[PATCH 1/4] crypto: arm: generate *.S by Perl at build time instead of shipping them

From: Masahiro Yamada
Date: Sun Apr 25 2021 - 13:59:36 EST

Next message: Masahiro Yamada: "[PATCH 2/4] crypto: arm: use a pattern rule for generating *.S files"
Previous message: Masahiro Yamada: "[PATCH 4/4] crypto: arm64: use a pattern rule for generating *.S files"
Next in thread: Masahiro Yamada: "[PATCH 4/4] crypto: arm64: use a pattern rule for generating *.S files"
Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]

Generate *.S by Perl like arch/{mips,x86}/crypto/Makefile.

Signed-off-by: Masahiro Yamada <masahiroy@xxxxxxxxxx>
---

arch/arm/crypto/Makefile | 8 +-
arch/arm/crypto/poly1305-core.S_shipped | 1158 ----------
arch/arm/crypto/sha256-core.S_shipped | 2816 -----------------------
arch/arm/crypto/sha512-core.S_shipped | 1869 ---------------
4 files changed, 3 insertions(+), 5848 deletions(-)
delete mode 100644 arch/arm/crypto/poly1305-core.S_shipped
delete mode 100644 arch/arm/crypto/sha256-core.S_shipped
delete mode 100644 arch/arm/crypto/sha512-core.S_shipped

diff --git a/arch/arm/crypto/Makefile b/arch/arm/crypto/Makefile
index 8f26c454ea12..51f160c61740 100644
--- a/arch/arm/crypto/Makefile
+++ b/arch/arm/crypto/Makefile
@@ -45,19 +45,17 @@ poly1305-arm-y := poly1305-core.o poly1305-glue.o
nhpoly1305-neon-y := nh-neon-core.o nhpoly1305-neon-glue.o
curve25519-neon-y := curve25519-core.o curve25519-glue.o

-ifdef REGENERATE_ARM_CRYPTO
quiet_cmd_perl = PERL $@
cmd_perl = $(PERL) $(<) > $(@)

-$(src)/poly1305-core.S_shipped: $(src)/poly1305-armv4.pl
+$(obj)/poly1305-core.S: $(src)/poly1305-armv4.pl
$(call cmd,perl)

-$(src)/sha256-core.S_shipped: $(src)/sha256-armv4.pl
+$(obj)/sha256-core.S: $(src)/sha256-armv4.pl
$(call cmd,perl)

-$(src)/sha512-core.S_shipped: $(src)/sha512-armv4.pl
+$(obj)/sha512-core.S: $(src)/sha512-armv4.pl
$(call cmd,perl)
-endif

clean-files += poly1305-core.S sha256-core.S sha512-core.S

diff --git a/arch/arm/crypto/poly1305-core.S_shipped b/arch/arm/crypto/poly1305-core.S_shipped
deleted file mode 100644
index 37b71d990293..000000000000
--- a/arch/arm/crypto/poly1305-core.S_shipped
+++ /dev/null
@@ -1,1158 +0,0 @@
-#ifndef __KERNEL__
-# include "arm_arch.h"
-#else
-# define __ARM_ARCH__ __LINUX_ARM_ARCH__
-# define __ARM_MAX_ARCH__ __LINUX_ARM_ARCH__
-# define poly1305_init poly1305_init_arm
-# define poly1305_blocks poly1305_blocks_arm
-# define poly1305_emit poly1305_emit_arm
-.globl poly1305_blocks_neon
-#endif
-
-#if defined(__thumb2__)
-.syntax unified
-.thumb
-#else
-.code 32
-#endif
-
-.text
-
-.globl poly1305_emit
-.globl poly1305_blocks
-.globl poly1305_init
-.type poly1305_init,%function
-.align 5
-poly1305_init:
-.Lpoly1305_init:
- stmdb sp!,{r4-r11}
-
- eor r3,r3,r3
- cmp r1,#0
- str r3,[r0,#0] @ zero hash value
- str r3,[r0,#4]
- str r3,[r0,#8]
- str r3,[r0,#12]
- str r3,[r0,#16]
- str r3,[r0,#36] @ clear is_base2_26
- add r0,r0,#20
-
-#ifdef __thumb2__
- it eq
-#endif
- moveq r0,#0
- beq .Lno_key
-
-#if __ARM_MAX_ARCH__>=7
- mov r3,#-1
- str r3,[r0,#28] @ impossible key power value
-# ifndef __KERNEL__
- adr r11,.Lpoly1305_init
- ldr r12,.LOPENSSL_armcap
-# endif
-#endif
- ldrb r4,[r1,#0]
- mov r10,#0x0fffffff
- ldrb r5,[r1,#1]
- and r3,r10,#-4 @ 0x0ffffffc
- ldrb r6,[r1,#2]
- ldrb r7,[r1,#3]
- orr r4,r4,r5,lsl#8
- ldrb r5,[r1,#4]
- orr r4,r4,r6,lsl#16
- ldrb r6,[r1,#5]
- orr r4,r4,r7,lsl#24
- ldrb r7,[r1,#6]
- and r4,r4,r10
-
-#if __ARM_MAX_ARCH__>=7 && !defined(__KERNEL__)
-# if !defined(_WIN32)
- ldr r12,[r11,r12] @ OPENSSL_armcap_P
-# endif
-# if defined(__APPLE__) || defined(_WIN32)
- ldr r12,[r12]
-# endif
-#endif
- ldrb r8,[r1,#7]
- orr r5,r5,r6,lsl#8
- ldrb r6,[r1,#8]
- orr r5,r5,r7,lsl#16
- ldrb r7,[r1,#9]
- orr r5,r5,r8,lsl#24
- ldrb r8,[r1,#10]
- and r5,r5,r3
-
-#if __ARM_MAX_ARCH__>=7 && !defined(__KERNEL__)
- tst r12,#ARMV7_NEON @ check for NEON
-# ifdef __thumb2__
- adr r9,.Lpoly1305_blocks_neon
- adr r11,.Lpoly1305_blocks
- it ne
- movne r11,r9
- adr r12,.Lpoly1305_emit
- orr r11,r11,#1 @ thumb-ify addresses
- orr r12,r12,#1
-# else
- add r12,r11,#(.Lpoly1305_emit-.Lpoly1305_init)
- ite eq
- addeq r11,r11,#(.Lpoly1305_blocks-.Lpoly1305_init)
- addne r11,r11,#(.Lpoly1305_blocks_neon-.Lpoly1305_init)
-# endif
-#endif
- ldrb r9,[r1,#11]
- orr r6,r6,r7,lsl#8
- ldrb r7,[r1,#12]
- orr r6,r6,r8,lsl#16
- ldrb r8,[r1,#13]
- orr r6,r6,r9,lsl#24
- ldrb r9,[r1,#14]
- and r6,r6,r3
-
- ldrb r10,[r1,#15]
- orr r7,r7,r8,lsl#8
- str r4,[r0,#0]
- orr r7,r7,r9,lsl#16
- str r5,[r0,#4]
- orr r7,r7,r10,lsl#24
- str r6,[r0,#8]
- and r7,r7,r3
- str r7,[r0,#12]
-#if __ARM_MAX_ARCH__>=7 && !defined(__KERNEL__)
- stmia r2,{r11,r12} @ fill functions table
- mov r0,#1
-#else
- mov r0,#0
-#endif
-.Lno_key:
- ldmia sp!,{r4-r11}
-#if __ARM_ARCH__>=5
- bx lr @ bx lr
-#else
- tst lr,#1
- moveq pc,lr @ be binary compatible with V4, yet
- .word 0xe12fff1e @ interoperable with Thumb ISA:-)
-#endif
-.size poly1305_init,.-poly1305_init
-.type poly1305_blocks,%function
-.align 5
-poly1305_blocks:
-.Lpoly1305_blocks:
- stmdb sp!,{r3-r11,lr}
-
- ands r2,r2,#-16
- beq .Lno_data
-
- add r2,r2,r1 @ end pointer
- sub sp,sp,#32
-
-#if __ARM_ARCH__<7
- ldmia r0,{r4-r12} @ load context
- add r0,r0,#20
- str r2,[sp,#16] @ offload stuff
- str r0,[sp,#12]
-#else
- ldr lr,[r0,#36] @ is_base2_26
- ldmia r0!,{r4-r8} @ load hash value
- str r2,[sp,#16] @ offload stuff
- str r0,[sp,#12]
-
- adds r9,r4,r5,lsl#26 @ base 2^26 -> base 2^32
- mov r10,r5,lsr#6
- adcs r10,r10,r6,lsl#20
- mov r11,r6,lsr#12
- adcs r11,r11,r7,lsl#14
- mov r12,r7,lsr#18
- adcs r12,r12,r8,lsl#8
- mov r2,#0
- teq lr,#0
- str r2,[r0,#16] @ clear is_base2_26
- adc r2,r2,r8,lsr#24
-
- itttt ne
- movne r4,r9 @ choose between radixes
- movne r5,r10
- movne r6,r11
- movne r7,r12
- ldmia r0,{r9-r12} @ load key
- it ne
- movne r8,r2
-#endif
-
- mov lr,r1
- cmp r3,#0
- str r10,[sp,#20]
- str r11,[sp,#24]
- str r12,[sp,#28]
- b .Loop
-
-.align 4
-.Loop:
-#if __ARM_ARCH__<7
- ldrb r0,[lr],#16 @ load input
-# ifdef __thumb2__
- it hi
-# endif
- addhi r8,r8,#1 @ 1<<128
- ldrb r1,[lr,#-15]
- ldrb r2,[lr,#-14]
- ldrb r3,[lr,#-13]
- orr r1,r0,r1,lsl#8
- ldrb r0,[lr,#-12]
- orr r2,r1,r2,lsl#16
- ldrb r1,[lr,#-11]
- orr r3,r2,r3,lsl#24
- ldrb r2,[lr,#-10]
- adds r4,r4,r3 @ accumulate input
-
- ldrb r3,[lr,#-9]
- orr r1,r0,r1,lsl#8
- ldrb r0,[lr,#-8]
- orr r2,r1,r2,lsl#16
- ldrb r1,[lr,#-7]
- orr r3,r2,r3,lsl#24
- ldrb r2,[lr,#-6]
- adcs r5,r5,r3
-
- ldrb r3,[lr,#-5]
- orr r1,r0,r1,lsl#8
- ldrb r0,[lr,#-4]
- orr r2,r1,r2,lsl#16
- ldrb r1,[lr,#-3]
- orr r3,r2,r3,lsl#24
- ldrb r2,[lr,#-2]
- adcs r6,r6,r3
-
- ldrb r3,[lr,#-1]
- orr r1,r0,r1,lsl#8
- str lr,[sp,#8] @ offload input pointer
- orr r2,r1,r2,lsl#16
- add r10,r10,r10,lsr#2
- orr r3,r2,r3,lsl#24
-#else
- ldr r0,[lr],#16 @ load input
- it hi
- addhi r8,r8,#1 @ padbit
- ldr r1,[lr,#-12]
- ldr r2,[lr,#-8]
- ldr r3,[lr,#-4]
-# ifdef __ARMEB__
- rev r0,r0
- rev r1,r1
- rev r2,r2
- rev r3,r3
-# endif
- adds r4,r4,r0 @ accumulate input
- str lr,[sp,#8] @ offload input pointer
- adcs r5,r5,r1
- add r10,r10,r10,lsr#2
- adcs r6,r6,r2
-#endif
- add r11,r11,r11,lsr#2
- adcs r7,r7,r3
- add r12,r12,r12,lsr#2
-
- umull r2,r3,r5,r9
- adc r8,r8,#0
- umull r0,r1,r4,r9
- umlal r2,r3,r8,r10
- umlal r0,r1,r7,r10
- ldr r10,[sp,#20] @ reload r10
- umlal r2,r3,r6,r12
- umlal r0,r1,r5,r12
- umlal r2,r3,r7,r11
- umlal r0,r1,r6,r11
- umlal r2,r3,r4,r10
- str r0,[sp,#0] @ future r4
- mul r0,r11,r8
- ldr r11,[sp,#24] @ reload r11
- adds r2,r2,r1 @ d1+=d0>>32
- eor r1,r1,r1
- adc lr,r3,#0 @ future r6
- str r2,[sp,#4] @ future r5
-
- mul r2,r12,r8
- eor r3,r3,r3
- umlal r0,r1,r7,r12
- ldr r12,[sp,#28] @ reload r12
- umlal r2,r3,r7,r9
- umlal r0,r1,r6,r9
- umlal r2,r3,r6,r10
- umlal r0,r1,r5,r10
- umlal r2,r3,r5,r11
- umlal r0,r1,r4,r11
- umlal r2,r3,r4,r12
- ldr r4,[sp,#0]
- mul r8,r9,r8
- ldr r5,[sp,#4]
-
- adds r6,lr,r0 @ d2+=d1>>32
- ldr lr,[sp,#8] @ reload input pointer
- adc r1,r1,#0
- adds r7,r2,r1 @ d3+=d2>>32
- ldr r0,[sp,#16] @ reload end pointer
- adc r3,r3,#0
- add r8,r8,r3 @ h4+=d3>>32
-
- and r1,r8,#-4
- and r8,r8,#3
- add r1,r1,r1,lsr#2 @ *=5
- adds r4,r4,r1
- adcs r5,r5,#0
- adcs r6,r6,#0
- adcs r7,r7,#0
- adc r8,r8,#0
-
- cmp r0,lr @ done yet?
- bhi .Loop
-
- ldr r0,[sp,#12]
- add sp,sp,#32
- stmdb r0,{r4-r8} @ store the result
-
-.Lno_data:
-#if __ARM_ARCH__>=5
- ldmia sp!,{r3-r11,pc}
-#else
- ldmia sp!,{r3-r11,lr}
- tst lr,#1
- moveq pc,lr @ be binary compatible with V4, yet
- .word 0xe12fff1e @ interoperable with Thumb ISA:-)
-#endif
-.size poly1305_blocks,.-poly1305_blocks
-.type poly1305_emit,%function
-.align 5
-poly1305_emit:
-.Lpoly1305_emit:
- stmdb sp!,{r4-r11}
-
- ldmia r0,{r3-r7}
-
-#if __ARM_ARCH__>=7
- ldr ip,[r0,#36] @ is_base2_26
-
- adds r8,r3,r4,lsl#26 @ base 2^26 -> base 2^32
- mov r9,r4,lsr#6
- adcs r9,r9,r5,lsl#20
- mov r10,r5,lsr#12
- adcs r10,r10,r6,lsl#14
- mov r11,r6,lsr#18
- adcs r11,r11,r7,lsl#8
- mov r0,#0
- adc r0,r0,r7,lsr#24
-
- tst ip,ip
- itttt ne
- movne r3,r8
- movne r4,r9
- movne r5,r10
- movne r6,r11
- it ne
- movne r7,r0
-#endif
-
- adds r8,r3,#5 @ compare to modulus
- adcs r9,r4,#0
- adcs r10,r5,#0
- adcs r11,r6,#0
- adc r0,r7,#0
- tst r0,#4 @ did it carry/borrow?
-
-#ifdef __thumb2__
- it ne
-#endif
- movne r3,r8
- ldr r8,[r2,#0]
-#ifdef __thumb2__
- it ne
-#endif
- movne r4,r9
- ldr r9,[r2,#4]
-#ifdef __thumb2__
- it ne
-#endif
- movne r5,r10
- ldr r10,[r2,#8]
-#ifdef __thumb2__
- it ne
-#endif
- movne r6,r11
- ldr r11,[r2,#12]
-
- adds r3,r3,r8
- adcs r4,r4,r9
- adcs r5,r5,r10
- adc r6,r6,r11
-
-#if __ARM_ARCH__>=7
-# ifdef __ARMEB__
- rev r3,r3
- rev r4,r4
- rev r5,r5
- rev r6,r6
-# endif
- str r3,[r1,#0]
- str r4,[r1,#4]
- str r5,[r1,#8]
- str r6,[r1,#12]
-#else
- strb r3,[r1,#0]
- mov r3,r3,lsr#8
- strb r4,[r1,#4]
- mov r4,r4,lsr#8
- strb r5,[r1,#8]
- mov r5,r5,lsr#8
- strb r6,[r1,#12]
- mov r6,r6,lsr#8
-
- strb r3,[r1,#1]
- mov r3,r3,lsr#8
- strb r4,[r1,#5]
- mov r4,r4,lsr#8
- strb r5,[r1,#9]
- mov r5,r5,lsr#8
- strb r6,[r1,#13]
- mov r6,r6,lsr#8
-
- strb r3,[r1,#2]
- mov r3,r3,lsr#8
- strb r4,[r1,#6]
- mov r4,r4,lsr#8
- strb r5,[r1,#10]
- mov r5,r5,lsr#8
- strb r6,[r1,#14]
- mov r6,r6,lsr#8
-
- strb r3,[r1,#3]
- strb r4,[r1,#7]
- strb r5,[r1,#11]
- strb r6,[r1,#15]
-#endif
- ldmia sp!,{r4-r11}
-#if __ARM_ARCH__>=5
- bx lr @ bx lr
-#else
- tst lr,#1
- moveq pc,lr @ be binary compatible with V4, yet
- .word 0xe12fff1e @ interoperable with Thumb ISA:-)
-#endif
-.size poly1305_emit,.-poly1305_emit
-#if __ARM_MAX_ARCH__>=7
-.fpu neon
-
-.type poly1305_init_neon,%function
-.align 5
-poly1305_init_neon:
-.Lpoly1305_init_neon:
- ldr r3,[r0,#48] @ first table element
- cmp r3,#-1 @ is value impossible?
- bne .Lno_init_neon
-
- ldr r4,[r0,#20] @ load key base 2^32
- ldr r5,[r0,#24]
- ldr r6,[r0,#28]
- ldr r7,[r0,#32]
-
- and r2,r4,#0x03ffffff @ base 2^32 -> base 2^26
- mov r3,r4,lsr#26
- mov r4,r5,lsr#20
- orr r3,r3,r5,lsl#6
- mov r5,r6,lsr#14
- orr r4,r4,r6,lsl#12
- mov r6,r7,lsr#8
- orr r5,r5,r7,lsl#18
- and r3,r3,#0x03ffffff
- and r4,r4,#0x03ffffff
- and r5,r5,#0x03ffffff
-
- vdup.32 d0,r2 @ r^1 in both lanes
- add r2,r3,r3,lsl#2 @ *5
- vdup.32 d1,r3
- add r3,r4,r4,lsl#2
- vdup.32 d2,r2
- vdup.32 d3,r4
- add r4,r5,r5,lsl#2
- vdup.32 d4,r3
- vdup.32 d5,r5
- add r5,r6,r6,lsl#2
- vdup.32 d6,r4
- vdup.32 d7,r6
- vdup.32 d8,r5
-
- mov r5,#2 @ counter
-
-.Lsquare_neon:
- @@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@
- @ d0 = h0*r0 + h4*5*r1 + h3*5*r2 + h2*5*r3 + h1*5*r4
- @ d1 = h1*r0 + h0*r1 + h4*5*r2 + h3*5*r3 + h2*5*r4
- @ d2 = h2*r0 + h1*r1 + h0*r2 + h4*5*r3 + h3*5*r4
- @ d3 = h3*r0 + h2*r1 + h1*r2 + h0*r3 + h4*5*r4
- @ d4 = h4*r0 + h3*r1 + h2*r2 + h1*r3 + h0*r4
-
- vmull.u32 q5,d0,d0[1]
- vmull.u32 q6,d1,d0[1]
- vmull.u32 q7,d3,d0[1]
- vmull.u32 q8,d5,d0[1]
- vmull.u32 q9,d7,d0[1]
-
- vmlal.u32 q5,d7,d2[1]
- vmlal.u32 q6,d0,d1[1]
- vmlal.u32 q7,d1,d1[1]
- vmlal.u32 q8,d3,d1[1]
- vmlal.u32 q9,d5,d1[1]
-
- vmlal.u32 q5,d5,d4[1]
- vmlal.u32 q6,d7,d4[1]
- vmlal.u32 q8,d1,d3[1]
- vmlal.u32 q7,d0,d3[1]
- vmlal.u32 q9,d3,d3[1]
-
- vmlal.u32 q5,d3,d6[1]
- vmlal.u32 q8,d0,d5[1]
- vmlal.u32 q6,d5,d6[1]
- vmlal.u32 q7,d7,d6[1]
- vmlal.u32 q9,d1,d5[1]
-
- vmlal.u32 q8,d7,d8[1]
- vmlal.u32 q5,d1,d8[1]
- vmlal.u32 q6,d3,d8[1]
- vmlal.u32 q7,d5,d8[1]
- vmlal.u32 q9,d0,d7[1]
-
- @@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@
- @ lazy reduction as discussed in "NEON crypto" by D.J. Bernstein
- @ and P. Schwabe
- @
- @ H0>>+H1>>+H2>>+H3>>+H4
- @ H3>>+H4>>*5+H0>>+H1
- @
- @ Trivia.
- @
- @ Result of multiplication of n-bit number by m-bit number is
- @ n+m bits wide. However! Even though 2^n is a n+1-bit number,
- @ m-bit number multiplied by 2^n is still n+m bits wide.
- @
- @ Sum of two n-bit numbers is n+1 bits wide, sum of three - n+2,
- @ and so is sum of four. Sum of 2^m n-m-bit numbers and n-bit
- @ one is n+1 bits wide.
- @
- @ >>+ denotes Hnext += Hn>>26, Hn &= 0x3ffffff. This means that
- @ H0, H2, H3 are guaranteed to be 26 bits wide, while H1 and H4
- @ can be 27. However! In cases when their width exceeds 26 bits
- @ they are limited by 2^26+2^6. This in turn means that *sum*
- @ of the products with these values can still be viewed as sum
- @ of 52-bit numbers as long as the amount of addends is not a
- @ power of 2. For example,
- @
- @ H4 = H4*R0 + H3*R1 + H2*R2 + H1*R3 + H0 * R4,
- @
- @ which can't be larger than 5 * (2^26 + 2^6) * (2^26 + 2^6), or
- @ 5 * (2^52 + 2*2^32 + 2^12), which in turn is smaller than
- @ 8 * (2^52) or 2^55. However, the value is then multiplied by
- @ by 5, so we should be looking at 5 * 5 * (2^52 + 2^33 + 2^12),
- @ which is less than 32 * (2^52) or 2^57. And when processing
- @ data we are looking at triple as many addends...
- @
- @ In key setup procedure pre-reduced H0 is limited by 5*4+1 and
- @ 5*H4 - by 5*5 52-bit addends, or 57 bits. But when hashing the
- @ input H0 is limited by (5*4+1)*3 addends, or 58 bits, while
- @ 5*H4 by 5*5*3, or 59[!] bits. How is this relevant? vmlal.u32
- @ instruction accepts 2x32-bit input and writes 2x64-bit result.
- @ This means that result of reduction have to be compressed upon
- @ loop wrap-around. This can be done in the process of reduction
- @ to minimize amount of instructions [as well as amount of
- @ 128-bit instructions, which benefits low-end processors], but
- @ one has to watch for H2 (which is narrower than H0) and 5*H4
- @ not being wider than 58 bits, so that result of right shift
- @ by 26 bits fits in 32 bits. This is also useful on x86,
- @ because it allows to use paddd in place for paddq, which
- @ benefits Atom, where paddq is ridiculously slow.
-
- vshr.u64 q15,q8,#26
- vmovn.i64 d16,q8
- vshr.u64 q4,q5,#26
- vmovn.i64 d10,q5
- vadd.i64 q9,q9,q15 @ h3 -> h4
- vbic.i32 d16,#0xfc000000 @ &=0x03ffffff
- vadd.i64 q6,q6,q4 @ h0 -> h1
- vbic.i32 d10,#0xfc000000
-
- vshrn.u64 d30,q9,#26
- vmovn.i64 d18,q9
- vshr.u64 q4,q6,#26
- vmovn.i64 d12,q6
- vadd.i64 q7,q7,q4 @ h1 -> h2
- vbic.i32 d18,#0xfc000000
- vbic.i32 d12,#0xfc000000
-
- vadd.i32 d10,d10,d30
- vshl.u32 d30,d30,#2
- vshrn.u64 d8,q7,#26
- vmovn.i64 d14,q7
- vadd.i32 d10,d10,d30 @ h4 -> h0
- vadd.i32 d16,d16,d8 @ h2 -> h3
- vbic.i32 d14,#0xfc000000
-
- vshr.u32 d30,d10,#26
- vbic.i32 d10,#0xfc000000
- vshr.u32 d8,d16,#26
- vbic.i32 d16,#0xfc000000
- vadd.i32 d12,d12,d30 @ h0 -> h1
- vadd.i32 d18,d18,d8 @ h3 -> h4
-
- subs r5,r5,#1
- beq .Lsquare_break_neon
-
- add r6,r0,#(48+0*9*4)
- add r7,r0,#(48+1*9*4)
-
- vtrn.32 d0,d10 @ r^2:r^1
- vtrn.32 d3,d14
- vtrn.32 d5,d16
- vtrn.32 d1,d12
- vtrn.32 d7,d18
-
- vshl.u32 d4,d3,#2 @ *5
- vshl.u32 d6,d5,#2
- vshl.u32 d2,d1,#2
- vshl.u32 d8,d7,#2
- vadd.i32 d4,d4,d3
- vadd.i32 d2,d2,d1
- vadd.i32 d6,d6,d5
- vadd.i32 d8,d8,d7
-
- vst4.32 {d0[0],d1[0],d2[0],d3[0]},[r6]!
- vst4.32 {d0[1],d1[1],d2[1],d3[1]},[r7]!
- vst4.32 {d4[0],d5[0],d6[0],d7[0]},[r6]!
- vst4.32 {d4[1],d5[1],d6[1],d7[1]},[r7]!
- vst1.32 {d8[0]},[r6,:32]
- vst1.32 {d8[1]},[r7,:32]
-
- b .Lsquare_neon
-
-.align 4
-.Lsquare_break_neon:
- add r6,r0,#(48+2*4*9)
- add r7,r0,#(48+3*4*9)
-
- vmov d0,d10 @ r^4:r^3
- vshl.u32 d2,d12,#2 @ *5
- vmov d1,d12
- vshl.u32 d4,d14,#2
- vmov d3,d14
- vshl.u32 d6,d16,#2
- vmov d5,d16
- vshl.u32 d8,d18,#2
- vmov d7,d18
- vadd.i32 d2,d2,d12
- vadd.i32 d4,d4,d14
- vadd.i32 d6,d6,d16
- vadd.i32 d8,d8,d18
-
- vst4.32 {d0[0],d1[0],d2[0],d3[0]},[r6]!
