[llvm] [NVPTX] Make i16x2 a native type and add supported vec instructions (PR #65432)
via llvm-commits
llvm-commits at lists.llvm.org
Wed Sep 6 15:00:46 PDT 2023
================
@@ -747,6 +754,13 @@ def SELP_f16x2rr :
[(set Int32Regs:$dst,
(select Int1Regs:$p, (v2f16 Int32Regs:$a), (v2f16 Int32Regs:$b)))]>;
+def SELP_i16x2rr :
----------------
ThomasRaoux wrote:
Good point, changed it to a pattern for all the cases
https://github.com/llvm/llvm-project/pull/65432
More information about the llvm-commits
mailing list