Ryan Houdek 47fd73f6cf Arm64: Optimize non-SVE gather load ...

When FEX hits the optimal case that the destination isn't one of the
incoming sources (other than the incomingDest source) then we can
optimize out two moves per 128-bit lane.

Cuts 256-bit non-SVE gather loads from 50 instructions down to 46.

2024-06-29 13:02:10 -07:00

..

Passes

IR: drop RCLSE

2024-06-26 14:49:05 -04:00

AOTIR.cpp

Core: Clean up ownership management for IRListView and RegisterAllocationData

2024-05-21 17:51:17 +02:00

AOTIR.h

Core: Clean up ownership management for IRListView and RegisterAllocationData

2024-05-21 17:51:17 +02:00

IntrusiveIRList.h

IR: use Ref instead of OrderedNode

2024-06-03 12:19:34 -04:00

IR.h

IR: add Ref typedef

2024-06-03 12:19:34 -04:00

IR.json

Arm64: Optimize non-SVE gather load

2024-06-29 13:02:10 -07:00

IRDumper.cpp

IR: Adds support for new SUBADD FMA constants

2024-06-25 11:22:22 -07:00

IREmitter.cpp

IR: use Ref instead of OrderedNode

2024-06-03 12:19:34 -04:00

IREmitter.h

IR: use Ref instead of OrderedNode

2024-06-03 12:19:34 -04:00

Passes.h

IR: drop RCLSE

2024-06-26 14:49:05 -04:00

PassManager.cpp

IR: drop RCLSE

2024-06-26 14:49:05 -04:00

PassManager.h

ConstProp: always inline constants

2024-06-04 10:09:51 -04:00

RegisterAllocationData.h

AOTIR: Remove obsolete fields from serialized data

2024-05-21 17:54:28 +02:00