[PATCH] D155432: [AArch64][SME] Use `fmov` instead of NEON `movi` for FP value.
Sander de Smalen via Phabricator via llvm-commits
llvm-commits at lists.llvm.org
Thu Jul 20 01:50:48 PDT 2023
sdesmalen added inline comments.
================
Comment at: llvm/test/CodeGen/AArch64/sve-streaming-mode-test-register-mov.ll:36
+; CHECK: // %bb.0:
+; CHECK-NEXT: mov z0.d, #0 // =0x0
+; CHECK-NEXT: // kill: def $q0 killed $q0 killed $z0
----------------
hassnaa-arm wrote:
> while the initialised vector is double, why is this mov instead of fmov ?
FMOV (vector, immediate) is not available in streaming SVE mode, so we can't use it. Instead we use the SVE mov instruction instead.
Repository:
rG LLVM Github Monorepo
CHANGES SINCE LAST ACTION
https://reviews.llvm.org/D155432/new/
https://reviews.llvm.org/D155432
More information about the llvm-commits
mailing list