This also has the false dependency problem (using eax as the popcnt destination register three times), and neither one of your VC examples is using the 8 byte popcnt instruction.
RES64 cnt0=0, cnt1=0, cnt2=0, cnt3=0;
SIZE_T ndqwords = len / (sizeof(RES64) * 4);
for(; ndqwords; ndqwords--) {
cnt0 += __popcnt64(*(RES64*)buf);
cnt1 += __popcnt64(*(RES64*)(buf + sizeof(RES64) ));
cnt2 += __popcnt64(*(RES64*)(buf + sizeof(RES64) * 2 ));
cnt3 += __popcnt64(*(RES64*)(buf + sizeof(RES64) * 3 ));
buf += sizeof(RES64) * 4;
}
cnt = cnt0 + cnt1 + cnt2 + cnt3;
000000013FD61FF3 popcnt rax,qword ptr [rdx]
000000013FD61FF8 add rdx,20h
000000013FD61FFC add r9,rax
000000013FD61FFF popcnt rax,qword ptr [rdx-18h]
000000013FD62005 add r10,rax
000000013FD62008 popcnt rax,qword ptr [rdx-10h]
000000013FD6200E add r8,rax
000000013FD62011 popcnt rax,qword ptr [rdx-8]
000000013FD62017 add r11,rax
000000013FD6201A dec rcx
000000013FD6201D jne main+0C3h (13FD61FF3h) struct A { RES64 cnt0; RES64 cnt1; RES64 cnt2; RES64 cnt3; } a;
RES64 cnt0=0, cnt1=0, cnt2=0, cnt3=0;
SIZE_T ndqwords = len / (sizeof(RES64) * 4);
for(; ndqwords; ndqwords--) {
a.cnt0 = __popcnt64(*(RES64*)buf);
a.cnt1 = __popcnt64(*(RES64*)(buf + sizeof(RES64) ));
a.cnt2 = __popcnt64(*(RES64*)(buf + sizeof(RES64) * 2 ));
a.cnt3 = __popcnt64(*(RES64*)(buf + sizeof(RES64) * 3 ));
cnt0 += a.cnt0;
cnt1 += a.cnt1;
cnt2 += a.cnt2;
cnt3 += a.cnt3;
buf += sizeof(RES64) * 4;
}
cnt = cnt0 + cnt1 + cnt2 + cnt3;
000000013F2320C0 popcnt rax,qword ptr [r8]
000000013F2320C5 popcnt rcx,qword ptr [r8+8]
000000013F2320CB popcnt rdx,qword ptr [r8+10h]
000000013F2320D1 popcnt rbx,qword ptr [r8+18h]
000000013F2320D7 add r11,rax
000000013F2320DA add rdi,rcx
000000013F2320DD add rsi,rdx
000000013F2320E0 add r8,20h
000000013F2320E4 add rbp,rbx
000000013F2320E7 dec r10
000000013F2320EA jne main+0D0h (13F2320C0h)