Files
gem5/src/arch
Matthew Poremba 31e63b01ad arch-vega: Add vop3p DOT instructions
Implemented according to the ISA spec. Validated with silion. In
particular the sign extend is important for the signed variants and the
unsigned variants seem to overflow lanes (hence why there is no mask()
in the unsigned varints. FP16 -> FP32 continues using ARM's fplib.

Tested vs. an MI210. Clamp has not been verified.

Change-Id: Ifc09aecbc1ef2c92a5524a43ca529983018a6d59
2024-01-03 15:41:06 -06:00
..