Ben Dooks wrote: > actually, thinking about it, we can probably get better code by doing: > > /* mop up any non-word aligned length reads. */ > for (i = (len & ~3); i != len; i++) > ptr[i] = readb(info->regs + S3C2440_NFDATA);
It looks nicer, but, surprisingly, it's one instruction longer and
three instructions slower (in the normal case, i.e., with word
alignment), see below (with the "buf" fix).
Notation:
; <instruction count> +<instructions executed after readsl>
- Werner
----- for (i = 0; i != (len & 3); i++) ------------------------------------
s3c2440_nand_read_buf:
@ args = 0, pretend = 0, frame = 0
@ frame_needed = 1, uses_anonymous_args = 0
mov ip, sp ; 1
stmfd sp!, {r4, r5, r6, fp, ip, lr, pc} ; 2
sub fp, ip, #4 ; 3
sub sp, sp, #4 ; 4
ldr r6, [r0, #536] ; 5
mov r4, r2 ; 6
ldr r0, [r6, #96] ; 7
cmp r4, #0 ; 8
add r2, r2, #3 ; 9
movge r2, r4 ; 10
mov r2, r2, asr #2 ; 11
bic r3, r4, #3 ; 12
add r0, r0, #16 ; 13
add r5, r1, r3 ; 14
bl __raw_readsl ; 15
mov r2, #0 ; 16 +1
b .L212 ; 17 +2
.L213:
ldr r3, [r6, #96] ; 18
ldrb r3, [r3, #16] @ zero_extendqisi2 ; 19
strb r3, [r5, r2] ; 20
add r2, r2, #1 ; 21
.L212:
and r3, r4, #3 ; 22 +3
cmp r2, r3 ; 23 +4
bne .L213 ; 24 +5
ldmfd sp, {r3, r4, r5, r6, fp, sp, pc} ; 25 +6
----- for (i = (len & ~3); i != len; i++) ---------------------------------
s3c2440_nand_read_buf:
@ args = 0, pretend = 0, frame = 0
@ frame_needed = 1, uses_anonymous_args = 0
mov ip, sp ; 1
stmfd sp!, {r4, r5, r6, fp, ip, lr, pc} ; 2
sub fp, ip, #4 ; 3
sub sp, sp, #4 ; 4
ldr r6, [r0, #536] ; 5
mov r5, r2 ; 6
ldr r0, [r6, #96] ; 7
cmp r5, #0 ; 8
add r2, r2, #3 ; 9
movge r2, r5 ; 10
mov r2, r2, asr #2 ; 11
add r0, r0, #16 ; 12
mov r4, r1 ; 13
bl __raw_readsl ; 14
bic r1, r5, #3 ; 15 +1
add r4, r4, r1 ; 16 +2
mov r2, #0 ; 17 +3
b .L212 ; 18 +4
.L213:
ldr r3, [r6, #96] ; 19
ldrb r3, [r3, #16] @ zero_extendqisi2 ; 20
strb r3, [r4], #1 ; 21
.L212:
rsb r3, r1, r5 ; 22 +5
cmp r2, r3 ; 23 +6
add r2, r2, #1 ; 24 +7
bne .L213 ; 25 +8
ldmfd sp, {r3, r4, r5, r6, fp, sp, pc} ; 26 +9
