Hacktoberfest 2026: the issues maintainers tagged for October, open and beginner-friendly. Browse Hacktoberfest issues

Panama FP32 matmul: first call in a JVM differs by an ULP from later calls (JIT-dependent reduceLanes order)

Open
  • Is something wrong?
#1,261 0 comments 0 reactions 0 assignees View on GitHub

Maintainers usually reply within 1 day

Nobody has claimed this yet.

Assessment

Difficulty
4/5
Estimated time
3-5 days
Newbie friendliness
45/100
Issue type
Bug
Clarity
Mostly clear
Activity status
Quiet
Tech stack
kotlin
Domain
performance

Research direction

Start with PanamaVectorMatmulKernel and inspect its FloatVector.reduceLanes(ADD) reduction, then read DirectCpuExecutionContextScheduleTest for the existing warm-up behavior. Reproduce the first-call versus later-call difference on the same context with identical inputs. Done when repeated calls produce consistent results regardless of whether the JVM has compiled the intrinsic.

Written by the indexing model from the issue text.

Description

bug compute-backend skill:numerics

Summary

On a fresh DirectCpuExecutionContext() the first dense FP32 matmul in a JVM process produces results that differ by 1 ULP (in ~37k of 153k elements for m=300, k=64, n=512) from every later call on the same context with the same inputs. After that first call the results are stable and independent of threading or schedule.

Observed while writing SKEEP-005 parity tests (DirectCpuExecutionContextScheduleTest): probe output

same-ctx twice diff=37355   (first call vs second call)
seq twice diff=0
par-vs-seq diff=0

Likely cause

PanamaVectorMatmulKernel reduces with FloatVector.reduceLanes(ADD), whose lane-reduction order is unspecified and differs between the interpreter/C1 fallback and the C2 intrinsic. The first call runs before the intrinsic is compiled.

Why it matters

  • Golden-token parity gates (*GoldenTokenParityTest in SKaiNET-transformers) assert exact llama.cpp text equality; a warm-up-dependent ULP can flip a greedy argmax.
  • Any test comparing two contexts must warm up first (the SKEEP-005 tests now do).

Options

  • Replace reduceLanes with an explicit fixed-order tree reduction (reduceLanesToLong-style) or accumulate into a vector and reduce with a deterministic scalar loop.
  • Document the property and add a warm-up helper for parity tests.

Not fixed in feature/skeep-005-schedules; the schedule tests warm up before comparing.

Dominant language
Kotlin
Stars
52
Forks
15
Avg merge
23h 34m
Merged PRs (30d)
45

Getting set up

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

More from SKaiNET-developers/SKaiNET

All issues in SKaiNET-developers/SKaiNET

Similar issues

More Kotlin issues

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.