linux-sg2042/arch/arm/crypto/sha1-armv4-large.S

498 lines
13 KiB
ArmAsm

#define __ARM_ARCH__ __LINUX_ARM_ARCH__
@ ====================================================================
@ Written by Andy Polyakov <appro@fy.chalmers.se> for the OpenSSL
@ project. The module is, however, dual licensed under OpenSSL and
@ CRYPTOGAMS licenses depending on where you obtain it. For further
@ details see http://www.openssl.org/~appro/cryptogams/.
@ ====================================================================
@ sha1_block procedure for ARMv4.
@
@ January 2007.
@ Size/performance trade-off
@ ====================================================================
@ impl size in bytes comp cycles[*] measured performance
@ ====================================================================
@ thumb 304 3212 4420
@ armv4-small 392/+29% 1958/+64% 2250/+96%
@ armv4-compact 740/+89% 1552/+26% 1840/+22%
@ armv4-large 1420/+92% 1307/+19% 1370/+34%[***]
@ full unroll ~5100/+260% ~1260/+4% ~1300/+5%
@ ====================================================================
@ thumb = same as 'small' but in Thumb instructions[**] and
@ with recurring code in two private functions;
@ small = detached Xload/update, loops are folded;
@ compact = detached Xload/update, 5x unroll;
@ large = interleaved Xload/update, 5x unroll;
@ full unroll = interleaved Xload/update, full unroll, estimated[!];
@
@ [*] Manually counted instructions in "grand" loop body. Measured
@ performance is affected by prologue and epilogue overhead,
@ i-cache availability, branch penalties, etc.
@ [**] While each Thumb instruction is twice smaller, they are not as
@ diverse as ARM ones: e.g., there are only two arithmetic
@ instructions with 3 arguments, no [fixed] rotate, addressing
@ modes are limited. As result it takes more instructions to do
@ the same job in Thumb, therefore the code is never twice as
@ small and always slower.
@ [***] which is also ~35% better than compiler generated code. Dual-
@ issue Cortex A8 core was measured to process input block in
@ ~990 cycles.
@ August 2010.
@
@ Rescheduling for dual-issue pipeline resulted in 13% improvement on
@ Cortex A8 core and in absolute terms ~870 cycles per input block
@ [or 13.6 cycles per byte].
@ February 2011.
@
@ Profiler-assisted and platform-specific optimization resulted in 10%
@ improvement on Cortex A8 core and 12.2 cycles per byte.
#include <linux/linkage.h>
.text
.align 2
ENTRY(sha1_block_data_order)
stmdb sp!,{r4-r12,lr}
add r2,r1,r2,lsl#6 @ r2 to point at the end of r1
ldmia r0,{r3,r4,r5,r6,r7}
.Lloop:
ldr r8,.LK_00_19
mov r14,sp
sub sp,sp,#15*4
mov r5,r5,ror#30
mov r6,r6,ror#30
mov r7,r7,ror#30 @ [6]
.L_00_15:
#if __ARM_ARCH__<7
ldrb r10,[r1,#2]
ldrb r9,[r1,#3]
ldrb r11,[r1,#1]
add r7,r8,r7,ror#2 @ E+=K_00_19
ldrb r12,[r1],#4
orr r9,r9,r10,lsl#8
eor r10,r5,r6 @ F_xx_xx
orr r9,r9,r11,lsl#16
add r7,r7,r3,ror#27 @ E+=ROR(A,27)
orr r9,r9,r12,lsl#24
#else
ldr r9,[r1],#4 @ handles unaligned
add r7,r8,r7,ror#2 @ E+=K_00_19
eor r10,r5,r6 @ F_xx_xx
add r7,r7,r3,ror#27 @ E+=ROR(A,27)
#ifdef __ARMEL__
rev r9,r9 @ byte swap
#endif
#endif
and r10,r4,r10,ror#2
add r7,r7,r9 @ E+=X[i]
eor r10,r10,r6,ror#2 @ F_00_19(B,C,D)
str r9,[r14,#-4]!
