Benjamin Maxwell ced97ffd08

[mlir][Vector] Don't fully unroll transfer_writes of n-D scalable vectors (#71924) ...

It is not possible to unroll a scalable vector at compile time. This
currently prevents transfer_writes from being lowered to
arm_sme.tile_writes (downstream).

2023-11-13 11:22:55 +00:00

..

CMakeLists.txt

[mlir][arith] Change dialect name from Arithmetic to Arith

2022-09-29 11:23:28 -04:00

VectorToSCF.cpp

[mlir][Vector] Don't fully unroll transfer_writes of n-D scalable vectors (#71924)

2023-11-13 11:22:55 +00:00