https://gcc.gnu.org/bugzilla/show_bug.cgi?id=65413
Bug ID: 65413
Summary: inefficient code returning aggregates on powepc64le
Product: gcc
Version: 5.0
Status: UNCONFIRMED
Severity: normal
Priority: P3
Component: c
Assignee: unassigned at gcc dot gnu.org
Reporter: msebor at gcc dot gnu.org
When returning aggregates that don't fit into a single register on powerpc64le,
gcc emits the assembly below which ultimately results in the same values in the
r3 and r4 registers as it started out with. All the shift and rotate
instructions are unnecessary (and in fact, foo could be as simple as a blr).
$ cat ~/tmp/x.c && gcc -O2 -S -Wall -o/dev/tty ~/tmp/x.c
typedef struct { int a[3]; } A;
A __attribute__ ((noinline)) foo (A a) {
return a;
}
A bar (A a) {
return foo (a);
}
.file "x.c"
.machine power8
.abiversion 2
.section ".toc","aw"
.section ".text"
.align 2
.p2align 4,,15
.globl foo
.type foo, @function
foo:
mr 9,3
li 3,0
rldicl 10,9,0,32
srdi 9,9,32
rldimi 3,10,0,32
rldicl 4,4,0,32
rldimi 3,9,32,0
blr
.long 0
.byte 0,0,0,0,0,0,0,0
.size foo,.-foo
.align 2
.p2align 4,,15
.globl bar
.type bar, @function
bar:
0: addis 2,12,.TOC.-0b@ha
addi 2,2,.TOC.-0b@l
.localentry bar,.-bar
mflr 0
std 0,16(1)
stdu 1,-64(1)
bl foo
addi 1,1,64
ld 0,16(1)
mr 9,3
li 3,0
rldicl 10,9,0,32
srdi 9,9,32
rldimi 3,10,0,32
rldicl 4,4,0,32
mtlr 0
rldimi 3,9,32,0
blr
.long 0
.byte 0,0,0,1,128,0,0,0
.size bar,.-bar
.ident "GCC: (GNU) 5.0.0 20150303 (experimental)"
.section .note.GNU-stack,"",@progbits
