https://gcc.gnu.org/bugzilla/show_bug.cgi?id=102125
Bug ID: 102125
Summary: (ARM Cortex-M3 and newer) missed optimization. memcpy
not needed operations
Product: gcc
Version: 10.2.1
Status: UNCONFIRMED
Severity: normal
Priority: P3
Component: c
Assignee: unassigned at gcc dot gnu.org
Reporter: jankowski938 at gmail dot com
Target Milestone: ---
uint64_t bar64(const uint8_t *rData1)
{
uint64_t buffer;
memcpy(&buffer, rData1, sizeof(buffer));
return buffer;
}
compiler options:
-Ox -mthumb -mcpu=cortex-my
where x : 2,3,s y:3,4,7
```
bar64:
sub sp, sp, #8
mov r2, r0
ldr r0, [r0] @ unaligned
ldr r1, [r2, #4] @ unaligned
mov r3, sp
stmia r3!, {r0, r1}
ldrd r0, [sp]
add sp, sp, #8
bx lr
```
it is enough to:
```
mov r3, r0
ldr r0, [r0] @ unaligned
ldr r1, [r3, #4] @ unaligned
bx lr
```
32 bit memcpy is optimized correctly:
Full example code:
```
uint64_t foo64(const uint8_t *rData1)
{
uint64_t buffer;
buffer = (((uint64_t)rData1[7]) << 56)|((uint64_t)(rData1[6]) <<
48)|((uint64_t)(rData1[5]) << 40)|(((uint64_t)rData1[4]) << 32)|
(((uint64_t)rData1[3]) <<
24)|(((uint64_t)rData1[2]) << 16)|((uint64_t)(rData1[1]) << 8)|rData1[0];
return buffer;
}
uint64_t bar64(const uint8_t *rData1)
{
uint64_t buffer;
memcpy(&buffer, rData1, sizeof(buffer));
return buffer;
}
uint32_t foo32(const uint8_t *rData1)
{
uint32_t buffer;
buffer = (((uint32_t)rData1[3]) << 24)|(((uint32_t)rData1[2]) <<
16)|((uint32_t)(rData1[1]) << 8)|rData1[0];
return buffer;
}
uint32_t bar32(const uint8_t *rData1)
{
uint32_t buffer;
memcpy(&buffer, rData1, sizeof(buffer));
return buffer;
}
```
compiler output:
```
foo64:
mov r3, r0
ldr r0, [r0] @ unaligned
ldr r1, [r3, #4] @ unaligned
bx lr
bar64:
sub sp, sp, #8
mov r2, r0
ldr r0, [r0] @ unaligned
ldr r1, [r2, #4] @ unaligned
mov r3, sp
stmia r3!, {r0, r1}
ldrd r0, [sp]
add sp, sp, #8
bx lr
foo32:
ldr r0, [r0] @ unaligned
bx lr
bar32:
ldr r0, [r0] @ unaligned
bx lr
```
Clang compiles without overhead:
https://godbolt.org/z/P7G7Whxqz
