1
0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-11-23 11:13:28 +01:00
llvm-mirror/test/CodeGen/X86/pr36199.ll
Sanjay Patel b527648058 [DAGCombiner] look through bitcasts when trying to narrow vector binops
This is another step in vector narrowing - a follow-up to D53784
(and hoping to eventually squash potential regressions seen in
D51553).

The x86 test diffs are wins, but the AArch64 diff is probably not.
That problem already exists independent of this patch (see PR39722), but it
went unnoticed in the previous patch because there were no regression tests
that showed the possibility.

The x86 diff in i64-mem-copy.ll is close. Given the frequency throttling
concerns with using wider vector ops, an extra extract to reduce vector
width is the right trade-off at this level of codegen.

Differential Revision: https://reviews.llvm.org/D54392

llvm-svn: 347356
2018-11-20 22:26:35 +00:00

23 lines
890 B
LLVM

; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=avx512f | FileCheck %s
define void @foo(<16 x float> %x) {
; CHECK-LABEL: foo:
; CHECK: # %bb.0:
; CHECK-NEXT: vaddps %xmm0, %xmm0, %xmm0
; CHECK-NEXT: vinsertf128 $1, %xmm0, %ymm0, %ymm0
; CHECK-NEXT: vinsertf64x4 $1, %ymm0, %zmm0, %zmm0
; CHECK-NEXT: vmovups %zmm0, (%rax)
; CHECK-NEXT: vzeroupper
; CHECK-NEXT: retq
%1 = fadd <16 x float> %x, %x
%bc256 = bitcast <16 x float> %1 to <4 x i128>
%2 = extractelement <4 x i128> %bc256, i32 0
%3 = bitcast i128 %2 to <4 x float>
%4 = shufflevector <4 x float> %3, <4 x float> undef, <16 x i32> <i32 0, i32
1, i32 2, i32 3, i32 0, i32 1, i32 2, i32 3, i32 0, i32 1, i32 2, i32 3, i32 0,
i32 1, i32 2, i32 3>
store <16 x float> %4, <16 x float>* undef, align 4
ret void
}