[Bug rtl-optimization/55360] New: [TileGX] Passing structure by value on stack needlessly writes to and reads from memory

["colanderman at gmail dot com" <gcc-bugzilla at gcc dot gnu dot org>]

http://gcc.gnu.org/bugzilla/show_bug.cgi?id=55360

             Bug #: 55360
           Summary: [TileGX] Passing structure by value on stack
                    needlessly writes to and reads from memory
    Classification: Unclassified
           Product: gcc
           Version: 4.7.2
            Status: UNCONFIRMED
          Severity: enhancement
          Priority: P3
         Component: rtl-optimization
        AssignedTo: unassigned@gcc.gnu.org
        ReportedBy: colanderman@gmail.com


#include <stdint.h>

struct bar { uint8_t a, b, c, d; };
struct bla { unsigned long a:8, b:8, c:8, d:8; };

uint64_t bar(struct bar);
uint64_t bla(struct bla);

uint64_t foo(uint8_t a, uint8_t b, uint8_t c, uint8_t d)
{ return bar((struct bar) { a, b, c, d }); }

uint64_t baz(uint8_t a, uint8_t b, uint8_t c, uint8_t d)
{ return bla((struct bla) { a, b, c, d }); }

when compiled with "gcc -Wall -std=gnu99 -O3 -S pbv.c" produces:

    .file    "pbv.c"
    .text
    .align 8
.global foo
    .type    foo, @function
foo:
.LFB0:
    .cfi_startproc
    {
    st    sp, lr
    .cfi_offset 55, 0
    move    r29, sp
    addi    r28, sp, -16
    }
    addi    sp, sp, -24
    .cfi_def_cfa_offset 24
    {
    st    r28, r29
    addi    r11, sp, 21
    addi    r10, sp, 20
    }
    {
    st1    r11, r1
    addi    r11, sp, 22
    }
    {
    st1    r11, r2
    addi    r11, sp, 23
    }
    {
    st1    r10, r0
    movei    r0, 0
    }
    st1    r11, r3
    ld4u    r10, r10
    {
    bfins    r0, r10, 0, 0+32-1
    jal    bar
    }
    addi    r29, sp, 24
    ld    lr, r29
    {

    addi    sp, sp, 24
    .cfi_restore 54
    .cfi_restore 55
    .cfi_def_cfa_offset 0
    jrp    lr
    }
    .cfi_endproc
.LFE0:
    .size    foo, .-foo
    .align 8
.global baz
    .type    baz, @function
baz:
.LFB1:
    .cfi_startproc
    {
    movei    r10, 0
    st    sp, lr
    .cfi_offset 55, 0
    move    r29, sp
    }
    {
    bfins    r10, r0, 0, 7
    addi    r28, sp, -8
    }
    {
    bfins    r10, r1, 8, 8+8-1
    addi    sp, sp, -16
    }
    .cfi_def_cfa_offset 16
    {
    bfins    r10, r2, 16, 16+8-1
    st    r28, r29
    }
    bfins    r10, r3, 24, 24+8-1
    {
    move    r0, r10
    jal    bla
    }
    addi    r29, sp, 16
    ld    lr, r29
    {

    addi    sp, sp, 16
    .cfi_restore 54
    .cfi_restore 55
    .cfi_def_cfa_offset 0
    jrp    lr
    }
    .cfi_endproc
.LFE1:
    .size    baz, .-baz
    .ident    "GCC: (GNU) 4.7.2"
    .section    .note.GNU-stack,"",@progbits

My expectation is that the foo and baz should compile identically, and should
use the bfins bit-arithmetic functions like baz does, rather than redundant
stores and loads to stack like foo does.

This is with a vanilla GCC 4.7.2 build on a Tilempower system (roughly CentOS
5.7).

The problem does not occur on Debian x86-64 with either GCC 4.4.6 or GCC 4.7.2.

Possibly related to http://gcc.gnu.org/bugzilla/show_bug.cgi?id=7061 (however
that case seems to be fixed in 4.7.2).