- vst4.32 {d0[1],d1[1],d2[1],d3[1]},[r7]!
- vst4.32 {d4[0],d5[0],d6[0],d7[0]},[r6]!
- vst4.32 {d4[1],d5[1],d6[1],d7[1]},[r7]!
- vst1.32 {d8[0]},[r6]
- vst1.32 {d8[1]},[r7]
-
-.Lno_init_neon:
- bx lr @ bx lr
-.size poly1305_init_neon,.-poly1305_init_neon
-
-.type poly1305_blocks_neon,%function
-.align 5
-poly1305_blocks_neon:
-.Lpoly1305_blocks_neon:
- ldr ip,[r0,#36] @ is_base2_26
-
- cmp r2,#64
- blo .Lpoly1305_blocks
-
- stmdb sp!,{r4-r7}
- vstmdb sp!,{d8-d15} @ ABI specification says so
-
- tst ip,ip @ is_base2_26?
- bne .Lbase2_26_neon
-
- stmdb sp!,{r1-r3,lr}
- bl .Lpoly1305_init_neon
-
- ldr r4,[r0,#0] @ load hash value base 2^32
- ldr r5,[r0,#4]
- ldr r6,[r0,#8]
- ldr r7,[r0,#12]
- ldr ip,[r0,#16]
-
- and r2,r4,#0x03ffffff @ base 2^32 -> base 2^26
- mov r3,r4,lsr#26
- veor d10,d10,d10
- mov r4,r5,lsr#20
- orr r3,r3,r5,lsl#6
- veor d12,d12,d12
- mov r5,r6,lsr#14
- orr r4,r4,r6,lsl#12
- veor d14,d14,d14
- mov r6,r7,lsr#8
- orr r5,r5,r7,lsl#18
- veor d16,d16,d16
- and r3,r3,#0x03ffffff
- orr r6,r6,ip,lsl#24
- veor d18,d18,d18
- and r4,r4,#0x03ffffff
- mov r1,#1
- and r5,r5,#0x03ffffff
- str r1,[r0,#36] @ set is_base2_26
-
- vmov.32 d10[0],r2
- vmov.32 d12[0],r3
- vmov.32 d14[0],r4
- vmov.32 d16[0],r5
- vmov.32 d18[0],r6
- adr r5,.Lzeros
-
- ldmia sp!,{r1-r3,lr}
- b .Lhash_loaded
-
-.align 4
-.Lbase2_26_neon:
- @@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@
- @ load hash value
-
- veor d10,d10,d10
- veor d12,d12,d12
- veor d14,d14,d14
- veor d16,d16,d16
- veor d18,d18,d18
- vld4.32 {d10[0],d12[0],d14[0],d16[0]},[r0]!
- adr r5,.Lzeros
- vld1.32 {d18[0]},[r0]
- sub r0,r0,#16 @ rewind
-
-.Lhash_loaded:
- add r4,r1,#32
- mov r3,r3,lsl#24
- tst r2,#31
- beq .Leven
-
- vld4.32 {d20[0],d22[0],d24[0],d26[0]},[r1]!
- vmov.32 d28[0],r3
- sub r2,r2,#16
- add r4,r1,#32
-
-# ifdef __ARMEB__
- vrev32.8 q10,q10
- vrev32.8 q13,q13
- vrev32.8 q11,q11
- vrev32.8 q12,q12
-# endif
- vsri.u32 d28,d26,#8 @ base 2^32 -> base 2^26
- vshl.u32 d26,d26,#18
-
- vsri.u32 d26,d24,#14
- vshl.u32 d24,d24,#12
- vadd.i32 d29,d28,d18 @ add hash value and move to #hi
-
- vbic.i32 d26,#0xfc000000
- vsri.u32 d24,d22,#20
- vshl.u32 d22,d22,#6
-
- vbic.i32 d24,#0xfc000000
- vsri.u32 d22,d20,#26
- vadd.i32 d27,d26,d16
-
- vbic.i32 d20,#0xfc000000
- vbic.i32 d22,#0xfc000000
- vadd.i32 d25,d24,d14
-
- vadd.i32 d21,d20,d10
- vadd.i32 d23,d22,d12
-
- mov r7,r5
- add r6,r0,#48
-
- cmp r2,r2
- b .Long_tail
-
-.align 4
-.Leven:
- subs r2,r2,#64
- it lo
- movlo r4,r5
-
- vmov.i32 q14,#1<<24 @ padbit, yes, always
- vld4.32 {d20,d22,d24,d26},[r1] @ inp[0:1]
- add r1,r1,#64
- vld4.32 {d21,d23,d25,d27},[r4] @ inp[2:3] (or 0)
- add r4,r4,#64
- itt hi
- addhi r7,r0,#(48+1*9*4)
- addhi r6,r0,#(48+3*9*4)
-
-# ifdef __ARMEB__
- vrev32.8 q10,q10
- vrev32.8 q13,q13
- vrev32.8 q11,q11
- vrev32.8 q12,q12
-# endif
- vsri.u32 q14,q13,#8 @ base 2^32 -> base 2^26
- vshl.u32 q13,q13,#18
-
- vsri.u32 q13,q12,#14
- vshl.u32 q12,q12,#12
-
- vbic.i32 q13,#0xfc000000
- vsri.u32 q12,q11,#20
- vshl.u32 q11,q11,#6
-
- vbic.i32 q12,#0xfc000000
- vsri.u32 q11,q10,#26
-
- vbic.i32 q10,#0xfc000000
- vbic.i32 q11,#0xfc000000
-
- bls .Lskip_loop
-
- vld4.32 {d0[1],d1[1],d2[1],d3[1]},[r7]! @ load r^2
- vld4.32 {d0[0],d1[0],d2[0],d3[0]},[r6]! @ load r^4
- vld4.32 {d4[1],d5[1],d6[1],d7[1]},[r7]!
- vld4.32 {d4[0],d5[0],d6[0],d7[0]},[r6]!
- b .Loop_neon
-
-.align 5
-.Loop_neon:
- @@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@
- @ ((inp[0]*r^4+inp[2]*r^2+inp[4])*r^4+inp[6]*r^2
- @ ((inp[1]*r^4+inp[3]*r^2+inp[5])*r^3+inp[7]*r
- @ ___________________/
- @ ((inp[0]*r^4+inp[2]*r^2+inp[4])*r^4+inp[6]*r^2+inp[8])*r^2
- @ ((inp[1]*r^4+inp[3]*r^2+inp[5])*r^4+inp[7]*r^2+inp[9])*r
- @ ___________________/ ____________________/
- @
- @ Note that we start with inp[2:3]*r^2. This is because it
- @ doesn't depend on reduction in previous iteration.
- @@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@
- @ d4 = h4*r0 + h3*r1 + h2*r2 + h1*r3 + h0*r4
- @ d3 = h3*r0 + h2*r1 + h1*r2 + h0*r3 + h4*5*r4
- @ d2 = h2*r0 + h1*r1 + h0*r2 + h4*5*r3 + h3*5*r4
- @ d1 = h1*r0 + h0*r1 + h4*5*r2 + h3*5*r3 + h2*5*r4
- @ d0 = h0*r0 + h4*5*r1 + h3*5*r2 + h2*5*r3 + h1*5*r4
-
- @@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@
- @ inp[2:3]*r^2
-
- vadd.i32 d24,d24,d14 @ accumulate inp[0:1]
- vmull.u32 q7,d25,d0[1]
- vadd.i32 d20,d20,d10
- vmull.u32 q5,d21,d0[1]
- vadd.i32 d26,d26,d16
- vmull.u32 q8,d27,d0[1]
- vmlal.u32 q7,d23,d1[1]
- vadd.i32 d22,d22,d12
- vmull.u32 q6,d23,d0[1]
-
- vadd.i32 d28,d28,d18
- vmull.u32 q9,d29,d0[1]
- subs r2,r2,#64
- vmlal.u32 q5,d29,d2[1]
- it lo
- movlo r4,r5
- vmlal.u32 q8,d25,d1[1]
- vld1.32 d8[1],[r7,:32]
- vmlal.u32 q6,d21,d1[1]
- vmlal.u32 q9,d27,d1[1]
-
- vmlal.u32 q5,d27,d4[1]
- vmlal.u32 q8,d23,d3[1]
- vmlal.u32 q9,d25,d3[1]
- vmlal.u32 q6,d29,d4[1]
- vmlal.u32 q7,d21,d3[1]
-
- vmlal.u32 q8,d21,d5[1]
- vmlal.u32 q5,d25,d6[1]
- vmlal.u32 q9,d23,d5[1]
- vmlal.u32 q6,d27,d6[1]
- vmlal.u32 q7,d29,d6[1]
-
- vmlal.u32 q8,d29,d8[1]
- vmlal.u32 q5,d23,d8[1]
- vmlal.u32 q9,d21,d7[1]
- vmlal.u32 q6,d25,d8[1]
- vmlal.u32 q7,d27,d8[1]
-
- vld4.32 {d21,d23,d25,d27},[r4] @ inp[2:3] (or 0)
- add r4,r4,#64
-
- @@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@
- @ (hash+inp[0:1])*r^4 and accumulate
-
- vmlal.u32 q8,d26,d0[0]
- vmlal.u32 q5,d20,d0[0]
- vmlal.u32 q9,d28,d0[0]
- vmlal.u32 q6,d22,d0[0]
- vmlal.u32 q7,d24,d0[0]
- vld1.32 d8[0],[r6,:32]
-
- vmlal.u32 q8,d24,d1[0]
- vmlal.u32 q5,d28,d2[0]
- vmlal.u32 q9,d26,d1[0]
- vmlal.u32 q6,d20,d1[0]
- vmlal.u32 q7,d22,d1[0]
-
- vmlal.u32 q8,d22,d3[0]
- vmlal.u32 q5,d26,d4[0]
- vmlal.u32 q9,d24,d3[0]
- vmlal.u32 q6,d28,d4[0]
- vmlal.u32 q7,d20,d3[0]
-
- vmlal.u32 q8,d20,d5[0]
- vmlal.u32 q5,d24,d6[0]
- vmlal.u32 q9,d22,d5[0]
- vmlal.u32 q6,d26,d6[0]
- vmlal.u32 q8,d28,d8[0]
-
- vmlal.u32 q7,d28,d6[0]
- vmlal.u32 q5,d22,d8[0]
- vmlal.u32 q9,d20,d7[0]
- vmov.i32 q14,#1<<24 @ padbit, yes, always
- vmlal.u32 q6,d24,d8[0]
- vmlal.u32 q7,d26,d8[0]
-
- vld4.32 {d20,d22,d24,d26},[r1] @ inp[0:1]
- add r1,r1,#64
-# ifdef __ARMEB__
- vrev32.8 q10,q10
- vrev32.8 q11,q11
- vrev32.8 q12,q12
- vrev32.8 q13,q13
-# endif
-
- @@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@
- @ lazy reduction interleaved with base 2^32 -> base 2^26 of
- @ inp[0:3] previously loaded to q10-q13 and smashed to q10-q14.
-
- vshr.u64 q15,q8,#26
- vmovn.i64 d16,q8
- vshr.u64 q4,q5,#26
- vmovn.i64 d10,q5
- vadd.i64 q9,q9,q15 @ h3 -> h4
- vbic.i32 d16,#0xfc000000
- vsri.u32 q14,q13,#8 @ base 2^32 -> base 2^26
- vadd.i64 q6,q6,q4 @ h0 -> h1
- vshl.u32 q13,q13,#18
- vbic.i32 d10,#0xfc000000
-
- vshrn.u64 d30,q9,#26
- vmovn.i64 d18,q9
- vshr.u64 q4,q6,#26
- vmovn.i64 d12,q6
- vadd.i64 q7,q7,q4 @ h1 -> h2
- vsri.u32 q13,q12,#14
- vbic.i32 d18,#0xfc000000
- vshl.u32 q12,q12,#12
- vbic.i32 d12,#0xfc000000
-
- vadd.i32 d10,d10,d30
- vshl.u32 d30,d30,#2
- vbic.i32 q13,#0xfc000000
- vshrn.u64 d8,q7,#26
- vmovn.i64 d14,q7
- vaddl.u32 q5,d10,d30 @ h4 -> h0 [widen for a sec]
- vsri.u32 q12,q11,#20
- vadd.i32 d16,d16,d8 @ h2 -> h3
- vshl.u32 q11,q11,#6
- vbic.i32 d14,#0xfc000000
- vbic.i32 q12,#0xfc000000
-
- vshrn.u64 d30,q5,#26 @ re-narrow
- vmovn.i64 d10,q5
- vsri.u32 q11,q10,#26
- vbic.i32 q10,#0xfc000000
- vshr.u32 d8,d16,#26
- vbic.i32 d16,#0xfc000000
- vbic.i32 d10,#0xfc000000
- vadd.i32 d12,d12,d30 @ h0 -> h1
- vadd.i32 d18,d18,d8 @ h3 -> h4
- vbic.i32 q11,#0xfc000000
-
- bhi .Loop_neon
-
-.Lskip_loop:
- @@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@
- @ multiply (inp[0:1]+hash) or inp[2:3] by r^2:r^1
-
- add r7,r0,#(48+0*9*4)
- add r6,r0,#(48+1*9*4)
- adds r2,r2,#32
- it ne
- movne r2,#0
- bne .Long_tail
-
- vadd.i32 d25,d24,d14 @ add hash value and move to #hi
- vadd.i32 d21,d20,d10
- vadd.i32 d27,d26,d16
- vadd.i32 d23,d22,d12
- vadd.i32 d29,d28,d18
-
-.Long_tail:
- vld4.32 {d0[1],d1[1],d2[1],d3[1]},[r7]! @ load r^1
- vld4.32 {d0[0],d1[0],d2[0],d3[0]},[r6]! @ load r^2
-
- vadd.i32 d24,d24,d14 @ can be redundant
- vmull.u32 q7,d25,d0
- vadd.i32 d20,d20,d10
- vmull.u32 q5,d21,d0
- vadd.i32 d26,d26,d16
- vmull.u32 q8,d27,d0
- vadd.i32 d22,d22,d12
- vmull.u32 q6,d23,d0
- vadd.i32 d28,d28,d18
- vmull.u32 q9,d29,d0
-
- vmlal.u32 q5,d29,d2
- vld4.32 {d4[1],d5[1],d6[1],d7[1]},[r7]!
- vmlal.u32 q8,d25,d1
- vld4.32 {d4[0],d5[0],d6[0],d7[0]},[r6]!
- vmlal.u32 q6,d21,d1
- vmlal.u32 q9,d27,d1
- vmlal.u32 q7,d23,d1
-
- vmlal.u32 q8,d23,d3
- vld1.32 d8[1],[r7,:32]
- vmlal.u32 q5,d27,d4
- vld1.32 d8[0],[r6,:32]
- vmlal.u32 q9,d25,d3
- vmlal.u32 q6,d29,d4
- vmlal.u32 q7,d21,d3
-
- vmlal.u32 q8,d21,d5
- it ne
- addne r7,r0,#(48+2*9*4)
- vmlal.u32 q5,d25,d6
- it ne
- addne r6,r0,#(48+3*9*4)
- vmlal.u32 q9,d23,d5
- vmlal.u32 q6,d27,d6
- vmlal.u32 q7,d29,d6
-
- vmlal.u32 q8,d29,d8
- vorn q0,q0,q0 @ all-ones, can be redundant
- vmlal.u32 q5,d23,d8
- vshr.u64 q0,q0,#38
- vmlal.u32 q9,d21,d7
- vmlal.u32 q6,d25,d8
- vmlal.u32 q7,d27,d8
-
- beq .Lshort_tail
-
- @@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@
- @ (hash+inp[0:1])*r^4:r^3 and accumulate
-
- vld4.32 {d0[1],d1[1],d2[1],d3[1]},[r7]! @ load r^3
- vld4.32 {d0[0],d1[0],d2[0],d3[0]},[r6]! @ load r^4
-
- vmlal.u32 q7,d24,d0
- vmlal.u32 q5,d20,d0
- vmlal.u32 q8,d26,d0
- vmlal.u32 q6,d22,d0
- vmlal.u32 q9,d28,d0
-
- vmlal.u32 q5,d28,d2
- vld4.32 {d4[1],d5[1],d6[1],d7[1]},[r7]!
- vmlal.u32 q8,d24,d1
- vld4.32 {d4[0],d5[0],d6[0],d7[0]},[r6]!
- vmlal.u32 q6,d20,d1
- vmlal.u32 q9,d26,d1
- vmlal.u32 q7,d22,d1
-
- vmlal.u32 q8,d22,d3
- vld1.32 d8[1],[r7,:32]
- vmlal.u32 q5,d26,d4
- vld1.32 d8[0],[r6,:32]
- vmlal.u32 q9,d24,d3
- vmlal.u32 q6,d28,d4
- vmlal.u32 q7,d20,d3
-
- vmlal.u32 q8,d20,d5
- vmlal.u32 q5,d24,d6
- vmlal.u32 q9,d22,d5
- vmlal.u32 q6,d26,d6
- vmlal.u32 q7,d28,d6
-
- vmlal.u32 q8,d28,d8
- vorn q0,q0,q0 @ all-ones
- vmlal.u32 q5,d22,d8
- vshr.u64 q0,q0,#38
- vmlal.u32 q9,d20,d7
- vmlal.u32 q6,d24,d8
- vmlal.u32 q7,d26,d8
-
-.Lshort_tail:
- @@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@
- @ horizontal addition
-
- vadd.i64 d16,d16,d17
- vadd.i64 d10,d10,d11
- vadd.i64 d18,d18,d19
- vadd.i64 d12,d12,d13
- vadd.i64 d14,d14,d15
-
- @@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@
- @ lazy reduction, but without narrowing
-
- vshr.u64 q15,q8,#26
- vand.i64 q8,q8,q0
- vshr.u64 q4,q5,#26
- vand.i64 q5,q5,q0
- vadd.i64 q9,q9,q15 @ h3 -> h4
- vadd.i64 q6,q6,q4 @ h0 -> h1
-
- vshr.u64 q15,q9,#26
- vand.i64 q9,q9,q0
- vshr.u64 q4,q6,#26
- vand.i64 q6,q6,q0
- vadd.i64 q7,q7,q4 @ h1 -> h2
-
- vadd.i64 q5,q5,q15
- vshl.u64 q15,q15,#2
- vshr.u64 q4,q7,#26
- vand.i64 q7,q7,q0
- vadd.i64 q5,q5,q15 @ h4 -> h0
- vadd.i64 q8,q8,q4 @ h2 -> h3
-
- vshr.u64 q15,q5,#26
- vand.i64 q5,q5,q0
- vshr.u64 q4,q8,#26
- vand.i64 q8,q8,q0
- vadd.i64 q6,q6,q15 @ h0 -> h1
- vadd.i64 q9,q9,q4 @ h3 -> h4
-
- cmp r2,#0
- bne .Leven
-
- @@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@
- @ store hash value
-
- vst4.32 {d10[0],d12[0],d14[0],d16[0]},[r0]!
- vst1.32 {d18[0]},[r0]
-
- vldmia sp!,{d8-d15} @ epilogue
- ldmia sp!,{r4-r7}
- bx lr @ bx lr
-.size poly1305_blocks_neon,.-poly1305_blocks_neon
-
-.align 5
-.Lzeros:
-.long 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0
-#ifndef __KERNEL__
-.LOPENSSL_armcap:
-# ifdef _WIN32
-.word OPENSSL_armcap_P
-# else
-.word OPENSSL_armcap_P-.Lpoly1305_init
-# endif
-.comm OPENSSL_armcap_P,4,4
-.hidden OPENSSL_armcap_P
-#endif
-#endif
-.asciz "Poly1305 for ARMv4/NEON, CRYPTOGAMS by @dot-asm"
-.align 2
diff --git a/arch/arm/crypto/sha256-core.S_shipped b/arch/arm/crypto/sha256-core.S_shipped
deleted file mode 100644
index 6363014a50d7..000000000000
--- a/arch/arm/crypto/sha256-core.S_shipped
+++ /dev/null
@@ -1,2816 +0,0 @@
-@ SPDX-License-Identifier: GPL-2.0
-
-@ This code is taken from the OpenSSL project but the author (Andy Polyakov)
-@ has relicensed it under the GPLv2. Therefore this program is free software;
-@ you can redistribute it and/or modify it under the terms of the GNU General
-@ Public License version 2 as published by the Free Software Foundation.
-@
-@ The original headers, including the original license headers, are
-@ included below for completeness.
-
-@ ====================================================================
-@ Written by Andy Polyakov <appro@xxxxxxxxxxx> 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 https://www.openssl.org/~appro/cryptogams/.
-@ ====================================================================
-
-@ SHA256 block procedure for ARMv4. May 2007.
-
-@ Performance is ~2x better than gcc 3.4 generated code and in "abso-
-@ lute" terms is ~2250 cycles per 64-byte block or ~35 cycles per
-@ byte [on single-issue Xscale PXA250 core].
-
-@ July 2010.
-@
-@ Rescheduling for dual-issue pipeline resulted in 22% improvement on
-@ Cortex A8 core and ~20 cycles per processed byte.
-
-@ February 2011.
-@
-@ Profiler-assisted and platform-specific optimization resulted in 16%
-@ improvement on Cortex A8 core and ~15.4 cycles per processed byte.
-
-@ September 2013.
-@
-@ Add NEON implementation. On Cortex A8 it was measured to process one
-@ byte in 12.5 cycles or 23% faster than integer-only code. Snapdragon
-@ S4 does it in 12.5 cycles too, but it's 50% faster than integer-only
-@ code (meaning that latter performs sub-optimally, nothing was done
-@ about it).
-
-@ May 2014.
-@
-@ Add ARMv8 code path performing at 2.0 cpb on Apple A7.
-
-#ifndef __KERNEL__
-# include "arm_arch.h"
-#else
-# define __ARM_ARCH__ __LINUX_ARM_ARCH__
-# define __ARM_MAX_ARCH__ 7
-#endif
-
-.text
-#if __ARM_ARCH__<7
-.code 32
-#else
-.syntax unified
-# ifdef __thumb2__
-.thumb
-# else
-.code 32
-# endif
-#endif
-
-.type K256,%object
-.align 5
-K256:
-.word 0x428a2f98,0x71374491,0xb5c0fbcf,0xe9b5dba5
-.word 0x3956c25b,0x59f111f1,0x923f82a4,0xab1c5ed5
-.word 0xd807aa98,0x12835b01,0x243185be,0x550c7dc3
-.word 0x72be5d74,0x80deb1fe,0x9bdc06a7,0xc19bf174
-.word 0xe49b69c1,0xefbe4786,0x0fc19dc6,0x240ca1cc
-.word 0x2de92c6f,0x4a7484aa,0x5cb0a9dc,0x76f988da
-.word 0x983e5152,0xa831c66d,0xb00327c8,0xbf597fc7
-.word 0xc6e00bf3,0xd5a79147,0x06ca6351,0x14292967
-.word 0x27b70a85,0x2e1b2138,0x4d2c6dfc,0x53380d13
-.word 0x650a7354,0x766a0abb,0x81c2c92e,0x92722c85
-.word 0xa2bfe8a1,0xa81a664b,0xc24b8b70,0xc76c51a3
-.word 0xd192e819,0xd6990624,0xf40e3585,0x106aa070
-.word 0x19a4c116,0x1e376c08,0x2748774c,0x34b0bcb5
-.word 0x391c0cb3,0x4ed8aa4a,0x5b9cca4f,0x682e6ff3
-.word 0x748f82ee,0x78a5636f,0x84c87814,0x8cc70208
-.word 0x90befffa,0xa4506ceb,0xbef9a3f7,0xc67178f2
-.size K256,.-K256
-.word 0 @ terminator
-#if __ARM_MAX_ARCH__>=7 && !defined(__KERNEL__)
-.LOPENSSL_armcap:
-.word OPENSSL_armcap_P-sha256_block_data_order
-#endif
-.align 5
-
-.global sha256_block_data_order
-.type sha256_block_data_order,%function
-sha256_block_data_order:
-.Lsha256_block_data_order:
-#if __ARM_ARCH__<7
- sub r3,pc,#8 @ sha256_block_data_order
-#else
- adr r3,.Lsha256_block_data_order
-#endif
-#if __ARM_MAX_ARCH__>=7 && !defined(__KERNEL__)
- ldr r12,.LOPENSSL_armcap
- ldr r12,[r3,r12] @ OPENSSL_armcap_P
- tst r12,#ARMV8_SHA256
- bne .LARMv8
- tst r12,#ARMV7_NEON
- bne .LNEON
-#endif
- add r2,r1,r2,lsl#6 @ len to point at the end of inp
- stmdb sp!,{r0,r1,r2,r4-r11,lr}
- ldmia r0,{r4,r5,r6,r7,r8,r9,r10,r11}
- sub r14,r3,#256+32 @ K256
- sub sp,sp,#16*4 @ alloca(X[16])
-.Loop:
-# if __ARM_ARCH__>=7
- ldr r2,[r1],#4
-# else
- ldrb r2,[r1,#3]
-# endif
- eor r3,r5,r6 @ magic
- eor r12,r12,r12
-#if __ARM_ARCH__>=7
- @ ldr r2,[r1],#4 @ 0
-# if 0==15
- str r1,[sp,#17*4] @ make room for r1
-# endif
- eor r0,r8,r8,ror#5
- add r4,r4,r12 @ h+=Maj(a,b,c) from the past
- eor r0,r0,r8,ror#19 @ Sigma1(e)
-# ifndef __ARMEB__
- rev r2,r2
-# endif
-#else
- @ ldrb r2,[r1,#3] @ 0
- add r4,r4,r12 @ h+=Maj(a,b,c) from the past
- ldrb r12,[r1,#2]
- ldrb r0,[r1,#1]
- orr r2,r2,r12,lsl#8
- ldrb r12,[r1],#4
- orr r2,r2,r0,lsl#16
-# if 0==15
- str r1,[sp,#17*4] @ make room for r1
-# endif
- eor r0,r8,r8,ror#5
- orr r2,r2,r12,lsl#24
- eor r0,r0,r8,ror#19 @ Sigma1(e)
-#endif
- ldr r12,[r14],#4 @ *K256++
- add r11,r11,r2 @ h+=X[i]
- str r2,[sp,#0*4]
- eor r2,r9,r10
- add r11,r11,r0,ror#6 @ h+=Sigma1(e)
- and r2,r2,r8
- add r11,r11,r12 @ h+=K256[i]
- eor r2,r2,r10 @ Ch(e,f,g)
- eor r0,r4,r4,ror#11
- add r11,r11,r2 @ h+=Ch(e,f,g)
-#if 0==31
- and r12,r12,#0xff
- cmp r12,#0xf2 @ done?
