; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -mtriple=x86_64-unknown -mattr=+avx512f -O0 | FileCheck %s
define <16 x float> @makefloat(float %f1, float %f2, float %f3, float %f4, float %f5, float %f6, float %f7, float %f8, float %f9, float %f10, float %f11, float %f12, float %f13, float %f14, float %f15, float %f16) #0 {
; CHECK-LABEL: makefloat:
; 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 $-64, %rsp
; CHECK-NEXT: subq $256, %rsp # imm = 0x100
; CHECK-NEXT: vmovss {{.*#+}} xmm8 = mem[0],zero,zero,zero
; CHECK-NEXT: vmovss {{.*#+}} xmm8 = mem[0],zero,zero,zero
; CHECK-NEXT: vmovss {{.*#+}} xmm8 = mem[0],zero,zero,zero
; CHECK-NEXT: vmovss {{.*#+}} xmm8 = mem[0],zero,zero,zero
; CHECK-NEXT: vmovss {{.*#+}} xmm8 = mem[0],zero,zero,zero
; CHECK-NEXT: vmovss {{.*#+}} xmm8 = mem[0],zero,zero,zero
; CHECK-NEXT: vmovss {{.*#+}} xmm8 = mem[0],zero,zero,zero
; CHECK-NEXT: vmovss {{.*#+}} xmm8 = mem[0],zero,zero,zero
; CHECK-NEXT: vmovss %xmm0, {{[0-9]+}}(%rsp)
; CHECK-NEXT: vmovss %xmm1, {{[0-9]+}}(%rsp)
; CHECK-NEXT: vmovss %xmm2, {{[0-9]+}}(%rsp)
; CHECK-NEXT: vmovss %xmm3, {{[0-9]+}}(%rsp)
; CHECK-NEXT: vmovss %xmm4, {{[0-9]+}}(%rsp)
; CHECK-NEXT: vmovss %xmm5, {{[0-9]+}}(%rsp)
; CHECK-NEXT: vmovss %xmm6, {{[0-9]+}}(%rsp)
; CHECK-NEXT: vmovss %xmm7, {{[0-9]+}}(%rsp)
; CHECK-NEXT: vmovss {{.*#+}} xmm15 = mem[0],zero,zero,zero
; CHECK-NEXT: vmovss {{.*#+}} xmm14 = mem[0],zero,zero,zero
; CHECK-NEXT: vmovss {{.*#+}} xmm13 = mem[0],zero,zero,zero
; CHECK-NEXT: vmovss {{.*#+}} xmm12 = mem[0],zero,zero,zero
; CHECK-NEXT: vmovss {{.*#+}} xmm11 = mem[0],zero,zero,zero
; CHECK-NEXT: vmovss {{.*#+}} xmm10 = mem[0],zero,zero,zero
; CHECK-NEXT: vmovss {{.*#+}} xmm9 = mem[0],zero,zero,zero
; CHECK-NEXT: vmovss {{.*#+}} xmm8 = mem[0],zero,zero,zero
; CHECK-NEXT: vmovss {{.*#+}} xmm7 = mem[0],zero,zero,zero
; CHECK-NEXT: vmovss {{.*#+}} xmm6 = mem[0],zero,zero,zero
; CHECK-NEXT: vmovss {{.*#+}} xmm5 = mem[0],zero,zero,zero
; CHECK-NEXT: vmovss {{.*#+}} xmm4 = mem[0],zero,zero,zero
; CHECK-NEXT: vmovss {{.*#+}} xmm3 = mem[0],zero,zero,zero
; CHECK-NEXT: vmovss {{.*#+}} xmm2 = mem[0],zero,zero,zero
; CHECK-NEXT: vmovss {{.*#+}} xmm1 = mem[0],zero,zero,zero
; CHECK-NEXT: vmovss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; CHECK-NEXT: vmovss %xmm15, {{[0-9]+}}(%rsp)
; CHECK-NEXT: vmovss %xmm14, {{[0-9]+}}(%rsp)
; CHECK-NEXT: vmovss %xmm13, {{[0-9]+}}(%rsp)
; CHECK-NEXT: vmovss %xmm12, {{[0-9]+}}(%rsp)
; CHECK-NEXT: vmovss %xmm11, {{[0-9]+}}(%rsp)
; CHECK-NEXT: vmovss %xmm10, {{[0-9]+}}(%rsp)
; CHECK-NEXT: vmovss %xmm9, {{[0-9]+}}(%rsp)
; CHECK-NEXT: vmovss %xmm8, {{[0-9]+}}(%rsp)
