https://gcc.gnu.org/bugzilla/show_bug.cgi?id=97770
--- Comment #3 from Hongtao.liu <crazylht at gmail dot com> ---
> But for vector byte/word/quadword, vectorizer still use vpopcntd, but not
> vpopcnt{b,w,q}, missing corresponding ifn?
We don't have __builtin_popcount{w,b}, but we have __builtin_popcountl.
for testcase
---
void
fooq(unsigned long long* __restrict dest, unsigned long long* src)
{
for (int i = 0; i != 4; i++)
dest[i] = __builtin_popcountl (src[i]);
}
----
icc/clang generate
---
_Z4fooqPxS_: # @_Z4fooqPxS_
vpopcntq ymm0, ymmword ptr [rsi]
vmovdqu ymmword ptr [rdi], ymm0
vzeroupper
ret
---
But gcc generate
---
fooq:
.LFB0:
.cfi_startproc
vpopcntq 16(%rsi), %xmm1
vpopcntq (%rsi), %xmm0
vshufps $136, %xmm1, %xmm0, %xmm0
vpmovsxdq %xmm0, %xmm1
vpsrldq $8, %xmm0, %xmm0
vpmovsxdq %xmm0, %xmm0
vmovdqu %xmm1, (%rdi)
vmovdqu %xmm0, 16(%rdi)
ret
.cfi_endproc
---
dump for 164.vect
---
;; Function fooq (fooq, funcdef_no=0, decl_uid=4228, cgraph_uid=1,
symbol_order=0)
Merging blocks 2 and 6
fooq (long long unsigned int * restrict dest, long long unsigned int * src)
{
vector(2) long long unsigned int * vectp_dest.10;
vector(2) long long unsigned int * vectp_dest.9;
vector(2) long long unsigned int vect__7.8;
vector(4) int vect__5.7;
vector(2) long long unsigned int vect__4.6;
vector(2) long long unsigned int vect__4.5;
vector(2) long long unsigned int * vectp_src.4;
vector(2) long long unsigned int * vectp_src.3;
int i;
long unsigned int _1;
long unsigned int _2;
long long unsigned int * _3;
long long unsigned int _4;
int _5;
long long unsigned int * _6;
long long unsigned int _7;
vector(2) long long unsigned int _8;
vector(2) long long unsigned int _26;
unsigned int ivtmp_30;
unsigned int ivtmp_31;
unsigned int ivtmp_36;
unsigned int ivtmp_37;
<bb 2> [local count: 214748368]:
<bb 3> [local count: 214748371]:
# i_18 = PHI <i_14(5), 0(2)>
# ivtmp_31 = PHI <ivtmp_30(5), 4(2)>
# vectp_src.3_20 = PHI <vectp_src.3_17(5), src_11(D)(2)>
# vectp_dest.9_24 = PHI <vectp_dest.9_32(5), dest_12(D)(2)>
# ivtmp_36 = PHI <ivtmp_37(5), 0(2)>
_1 = (long unsigned int) i_18;
_2 = _1 * 8;
_3 = src_11(D) + _2;
vect__4.5_16 = MEM <vector(2) long long unsigned int> [(long long unsigned
int *)vectp_src.3_20];
vectp_src.3_15 = vectp_src.3_20 + 16;
vect__4.6_9 = MEM <vector(2) long long unsigned int> [(long long unsigned int
*)vectp_src.3_15];
_4 = *_3;
_8 = .POPCOUNT (vect__4.5_16);
_26 = .POPCOUNT (vect__4.6_9);
vect__5.7_22 = VEC_PACK_TRUNC_EXPR <_8, _26>; --- Why do we do this?
_5 = 0;
_6 = dest_12(D) + _2;
vect__7.8_23 = [vec_unpack_lo_expr] vect__5.7_22;
vect__7.8_25 = [vec_unpack_hi_expr] vect__5.7_22;
_7 = (long long unsigned int) _5;
MEM <vector(2) long long unsigned int> [(long long unsigned int
*)vectp_dest.9_24] = vect__7.8_23;
vectp_dest.9_34 = vectp_dest.9_24 + 16;
MEM <vector(2) long long unsigned int> [(long long unsigned int
*)vectp_dest.9_34] = vect__7.8_25;
i_14 = i_18 + 1;
ivtmp_30 = ivtmp_31 - 1;
vectp_src.3_17 = vectp_src.3_15 + 16;
vectp_dest.9_32 = vectp_dest.9_34 + 16;
ivtmp_37 = ivtmp_36 + 1;
if (ivtmp_37 < 1)
goto <bb 5>; [0.00%]
else
goto <bb 4>; [100.00%]
<bb 5> [local count: 0]:
goto <bb 3>; [100.00%]
<bb 4> [local count: 214748368]:
return;
}
---
