Compile the attached test case with options -mthumb -Os -fpic, gcc generates:
goo:
push {r3, r4, r5, lr}
ldr r4, .L7
ldr r3, .L7+4 // A
.LPIC0:
add r4, pc
ldr r3, [r4, r3] // B
ldr r3, [r3]
mov r5, r0
ldr r0, [r3]
cmp r0, #0
beq .L2
mov r1, r5
bl foo
.L2:
ldr r3, [r5]
mov r0, #0
cmp r3, #0
beq .L3
ldr r2, .L7+4 // C
ldr r2, [r4, r2] // D
ldr r2, [r2, #4]
ldr r2, [r2]
cmp r3, r2
beq .L3
ldr r0, [r3]
.L3:
@ sp needed for prologue
pop {r3, r4, r5}
pop {r1}
bx r1
.L7:
.word _GLOBAL_OFFSET_TABLE_-(.LPIC0+4)
.word gObj(GOT)
Notice instructions A,B,C,D, they load the address of global variable gObj
twice.
When compiled with options -mthumb -O2 -fpic, gcc generates:
goo:
push {r4, r5, r6, lr}
ldr r4, .L8
ldr r5, .L8+4 // E
.LPIC0:
add r4, pc
ldr r3, [r4, r5] // F
ldr r3, [r3]
mov r6, r0
ldr r0, [r3]
cmp r0, #0
bne .L7
.L2:
ldr r3, [r6]
mov r0, #0
cmp r3, #0
beq .L3
ldr r2, [r4, r5] // G
ldr r2, [r2, #4] // H
ldr r2, [r2]
cmp r2, r3
beq .L3
ldr r0, [r3]
.L3:
@ sp needed for prologue
pop {r4, r5, r6}
pop {r1}
bx r1
.L7:
mov r1, r6
bl foo
b .L2
.L9:
.align 2
.L8:
.word _GLOBAL_OFFSET_TABLE_-(.LPIC0+4)
.word gObj(GOT)
Instructions E,F,G do the same thing, but with one less memory load
instruction. It uses the same number of instructions. -Os should do the same
optimization.
Actually -O2 result is still not optimal. If we store the result of F into r4,
we can directly use r4 in instruction H, so G can also be removed.
--
Summary: redundant memory load
Product: gcc
Version: 4.5.0
Status: UNCONFIRMED
Severity: normal
Priority: P3
Component: target
AssignedTo: unassigned at gcc dot gnu dot org
ReportedBy: carrot at google dot com
GCC build triplet: i686-linux
GCC host triplet: i686-linux
GCC target triplet: arm-eabi
http://gcc.gnu.org/bugzilla/show_bug.cgi?id=42495
