; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -mtriple=i686-unknown-unknown | FileCheck %s --check-prefix=X86-X87
; RUN: llc < %s -mtriple=i686-unknown-unknown -mattr=+sse2 | FileCheck %s --check-prefix=X86-SSE
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+sse2 | FileCheck %s --check-prefix=X64

; Ideally this would compile to 5 multiplies.

define double @pow_wrapper(double %a) nounwind readonly ssp noredzone {
; X86-X87-LABEL: pow_wrapper:
; X86-X87:       # %bb.0:
; X86-X87-NEXT:    fldl {{[0-9]+}}(%esp)
; X86-X87-NEXT:    fld %st(0)
; X86-X87-NEXT:    fmul %st(1), %st
; X86-X87-NEXT:    fmul %st, %st(1)
; X86-X87-NEXT:    fmul %st, %st(0)
; X86-X87-NEXT:    fmul %st, %st(1)
; X86-X87-NEXT:    fmul %st, %st(0)
; X86-X87-NEXT:    fmulp %st, %st(1)
; X86-X87-NEXT:    retl
;
; X86-SSE-LABEL: pow_wrapper:
; X86-SSE:       # %bb.0:
; X86-SSE-NEXT:    pushl %ebp
; X86-SSE-NEXT:    movl %esp, %ebp
; X86-SSE-NEXT:    andl $-8, %esp
; X86-SSE-NEXT:    subl $8, %esp
; X86-SSE-NEXT:    movsd {{.*#+}} xmm0 = mem[0],zero
; X86-SSE-NEXT:    movapd %xmm0, %xmm1
; X86-SSE-NEXT:    mulsd %xmm0, %xmm1
; X86-SSE-NEXT:    mulsd %xmm1, %xmm0
; X86-SSE-NEXT:    mulsd %xmm1, %xmm1
; X86-SSE-NEXT:    mulsd %xmm1, %xmm0
; X86-SSE-NEXT:    mulsd %xmm1, %xmm1
; X86-SSE-NEXT:    mulsd %xmm0, %xmm1
; X86-SSE-NEXT:    movsd %xmm1, (%esp)
; X86-SSE-NEXT:    fldl (%esp)
; X86-SSE-NEXT:    movl %ebp, %esp
; X86-SSE-NEXT:    popl %ebp
; X86-SSE-NEXT:    retl
;
; X64-LABEL: pow_wrapper:
; X64:       # %bb.0:
; X64-NEXT:    movapd %xmm0, %xmm1
; X64-NEXT:    mulsd %xmm0, %xmm1
; X64-NEXT:    mulsd %xmm1, %xmm0
; X64-NEXT:    mulsd %xmm1, %xmm1
; X64-NEXT:    mulsd %xmm1, %xmm0
; X64-NEXT:    mulsd %xmm1, %xmm1
; X64-NEXT:    mulsd %xmm1, %xmm0
; X64-NEXT:    retq
  %ret = tail call double @llvm.powi.f64.i32(double %a, i32 15) nounwind ; <double> [#uses=1]
  ret double %ret
}

define double @pow_wrapper_optsize(double %a) nounwind optsize {
; X86-X87-LABEL: pow_wrapper_optsize:
; X86-X87:       # %bb.0:
; X86-X87-NEXT:    subl $12, %esp
; X86-X87-NEXT:    fldl {{[0-9]+}}(%esp)
; X86-X87-NEXT:    fstpl (%esp)
; X86-X87-NEXT:    movl $15, {{[0-9]+}}(%esp)
; X86-X87-NEXT:    calll __powidf2
; X86-X87-NEXT:    addl $12, %esp
; X86-X87-NEXT:    retl
;
; X86-SSE-LABEL: pow_wrapper_optsize:
; X86-SSE:       # %bb.0:
; X86-SSE-NEXT:    subl $12, %esp
; X86-SSE-NEXT:    movsd {{.*#+}} xmm0 = mem[0],zero
; X86-SSE-NEXT:    movsd %xmm0, (%esp)
; X86-SSE-NEXT:    movl $15, {{[0-9]+}}(%esp)
; X86-SSE-NEXT:    calll __powidf2
; X86-SSE-NEXT:    addl $12, %esp
; X86-SSE-NEXT:    retl
;
; X64-LABEL: pow_wrapper_optsize:
; X64:       # %bb.0:
; X64-NEXT:    movl $15, %edi
; X64-NEXT:    jmp __powidf2@PLT # TAILCALL
  %ret = tail call double @llvm.powi.f64.i32(double %a, i32 15) nounwind ; <double> [#uses=1]
  ret double %ret
}