; CHECK-NEXT: vmovss %xmm7, {{[0-9]+}}(%rsp)
; CHECK-NEXT: vmovss %xmm6, {{[0-9]+}}(%rsp)
; CHECK-NEXT: vmovss %xmm5, {{[0-9]+}}(%rsp)
; CHECK-NEXT: vmovss %xmm4, {{[0-9]+}}(%rsp)
; CHECK-NEXT: vmovss %xmm3, {{[0-9]+}}(%rsp)
; CHECK-NEXT: vmovss %xmm2, {{[0-9]+}}(%rsp)
; CHECK-NEXT: vmovss %xmm1, {{[0-9]+}}(%rsp)
; CHECK-NEXT: vmovss %xmm0, {{[0-9]+}}(%rsp)
; CHECK-NEXT: vmovss {{.*#+}} xmm1 = mem[0],zero,zero,zero
; CHECK-NEXT: vmovss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; CHECK-NEXT: vinsertps {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[2,3]
; CHECK-NEXT: vmovss {{.*#+}} xmm1 = mem[0],zero,zero,zero
; CHECK-NEXT: vinsertps {{.*#+}} xmm0 = xmm0[0,1],xmm1[0],xmm0[3]
; CHECK-NEXT: vmovss {{.*#+}} xmm1 = mem[0],zero,zero,zero
; CHECK-NEXT: vinsertps {{.*#+}} xmm1 = xmm0[0,1,2],xmm1[0]
; CHECK-NEXT: vmovss {{.*#+}} xmm2 = mem[0],zero,zero,zero
; CHECK-NEXT: vmovss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; CHECK-NEXT: vinsertps {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[2,3]
; CHECK-NEXT: vmovss {{.*#+}} xmm2 = mem[0],zero,zero,zero
; CHECK-NEXT: vinsertps {{.*#+}} xmm0 = xmm0[0,1],xmm2[0],xmm0[3]
; CHECK-NEXT: vmovss {{.*#+}} xmm2 = mem[0],zero,zero,zero
; CHECK-NEXT: vinsertps {{.*#+}} xmm2 = xmm0[0,1,2],xmm2[0]
; CHECK-NEXT: # implicit-def: $ymm0
; CHECK-NEXT: vmovaps %xmm2, %xmm0
; CHECK-NEXT: vinsertf128 $1, %xmm1, %ymm0, %ymm1
; CHECK-NEXT: vmovss {{.*#+}} xmm2 = mem[0],zero,zero,zero
; CHECK-NEXT: vmovss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; CHECK-NEXT: vinsertps {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[2,3]
; CHECK-NEXT: vmovss {{.*#+}} xmm2 = mem[0],zero,zero,zero
; CHECK-NEXT: vinsertps {{.*#+}} xmm0 = xmm0[0,1],xmm2[0],xmm0[3]
; CHECK-NEXT: vmovss {{.*#+}} xmm2 = mem[0],zero,zero,zero
; CHECK-NEXT: vinsertps {{.*#+}} xmm2 = xmm0[0,1,2],xmm2[0]
; CHECK-NEXT: vmovss {{.*#+}} xmm3 = mem[0],zero,zero,zero
; CHECK-NEXT: vmovss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; CHECK-NEXT: vinsertps {{.*#+}} xmm0 = xmm0[0],xmm3[0],xmm0[2,3]
; CHECK-NEXT: vmovss {{.*#+}} xmm3 = mem[0],zero,zero,zero
; CHECK-NEXT: vinsertps {{.*#+}} xmm0 = xmm0[0,1],xmm3[0],xmm0[3]
; CHECK-NEXT: vmovss {{.*#+}} xmm3 = mem[0],zero,zero,zero
; CHECK-NEXT: vinsertps {{.*#+}} xmm3 = xmm0[0,1,2],xmm3[0]
; CHECK-NEXT: # implicit-def: $ymm0
; CHECK-NEXT: vmovaps %xmm3, %xmm0
; CHECK-NEXT: vinsertf128 $1, %xmm2, %ymm0, %ymm2
; CHECK-NEXT: # implicit-def: $zmm0
; CHECK-NEXT: vmovaps %ymm2, %ymm0
; CHECK-NEXT: vinsertf64x4 $1, %ymm1, %zmm0, %zmm0
; CHECK-NEXT: vmovaps %zmm0, {{[0-9]+}}(%rsp)
