This change enables VOP3 shifts to be explicitly selected dependent on the divergence.
Tests: CodeGen/AMDGPU passed
Differential D52559
[AMDGPU] Divergence driven instruction selection. Shift operations. alex-t on Sep 26 2018, 9:31 AM. Authored by
Details This change enables VOP3 shifts to be explicitly selected dependent on the divergence. Tests: CodeGen/AMDGPU passed
Diff Detail Event TimelineComment Actions Pattern changed to GCNPat, divergence check added.
|
It sounds like from your explanation below and the logic of the getVOP3Pat this will create a bogus pattern with wrong operand order. Only one pattern shall exist for (shl i64:x, i32:y) and it seems to be the pattern below. At best this one will never match.