maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity
llvm-project/llvm/test/CodeGen/X86/pr34653.ll

210 lines
11 KiB
LLVM
Raw Normal View History

[X86] Fix bug in legalize vector types - Split large loads When splitting a large load to smaller legally-typed loads, the last load should be padded to reach the size of the previous one so a CONCAT_VECTORS node could reunite them again. The code currently pads the last load to reach the size of the first load (instead of the previous). Differential Revision: https://reviews.llvm.org/D38495 Change-Id: Ib60b55ed26ce901fabf68108daf52683fbd5013f llvm-svn: 317206
2017-11-02 21:07:06 +08:00
; 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
declare fastcc <38 x double> @test()
define void @pr34653() {
; CHECK-LABEL: pr34653:
; CHECK: # BB#0: # %entry
; CHECK-NEXT: pushq %rbp
; CHECK-NEXT: .cfi_def_cfa_offset 16
; CHECK-NEXT: .cfi_offset %rbp, -16
; CHECK-NEXT: movq %rsp, %rbp
; CHECK-NEXT: .cfi_def_cfa_register %rbp
; CHECK-NEXT: andq $-512, %rsp # imm = 0xFE00
; CHECK-NEXT: subq $2048, %rsp # imm = 0x800
; CHECK-NEXT: leaq {{[0-9]+}}(%rsp), %rdi
; CHECK-NEXT: callq test
; CHECK-NEXT: vmovupd {{[0-9]+}}(%rsp), %xmm0
; CHECK-NEXT: vmovaps %xmm0, %xmm1
; CHECK-NEXT: vpermilpd {{.*#+}} xmm0 = xmm0[1,0]
; CHECK-NEXT: vmovupd {{[0-9]+}}(%rsp), %ymm2
; CHECK-NEXT: vextractf128 $1, %ymm2, %xmm3
; CHECK-NEXT: vmovaps %xmm3, %xmm4
; CHECK-NEXT: vmovaps %xmm2, %xmm5
; CHECK-NEXT: vmovaps %xmm5, %xmm6
; CHECK-NEXT: vmovupd {{[0-9]+}}(%rsp), %zmm7
; CHECK-NEXT: vmovupd {{[0-9]+}}(%rsp), %zmm8
; CHECK-NEXT: vmovupd {{[0-9]+}}(%rsp), %zmm9
; CHECK-NEXT: vmovupd {{[0-9]+}}(%rsp), %zmm10
; CHECK-NEXT: vextractf32x4 $3, %zmm10, %xmm11
; CHECK-NEXT: vmovaps %xmm11, %xmm12
; CHECK-NEXT: vextractf32x4 $2, %zmm10, %xmm13
; CHECK-NEXT: vmovaps %xmm13, %xmm14
; CHECK-NEXT: vmovaps %xmm10, %xmm15
; CHECK-NEXT: vmovaps %xmm15, %xmm2
; CHECK-NEXT: vmovsd %xmm0, {{[0-9]+}}(%rsp) # 8-byte Spill
; CHECK-NEXT: vextractf32x4 $3, %zmm9, %xmm0
; CHECK-NEXT: vmovaps %xmm0, {{[0-9]+}}(%rsp) # 16-byte Spill
; CHECK-NEXT: vmovsd %xmm0, {{[0-9]+}}(%rsp) # 8-byte Spill
; CHECK-NEXT: vextractf32x4 $2, %zmm9, %xmm0
