[PATCH] D108633: [AArch64] Generate smov in place of sext(fmov(...))

[Paul Walker via Phabricator via llvm-commits]

paulwalker-arm accepted this revision.
paulwalker-arm added a comment.
This revision is now accepted and ready to land.

The out-of-range tests show that with a few more patterns we can do better, but given they're not the common case I guess they can wait.



================
Comment at: llvm/lib/Target/AArch64/AArch64SVEInstrInfo.td:2496-2507
+  def : Pat<(sext_inreg (vector_extract (nxv16i8 ZPR:$vec), VectorIndexB:$index), i8),
+            (i32 (SMOVvi8to32 (v16i8 (EXTRACT_SUBREG ZPR:$vec, zsub)), VectorIndexB:$index))>;
+  def : Pat<(sext_inreg (anyext (vector_extract (nxv16i8 ZPR:$vec), VectorIndexB:$index)), i8),
+            (i64 (SMOVvi8to64 (v16i8 (EXTRACT_SUBREG ZPR:$vec, zsub)), VectorIndexB:$index))>;
+
+  def : Pat<(sext_inreg (vector_extract (nxv8i16 ZPR:$vec), VectorIndexH:$index), i16),
+            (i32 (SMOVvi16to32 (v8i16 (EXTRACT_SUBREG ZPR:$vec, zsub)), VectorIndexH:$index))>;
----------------
Can you move these patterns up a couple of blocks to be just after  the `UMOV` variants as that's the block they relate to.


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D108633/new/

https://reviews.llvm.org/D108633