Skip to content

Fix AntaresCpuKernelEmitter and add ir_based_fusion in GENERIC_CPU backend#351

Merged
xysmlx merged 3 commits intomicrosoft:masterfrom
xysmlx:fix_cpu_antares
Nov 23, 2021
Merged

Fix AntaresCpuKernelEmitter and add ir_based_fusion in GENERIC_CPU backend#351
xysmlx merged 3 commits intomicrosoft:masterfrom
xysmlx:fix_cpu_antares

Conversation

@xysmlx
Copy link
Copy Markdown
Contributor

@xysmlx xysmlx commented Nov 13, 2021

  • Update AntaresCpuKernelEmitter for Antares v0.2.x
  • Add IRBasedFusion for GENERIC_CPU backend
  • Performance could match Antares when the compilation environments (e.g., compiler, compile flags) of the generated model code and Antares kernel tuning are the same.
  • Not solved: Antares returns multiple kernels for an op

@xysmlx xysmlx merged commit 0777e29 into microsoft:master Nov 23, 2021
@xysmlx xysmlx deleted the fix_cpu_antares branch November 23, 2021 07:52
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

[BUG] GENERIC_CPU backend can not generate model code with Antares kernels

2 participants