; CHECK-NEXT: vmovaps %xmm0, {{[0-9]+}}(%rsp) # 16-byte Spill
; CHECK-NEXT: vmovsd %xmm0, {{[0-9]+}}(%rsp) # 8-byte Spill
; CHECK-NEXT: vmovaps %xmm9, %xmm0
; CHECK-NEXT: vmovaps %xmm0, {{[0-9]+}}(%rsp) # 16-byte Spill
; CHECK-NEXT: vmovsd %xmm0, {{[0-9]+}}(%rsp) # 8-byte Spill
; CHECK-NEXT: vextractf32x4 $3, %zmm8, %xmm0
; CHECK-NEXT: vmovaps %xmm0, {{[0-9]+}}(%rsp) # 16-byte Spill
; CHECK-NEXT: vmovsd %xmm0, {{[0-9]+}}(%rsp) # 8-byte Spill
; CHECK-NEXT: vextractf32x4 $2, %zmm8, %xmm0
; CHECK-NEXT: vmovaps %xmm0, {{[0-9]+}}(%rsp) # 16-byte Spill
; CHECK-NEXT: vmovsd %xmm0, {{[0-9]+}}(%rsp) # 8-byte Spill
; CHECK-NEXT: vmovaps %xmm8, %xmm0
; CHECK-NEXT: vmovaps %xmm0, {{[0-9]+}}(%rsp) # 16-byte Spill
; CHECK-NEXT: vmovsd %xmm0, {{[0-9]+}}(%rsp) # 8-byte Spill
; CHECK-NEXT: vextractf32x4 $3, %zmm7, %xmm0
; CHECK-NEXT: vmovaps %xmm0, {{[0-9]+}}(%rsp) # 16-byte Spill
; CHECK-NEXT: vmovsd %xmm0, {{[0-9]+}}(%rsp) # 8-byte Spill
; CHECK-NEXT: vextractf32x4 $2, %zmm7, %xmm0
; CHECK-NEXT: vmovaps %xmm0, {{[0-9]+}}(%rsp) # 16-byte Spill
; CHECK-NEXT: vmovsd %xmm0, {{[0-9]+}}(%rsp) # 8-byte Spill
; CHECK-NEXT: vmovaps %xmm7, %xmm0
; CHECK-NEXT: vmovaps %xmm0, {{[0-9]+}}(%rsp) # 16-byte Spill
; CHECK-NEXT: vpermilpd {{.*#+}} xmm3 = xmm3[1,0]
; CHECK-NEXT: vpermilpd {{.*#+}} xmm5 = xmm5[1,0]
; CHECK-NEXT: vpermilpd {{.*#+}} xmm11 = xmm11[1,0]
; CHECK-NEXT: vpermilpd {{.*#+}} xmm13 = xmm13[1,0]
; CHECK-NEXT: # kill: %YMM10<def> %YMM10<kill> %ZMM10<kill>
; CHECK-NEXT: vextractf128 $1, %ymm10, %xmm10
; CHECK-NEXT: vmovsd %xmm0, {{[0-9]+}}(%rsp) # 8-byte Spill
; CHECK-NEXT: vmovaps %xmm10, %xmm0
; CHECK-NEXT: vpermilpd {{.*#+}} xmm15 = xmm15[1,0]
; CHECK-NEXT: vmovsd %xmm0, {{[0-9]+}}(%rsp) # 8-byte Spill
; CHECK-NEXT: vmovaps {{[0-9]+}}(%rsp), %xmm0 # 16-byte Reload
; CHECK-NEXT: vpermilpd {{.*#+}} xmm0 = xmm0[1,0]
; CHECK-NEXT: vmovsd %xmm0, {{[0-9]+}}(%rsp) # 8-byte Spill
; CHECK-NEXT: vmovaps {{[0-9]+}}(%rsp), %xmm0 # 16-byte Reload
; CHECK-NEXT: vpermilpd {{.*#+}} xmm0 = xmm0[1,0]
; CHECK-NEXT: # kill: %YMM9<def> %YMM9<kill> %ZMM9<kill>
; CHECK-NEXT: vextractf128 $1, %ymm9, %xmm9
; CHECK-NEXT: vmovsd %xmm0, {{[0-9]+}}(%rsp) # 8-byte Spill
; CHECK-NEXT: vmovaps %xmm9, %xmm0