add r7,r7,r10 @ E+=F_00_19(B,C,D)
#if __ARM_ARCH__<7
ldrb r10,[r1,#2]
ldrb r9,[r1,#3]
ldrb r11,[r1,#1]
add r6,r8,r6,ror#2 @ E+=K_00_19
ldrb r12,[r1],#4
orr r9,r9,r10,lsl#8
eor r10,r4,r5 @ F_xx_xx
orr r9,r9,r11,lsl#16
add r6,r6,r7,ror#27 @ E+=ROR(A,27)
orr r9,r9,r12,lsl#24
#else
ldr r9,[r1],#4 @ handles unaligned
add r6,r8,r6,ror#2 @ E+=K_00_19
eor r10,r4,r5 @ F_xx_xx
add r6,r6,r7,ror#27 @ E+=ROR(A,27)
#ifdef __ARMEL__
rev r9,r9 @ byte swap
#endif
#endif
and r10,r3,r10,ror#2
add r6,r6,r9 @ E+=X[i]
eor r10,r10,r5,ror#2 @ F_00_19(B,C,D)
str r9,[r14,#-4]!
add r6,r6,r10 @ E+=F_00_19(B,C,D)
#if __ARM_ARCH__<7
ldrb r10,[r1,#2]
ldrb r9,[r1,#3]
ldrb r11,[r1,#1]
add r5,r8,r5,ror#2 @ E+=K_00_19
ldrb r12,[r1],#4
orr r9,r9,r10,lsl#8
eor r10,r3,r4 @ F_xx_xx
orr r9,r9,r11,lsl#16
add r5,r5,r6,ror#27 @ E+=ROR(A,27)
orr r9,r9,r12,lsl#24
#else
ldr r9,[r1],#4 @ handles unaligned
add r5,r8,r5,ror#2 @ E+=K_00_19
eor r10,r3,r4 @ F_xx_xx
add r5,r5,r6,ror#27 @ E+=ROR(A,27)
#ifdef __ARMEL__
rev r9,r9 @ byte swap
#endif
#endif
and r10,r7,r10,ror#2
add r5,r5,r9 @ E+=X[i]
eor r10,r10,r4,ror#2 @ F_00_19(B,C,D)
str r9,[r14,#-4]!
add r5,r5,r10 @ E+=F_00_19(B,C,D)
#if __ARM_ARCH__<7
ldrb r10,[r1,#2]
ldrb r9,[r1,#3]
ldrb r11,[r1,#1]
add r4,r8,r4,ror#2 @ E+=K_00_19
ldrb r12,[r1],#4
orr r9,r9,r10,lsl#8
eor r10,r7,r3 @ F_xx_xx
orr r9,r9,r11,lsl#16
add r4,r4,r5,ror#27 @ E+=ROR(A,27)
orr r9,r9,r12,lsl#24
#else
ldr r9,[r1],#4 @ handles unaligned
add r4,r8,r4,ror#2 @ E+=K_00_19
eor r10,r7,r3 @ F_xx_xx
add r4,r4,r5,ror#27 @ E+=ROR(A,27)
#ifdef __ARMEL__
rev r9,r9 @ byte swap
#endif
#endif
and r10,r6,r10,ror#2
add r4,r4,r9 @ E+=X[i]
eor r10,r10,r3,ror#2 @ F_00_19(B,C,D)
str r9,[r14,#-4]!
add r4,r4,r10 @ E+=F_00_19(B,C,D)
#if __ARM_ARCH__<7
ldrb r10,[r1,#2]
ldrb r9,[r1,#3]
ldrb r11,[r1,#1]
add r3,r8,r3,ror#2 @ E+=K_00_19
ldrb r12,[r1],#4
orr r9,r9,r10,lsl#8
eor r10,r6,r7 @ F_xx_xx
orr r9,r9,r11,lsl#16
add r3,r3,r4,ror#27 @ E+=ROR(A,27)
orr r9,r9,r12,lsl#24
#else
ldr r9,[r1],#4 @ handles unaligned
add r3,r8,r3,ror#2 @ E+=K_00_19
eor r10,r6,r7 @ F_xx_xx
add r3,r3,r4,ror#27 @ E+=ROR(A,27)
#ifdef __ARMEL__
rev r9,r9 @ byte swap
#endif
#endif
and r10,r5,r10,ror#2
add r3,r3,r9 @ E+=X[i]
eor r10,r10,r7,ror#2 @ F_00_19(B,C,D)
str r9,[r14,#-4]!