-#endif
-#if 0<15
-# if __ARM_ARCH__>=7
- ldr r2,[r1],#4 @ prefetch
-# else
- ldrb r2,[r1,#3]
-# endif
- eor r12,r4,r5 @ a^b, b^c in next round
-#else
- ldr r2,[sp,#2*4] @ from future BODY_16_xx
- eor r12,r4,r5 @ a^b, b^c in next round
- ldr r1,[sp,#15*4] @ from future BODY_16_xx
-#endif
- eor r0,r0,r4,ror#20 @ Sigma0(a)
- and r3,r3,r12 @ (b^c)&=(a^b)
- add r7,r7,r11 @ d+=h
- eor r3,r3,r5 @ Maj(a,b,c)
- add r11,r11,r0,ror#2 @ h+=Sigma0(a)
- @ add r11,r11,r3 @ h+=Maj(a,b,c)
-#if __ARM_ARCH__>=7
- @ ldr r2,[r1],#4 @ 1
-# if 1==15
- str r1,[sp,#17*4] @ make room for r1
-# endif
- eor r0,r7,r7,ror#5
- add r11,r11,r3 @ h+=Maj(a,b,c) from the past
- eor r0,r0,r7,ror#19 @ Sigma1(e)
-# ifndef __ARMEB__
- rev r2,r2
-# endif
-#else
- @ ldrb r2,[r1,#3] @ 1
- add r11,r11,r3 @ h+=Maj(a,b,c) from the past
- ldrb r3,[r1,#2]
- ldrb r0,[r1,#1]
- orr r2,r2,r3,lsl#8
- ldrb r3,[r1],#4
- orr r2,r2,r0,lsl#16
-# if 1==15
- str r1,[sp,#17*4] @ make room for r1
-# endif
- eor r0,r7,r7,ror#5
- orr r2,r2,r3,lsl#24
- eor r0,r0,r7,ror#19 @ Sigma1(e)
-#endif
- ldr r3,[r14],#4 @ *K256++
- add r10,r10,r2 @ h+=X[i]
- str r2,[sp,#1*4]
- eor r2,r8,r9
- add r10,r10,r0,ror#6 @ h+=Sigma1(e)
- and r2,r2,r7
- add r10,r10,r3 @ h+=K256[i]
- eor r2,r2,r9 @ Ch(e,f,g)
- eor r0,r11,r11,ror#11
- add r10,r10,r2 @ h+=Ch(e,f,g)
-#if 1==31
- and r3,r3,#0xff
- cmp r3,#0xf2 @ done?
-#endif
-#if 1<15
-# if __ARM_ARCH__>=7
- ldr r2,[r1],#4 @ prefetch
-# else
- ldrb r2,[r1,#3]
-# endif
- eor r3,r11,r4 @ a^b, b^c in next round
-#else
- ldr r2,[sp,#3*4] @ from future BODY_16_xx
- eor r3,r11,r4 @ a^b, b^c in next round
- ldr r1,[sp,#0*4] @ from future BODY_16_xx
-#endif
- eor r0,r0,r11,ror#20 @ Sigma0(a)
- and r12,r12,r3 @ (b^c)&=(a^b)
- add r6,r6,r10 @ d+=h
- eor r12,r12,r4 @ Maj(a,b,c)
- add r10,r10,r0,ror#2 @ h+=Sigma0(a)
- @ add r10,r10,r12 @ h+=Maj(a,b,c)
-#if __ARM_ARCH__>=7
- @ ldr r2,[r1],#4 @ 2
-# if 2==15
- str r1,[sp,#17*4] @ make room for r1
-# endif
- eor r0,r6,r6,ror#5
- add r10,r10,r12 @ h+=Maj(a,b,c) from the past
- eor r0,r0,r6,ror#19 @ Sigma1(e)
-# ifndef __ARMEB__
- rev r2,r2
-# endif
-#else
- @ ldrb r2,[r1,#3] @ 2
- add r10,r10,r12 @ h+=Maj(a,b,c) from the past
- ldrb r12,[r1,#2]
- ldrb r0,[r1,#1]
- orr r2,r2,r12,lsl#8
- ldrb r12,[r1],#4
- orr r2,r2,r0,lsl#16
-# if 2==15
- str r1,[sp,#17*4] @ make room for r1
-# endif
- eor r0,r6,r6,ror#5
- orr r2,r2,r12,lsl#24
- eor r0,r0,r6,ror#19 @ Sigma1(e)
-#endif
- ldr r12,[r14],#4 @ *K256++
- add r9,r9,r2 @ h+=X[i]
- str r2,[sp,#2*4]
- eor r2,r7,r8
- add r9,r9,r0,ror#6 @ h+=Sigma1(e)
- and r2,r2,r6
- add r9,r9,r12 @ h+=K256[i]
- eor r2,r2,r8 @ Ch(e,f,g)
- eor r0,r10,r10,ror#11
- add r9,r9,r2 @ h+=Ch(e,f,g)
-#if 2==31
- and r12,r12,#0xff
- cmp r12,#0xf2 @ done?
-#endif
-#if 2<15
-# if __ARM_ARCH__>=7
- ldr r2,[r1],#4 @ prefetch
-# else
- ldrb r2,[r1,#3]
-# endif
- eor r12,r10,r11 @ a^b, b^c in next round
-#else
- ldr r2,[sp,#4*4] @ from future BODY_16_xx
- eor r12,r10,r11 @ a^b, b^c in next round
- ldr r1,[sp,#1*4] @ from future BODY_16_xx
-#endif
- eor r0,r0,r10,ror#20 @ Sigma0(a)
- and r3,r3,r12 @ (b^c)&=(a^b)
- add r5,r5,r9 @ d+=h
- eor r3,r3,r11 @ Maj(a,b,c)
- add r9,r9,r0,ror#2 @ h+=Sigma0(a)
- @ add r9,r9,r3 @ h+=Maj(a,b,c)
-#if __ARM_ARCH__>=7
- @ ldr r2,[r1],#4 @ 3
-# if 3==15
- str r1,[sp,#17*4] @ make room for r1
-# endif
- eor r0,r5,r5,ror#5
- add r9,r9,r3 @ h+=Maj(a,b,c) from the past
- eor r0,r0,r5,ror#19 @ Sigma1(e)
-# ifndef __ARMEB__
- rev r2,r2
-# endif
-#else
- @ ldrb r2,[r1,#3] @ 3
- add r9,r9,r3 @ h+=Maj(a,b,c) from the past
- ldrb r3,[r1,#2]
- ldrb r0,[r1,#1]
- orr r2,r2,r3,lsl#8
- ldrb r3,[r1],#4
- orr r2,r2,r0,lsl#16
-# if 3==15
- str r1,[sp,#17*4] @ make room for r1
-# endif
- eor r0,r5,r5,ror#5
- orr r2,r2,r3,lsl#24
- eor r0,r0,r5,ror#19 @ Sigma1(e)
-#endif
- ldr r3,[r14],#4 @ *K256++
- add r8,r8,r2 @ h+=X[i]
- str r2,[sp,#3*4]
- eor r2,r6,r7
- add r8,r8,r0,ror#6 @ h+=Sigma1(e)
- and r2,r2,r5
- add r8,r8,r3 @ h+=K256[i]
- eor r2,r2,r7 @ Ch(e,f,g)
- eor r0,r9,r9,ror#11
- add r8,r8,r2 @ h+=Ch(e,f,g)
-#if 3==31
- and r3,r3,#0xff
- cmp r3,#0xf2 @ done?
-#endif
-#if 3<15
-# if __ARM_ARCH__>=7
- ldr r2,[r1],#4 @ prefetch
-# else
- ldrb r2,[r1,#3]
-# endif
- eor r3,r9,r10 @ a^b, b^c in next round
-#else
- ldr r2,[sp,#5*4] @ from future BODY_16_xx
- eor r3,r9,r10 @ a^b, b^c in next round
- ldr r1,[sp,#2*4] @ from future BODY_16_xx
-#endif
- eor r0,r0,r9,ror#20 @ Sigma0(a)
- and r12,r12,r3 @ (b^c)&=(a^b)
- add r4,r4,r8 @ d+=h
- eor r12,r12,r10 @ Maj(a,b,c)
- add r8,r8,r0,ror#2 @ h+=Sigma0(a)
- @ add r8,r8,r12 @ h+=Maj(a,b,c)
-#if __ARM_ARCH__>=7
- @ ldr r2,[r1],#4 @ 4
-# if 4==15
- str r1,[sp,#17*4] @ make room for r1
-# endif
- eor r0,r4,r4,ror#5
- add r8,r8,r12 @ h+=Maj(a,b,c) from the past
- eor r0,r0,r4,ror#19 @ Sigma1(e)
-# ifndef __ARMEB__
- rev r2,r2
-# endif
-#else
- @ ldrb r2,[r1,#3] @ 4
- add r8,r8,r12 @ h+=Maj(a,b,c) from the past
- ldrb r12,[r1,#2]
- ldrb r0,[r1,#1]
- orr r2,r2,r12,lsl#8
- ldrb r12,[r1],#4
- orr r2,r2,r0,lsl#16
-# if 4==15
- str r1,[sp,#17*4] @ make room for r1
-# endif
- eor r0,r4,r4,ror#5
- orr r2,r2,r12,lsl#24
- eor r0,r0,r4,ror#19 @ Sigma1(e)
-#endif
- ldr r12,[r14],#4 @ *K256++
- add r7,r7,r2 @ h+=X[i]
- str r2,[sp,#4*4]
- eor r2,r5,r6
- add r7,r7,r0,ror#6 @ h+=Sigma1(e)
- and r2,r2,r4
- add r7,r7,r12 @ h+=K256[i]
- eor r2,r2,r6 @ Ch(e,f,g)
- eor r0,r8,r8,ror#11
- add r7,r7,r2 @ h+=Ch(e,f,g)
-#if 4==31
- and r12,r12,#0xff
- cmp r12,#0xf2 @ done?
-#endif
-#if 4<15
-# if __ARM_ARCH__>=7
- ldr r2,[r1],#4 @ prefetch
-# else
- ldrb r2,[r1,#3]
-# endif
- eor r12,r8,r9 @ a^b, b^c in next round
-#else
- ldr r2,[sp,#6*4] @ from future BODY_16_xx
- eor r12,r8,r9 @ a^b, b^c in next round
- ldr r1,[sp,#3*4] @ from future BODY_16_xx
-#endif
- eor r0,r0,r8,ror#20 @ Sigma0(a)
- and r3,r3,r12 @ (b^c)&=(a^b)
- add r11,r11,r7 @ d+=h
- eor r3,r3,r9 @ Maj(a,b,c)
- add r7,r7,r0,ror#2 @ h+=Sigma0(a)
- @ add r7,r7,r3 @ h+=Maj(a,b,c)
-#if __ARM_ARCH__>=7
- @ ldr r2,[r1],#4 @ 5
-# if 5==15
- str r1,[sp,#17*4] @ make room for r1
-# endif
- eor r0,r11,r11,ror#5
- add r7,r7,r3 @ h+=Maj(a,b,c) from the past
- eor r0,r0,r11,ror#19 @ Sigma1(e)
-# ifndef __ARMEB__
- rev r2,r2
-# endif
-#else
- @ ldrb r2,[r1,#3] @ 5
- add r7,r7,r3 @ h+=Maj(a,b,c) from the past
- ldrb r3,[r1,#2]
- ldrb r0,[r1,#1]
- orr r2,r2,r3,lsl#8
- ldrb r3,[r1],#4
- orr r2,r2,r0,lsl#16
-# if 5==15
- str r1,[sp,#17*4] @ make room for r1
-# endif
- eor r0,r11,r11,ror#5
- orr r2,r2,r3,lsl#24
- eor r0,r0,r11,ror#19 @ Sigma1(e)
-#endif
- ldr r3,[r14],#4 @ *K256++
- add r6,r6,r2 @ h+=X[i]
- str r2,[sp,#5*4]
- eor r2,r4,r5
- add r6,r6,r0,ror#6 @ h+=Sigma1(e)
- and r2,r2,r11
- add r6,r6,r3 @ h+=K256[i]
- eor r2,r2,r5 @ Ch(e,f,g)
- eor r0,r7,r7,ror#11
- add r6,r6,r2 @ h+=Ch(e,f,g)
-#if 5==31
- and r3,r3,#0xff
- cmp r3,#0xf2 @ done?
-#endif
-#if 5<15
-# if __ARM_ARCH__>=7
- ldr r2,[r1],#4 @ prefetch
-# else
- ldrb r2,[r1,#3]
-# endif
- eor r3,r7,r8 @ a^b, b^c in next round
-#else
- ldr r2,[sp,#7*4] @ from future BODY_16_xx
- eor r3,r7,r8 @ a^b, b^c in next round
- ldr r1,[sp,#4*4] @ from future BODY_16_xx
-#endif
- eor r0,r0,r7,ror#20 @ Sigma0(a)
- and r12,r12,r3 @ (b^c)&=(a^b)
- add r10,r10,r6 @ d+=h
- eor r12,r12,r8 @ Maj(a,b,c)
- add r6,r6,r0,ror#2 @ h+=Sigma0(a)
- @ add r6,r6,r12 @ h+=Maj(a,b,c)
-#if __ARM_ARCH__>=7
- @ ldr r2,[r1],#4 @ 6
-# if 6==15
- str r1,[sp,#17*4] @ make room for r1
-# endif
- eor r0,r10,r10,ror#5
- add r6,r6,r12 @ h+=Maj(a,b,c) from the past
- eor r0,r0,r10,ror#19 @ Sigma1(e)
-# ifndef __ARMEB__
- rev r2,r2
-# endif
-#else
- @ ldrb r2,[r1,#3] @ 6
- add r6,r6,r12 @ h+=Maj(a,b,c) from the past
- ldrb r12,[r1,#2]
- ldrb r0,[r1,#1]
- orr r2,r2,r12,lsl#8
- ldrb r12,[r1],#4
- orr r2,r2,r0,lsl#16
-# if 6==15
- str r1,[sp,#17*4] @ make room for r1
-# endif
- eor r0,r10,r10,ror#5
- orr r2,r2,r12,lsl#24
- eor r0,r0,r10,ror#19 @ Sigma1(e)
-#endif
- ldr r12,[r14],#4 @ *K256++
- add r5,r5,r2 @ h+=X[i]
- str r2,[sp,#6*4]
- eor r2,r11,r4
- add r5,r5,r0,ror#6 @ h+=Sigma1(e)
- and r2,r2,r10
- add r5,r5,r12 @ h+=K256[i]
- eor r2,r2,r4 @ Ch(e,f,g)
- eor r0,r6,r6,ror#11
- add r5,r5,r2 @ h+=Ch(e,f,g)
-#if 6==31
- and r12,r12,#0xff
- cmp r12,#0xf2 @ done?
-#endif
-#if 6<15
-# if __ARM_ARCH__>=7
- ldr r2,[r1],#4 @ prefetch
-# else
- ldrb r2,[r1,#3]
-# endif
- eor r12,r6,r7 @ a^b, b^c in next round
-#else
- ldr r2,[sp,#8*4] @ from future BODY_16_xx
- eor r12,r6,r7 @ a^b, b^c in next round
- ldr r1,[sp,#5*4] @ from future BODY_16_xx
-#endif
- eor r0,r0,r6,ror#20 @ Sigma0(a)
- and r3,r3,r12 @ (b^c)&=(a^b)
- add r9,r9,r5 @ d+=h
- eor r3,r3,r7 @ Maj(a,b,c)
- add r5,r5,r0,ror#2 @ h+=Sigma0(a)
- @ add r5,r5,r3 @ h+=Maj(a,b,c)
-#if __ARM_ARCH__>=7
- @ ldr r2,[r1],#4 @ 7
-# if 7==15
- str r1,[sp,#17*4] @ make room for r1
-# endif
- eor r0,r9,r9,ror#5
- add r5,r5,r3 @ h+=Maj(a,b,c) from the past
- eor r0,r0,r9,ror#19 @ Sigma1(e)
-# ifndef __ARMEB__
- rev r2,r2
-# endif
-#else
- @ ldrb r2,[r1,#3] @ 7
- add r5,r5,r3 @ h+=Maj(a,b,c) from the past
- ldrb r3,[r1,#2]
- ldrb r0,[r1,#1]
- orr r2,r2,r3,lsl#8
- ldrb r3,[r1],#4
- orr r2,r2,r0,lsl#16
-# if 7==15
- str r1,[sp,#17*4] @ make room for r1
-# endif
- eor r0,r9,r9,ror#5
- orr r2,r2,r3,lsl#24
- eor r0,r0,r9,ror#19 @ Sigma1(e)
-#endif
- ldr r3,[r14],#4 @ *K256++
- add r4,r4,r2 @ h+=X[i]
- str r2,[sp,#7*4]
- eor r2,r10,r11
- add r4,r4,r0,ror#6 @ h+=Sigma1(e)
- and r2,r2,r9
- add r4,r4,r3 @ h+=K256[i]
- eor r2,r2,r11 @ Ch(e,f,g)
- eor r0,r5,r5,ror#11
- add r4,r4,r2 @ h+=Ch(e,f,g)
-#if 7==31
- and r3,r3,#0xff
- cmp r3,#0xf2 @ done?
-#endif
-#if 7<15
-# if __ARM_ARCH__>=7
- ldr r2,[r1],#4 @ prefetch
-# else
- ldrb r2,[r1,#3]
-# endif
- eor r3,r5,r6 @ a^b, b^c in next round
-#else
- ldr r2,[sp,#9*4] @ from future BODY_16_xx
- eor r3,r5,r6 @ a^b, b^c in next round
- ldr r1,[sp,#6*4] @ from future BODY_16_xx
-#endif
- eor r0,r0,r5,ror#20 @ Sigma0(a)
- and r12,r12,r3 @ (b^c)&=(a^b)
- add r8,r8,r4 @ d+=h
- eor r12,r12,r6 @ Maj(a,b,c)
- add r4,r4,r0,ror#2 @ h+=Sigma0(a)
- @ add r4,r4,r12 @ h+=Maj(a,b,c)
-#if __ARM_ARCH__>=7
- @ ldr r2,[r1],#4 @ 8
-# if 8==15
- str r1,[sp,#17*4] @ make room for r1
-# endif
- eor r0,r8,r8,ror#5
- add r4,r4,r12 @ h+=Maj(a,b,c) from the past
- eor r0,r0,r8,ror#19 @ Sigma1(e)
-# ifndef __ARMEB__
- rev r2,r2
-# endif
-#else
- @ ldrb r2,[r1,#3] @ 8
- add r4,r4,r12 @ h+=Maj(a,b,c) from the past
- ldrb r12,[r1,#2]
- ldrb r0,[r1,#1]
- orr r2,r2,r12,lsl#8
- ldrb r12,[r1],#4
- orr r2,r2,r0,lsl#16
-# if 8==15
- str r1,[sp,#17*4] @ make room for r1
-# endif
- eor r0,r8,r8,ror#5
- orr r2,r2,r12,lsl#24
- eor r0,r0,r8,ror#19 @ Sigma1(e)
-#endif
- ldr r12,[r14],#4 @ *K256++
- add r11,r11,r2 @ h+=X[i]
- str r2,[sp,#8*4]
- eor r2,r9,r10
- add r11,r11,r0,ror#6 @ h+=Sigma1(e)
- and r2,r2,r8
- add r11,r11,r12 @ h+=K256[i]
- eor r2,r2,r10 @ Ch(e,f,g)
- eor r0,r4,r4,ror#11
- add r11,r11,r2 @ h+=Ch(e,f,g)
-#if 8==31
- and r12,r12,#0xff
- cmp r12,#0xf2 @ done?
-#endif
-#if 8<15
-# if __ARM_ARCH__>=7
- ldr r2,[r1],#4 @ prefetch
-# else
- ldrb r2,[r1,#3]
-# endif
- eor r12,r4,r5 @ a^b, b^c in next round
-#else
- ldr r2,[sp,#10*4] @ from future BODY_16_xx
- eor r12,r4,r5 @ a^b, b^c in next round
- ldr r1,[sp,#7*4] @ from future BODY_16_xx
-#endif
- eor r0,r0,r4,ror#20 @ Sigma0(a)
- and r3,r3,r12 @ (b^c)&=(a^b)
- add r7,r7,r11 @ d+=h
- eor r3,r3,r5 @ Maj(a,b,c)
- add r11,r11,r0,ror#2 @ h+=Sigma0(a)
- @ add r11,r11,r3 @ h+=Maj(a,b,c)
-#if __ARM_ARCH__>=7
- @ ldr r2,[r1],#4 @ 9
-# if 9==15
- str r1,[sp,#17*4] @ make room for r1
-# endif
- eor r0,r7,r7,ror#5
- add r11,r11,r3 @ h+=Maj(a,b,c) from the past
- eor r0,r0,r7,ror#19 @ Sigma1(e)
-# ifndef __ARMEB__
- rev r2,r2
-# endif
-#else
- @ ldrb r2,[r1,#3] @ 9
- add r11,r11,r3 @ h+=Maj(a,b,c) from the past
- ldrb r3,[r1,#2]
- ldrb r0,[r1,#1]
- orr r2,r2,r3,lsl#8
- ldrb r3,[r1],#4
- orr r2,r2,r0,lsl#16
-# if 9==15
- str r1,[sp,#17*4] @ make room for r1
-# endif
- eor r0,r7,r7,ror#5
- orr r2,r2,r3,lsl#24
- eor r0,r0,r7,ror#19 @ Sigma1(e)
-#endif
- ldr r3,[r14],#4 @ *K256++
- add r10,r10,r2 @ h+=X[i]
- str r2,[sp,#9*4]
- eor r2,r8,r9
- add r10,r10,r0,ror#6 @ h+=Sigma1(e)
- and r2,r2,r7
- add r10,r10,r3 @ h+=K256[i]
- eor r2,r2,r9 @ Ch(e,f,g)
- eor r0,r11,r11,ror#11
- add r10,r10,r2 @ h+=Ch(e,f,g)
-#if 9==31
- and r3,r3,#0xff
- cmp r3,#0xf2 @ done?
-#endif
-#if 9<15
-# if __ARM_ARCH__>=7
- ldr r2,[r1],#4 @ prefetch
-# else
- ldrb r2,[r1,#3]
-# endif
- eor r3,r11,r4 @ a^b, b^c in next round
-#else
- ldr r2,[sp,#11*4] @ from future BODY_16_xx
- eor r3,r11,r4 @ a^b, b^c in next round
- ldr r1,[sp,#8*4] @ from future BODY_16_xx
-#endif
- eor r0,r0,r11,ror#20 @ Sigma0(a)
- and r12,r12,r3 @ (b^c)&=(a^b)
- add r6,r6,r10 @ d+=h
- eor r12,r12,r4 @ Maj(a,b,c)
- add r10,r10,r0,ror#2 @ h+=Sigma0(a)
- @ add r10,r10,r12 @ h+=Maj(a,b,c)
-#if __ARM_ARCH__>=7
- @ ldr r2,[r1],#4 @ 10
-# if 10==15
- str r1,[sp,#17*4] @ make room for r1
-# endif
- eor r0,r6,r6,ror#5
- add r10,r10,r12 @ h+=Maj(a,b,c) from the past
- eor r0,r0,r6,ror#19 @ Sigma1(e)
-# ifndef __ARMEB__
- rev r2,r2
-# endif
-#else
- @ ldrb r2,[r1,#3] @ 10
- add r10,r10,r12 @ h+=Maj(a,b,c) from the past
- ldrb r12,[r1,#2]
- ldrb r0,[r1,#1]
- orr r2,r2,r12,lsl#8
- ldrb r12,[r1],#4
- orr r2,r2,r0,lsl#16
-# if 10==15
- str r1,[sp,#17*4] @ make room for r1
-# endif
- eor r0,r6,r6,ror#5
- orr r2,r2,r12,lsl#24
- eor r0,r0,r6,ror#19 @ Sigma1(e)
-#endif
- ldr r12,[r14],#4 @ *K256++
- add r9,r9,r2 @ h+=X[i]
- str r2,[sp,#10*4]
- eor r2,r7,r8
- add r9,r9,r0,ror#6 @ h+=Sigma1(e)
- and r2,r2,r6
- add r9,r9,r12 @ h+=K256[i]
- eor r2,r2,r8 @ Ch(e,f,g)
- eor r0,r10,r10,ror#11
- add r9,r9,r2 @ h+=Ch(e,f,g)
-#if 10==31
- and r12,r12,#0xff
- cmp r12,#0xf2 @ done?
-#endif
-#if 10<15
-# if __ARM_ARCH__>=7
- ldr r2,[r1],#4 @ prefetch
-# else
- ldrb r2,[r1,#3]
-# endif
- eor r12,r10,r11 @ a^b, b^c in next round
-#else
- ldr r2,[sp,#12*4] @ from future BODY_16_xx
- eor r12,r10,r11 @ a^b, b^c in next round
- ldr r1,[sp,#9*4] @ from future BODY_16_xx
-#endif
- eor r0,r0,r10,ror#20 @ Sigma0(a)
- and r3,r3,r12 @ (b^c)&=(a^b)
- add r5,r5,r9 @ d+=h
- eor r3,r3,r11 @ Maj(a,b,c)
- add r9,r9,r0,ror#2 @ h+=Sigma0(a)
- @ add r9,r9,r3 @ h+=Maj(a,b,c)
-#if __ARM_ARCH__>=7
- @ ldr r2,[r1],#4 @ 11
-# if 11==15
- str r1,[sp,#17*4] @ make room for r1
-# endif
- eor r0,r5,r5,ror#5
- add r9,r9,r3 @ h+=Maj(a,b,c) from the past
- eor r0,r0,r5,ror#19 @ Sigma1(e)
-# ifndef __ARMEB__
- rev r2,r2
-# endif
-#else
- @ ldrb r2,[r1,#3] @ 11
- add r9,r9,r3 @ h+=Maj(a,b,c) from the past
- ldrb r3,[r1,#2]
- ldrb r0,[r1,#1]
- orr r2,r2,r3,lsl#8
- ldrb r3,[r1],#4
- orr r2,r2,r0,lsl#16
-# if 11==15
- str r1,[sp,#17*4] @ make room for r1
-# endif
- eor r0,r5,r5,ror#5
- orr r2,r2,r3,lsl#24
- eor r0,r0,r5,ror#19 @ Sigma1(e)
-#endif
- ldr r3,[r14],#4 @ *K256++
- add r8,r8,r2 @ h+=X[i]
- str r2,[sp,#11*4]
- eor r2,r6,r7
- add r8,r8,r0,ror#6 @ h+=Sigma1(e)
- and r2,r2,r5
- add r8,r8,r3 @ h+=K256[i]
- eor r2,r2,r7 @ Ch(e,f,g)
- eor r0,r9,r9,ror#11
- add r8,r8,r2 @ h+=Ch(e,f,g)
-#if 11==31
- and r3,r3,#0xff
- cmp r3,#0xf2 @ done?
