mirror of
https://github.com/RPCS3/llvm-mirror.git
synced 2025-02-01 05:01:59 +01:00
673cd30eff
If we are extracting a chunk of a vector that's a fraction of an operand of the concatenated vector operand, we can extract directly from one of those original operands. This is another suggestion from PR42024: https://bugs.llvm.org/show_bug.cgi?id=42024#c2 But I'm not sure yet if it will make any difference on those patterns. It seems to help a few existing AVX512 tests though. Differential Revision: https://reviews.llvm.org/D72361
20 lines
713 B
LLVM
20 lines
713 B
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
|
|
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx512f,+avx512bw | FileCheck %s
|
|
|
|
define <112 x i8> @pr34657(<112 x i8>* %src) local_unnamed_addr {
|
|
; CHECK-LABEL: pr34657:
|
|
; CHECK: # %bb.0: # %entry
|
|
; CHECK-NEXT: movq %rdi, %rax
|
|
; CHECK-NEXT: vmovups (%rsi), %zmm0
|
|
; CHECK-NEXT: vmovups 64(%rsi), %ymm1
|
|
; CHECK-NEXT: vmovups 96(%rsi), %xmm2
|
|
; CHECK-NEXT: vmovaps %xmm2, 96(%rdi)
|
|
; CHECK-NEXT: vmovaps %ymm1, 64(%rdi)
|
|
; CHECK-NEXT: vmovaps %zmm0, (%rdi)
|
|
; CHECK-NEXT: vzeroupper
|
|
; CHECK-NEXT: retq
|
|
entry:
|
|
%wide.vec51 = load <112 x i8>, <112 x i8>* %src, align 2
|
|
ret <112 x i8> %wide.vec51
|
|
}
|