; CHECK-NEXT: vmovaps {{[0-9]+}}(%rsp), %zmm0
; CHECK-NEXT: movq %rbp, %rsp
; CHECK-NEXT: popq %rbp
; CHECK-NEXT: .cfi_def_cfa %rsp, 8
; CHECK-NEXT: retq
entry:
%__A.addr.i = alloca float, align 4
%__B.addr.i = alloca float, align 4
%__C.addr.i = alloca float, align 4
%__D.addr.i = alloca float, align 4
%__E.addr.i = alloca float, align 4
%__F.addr.i = alloca float, align 4
%__G.addr.i = alloca float, align 4
%__H.addr.i = alloca float, align 4
%__I.addr.i = alloca float, align 4
%__J.addr.i = alloca float, align 4
%__K.addr.i = alloca float, align 4
%__L.addr.i = alloca float, align 4
%__M.addr.i = alloca float, align 4
%__N.addr.i = alloca float, align 4
%__O.addr.i = alloca float, align 4
%__P.addr.i = alloca float, align 4
%.compoundliteral.i = alloca <16 x float>, align 64
%f1.addr = alloca float, align 4
%f2.addr = alloca float, align 4
%f3.addr = alloca float, align 4
%f4.addr = alloca float, align 4
%f5.addr = alloca float, align 4
%f6.addr = alloca float, align 4
%f7.addr = alloca float, align 4
%f8.addr = alloca float, align 4
%f9.addr = alloca float, align 4
%f10.addr = alloca float, align 4
%f11.addr = alloca float, align 4
%f12.addr = alloca float, align 4
%f13.addr = alloca float, align 4
%f14.addr = alloca float, align 4
%f15.addr = alloca float, align 4
%f16.addr = alloca float, align 4
store float %f1, ptr %f1.addr, align 4
store float %f2, ptr %f2.addr, align 4
store float %f3, ptr %f3.addr, align 4
store float %f4, ptr %f4.addr, align 4
store float %f5, ptr %f5.addr, align 4
store float %f6, ptr %f6.addr, align 4
store float %f7, ptr %f7.addr, align 4
store float %f8, ptr %f8.addr, align 4
store float %f9, ptr %f9.addr, align 4
store float %f10, ptr %f10.addr, align 4
store float %f11, ptr %f11.addr, align 4
store float %f12, ptr %f12.addr, align 4
store float %f13, ptr %f13.addr, align 4
store float %f14, ptr %f14.addr, align 4
store float %f15, ptr %f15.addr, align 4
store float %f16, ptr %f16.addr, align 4
%0 = load float, ptr %f16.addr, align 4
%1 = load float, ptr %f15.addr, align 4
%2 = load float, ptr %f14.addr, align 4
%3 = load float, ptr %f13.addr, align 4
%4 = load float, ptr %f12.addr, align 4
%5 = load float, ptr %f11.addr, align 4
%6 = load float, ptr %f10.addr, align 4
%7 = load float, ptr %f9.addr, align 4
%8 = load float, ptr %f8.addr, align 4
%9 = load float, ptr %f7.addr, align 4
%10 = load float, ptr %f6.addr, align 4
%11 = load float, ptr %f5.addr, align 4
%12 = load float, ptr %f4.addr, align 4
%13 = load float, ptr %f3.addr, align 4
%14 = load float, ptr %f2.addr, align 4
%15 = load float, ptr %f1.addr, align 4
store float %0, ptr %__A.addr.i, align 4
