https://gcc.gnu.org/bugzilla/show_bug.cgi?id=102117
Bug ID: 102117
Summary: s390: Inefficient code for 64x64=128 signed multiply
for <= z13
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: ---
__int128 imul128(long long a, long long b)
{
return (__int128)a * (__int128)b;
}
creates sequence with 3 multiplies:
_Z7imul128xx:
.LFB0:
.cfi_startproc
ldgr %f2,%r12
.cfi_register 12, 17
ldgr %f0,%r13
.cfi_register 13, 16
lgr %r13,%r3
mlgr %r12,%r4
srag %r1,%r3,63
msgr %r1,%r4
srag %r4,%r4,63
msgr %r4,%r3
agr %r4,%r1
agr %r12,%r4
stmg %r12,%r13,0(%r2)
lgdr %r13,%f0
.cfi_restore 13
lgdr %r12,%f2
.cfi_restore 12
br %r14
.cfi_endproc
The following sequence only requires 1 multiply:
__int128 imul128_opt(long long a, long long b)
{
unsigned __int128 x = (unsigned __int128)(unsigned long long)a;
unsigned __int128 y = (unsigned __int128)(unsigned long long)b;
unsigned long long t1 = (a >> 63) & a;
unsigned long long t2 = (b >> 63) & b;
unsigned __int128 u128 = x * y;
unsigned long long hi = (u128 >> 64) - (t1 + t2);
unsigned long long lo = (unsigned long long)u128;
unsigned __int128 res = hi;
res <<= 64;
res |= lo;
return (__int128)res;
}
_Z11imul128_optxx:
.LFB1:
.cfi_startproc
ldgr %f2,%r12
.cfi_register 12, 17
ldgr %f0,%r13
.cfi_register 13, 16
lgr %r13,%r3
mlgr %r12,%r4
lgr %r1,%r3
srag %r3,%r3,63
ngr %r3,%r1
srag %r1,%r4,63
ngr %r4,%r1
agr %r3,%r4
sgrk %r3,%r12,%r3
stg %r13,8(%r2)
lgdr %r12,%f2
.cfi_restore 12
lgdr %r13,%f0
.cfi_restore 13
stg %r3,0(%r2)
br %r14
.cfi_endproc