-#endif
-#if 11<15
-# if __ARM_ARCH__>=7
- ldr r2,[r1],#4 @ prefetch
-# else
- ldrb r2,[r1,#3]
-# endif
- eor r3,r9,r10 @ a^b, b^c in next round
-#else
- ldr r2,[sp,#13*4] @ from future BODY_16_xx
- eor r3,r9,r10 @ a^b, b^c in next round
- ldr r1,[sp,#10*4] @ from future BODY_16_xx
-#endif
- eor r0,r0,r9,ror#20 @ Sigma0(a)
- and r12,r12,r3 @ (b^c)&=(a^b)
- add r4,r4,r8 @ d+=h
- eor r12,r12,r10 @ Maj(a,b,c)
- add r8,r8,r0,ror#2 @ h+=Sigma0(a)
- @ add r8,r8,r12 @ h+=Maj(a,b,c)
-#if __ARM_ARCH__>=7
- @ ldr r2,[r1],#4 @ 12
-# if 12==15
- str r1,[sp,#17*4] @ make room for r1
-# endif
- eor r0,r4,r4,ror#5
- add r8,r8,r12 @ h+=Maj(a,b,c) from the past
- eor r0,r0,r4,ror#19 @ Sigma1(e)
-# ifndef __ARMEB__
- rev r2,r2
-# endif
-#else
- @ ldrb r2,[r1,#3] @ 12
- add r8,r8,r12 @ h+=Maj(a,b,c) from the past
- ldrb r12,[r1,#2]
- ldrb r0,[r1,#1]
- orr r2,r2,r12,lsl#8
- ldrb r12,[r1],#4
- orr r2,r2,r0,lsl#16
-# if 12==15
- str r1,[sp,#17*4] @ make room for r1
-# endif
- eor r0,r4,r4,ror#5
- orr r2,r2,r12,lsl#24
- eor r0,r0,r4,ror#19 @ Sigma1(e)
-#endif
- ldr r12,[r14],#4 @ *K256++
- add r7,r7,r2 @ h+=X[i]
- str r2,[sp,#12*4]
- eor r2,r5,r6
- add r7,r7,r0,ror#6 @ h+=Sigma1(e)
- and r2,r2,r4
- add r7,r7,r12 @ h+=K256[i]
- eor r2,r2,r6 @ Ch(e,f,g)
- eor r0,r8,r8,ror#11
- add r7,r7,r2 @ h+=Ch(e,f,g)
-#if 12==31
- and r12,r12,#0xff
- cmp r12,#0xf2 @ done?
-#endif
-#if 12<15
-# if __ARM_ARCH__>=7
- ldr r2,[r1],#4 @ prefetch
-# else
- ldrb r2,[r1,#3]
-# endif
- eor r12,r8,r9 @ a^b, b^c in next round
-#else
- ldr r2,[sp,#14*4] @ from future BODY_16_xx
- eor r12,r8,r9 @ a^b, b^c in next round
- ldr r1,[sp,#11*4] @ from future BODY_16_xx
-#endif
- eor r0,r0,r8,ror#20 @ Sigma0(a)
- and r3,r3,r12 @ (b^c)&=(a^b)
- add r11,r11,r7 @ d+=h
- eor r3,r3,r9 @ Maj(a,b,c)
- add r7,r7,r0,ror#2 @ h+=Sigma0(a)
- @ add r7,r7,r3 @ h+=Maj(a,b,c)
-#if __ARM_ARCH__>=7
- @ ldr r2,[r1],#4 @ 13
-# if 13==15
- str r1,[sp,#17*4] @ make room for r1
-# endif
- eor r0,r11,r11,ror#5
- add r7,r7,r3 @ h+=Maj(a,b,c) from the past
- eor r0,r0,r11,ror#19 @ Sigma1(e)
-# ifndef __ARMEB__
- rev r2,r2
-# endif
-#else
- @ ldrb r2,[r1,#3] @ 13
- add r7,r7,r3 @ h+=Maj(a,b,c) from the past
- ldrb r3,[r1,#2]
- ldrb r0,[r1,#1]
- orr r2,r2,r3,lsl#8
- ldrb r3,[r1],#4
- orr r2,r2,r0,lsl#16
-# if 13==15
- str r1,[sp,#17*4] @ make room for r1
-# endif
- eor r0,r11,r11,ror#5
- orr r2,r2,r3,lsl#24
- eor r0,r0,r11,ror#19 @ Sigma1(e)
-#endif
- ldr r3,[r14],#4 @ *K256++
- add r6,r6,r2 @ h+=X[i]
- str r2,[sp,#13*4]
- eor r2,r4,r5
- add r6,r6,r0,ror#6 @ h+=Sigma1(e)
- and r2,r2,r11
- add r6,r6,r3 @ h+=K256[i]
- eor r2,r2,r5 @ Ch(e,f,g)
- eor r0,r7,r7,ror#11
- add r6,r6,r2 @ h+=Ch(e,f,g)
-#if 13==31
- and r3,r3,#0xff
- cmp r3,#0xf2 @ done?
-#endif
-#if 13<15
-# if __ARM_ARCH__>=7
- ldr r2,[r1],#4 @ prefetch
-# else
- ldrb r2,[r1,#3]
-# endif
- eor r3,r7,r8 @ a^b, b^c in next round
-#else
- ldr r2,[sp,#15*4] @ from future BODY_16_xx
- eor r3,r7,r8 @ a^b, b^c in next round
- ldr r1,[sp,#12*4] @ from future BODY_16_xx
-#endif
- eor r0,r0,r7,ror#20 @ Sigma0(a)
- and r12,r12,r3 @ (b^c)&=(a^b)
- add r10,r10,r6 @ d+=h
- eor r12,r12,r8 @ Maj(a,b,c)
- add r6,r6,r0,ror#2 @ h+=Sigma0(a)
- @ add r6,r6,r12 @ h+=Maj(a,b,c)
-#if __ARM_ARCH__>=7
- @ ldr r2,[r1],#4 @ 14
-# if 14==15
- str r1,[sp,#17*4] @ make room for r1
-# endif
- eor r0,r10,r10,ror#5
- add r6,r6,r12 @ h+=Maj(a,b,c) from the past
- eor r0,r0,r10,ror#19 @ Sigma1(e)
-# ifndef __ARMEB__
- rev r2,r2
-# endif
-#else
- @ ldrb r2,[r1,#3] @ 14
- add r6,r6,r12 @ h+=Maj(a,b,c) from the past
- ldrb r12,[r1,#2]
- ldrb r0,[r1,#1]
- orr r2,r2,r12,lsl#8
- ldrb r12,[r1],#4
- orr r2,r2,r0,lsl#16
-# if 14==15
- str r1,[sp,#17*4] @ make room for r1
-# endif
- eor r0,r10,r10,ror#5
- orr r2,r2,r12,lsl#24
- eor r0,r0,r10,ror#19 @ Sigma1(e)
-#endif
- ldr r12,[r14],#4 @ *K256++
- add r5,r5,r2 @ h+=X[i]
- str r2,[sp,#14*4]
- eor r2,r11,r4
- add r5,r5,r0,ror#6 @ h+=Sigma1(e)
- and r2,r2,r10
- add r5,r5,r12 @ h+=K256[i]
- eor r2,r2,r4 @ Ch(e,f,g)
- eor r0,r6,r6,ror#11
- add r5,r5,r2 @ h+=Ch(e,f,g)
-#if 14==31
- and r12,r12,#0xff
- cmp r12,#0xf2 @ done?
-#endif
-#if 14<15
-# if __ARM_ARCH__>=7
- ldr r2,[r1],#4 @ prefetch
-# else
- ldrb r2,[r1,#3]
-# endif
- eor r12,r6,r7 @ a^b, b^c in next round
-#else
- ldr r2,[sp,#0*4] @ from future BODY_16_xx
- eor r12,r6,r7 @ a^b, b^c in next round
- ldr r1,[sp,#13*4] @ from future BODY_16_xx
-#endif
- eor r0,r0,r6,ror#20 @ Sigma0(a)
- and r3,r3,r12 @ (b^c)&=(a^b)
- add r9,r9,r5 @ d+=h
- eor r3,r3,r7 @ Maj(a,b,c)
- add r5,r5,r0,ror#2 @ h+=Sigma0(a)
- @ add r5,r5,r3 @ h+=Maj(a,b,c)
-#if __ARM_ARCH__>=7
- @ ldr r2,[r1],#4 @ 15
-# if 15==15
- str r1,[sp,#17*4] @ make room for r1
-# endif
- eor r0,r9,r9,ror#5
- add r5,r5,r3 @ h+=Maj(a,b,c) from the past
- eor r0,r0,r9,ror#19 @ Sigma1(e)
-# ifndef __ARMEB__
- rev r2,r2
-# endif
-#else
- @ ldrb r2,[r1,#3] @ 15
- add r5,r5,r3 @ h+=Maj(a,b,c) from the past
- ldrb r3,[r1,#2]
- ldrb r0,[r1,#1]
- orr r2,r2,r3,lsl#8
- ldrb r3,[r1],#4
- orr r2,r2,r0,lsl#16
-# if 15==15
- str r1,[sp,#17*4] @ make room for r1
-# endif
- eor r0,r9,r9,ror#5
- orr r2,r2,r3,lsl#24
- eor r0,r0,r9,ror#19 @ Sigma1(e)
-#endif
- ldr r3,[r14],#4 @ *K256++
- add r4,r4,r2 @ h+=X[i]
- str r2,[sp,#15*4]
- eor r2,r10,r11
- add r4,r4,r0,ror#6 @ h+=Sigma1(e)
- and r2,r2,r9
- add r4,r4,r3 @ h+=K256[i]
- eor r2,r2,r11 @ Ch(e,f,g)
- eor r0,r5,r5,ror#11
- add r4,r4,r2 @ h+=Ch(e,f,g)
-#if 15==31
- and r3,r3,#0xff
- cmp r3,#0xf2 @ done?
-#endif
-#if 15<15
-# if __ARM_ARCH__>=7
- ldr r2,[r1],#4 @ prefetch
-# else
- ldrb r2,[r1,#3]
-# endif
- eor r3,r5,r6 @ a^b, b^c in next round
-#else
- ldr r2,[sp,#1*4] @ from future BODY_16_xx
- eor r3,r5,r6 @ a^b, b^c in next round
- ldr r1,[sp,#14*4] @ from future BODY_16_xx
-#endif
- eor r0,r0,r5,ror#20 @ Sigma0(a)
- and r12,r12,r3 @ (b^c)&=(a^b)
- add r8,r8,r4 @ d+=h
- eor r12,r12,r6 @ Maj(a,b,c)
- add r4,r4,r0,ror#2 @ h+=Sigma0(a)
- @ add r4,r4,r12 @ h+=Maj(a,b,c)
-.Lrounds_16_xx:
- @ ldr r2,[sp,#1*4] @ 16
- @ ldr r1,[sp,#14*4]
- mov r0,r2,ror#7
- add r4,r4,r12 @ h+=Maj(a,b,c) from the past
- mov r12,r1,ror#17
- eor r0,r0,r2,ror#18
- eor r12,r12,r1,ror#19
- eor r0,r0,r2,lsr#3 @ sigma0(X[i+1])
- ldr r2,[sp,#0*4]
- eor r12,r12,r1,lsr#10 @ sigma1(X[i+14])
- ldr r1,[sp,#9*4]
-
- add r12,r12,r0
- eor r0,r8,r8,ror#5 @ from BODY_00_15
- add r2,r2,r12
- eor r0,r0,r8,ror#19 @ Sigma1(e)
- add r2,r2,r1 @ X[i]
- ldr r12,[r14],#4 @ *K256++
- add r11,r11,r2 @ h+=X[i]
- str r2,[sp,#0*4]
- eor r2,r9,r10
- add r11,r11,r0,ror#6 @ h+=Sigma1(e)
- and r2,r2,r8
- add r11,r11,r12 @ h+=K256[i]
- eor r2,r2,r10 @ Ch(e,f,g)
- eor r0,r4,r4,ror#11
- add r11,r11,r2 @ h+=Ch(e,f,g)
-#if 16==31
- and r12,r12,#0xff
- cmp r12,#0xf2 @ done?
-#endif
-#if 16<15
-# if __ARM_ARCH__>=7
- ldr r2,[r1],#4 @ prefetch
-# else
- ldrb r2,[r1,#3]
-# endif
- eor r12,r4,r5 @ a^b, b^c in next round
-#else
- ldr r2,[sp,#2*4] @ from future BODY_16_xx
- eor r12,r4,r5 @ a^b, b^c in next round
- ldr r1,[sp,#15*4] @ from future BODY_16_xx
-#endif
- eor r0,r0,r4,ror#20 @ Sigma0(a)
- and r3,r3,r12 @ (b^c)&=(a^b)
- add r7,r7,r11 @ d+=h
- eor r3,r3,r5 @ Maj(a,b,c)
- add r11,r11,r0,ror#2 @ h+=Sigma0(a)
- @ add r11,r11,r3 @ h+=Maj(a,b,c)
- @ ldr r2,[sp,#2*4] @ 17
- @ ldr r1,[sp,#15*4]
- mov r0,r2,ror#7
- add r11,r11,r3 @ h+=Maj(a,b,c) from the past
- mov r3,r1,ror#17
- eor r0,r0,r2,ror#18
- eor r3,r3,r1,ror#19
- eor r0,r0,r2,lsr#3 @ sigma0(X[i+1])
- ldr r2,[sp,#1*4]
- eor r3,r3,r1,lsr#10 @ sigma1(X[i+14])
- ldr r1,[sp,#10*4]
-
- add r3,r3,r0
- eor r0,r7,r7,ror#5 @ from BODY_00_15
- add r2,r2,r3
- eor r0,r0,r7,ror#19 @ Sigma1(e)
- add r2,r2,r1 @ X[i]
- ldr r3,[r14],#4 @ *K256++
- add r10,r10,r2 @ h+=X[i]
- str r2,[sp,#1*4]
- eor r2,r8,r9
- add r10,r10,r0,ror#6 @ h+=Sigma1(e)
- and r2,r2,r7
- add r10,r10,r3 @ h+=K256[i]
- eor r2,r2,r9 @ Ch(e,f,g)
- eor r0,r11,r11,ror#11
- add r10,r10,r2 @ h+=Ch(e,f,g)
-#if 17==31
- and r3,r3,#0xff
- cmp r3,#0xf2 @ done?
-#endif
-#if 17<15
-# if __ARM_ARCH__>=7
- ldr r2,[r1],#4 @ prefetch
-# else
- ldrb r2,[r1,#3]
-# endif
- eor r3,r11,r4 @ a^b, b^c in next round
-#else
- ldr r2,[sp,#3*4] @ from future BODY_16_xx
- eor r3,r11,r4 @ a^b, b^c in next round
- ldr r1,[sp,#0*4] @ from future BODY_16_xx
-#endif
- eor r0,r0,r11,ror#20 @ Sigma0(a)
- and r12,r12,r3 @ (b^c)&=(a^b)
- add r6,r6,r10 @ d+=h
- eor r12,r12,r4 @ Maj(a,b,c)
- add r10,r10,r0,ror#2 @ h+=Sigma0(a)
- @ add r10,r10,r12 @ h+=Maj(a,b,c)
- @ ldr r2,[sp,#3*4] @ 18
- @ ldr r1,[sp,#0*4]
- mov r0,r2,ror#7
- add r10,r10,r12 @ h+=Maj(a,b,c) from the past
- mov r12,r1,ror#17
- eor r0,r0,r2,ror#18
- eor r12,r12,r1,ror#19
- eor r0,r0,r2,lsr#3 @ sigma0(X[i+1])
- ldr r2,[sp,#2*4]
- eor r12,r12,r1,lsr#10 @ sigma1(X[i+14])
- ldr r1,[sp,#11*4]
-
- add r12,r12,r0
- eor r0,r6,r6,ror#5 @ from BODY_00_15
- add r2,r2,r12
- eor r0,r0,r6,ror#19 @ Sigma1(e)
- add r2,r2,r1 @ X[i]
- ldr r12,[r14],#4 @ *K256++
- add r9,r9,r2 @ h+=X[i]
- str r2,[sp,#2*4]
- eor r2,r7,r8
- add r9,r9,r0,ror#6 @ h+=Sigma1(e)
- and r2,r2,r6
- add r9,r9,r12 @ h+=K256[i]
- eor r2,r2,r8 @ Ch(e,f,g)
- eor r0,r10,r10,ror#11
- add r9,r9,r2 @ h+=Ch(e,f,g)
-#if 18==31
- and r12,r12,#0xff
- cmp r12,#0xf2 @ done?
-#endif
-#if 18<15
-# if __ARM_ARCH__>=7
- ldr r2,[r1],#4 @ prefetch
-# else
- ldrb r2,[r1,#3]
-# endif
- eor r12,r10,r11 @ a^b, b^c in next round
-#else
- ldr r2,[sp,#4*4] @ from future BODY_16_xx
- eor r12,r10,r11 @ a^b, b^c in next round
- ldr r1,[sp,#1*4] @ from future BODY_16_xx
-#endif
- eor r0,r0,r10,ror#20 @ Sigma0(a)
- and r3,r3,r12 @ (b^c)&=(a^b)
- add r5,r5,r9 @ d+=h
- eor r3,r3,r11 @ Maj(a,b,c)
- add r9,r9,r0,ror#2 @ h+=Sigma0(a)
- @ add r9,r9,r3 @ h+=Maj(a,b,c)
- @ ldr r2,[sp,#4*4] @ 19
- @ ldr r1,[sp,#1*4]
- mov r0,r2,ror#7
- add r9,r9,r3 @ h+=Maj(a,b,c) from the past
- mov r3,r1,ror#17
- eor r0,r0,r2,ror#18
- eor r3,r3,r1,ror#19
- eor r0,r0,r2,lsr#3 @ sigma0(X[i+1])
- ldr r2,[sp,#3*4]
- eor r3,r3,r1,lsr#10 @ sigma1(X[i+14])
- ldr r1,[sp,#12*4]
-
- add r3,r3,r0
- eor r0,r5,r5,ror#5 @ from BODY_00_15
- add r2,r2,r3
- eor r0,r0,r5,ror#19 @ Sigma1(e)
- add r2,r2,r1 @ X[i]
- ldr r3,[r14],#4 @ *K256++
- add r8,r8,r2 @ h+=X[i]
- str r2,[sp,#3*4]
- eor r2,r6,r7
- add r8,r8,r0,ror#6 @ h+=Sigma1(e)
- and r2,r2,r5
- add r8,r8,r3 @ h+=K256[i]
- eor r2,r2,r7 @ Ch(e,f,g)
- eor r0,r9,r9,ror#11
- add r8,r8,r2 @ h+=Ch(e,f,g)
-#if 19==31
- and r3,r3,#0xff
- cmp r3,#0xf2 @ done?
-#endif
-#if 19<15
-# if __ARM_ARCH__>=7
- ldr r2,[r1],#4 @ prefetch
-# else
- ldrb r2,[r1,#3]
-# endif
- eor r3,r9,r10 @ a^b, b^c in next round
-#else
- ldr r2,[sp,#5*4] @ from future BODY_16_xx
- eor r3,r9,r10 @ a^b, b^c in next round
- ldr r1,[sp,#2*4] @ from future BODY_16_xx
-#endif
- eor r0,r0,r9,ror#20 @ Sigma0(a)
- and r12,r12,r3 @ (b^c)&=(a^b)
- add r4,r4,r8 @ d+=h
- eor r12,r12,r10 @ Maj(a,b,c)
- add r8,r8,r0,ror#2 @ h+=Sigma0(a)
- @ add r8,r8,r12 @ h+=Maj(a,b,c)
- @ ldr r2,[sp,#5*4] @ 20
- @ ldr r1,[sp,#2*4]
- mov r0,r2,ror#7
- add r8,r8,r12 @ h+=Maj(a,b,c) from the past
- mov r12,r1,ror#17
- eor r0,r0,r2,ror#18
- eor r12,r12,r1,ror#19
- eor r0,r0,r2,lsr#3 @ sigma0(X[i+1])
- ldr r2,[sp,#4*4]
- eor r12,r12,r1,lsr#10 @ sigma1(X[i+14])
- ldr r1,[sp,#13*4]
-
- add r12,r12,r0
- eor r0,r4,r4,ror#5 @ from BODY_00_15
- add r2,r2,r12
- eor r0,r0,r4,ror#19 @ Sigma1(e)
- add r2,r2,r1 @ X[i]
- ldr r12,[r14],#4 @ *K256++
- add r7,r7,r2 @ h+=X[i]
- str r2,[sp,#4*4]
- eor r2,r5,r6
- add r7,r7,r0,ror#6 @ h+=Sigma1(e)
- and r2,r2,r4
- add r7,r7,r12 @ h+=K256[i]
- eor r2,r2,r6 @ Ch(e,f,g)
- eor r0,r8,r8,ror#11
- add r7,r7,r2 @ h+=Ch(e,f,g)
-#if 20==31
- and r12,r12,#0xff
- cmp r12,#0xf2 @ done?
-#endif
-#if 20<15
-# if __ARM_ARCH__>=7
- ldr r2,[r1],#4 @ prefetch
-# else
- ldrb r2,[r1,#3]
-# endif
- eor r12,r8,r9 @ a^b, b^c in next round
-#else
- ldr r2,[sp,#6*4] @ from future BODY_16_xx
- eor r12,r8,r9 @ a^b, b^c in next round
- ldr r1,[sp,#3*4] @ from future BODY_16_xx
-#endif
- eor r0,r0,r8,ror#20 @ Sigma0(a)
- and r3,r3,r12 @ (b^c)&=(a^b)
- add r11,r11,r7 @ d+=h
- eor r3,r3,r9 @ Maj(a,b,c)
- add r7,r7,r0,ror#2 @ h+=Sigma0(a)
- @ add r7,r7,r3 @ h+=Maj(a,b,c)
- @ ldr r2,[sp,#6*4] @ 21
- @ ldr r1,[sp,#3*4]
- mov r0,r2,ror#7
- add r7,r7,r3 @ h+=Maj(a,b,c) from the past
- mov r3,r1,ror#17
- eor r0,r0,r2,ror#18
- eor r3,r3,r1,ror#19
- eor r0,r0,r2,lsr#3 @ sigma0(X[i+1])
- ldr r2,[sp,#5*4]
- eor r3,r3,r1,lsr#10 @ sigma1(X[i+14])
- ldr r1,[sp,#14*4]
-
- add r3,r3,r0
- eor r0,r11,r11,ror#5 @ from BODY_00_15
- add r2,r2,r3
- eor r0,r0,r11,ror#19 @ Sigma1(e)
- add r2,r2,r1 @ X[i]
- ldr r3,[r14],#4 @ *K256++
- add r6,r6,r2 @ h+=X[i]
- str r2,[sp,#5*4]
- eor r2,r4,r5
- add r6,r6,r0,ror#6 @ h+=Sigma1(e)
- and r2,r2,r11
- add r6,r6,r3 @ h+=K256[i]
- eor r2,r2,r5 @ Ch(e,f,g)
- eor r0,r7,r7,ror#11
- add r6,r6,r2 @ h+=Ch(e,f,g)
-#if 21==31
- and r3,r3,#0xff
- cmp r3,#0xf2 @ done?
-#endif
-#if 21<15
-# if __ARM_ARCH__>=7
- ldr r2,[r1],#4 @ prefetch
-# else
- ldrb r2,[r1,#3]
-# endif
- eor r3,r7,r8 @ a^b, b^c in next round
-#else
- ldr r2,[sp,#7*4] @ from future BODY_16_xx
- eor r3,r7,r8 @ a^b, b^c in next round
- ldr r1,[sp,#4*4] @ from future BODY_16_xx
-#endif
- eor r0,r0,r7,ror#20 @ Sigma0(a)
- and r12,r12,r3 @ (b^c)&=(a^b)
- add r10,r10,r6 @ d+=h
- eor r12,r12,r8 @ Maj(a,b,c)
- add r6,r6,r0,ror#2 @ h+=Sigma0(a)
- @ add r6,r6,r12 @ h+=Maj(a,b,c)
- @ ldr r2,[sp,#7*4] @ 22
- @ ldr r1,[sp,#4*4]
- mov r0,r2,ror#7
- add r6,r6,r12 @ h+=Maj(a,b,c) from the past
- mov r12,r1,ror#17
- eor r0,r0,r2,ror#18
- eor r12,r12,r1,ror#19
- eor r0,r0,r2,lsr#3 @ sigma0(X[i+1])
- ldr r2,[sp,#6*4]
- eor r12,r12,r1,lsr#10 @ sigma1(X[i+14])
- ldr r1,[sp,#15*4]
-
- add r12,r12,r0
- eor r0,r10,r10,ror#5 @ from BODY_00_15
- add r2,r2,r12
- eor r0,r0,r10,ror#19 @ Sigma1(e)
- add r2,r2,r1 @ X[i]
- ldr r12,[r14],#4 @ *K256++
- add r5,r5,r2 @ h+=X[i]
- str r2,[sp,#6*4]
- eor r2,r11,r4
- add r5,r5,r0,ror#6 @ h+=Sigma1(e)
- and r2,r2,r10
- add r5,r5,r12 @ h+=K256[i]
- eor r2,r2,r4 @ Ch(e,f,g)
- eor r0,r6,r6,ror#11
- add r5,r5,r2 @ h+=Ch(e,f,g)
-#if 22==31
- and r12,r12,#0xff
- cmp r12,#0xf2 @ done?
