forked from OSchip/llvm-project
153 lines
7.9 KiB
LLVM
153 lines
7.9 KiB
LLVM
; 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 $1536, %rsp # imm = 0x600
|
|
; CHECK-NEXT: leaq {{[0-9]+}}(%rsp), %rdi
|
|
; CHECK-NEXT: callq test
|
|
; CHECK-NEXT: vmovupd {{[0-9]+}}(%rsp), %xmm0
|
|
; CHECK-NEXT: vmovupd {{[0-9]+}}(%rsp), %xmm1
|
|
; CHECK-NEXT: vmovaps %xmm1, %xmm2
|
|
; CHECK-NEXT: vmovupd {{[0-9]+}}(%rsp), %xmm3
|
|
; CHECK-NEXT: vmovaps %xmm3, %xmm4
|
|
; CHECK-NEXT: vmovupd {{[0-9]+}}(%rsp), %xmm5
|
|
; CHECK-NEXT: vmovaps %xmm5, %xmm6
|
|
; CHECK-NEXT: vmovupd {{[0-9]+}}(%rsp), %xmm7
|
|
; CHECK-NEXT: vmovaps %xmm7, %xmm8
|
|
; CHECK-NEXT: vmovupd {{[0-9]+}}(%rsp), %xmm9
|
|
; CHECK-NEXT: vmovaps %xmm9, %xmm10
|
|
; CHECK-NEXT: vmovupd {{[0-9]+}}(%rsp), %xmm11
|
|
; CHECK-NEXT: vmovaps %xmm11, %xmm12
|
|
; CHECK-NEXT: vmovupd {{[0-9]+}}(%rsp), %xmm13
|
|
; CHECK-NEXT: vmovaps %xmm13, %xmm14
|
|
; CHECK-NEXT: vmovupd {{[0-9]+}}(%rsp), %xmm15
|
|
; CHECK-NEXT: vmovaps %zmm15, %zmm16
|
|
; CHECK-NEXT: vmovsd %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill
|
|
; CHECK-NEXT: vmovupd {{[0-9]+}}(%rsp), %xmm0
|
|
; CHECK-NEXT: vmovaps %zmm0, %zmm17
|
|
; CHECK-NEXT: vmovaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
|
; CHECK-NEXT: vmovupd {{[0-9]+}}(%rsp), %xmm0
|
|
; CHECK-NEXT: vmovaps %zmm0, %zmm18
|
|
; CHECK-NEXT: vmovaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
|
; CHECK-NEXT: vmovupd {{[0-9]+}}(%rsp), %xmm0
|
|
; CHECK-NEXT: vmovaps %zmm0, %zmm19
|
|
; CHECK-NEXT: vmovaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
|
; CHECK-NEXT: vmovupd {{[0-9]+}}(%rsp), %xmm0
|
|
; CHECK-NEXT: vmovaps %zmm0, %zmm20
|
|
; CHECK-NEXT: vmovaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
|
; CHECK-NEXT: vmovupd {{[0-9]+}}(%rsp), %xmm0
|
|
; CHECK-NEXT: vmovaps %zmm0, %zmm21
|
|
; CHECK-NEXT: vmovaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
|
; CHECK-NEXT: vmovupd {{[0-9]+}}(%rsp), %xmm0
|
|
; CHECK-NEXT: vmovaps %zmm0, %zmm22
|
|
; CHECK-NEXT: vmovaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
|
; CHECK-NEXT: vmovupd {{[0-9]+}}(%rsp), %xmm0
|
|
; CHECK-NEXT: vmovaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
|
; CHECK-NEXT: vmovupd {{[0-9]+}}(%rsp), %xmm0
|
|
; CHECK-NEXT: vmovaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
|
; CHECK-NEXT: vmovupd {{[0-9]+}}(%rsp), %xmm0
|
|
; CHECK-NEXT: vmovaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
|
; CHECK-NEXT: vmovupd {{[0-9]+}}(%rsp), %xmm0
|
|
; CHECK-NEXT: vmovaps %zmm0, %zmm23
|
|
; CHECK-NEXT: vmovaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
|
; CHECK-NEXT: vmovaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Reload
|
|
; CHECK-NEXT: vmovsd %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill
|
|
; CHECK-NEXT: vmovaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Reload
|
|
; CHECK-NEXT: vmovsd %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill
|
|
; CHECK-NEXT: vmovaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Reload
|
|
; CHECK-NEXT: vpermilpd {{.*#+}} xmm1 = xmm1[1,0]
|
|
; CHECK-NEXT: vpermilpd {{.*#+}} xmm3 = xmm3[1,0]
|
|
; CHECK-NEXT: vpermilpd {{.*#+}} xmm5 = xmm5[1,0]
|
|
; CHECK-NEXT: vpermilpd {{.*#+}} xmm7 = xmm7[1,0]
|
|
; CHECK-NEXT: vpermilpd {{.*#+}} xmm9 = xmm9[1,0]
|
|
; CHECK-NEXT: vpermilpd {{.*#+}} xmm11 = xmm11[1,0]
|
|
; CHECK-NEXT: vpermilpd {{.*#+}} xmm13 = xmm13[1,0]
|
|
; CHECK-NEXT: vpermilpd {{.*#+}} xmm15 = xmm15[1,0]
|
|
; CHECK-NEXT: vmovsd %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill
|
|
; CHECK-NEXT: vmovaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Reload
|
|
; CHECK-NEXT: vpermilpd {{.*#+}} xmm0 = xmm0[1,0]
|
|
; CHECK-NEXT: vmovsd %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill
|
|
; CHECK-NEXT: vmovaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Reload
|
|
; CHECK-NEXT: vpermilpd {{.*#+}} xmm0 = xmm0[1,0]
|
|
; CHECK-NEXT: vmovsd %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill
|
|
; CHECK-NEXT: vmovaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Reload
|
|