store float %1, ptr %__B.addr.i, align 4
store float %2, ptr %__C.addr.i, align 4
store float %3, ptr %__D.addr.i, align 4
store float %4, ptr %__E.addr.i, align 4
store float %5, ptr %__F.addr.i, align 4
store float %6, ptr %__G.addr.i, align 4
store float %7, ptr %__H.addr.i, align 4
store float %8, ptr %__I.addr.i, align 4
store float %9, ptr %__J.addr.i, align 4
store float %10, ptr %__K.addr.i, align 4
store float %11, ptr %__L.addr.i, align 4
store float %12, ptr %__M.addr.i, align 4
store float %13, ptr %__N.addr.i, align 4
store float %14, ptr %__O.addr.i, align 4
store float %15, ptr %__P.addr.i, align 4
%16 = load float, ptr %__P.addr.i, align 4
%vecinit.i = insertelement <16 x float> undef, float %16, i32 0
%17 = load float, ptr %__O.addr.i, align 4
%vecinit1.i = insertelement <16 x float> %vecinit.i, float %17, i32 1
%18 = load float, ptr %__N.addr.i, align 4
%vecinit2.i = insertelement <16 x float> %vecinit1.i, float %18, i32 2
%19 = load float, ptr %__M.addr.i, align 4
%vecinit3.i = insertelement <16 x float> %vecinit2.i, float %19, i32 3
%20 = load float, ptr %__L.addr.i, align 4
%vecinit4.i = insertelement <16 x float> %vecinit3.i, float %20, i32 4
%21 = load float, ptr %__K.addr.i, align 4
%vecinit5.i = insertelement <16 x float> %vecinit4.i, float %21, i32 5
%22 = load float, ptr %__J.addr.i, align 4
%vecinit6.i = insertelement <16 x float> %vecinit5.i, float %22, i32 6
%23 = load float, ptr %__I.addr.i, align 4
%vecinit7.i = insertelement <16 x float> %vecinit6.i, float %23, i32 7
%24 = load float, ptr %__H.addr.i, align 4
%vecinit8.i = insertelement <16 x float> %vecinit7.i, float %24, i32 8
%25 = load float, ptr %__G.addr.i, align 4
%vecinit9.i = insertelement <16 x float> %vecinit8.i, float %25, i32 9
%26 = load float, ptr %__F.addr.i, align 4
%vecinit10.i = insertelement <16 x float> %vecinit9.i, float %26, i32 10
%27 = load float, ptr %__E.addr.i, align 4
%vecinit11.i = insertelement <16 x float> %vecinit10.i, float %27, i32 11
%28 = load float, ptr %__D.addr.i, align 4
%vecinit12.i = insertelement <16 x float> %vecinit11.i, float %28, i32 12
%29 = load float, ptr %__C.addr.i, align 4
%vecinit13.i = insertelement <16 x float> %vecinit12.i, float %29, i32 13
%30 = load float, ptr %__B.addr.i, align 4
%vecinit14.i = insertelement <16 x float> %vecinit13.i, float %30, i32 14
%31 = load float, ptr %__A.addr.i, align 4
%vecinit15.i = insertelement <16 x float> %vecinit14.i, float %31, i32 15
store <16 x float> %vecinit15.i, ptr %.compoundliteral.i, align 64
%32 = load <16 x float>, ptr %.compoundliteral.i, align 64
ret <16 x float> %32
}
Codebase Browser
llvm