------- Comment #8 from froydnj at gcc dot gnu dot org 2010-01-25 21:10 -------
First, something has gotten better; an arm-eabi gcc (-O2 -std=c99 -mcpu=arm9
-funroll-loops) from 20091209 gives:
Unroll:
@ Function supports interworking.
@ args = 0, pretend = 0, frame = 0
@ frame_needed = 0, uses_anonymous_args = 0
@ link register save eliminated.
stmfd sp!, {r4, r5, r6, r7, r8}
add r8, r1, #256
.L2:
ldr ip, [r1, #0]
mov r7, r1
mul r2, ip, r0
str r2, [r7], #4
ldr r3, [r1, #4]
ldr r5, [r7, #4]
mul r6, r3, r0
str r6, [r7, #0]
ldr r4, [r1, #12]
ldr ip, [r1, #16]
add r2, r1, #20
ldmia r2, {r2, r3, r7} @ phole ldm
mul r6, r5, r0
mul r5, r4, r0
mul r4, ip, r0
mul ip, r2, r0
mul r2, r3, r0
mul r3, r7, r0
str r6, [r1, #8]
str r5, [r1, #12]
str r4, [r1, #16]
str ip, [r1, #20]
str r2, [r1, #24]
add r1, r1, #32
cmp r1, r8
str r3, [r1, #-4]
bne .L2
ldmfd sp!, {r4, r5, r6, r7, r8}
bx lr
.size Unroll, .-Unroll
.ident "GCC: (GNU) 4.5.0 20091209 (experimental)"
which, if not close to ManualUnroll from the first comment, is much better than
the initial example.
Second, the problem Daniel mentioned concerning auto-inc/dec not doing the
right thing is because of the cleverness of
loop-unroll.c:analyze_iv_to_split_insn. It breaks the code shape that
auto-inc/dec needs. (You can see its effects in the assembly above; the
spurious move to r7 at the top of the loop.) Even if you disable that bit of
RTL loop unrolling, you also need to disable the web pass so as to not really
break the code shape for auto-inc/dec and introduce spurious moves into the
RTL. Once you do that, you get:
Unroll:
@ Function supports interworking.
@ args = 0, pretend = 0, frame = 0
@ frame_needed = 0, uses_anonymous_args = 0
@ link register save eliminated.
add ip, r1, #256
.L2:
ldr r2, [r1, #0]
mul r3, r2, r0
str r3, [r1], #4
ldr r2, [r1, #0]
mul r3, r2, r0
str r3, [r1], #4
ldr r2, [r1, #0]
mul r3, r2, r0
str r3, [r1], #4
ldr r2, [r1, #0]
mul r3, r2, r0
str r3, [r1], #4
ldr r2, [r1, #0]
mul r3, r2, r0
str r3, [r1], #4
ldr r2, [r1, #0]
mul r3, r2, r0
str r3, [r1], #4
ldr r2, [r1, #0]
mul r3, r2, r0
str r3, [r1], #4
ldr r2, [r1, #0]
mul r3, r2, r0
str r3, [r1], #4
cmp r1, ip
bne .L2
bx lr
--
http://gcc.gnu.org/bugzilla/show_bug.cgi?id=36712