define double @pow_wrapper_pgso(double %a) nounwind !prof !14 {
; X86-X87-LABEL: pow_wrapper_pgso:
; X86-X87:       # %bb.0:
; X86-X87-NEXT:    subl $12, %esp
; X86-X87-NEXT:    fldl {{[0-9]+}}(%esp)
; X86-X87-NEXT:    fstpl (%esp)
; X86-X87-NEXT:    movl $15, {{[0-9]+}}(%esp)
; X86-X87-NEXT:    calll __powidf2
; X86-X87-NEXT:    addl $12, %esp
; X86-X87-NEXT:    retl
;
; X86-SSE-LABEL: pow_wrapper_pgso:
; X86-SSE:       # %bb.0:
; X86-SSE-NEXT:    subl $12, %esp
; X86-SSE-NEXT:    movsd {{.*#+}} xmm0 = mem[0],zero
; X86-SSE-NEXT:    movsd %xmm0, (%esp)
; X86-SSE-NEXT:    movl $15, {{[0-9]+}}(%esp)
; X86-SSE-NEXT:    calll __powidf2
; X86-SSE-NEXT:    addl $12, %esp
; X86-SSE-NEXT:    retl
;
; X64-LABEL: pow_wrapper_pgso:
; X64:       # %bb.0:
; X64-NEXT:    movl $15, %edi
; X64-NEXT:    jmp __powidf2@PLT # TAILCALL
  %ret = tail call double @llvm.powi.f64.i32(double %a, i32 15) nounwind ; <double> [#uses=1]
  ret double %ret
}

define double @pow_wrapper_minsize(double %a) nounwind minsize {
; X86-X87-LABEL: pow_wrapper_minsize:
; X86-X87:       # %bb.0:
; X86-X87-NEXT:    subl $12, %esp
; X86-X87-NEXT:    fldl {{[0-9]+}}(%esp)
; X86-X87-NEXT:    fstpl (%esp)
; X86-X87-NEXT:    movl $15, {{[0-9]+}}(%esp)
; X86-X87-NEXT:    calll __powidf2
; X86-X87-NEXT:    addl $12, %esp
; X86-X87-NEXT:    retl
;
; X86-SSE-LABEL: pow_wrapper_minsize:
; X86-SSE:       # %bb.0:
; X86-SSE-NEXT:    subl $12, %esp
; X86-SSE-NEXT:    movsd {{.*#+}} xmm0 = mem[0],zero
; X86-SSE-NEXT:    movsd %xmm0, (%esp)
; X86-SSE-NEXT:    movl $15, {{[0-9]+}}(%esp)
; X86-SSE-NEXT:    calll __powidf2
; X86-SSE-NEXT:    addl $12, %esp
; X86-SSE-NEXT:    retl
;
; X64-LABEL: pow_wrapper_minsize:
; X64:       # %bb.0:
; X64-NEXT:    pushq $15
; X64-NEXT:    popq %rdi
; X64-NEXT:    jmp __powidf2@PLT # TAILCALL
  %ret = tail call double @llvm.powi.f64.i32(double %a, i32 15) nounwind ; <double> [#uses=1]
  ret double %ret
}

