Index: llvm/trunk/test/CodeGen/X86/fmf-flags.ll =================================================================== --- llvm/trunk/test/CodeGen/X86/fmf-flags.ll +++ llvm/trunk/test/CodeGen/X86/fmf-flags.ll @@ -48,12 +48,15 @@ ; The multiply is strict. +@mul1 = common global double 0.000000e+00, align 4 + define double @not_so_fast_mul_add(double %x) { ; X64-LABEL: not_so_fast_mul_add: ; X64: # BB#0: ; X64-NEXT: movsd {{.*#+}} xmm1 = mem[0],zero ; X64-NEXT: mulsd %xmm0, %xmm1 ; X64-NEXT: addsd %xmm1, %xmm0 +; X64-NEXT: movsd %xmm1, {{.*}}(%rip) ; X64-NEXT: retq ; ; X86-LABEL: not_so_fast_mul_add: @@ -61,21 +64,26 @@ ; X86-NEXT: fldl {{[0-9]+}}(%esp) ; X86-NEXT: fld %st(0) ; X86-NEXT: fmull {{\.LCPI.*}} -; X86-NEXT: faddp %st(1) +; X86-NEXT: fadd %st(0), %st(1) +; X86-NEXT: fstpl mul1 ; X86-NEXT: retl %m = fmul double %x, 4.2 %a = fadd fast double %m, %x + store double %m, double* @mul1, align 4 ret double %a } ; The sqrt is strict. +@sqrt1 = common global float 0.000000e+00, align 4 + define float @not_so_fast_recip_sqrt(float %x) { ; X64-LABEL: not_so_fast_recip_sqrt: ; X64: # BB#0: ; X64-NEXT: sqrtss %xmm0, %xmm1 ; X64-NEXT: movss {{.*#+}} xmm0 = mem[0],zero,zero,zero ; X64-NEXT: divss %xmm1, %xmm0 +; X64-NEXT: movss %xmm1, {{.*}}(%rip) ; X64-NEXT: retq ; ; X86-LABEL: not_so_fast_recip_sqrt: @@ -83,10 +91,14 @@ ; X86-NEXT: flds {{[0-9]+}}(%esp) ; X86-NEXT: fsqrt ; X86-NEXT: fld1 -; X86-NEXT: fdivp %st(1) +; X86-NEXT: fdiv %st(1) +; X86-NEXT: fxch %st(1) +; X86-NEXT: fstps sqrt1 ; X86-NEXT: retl %y = call float @llvm.sqrt.f32(float %x) %z = fdiv fast float 1.0, %y + store float %y, float* @sqrt1, align 4 + %ret = fadd float %z , 14.5 ret float %z }