add r3,r3,r10 @ E+=F_00_19(B,C,D)
cmp r14,sp
bne .L_00_15 @ [((11+4)*5+2)*3]
sub sp,sp,#25*4
#if __ARM_ARCH__<7
ldrb r10,[r1,#2]
ldrb r9,[r1,#3]
ldrb r11,[r1,#1]
add r7,r8,r7,ror#2 @ E+=K_00_19
ldrb r12,[r1],#4
orr r9,r9,r10,lsl#8
eor r10,r5,r6 @ F_xx_xx
orr r9,r9,r11,lsl#16
add r7,r7,r3,ror#27 @ E+=ROR(A,27)
orr r9,r9,r12,lsl#24
#else
ldr r9,[r1],#4 @ handles unaligned
add r7,r8,r7,ror#2 @ E+=K_00_19
eor r10,r5,r6 @ F_xx_xx
add r7,r7,r3,ror#27 @ E+=ROR(A,27)
#ifdef __ARMEL__
rev r9,r9 @ byte swap
#endif
#endif
and r10,r4,r10,ror#2
add r7,r7,r9 @ E+=X[i]
eor r10,r10,r6,ror#2 @ F_00_19(B,C,D)
str r9,[r14,#-4]!
add r7,r7,r10 @ E+=F_00_19(B,C,D)
ldr r9,[r14,#15*4]
ldr r10,[r14,#13*4]
ldr r11,[r14,#7*4]
add r6,r8,r6,ror#2 @ E+=K_xx_xx
ldr r12,[r14,#2*4]
eor r9,r9,r10
eor r11,r11,r12 @ 1 cycle stall
eor r10,r4,r5 @ F_xx_xx
mov r9,r9,ror#31
add r6,r6,r7,ror#27 @ E+=ROR(A,27)
eor r9,r9,r11,ror#31
str r9,[r14,#-4]!
and r10,r3,r10,ror#2 @ F_xx_xx
@ F_xx_xx
add r6,r6,r9 @ E+=X[i]
eor r10,r10,r5,ror#2 @ F_00_19(B,C,D)
add r6,r6,r10 @ E+=F_00_19(B,C,D)
ldr r9,[r14,#15*4]
ldr r10,[r14,#13*4]
ldr r11,[r14,#7*4]
add r5,r8,r5,ror#2 @ E+=K_xx_xx
ldr r12,[r14,#2*4]
eor r9,r9,r10
eor r11,r11,r12 @ 1 cycle stall
eor r10,r3,r4 @ F_xx_xx
mov r9,r9,ror#31
add r5,r5,r6,ror#27 @ E+=ROR(A,27)
eor r9,r9,r11,ror#31
str r9,[r14,#-4]!
and r10,r7,r10,ror#2 @ F_xx_xx
@ F_xx_xx
add r5,r5,r9 @ E+=X[i]
eor r10,r10,r4,ror#2 @ F_00_19(B,C,D)
add r5,r5,r10 @ E+=F_00_19(B,C,D)
ldr r9,[r14,#15*4]
ldr r10,[r14,#13*4]
ldr r11,[r14,#7*4]
add r4,r8,r4,ror#2 @ E+=K_xx_xx
ldr r12,[r14,#2*4]
eor r9,r9,r10
eor r11,r11,r12 @ 1 cycle stall
eor r10,r7,r3 @ F_xx_xx
mov r9,r9,ror#31
add r4,r4,r5,ror#27 @ E+=ROR(A,27)
eor r9,r9,r11,ror#31
str r9,[r14,#-4]!
and r10,r6,r10,ror#2 @ F_xx_xx
@ F_xx_xx
add r4,r4,r9 @ E+=X[i]
eor r10,r10,r3,ror#2 @ F_00_19(B,C,D)
add r4,r4,r10 @ E+=F_00_19(B,C,D)
ldr r9,[r14,#15*4]
ldr r10,[r14,#13*4]
ldr r11,[r14,#7*4]
add r3,r8,r3,ror#2 @ E+=K_xx_xx
ldr r12,[r14,#2*4]
eor r9,r9,r10
eor r11,r11,r12 @ 1 cycle stall
eor r10,r6,r7 @ F_xx_xx
mov r9,r9,ror#31
add r3,r3,r4,ror#27 @ E+=ROR(A,27)
eor r9,r9,r11,ror#31
str r9,[r14,#-4]!
and r10,r5,r10,ror#2 @ F_xx_xx
@ F_xx_xx
add r3,r3,r9 @ E+=X[i]
eor r10,r10,r7,ror#2 @ F_00_19(B,C,D)
add r3,r3,r10 @ E+=F_00_19(B,C,D)
ldr r8,.LK_20_39 @ [+15+16*4]
cmn sp,#0 @ [+3], clear carry to denote 20_39
.L_20_39_or_60_79:
ldr r9,[r14,#15*4]
ldr r10,[r14,#13*4]
ldr r11,[r14,#7*4]
add r7,r8,r7,ror#2 @ E+=K_xx_xx
ldr r12,[r14,#2*4]
eor r9,r9,r10
eor r11,r11,r12 @ 1 cycle stall
eor r10,r5,r6 @ F_xx_xx
mov r9,r9,ror#31
add r7,r7,r3,ror#27 @ E+=ROR(A,27)
eor r9,r9,r11,ror#31
str r9,[r14,#-4]!
