https://gcc.gnu.org/bugzilla/show_bug.cgi?id=101041
Bug ID: 101041
Summary: z13: Inefficient handling of vector register passed to
function
Product: gcc
Version: 8.3.1
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 long long mul64(vector unsigned long long a, vector unsigned
long long b)
{
return a * b;
}
creates:
_Z5mul64Dv2_yS_:
.LFB9:
.cfi_startproc
ldgr %f4,%r15
.cfi_register 15, 18
lay %r15,-192(%r15)
.cfi_def_cfa_offset 352
vst %v24,160(%r15),3
vst %v26,176(%r15),3
lg %r2,160(%r15)
lg %r1,176(%r15)
lgr %r4,%r2
lg %r0,168(%r15)
lgr %r2,%r1
lg %r1,184(%r15)
lgr %r5,%r0
lgr %r3,%r1
vlvgp %v2,%r4,%r5
vlvgp %v0,%r2,%r3
vlgvg %r4,%v2,0
vlgvg %r1,%v2,1
vlgvg %r2,%v0,0
vlgvg %r3,%v0,1
msgr %r2,%r4
msgr %r1,%r3
lgdr %r15,%f4
.cfi_restore 15
.cfi_def_cfa_offset 160
vlvgp %v24,%r2,%r1
br %r14
Store to stack of v24,v26, then lg+lgr for all 4 parts, then constructing new
vector register v0 and v2 and then extract the 4 elements again using vlgvg.
Expected 4 * vlgvg + 2 * msgr + vlvgp