; CHECK-NEXT: vmovsd %xmm0, {{[0-9]+}}(%rsp) # 8-byte Spill
; CHECK-NEXT: vmovaps {{[0-9]+}}(%rsp), %xmm0 # 16-byte Reload
; CHECK-NEXT: vpermilpd {{.*#+}} xmm0 = xmm0[1,0]
; CHECK-NEXT: vmovsd %xmm0, {{[0-9]+}}(%rsp) # 8-byte Spill
; CHECK-NEXT: vmovaps {{[0-9]+}}(%rsp), %xmm0 # 16-byte Reload
; CHECK-NEXT: vpermilpd {{.*#+}} xmm0 = xmm0[1,0]
; CHECK-NEXT: vmovsd %xmm0, {{[0-9]+}}(%rsp) # 8-byte Spill
; CHECK-NEXT: vmovaps {{[0-9]+}}(%rsp), %xmm0 # 16-byte Reload
; CHECK-NEXT: vpermilpd {{.*#+}} xmm0 = xmm0[1,0]
; CHECK-NEXT: # kill: %YMM8<def> %YMM8<kill> %ZMM8<kill>
; CHECK-NEXT: vextractf128 $1, %ymm8, %xmm8
; CHECK-NEXT: vmovsd %xmm0, {{[0-9]+}}(%rsp) # 8-byte Spill
; CHECK-NEXT: vmovaps %xmm8, %xmm0
; CHECK-NEXT: vmovsd %xmm0, {{[0-9]+}}(%rsp) # 8-byte Spill
; CHECK-NEXT: vmovaps {{[0-9]+}}(%rsp), %xmm0 # 16-byte Reload
; CHECK-NEXT: vpermilpd {{.*#+}} xmm0 = xmm0[1,0]
; CHECK-NEXT: vmovsd %xmm0, {{[0-9]+}}(%rsp) # 8-byte Spill
; CHECK-NEXT: vmovaps {{[0-9]+}}(%rsp), %xmm0 # 16-byte Reload
; CHECK-NEXT: vpermilpd {{.*#+}} xmm0 = xmm0[1,0]
; CHECK-NEXT: vmovsd %xmm0, {{[0-9]+}}(%rsp) # 8-byte Spill
; CHECK-NEXT: vmovaps {{[0-9]+}}(%rsp), %xmm0 # 16-byte Reload
; CHECK-NEXT: vpermilpd {{.*#+}} xmm0 = xmm0[1,0]
; CHECK-NEXT: # kill: %YMM7<def> %YMM7<kill> %ZMM7<kill>
; CHECK-NEXT: vextractf128 $1, %ymm7, %xmm7
; CHECK-NEXT: vmovsd %xmm0, {{[0-9]+}}(%rsp) # 8-byte Spill
; CHECK-NEXT: vmovaps %xmm7, %xmm0
; CHECK-NEXT: vmovsd %xmm0, {{[0-9]+}}(%rsp) # 8-byte Spill
; CHECK-NEXT: vmovaps {{[0-9]+}}(%rsp), %xmm0 # 16-byte Reload
; CHECK-NEXT: vpermilpd {{.*#+}} xmm0 = xmm0[1,0]
; CHECK-NEXT: vpermilpd {{.*#+}} xmm10 = xmm10[1,0]
; CHECK-NEXT: vpermilpd {{.*#+}} xmm9 = xmm9[1,0]
; CHECK-NEXT: vpermilpd {{.*#+}} xmm8 = xmm8[1,0]
; CHECK-NEXT: vpermilpd {{.*#+}} xmm7 = xmm7[1,0]
; CHECK-NEXT: vmovsd %xmm0, {{[0-9]+}}(%rsp) # 8-byte Spill
; CHECK-NEXT: vmovsd {{[0-9]+}}(%rsp), %xmm0 # 8-byte Reload
; CHECK-NEXT: # xmm0 = mem[0],zero
; CHECK-NEXT: vmovsd %xmm0, {{[0-9]+}}(%rsp) # 8-byte Spill
; CHECK-NEXT: vmovsd {{[0-9]+}}(%rsp), %xmm0 # 8-byte Reload
; CHECK-NEXT: # xmm0 = mem[0],zero
; CHECK-NEXT: vmovsd %xmm0, {{[0-9]+}}(%rsp) # 8-byte Spill