eor r10,r4,r10,ror#2 @ F_xx_xx
@ F_xx_xx
add r7,r7,r9 @ E+=X[i]
add r7,r7,r10 @ E+=F_20_39(B,C,D)
ldr r9,[r14,#15*4]
ldr r10,[r14,#13*4]
ldr r11,[r14,#7*4]
add r6,r8,r6,ror#2 @ E+=K_xx_xx
ldr r12,[r14,#2*4]
eor r9,r9,r10
eor r11,r11,r12 @ 1 cycle stall
eor r10,r4,r5 @ F_xx_xx
mov r9,r9,ror#31
add r6,r6,r7,ror#27 @ E+=ROR(A,27)
eor r9,r9,r11,ror#31
str r9,[r14,#-4]!
eor r10,r3,r10,ror#2 @ F_xx_xx
@ F_xx_xx
add r6,r6,r9 @ E+=X[i]
add r6,r6,r10 @ E+=F_20_39(B,C,D)
ldr r9,[r14,#15*4]
ldr r10,[r14,#13*4]
ldr r11,[r14,#7*4]
add r5,r8,r5,ror#2 @ E+=K_xx_xx
ldr r12,[r14,#2*4]
eor r9,r9,r10
eor r11,r11,r12 @ 1 cycle stall
eor r10,r3,r4 @ F_xx_xx
mov r9,r9,ror#31
add r5,r5,r6,ror#27 @ E+=ROR(A,27)
eor r9,r9,r11,ror#31
str r9,[r14,#-4]!
eor r10,r7,r10,ror#2 @ F_xx_xx
@ F_xx_xx
add r5,r5,r9 @ E+=X[i]
add r5,r5,r10 @ E+=F_20_39(B,C,D)
ldr r9,[r14,#15*4]
ldr r10,[r14,#13*4]
ldr r11,[r14,#7*4]
add r4,r8,r4,ror#2 @ E+=K_xx_xx
ldr r12,[r14,#2*4]
eor r9,r9,r10
eor r11,r11,r12 @ 1 cycle stall
eor r10,r7,r3 @ F_xx_xx
mov r9,r9,ror#31
add r4,r4,r5,ror#27 @ E+=ROR(A,27)
eor r9,r9,r11,ror#31
str r9,[r14,#-4]!
eor r10,r6,r10,ror#2 @ F_xx_xx
@ F_xx_xx
add r4,r4,r9 @ E+=X[i]
add r4,r4,r10 @ E+=F_20_39(B,C,D)
ldr r9,[r14,#15*4]
ldr r10,[r14,#13*4]
ldr r11,[r14,#7*4]
add r3,r8,r3,ror#2 @ E+=K_xx_xx
ldr r12,[r14,#2*4]
eor r9,r9,r10
eor r11,r11,r12 @ 1 cycle stall
eor r10,r6,r7 @ F_xx_xx
mov r9,r9,ror#31
add r3,r3,r4,ror#27 @ E+=ROR(A,27)
eor r9,r9,r11,ror#31
str r9,[r14,#-4]!
eor r10,r5,r10,ror#2 @ F_xx_xx
@ F_xx_xx
add r3,r3,r9 @ E+=X[i]
add r3,r3,r10 @ E+=F_20_39(B,C,D)
ARM( teq r14,sp ) @ preserve carry
THUMB( mov r11,sp )
THUMB( teq r14,r11 ) @ preserve carry
bne .L_20_39_or_60_79 @ [+((12+3)*5+2)*4]
bcs .L_done @ [+((12+3)*5+2)*4], spare 300 bytes
ldr r8,.LK_40_59
sub sp,sp,#20*4 @ [+2]
.L_40_59:
ldr r9,[r14,#15*4]
ldr r10,[r14,#13*4]
ldr r11,[r14,#7*4]
add r7,r8,r7,ror#2 @ E+=K_xx_xx
ldr r12,[r14,#2*4]
eor r9,r9,r10
eor r11,r11,r12 @ 1 cycle stall
eor r10,r5,r6 @ F_xx_xx
mov r9,r9,ror#31
add r7,r7,r3,ror#27 @ E+=ROR(A,27)
eor r9,r9,r11,ror#31
str r9,[r14,#-4]!