-#endif
-#if 22<15
-# if __ARM_ARCH__>=7
- ldr r2,[r1],#4 @ prefetch
-# else
- ldrb r2,[r1,#3]
-# endif
- eor r12,r6,r7 @ a^b, b^c in next round
-#else
- ldr r2,[sp,#8*4] @ from future BODY_16_xx
- eor r12,r6,r7 @ a^b, b^c in next round
- ldr r1,[sp,#5*4] @ from future BODY_16_xx
-#endif
- eor r0,r0,r6,ror#20 @ Sigma0(a)
- and r3,r3,r12 @ (b^c)&=(a^b)
- add r9,r9,r5 @ d+=h
- eor r3,r3,r7 @ Maj(a,b,c)
- add r5,r5,r0,ror#2 @ h+=Sigma0(a)
- @ add r5,r5,r3 @ h+=Maj(a,b,c)
- @ ldr r2,[sp,#8*4] @ 23
- @ ldr r1,[sp,#5*4]
- mov r0,r2,ror#7
- add r5,r5,r3 @ h+=Maj(a,b,c) from the past
- mov r3,r1,ror#17
- eor r0,r0,r2,ror#18
- eor r3,r3,r1,ror#19
- eor r0,r0,r2,lsr#3 @ sigma0(X[i+1])
- ldr r2,[sp,#7*4]
- eor r3,r3,r1,lsr#10 @ sigma1(X[i+14])
- ldr r1,[sp,#0*4]
-
- add r3,r3,r0
- eor r0,r9,r9,ror#5 @ from BODY_00_15
- add r2,r2,r3
- eor r0,r0,r9,ror#19 @ Sigma1(e)
- add r2,r2,r1 @ X[i]
- ldr r3,[r14],#4 @ *K256++
- add r4,r4,r2 @ h+=X[i]
- str r2,[sp,#7*4]
- eor r2,r10,r11
- add r4,r4,r0,ror#6 @ h+=Sigma1(e)
- and r2,r2,r9
- add r4,r4,r3 @ h+=K256[i]
- eor r2,r2,r11 @ Ch(e,f,g)
- eor r0,r5,r5,ror#11
- add r4,r4,r2 @ h+=Ch(e,f,g)
-#if 23==31
- and r3,r3,#0xff
- cmp r3,#0xf2 @ done?
-#endif
-#if 23<15
-# if __ARM_ARCH__>=7
- ldr r2,[r1],#4 @ prefetch
-# else
- ldrb r2,[r1,#3]
-# endif
- eor r3,r5,r6 @ a^b, b^c in next round
-#else
- ldr r2,[sp,#9*4] @ from future BODY_16_xx
- eor r3,r5,r6 @ a^b, b^c in next round
- ldr r1,[sp,#6*4] @ from future BODY_16_xx
-#endif
- eor r0,r0,r5,ror#20 @ Sigma0(a)
- and r12,r12,r3 @ (b^c)&=(a^b)
- add r8,r8,r4 @ d+=h
- eor r12,r12,r6 @ Maj(a,b,c)
- add r4,r4,r0,ror#2 @ h+=Sigma0(a)
- @ add r4,r4,r12 @ h+=Maj(a,b,c)
- @ ldr r2,[sp,#9*4] @ 24
- @ ldr r1,[sp,#6*4]
- mov r0,r2,ror#7
- add r4,r4,r12 @ h+=Maj(a,b,c) from the past
- mov r12,r1,ror#17
- eor r0,r0,r2,ror#18
- eor r12,r12,r1,ror#19
- eor r0,r0,r2,lsr#3 @ sigma0(X[i+1])
- ldr r2,[sp,#8*4]
- eor r12,r12,r1,lsr#10 @ sigma1(X[i+14])
- ldr r1,[sp,#1*4]
-
- add r12,r12,r0
- eor r0,r8,r8,ror#5 @ from BODY_00_15
- add r2,r2,r12
- eor r0,r0,r8,ror#19 @ Sigma1(e)
- add r2,r2,r1 @ X[i]
- ldr r12,[r14],#4 @ *K256++
- add r11,r11,r2 @ h+=X[i]
- str r2,[sp,#8*4]
- eor r2,r9,r10
- add r11,r11,r0,ror#6 @ h+=Sigma1(e)
- and r2,r2,r8
- add r11,r11,r12 @ h+=K256[i]
- eor r2,r2,r10 @ Ch(e,f,g)
- eor r0,r4,r4,ror#11
- add r11,r11,r2 @ h+=Ch(e,f,g)
-#if 24==31
- and r12,r12,#0xff
- cmp r12,#0xf2 @ done?
-#endif
-#if 24<15
-# if __ARM_ARCH__>=7
- ldr r2,[r1],#4 @ prefetch
-# else
- ldrb r2,[r1,#3]
-# endif
- eor r12,r4,r5 @ a^b, b^c in next round
-#else
- ldr r2,[sp,#10*4] @ from future BODY_16_xx
- eor r12,r4,r5 @ a^b, b^c in next round
- ldr r1,[sp,#7*4] @ from future BODY_16_xx
-#endif
- eor r0,r0,r4,ror#20 @ Sigma0(a)
- and r3,r3,r12 @ (b^c)&=(a^b)
- add r7,r7,r11 @ d+=h
- eor r3,r3,r5 @ Maj(a,b,c)
- add r11,r11,r0,ror#2 @ h+=Sigma0(a)
- @ add r11,r11,r3 @ h+=Maj(a,b,c)
- @ ldr r2,[sp,#10*4] @ 25
- @ ldr r1,[sp,#7*4]
- mov r0,r2,ror#7
- add r11,r11,r3 @ h+=Maj(a,b,c) from the past
- mov r3,r1,ror#17
- eor r0,r0,r2,ror#18
- eor r3,r3,r1,ror#19
- eor r0,r0,r2,lsr#3 @ sigma0(X[i+1])
- ldr r2,[sp,#9*4]
- eor r3,r3,r1,lsr#10 @ sigma1(X[i+14])
- ldr r1,[sp,#2*4]
-
- add r3,r3,r0
- eor r0,r7,r7,ror#5 @ from BODY_00_15
- add r2,r2,r3
- eor r0,r0,r7,ror#19 @ Sigma1(e)
- add r2,r2,r1 @ X[i]
- ldr r3,[r14],#4 @ *K256++
- add r10,r10,r2 @ h+=X[i]
- str r2,[sp,#9*4]
- eor r2,r8,r9
- add r10,r10,r0,ror#6 @ h+=Sigma1(e)
- and r2,r2,r7
- add r10,r10,r3 @ h+=K256[i]
- eor r2,r2,r9 @ Ch(e,f,g)
- eor r0,r11,r11,ror#11
- add r10,r10,r2 @ h+=Ch(e,f,g)
-#if 25==31
- and r3,r3,#0xff
- cmp r3,#0xf2 @ done?
-#endif
-#if 25<15
-# if __ARM_ARCH__>=7
- ldr r2,[r1],#4 @ prefetch
-# else
- ldrb r2,[r1,#3]
-# endif
- eor r3,r11,r4 @ a^b, b^c in next round
-#else
- ldr r2,[sp,#11*4] @ from future BODY_16_xx
- eor r3,r11,r4 @ a^b, b^c in next round
- ldr r1,[sp,#8*4] @ from future BODY_16_xx
-#endif
- eor r0,r0,r11,ror#20 @ Sigma0(a)
- and r12,r12,r3 @ (b^c)&=(a^b)
- add r6,r6,r10 @ d+=h
- eor r12,r12,r4 @ Maj(a,b,c)
- add r10,r10,r0,ror#2 @ h+=Sigma0(a)
- @ add r10,r10,r12 @ h+=Maj(a,b,c)
- @ ldr r2,[sp,#11*4] @ 26
- @ ldr r1,[sp,#8*4]
- mov r0,r2,ror#7
- add r10,r10,r12 @ h+=Maj(a,b,c) from the past
- mov r12,r1,ror#17
- eor r0,r0,r2,ror#18
- eor r12,r12,r1,ror#19
- eor r0,r0,r2,lsr#3 @ sigma0(X[i+1])
- ldr r2,[sp,#10*4]
- eor r12,r12,r1,lsr#10 @ sigma1(X[i+14])
- ldr r1,[sp,#3*4]
-
- add r12,r12,r0
- eor r0,r6,r6,ror#5 @ from BODY_00_15
- add r2,r2,r12
- eor r0,r0,r6,ror#19 @ Sigma1(e)
- add r2,r2,r1 @ X[i]
- ldr r12,[r14],#4 @ *K256++
- add r9,r9,r2 @ h+=X[i]
- str r2,[sp,#10*4]
- eor r2,r7,r8
- add r9,r9,r0,ror#6 @ h+=Sigma1(e)
- and r2,r2,r6
- add r9,r9,r12 @ h+=K256[i]
- eor r2,r2,r8 @ Ch(e,f,g)
- eor r0,r10,r10,ror#11
- add r9,r9,r2 @ h+=Ch(e,f,g)
-#if 26==31
- and r12,r12,#0xff
- cmp r12,#0xf2 @ done?
-#endif
-#if 26<15
-# if __ARM_ARCH__>=7
- ldr r2,[r1],#4 @ prefetch
-# else
- ldrb r2,[r1,#3]
-# endif
- eor r12,r10,r11 @ a^b, b^c in next round
-#else
- ldr r2,[sp,#12*4] @ from future BODY_16_xx
- eor r12,r10,r11 @ a^b, b^c in next round
- ldr r1,[sp,#9*4] @ from future BODY_16_xx
-#endif
- eor r0,r0,r10,ror#20 @ Sigma0(a)
- and r3,r3,r12 @ (b^c)&=(a^b)
- add r5,r5,r9 @ d+=h
- eor r3,r3,r11 @ Maj(a,b,c)
- add r9,r9,r0,ror#2 @ h+=Sigma0(a)
- @ add r9,r9,r3 @ h+=Maj(a,b,c)
- @ ldr r2,[sp,#12*4] @ 27
- @ ldr r1,[sp,#9*4]
- mov r0,r2,ror#7
- add r9,r9,r3 @ h+=Maj(a,b,c) from the past
- mov r3,r1,ror#17
- eor r0,r0,r2,ror#18
- eor r3,r3,r1,ror#19
- eor r0,r0,r2,lsr#3 @ sigma0(X[i+1])
- ldr r2,[sp,#11*4]
- eor r3,r3,r1,lsr#10 @ sigma1(X[i+14])
- ldr r1,[sp,#4*4]
-
- add r3,r3,r0
- eor r0,r5,r5,ror#5 @ from BODY_00_15
- add r2,r2,r3
- eor r0,r0,r5,ror#19 @ Sigma1(e)
- add r2,r2,r1 @ X[i]
- ldr r3,[r14],#4 @ *K256++
- add r8,r8,r2 @ h+=X[i]
- str r2,[sp,#11*4]
- eor r2,r6,r7
- add r8,r8,r0,ror#6 @ h+=Sigma1(e)
- and r2,r2,r5
- add r8,r8,r3 @ h+=K256[i]
- eor r2,r2,r7 @ Ch(e,f,g)
- eor r0,r9,r9,ror#11
- add r8,r8,r2 @ h+=Ch(e,f,g)
-#if 27==31
- and r3,r3,#0xff
- cmp r3,#0xf2 @ done?
-#endif
-#if 27<15
-# if __ARM_ARCH__>=7
- ldr r2,[r1],#4 @ prefetch
-# else
- ldrb r2,[r1,#3]
-# endif
- eor r3,r9,r10 @ a^b, b^c in next round
-#else
- ldr r2,[sp,#13*4] @ from future BODY_16_xx
- eor r3,r9,r10 @ a^b, b^c in next round
- ldr r1,[sp,#10*4] @ from future BODY_16_xx
-#endif
- eor r0,r0,r9,ror#20 @ Sigma0(a)
- and r12,r12,r3 @ (b^c)&=(a^b)
- add r4,r4,r8 @ d+=h
- eor r12,r12,r10 @ Maj(a,b,c)
- add r8,r8,r0,ror#2 @ h+=Sigma0(a)
- @ add r8,r8,r12 @ h+=Maj(a,b,c)
- @ ldr r2,[sp,#13*4] @ 28
- @ ldr r1,[sp,#10*4]
- mov r0,r2,ror#7
- add r8,r8,r12 @ h+=Maj(a,b,c) from the past
- mov r12,r1,ror#17
- eor r0,r0,r2,ror#18
- eor r12,r12,r1,ror#19
- eor r0,r0,r2,lsr#3 @ sigma0(X[i+1])
- ldr r2,[sp,#12*4]
- eor r12,r12,r1,lsr#10 @ sigma1(X[i+14])
- ldr r1,[sp,#5*4]
-
- add r12,r12,r0
- eor r0,r4,r4,ror#5 @ from BODY_00_15
- add r2,r2,r12
- eor r0,r0,r4,ror#19 @ Sigma1(e)
- add r2,r2,r1 @ X[i]
- ldr r12,[r14],#4 @ *K256++
- add r7,r7,r2 @ h+=X[i]
- str r2,[sp,#12*4]
- eor r2,r5,r6
- add r7,r7,r0,ror#6 @ h+=Sigma1(e)
- and r2,r2,r4
- add r7,r7,r12 @ h+=K256[i]
- eor r2,r2,r6 @ Ch(e,f,g)
- eor r0,r8,r8,ror#11
- add r7,r7,r2 @ h+=Ch(e,f,g)
-#if 28==31
- and r12,r12,#0xff
- cmp r12,#0xf2 @ done?
-#endif
-#if 28<15
-# if __ARM_ARCH__>=7
- ldr r2,[r1],#4 @ prefetch
-# else
- ldrb r2,[r1,#3]
-# endif
- eor r12,r8,r9 @ a^b, b^c in next round
-#else
- ldr r2,[sp,#14*4] @ from future BODY_16_xx
- eor r12,r8,r9 @ a^b, b^c in next round
- ldr r1,[sp,#11*4] @ from future BODY_16_xx
-#endif
- eor r0,r0,r8,ror#20 @ Sigma0(a)
- and r3,r3,r12 @ (b^c)&=(a^b)
- add r11,r11,r7 @ d+=h
- eor r3,r3,r9 @ Maj(a,b,c)
- add r7,r7,r0,ror#2 @ h+=Sigma0(a)
- @ add r7,r7,r3 @ h+=Maj(a,b,c)
- @ ldr r2,[sp,#14*4] @ 29
- @ ldr r1,[sp,#11*4]
- mov r0,r2,ror#7
- add r7,r7,r3 @ h+=Maj(a,b,c) from the past
- mov r3,r1,ror#17
- eor r0,r0,r2,ror#18
- eor r3,r3,r1,ror#19
- eor r0,r0,r2,lsr#3 @ sigma0(X[i+1])
- ldr r2,[sp,#13*4]
- eor r3,r3,r1,lsr#10 @ sigma1(X[i+14])
- ldr r1,[sp,#6*4]
-
- add r3,r3,r0
- eor r0,r11,r11,ror#5 @ from BODY_00_15
- add r2,r2,r3
- eor r0,r0,r11,ror#19 @ Sigma1(e)
- add r2,r2,r1 @ X[i]
- ldr r3,[r14],#4 @ *K256++
- add r6,r6,r2 @ h+=X[i]
- str r2,[sp,#13*4]
- eor r2,r4,r5
- add r6,r6,r0,ror#6 @ h+=Sigma1(e)
- and r2,r2,r11
- add r6,r6,r3 @ h+=K256[i]
- eor r2,r2,r5 @ Ch(e,f,g)
- eor r0,r7,r7,ror#11
- add r6,r6,r2 @ h+=Ch(e,f,g)
-#if 29==31
- and r3,r3,#0xff
- cmp r3,#0xf2 @ done?
-#endif
-#if 29<15
-# if __ARM_ARCH__>=7
- ldr r2,[r1],#4 @ prefetch
-# else
- ldrb r2,[r1,#3]
-# endif
- eor r3,r7,r8 @ a^b, b^c in next round
-#else
- ldr r2,[sp,#15*4] @ from future BODY_16_xx
- eor r3,r7,r8 @ a^b, b^c in next round
- ldr r1,[sp,#12*4] @ from future BODY_16_xx
-#endif
- eor r0,r0,r7,ror#20 @ Sigma0(a)
- and r12,r12,r3 @ (b^c)&=(a^b)
- add r10,r10,r6 @ d+=h
- eor r12,r12,r8 @ Maj(a,b,c)
- add r6,r6,r0,ror#2 @ h+=Sigma0(a)
- @ add r6,r6,r12 @ h+=Maj(a,b,c)
- @ ldr r2,[sp,#15*4] @ 30
- @ ldr r1,[sp,#12*4]
- mov r0,r2,ror#7
- add r6,r6,r12 @ h+=Maj(a,b,c) from the past
- mov r12,r1,ror#17
- eor r0,r0,r2,ror#18
- eor r12,r12,r1,ror#19
- eor r0,r0,r2,lsr#3 @ sigma0(X[i+1])
- ldr r2,[sp,#14*4]
- eor r12,r12,r1,lsr#10 @ sigma1(X[i+14])
- ldr r1,[sp,#7*4]
-
- add r12,r12,r0
- eor r0,r10,r10,ror#5 @ from BODY_00_15
- add r2,r2,r12
- eor r0,r0,r10,ror#19 @ Sigma1(e)
- add r2,r2,r1 @ X[i]
- ldr r12,[r14],#4 @ *K256++
- add r5,r5,r2 @ h+=X[i]
- str r2,[sp,#14*4]
- eor r2,r11,r4
- add r5,r5,r0,ror#6 @ h+=Sigma1(e)
- and r2,r2,r10
- add r5,r5,r12 @ h+=K256[i]
- eor r2,r2,r4 @ Ch(e,f,g)
- eor r0,r6,r6,ror#11
- add r5,r5,r2 @ h+=Ch(e,f,g)
-#if 30==31
- and r12,r12,#0xff
- cmp r12,#0xf2 @ done?
-#endif
-#if 30<15
-# if __ARM_ARCH__>=7
- ldr r2,[r1],#4 @ prefetch
-# else
- ldrb r2,[r1,#3]
-# endif
- eor r12,r6,r7 @ a^b, b^c in next round
-#else
- ldr r2,[sp,#0*4] @ from future BODY_16_xx
- eor r12,r6,r7 @ a^b, b^c in next round
- ldr r1,[sp,#13*4] @ from future BODY_16_xx
-#endif
- eor r0,r0,r6,ror#20 @ Sigma0(a)
- and r3,r3,r12 @ (b^c)&=(a^b)
- add r9,r9,r5 @ d+=h
- eor r3,r3,r7 @ Maj(a,b,c)
- add r5,r5,r0,ror#2 @ h+=Sigma0(a)
- @ add r5,r5,r3 @ h+=Maj(a,b,c)
- @ ldr r2,[sp,#0*4] @ 31
- @ ldr r1,[sp,#13*4]
- mov r0,r2,ror#7
- add r5,r5,r3 @ h+=Maj(a,b,c) from the past
- mov r3,r1,ror#17
- eor r0,r0,r2,ror#18
- eor r3,r3,r1,ror#19
- eor r0,r0,r2,lsr#3 @ sigma0(X[i+1])
- ldr r2,[sp,#15*4]
- eor r3,r3,r1,lsr#10 @ sigma1(X[i+14])
- ldr r1,[sp,#8*4]
-
- add r3,r3,r0
- eor r0,r9,r9,ror#5 @ from BODY_00_15
- add r2,r2,r3
- eor r0,r0,r9,ror#19 @ Sigma1(e)
- add r2,r2,r1 @ X[i]
- ldr r3,[r14],#4 @ *K256++
- add r4,r4,r2 @ h+=X[i]
- str r2,[sp,#15*4]
- eor r2,r10,r11
- add r4,r4,r0,ror#6 @ h+=Sigma1(e)
- and r2,r2,r9
- add r4,r4,r3 @ h+=K256[i]
- eor r2,r2,r11 @ Ch(e,f,g)
- eor r0,r5,r5,ror#11
- add r4,r4,r2 @ h+=Ch(e,f,g)
-#if 31==31
- and r3,r3,#0xff
- cmp r3,#0xf2 @ done?
-#endif
-#if 31<15
-# if __ARM_ARCH__>=7
- ldr r2,[r1],#4 @ prefetch
-# else
- ldrb r2,[r1,#3]
-# endif
- eor r3,r5,r6 @ a^b, b^c in next round
-#else
- ldr r2,[sp,#1*4] @ from future BODY_16_xx
- eor r3,r5,r6 @ a^b, b^c in next round
- ldr r1,[sp,#14*4] @ from future BODY_16_xx
-#endif
- eor r0,r0,r5,ror#20 @ Sigma0(a)
- and r12,r12,r3 @ (b^c)&=(a^b)
- add r8,r8,r4 @ d+=h
- eor r12,r12,r6 @ Maj(a,b,c)
- add r4,r4,r0,ror#2 @ h+=Sigma0(a)
- @ add r4,r4,r12 @ h+=Maj(a,b,c)
-#if __ARM_ARCH__>=7
- ite eq @ Thumb2 thing, sanity check in ARM
-#endif
- ldreq r3,[sp,#16*4] @ pull ctx
- bne .Lrounds_16_xx
-
- add r4,r4,r12 @ h+=Maj(a,b,c) from the past
- ldr r0,[r3,#0]
- ldr r2,[r3,#4]
- ldr r12,[r3,#8]
- add r4,r4,r0
- ldr r0,[r3,#12]
- add r5,r5,r2
- ldr r2,[r3,#16]
- add r6,r6,r12
- ldr r12,[r3,#20]
- add r7,r7,r0
- ldr r0,[r3,#24]
- add r8,r8,r2
- ldr r2,[r3,#28]
- add r9,r9,r12
- ldr r1,[sp,#17*4] @ pull inp
- ldr r12,[sp,#18*4] @ pull inp+len
- add r10,r10,r0
- add r11,r11,r2
- stmia r3,{r4,r5,r6,r7,r8,r9,r10,r11}
- cmp r1,r12
- sub r14,r14,#256 @ rewind Ktbl
- bne .Loop
-
- add sp,sp,#19*4 @ destroy frame
-#if __ARM_ARCH__>=5
- ldmia sp!,{r4-r11,pc}
-#else
- ldmia sp!,{r4-r11,lr}
- tst lr,#1
- moveq pc,lr @ be binary compatible with V4, yet
- .word 0xe12fff1e @ interoperable with Thumb ISA:-)
-#endif
-.size sha256_block_data_order,.-sha256_block_data_order
-#if __ARM_MAX_ARCH__>=7
-.arch armv7-a
-.fpu neon
-
-.global sha256_block_data_order_neon
-.type sha256_block_data_order_neon,%function
-.align 4
-sha256_block_data_order_neon:
-.LNEON:
- stmdb sp!,{r4-r12,lr}
-
- sub r11,sp,#16*4+16
- adr r14,.Lsha256_block_data_order
- sub r14,r14,#.Lsha256_block_data_order-K256
- bic r11,r11,#15 @ align for 128-bit stores
- mov r12,sp
- mov sp,r11 @ alloca
- add r2,r1,r2,lsl#6 @ len to point at the end of inp
-
- vld1.8 {q0},[r1]!
- vld1.8 {q1},[r1]!
- vld1.8 {q2},[r1]!
- vld1.8 {q3},[r1]!
- vld1.32 {q8},[r14,:128]!
- vld1.32 {q9},[r14,:128]!
- vld1.32 {q10},[r14,:128]!
- vld1.32 {q11},[r14,:128]!
- vrev32.8 q0,q0 @ yes, even on
- str r0,[sp,#64]
- vrev32.8 q1,q1 @ big-endian
- str r1,[sp,#68]
- mov r1,sp
- vrev32.8 q2,q2
- str r2,[sp,#72]
- vrev32.8 q3,q3
- str r12,[sp,#76] @ save original sp
- vadd.i32 q8,q8,q0
- vadd.i32 q9,q9,q1
- vst1.32 {q8},[r1,:128]!
- vadd.i32 q10,q10,q2
- vst1.32 {q9},[r1,:128]!
- vadd.i32 q11,q11,q3
- vst1.32 {q10},[r1,:128]!
- vst1.32 {q11},[r1,:128]!
-
- ldmia r0,{r4-r11}
- sub r1,r1,#64
- ldr r2,[sp,#0]
- eor r12,r12,r12
- eor r3,r5,r6
- b .L_00_48
-
-.align 4
-.L_00_48:
- vext.8 q8,q0,q1,#4
- add r11,r11,r2
- eor r2,r9,r10
- eor r0,r8,r8,ror#5
- vext.8 q9,q2,q3,#4
- add r4,r4,r12
- and r2,r2,r8
- eor r12,r0,r8,ror#19
- vshr.u32 q10,q8,#7
- eor r0,r4,r4,ror#11
- eor r2,r2,r10
- vadd.i32 q0,q0,q9
- add r11,r11,r12,ror#6
- eor r12,r4,r5
- vshr.u32 q9,q8,#3
- eor r0,r0,r4,ror#20
- add r11,r11,r2
- vsli.32 q10,q8,#25
- ldr r2,[sp,#4]
- and r3,r3,r12
- vshr.u32 q11,q8,#18
- add r7,r7,r11
- add r11,r11,r0,ror#2
- eor r3,r3,r5
- veor q9,q9,q10
- add r10,r10,r2
- vsli.32 q11,q8,#14
- eor r2,r8,r9
- eor r0,r7,r7,ror#5
- vshr.u32 d24,d7,#17
- add r11,r11,r3
- and r2,r2,r7
- veor q9,q9,q11
- eor r3,r0,r7,ror#19
- eor r0,r11,r11,ror#11
- vsli.32 d24,d7,#15
- eor r2,r2,r9
- add r10,r10,r3,ror#6
- vshr.u32 d25,d7,#10
- eor r3,r11,r4
- eor r0,r0,r11,ror#20
- vadd.i32 q0,q0,q9
- add r10,r10,r2
- ldr r2,[sp,#8]
- veor d25,d25,d24
- and r12,r12,r3
- add r6,r6,r10
- vshr.u32 d24,d7,#19
- add r10,r10,r0,ror#2
- eor r12,r12,r4
- vsli.32 d24,d7,#13
- add r9,r9,r2
- eor r2,r7,r8
- veor d25,d25,d24
- eor r0,r6,r6,ror#5
- add r10,r10,r12
- vadd.i32 d0,d0,d25
- and r2,r2,r6
- eor r12,r0,r6,ror#19
- vshr.u32 d24,d0,#17
- eor r0,r10,r10,ror#11
- eor r2,r2,r8
- vsli.32 d24,d0,#15
- add r9,r9,r12,ror#6
- eor r12,r10,r11
- vshr.u32 d25,d0,#10
- eor r0,r0,r10,ror#20
- add r9,r9,r2
- veor d25,d25,d24
- ldr r2,[sp,#12]
- and r3,r3,r12
- vshr.u32 d24,d0,#19
- add r5,r5,r9
- add r9,r9,r0,ror#2
- eor r3,r3,r11
- vld1.32 {q8},[r14,:128]!