; CHECK-NEXT: vmovsd {{[0-9]+}}(%rsp), %xmm0 # 8-byte Reload
; CHECK-NEXT: # xmm0 = mem[0],zero
; CHECK-NEXT: vmovsd %xmm0, {{[0-9]+}}(%rsp) # 8-byte Spill
; CHECK-NEXT: vmovsd {{[0-9]+}}(%rsp), %xmm0 # 8-byte Reload
; CHECK-NEXT: # xmm0 = mem[0],zero
; CHECK-NEXT: vmovsd %xmm0, {{[0-9]+}}(%rsp) # 8-byte Spill
; CHECK-NEXT: vmovsd {{[0-9]+}}(%rsp), %xmm0 # 8-byte Reload
; CHECK-NEXT: # xmm0 = mem[0],zero
; CHECK-NEXT: vmovsd %xmm0, {{[0-9]+}}(%rsp) # 8-byte Spill
; CHECK-NEXT: vmovsd {{[0-9]+}}(%rsp), %xmm0 # 8-byte Reload
; CHECK-NEXT: # xmm0 = mem[0],zero
; CHECK-NEXT: vmovsd %xmm0, {{[0-9]+}}(%rsp) # 8-byte Spill
; CHECK-NEXT: vmovsd {{[0-9]+}}(%rsp), %xmm0 # 8-byte Reload
; CHECK-NEXT: # xmm0 = mem[0],zero
; CHECK-NEXT: vmovsd %xmm0, {{[0-9]+}}(%rsp) # 8-byte Spill
; CHECK-NEXT: vmovsd {{[0-9]+}}(%rsp), %xmm0 # 8-byte Reload
; CHECK-NEXT: # xmm0 = mem[0],zero
; CHECK-NEXT: vmovsd %xmm0, {{[0-9]+}}(%rsp) # 8-byte Spill
; CHECK-NEXT: vmovsd {{[0-9]+}}(%rsp), %xmm0 # 8-byte Reload
; CHECK-NEXT: # xmm0 = mem[0],zero
; CHECK-NEXT: vmovsd %xmm0, {{[0-9]+}}(%rsp) # 8-byte Spill
; CHECK-NEXT: vmovsd {{[0-9]+}}(%rsp), %xmm0 # 8-byte Reload
; CHECK-NEXT: # xmm0 = mem[0],zero
; CHECK-NEXT: vmovsd %xmm0, {{[0-9]+}}(%rsp) # 8-byte Spill
; CHECK-NEXT: vmovsd {{[0-9]+}}(%rsp), %xmm0 # 8-byte Reload
; CHECK-NEXT: # xmm0 = mem[0],zero
; CHECK-NEXT: vmovsd %xmm0, {{[0-9]+}}(%rsp) # 8-byte Spill
; CHECK-NEXT: vmovsd {{[0-9]+}}(%rsp), %xmm0 # 8-byte Reload
; CHECK-NEXT: # xmm0 = mem[0],zero
; CHECK-NEXT: vmovsd %xmm0, {{[0-9]+}}(%rsp) # 8-byte Spill
; CHECK-NEXT: vmovsd {{[0-9]+}}(%rsp), %xmm0 # 8-byte Reload
; CHECK-NEXT: # xmm0 = mem[0],zero
; CHECK-NEXT: vmovsd %xmm0, {{[0-9]+}}(%rsp) # 8-byte Spill
; CHECK-NEXT: vmovsd {{[0-9]+}}(%rsp), %xmm0 # 8-byte Reload
; CHECK-NEXT: # xmm0 = mem[0],zero
; CHECK-NEXT: vmovsd %xmm0, {{[0-9]+}}(%rsp) # 8-byte Spill
; CHECK-NEXT: vmovsd {{[0-9]+}}(%rsp), %xmm0 # 8-byte Reload
; CHECK-NEXT: # xmm0 = mem[0],zero
; CHECK-NEXT: vmovsd %xmm0, {{[0-9]+}}(%rsp) # 8-byte Spill
; CHECK-NEXT: vmovsd {{[0-9]+}}(%rsp), %xmm0 # 8-byte Reload
; CHECK-NEXT: # xmm0 = mem[0],zero
; CHECK-NEXT: vmovsd %xmm0, {{[0-9]+}}(%rsp) # 8-byte Spill
