Page MenuHomePhabricator

Please use GitHub pull requests for new patches. Phabricator shutdown timeline

Differential D47954 Diff 151556 llvm/trunk/test/CodeGen/X86/fmf-flags.ll

Changeset View

Standalone View

View Options

llvm/trunk/test/CodeGen/X86/fmf-flags.ll

; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -mtriple=x86_64-unknown | FileCheck %s -check-prefix=X64 ; RUN: llc < %s -mtriple=x86_64-unknown | FileCheck %s -check-prefix=X64
; RUN: llc < %s -mtriple=i686-unknown | FileCheck %s -check-prefix=X86 ; RUN: llc < %s -mtriple=i686-unknown | FileCheck %s -check-prefix=X86
declare float @llvm.sqrt.f32(float %x); declare float @llvm.sqrt.f32(float %x);
define float @fast_recip_sqrt(float %x) { define float @fast_recip_sqrt(float %x) {
; X64-LABEL: fast_recip_sqrt: ; X64-LABEL: fast_recip_sqrt:
; X64: # %bb.0: ; X64: # %bb.0:
; X64-NEXT: rsqrtss %xmm0, %xmm1 ; X64-NEXT: rsqrtss %xmm0, %xmm1
; X64-NEXT: xorps %xmm2, %xmm2
; X64-NEXT: cmpeqss %xmm0, %xmm2
; X64-NEXT: mulss %xmm1, %xmm0 ; X64-NEXT: mulss %xmm1, %xmm0
; X64-NEXT: movss {{.*}}(%rip), %xmm3
; X64-NEXT: mulss %xmm0, %xmm3
; X64-NEXT: mulss %xmm1, %xmm0 ; X64-NEXT: mulss %xmm1, %xmm0
; X64-NEXT: addss {{.*}}(%rip), %xmm0 ; X64-NEXT: addss {{.*}}(%rip), %xmm0
; X64-NEXT: mulss %xmm3, %xmm0 ; X64-NEXT: mulss {{.*}}(%rip), %xmm1
; X64-NEXT: andnps %xmm0, %xmm2 ; X64-NEXT: mulss %xmm1, %xmm0
; X64-NEXT: movss {{.*}}(%rip), %xmm0
; X64-NEXT: divss %xmm2, %xmm0
; X64-NEXT: retq ; X64-NEXT: retq
; ;
; X86-LABEL: fast_recip_sqrt: ; X86-LABEL: fast_recip_sqrt:
; X86: # %bb.0: ; X86: # %bb.0:
; X86-NEXT: flds {{[0-9]+}}(%esp) ; X86-NEXT: flds {{[0-9]+}}(%esp)
; X86-NEXT: fsqrt ; X86-NEXT: fsqrt
; X86-NEXT: fld1 ; X86-NEXT: fld1
; X86-NEXT: fdivp %st(1) ; X86-NEXT: fdivp %st(1)
▲ Show 20 Lines • Show All 54 Lines • ▼ Show 20 Lines
; The sqrt is strict. ; The sqrt is strict.
@sqrt1 = common global float 0.000000e+00, align 4 @sqrt1 = common global float 0.000000e+00, align 4
define float @not_so_fast_recip_sqrt(float %x) { define float @not_so_fast_recip_sqrt(float %x) {
; X64-LABEL: not_so_fast_recip_sqrt: ; X64-LABEL: not_so_fast_recip_sqrt:
; X64: # %bb.0: ; X64: # %bb.0:
; X64-NEXT: sqrtss %xmm0, %xmm1 ; X64-NEXT: rsqrtss %xmm0, %xmm1
; X64-NEXT: movss {{.*#+}} xmm0 = mem[0],zero,zero,zero ; X64-NEXT: sqrtss %xmm0, %xmm2
; X64-NEXT: divss %xmm1, %xmm0 ; X64-NEXT: mulss %xmm1, %xmm0
; X64-NEXT: movss %xmm1, {{.*}}(%rip) ; X64-NEXT: mulss %xmm1, %xmm0
; X64-NEXT: addss {{.*}}(%rip), %xmm0
; X64-NEXT: mulss {{.*}}(%rip), %xmm1
; X64-NEXT: mulss %xmm1, %xmm0
; X64-NEXT: movss %xmm2, sqrt1(%rip)
; X64-NEXT: retq ; X64-NEXT: retq
; ;
; X86-LABEL: not_so_fast_recip_sqrt: ; X86-LABEL: not_so_fast_recip_sqrt:
; X86: # %bb.0: ; X86: # %bb.0:
; X86-NEXT: flds {{[0-9]+}}(%esp) ; X86-NEXT: flds {{[0-9]+}}(%esp)
; X86-NEXT: fsqrt ; X86-NEXT: fsqrt
; X86-NEXT: fld1 ; X86-NEXT: fld1
; X86-NEXT: fdiv %st(1) ; X86-NEXT: fdiv %st(1)
; X86-NEXT: fxch %st(1) ; X86-NEXT: fxch %st(1)
; X86-NEXT: fstps sqrt1 ; X86-NEXT: fstps sqrt1
; X86-NEXT: retl ; X86-NEXT: retl
%y = call float @llvm.sqrt.f32(float %x) %y = call float @llvm.sqrt.f32(float %x)
%z = fdiv fast float 1.0, %y %z = fdiv fast float 1.0, %y
store float %y, float* @sqrt1, align 4 store float %y, float* @sqrt1, align 4
%ret = fadd float %z , 14.5 %ret = fadd float %z , 14.5
ret float %z ret float %z
} }
define float @div_arcp_by_const(half %x) {
; X64-LABEL: .LCPI4_0:
; X64-NEXT: .long 1036828672
; X64-LABEL: div_arcp_by_const:
; X64: movzwl %ax, %edi
; X64: mulss .LCPI4_0(%rip), %xmm0
;
; X86-LABEL: .LCPI4_0:
; X86-NEXT: .long 1036828672
; X86-LABEL: div_arcp_by_const:
; X86: movzwl %ax, %eax
; X86: fmuls .LCPI4_0
%rcp = fdiv arcp half %x, 10.0
%z = fpext half %rcp to float
ret float %z
}