[PATCH] D54073: [x86] allow vector load narrowing with multi-use values
Simon Pilgrim via Phabricator via llvm-commits
llvm-commits at lists.llvm.org
Fri Nov 9 06:25:39 PST 2018
RKSimon accepted this revision.
RKSimon added a comment.
This revision is now accepted and ready to land.
LGTM - thanks
================
Comment at: test/CodeGen/X86/pr34653.ll:2
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc %s -O0 -mtriple=x86_64-unknown-unknown -mattr=+avx512f -o - | FileCheck %s
----------------
spatel wrote:
> This is a -O0 test, so doesn't matter? With optimization, everything disappears:
>
> ```
> pushq %rbp
> movq %rsp, %rbp
> andq $-512, %rsp ## imm = 0xFE00
> subq $1024, %rsp ## imm = 0x400
> movq %rsp, %rdi
> callq _test
> movq %rbp, %rsp
> popq %rbp
>
> ```
Agreed - it's annoying but doesn't matter.
https://reviews.llvm.org/D54073
More information about the llvm-commits
mailing list