define <2 x float> @powi_v2f32(<2 x float> %a) nounwind minsize {
; X86-X87-LABEL: powi_v2f32:
; X86-X87:       # %bb.0:
; X86-X87-NEXT:    pushl %esi
; X86-X87-NEXT:    subl $16, %esp
; X86-X87-NEXT:    flds {{[0-9]+}}(%esp)
; X86-X87-NEXT:    fstps {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
; X86-X87-NEXT:    flds {{[0-9]+}}(%esp)
; X86-X87-NEXT:    pushl $15
; X86-X87-NEXT:    popl %esi
; X86-X87-NEXT:    movl %esi, {{[0-9]+}}(%esp)
; X86-X87-NEXT:    fstps (%esp)
; X86-X87-NEXT:    calll __powisf2
; X86-X87-NEXT:    fstps {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
; X86-X87-NEXT:    movl %esi, {{[0-9]+}}(%esp)
; X86-X87-NEXT:    flds {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Reload
; X86-X87-NEXT:    fstps (%esp)
; X86-X87-NEXT:    calll __powisf2
; X86-X87-NEXT:    flds {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Reload
; X86-X87-NEXT:    fxch %st(1)
; X86-X87-NEXT:    addl $16, %esp
; X86-X87-NEXT:    popl %esi
; X86-X87-NEXT:    retl
;
; X86-SSE-LABEL: powi_v2f32:
; X86-SSE:       # %bb.0:
; X86-SSE-NEXT:    pushl %esi
; X86-SSE-NEXT:    subl $32, %esp
; X86-SSE-NEXT:    movups %xmm0, {{[-0-9]+}}(%e{{[sb]}}p) # 16-byte Spill
; X86-SSE-NEXT:    pushl $15
; X86-SSE-NEXT:    popl %esi
; X86-SSE-NEXT:    movl %esi, {{[0-9]+}}(%esp)
; X86-SSE-NEXT:    movss %xmm0, (%esp)
; X86-SSE-NEXT:    calll __powisf2
; X86-SSE-NEXT:    movl %esi, {{[0-9]+}}(%esp)
; X86-SSE-NEXT:    movups {{[-0-9]+}}(%e{{[sb]}}p), %xmm0 # 16-byte Reload
; X86-SSE-NEXT:    shufps {{.*#+}} xmm0 = xmm0[1,1,1,1]
; X86-SSE-NEXT:    movss %xmm0, (%esp)
; X86-SSE-NEXT:    fstps {{[0-9]+}}(%esp)
; X86-SSE-NEXT:    calll __powisf2
; X86-SSE-NEXT:    fstps {{[0-9]+}}(%esp)
; X86-SSE-NEXT:    movss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; X86-SSE-NEXT:    movss {{.*#+}} xmm1 = mem[0],zero,zero,zero
; X86-SSE-NEXT:    unpcklps {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
; X86-SSE-NEXT:    addl $32, %esp
; X86-SSE-NEXT:    popl %esi
; X86-SSE-NEXT:    retl
;
; X64-LABEL: powi_v2f32:
; X64:       # %bb.0:
; X64-NEXT:    pushq %rbx
; X64-NEXT:    subq $32, %rsp
; X64-NEXT:    movaps %xmm0, (%rsp) # 16-byte Spill
; X64-NEXT:    pushq $15
; X64-NEXT:    popq %rbx
; X64-NEXT:    movl %ebx, %edi
; X64-NEXT:    callq __powisf2@PLT
; X64-NEXT:    movaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
; X64-NEXT:    movaps (%rsp), %xmm0 # 16-byte Reload
; X64-NEXT:    shufps {{.*#+}} xmm0 = xmm0[1,1,1,1]
; X64-NEXT:    movl %ebx, %edi
; X64-NEXT:    callq __powisf2@PLT
; X64-NEXT:    movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm1 # 16-byte Reload
; X64-NEXT:    unpcklps {{.*#+}} xmm1 = xmm1[0],xmm0[0],xmm1[1],xmm0[1]
; X64-NEXT:    movaps %xmm1, %xmm0
; X64-NEXT:    addq $32, %rsp
; X64-NEXT:    popq %rbx
; X64-NEXT:    retq
  %ret = tail call < 2 x float> @llvm.powi.v2f32.i32(<2 x float> %a, i32 15) nounwind ;
  ret <2 x float> %ret
}

declare double @llvm.powi.f64.i32(double, i32) nounwind readonly
declare < 2 x float> @llvm.powi.v2f32.i32(<2 x float>, i32) nounwind readonly

!llvm.module.flags = !{!0}
!0 = !{i32 1, !"ProfileSummary", !1}
!1 = !{!2, !3, !4, !5, !6, !7, !8, !9}
!2 = !{!"ProfileFormat", !"InstrProf"}
!3 = !{!"TotalCount", i64 10000}
!4 = !{!"MaxCount", i64 10}
!5 = !{!"MaxInternalCount", i64 1}
!6 = !{!"MaxFunctionCount", i64 1000}
!7 = !{!"NumCounts", i64 3}
!8 = !{!"NumFunctions", i64 3}
!9 = !{!"DetailedSummary", !10}
!10 = !{!11, !12, !13}
!11 = !{i32 10000, i64 100, i32 1}
!12 = !{i32 999000, i64 100, i32 1}
!13 = !{i32 999999, i64 1, i32 2}
!14 = !{!"function_entry_count", i64 0}