Page MenuHomePhabricator

[mlir][bufferization][NFC] Improve assembly format of AllocTensorOp
ClosedPublic

Authored by springerm on May 22 2022, 5:12 PM.

Details

Summary

No longer pass static dim sizes as an attribute. This was redundant and required extra checks in the verifier. This change also makes the op symmetrical to memref::AllocOp.

Diff Detail

Event Timeline

springerm created this revision.May 22 2022, 5:12 PM
springerm requested review of this revision.May 22 2022, 5:12 PM
Herald added a project: Restricted Project. · View Herald TranscriptMay 22 2022, 5:12 PM
pifon2a accepted this revision.May 23 2022, 6:54 AM

Should there be a similar change to alloc ops in MemRefOps.td?

This revision is now accepted and ready to land.May 23 2022, 6:54 AM

The AllocTensorOp assembly format is changes so that it matches the MemRef AllocOp format. No change to MemRefOps.td.