feat(text): wire D-245 SIMD kernels to production consumers (11.14 layer 4) - #70
Open
thejustinwalsh wants to merge 2 commits into
Open
feat(text): wire D-245 SIMD kernels to production consumers (11.14 layer 4)#70thejustinwalsh wants to merge 2 commits into
thejustinwalsh wants to merge 2 commits into
Conversation
…yer 4) Transition masks drive the bidi run scan and flag masks drive the justification space scan, each graduated from the kernel lab into engine/line_kernels.rs as a scalar function with a cfg(simd128) sixteen-lane prefix and scalar tail. The CLUSTER_SPACE flag replaces per-cluster text lookups everywhere justification detects spaces, and the dead text plumbing through the justification and measurement chains is gone. Boundary-sweeping parity tests prove the scalar path; the shipped simd128 wasm exercises the SIMD path through every layout integration test. Chunk-64 advance summaries stay lab-admitted with the fixed-point prerequisite recorded in D-245.
size-limit report 📦
|
thejustinwalsh
marked this pull request as ready for review
August 14, 2026 02:36
# Conflicts: # docs/packages/benchmarks.md # docs/packages/glyph.md # docs/planning/decision-register.md # packages/glyph/rust/shaper/src/engine/line_kernels.rs
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
What
Layer 4 of the 11.14 typography tier: two of D-245's lab-admitted SIMD kernels graduate to production consumers in
engine/line_kernels.rs.CLUSTER_SPACEflagShape and proof
Each kernel is one scalar function with a
cfg(simd128)sixteen-lane prefix and a scalar tail, so native builds and Wasm builds agree exactly. Boundary-sweeping parity tests prove the scalar path against naive scans across 15/16/17-index block boundaries; the shipped simd128 Wasm exercises the SIMD path through every layout integration test.CLUSTER_SPACEalso replaces per-cluster text lookups everywhere justification detects spaces, and the deadtextplumbing through the justification and measurement chains is removed.Chunk-64 advance summaries stay lab-admitted, with the reason recorded in D-245: exact parity for whole-chunk width arithmetic needs a fixed-point cluster-advance representation first, scheduled with the editorial performance pass.