https://gcc.gnu.org/bugzilla/show_bug.cgi?id=91776
--- Comment #2 from yhr-_-yhr at qq dot com ---
> I think it's BM2837, ie. Cortex-A53. Or did you mean a different Pi?
oops you're right, I just got this pointed out when I showed this post to my
friend. I just copied it from `cat /proc/cpuinfo`.
> Can you try using -mno-strict-it on your examples and see whether that helps?
Did you mean -mno-restrict-it? I followed gcc's correction info.
(4)
pi@rpi:~/Desktop $ gcc -v -save-temps -Wall -march=native -mtune=native
-mno-restrict-it -o fibmod -O2 -fsplit-paths fibmod.c
[...]
pi@rpi:~/Desktop $ ./fibmod
~ 129358055 loop/s
~ 144338387 loop/s
~ 143361058 loop/s
~ 143191701 loop/s
~ 143414626 loop/s
~ 143312006 loop/s
^C
[fibmod.S]
.L7:
mov r1, #0
mov r2, #1
mov r0, r1
b .L5
.L13:
sub r3, r3, r10
cmp r2, #0
cmpeq r3, #1
beq .L4
.L3:
mov r0, r2
mov r2, r3
.L5:
add r3, r0, r2
add r1, r1, #1
cmp r10, r3
bls .L13
cmp r3, #1
cmpeq r2, #0
bne .L3
.L4:
adds r4, r4, r1
adc r5, r5, #0
subs r6, r4, ip
sbc r7, r5, lr
cmp r7, r9
cmpeq r6, r8
bls .L6
bl clock
mov r1, r7
str r0, [sp]
mov r0, r6
bl __aeabi_ul2d
ldr r3, [sp]
vmov d6, r0, r1
ldr r0, [sp, #4]
sub r2, r3, fp
vmov s14, r2 @ int
mov fp, r3
vcvt.f64.s32 d7, s14
vdiv.f64 d6, d6, d7
vmul.f64 d7, d6, d8
vmov r2, r3, d7
bl printf
mov ip, r4
mov lr, r5
.L6:
add r10, r10, #1
b .L7
(5)
pi@rpi:~/Desktop $ gcc -v -save-temps -Wall -march=native -mtune=native
-mno-restrict-it -o fibmod -O2 fibmod.c
[...]
pi@rpi:~/Desktop $ ./fibmod
~ 277312518 loop/s
~ 279153709 loop/s
~ 278075227 loop/s
~ 277919398 loop/s
~ 277167351 loop/s
~ 278028104 loop/s
~ 278017452 loop/s
^C
[fibmod.S]
.L5:
mov r1, #0
mov r2, #1
mov r0, r1
.L3:
add r3, r0, r2
add r1, r1, #1
cmp r10, r3
mov r0, r2
subls r3, r3, r10
cmp r3, #1
cmpeq r2, #0
mov r2, r3
bne .L3
adds r4, r4, r1
adc r5, r5, #0
subs r6, r4, ip
sbc r7, r5, lr
cmp r7, r9
cmpeq r6, r8
bls .L4
bl clock
mov r1, r7
str r0, [sp]
mov r0, r6
bl __aeabi_ul2d
ldr r3, [sp]
vmov d6, r0, r1
ldr r0, [sp, #4]
sub r2, r3, fp
vmov s14, r2 @ int
mov fp, r3
vcvt.f64.s32 d7, s14
vdiv.f64 d6, d6, d7
vmul.f64 d7, d6, d8
vmov r2, r3, d7
bl printf
mov ip, r4
mov lr, r5
.L4:
add r10, r10, #1
b .L5
I also checked the two fibmod.S without `-mno-restrict-it` but it seems to be
no difference.
Oh but I found another that actually makes a little (~7%) difference.. without
`-march=native -mtune=native`
(6)
pi@rpi:~/Desktop $ gcc -v -save-temps -Wall -mno-restrict-it -o fibmod -O2
-fsplit-paths fibmod.c
[...]
pi@rpi:~/Desktop $ ./fibmod
~ 140006573 loop/s
~ 153067683 loop/s
~ 153172437 loop/s
~ 152992126 loop/s
~ 153133548 loop/s
^C
[fibmod.S]
.L7:
mov r1, #0
mov r0, r1 @ here
mov r2, #1 @ here
b .L5
.L13:
sub r3, r3, r10
cmp r2, #0
cmpeq r3, #1
beq .L4
.L3:
mov r0, r2
mov r2, r3
.L5:
add r3, r0, r2
cmp r10, r3 @ here
add r1, r1, #1 @ here
bls .L13
cmp r3, #1
cmpeq r2, #0
bne .L3
.L4:
adds r4, r4, r1
adc r5, r5, #0
subs r6, r4, ip
sbc r7, r5, lr
cmp r7, r9
cmpeq r6, r8
bls .L6
bl clock
mov r1, r7
str r0, [sp, #4]
mov r0, r6
bl __aeabi_ul2d
ldr r3, [sp, #4]
sub r2, r3, fp
mov fp, r3
vmov s14, r2 @ int
vcvt.f64.s32 d7, s14
vmov d6, r0, r1
ldr r0, .L14+16
vdiv.f64 d6, d6, d7
vmul.f64 d7, d6, d8
vmov r2, r3, d7
bl printf
mov ip, r4
mov lr, r5
.L6:
add r10, r10, #1
b .L7
with neither `-fsplit-paths` nor `-march=native -mtune=native` the speed is
identical to (5).