- add r8,r8,r2
- vsli.32 d24,d0,#13
- eor r2,r6,r7
- eor r0,r5,r5,ror#5
- veor d25,d25,d24
- add r9,r9,r3
- and r2,r2,r5
- vadd.i32 d1,d1,d25
- eor r3,r0,r5,ror#19
- eor r0,r9,r9,ror#11
- vadd.i32 q8,q8,q0
- eor r2,r2,r7
- add r8,r8,r3,ror#6
- eor r3,r9,r10
- eor r0,r0,r9,ror#20
- add r8,r8,r2
- ldr r2,[sp,#16]
- and r12,r12,r3
- add r4,r4,r8
- vst1.32 {q8},[r1,:128]!
- add r8,r8,r0,ror#2
- eor r12,r12,r10
- vext.8 q8,q1,q2,#4
- add r7,r7,r2
- eor r2,r5,r6
- eor r0,r4,r4,ror#5
- vext.8 q9,q3,q0,#4
- add r8,r8,r12
- and r2,r2,r4
- eor r12,r0,r4,ror#19
- vshr.u32 q10,q8,#7
- eor r0,r8,r8,ror#11
- eor r2,r2,r6
- vadd.i32 q1,q1,q9
- add r7,r7,r12,ror#6
- eor r12,r8,r9
- vshr.u32 q9,q8,#3
- eor r0,r0,r8,ror#20
- add r7,r7,r2
- vsli.32 q10,q8,#25
- ldr r2,[sp,#20]
- and r3,r3,r12
- vshr.u32 q11,q8,#18
- add r11,r11,r7
- add r7,r7,r0,ror#2
- eor r3,r3,r9
- veor q9,q9,q10
- add r6,r6,r2
- vsli.32 q11,q8,#14
- eor r2,r4,r5
- eor r0,r11,r11,ror#5
- vshr.u32 d24,d1,#17
- add r7,r7,r3
- and r2,r2,r11
- veor q9,q9,q11
- eor r3,r0,r11,ror#19
- eor r0,r7,r7,ror#11
- vsli.32 d24,d1,#15
- eor r2,r2,r5
- add r6,r6,r3,ror#6
- vshr.u32 d25,d1,#10
- eor r3,r7,r8
- eor r0,r0,r7,ror#20
- vadd.i32 q1,q1,q9
- add r6,r6,r2
- ldr r2,[sp,#24]
- veor d25,d25,d24
- and r12,r12,r3
- add r10,r10,r6
- vshr.u32 d24,d1,#19
- add r6,r6,r0,ror#2
- eor r12,r12,r8
- vsli.32 d24,d1,#13
- add r5,r5,r2
- eor r2,r11,r4
- veor d25,d25,d24
- eor r0,r10,r10,ror#5
- add r6,r6,r12
- vadd.i32 d2,d2,d25
- and r2,r2,r10
- eor r12,r0,r10,ror#19
- vshr.u32 d24,d2,#17
- eor r0,r6,r6,ror#11
- eor r2,r2,r4
- vsli.32 d24,d2,#15
- add r5,r5,r12,ror#6
- eor r12,r6,r7
- vshr.u32 d25,d2,#10
- eor r0,r0,r6,ror#20
- add r5,r5,r2
- veor d25,d25,d24
- ldr r2,[sp,#28]
- and r3,r3,r12
- vshr.u32 d24,d2,#19
- add r9,r9,r5
- add r5,r5,r0,ror#2
- eor r3,r3,r7
- vld1.32 {q8},[r14,:128]!
- add r4,r4,r2
- vsli.32 d24,d2,#13
- eor r2,r10,r11
- eor r0,r9,r9,ror#5
- veor d25,d25,d24
- add r5,r5,r3
- and r2,r2,r9
- vadd.i32 d3,d3,d25
- eor r3,r0,r9,ror#19
- eor r0,r5,r5,ror#11
- vadd.i32 q8,q8,q1
- eor r2,r2,r11
- add r4,r4,r3,ror#6
- eor r3,r5,r6
- eor r0,r0,r5,ror#20
- add r4,r4,r2
- ldr r2,[sp,#32]
- and r12,r12,r3
- add r8,r8,r4
- vst1.32 {q8},[r1,:128]!
- add r4,r4,r0,ror#2
- eor r12,r12,r6
- vext.8 q8,q2,q3,#4
- add r11,r11,r2
- eor r2,r9,r10
- eor r0,r8,r8,ror#5
- vext.8 q9,q0,q1,#4
- add r4,r4,r12
- and r2,r2,r8
- eor r12,r0,r8,ror#19
- vshr.u32 q10,q8,#7
- eor r0,r4,r4,ror#11
- eor r2,r2,r10
- vadd.i32 q2,q2,q9
- add r11,r11,r12,ror#6
- eor r12,r4,r5
- vshr.u32 q9,q8,#3
- eor r0,r0,r4,ror#20
- add r11,r11,r2
- vsli.32 q10,q8,#25
- ldr r2,[sp,#36]
- and r3,r3,r12
- vshr.u32 q11,q8,#18
- add r7,r7,r11
- add r11,r11,r0,ror#2
- eor r3,r3,r5
- veor q9,q9,q10
- add r10,r10,r2
- vsli.32 q11,q8,#14
- eor r2,r8,r9
- eor r0,r7,r7,ror#5
- vshr.u32 d24,d3,#17
- add r11,r11,r3
- and r2,r2,r7
- veor q9,q9,q11
- eor r3,r0,r7,ror#19
- eor r0,r11,r11,ror#11
- vsli.32 d24,d3,#15
- eor r2,r2,r9
- add r10,r10,r3,ror#6
- vshr.u32 d25,d3,#10
- eor r3,r11,r4
- eor r0,r0,r11,ror#20
- vadd.i32 q2,q2,q9
- add r10,r10,r2
- ldr r2,[sp,#40]
- veor d25,d25,d24
- and r12,r12,r3
- add r6,r6,r10
- vshr.u32 d24,d3,#19
- add r10,r10,r0,ror#2
- eor r12,r12,r4
- vsli.32 d24,d3,#13
- add r9,r9,r2
- eor r2,r7,r8
- veor d25,d25,d24
- eor r0,r6,r6,ror#5
- add r10,r10,r12
- vadd.i32 d4,d4,d25
- and r2,r2,r6
- eor r12,r0,r6,ror#19
- vshr.u32 d24,d4,#17
- eor r0,r10,r10,ror#11
- eor r2,r2,r8
- vsli.32 d24,d4,#15
- add r9,r9,r12,ror#6
- eor r12,r10,r11
- vshr.u32 d25,d4,#10
- eor r0,r0,r10,ror#20
- add r9,r9,r2
- veor d25,d25,d24
- ldr r2,[sp,#44]
- and r3,r3,r12
- vshr.u32 d24,d4,#19
- add r5,r5,r9
- add r9,r9,r0,ror#2
- eor r3,r3,r11
- vld1.32 {q8},[r14,:128]!
- add r8,r8,r2
- vsli.32 d24,d4,#13
- eor r2,r6,r7
- eor r0,r5,r5,ror#5
- veor d25,d25,d24
- add r9,r9,r3
- and r2,r2,r5
- vadd.i32 d5,d5,d25
- eor r3,r0,r5,ror#19
- eor r0,r9,r9,ror#11
- vadd.i32 q8,q8,q2
- eor r2,r2,r7
- add r8,r8,r3,ror#6
- eor r3,r9,r10
- eor r0,r0,r9,ror#20
- add r8,r8,r2
- ldr r2,[sp,#48]
- and r12,r12,r3
- add r4,r4,r8
- vst1.32 {q8},[r1,:128]!
- add r8,r8,r0,ror#2
- eor r12,r12,r10
- vext.8 q8,q3,q0,#4
- add r7,r7,r2
- eor r2,r5,r6
- eor r0,r4,r4,ror#5
- vext.8 q9,q1,q2,#4
- add r8,r8,r12
- and r2,r2,r4
- eor r12,r0,r4,ror#19
- vshr.u32 q10,q8,#7
- eor r0,r8,r8,ror#11
- eor r2,r2,r6
- vadd.i32 q3,q3,q9
- add r7,r7,r12,ror#6
- eor r12,r8,r9
- vshr.u32 q9,q8,#3
- eor r0,r0,r8,ror#20
- add r7,r7,r2
- vsli.32 q10,q8,#25
- ldr r2,[sp,#52]
- and r3,r3,r12
- vshr.u32 q11,q8,#18
- add r11,r11,r7
- add r7,r7,r0,ror#2
- eor r3,r3,r9
- veor q9,q9,q10
- add r6,r6,r2
- vsli.32 q11,q8,#14
- eor r2,r4,r5
- eor r0,r11,r11,ror#5
- vshr.u32 d24,d5,#17
- add r7,r7,r3
- and r2,r2,r11
- veor q9,q9,q11
- eor r3,r0,r11,ror#19
- eor r0,r7,r7,ror#11
- vsli.32 d24,d5,#15
- eor r2,r2,r5
- add r6,r6,r3,ror#6
- vshr.u32 d25,d5,#10
- eor r3,r7,r8
- eor r0,r0,r7,ror#20
- vadd.i32 q3,q3,q9
- add r6,r6,r2
- ldr r2,[sp,#56]
- veor d25,d25,d24
- and r12,r12,r3
- add r10,r10,r6
- vshr.u32 d24,d5,#19
- add r6,r6,r0,ror#2
- eor r12,r12,r8
- vsli.32 d24,d5,#13
- add r5,r5,r2
- eor r2,r11,r4
- veor d25,d25,d24
- eor r0,r10,r10,ror#5
- add r6,r6,r12
- vadd.i32 d6,d6,d25
- and r2,r2,r10
- eor r12,r0,r10,ror#19
- vshr.u32 d24,d6,#17
- eor r0,r6,r6,ror#11
- eor r2,r2,r4
- vsli.32 d24,d6,#15
- add r5,r5,r12,ror#6
- eor r12,r6,r7
- vshr.u32 d25,d6,#10
- eor r0,r0,r6,ror#20
- add r5,r5,r2
- veor d25,d25,d24
- ldr r2,[sp,#60]
- and r3,r3,r12
- vshr.u32 d24,d6,#19
- add r9,r9,r5
- add r5,r5,r0,ror#2
- eor r3,r3,r7
- vld1.32 {q8},[r14,:128]!
- add r4,r4,r2
- vsli.32 d24,d6,#13
- eor r2,r10,r11
- eor r0,r9,r9,ror#5
- veor d25,d25,d24
- add r5,r5,r3
- and r2,r2,r9
- vadd.i32 d7,d7,d25
- eor r3,r0,r9,ror#19
- eor r0,r5,r5,ror#11
- vadd.i32 q8,q8,q3
- eor r2,r2,r11
- add r4,r4,r3,ror#6
- eor r3,r5,r6
- eor r0,r0,r5,ror#20
- add r4,r4,r2
- ldr r2,[r14]
- and r12,r12,r3
- add r8,r8,r4
- vst1.32 {q8},[r1,:128]!
- add r4,r4,r0,ror#2
- eor r12,r12,r6
- teq r2,#0 @ check for K256 terminator
- ldr r2,[sp,#0]
- sub r1,r1,#64
- bne .L_00_48
-
- ldr r1,[sp,#68]
- ldr r0,[sp,#72]
- sub r14,r14,#256 @ rewind r14
- teq r1,r0
- it eq
- subeq r1,r1,#64 @ avoid SEGV
- vld1.8 {q0},[r1]! @ load next input block
- vld1.8 {q1},[r1]!
- vld1.8 {q2},[r1]!
- vld1.8 {q3},[r1]!
- it ne
- strne r1,[sp,#68]
- mov r1,sp
- add r11,r11,r2
- eor r2,r9,r10
- eor r0,r8,r8,ror#5
- add r4,r4,r12
- vld1.32 {q8},[r14,:128]!
- and r2,r2,r8
- eor r12,r0,r8,ror#19
- eor r0,r4,r4,ror#11
- eor r2,r2,r10
- vrev32.8 q0,q0
- add r11,r11,r12,ror#6
- eor r12,r4,r5
- eor r0,r0,r4,ror#20
- add r11,r11,r2
- vadd.i32 q8,q8,q0
- ldr r2,[sp,#4]
- and r3,r3,r12
- add r7,r7,r11
- add r11,r11,r0,ror#2
- eor r3,r3,r5
- add r10,r10,r2
- eor r2,r8,r9
- eor r0,r7,r7,ror#5
- add r11,r11,r3
- and r2,r2,r7
- eor r3,r0,r7,ror#19
- eor r0,r11,r11,ror#11
- eor r2,r2,r9
- add r10,r10,r3,ror#6
- eor r3,r11,r4
- eor r0,r0,r11,ror#20
- add r10,r10,r2
- ldr r2,[sp,#8]
- and r12,r12,r3
- add r6,r6,r10
- add r10,r10,r0,ror#2
- eor r12,r12,r4
- add r9,r9,r2
- eor r2,r7,r8
- eor r0,r6,r6,ror#5
- add r10,r10,r12
- and r2,r2,r6
- eor r12,r0,r6,ror#19
- eor r0,r10,r10,ror#11
- eor r2,r2,r8
- add r9,r9,r12,ror#6
- eor r12,r10,r11
- eor r0,r0,r10,ror#20
- add r9,r9,r2
- ldr r2,[sp,#12]
- and r3,r3,r12
- add r5,r5,r9
- add r9,r9,r0,ror#2
- eor r3,r3,r11
- add r8,r8,r2
- eor r2,r6,r7
- eor r0,r5,r5,ror#5
- add r9,r9,r3
- and r2,r2,r5
- eor r3,r0,r5,ror#19
- eor r0,r9,r9,ror#11
- eor r2,r2,r7
- add r8,r8,r3,ror#6
- eor r3,r9,r10
- eor r0,r0,r9,ror#20
- add r8,r8,r2
- ldr r2,[sp,#16]
- and r12,r12,r3
- add r4,r4,r8
- add r8,r8,r0,ror#2
- eor r12,r12,r10
- vst1.32 {q8},[r1,:128]!
- add r7,r7,r2
- eor r2,r5,r6
- eor r0,r4,r4,ror#5
- add r8,r8,r12
- vld1.32 {q8},[r14,:128]!
- and r2,r2,r4
- eor r12,r0,r4,ror#19
- eor r0,r8,r8,ror#11
- eor r2,r2,r6
- vrev32.8 q1,q1
- add r7,r7,r12,ror#6
- eor r12,r8,r9
- eor r0,r0,r8,ror#20
- add r7,r7,r2
- vadd.i32 q8,q8,q1
- ldr r2,[sp,#20]
- and r3,r3,r12
- add r11,r11,r7
- add r7,r7,r0,ror#2
- eor r3,r3,r9
- add r6,r6,r2
- eor r2,r4,r5
- eor r0,r11,r11,ror#5
- add r7,r7,r3
- and r2,r2,r11
- eor r3,r0,r11,ror#19
- eor r0,r7,r7,ror#11
- eor r2,r2,r5
- add r6,r6,r3,ror#6
- eor r3,r7,r8
- eor r0,r0,r7,ror#20
- add r6,r6,r2
- ldr r2,[sp,#24]
- and r12,r12,r3
- add r10,r10,r6
- add r6,r6,r0,ror#2
- eor r12,r12,r8
- add r5,r5,r2
- eor r2,r11,r4
- eor r0,r10,r10,ror#5
- add r6,r6,r12
- and r2,r2,r10
- eor r12,r0,r10,ror#19
- eor r0,r6,r6,ror#11
- eor r2,r2,r4
- add r5,r5,r12,ror#6
- eor r12,r6,r7
- eor r0,r0,r6,ror#20
- add r5,r5,r2
- ldr r2,[sp,#28]
- and r3,r3,r12
- add r9,r9,r5
- add r5,r5,r0,ror#2
- eor r3,r3,r7
- add r4,r4,r2
- eor r2,r10,r11
- eor r0,r9,r9,ror#5
- add r5,r5,r3
- and r2,r2,r9
- eor r3,r0,r9,ror#19
- eor r0,r5,r5,ror#11
- eor r2,r2,r11
- add r4,r4,r3,ror#6
- eor r3,r5,r6
- eor r0,r0,r5,ror#20
- add r4,r4,r2
- ldr r2,[sp,#32]
- and r12,r12,r3
- add r8,r8,r4
- add r4,r4,r0,ror#2
- eor r12,r12,r6
- vst1.32 {q8},[r1,:128]!
- add r11,r11,r2
- eor r2,r9,r10
- eor r0,r8,r8,ror#5
- add r4,r4,r12
- vld1.32 {q8},[r14,:128]!
- and r2,r2,r8
- eor r12,r0,r8,ror#19
- eor r0,r4,r4,ror#11
- eor r2,r2,r10
- vrev32.8 q2,q2
- add r11,r11,r12,ror#6
- eor r12,r4,r5
- eor r0,r0,r4,ror#20
- add r11,r11,r2
- vadd.i32 q8,q8,q2
- ldr r2,[sp,#36]
- and r3,r3,r12
- add r7,r7,r11
- add r11,r11,r0,ror#2
- eor r3,r3,r5
- add r10,r10,r2
- eor r2,r8,r9
- eor r0,r7,r7,ror#5
- add r11,r11,r3
- and r2,r2,r7
- eor r3,r0,r7,ror#19
- eor r0,r11,r11,ror#11
- eor r2,r2,r9
- add r10,r10,r3,ror#6
- eor r3,r11,r4
- eor r0,r0,r11,ror#20
- add r10,r10,r2
- ldr r2,[sp,#40]
- and r12,r12,r3
- add r6,r6,r10
- add r10,r10,r0,ror#2
- eor r12,r12,r4
- add r9,r9,r2
- eor r2,r7,r8
- eor r0,r6,r6,ror#5
- add r10,r10,r12
- and r2,r2,r6
- eor r12,r0,r6,ror#19
- eor r0,r10,r10,ror#11
- eor r2,r2,r8
- add r9,r9,r12,ror#6
- eor r12,r10,r11
- eor r0,r0,r10,ror#20
- add r9,r9,r2
- ldr r2,[sp,#44]
- and r3,r3,r12
- add r5,r5,r9
- add r9,r9,r0,ror#2
- eor r3,r3,r11
- add r8,r8,r2
- eor r2,r6,r7
- eor r0,r5,r5,ror#5
- add r9,r9,r3
- and r2,r2,r5
- eor r3,r0,r5,ror#19
- eor r0,r9,r9,ror#11
- eor r2,r2,r7
- add r8,r8,r3,ror#6
- eor r3,r9,r10
- eor r0,r0,r9,ror#20
- add r8,r8,r2
- ldr r2,[sp,#48]
- and r12,r12,r3
- add r4,r4,r8
- add r8,r8,r0,ror#2
- eor r12,r12,r10
- vst1.32 {q8},[r1,:128]!
- add r7,r7,r2
- eor r2,r5,r6
- eor r0,r4,r4,ror#5
- add r8,r8,r12
- vld1.32 {q8},[r14,:128]!
- and r2,r2,r4
- eor r12,r0,r4,ror#19
- eor r0,r8,r8,ror#11
- eor r2,r2,r6
- vrev32.8 q3,q3
- add r7,r7,r12,ror#6
- eor r12,r8,r9
- eor r0,r0,r8,ror#20
- add r7,r7,r2
- vadd.i32 q8,q8,q3
- ldr r2,[sp,#52]
- and r3,r3,r12
- add r11,r11,r7
- add r7,r7,r0,ror#2
- eor r3,r3,r9
- add r6,r6,r2
- eor r2,r4,r5
- eor r0,r11,r11,ror#5
- add r7,r7,r3
- and r2,r2,r11
- eor r3,r0,r11,ror#19
- eor r0,r7,r7,ror#11
- eor r2,r2,r5
- add r6,r6,r3,ror#6
- eor r3,r7,r8
- eor r0,r0,r7,ror#20
- add r6,r6,r2
- ldr r2,[sp,#56]
- and r12,r12,r3
- add r10,r10,r6
- add r6,r6,r0,ror#2
- eor r12,r12,r8
- add r5,r5,r2
- eor r2,r11,r4
- eor r0,r10,r10,ror#5
- add r6,r6,r12
- and r2,r2,r10
- eor r12,r0,r10,ror#19
- eor r0,r6,r6,ror#11
- eor r2,r2,r4
- add r5,r5,r12,ror#6
- eor r12,r6,r7
- eor r0,r0,r6,ror#20
- add r5,r5,r2
- ldr r2,[sp,#60]
- and r3,r3,r12
- add r9,r9,r5
- add r5,r5,r0,ror#2
- eor r3,r3,r7
- add r4,r4,r2
- eor r2,r10,r11
- eor r0,r9,r9,ror#5
- add r5,r5,r3
- and r2,r2,r9
- eor r3,r0,r9,ror#19
- eor r0,r5,r5,ror#11
- eor r2,r2,r11
- add r4,r4,r3,ror#6
- eor r3,r5,r6
- eor r0,r0,r5,ror#20
- add r4,r4,r2
- ldr r2,[sp,#64]
- and r12,r12,r3
- add r8,r8,r4
- add r4,r4,r0,ror#2
- eor r12,r12,r6
- vst1.32 {q8},[r1,:128]!
- ldr r0,[r2,#0]
- add r4,r4,r12 @ h+=Maj(a,b,c) from the past
- ldr r12,[r2,#4]
- ldr r3,[r2,#8]
- ldr r1,[r2,#12]
- add r4,r4,r0 @ accumulate
- ldr r0,[r2,#16]
- add r5,r5,r12
- ldr r12,[r2,#20]
- add r6,r6,r3
- ldr r3,[r2,#24]
- add r7,r7,r1
- ldr r1,[r2,#28]
- add r8,r8,r0
- str r4,[r2],#4
- add r9,r9,r12
- str r5,[r2],#4
- add r10,r10,r3
- str r6,[r2],#4
- add r11,r11,r1
- str r7,[r2],#4
- stmia r2,{r8-r11}
-
- ittte ne
- movne r1,sp
- ldrne r2,[sp,#0]
- eorne r12,r12,r12
- ldreq sp,[sp,#76] @ restore original sp
- itt ne
- eorne r3,r5,r6
- bne .L_00_48
-
- ldmia sp!,{r4-r12,pc}
-.size sha256_block_data_order_neon,.-sha256_block_data_order_neon
-#endif
-#if __ARM_MAX_ARCH__>=7 && !defined(__KERNEL__)
-
-# ifdef __thumb2__
-# define INST(a,b,c,d) .byte c,d|0xc,a,b
-# else
-# define INST(a,b,c,d) .byte a,b,c,d
-# endif
-
-.type sha256_block_data_order_armv8,%function
-.align 5
-sha256_block_data_order_armv8:
-.LARMv8:
- vld1.32 {q0,q1},[r0]
-# ifdef __thumb2__
- adr r3,.LARMv8
- sub r3,r3,#.LARMv8-K256
-# else
- adrl r3,K256
-# endif
- add r2,r1,r2,lsl#6 @ len to point at the end of inp
-
-.Loop_v8:
- vld1.8 {q8-q9},[r1]!
- vld1.8 {q10-q11},[r1]!
- vld1.32 {q12},[r3]!
- vrev32.8 q8,q8
- vrev32.8 q9,q9
- vrev32.8 q10,q10
- vrev32.8 q11,q11
- vmov q14,q0 @ offload
- vmov q15,q1
- teq r1,r2
- vld1.32 {q13},[r3]!
- vadd.i32 q12,q12,q8
- INST(0xe2,0x03,0xfa,0xf3) @ sha256su0 q8,q9
- vmov q2,q0
- INST(0x68,0x0c,0x02,0xf3) @ sha256h q0,q1,q12
- INST(0x68,0x2c,0x14,0xf3) @ sha256h2 q1,q2,q12
- INST(0xe6,0x0c,0x64,0xf3) @ sha256su1 q8,q10,q11
- vld1.32 {q12},[r3]!
- vadd.i32 q13,q13,q9
- INST(0xe4,0x23,0xfa,0xf3) @ sha256su0 q9,q10
- vmov q2,q0
- INST(0x6a,0x0c,0x02,0xf3) @ sha256h q0,q1,q13
- INST(0x6a,0x2c,0x14,0xf3) @ sha256h2 q1,q2,q13
- INST(0xe0,0x2c,0x66,0xf3) @ sha256su1 q9,q11,q8
- vld1.32 {q13},[r3]!
- vadd.i32 q12,q12,q10
- INST(0xe6,0x43,0xfa,0xf3) @ sha256su0 q10,q11
- vmov q2,q0
- INST(0x68,0x0c,0x02,0xf3) @ sha256h q0,q1,q12
- INST(0x68,0x2c,0x14,0xf3) @ sha256h2 q1,q2,q12
- INST(0xe2,0x4c,0x60,0xf3) @ sha256su1 q10,q8,q9
- vld1.32 {q12},[r3]!
- vadd.i32 q13,q13,q11
- INST(0xe0,0x63,0xfa,0xf3) @ sha256su0 q11,q8
- vmov q2,q0
- INST(0x6a,0x0c,0x02,0xf3) @ sha256h q0,q1,q13
- INST(0x6a,0x2c,0x14,0xf3) @ sha256h2 q1,q2,q13
- INST(0xe4,0x6c,0x62,0xf3) @ sha256su1 q11,q9,q10
- vld1.32 {q13},[r3]!
- vadd.i32 q12,q12,q8
- INST(0xe2,0x03,0xfa,0xf3) @ sha256su0 q8,q9
- vmov q2,q0
- INST(0x68,0x0c,0x02,0xf3) @ sha256h q0,q1,q12
- INST(0x68,0x2c,0x14,0xf3) @ sha256h2 q1,q2,q12
- INST(0xe6,0x0c,0x64,0xf3) @ sha256su1 q8,q10,q11
- vld1.32 {q12},[r3]!
- vadd.i32 q13,q13,q9
- INST(0xe4,0x23,0xfa,0xf3) @ sha256su0 q9,q10
- vmov q2,q0
- INST(0x6a,0x0c,0x02,0xf3) @ sha256h q0,q1,q13
- INST(0x6a,0x2c,0x14,0xf3) @ sha256h2 q1,q2,q13
- INST(0xe0,0x2c,0x66,0xf3) @ sha256su1 q9,q11,q8
- vld1.32 {q13},[r3]!
- vadd.i32 q12,q12,q10
- INST(0xe6,0x43,0xfa,0xf3) @ sha256su0 q10,q11
- vmov q2,q0
- INST(0x68,0x0c,0x02,0xf3) @ sha256h q0,q1,q12
- INST(0x68,0x2c,0x14,0xf3) @ sha256h2 q1,q2,q12
- INST(0xe2,0x4c,0x60,0xf3) @ sha256su1 q10,q8,q9
- vld1.32 {q12},[r3]!
