Files
clang-p2996/llvm/lib/Target/AMDGPU/AMDGPUTargetMachine.cpp
alex-t 5b898bddff [AMDGPU] Enable carry out ADD/SUB operations divergence driven instruction selection.
Summary: This change enables all kind of carry out ISD opcodes to be selected according to the node divergence.

Reviewers: rampitec, arsenm, vpykhtin

Reviewed By: rampitec

Subscribers: kzhuravl, jvesely, wdng, nhaehnle, yaxunl, dstuttard, tpr, t-tye, hiraditya, kerbowa, llvm-commits

Tags: #llvm

Differential Revision: https://reviews.llvm.org/D78091
2020-05-04 16:42:25 +03:00

42 KiB