834cc88c5d
lowerBuildVectorAsBroadcast will not broadcast splat constants in all cases, resulting in a lot of situations where a full width vector load that has failed to fold but is loading splat constant values could use a broadcast load instruction just as cheaply, and save constant pool space. NOTE: SSE3 targets can use MOVDDUP but not all SSE era CPUs can perform this as cheaply as a vector load, we will need to add scheduler model checks if we want to pursue this. This is an updated commit of 98061013e01207444cfd3980cde17b5e75764fbe after being reverted at a279a09ab9524d1d74ef29b34618102d4b202e2f
52 lines
1.8 KiB
LLVM
52 lines
1.8 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
|
|
; RUN: llc < %s -mcpu=penryn | FileCheck %s --check-prefix=SSE
|
|
; RUN: llc < %s -mcpu=sandybridge | FileCheck %s --check-prefix=AVX
|
|
; RUN: llc < %s -mcpu=haswell | FileCheck %s --check-prefix=AVX2
|
|
; This checks that lowering for creation of constant vectors is sane and
|
|
; doesn't use redundant shuffles. (fixes PR22276)
|
|
target triple = "x86_64-unknown-unknown"
|
|
|
|
define <4 x i32> @zero_vector() {
|
|
; SSE-LABEL: zero_vector:
|
|
; SSE: # %bb.0:
|
|
; SSE-NEXT: xorps %xmm0, %xmm0
|
|
; SSE-NEXT: retq
|
|
;
|
|
; AVX-LABEL: zero_vector:
|
|
; AVX: # %bb.0:
|
|
; AVX-NEXT: vxorps %xmm0, %xmm0, %xmm0
|
|
; AVX-NEXT: retq
|
|
;
|
|
; AVX2-LABEL: zero_vector:
|
|
; AVX2: # %bb.0:
|
|
; AVX2-NEXT: vxorps %xmm0, %xmm0, %xmm0
|
|
; AVX2-NEXT: retq
|
|
%zero = insertelement <4 x i32> undef, i32 0, i32 0
|
|
%splat = shufflevector <4 x i32> %zero, <4 x i32> undef, <4 x i32> zeroinitializer
|
|
ret <4 x i32> %splat
|
|
}
|
|
|
|
; Note that for the "const_vector" versions, lowering that uses a shuffle
|
|
; instead of a load would be legitimate, if it's a single broadcast shuffle.
|
|
; (as opposed to the previous mess)
|
|
; However, this is not the current preferred lowering.
|
|
define <4 x i32> @const_vector() {
|
|
; SSE-LABEL: const_vector:
|
|
; SSE: # %bb.0:
|
|
; SSE-NEXT: movaps {{.*#+}} xmm0 = [42,42,42,42]
|
|
; SSE-NEXT: retq
|
|
;
|
|
; AVX-LABEL: const_vector:
|
|
; AVX: # %bb.0:
|
|
; AVX-NEXT: vbroadcastss {{.*#+}} xmm0 = [42,42,42,42]
|
|
; AVX-NEXT: retq
|
|
;
|
|
; AVX2-LABEL: const_vector:
|
|
; AVX2: # %bb.0:
|
|
; AVX2-NEXT: vbroadcastss {{.*#+}} xmm0 = [42,42,42,42]
|
|
; AVX2-NEXT: retq
|
|
%const = insertelement <4 x i32> undef, i32 42, i32 0
|
|
%splat = shufflevector <4 x i32> %const, <4 x i32> undef, <4 x i32> zeroinitializer
|
|
ret <4 x i32> %splat
|
|
}
|