecode: 6 unch. · avg +0.8%
tsv.js — Interp: 🔴 1, 8 unch. · avg -0.7% · Bytecode: 🟢 3, 6 unch. · avg +3.9%
typed-arrays.js — Interp: 🔴 9, 13 unch. · avg -9.5% · Bytecode: 🟢 6, 🔴 2, 14 unch. · avg +2.4%
uint8array-encoding.js — Interp: 🟢 8, 10 unch. · avg +26.9% · Bytecode: 🔴 5, 13 unch. · avg -8.3%
weak-collections.js — Interp: 🟢 2, 🔴 2, 11 unch. · avg -5.4% · Bytecode: 🟢 4, 🔴 1, 10 unch. · avg +4.1%
Deterministic profile diffDeterministic profile diff: no significant changes. Measured on ubuntu-latest x64. Each PR run also builds the |
Contributor
JetStream 3 Performance Barometer
Geomean reference ratio: QuickJS 27.51×; Node.js 303.37×. 1.00× means aligned; values above 1.00× mean Goccia was proportionally slower after normalizing JetStream’s higher-is-better score. This is a directional barometer across runtimes with different goals, not a product ranking. Raw samples and failure details remain in the |
Contributor
test262 Conformance
Areas closest to 100%
Per-test deltas (+0 / -0 / timeout +2 / -1)New timeouts (2):
Resolved timeouts (1):
Steady-state failures and timeouts are non-blocking; PASS → non-timeout failure transitions fail the conformance gate. Measured on ubuntu-latest x64, bytecode mode. Areas grouped by the first two test262 path components; minimum 25 attempted tests, areas already at 100% excluded. Δ vs main compares against the most recent cached |
Contributor
AWFY Results
Geomean Ratios
14 pinned AWFY benchmarks. Medians from 5 interleaved samples per engine; raw JSON includes min/max/CV and is attached as the |
frostney
marked this pull request as ready for review
August 26, 2026 14:42
Owner
Author
|
@coderabbitai review |
Contributor
✅ Action performedReview finished.
|
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.
Summary
ExecuteRegistersinto a production loop and an instrumented loop that share one opcodecaseviaGoccia.VM.DispatchCase.inc. The production path omits stop-IP, coverage, opcode profiling, and inactive instruction-limit polls.#1215←#1216←#1217).case(FPC “Procedure too complex”), changing observable VM semantics.Testing
Full interpreter + bytecode JS suite and Pascal unit tests were run on stack tip
629087c8. Docs updates:docs/bytecode-vm.md,docs/embedding.md,docs/profiling.md,docs/testing.md. Combined A/B vs the wave-1 head (/tmp/combined-w2-prod-dispatch-ab.json): loop-dispatch-floor 0.960, Richards 0.961, Bounce 0.985, geomean 0.958; checksums matched.