quantumclaw/clawhdf5
3
1
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases 1 Wiki Activity

docs: measured ARM numbers, and a correction

Browse Source 
On a Raspberry Pi 5 at N = 100 000 and equal recall (0.9940 vs 0.9945),
medians of three runs:

  f32             33 413 ms build   6 164 QPS
  int8 scalar     18 950 ms         ~6 190 QPS   (what v2.7.0 shipped)
  int8 NEON      ~17 000 ms          6 640 QPS
  int8 SDOT       14 464 ms          7 267 QPS   1.18x f32, 2.3x build

The docs said quantised search stayed off by default because aarch64
"falls back to the scalar loop, where the original trade still
applies" — that it was ~13% slower than f32 there, as on x86. That was
extrapolated rather than measured, and it was wrong: x86's portable
baseline is SSE2 against hand-written AVX2 f32 kernels, but on aarch64
NEON is the baseline and the scalar loop vectorises well, so it already
matched f32. Corrected in BENCHMARKS.md, README.md and CLAUDE.md; the
released v2.7.0 changelog entry is left as it was and the correction is
recorded in a new one.

Labelled as Pi 5 figures throughout — a Pi's memory bandwidth and cache
are far below an M-series or flagship phone, so the ratios will move.

Co-Authored-By: Claude Opus 5 (1M context) <[email protected]>
This commit is contained in:
osobh
2026-09-21 17:34:51 -07:00
co-authored by Claude Opus 5
parent 56a8c2f3d0
commit 114a2dfcba
4 changed files with 65 additions and 13 deletions
Download Patch File Download Diff File Expand all files Collapse all files
README.md
+3 -4
View File
@@ -442,10 +442,9 @@ copy of the embeddings as `i8`, roughly halving a loaded store's memory
(2.72x -> 1.74x the raw vectors at 100k x 384). Quantised distances are
approximate, so the query path re-scores the candidate pool against the exact
embeddings the store already holds, which keeps recall at the `f32` index's
level. On AVX2 it is also **faster** — 1.63x the queries per second and 1.8x
the build speed at equal recall — because the int8 kernel is SIMD too. It
stays off by default only because that kernel is AVX2-only and aarch64 falls
back to a scalar loop. See `BENCHMARKS.md`, "Quantising the index copy".
level. It is also **faster**: 1.63x the queries per second at equal recall on
x86-64 (AVX2) and 1.18x on a Raspberry Pi 5 (NEON `SDOT`), with index builds
1.8x and 2.3x faster respectively. See `BENCHMARKS.md`, "Quantising the index copy".
| `parallel` | no | Rayon parallel search |
| `fast-math` | no | BLAS matrix-vector multiply |
| `accelerate` | no | Apple Accelerate / AMX (macOS) |