- vadd.i32 q13,q13,q11
- INST(0xe0,0x63,0xfa,0xf3) @ sha256su0 q11,q8
- vmov q2,q0
- INST(0x6a,0x0c,0x02,0xf3) @ sha256h q0,q1,q13
- INST(0x6a,0x2c,0x14,0xf3) @ sha256h2 q1,q2,q13
- INST(0xe4,0x6c,0x62,0xf3) @ sha256su1 q11,q9,q10
- vld1.32 {q13},[r3]!
- vadd.i32 q12,q12,q8
- INST(0xe2,0x03,0xfa,0xf3) @ sha256su0 q8,q9
- vmov q2,q0
- INST(0x68,0x0c,0x02,0xf3) @ sha256h q0,q1,q12
- INST(0x68,0x2c,0x14,0xf3) @ sha256h2 q1,q2,q12
- INST(0xe6,0x0c,0x64,0xf3) @ sha256su1 q8,q10,q11
- vld1.32 {q12},[r3]!
- vadd.i32 q13,q13,q9
- INST(0xe4,0x23,0xfa,0xf3) @ sha256su0 q9,q10
- vmov q2,q0
- INST(0x6a,0x0c,0x02,0xf3) @ sha256h q0,q1,q13
- INST(0x6a,0x2c,0x14,0xf3) @ sha256h2 q1,q2,q13
- INST(0xe0,0x2c,0x66,0xf3) @ sha256su1 q9,q11,q8
- vld1.32 {q13},[r3]!
- vadd.i32 q12,q12,q10
- INST(0xe6,0x43,0xfa,0xf3) @ sha256su0 q10,q11
- vmov q2,q0
- INST(0x68,0x0c,0x02,0xf3) @ sha256h q0,q1,q12
- INST(0x68,0x2c,0x14,0xf3) @ sha256h2 q1,q2,q12
- INST(0xe2,0x4c,0x60,0xf3) @ sha256su1 q10,q8,q9
- vld1.32 {q12},[r3]!
- vadd.i32 q13,q13,q11
- INST(0xe0,0x63,0xfa,0xf3) @ sha256su0 q11,q8
- vmov q2,q0
- INST(0x6a,0x0c,0x02,0xf3) @ sha256h q0,q1,q13
- INST(0x6a,0x2c,0x14,0xf3) @ sha256h2 q1,q2,q13
- INST(0xe4,0x6c,0x62,0xf3) @ sha256su1 q11,q9,q10
- vld1.32 {q13},[r3]!
- vadd.i32 q12,q12,q8
- vmov q2,q0
- INST(0x68,0x0c,0x02,0xf3) @ sha256h q0,q1,q12
- INST(0x68,0x2c,0x14,0xf3) @ sha256h2 q1,q2,q12
-
- vld1.32 {q12},[r3]!
- vadd.i32 q13,q13,q9
- vmov q2,q0
- INST(0x6a,0x0c,0x02,0xf3) @ sha256h q0,q1,q13
- INST(0x6a,0x2c,0x14,0xf3) @ sha256h2 q1,q2,q13
-
- vld1.32 {q13},[r3]
- vadd.i32 q12,q12,q10
- sub r3,r3,#256-16 @ rewind
- vmov q2,q0
- INST(0x68,0x0c,0x02,0xf3) @ sha256h q0,q1,q12
- INST(0x68,0x2c,0x14,0xf3) @ sha256h2 q1,q2,q12
-
- vadd.i32 q13,q13,q11
- vmov q2,q0
- INST(0x6a,0x0c,0x02,0xf3) @ sha256h q0,q1,q13
- INST(0x6a,0x2c,0x14,0xf3) @ sha256h2 q1,q2,q13
-
- vadd.i32 q0,q0,q14
- vadd.i32 q1,q1,q15
- it ne
- bne .Loop_v8
-
- vst1.32 {q0,q1},[r0]
-
- bx lr @ bx lr
-.size sha256_block_data_order_armv8,.-sha256_block_data_order_armv8
-#endif
-.asciz "SHA256 block transform for ARMv4/NEON/ARMv8, CRYPTOGAMS by <appro@xxxxxxxxxxx>"
-.align 2
-#if __ARM_MAX_ARCH__>=7 && !defined(__KERNEL__)
-.comm OPENSSL_armcap_P,4,4
-#endif
diff --git a/arch/arm/crypto/sha512-core.S_shipped b/arch/arm/crypto/sha512-core.S_shipped
deleted file mode 100644
index 03014624f2ab..000000000000
--- a/arch/arm/crypto/sha512-core.S_shipped
+++ /dev/null
@@ -1,1869 +0,0 @@
-@ SPDX-License-Identifier: GPL-2.0
-
-@ This code is taken from the OpenSSL project but the author (Andy Polyakov)
-@ has relicensed it under the GPLv2. Therefore this program is free software;
-@ you can redistribute it and/or modify it under the terms of the GNU General
-@ Public License version 2 as published by the Free Software Foundation.
-@
-@ The original headers, including the original license headers, are
-@ included below for completeness.
-
-@ ====================================================================
-@ Written by Andy Polyakov <appro@xxxxxxxxxxx> 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 https://www.openssl.org/~appro/cryptogams/.
-@ ====================================================================
-
-@ SHA512 block procedure for ARMv4. September 2007.
-
-@ This code is ~4.5 (four and a half) times faster than code generated
-@ by gcc 3.4 and it spends ~72 clock cycles per byte [on single-issue
-@ Xscale PXA250 core].
-@
-@ July 2010.
-@
-@ Rescheduling for dual-issue pipeline resulted in 6% improvement on
-@ Cortex A8 core and ~40 cycles per processed byte.
-
-@ February 2011.
-@
-@ Profiler-assisted and platform-specific optimization resulted in 7%
-@ improvement on Coxtex A8 core and ~38 cycles per byte.
-
-@ March 2011.
-@
-@ Add NEON implementation. On Cortex A8 it was measured to process
-@ one byte in 23.3 cycles or ~60% faster than integer-only code.
-
-@ August 2012.
-@
-@ Improve NEON performance by 12% on Snapdragon S4. In absolute
-@ terms it's 22.6 cycles per byte, which is disappointing result.
-@ Technical writers asserted that 3-way S4 pipeline can sustain
-@ multiple NEON instructions per cycle, but dual NEON issue could
-@ not be observed, see https://www.openssl.org/~appro/Snapdragon-S4.html
-@ for further details. On side note Cortex-A15 processes one byte in
-@ 16 cycles.
-
-@ Byte order [in]dependence. =========================================
-@
-@ Originally caller was expected to maintain specific *dword* order in
-@ h[0-7], namely with most significant dword at *lower* address, which
-@ was reflected in below two parameters as 0 and 4. Now caller is
-@ expected to maintain native byte order for whole 64-bit values.
-#ifndef __KERNEL__
-# include "arm_arch.h"
-# define VFP_ABI_PUSH vstmdb sp!,{d8-d15}
-# define VFP_ABI_POP vldmia sp!,{d8-d15}
-#else
-# define __ARM_ARCH__ __LINUX_ARM_ARCH__
-# define __ARM_MAX_ARCH__ 7
-# define VFP_ABI_PUSH
-# define VFP_ABI_POP
-#endif
-
-#ifdef __ARMEL__
-# define LO 0
-# define HI 4
-# define WORD64(hi0,lo0,hi1,lo1) .word lo0,hi0, lo1,hi1
-#else
-# define HI 0
-# define LO 4
-# define WORD64(hi0,lo0,hi1,lo1) .word hi0,lo0, hi1,lo1
-#endif
-
-.text
-#if __ARM_ARCH__<7
-.code 32
-#else
-.syntax unified
-# ifdef __thumb2__
-.thumb
-# else
-.code 32
-# endif
-#endif
-
-.type K512,%object
-.align 5
-K512:
-WORD64(0x428a2f98,0xd728ae22, 0x71374491,0x23ef65cd)
-WORD64(0xb5c0fbcf,0xec4d3b2f, 0xe9b5dba5,0x8189dbbc)
-WORD64(0x3956c25b,0xf348b538, 0x59f111f1,0xb605d019)
-WORD64(0x923f82a4,0xaf194f9b, 0xab1c5ed5,0xda6d8118)
-WORD64(0xd807aa98,0xa3030242, 0x12835b01,0x45706fbe)
-WORD64(0x243185be,0x4ee4b28c, 0x550c7dc3,0xd5ffb4e2)
-WORD64(0x72be5d74,0xf27b896f, 0x80deb1fe,0x3b1696b1)
-WORD64(0x9bdc06a7,0x25c71235, 0xc19bf174,0xcf692694)
-WORD64(0xe49b69c1,0x9ef14ad2, 0xefbe4786,0x384f25e3)
-WORD64(0x0fc19dc6,0x8b8cd5b5, 0x240ca1cc,0x77ac9c65)
-WORD64(0x2de92c6f,0x592b0275, 0x4a7484aa,0x6ea6e483)
-WORD64(0x5cb0a9dc,0xbd41fbd4, 0x76f988da,0x831153b5)
-WORD64(0x983e5152,0xee66dfab, 0xa831c66d,0x2db43210)
-WORD64(0xb00327c8,0x98fb213f, 0xbf597fc7,0xbeef0ee4)
-WORD64(0xc6e00bf3,0x3da88fc2, 0xd5a79147,0x930aa725)
-WORD64(0x06ca6351,0xe003826f, 0x14292967,0x0a0e6e70)
-WORD64(0x27b70a85,0x46d22ffc, 0x2e1b2138,0x5c26c926)
-WORD64(0x4d2c6dfc,0x5ac42aed, 0x53380d13,0x9d95b3df)
-WORD64(0x650a7354,0x8baf63de, 0x766a0abb,0x3c77b2a8)
-WORD64(0x81c2c92e,0x47edaee6, 0x92722c85,0x1482353b)
-WORD64(0xa2bfe8a1,0x4cf10364, 0xa81a664b,0xbc423001)
-WORD64(0xc24b8b70,0xd0f89791, 0xc76c51a3,0x0654be30)
-WORD64(0xd192e819,0xd6ef5218, 0xd6990624,0x5565a910)
-WORD64(0xf40e3585,0x5771202a, 0x106aa070,0x32bbd1b8)
-WORD64(0x19a4c116,0xb8d2d0c8, 0x1e376c08,0x5141ab53)
-WORD64(0x2748774c,0xdf8eeb99, 0x34b0bcb5,0xe19b48a8)
-WORD64(0x391c0cb3,0xc5c95a63, 0x4ed8aa4a,0xe3418acb)
-WORD64(0x5b9cca4f,0x7763e373, 0x682e6ff3,0xd6b2b8a3)
-WORD64(0x748f82ee,0x5defb2fc, 0x78a5636f,0x43172f60)
-WORD64(0x84c87814,0xa1f0ab72, 0x8cc70208,0x1a6439ec)
-WORD64(0x90befffa,0x23631e28, 0xa4506ceb,0xde82bde9)
-WORD64(0xbef9a3f7,0xb2c67915, 0xc67178f2,0xe372532b)
-WORD64(0xca273ece,0xea26619c, 0xd186b8c7,0x21c0c207)
-WORD64(0xeada7dd6,0xcde0eb1e, 0xf57d4f7f,0xee6ed178)
-WORD64(0x06f067aa,0x72176fba, 0x0a637dc5,0xa2c898a6)
-WORD64(0x113f9804,0xbef90dae, 0x1b710b35,0x131c471b)
-WORD64(0x28db77f5,0x23047d84, 0x32caab7b,0x40c72493)
-WORD64(0x3c9ebe0a,0x15c9bebc, 0x431d67c4,0x9c100d4c)
-WORD64(0x4cc5d4be,0xcb3e42b6, 0x597f299c,0xfc657e2a)
-WORD64(0x5fcb6fab,0x3ad6faec, 0x6c44198c,0x4a475817)
-.size K512,.-K512
-#if __ARM_MAX_ARCH__>=7 && !defined(__KERNEL__)
-.LOPENSSL_armcap:
-.word OPENSSL_armcap_P-sha512_block_data_order
-.skip 32-4
-#else
-.skip 32
-#endif
-
-.global sha512_block_data_order
-.type sha512_block_data_order,%function
-sha512_block_data_order:
-.Lsha512_block_data_order:
-#if __ARM_ARCH__<7
- sub r3,pc,#8 @ sha512_block_data_order
-#else
- adr r3,.Lsha512_block_data_order
-#endif
-#if __ARM_MAX_ARCH__>=7 && !defined(__KERNEL__)
- ldr r12,.LOPENSSL_armcap
- ldr r12,[r3,r12] @ OPENSSL_armcap_P
- tst r12,#1
- bne .LNEON
-#endif
- add r2,r1,r2,lsl#7 @ len to point at the end of inp
- stmdb sp!,{r4-r12,lr}
- sub r14,r3,#672 @ K512
- sub sp,sp,#9*8
-
- ldr r7,[r0,#32+LO]
- ldr r8,[r0,#32+HI]
- ldr r9, [r0,#48+LO]
- ldr r10, [r0,#48+HI]
- ldr r11, [r0,#56+LO]
- ldr r12, [r0,#56+HI]
-.Loop:
- str r9, [sp,#48+0]
- str r10, [sp,#48+4]
- str r11, [sp,#56+0]
- str r12, [sp,#56+4]
- ldr r5,[r0,#0+LO]
- ldr r6,[r0,#0+HI]
- ldr r3,[r0,#8+LO]
- ldr r4,[r0,#8+HI]
- ldr r9, [r0,#16+LO]
- ldr r10, [r0,#16+HI]
- ldr r11, [r0,#24+LO]
- ldr r12, [r0,#24+HI]
- str r3,[sp,#8+0]
- str r4,[sp,#8+4]
- str r9, [sp,#16+0]
- str r10, [sp,#16+4]
- str r11, [sp,#24+0]
- str r12, [sp,#24+4]
- ldr r3,[r0,#40+LO]
- ldr r4,[r0,#40+HI]
- str r3,[sp,#40+0]
- str r4,[sp,#40+4]
-
-.L00_15:
-#if __ARM_ARCH__<7
- ldrb r3,[r1,#7]
- ldrb r9, [r1,#6]
- ldrb r10, [r1,#5]
- ldrb r11, [r1,#4]
- ldrb r4,[r1,#3]
- ldrb r12, [r1,#2]
- orr r3,r3,r9,lsl#8
- ldrb r9, [r1,#1]
- orr r3,r3,r10,lsl#16
- ldrb r10, [r1],#8
- orr r3,r3,r11,lsl#24
- orr r4,r4,r12,lsl#8
- orr r4,r4,r9,lsl#16
- orr r4,r4,r10,lsl#24
-#else
- ldr r3,[r1,#4]
- ldr r4,[r1],#8
-#ifdef __ARMEL__
- rev r3,r3
- rev r4,r4
-#endif
-#endif
- @ Sigma1(x) (ROTR((x),14) ^ ROTR((x),18) ^ ROTR((x),41))
- @ LO lo>>14^hi<<18 ^ lo>>18^hi<<14 ^ hi>>9^lo<<23
- @ HI hi>>14^lo<<18 ^ hi>>18^lo<<14 ^ lo>>9^hi<<23
- mov r9,r7,lsr#14
- str r3,[sp,#64+0]
- mov r10,r8,lsr#14
- str r4,[sp,#64+4]
- eor r9,r9,r8,lsl#18
- ldr r11,[sp,#56+0] @ h.lo
- eor r10,r10,r7,lsl#18
- ldr r12,[sp,#56+4] @ h.hi
- eor r9,r9,r7,lsr#18
- eor r10,r10,r8,lsr#18
- eor r9,r9,r8,lsl#14
- eor r10,r10,r7,lsl#14
- eor r9,r9,r8,lsr#9
- eor r10,r10,r7,lsr#9
- eor r9,r9,r7,lsl#23
- eor r10,r10,r8,lsl#23 @ Sigma1(e)
- adds r3,r3,r9
- ldr r9,[sp,#40+0] @ f.lo
- adc r4,r4,r10 @ T += Sigma1(e)
- ldr r10,[sp,#40+4] @ f.hi
- adds r3,r3,r11
- ldr r11,[sp,#48+0] @ g.lo
- adc r4,r4,r12 @ T += h
- ldr r12,[sp,#48+4] @ g.hi
-
- eor r9,r9,r11
- str r7,[sp,#32+0]
- eor r10,r10,r12
- str r8,[sp,#32+4]
- and r9,r9,r7
- str r5,[sp,#0+0]
- and r10,r10,r8
- str r6,[sp,#0+4]
- eor r9,r9,r11
- ldr r11,[r14,#LO] @ K[i].lo
- eor r10,r10,r12 @ Ch(e,f,g)
- ldr r12,[r14,#HI] @ K[i].hi
-
- adds r3,r3,r9
- ldr r7,[sp,#24+0] @ d.lo
- adc r4,r4,r10 @ T += Ch(e,f,g)
- ldr r8,[sp,#24+4] @ d.hi
- adds r3,r3,r11
- and r9,r11,#0xff
- adc r4,r4,r12 @ T += K[i]
- adds r7,r7,r3
- ldr r11,[sp,#8+0] @ b.lo
- adc r8,r8,r4 @ d += T
- teq r9,#148
-
- ldr r12,[sp,#16+0] @ c.lo
-#if __ARM_ARCH__>=7
- it eq @ Thumb2 thing, sanity check in ARM
-#endif
- orreq r14,r14,#1
- @ Sigma0(x) (ROTR((x),28) ^ ROTR((x),34) ^ ROTR((x),39))
- @ LO lo>>28^hi<<4 ^ hi>>2^lo<<30 ^ hi>>7^lo<<25
- @ HI hi>>28^lo<<4 ^ lo>>2^hi<<30 ^ lo>>7^hi<<25
- mov r9,r5,lsr#28
- mov r10,r6,lsr#28
- eor r9,r9,r6,lsl#4
- eor r10,r10,r5,lsl#4
- eor r9,r9,r6,lsr#2
- eor r10,r10,r5,lsr#2
- eor r9,r9,r5,lsl#30
- eor r10,r10,r6,lsl#30
- eor r9,r9,r6,lsr#7
- eor r10,r10,r5,lsr#7
- eor r9,r9,r5,lsl#25
- eor r10,r10,r6,lsl#25 @ Sigma0(a)
- adds r3,r3,r9
- and r9,r5,r11
- adc r4,r4,r10 @ T += Sigma0(a)
-
- ldr r10,[sp,#8+4] @ b.hi
- orr r5,r5,r11
- ldr r11,[sp,#16+4] @ c.hi
- and r5,r5,r12
- and r12,r6,r10
- orr r6,r6,r10
- orr r5,r5,r9 @ Maj(a,b,c).lo
- and r6,r6,r11
- adds r5,r5,r3
- orr r6,r6,r12 @ Maj(a,b,c).hi
- sub sp,sp,#8
- adc r6,r6,r4 @ h += T
- tst r14,#1
- add r14,r14,#8
- tst r14,#1
- beq .L00_15
- ldr r9,[sp,#184+0]
- ldr r10,[sp,#184+4]
- bic r14,r14,#1
-.L16_79:
- @ sigma0(x) (ROTR((x),1) ^ ROTR((x),8) ^ ((x)>>7))
- @ LO lo>>1^hi<<31 ^ lo>>8^hi<<24 ^ lo>>7^hi<<25
- @ HI hi>>1^lo<<31 ^ hi>>8^lo<<24 ^ hi>>7
- mov r3,r9,lsr#1
- ldr r11,[sp,#80+0]
- mov r4,r10,lsr#1
- ldr r12,[sp,#80+4]
- eor r3,r3,r10,lsl#31
- eor r4,r4,r9,lsl#31
- eor r3,r3,r9,lsr#8
- eor r4,r4,r10,lsr#8
- eor r3,r3,r10,lsl#24
- eor r4,r4,r9,lsl#24
- eor r3,r3,r9,lsr#7
- eor r4,r4,r10,lsr#7
- eor r3,r3,r10,lsl#25
-
- @ sigma1(x) (ROTR((x),19) ^ ROTR((x),61) ^ ((x)>>6))
- @ LO lo>>19^hi<<13 ^ hi>>29^lo<<3 ^ lo>>6^hi<<26
- @ HI hi>>19^lo<<13 ^ lo>>29^hi<<3 ^ hi>>6
- mov r9,r11,lsr#19
- mov r10,r12,lsr#19
- eor r9,r9,r12,lsl#13
- eor r10,r10,r11,lsl#13
- eor r9,r9,r12,lsr#29
- eor r10,r10,r11,lsr#29
- eor r9,r9,r11,lsl#3
- eor r10,r10,r12,lsl#3
- eor r9,r9,r11,lsr#6
- eor r10,r10,r12,lsr#6
- ldr r11,[sp,#120+0]
- eor r9,r9,r12,lsl#26
-
- ldr r12,[sp,#120+4]
- adds r3,r3,r9
- ldr r9,[sp,#192+0]
- adc r4,r4,r10
-
- ldr r10,[sp,#192+4]
- adds r3,r3,r11
- adc r4,r4,r12
- adds r3,r3,r9
- adc r4,r4,r10
- @ Sigma1(x) (ROTR((x),14) ^ ROTR((x),18) ^ ROTR((x),41))
- @ LO lo>>14^hi<<18 ^ lo>>18^hi<<14 ^ hi>>9^lo<<23
- @ HI hi>>14^lo<<18 ^ hi>>18^lo<<14 ^ lo>>9^hi<<23
- mov r9,r7,lsr#14
- str r3,[sp,#64+0]
- mov r10,r8,lsr#14
- str r4,[sp,#64+4]
- eor r9,r9,r8,lsl#18
- ldr r11,[sp,#56+0] @ h.lo
- eor r10,r10,r7,lsl#18
- ldr r12,[sp,#56+4] @ h.hi
- eor r9,r9,r7,lsr#18
- eor r10,r10,r8,lsr#18
- eor r9,r9,r8,lsl#14
- eor r10,r10,r7,lsl#14
- eor r9,r9,r8,lsr#9
- eor r10,r10,r7,lsr#9
- eor r9,r9,r7,lsl#23
- eor r10,r10,r8,lsl#23 @ Sigma1(e)
- adds r3,r3,r9
- ldr r9,[sp,#40+0] @ f.lo
- adc r4,r4,r10 @ T += Sigma1(e)
- ldr r10,[sp,#40+4] @ f.hi
- adds r3,r3,r11
- ldr r11,[sp,#48+0] @ g.lo
- adc r4,r4,r12 @ T += h
- ldr r12,[sp,#48+4] @ g.hi
-
- eor r9,r9,r11
- str r7,[sp,#32+0]
- eor r10,r10,r12
- str r8,[sp,#32+4]
- and r9,r9,r7
- str r5,[sp,#0+0]
- and r10,r10,r8
- str r6,[sp,#0+4]
- eor r9,r9,r11
- ldr r11,[r14,#LO] @ K[i].lo
- eor r10,r10,r12 @ Ch(e,f,g)
- ldr r12,[r14,#HI] @ K[i].hi
-
- adds r3,r3,r9
- ldr r7,[sp,#24+0] @ d.lo
- adc r4,r4,r10 @ T += Ch(e,f,g)
- ldr r8,[sp,#24+4] @ d.hi
- adds r3,r3,r11
- and r9,r11,#0xff
- adc r4,r4,r12 @ T += K[i]
- adds r7,r7,r3
- ldr r11,[sp,#8+0] @ b.lo
- adc r8,r8,r4 @ d += T
- teq r9,#23
-
- ldr r12,[sp,#16+0] @ c.lo
-#if __ARM_ARCH__>=7
- it eq @ Thumb2 thing, sanity check in ARM
-#endif
- orreq r14,r14,#1
- @ Sigma0(x) (ROTR((x),28) ^ ROTR((x),34) ^ ROTR((x),39))
- @ LO lo>>28^hi<<4 ^ hi>>2^lo<<30 ^ hi>>7^lo<<25
- @ HI hi>>28^lo<<4 ^ lo>>2^hi<<30 ^ lo>>7^hi<<25
- mov r9,r5,lsr#28
- mov r10,r6,lsr#28
- eor r9,r9,r6,lsl#4
- eor r10,r10,r5,lsl#4
- eor r9,r9,r6,lsr#2
- eor r10,r10,r5,lsr#2
- eor r9,r9,r5,lsl#30
- eor r10,r10,r6,lsl#30
- eor r9,r9,r6,lsr#7
- eor r10,r10,r5,lsr#7
- eor r9,r9,r5,lsl#25
- eor r10,r10,r6,lsl#25 @ Sigma0(a)
- adds r3,r3,r9
- and r9,r5,r11
- adc r4,r4,r10 @ T += Sigma0(a)
-
- ldr r10,[sp,#8+4] @ b.hi
- orr r5,r5,r11
- ldr r11,[sp,#16+4] @ c.hi
- and r5,r5,r12
- and r12,r6,r10
- orr r6,r6,r10
- orr r5,r5,r9 @ Maj(a,b,c).lo
- and r6,r6,r11
- adds r5,r5,r3
- orr r6,r6,r12 @ Maj(a,b,c).hi
- sub sp,sp,#8
- adc r6,r6,r4 @ h += T
- tst r14,#1
- add r14,r14,#8
-#if __ARM_ARCH__>=7
- ittt eq @ Thumb2 thing, sanity check in ARM
-#endif
- ldreq r9,[sp,#184+0]
- ldreq r10,[sp,#184+4]
- beq .L16_79
- bic r14,r14,#1
-
- ldr r3,[sp,#8+0]
- ldr r4,[sp,#8+4]
- ldr r9, [r0,#0+LO]
- ldr r10, [r0,#0+HI]
- ldr r11, [r0,#8+LO]
- ldr r12, [r0,#8+HI]
- adds r9,r5,r9
- str r9, [r0,#0+LO]
- adc r10,r6,r10
- str r10, [r0,#0+HI]
- adds r11,r3,r11
- str r11, [r0,#8+LO]
- adc r12,r4,r12
- str r12, [r0,#8+HI]
-
- ldr r5,[sp,#16+0]
- ldr r6,[sp,#16+4]
- ldr r3,[sp,#24+0]
- ldr r4,[sp,#24+4]
- ldr r9, [r0,#16+LO]
- ldr r10, [r0,#16+HI]
- ldr r11, [r0,#24+LO]
- ldr r12, [r0,#24+HI]
