There is a newer version of the record available.

Published April 11, 2023 | Version v0.9.2
Software Open

JuliaGPU/KernelAbstractions.jl: v0.9.2

  • 1. @mit
  • 2. Brown University
  • 3. LeiosOS
  • 4. Caltech
  • 5. Massachusetts Institute of Technology
  • 6. @JuliaComputing
  • 7. Australian National University
  • 8. Howard Hughes Medical Institute / Janelia Research Campus / Scientific Computing
  • 9. Hong Kong University of Science and Technology
  • 10. Argonne National Laboratory
  • 11. Max Planck Institute for Physics
  • 12. UMD

Description

KernelAbstractions v0.9.2

Diff since v0.9.1

Closed issues:

  • Use occupancy API for autotuning (#19)
  • Allow user to turn off contract (#20)
  • Assigning ::ROCDevice to ::KA.GPU (#321)
  • ROCKernels: using queue pool causes performance regression (#344)
  • KernelAbstractions.jl is blocked to v0.8.6 by CUDAKernels (#380)

Merged pull requests:

  • CI improvements (#378) (@maleadt)
  • Add unsafe_free! (#381) (@pxl-th)

Files

JuliaGPU/KernelAbstractions.jl-v0.9.2.zip

Files (51.3 kB)

Name Size Download all
md5:7ce8db7af00b1229351d6f1abd154363
51.3 kB Preview Download

Additional details