HomePhabricator

[mlir] [VectorOps] Canonicalization of 1-D memory operations

Authored by aartbik on Aug 13 2020, 3:53 PM.

Description

[mlir] [VectorOps] Canonicalization of 1-D memory operations

Masked loading/storing in various forms can be optimized
into simpler memory operations when the mask is all true
or all false. Note that the backend does similar optimizations
but doing this early may expose more opportunities for further
optimizations. This further prepares progressively lowering
transfer read and write into 1-D memory operations.

Reviewed By: ThomasRaoux

Differential Revision: https://reviews.llvm.org/D85769

Details

Committed
aartbikAug 13 2020, 5:15 PM
Reviewer
ThomasRaoux
Differential Revision
D85769: [mlir] [VectorOps] Canonicalization of 1-D memory operations
Parents
rGb182ccfc2d6a: [WebAssembly] Add missing lit.local.cfg
Branches
Unknown
Tags
Unknown