https://gcc.gnu.org/bugzilla/show_bug.cgi?id=65391
--- Comment #2 from Aaron Sawdey <acsawdey at linux dot vnet.ibm.com> ---
Asm for the test case as in the description (load/store of *o_ptr for every
update):
compute_object_gain:
ld 9,0(3)
li 10,0
std 10,0(4)
cmpdi 7,9,0
beqlr 7
.p2align 5,,31
.L6:
cmpd 7,5,9
blt 7,.L3
ld 10,0(4)
add 9,10,9
std 9,0(4)
.L3:
ldu 9,8(3)
cmpdi 7,9,0
bne 7,.L6
blr
Same test case, but with __restrict__ removed (essentially no difference):
compute_object_gain:
li 9,0
std 9,0(4)
ld 9,0(3)
cmpdi 7,9,0
beqlr 7
.p2align 5,,31
.L6:
cmpd 7,5,9
blt 7,.L3
ld 10,0(4)
add 9,10,9
std 9,0(4)
.L3:
ldu 9,8(3)
cmpdi 7,9,0
bne 7,.L6
blr
Remove the if() and add __restrict__ back (no load or store of *o_ptr in the
loop):
compute_object_gain:
ld 9,0(3)
li 8,0
li 10,0
std 8,0(4)
cmpdi 7,9,0
beqlr 7
.p2align 4,,15
.L5:
add 10,10,9
ldu 9,8(3)
cmpdi 7,9,0
bne 7,.L5
std 10,0(4)
blr
Remove both the if() and __restrict__ (now store to *o_ptr is in the loop but
no load):
compute_object_gain:
li 9,0
li 10,0
std 9,0(4)
ld 9,0(3)
cmpdi 7,9,0
beqlr 7
.p2align 5,,31
.L5:
add 10,10,9
std 10,0(4)
ldu 9,8(3)
cmpdi 7,9,0
bne 7,.L5
blr
