Thank you Oleh!
Upon checking the generated assembly, I'm noticing that it's executing
against AVX2 but not using YMM registers at all. Would you know why?
I've compiled it using -O2.
*AddVec4sProper_avx2:*
00007FF6F9E167E0 test r8d,r8d
00007FF6F9E167E3 jle AddVec4sProper_avx2+0B9h (07FF6F9E16899h)
00007FF6F9E167E9 lea eax,[r8-1]
00007FF6F9E167ED mov r9d,r8d
00007FF6F9E167F0 and r9d,3
00007FF6F9E167F4 cmp eax,3
00007FF6F9E167F7 jae AddVec4sProper_avx2+26h (07FF6F9E16806h)
00007FF6F9E167F9 xor r10d,r10d
00007FF6F9E167FC test r9d,r9d
00007FF6F9E167FF jne AddVec4sProper_avx2+90h (07FF6F9E16870h)
00007FF6F9E16801 jmp AddVec4sProper_avx2+0B9h (07FF6F9E16899h)
00007FF6F9E16806 sub r8d,r9d
00007FF6F9E16809 mov eax,30h
00007FF6F9E1680E xor r10d,r10d
00007FF6F9E16811 vmovss xmm0,dword ptr [__real@3f800000
(07FF6FA0EAF20h)]
00007FF6F9E16819 nop dword ptr [rax]
00007FF6F9E16820 vmovaps xmm1,xmmword ptr [rdx+rax-30h]
00007FF6F9E16826 vaddss xmm1,xmm1,xmm0
00007FF6F9E1682A vmovaps xmmword ptr [rcx+rax-30h],xmm1
00007FF6F9E16830 vmovaps xmm1,xmmword ptr [rdx+rax-20h]
00007FF6F9E16836 vaddss xmm1,xmm1,xmm0
00007FF6F9E1683A vmovaps xmmword ptr [rcx+rax-20h],xmm1
00007FF6F9E16840 vmovaps xmm1,xmmword ptr [rdx+rax-10h]
00007FF6F9E16846 vaddss xmm1,xmm1,xmm0
00007FF6F9E1684A vmovaps xmmword ptr [rcx+rax-10h],xmm1
00007FF6F9E16850 vmovaps xmm1,xmmword ptr [rdx+rax]
00007FF6F9E16855 vaddss xmm1,xmm1,xmm0
00007FF6F9E16859 vmovaps xmmword ptr [rcx+rax],xmm1
00007FF6F9E1685E add r10,4
00007FF6F9E16862 add rax,40h
00007FF6F9E16866 cmp r8d,r10d
00007FF6F9E16869 jne AddVec4sProper_avx2+40h (07FF6F9E16820h)
00007FF6F9E1686B test r9d,r9d
00007FF6F9E1686E je AddVec4sProper_avx2+0B9h (07FF6F9E16899h)
00007FF6F9E16870 shl r10,4
00007FF6F9E16874 neg r9d
00007FF6F9E16877 vmovss xmm0,dword ptr [__real@3f800000
(07FF6FA0EAF20h)]
00007FF6F9E1687F nop
00007FF6F9E16880 vmovaps xmm1,xmmword ptr [rdx+r10]
00007FF6F9E16886 vaddss xmm1,xmm1,xmm0
00007FF6F9E1688A vmovaps xmmword ptr [rcx+r10],xmm1
00007FF6F9E16890 add r10,10h
00007FF6F9E16894 inc r9d
00007FF6F9E16897 jne AddVec4sProper_avx2+0A0h (07FF6F9E16880h)
00007FF6F9E16899 ret
00007FF6F9E1689A nop word ptr [rax+rax]
On Saturday, March 21, 2020 at 12:21:43 PM UTC-5, Oleh Nechaev wrote:
>
> struct Vector4SOA
> {
> float<4> V;
> };
>
> export void Test(uniform Vector4SOA outs[], uniform Vector4SOA ins[],
> uniform int count)
> {
> for (uniform int i=0; i< count ; ++i)
> {
> uniform Vector4SOA vv = ins[i];
> vv.V.x++; // builtin access by x y z w and r g b a
> outs[i] = vv;
> }
> }
>
>
--
You received this message because you are subscribed to the Google Groups
"Intel SPMD Program Compiler Users" group.
To unsubscribe from this group and stop receiving emails from it, send an email
to [email protected].
To view this discussion on the web visit
https://groups.google.com/d/msgid/ispc-users/cf0af12b-d84a-463c-be09-c8b35b3baf81%40googlegroups.com.
