[llvm] [DAG] Support saturated truncate (PR #99418)
David Green via llvm-commits
llvm-commits at lists.llvm.org
Thu Jul 18 01:54:27 PDT 2024
================
@@ -5375,6 +5383,10 @@ def : Pat<(v16i8 (concat_vectors
(v8i8 (trunc (smax (smin (v8i16 V128:$Vn), (v8i16 VImm7F)),
(v8i16 VImm80)))))),
(SQXTNv16i8 (INSERT_SUBREG (IMPLICIT_DEF), V64:$Vd, dsub), V128:$Vn)>;
+def : Pat<(v16i8 (concat_vectors
----------------
davemgreen wrote:
It looks like we are missing some patterns for the unsigned upper "2" cases, I will see about adding them and they can be witched over too. Hopefully the new node will be able to handle i64->i32 cases too.
https://github.com/llvm/llvm-project/pull/99418
More information about the llvm-commits
mailing list