; CHECK-NEXT: vmovsd {{[0-9]+}}(%rsp), %xmm0 # 8-byte Reload
; CHECK-NEXT: # xmm0 = mem[0],zero
; CHECK-NEXT: vmovsd %xmm0, {{[0-9]+}}(%rsp) # 8-byte Spill
; CHECK-NEXT: vmovsd {{[0-9]+}}(%rsp), %xmm0 # 8-byte Reload
; CHECK-NEXT: # xmm0 = mem[0],zero
; CHECK-NEXT: vmovsd %xmm0, {{[0-9]+}}(%rsp) # 8-byte Spill
; CHECK-NEXT: vmovsd {{[0-9]+}}(%rsp), %xmm0 # 8-byte Reload
; CHECK-NEXT: # xmm0 = mem[0],zero
; CHECK-NEXT: vmovsd %xmm0, {{[0-9]+}}(%rsp) # 8-byte Spill
; CHECK-NEXT: vmovsd {{[0-9]+}}(%rsp), %xmm0 # 8-byte Reload
; CHECK-NEXT: # xmm0 = mem[0],zero
; CHECK-NEXT: vmovsd %xmm0, {{[0-9]+}}(%rsp) # 8-byte Spill
; CHECK-NEXT: vmovsd {{[0-9]+}}(%rsp), %xmm0 # 8-byte Reload
; CHECK-NEXT: # xmm0 = mem[0],zero
; CHECK-NEXT: vmovsd %xmm0, {{[0-9]+}}(%rsp) # 8-byte Spill
; CHECK-NEXT: vmovsd {{[0-9]+}}(%rsp), %xmm0 # 8-byte Reload
; CHECK-NEXT: # xmm0 = mem[0],zero
; CHECK-NEXT: vmovsd %xmm0, {{[0-9]+}}(%rsp) # 8-byte Spill
; CHECK-NEXT: vmovsd {{[0-9]+}}(%rsp), %xmm0 # 8-byte Reload
; CHECK-NEXT: # xmm0 = mem[0],zero
; CHECK-NEXT: vmovsd %xmm8, {{[0-9]+}}(%rsp) # 8-byte Spill
; CHECK-NEXT: vmovsd %xmm13, {{[0-9]+}}(%rsp) # 8-byte Spill
; CHECK-NEXT: vmovsd %xmm1, {{[0-9]+}}(%rsp) # 8-byte Spill
; CHECK-NEXT: vmovsd %xmm14, {{[0-9]+}}(%rsp) # 8-byte Spill
; CHECK-NEXT: vmovsd %xmm2, {{[0-9]+}}(%rsp) # 8-byte Spill
; CHECK-NEXT: vmovsd %xmm4, {{[0-9]+}}(%rsp) # 8-byte Spill
; CHECK-NEXT: vmovsd %xmm9, {{[0-9]+}}(%rsp) # 8-byte Spill
; CHECK-NEXT: vmovsd %xmm10, {{[0-9]+}}(%rsp) # 8-byte Spill
; CHECK-NEXT: vmovsd %xmm15, {{[0-9]+}}(%rsp) # 8-byte Spill
; CHECK-NEXT: vmovsd %xmm11, {{[0-9]+}}(%rsp) # 8-byte Spill
; CHECK-NEXT: vmovsd %xmm3, {{[0-9]+}}(%rsp) # 8-byte Spill
; CHECK-NEXT: vmovsd %xmm6, {{[0-9]+}}(%rsp) # 8-byte Spill
; CHECK-NEXT: vmovsd %xmm5, {{[0-9]+}}(%rsp) # 8-byte Spill
; CHECK-NEXT: vmovsd %xmm12, {{[0-9]+}}(%rsp) # 8-byte Spill
; CHECK-NEXT: vmovsd %xmm0, {{[0-9]+}}(%rsp) # 8-byte Spill
; CHECK-NEXT: vmovsd %xmm7, {{[0-9]+}}(%rsp) # 8-byte Spill
; CHECK-NEXT: movq %rbp, %rsp
; CHECK-NEXT: popq %rbp
; CHECK-NEXT: vzeroupper
; CHECK-NEXT: retq
entry:
%v = call fastcc <38 x double> @test()
%v.0 = extractelement <38 x double> %v, i32 0
ret void
}