https://gcc.gnu.org/bugzilla/show_bug.cgi?id=104268
Bug ID: 104268
Summary: 390: inefficient vec_popcnt for 16-bit for z13
Product: gcc
Version: 10.2.1
Status: UNCONFIRMED
Severity: normal
Priority: P3
Component: target
Assignee: unassigned at gcc dot gnu.org
Reporter: jens.seifert at de dot ibm.com
Target Milestone: ---
#include <vecintrin.h>
vector unsigned short popcnt(vector unsigned short a)
{
return vec_popcnt(a);
}
Generates with -march=z13
_Z6popcntDv8_t:
.LFB1:
.cfi_startproc
vzero %v0
vpopct %v24,%v24,0
vleib %v0,8,7
vsrlb %v0,%v24,%v0
vab %v24,%v24,%v0
vgbm %v0,21845
vn %v24,%v24,%v0
br %r14
.cfi_endproc
Optimal sequence would be:
vector unsigned short popcnt_opt(vector unsigned short a)
{
vector unsigned short r = (vector unsigned short)vec_popcnt((vector unsigned
char)a);
vector unsigned short b = vec_rli(r, 8);
r = r + b;
r = r >> 8;
return r;
}
_Z10popcnt_optDv8_t:
.LFB3:
.cfi_startproc
vpopct %v24,%v24,0
verllh %v0,%v24,8
vah %v24,%v0,%v24
vesrlh %v24,%v24,8
br %r14
.cfi_endproc