Skip to content

Thread-unsafe cuFFT plan cache usage #12

@michael-swan

Description

@michael-swan

Fortunately plans are cached by accelerate-fft however there is only one plan per shape and data-type and no mutual exclusion for concurrent usage of that plan which poses a thread-safety issue when multiple separate threads try to use the same plan, assign it a corresponding CUDA stream, and then execute said plan. Execution could feasibly look like:

 p = ... cached plan #1 ...
thread 1: FFT.setStream p s1
thread 2: FFT.setStream p s2
thread 1: FFT.execC2C p (fftMode mode) d_in d_out
thread 2: FFT.execC2C p (fftMode mode) d_in d_out

Solutions include:

  1. Make redundant copies of cuFFT plans as concurrent demand is observed.
  2. Enforce mutual exclusion on plans during cuFFT call.

The former is vastly preferred to the latter.

Additionally, the cuFFT documentation makes clear that concurrent usage of plans is fundamentally thread-unsafe.

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions