ASM_TestDiv proc ;rcx out, rdx A, r8 B mov rax,05555555555555555H kmovq k1,rax vmovdqu8 zmm0,zmmword ptr [rdx] vmovdqu8 zmm4,zmmword ptr [r8] vpbroadcastw zmm3,word ptr [FLOAT16_F8] vmovdqu8 zmm2{k1},zmm0 ;lower 8-bit vmovdqu8 zmm16{k1},zmm4 ;lower 8-bit vpsrlw zmm1,zmm0,8 ;higher 8-bit vpsrlw zmm5,zmm4,8 ;higher 8-bit vpord zmm1,zmm1,zmm3 vpord zmm2,zmm2,zmm3 vpord zmm5,zmm5,zmm3 vpord zmm16,zmm16,zmm3 vsubph zmm1,zmm1,zmm3{rd-sae} ;fast conv 16FP vsubph zmm2,zmm2,zmm3{rd-sae} vsubph zmm5,zmm5,zmm3{ru-sae} vsubph zmm16,zmm16,zmm3{ru-sae} vrcpph zmm5,zmm5 vrcpph zmm16,zmm16 vfmadd213ph zmm1,zmm5,zmm3{rd-sae} vfmadd213ph zmm2,zmm16,zmm3{rd-sae} vxorpd zmm1,zmm1,zmm3 vxorpd zmm2,zmm2,zmm3 vpsllw zmm1,zmm1,8 vpord zmm1,zmm1,zmm2 vmovdqu8 zmmword ptr [rcx],zmm1 ;16 8-bit unsigned int ret