and r10,r4,r10,ror#2 @ F_xx_xx
and r11,r5,r6 @ F_xx_xx
add r7,r7,r9 @ E+=X[i]
add r7,r7,r10 @ E+=F_40_59(B,C,D)
add r7,r7,r11,ror#2
ldr r9,[r14,#15*4]
ldr r10,[r14,#13*4]
ldr r11,[r14,#7*4]
add r6,r8,r6,ror#2 @ E+=K_xx_xx
ldr r12,[r14,#2*4]
eor r9,r9,r10
eor r11,r11,r12 @ 1 cycle stall
eor r10,r4,r5 @ F_xx_xx
mov r9,r9,ror#31
add r6,r6,r7,ror#27 @ E+=ROR(A,27)
eor r9,r9,r11,ror#31
str r9,[r14,#-4]!
and r10,r3,r10,ror#2 @ F_xx_xx
and r11,r4,r5 @ F_xx_xx
add r6,r6,r9 @ E+=X[i]
add r6,r6,r10 @ E+=F_40_59(B,C,D)
add r6,r6,r11,ror#2
ldr r9,[r14,#15*4]
ldr r10,[r14,#13*4]
ldr r11,[r14,#7*4]
add r5,r8,r5,ror#2 @ E+=K_xx_xx
ldr r12,[r14,#2*4]
eor r9,r9,r10
eor r11,r11,r12 @ 1 cycle stall
eor r10,r3,r4 @ F_xx_xx
mov r9,r9,ror#31
add r5,r5,r6,ror#27 @ E+=ROR(A,27)
eor r9,r9,r11,ror#31
str r9,[r14,#-4]!
and r10,r7,r10,ror#2 @ F_xx_xx
and r11,r3,r4 @ F_xx_xx
add r5,r5,r9 @ E+=X[i]
add r5,r5,r10 @ E+=F_40_59(B,C,D)
add r5,r5,r11,ror#2
ldr r9,[r14,#15*4]
ldr r10,[r14,#13*4]
ldr r11,[r14,#7*4]
add r4,r8,r4,ror#2 @ E+=K_xx_xx
ldr r12,[r14,#2*4]
eor r9,r9,r10
eor r11,r11,r12 @ 1 cycle stall
eor r10,r7,r3 @ F_xx_xx
mov r9,r9,ror#31
add r4,r4,r5,ror#27 @ E+=ROR(A,27)
eor r9,r9,r11,ror#31
str r9,[r14,#-4]!
and r10,r6,r10,ror#2 @ F_xx_xx
and r11,r7,r3 @ F_xx_xx
add r4,r4,r9 @ E+=X[i]
add r4,r4,r10 @ E+=F_40_59(B,C,D)
add r4,r4,r11,ror#2
ldr r9,[r14,#15*4]
ldr r10,[r14,#13*4]
ldr r11,[r14,#7*4]
add r3,r8,r3,ror#2 @ E+=K_xx_xx
ldr r12,[r14,#2*4]
eor r9,r9,r10
eor r11,r11,r12 @ 1 cycle stall
eor r10,r6,r7 @ F_xx_xx
mov r9,r9,ror#31
add r3,r3,r4,ror#27 @ E+=ROR(A,27)
eor r9,r9,r11,ror#31
str r9,[r14,#-4]!
and r10,r5,r10,ror#2 @ F_xx_xx
and r11,r6,r7 @ F_xx_xx
add r3,r3,r9 @ E+=X[i]
add r3,r3,r10 @ E+=F_40_59(B,C,D)
add r3,r3,r11,ror#2
cmp r14,sp
bne .L_40_59 @ [+((12+5)*5+2)*4]
ldr r8,.LK_60_79
sub sp,sp,#20*4
cmp sp,#0 @ set carry to denote 60_79
b .L_20_39_or_60_79 @ [+4], spare 300 bytes
.L_done:
add sp,sp,#80*4 @ "deallocate" stack frame
ldmia r0,{r8,r9,r10,r11,r12}
add r3,r8,r3
add r4,r9,r4
add r5,r10,r5,ror#2
add r6,r11,r6,ror#2
add r7,r12,r7,ror#2
stmia r0,{r3,r4,r5,r6,r7}
teq r1,r2
bne .Lloop @ [+18], total 1307
ldmia sp!,{r4-r12,pc}
.align 2
.LK_00_19: .word 0x5a827999
.LK_20_39: .word 0x6ed9eba1
.LK_40_59: .word 0x8f1bbcdc
.LK_60_79: .word 0xca62c1d6
ENDPROC(sha1_block_data_order)
.asciz "SHA1 block transform for ARMv4, CRYPTOGAMS by <appro@openssl.org>"
.align 2