llvm-project/llvm/test/CodeGen/X86/combine-concatvectors.ll

88 lines
4.3 KiB
LLVM

; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx | FileCheck %s --check-prefixes=CHECK,AVX1
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx2 | FileCheck %s --check-prefixes=CHECK,AVX2
define void @PR32957(<2 x float>* %in, <8 x float>* %out) {
; CHECK-LABEL: PR32957:
; CHECK: # %bb.0:
; CHECK-NEXT: vmovsd {{.*#+}} xmm0 = mem[0],zero
; CHECK-NEXT: vmovaps %ymm0, (%rsi)
; CHECK-NEXT: vzeroupper
; CHECK-NEXT: retq
%ld = load <2 x float>, <2 x float>* %in, align 8
%ext = extractelement <2 x float> %ld, i64 0
%ext2 = extractelement <2 x float> %ld, i64 1
%ins = insertelement <8 x float> <float undef, float undef, float 0.0, float 0.0, float 0.0, float 0.0, float 0.0, float 0.0>, float %ext, i64 0
%ins2 = insertelement <8 x float> %ins, float %ext2, i64 1
store <8 x float> %ins2, <8 x float>* %out, align 32
ret void
}
declare { i8, double } @fun()
; Check that this does not fail to combine concat_vectors of a value from
; merge_values through a bitcast.
define void @d(i1 %cmp) {
; CHECK-LABEL: d:
; CHECK: # %bb.0: # %bar
; CHECK-NEXT: pushq %rax
; CHECK-NEXT: .cfi_def_cfa_offset 16
; CHECK-NEXT: callq fun@PLT
bar:
%val = call { i8, double } @fun()
%extr = extractvalue { i8, double } %val, 1
%bc = bitcast double %extr to <2 x float>
br label %baz
baz:
%extr1 = extractelement <2 x float> %bc, i64 0
unreachable
}
@qa_ = external unnamed_addr global [49216 x i8], align 32
define void @concat_of_broadcast_v2f64_v4f64() {
; AVX1-LABEL: concat_of_broadcast_v2f64_v4f64:
; AVX1: # %bb.0: # %alloca_0
; AVX1-NEXT: movq qa_@GOTPCREL(%rip), %rax
; AVX1-NEXT: movl $1091567616, 30256(%rax) # imm = 0x41100000
; AVX1-NEXT: movabsq $4294967297, %rcx # imm = 0x100000001
; AVX1-NEXT: movq %rcx, 46348(%rax)
; AVX1-NEXT: vmovaps {{.*#+}} xmm0 = <1.0E+0,1.0E+0,u,u>
; AVX1-NEXT: vmovddup {{.*#+}} xmm1 = xmm0[0,0]
; AVX1-NEXT: vinsertf128 $1, %xmm1, %ymm1, %ymm1
; AVX1-NEXT: vmovups %ymm1, 48296(%rax)
; AVX1-NEXT: vmovlps %xmm0, 47372(%rax)
; AVX1-NEXT: vzeroupper
; AVX1-NEXT: retq
;
; AVX2-LABEL: concat_of_broadcast_v2f64_v4f64:
; AVX2: # %bb.0: # %alloca_0
; AVX2-NEXT: movq qa_@GOTPCREL(%rip), %rax
; AVX2-NEXT: movl $1091567616, 30256(%rax) # imm = 0x41100000
; AVX2-NEXT: movabsq $4294967297, %rcx # imm = 0x100000001
; AVX2-NEXT: movq %rcx, 46348(%rax)
; AVX2-NEXT: vbroadcastss {{.*#+}} xmm0 = [1.0E+0,1.0E+0,1.0E+0,1.0E+0]
; AVX2-NEXT: vbroadcastsd %xmm0, %ymm1
; AVX2-NEXT: vmovups %ymm1, 48296(%rax)
; AVX2-NEXT: vmovlps %xmm0, 47372(%rax)
; AVX2-NEXT: vzeroupper
; AVX2-NEXT: retq
alloca_0:
store float 9.000000e+00, float* bitcast (i8* getelementptr inbounds ([49216 x i8], [49216 x i8]* @qa_, i64 0, i64 30256) to float*), align 16
store <2 x i32> <i32 1, i32 1>, <2 x i32>* bitcast (i8* getelementptr inbounds ([49216 x i8], [49216 x i8]* @qa_, i64 0, i64 46348) to <2 x i32>*), align 4
br label %loop.4942
loop.4942: ; preds = %loop.4942, %alloca_0
br i1 undef, label %loop.4942, label %ifmerge.1298
ifmerge.1298: ; preds = %loop.4942
%gepload4638 = load float, float* bitcast (i8* getelementptr inbounds ([49216 x i8], [49216 x i8]* @qa_, i64 0, i64 28324) to float*), align 4
store <2 x float> <float 1.000000e+00, float 1.000000e+00>, <2 x float>* bitcast (i8* getelementptr inbounds ([49216 x i8], [49216 x i8]* @qa_, i64 0, i64 48296) to <2 x float>*), align 8
store <2 x float> <float 1.000000e+00, float 1.000000e+00>, <2 x float>* bitcast (i8* getelementptr inbounds ([49216 x i8], [49216 x i8]* @qa_, i64 0, i64 48304) to <2 x float>*), align 16
store <2 x float> <float 1.000000e+00, float 1.000000e+00>, <2 x float>* bitcast (i8* getelementptr inbounds ([49216 x i8], [49216 x i8]* @qa_, i64 0, i64 48312) to <2 x float>*), align 8
store <2 x float> <float 1.000000e+00, float 1.000000e+00>, <2 x float>* bitcast (i8* getelementptr inbounds ([49216 x i8], [49216 x i8]* @qa_, i64 0, i64 48320) to <2 x float>*), align 32
store <2 x float> <float 1.000000e+00, float 1.000000e+00>, <2 x float>* bitcast (i8* getelementptr inbounds ([49216 x i8], [49216 x i8]* @qa_, i64 0, i64 47372) to <2 x float>*), align 4
ret void
}