[PATCH] D142998: [SVE][codegen] Add test case for a fused multiply-add (NFC)
Sjoerd Meijer via Phabricator via llvm-commits
llvm-commits at lists.llvm.org
Tue Jan 31 12:19:47 PST 2023
SjoerdMeijer added inline comments.
================
Comment at: llvm/test/CodeGen/AArch64/sve-multiply-add-accumulate.ll:12
+; CHECK-NEXT: ret
+{
+ %1 = mul <vscale x 2 x i64> %a, %b
----------------
if I am not mistaken, the other patch will change this to
; CHECK-LABEL: muladd_i64:
; CHECK: // %bb.0:
; CHECK-NEXT: ptrue p0.d
; CHECK-NEXT: mov z2.d, #1 // =0x1
; CHECK-NEXT: mad z0.d, p0/m, z1.d, z2.d
; CHECK-NEXT: ret
(perhaps the immediate is different but that looks irrelevant to me).
This new codegen looks better, it has 1 mov less, but that is just to return the value. There is no real use of the value, which makes this move visible. Basically what I am saying is that it is unclear what the benefit is.
But either way, I will repeat my request on the other patch: let's separate things and let this be about instruction selection of 'mad'. This means that we only want to do have 'mad' tests here, and separate out the mla -> mad changes.
Repository:
rG LLVM Github Monorepo
CHANGES SINCE LAST ACTION
https://reviews.llvm.org/D142998/new/
https://reviews.llvm.org/D142998
More information about the llvm-commits
mailing list