[llvm] [RISCV] Use a ta vslideup if inserting over end of InterSubVT (PR #83230)
Luke Lau via llvm-commits
llvm-commits at lists.llvm.org
Tue Feb 27 23:32:00 PST 2024
================
@@ -474,7 +474,7 @@ define <vscale x 6 x half> @extract_nxv6f16_nxv12f16_6(<vscale x 12 x half> %in)
; CHECK-NEXT: vsetvli a1, zero, e16, m1, ta, ma
; CHECK-NEXT: vslidedown.vx v12, v9, a0
; CHECK-NEXT: add a1, a0, a0
-; CHECK-NEXT: vsetvli zero, a1, e16, m1, tu, ma
+; CHECK-NEXT: vsetvli zero, a1, e16, m1, ta, ma
----------------
lukel97 wrote:
It's worth noting that a1 is VLMAX here through a series of computations. We should probably be detecting this in RISCVInsertVSETVLI and canonicalising it to `VLMaxSentinel`
https://github.com/llvm/llvm-project/pull/83230
More information about the llvm-commits
mailing list