; CHECK-NEXT: vpermilpd {{.*#+}} xmm0 = xmm0[1,0]
|
|
; CHECK-NEXT: vmovsd %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill
|
|
; CHECK-NEXT: vmovaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Reload
|
|
; CHECK-NEXT: vpermilpd {{.*#+}} xmm0 = xmm0[1,0]
|
|
; CHECK-NEXT: vmovsd %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill
|
|
; CHECK-NEXT: vmovaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Reload
|
|
; CHECK-NEXT: vpermilpd {{.*#+}} xmm0 = xmm0[1,0]
|
|
; CHECK-NEXT: vmovsd %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill
|
|
; CHECK-NEXT: vmovaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Reload
|
|
; CHECK-NEXT: vpermilpd {{.*#+}} xmm0 = xmm0[1,0]
|
|
; CHECK-NEXT: vmovsd %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill
|
|
; CHECK-NEXT: vmovaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Reload
|
|
; CHECK-NEXT: vpermilpd {{.*#+}} xmm0 = xmm0[1,0]
|
|
; CHECK-NEXT: vmovsd %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill
|
|
; CHECK-NEXT: vmovaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Reload
|
|
; CHECK-NEXT: vpermilpd {{.*#+}} xmm0 = xmm0[1,0]
|
|
; CHECK-NEXT: vmovsd %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill
|
|
; CHECK-NEXT: vmovaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Reload
|
|
; CHECK-NEXT: vpermilpd {{.*#+}} xmm0 = xmm0[1,0]
|
|
; CHECK-NEXT: vmovsd %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill
|
|
; CHECK-NEXT: vmovaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Reload
|
|
; CHECK-NEXT: vpermilpd {{.*#+}} xmm0 = xmm0[1,0]
|
|
; CHECK-NEXT: vmovsd {{.*#+}} xmm24 = mem[0],zero
|
|
; CHECK-NEXT: vmovsd {{[-0-9]+}}(%r{{[sb]}}p), %xmm25 # 8-byte Reload
|
|
; CHECK-NEXT: # xmm25 = mem[0],zero
|
|
; CHECK-NEXT: vmovsd {{[-0-9]+}}(%r{{[sb]}}p), %xmm26 # 8-byte Reload
|
|
; CHECK-NEXT: # xmm26 = mem[0],zero
|
|
; CHECK-NEXT: vmovsd {{[-0-9]+}}(%r{{[sb]}}p), %xmm27 # 8-byte Reload
|
|
; CHECK-NEXT: # xmm27 = mem[0],zero
|
|
; CHECK-NEXT: vmovsd {{[-0-9]+}}(%r{{[sb]}}p), %xmm28 # 8-byte Reload
|
|
; CHECK-NEXT: # xmm28 = mem[0],zero
|
|
; CHECK-NEXT: vmovsd {{[-0-9]+}}(%r{{[sb]}}p), %xmm29 # 8-byte Reload
|
|
; CHECK-NEXT: # xmm29 = mem[0],zero
|
|
; CHECK-NEXT: vmovsd {{[-0-9]+}}(%r{{[sb]}}p), %xmm30 # 8-byte Reload
|
|
; CHECK-NEXT: # xmm30 = mem[0],zero
|
|
; CHECK-NEXT: vmovsd {{[-0-9]+}}(%r{{[sb]}}p), %xmm31 # 8-byte Reload
|
|
; CHECK-NEXT: # xmm31 = mem[0],zero
|
|
; CHECK-NEXT: vmovsd %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill
|
|
; CHECK-NEXT: vmovsd {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 8-byte Reload
|
|
; CHECK-NEXT: # xmm0 = mem[0],zero
|
|
; CHECK-NEXT: vmovsd %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill
|
|
; CHECK-NEXT: vmovsd {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 8-byte Reload
|
|
; CHECK-NEXT: # xmm0 = mem[0],zero
|
|
; CHECK-NEXT: vmovsd %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill
|
|
; CHECK-NEXT: vmovsd {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 8-byte Reload
|
|
; CHECK-NEXT: # xmm0 = mem[0],zero
|
|
; CHECK-NEXT: vmovsd %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill
|
|
; CHECK-NEXT: vmovsd {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 8-byte Reload
|
|
; CHECK-NEXT: # xmm0 = mem[0],zero
|
|
; CHECK-NEXT: vmovsd %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill
|
|
; CHECK-NEXT: vmovsd {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 8-byte Reload
|
|
; CHECK-NEXT: # xmm0 = mem[0],zero
|
|
; CHECK-NEXT: vmovsd %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill
|
|
; CHECK-NEXT: vmovsd {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 8-byte Reload
|
|
; CHECK-NEXT: # xmm0 = mem[0],zero
|
|
; CHECK-NEXT: vmovsd %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill
|
|
; CHECK-NEXT: vmovsd {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 8-byte Reload
|
|
; CHECK-NEXT: # xmm0 = mem[0],zero
|
|
; CHECK-NEXT: movq %rbp, %rsp
|
|
; CHECK-NEXT: popq %rbp
|
|
; CHECK-NEXT: .cfi_def_cfa %rsp, 8
|
|
; 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
|
|
}
|
|
|