- adds r9,r5,r9
- str r9, [r0,#16+LO]
- adc r10,r6,r10
- str r10, [r0,#16+HI]
- adds r11,r3,r11
- str r11, [r0,#24+LO]
- adc r12,r4,r12
- str r12, [r0,#24+HI]
-
- ldr r3,[sp,#40+0]
- ldr r4,[sp,#40+4]
- ldr r9, [r0,#32+LO]
- ldr r10, [r0,#32+HI]
- ldr r11, [r0,#40+LO]
- ldr r12, [r0,#40+HI]
- adds r7,r7,r9
- str r7,[r0,#32+LO]
- adc r8,r8,r10
- str r8,[r0,#32+HI]
- adds r11,r3,r11
- str r11, [r0,#40+LO]
- adc r12,r4,r12
- str r12, [r0,#40+HI]
-
- ldr r5,[sp,#48+0]
- ldr r6,[sp,#48+4]
- ldr r3,[sp,#56+0]
- ldr r4,[sp,#56+4]
- ldr r9, [r0,#48+LO]
- ldr r10, [r0,#48+HI]
- ldr r11, [r0,#56+LO]
- ldr r12, [r0,#56+HI]
- adds r9,r5,r9
- str r9, [r0,#48+LO]
- adc r10,r6,r10
- str r10, [r0,#48+HI]
- adds r11,r3,r11
- str r11, [r0,#56+LO]
- adc r12,r4,r12
- str r12, [r0,#56+HI]
-
- add sp,sp,#640
- sub r14,r14,#640
-
- teq r1,r2
- bne .Loop
-
- add sp,sp,#8*9 @ destroy frame
-#if __ARM_ARCH__>=5
- ldmia sp!,{r4-r12,pc}
-#else
- ldmia sp!,{r4-r12,lr}
- tst lr,#1
- moveq pc,lr @ be binary compatible with V4, yet
- .word 0xe12fff1e @ interoperable with Thumb ISA:-)
-#endif
-.size sha512_block_data_order,.-sha512_block_data_order
-#if __ARM_MAX_ARCH__>=7
-.arch armv7-a
-.fpu neon
-
-.global sha512_block_data_order_neon
-.type sha512_block_data_order_neon,%function
-.align 4
-sha512_block_data_order_neon:
-.LNEON:
- dmb @ errata #451034 on early Cortex A8
- add r2,r1,r2,lsl#7 @ len to point at the end of inp
- VFP_ABI_PUSH
- adr r3,.Lsha512_block_data_order
- sub r3,r3,.Lsha512_block_data_order-K512
- vldmia r0,{d16-d23} @ load context
-.Loop_neon:
- vshr.u64 d24,d20,#14 @ 0
-#if 0<16
- vld1.64 {d0},[r1]! @ handles unaligned
-#endif
- vshr.u64 d25,d20,#18
-#if 0>0
- vadd.i64 d16,d30 @ h+=Maj from the past
-#endif
- vshr.u64 d26,d20,#41
- vld1.64 {d28},[r3,:64]! @ K[i++]
- vsli.64 d24,d20,#50
- vsli.64 d25,d20,#46
- vmov d29,d20
- vsli.64 d26,d20,#23
-#if 0<16 && defined(__ARMEL__)
- vrev64.8 d0,d0
-#endif
- veor d25,d24
- vbsl d29,d21,d22 @ Ch(e,f,g)
- vshr.u64 d24,d16,#28
- veor d26,d25 @ Sigma1(e)
- vadd.i64 d27,d29,d23
- vshr.u64 d25,d16,#34
- vsli.64 d24,d16,#36
- vadd.i64 d27,d26
- vshr.u64 d26,d16,#39
- vadd.i64 d28,d0
- vsli.64 d25,d16,#30
- veor d30,d16,d17
- vsli.64 d26,d16,#25
- veor d23,d24,d25
- vadd.i64 d27,d28
- vbsl d30,d18,d17 @ Maj(a,b,c)
- veor d23,d26 @ Sigma0(a)
- vadd.i64 d19,d27
- vadd.i64 d30,d27
- @ vadd.i64 d23,d30
- vshr.u64 d24,d19,#14 @ 1
-#if 1<16
- vld1.64 {d1},[r1]! @ handles unaligned
-#endif
- vshr.u64 d25,d19,#18
-#if 1>0
- vadd.i64 d23,d30 @ h+=Maj from the past
-#endif
- vshr.u64 d26,d19,#41
- vld1.64 {d28},[r3,:64]! @ K[i++]
- vsli.64 d24,d19,#50
- vsli.64 d25,d19,#46
- vmov d29,d19
- vsli.64 d26,d19,#23
-#if 1<16 && defined(__ARMEL__)
- vrev64.8 d1,d1
-#endif
- veor d25,d24
- vbsl d29,d20,d21 @ Ch(e,f,g)
- vshr.u64 d24,d23,#28
- veor d26,d25 @ Sigma1(e)
- vadd.i64 d27,d29,d22
- vshr.u64 d25,d23,#34
- vsli.64 d24,d23,#36
- vadd.i64 d27,d26
- vshr.u64 d26,d23,#39
- vadd.i64 d28,d1
- vsli.64 d25,d23,#30
- veor d30,d23,d16
- vsli.64 d26,d23,#25
- veor d22,d24,d25
- vadd.i64 d27,d28
- vbsl d30,d17,d16 @ Maj(a,b,c)
- veor d22,d26 @ Sigma0(a)
- vadd.i64 d18,d27
- vadd.i64 d30,d27
- @ vadd.i64 d22,d30
- vshr.u64 d24,d18,#14 @ 2
-#if 2<16
- vld1.64 {d2},[r1]! @ handles unaligned
-#endif
- vshr.u64 d25,d18,#18
-#if 2>0
- vadd.i64 d22,d30 @ h+=Maj from the past
-#endif
- vshr.u64 d26,d18,#41
- vld1.64 {d28},[r3,:64]! @ K[i++]
- vsli.64 d24,d18,#50
- vsli.64 d25,d18,#46
- vmov d29,d18
- vsli.64 d26,d18,#23
-#if 2<16 && defined(__ARMEL__)
- vrev64.8 d2,d2
-#endif
- veor d25,d24
- vbsl d29,d19,d20 @ Ch(e,f,g)
- vshr.u64 d24,d22,#28
- veor d26,d25 @ Sigma1(e)
- vadd.i64 d27,d29,d21
- vshr.u64 d25,d22,#34
- vsli.64 d24,d22,#36
- vadd.i64 d27,d26
- vshr.u64 d26,d22,#39
- vadd.i64 d28,d2
- vsli.64 d25,d22,#30
- veor d30,d22,d23
- vsli.64 d26,d22,#25
- veor d21,d24,d25
- vadd.i64 d27,d28
- vbsl d30,d16,d23 @ Maj(a,b,c)
- veor d21,d26 @ Sigma0(a)
- vadd.i64 d17,d27
- vadd.i64 d30,d27
- @ vadd.i64 d21,d30
- vshr.u64 d24,d17,#14 @ 3
-#if 3<16
- vld1.64 {d3},[r1]! @ handles unaligned
-#endif
- vshr.u64 d25,d17,#18
-#if 3>0
- vadd.i64 d21,d30 @ h+=Maj from the past
-#endif
- vshr.u64 d26,d17,#41
- vld1.64 {d28},[r3,:64]! @ K[i++]
- vsli.64 d24,d17,#50
- vsli.64 d25,d17,#46
- vmov d29,d17
- vsli.64 d26,d17,#23
-#if 3<16 && defined(__ARMEL__)
- vrev64.8 d3,d3
-#endif
- veor d25,d24
- vbsl d29,d18,d19 @ Ch(e,f,g)
- vshr.u64 d24,d21,#28
- veor d26,d25 @ Sigma1(e)
- vadd.i64 d27,d29,d20
- vshr.u64 d25,d21,#34
- vsli.64 d24,d21,#36
- vadd.i64 d27,d26
- vshr.u64 d26,d21,#39
- vadd.i64 d28,d3
- vsli.64 d25,d21,#30
- veor d30,d21,d22
- vsli.64 d26,d21,#25
- veor d20,d24,d25
- vadd.i64 d27,d28
- vbsl d30,d23,d22 @ Maj(a,b,c)
- veor d20,d26 @ Sigma0(a)
- vadd.i64 d16,d27
- vadd.i64 d30,d27
- @ vadd.i64 d20,d30
- vshr.u64 d24,d16,#14 @ 4
-#if 4<16
- vld1.64 {d4},[r1]! @ handles unaligned
-#endif
- vshr.u64 d25,d16,#18
-#if 4>0
- vadd.i64 d20,d30 @ h+=Maj from the past
-#endif
- vshr.u64 d26,d16,#41
- vld1.64 {d28},[r3,:64]! @ K[i++]
- vsli.64 d24,d16,#50
- vsli.64 d25,d16,#46
- vmov d29,d16
- vsli.64 d26,d16,#23
-#if 4<16 && defined(__ARMEL__)
- vrev64.8 d4,d4
-#endif
- veor d25,d24
- vbsl d29,d17,d18 @ Ch(e,f,g)
- vshr.u64 d24,d20,#28
- veor d26,d25 @ Sigma1(e)
- vadd.i64 d27,d29,d19
- vshr.u64 d25,d20,#34
- vsli.64 d24,d20,#36
- vadd.i64 d27,d26
- vshr.u64 d26,d20,#39
- vadd.i64 d28,d4
- vsli.64 d25,d20,#30
- veor d30,d20,d21
- vsli.64 d26,d20,#25
- veor d19,d24,d25
- vadd.i64 d27,d28
- vbsl d30,d22,d21 @ Maj(a,b,c)
- veor d19,d26 @ Sigma0(a)
- vadd.i64 d23,d27
- vadd.i64 d30,d27
- @ vadd.i64 d19,d30
- vshr.u64 d24,d23,#14 @ 5
-#if 5<16
- vld1.64 {d5},[r1]! @ handles unaligned
-#endif
- vshr.u64 d25,d23,#18
-#if 5>0
- vadd.i64 d19,d30 @ h+=Maj from the past
-#endif
- vshr.u64 d26,d23,#41
- vld1.64 {d28},[r3,:64]! @ K[i++]
- vsli.64 d24,d23,#50
- vsli.64 d25,d23,#46
- vmov d29,d23
- vsli.64 d26,d23,#23
-#if 5<16 && defined(__ARMEL__)
- vrev64.8 d5,d5
-#endif
- veor d25,d24
- vbsl d29,d16,d17 @ Ch(e,f,g)
- vshr.u64 d24,d19,#28
- veor d26,d25 @ Sigma1(e)
- vadd.i64 d27,d29,d18
- vshr.u64 d25,d19,#34
- vsli.64 d24,d19,#36
- vadd.i64 d27,d26
- vshr.u64 d26,d19,#39
- vadd.i64 d28,d5
- vsli.64 d25,d19,#30
- veor d30,d19,d20
- vsli.64 d26,d19,#25
- veor d18,d24,d25
- vadd.i64 d27,d28
- vbsl d30,d21,d20 @ Maj(a,b,c)
- veor d18,d26 @ Sigma0(a)
- vadd.i64 d22,d27
- vadd.i64 d30,d27
- @ vadd.i64 d18,d30
- vshr.u64 d24,d22,#14 @ 6
-#if 6<16
- vld1.64 {d6},[r1]! @ handles unaligned
-#endif
- vshr.u64 d25,d22,#18
-#if 6>0
- vadd.i64 d18,d30 @ h+=Maj from the past
-#endif
- vshr.u64 d26,d22,#41
- vld1.64 {d28},[r3,:64]! @ K[i++]
- vsli.64 d24,d22,#50
- vsli.64 d25,d22,#46
- vmov d29,d22
- vsli.64 d26,d22,#23
-#if 6<16 && defined(__ARMEL__)
- vrev64.8 d6,d6
-#endif
- veor d25,d24
- vbsl d29,d23,d16 @ Ch(e,f,g)
- vshr.u64 d24,d18,#28
- veor d26,d25 @ Sigma1(e)
- vadd.i64 d27,d29,d17
- vshr.u64 d25,d18,#34
- vsli.64 d24,d18,#36
- vadd.i64 d27,d26
- vshr.u64 d26,d18,#39
- vadd.i64 d28,d6
- vsli.64 d25,d18,#30
- veor d30,d18,d19
- vsli.64 d26,d18,#25
- veor d17,d24,d25
- vadd.i64 d27,d28
- vbsl d30,d20,d19 @ Maj(a,b,c)
- veor d17,d26 @ Sigma0(a)
- vadd.i64 d21,d27
- vadd.i64 d30,d27
- @ vadd.i64 d17,d30
- vshr.u64 d24,d21,#14 @ 7
-#if 7<16
- vld1.64 {d7},[r1]! @ handles unaligned
-#endif
- vshr.u64 d25,d21,#18
-#if 7>0
- vadd.i64 d17,d30 @ h+=Maj from the past
-#endif
- vshr.u64 d26,d21,#41
- vld1.64 {d28},[r3,:64]! @ K[i++]
- vsli.64 d24,d21,#50
- vsli.64 d25,d21,#46
- vmov d29,d21
- vsli.64 d26,d21,#23
-#if 7<16 && defined(__ARMEL__)
- vrev64.8 d7,d7
-#endif
- veor d25,d24
- vbsl d29,d22,d23 @ Ch(e,f,g)
- vshr.u64 d24,d17,#28
- veor d26,d25 @ Sigma1(e)
- vadd.i64 d27,d29,d16
- vshr.u64 d25,d17,#34
- vsli.64 d24,d17,#36
- vadd.i64 d27,d26
- vshr.u64 d26,d17,#39
- vadd.i64 d28,d7
- vsli.64 d25,d17,#30
- veor d30,d17,d18
- vsli.64 d26,d17,#25
- veor d16,d24,d25
- vadd.i64 d27,d28
- vbsl d30,d19,d18 @ Maj(a,b,c)
- veor d16,d26 @ Sigma0(a)
- vadd.i64 d20,d27
- vadd.i64 d30,d27
- @ vadd.i64 d16,d30
- vshr.u64 d24,d20,#14 @ 8
-#if 8<16
- vld1.64 {d8},[r1]! @ handles unaligned
-#endif
- vshr.u64 d25,d20,#18
-#if 8>0
- vadd.i64 d16,d30 @ h+=Maj from the past
-#endif
- vshr.u64 d26,d20,#41
- vld1.64 {d28},[r3,:64]! @ K[i++]
- vsli.64 d24,d20,#50
- vsli.64 d25,d20,#46
- vmov d29,d20
- vsli.64 d26,d20,#23
-#if 8<16 && defined(__ARMEL__)
- vrev64.8 d8,d8
-#endif
- veor d25,d24
- vbsl d29,d21,d22 @ Ch(e,f,g)
- vshr.u64 d24,d16,#28
- veor d26,d25 @ Sigma1(e)
- vadd.i64 d27,d29,d23
- vshr.u64 d25,d16,#34
- vsli.64 d24,d16,#36
- vadd.i64 d27,d26
- vshr.u64 d26,d16,#39
- vadd.i64 d28,d8
- vsli.64 d25,d16,#30
- veor d30,d16,d17
- vsli.64 d26,d16,#25
- veor d23,d24,d25
- vadd.i64 d27,d28
- vbsl d30,d18,d17 @ Maj(a,b,c)
- veor d23,d26 @ Sigma0(a)
- vadd.i64 d19,d27
- vadd.i64 d30,d27
- @ vadd.i64 d23,d30
- vshr.u64 d24,d19,#14 @ 9
-#if 9<16
- vld1.64 {d9},[r1]! @ handles unaligned
-#endif
- vshr.u64 d25,d19,#18
-#if 9>0
- vadd.i64 d23,d30 @ h+=Maj from the past
-#endif
- vshr.u64 d26,d19,#41
- vld1.64 {d28},[r3,:64]! @ K[i++]
- vsli.64 d24,d19,#50
- vsli.64 d25,d19,#46
- vmov d29,d19
- vsli.64 d26,d19,#23
-#if 9<16 && defined(__ARMEL__)
- vrev64.8 d9,d9
-#endif
- veor d25,d24
- vbsl d29,d20,d21 @ Ch(e,f,g)
- vshr.u64 d24,d23,#28
- veor d26,d25 @ Sigma1(e)
- vadd.i64 d27,d29,d22
- vshr.u64 d25,d23,#34
- vsli.64 d24,d23,#36
- vadd.i64 d27,d26
- vshr.u64 d26,d23,#39
- vadd.i64 d28,d9
- vsli.64 d25,d23,#30
- veor d30,d23,d16
- vsli.64 d26,d23,#25
- veor d22,d24,d25
- vadd.i64 d27,d28
- vbsl d30,d17,d16 @ Maj(a,b,c)
- veor d22,d26 @ Sigma0(a)
- vadd.i64 d18,d27
- vadd.i64 d30,d27
- @ vadd.i64 d22,d30
- vshr.u64 d24,d18,#14 @ 10
-#if 10<16
- vld1.64 {d10},[r1]! @ handles unaligned
-#endif
- vshr.u64 d25,d18,#18
-#if 10>0
- vadd.i64 d22,d30 @ h+=Maj from the past
-#endif
- vshr.u64 d26,d18,#41
- vld1.64 {d28},[r3,:64]! @ K[i++]
- vsli.64 d24,d18,#50
- vsli.64 d25,d18,#46
- vmov d29,d18
- vsli.64 d26,d18,#23
-#if 10<16 && defined(__ARMEL__)
- vrev64.8 d10,d10
-#endif
- veor d25,d24
- vbsl d29,d19,d20 @ Ch(e,f,g)
- vshr.u64 d24,d22,#28
- veor d26,d25 @ Sigma1(e)
- vadd.i64 d27,d29,d21
- vshr.u64 d25,d22,#34
- vsli.64 d24,d22,#36
- vadd.i64 d27,d26
- vshr.u64 d26,d22,#39
- vadd.i64 d28,d10
- vsli.64 d25,d22,#30
- veor d30,d22,d23
- vsli.64 d26,d22,#25
- veor d21,d24,d25
- vadd.i64 d27,d28
- vbsl d30,d16,d23 @ Maj(a,b,c)
- veor d21,d26 @ Sigma0(a)
- vadd.i64 d17,d27
- vadd.i64 d30,d27
- @ vadd.i64 d21,d30
- vshr.u64 d24,d17,#14 @ 11
-#if 11<16
- vld1.64 {d11},[r1]! @ handles unaligned
-#endif
- vshr.u64 d25,d17,#18
-#if 11>0
- vadd.i64 d21,d30 @ h+=Maj from the past
-#endif
- vshr.u64 d26,d17,#41
- vld1.64 {d28},[r3,:64]! @ K[i++]
- vsli.64 d24,d17,#50
- vsli.64 d25,d17,#46
- vmov d29,d17
- vsli.64 d26,d17,#23
-#if 11<16 && defined(__ARMEL__)
- vrev64.8 d11,d11
-#endif
- veor d25,d24
- vbsl d29,d18,d19 @ Ch(e,f,g)
- vshr.u64 d24,d21,#28
- veor d26,d25 @ Sigma1(e)
- vadd.i64 d27,d29,d20
- vshr.u64 d25,d21,#34
- vsli.64 d24,d21,#36
- vadd.i64 d27,d26
- vshr.u64 d26,d21,#39
- vadd.i64 d28,d11
- vsli.64 d25,d21,#30
- veor d30,d21,d22
- vsli.64 d26,d21,#25
- veor d20,d24,d25
- vadd.i64 d27,d28
- vbsl d30,d23,d22 @ Maj(a,b,c)
- veor d20,d26 @ Sigma0(a)
- vadd.i64 d16,d27
- vadd.i64 d30,d27
- @ vadd.i64 d20,d30
- vshr.u64 d24,d16,#14 @ 12
-#if 12<16
- vld1.64 {d12},[r1]! @ handles unaligned
-#endif
- vshr.u64 d25,d16,#18
-#if 12>0
- vadd.i64 d20,d30 @ h+=Maj from the past
-#endif
- vshr.u64 d26,d16,#41
- vld1.64 {d28},[r3,:64]! @ K[i++]
- vsli.64 d24,d16,#50
- vsli.64 d25,d16,#46
- vmov d29,d16
- vsli.64 d26,d16,#23
-#if 12<16 && defined(__ARMEL__)
- vrev64.8 d12,d12
-#endif
- veor d25,d24
- vbsl d29,d17,d18 @ Ch(e,f,g)
- vshr.u64 d24,d20,#28
- veor d26,d25 @ Sigma1(e)
- vadd.i64 d27,d29,d19
- vshr.u64 d25,d20,#34
- vsli.64 d24,d20,#36
- vadd.i64 d27,d26
- vshr.u64 d26,d20,#39
- vadd.i64 d28,d12
- vsli.64 d25,d20,#30
- veor d30,d20,d21
- vsli.64 d26,d20,#25
- veor d19,d24,d25
- vadd.i64 d27,d28
- vbsl d30,d22,d21 @ Maj(a,b,c)
- veor d19,d26 @ Sigma0(a)
- vadd.i64 d23,d27
- vadd.i64 d30,d27
- @ vadd.i64 d19,d30
- vshr.u64 d24,d23,#14 @ 13
-#if 13<16
- vld1.64 {d13},[r1]! @ handles unaligned
-#endif
- vshr.u64 d25,d23,#18
-#if 13>0
- vadd.i64 d19,d30 @ h+=Maj from the past
-#endif
- vshr.u64 d26,d23,#41
- vld1.64 {d28},[r3,:64]! @ K[i++]
- vsli.64 d24,d23,#50
- vsli.64 d25,d23,#46
- vmov d29,d23
- vsli.64 d26,d23,#23
-#if 13<16 && defined(__ARMEL__)
- vrev64.8 d13,d13
-#endif
- veor d25,d24
- vbsl d29,d16,d17 @ Ch(e,f,g)
- vshr.u64 d24,d19,#28
- veor d26,d25 @ Sigma1(e)
- vadd.i64 d27,d29,d18
- vshr.u64 d25,d19,#34
- vsli.64 d24,d19,#36
- vadd.i64 d27,d26
- vshr.u64 d26,d19,#39
- vadd.i64 d28,d13
- vsli.64 d25,d19,#30
- veor d30,d19,d20
- vsli.64 d26,d19,#25
- veor d18,d24,d25
- vadd.i64 d27,d28
- vbsl d30,d21,d20 @ Maj(a,b,c)
- veor d18,d26 @ Sigma0(a)
- vadd.i64 d22,d27
- vadd.i64 d30,d27
- @ vadd.i64 d18,d30
- vshr.u64 d24,d22,#14 @ 14
-#if 14<16
- vld1.64 {d14},[r1]! @ handles unaligned
-#endif
- vshr.u64 d25,d22,#18
-#if 14>0
- vadd.i64 d18,d30 @ h+=Maj from the past
-#endif
- vshr.u64 d26,d22,#41
- vld1.64 {d28},[r3,:64]! @ K[i++]
- vsli.64 d24,d22,#50
- vsli.64 d25,d22,#46
- vmov d29,d22
- vsli.64 d26,d22,#23
-#if 14<16 && defined(__ARMEL__)
- vrev64.8 d14,d14
-#endif
- veor d25,d24
- vbsl d29,d23,d16 @ Ch(e,f,g)
- vshr.u64 d24,d18,#28
- veor d26,d25 @ Sigma1(e)
- vadd.i64 d27,d29,d17
- vshr.u64 d25,d18,#34
- vsli.64 d24,d18,#36
- vadd.i64 d27,d26
- vshr.u64 d26,d18,#39
- vadd.i64 d28,d14
- vsli.64 d25,d18,#30
- veor d30,d18,d19
- vsli.64 d26,d18,#25
- veor d17,d24,d25
- vadd.i64 d27,d28
- vbsl d30,d20,d19 @ Maj(a,b,c)
- veor d17,d26 @ Sigma0(a)
- vadd.i64 d21,d27
- vadd.i64 d30,d27
- @ vadd.i64 d17,d30
- vshr.u64 d24,d21,#14 @ 15
-#if 15<16
- vld1.64 {d15},[r1]! @ handles unaligned
-#endif
- vshr.u64 d25,d21,#18
-#if 15>0
- vadd.i64 d17,d30 @ h+=Maj from the past
-#endif
- vshr.u64 d26,d21,#41
- vld1.64 {d28},[r3,:64]! @ K[i++]
- vsli.64 d24,d21,#50
- vsli.64 d25,d21,#46
- vmov d29,d21
- vsli.64 d26,d21,#23
-#if 15<16 && defined(__ARMEL__)
- vrev64.8 d15,d15
-#endif
- veor d25,d24
- vbsl d29,d22,d23 @ Ch(e,f,g)
- vshr.u64 d24,d17,#28
- veor d26,d25 @ Sigma1(e)
- vadd.i64 d27,d29,d16
- vshr.u64 d25,d17,#34
- vsli.64 d24,d17,#36
- vadd.i64 d27,d26
- vshr.u64 d26,d17,#39
- vadd.i64 d28,d15
- vsli.64 d25,d17,#30
- veor d30,d17,d18
- vsli.64 d26,d17,#25
- veor d16,d24,d25
- vadd.i64 d27,d28
- vbsl d30,d19,d18 @ Maj(a,b,c)
- veor d16,d26 @ Sigma0(a)
- vadd.i64 d20,d27
- vadd.i64 d30,d27
- @ vadd.i64 d16,d30
- mov r12,#4
-.L16_79_neon:
- subs r12,#1
- vshr.u64 q12,q7,#19
- vshr.u64 q13,q7,#61
- vadd.i64 d16,d30 @ h+=Maj from the past
- vshr.u64 q15,q7,#6
- vsli.64 q12,q7,#45
- vext.8 q14,q0,q1,#8 @ X[i+1]
- vsli.64 q13,q7,#3
- veor q15,q12
- vshr.u64 q12,q14,#1
- veor q15,q13 @ sigma1(X[i+14])
- vshr.u64 q13,q14,#8
- vadd.i64 q0,q15
- vshr.u64 q15,q14,#7
- vsli.64 q12,q14,#63
- vsli.64 q13,q14,#56
- vext.8 q14,q4,q5,#8 @ X[i+9]
- veor q15,q12
- vshr.u64 d24,d20,#14 @ from NEON_00_15
- vadd.i64 q0,q14
- vshr.u64 d25,d20,#18 @ from NEON_00_15
- veor q15,q13 @ sigma0(X[i+1])
- vshr.u64 d26,d20,#41 @ from NEON_00_15
- vadd.i64 q0,q15
- vld1.64 {d28},[r3,:64]! @ K[i++]
- vsli.64 d24,d20,#50
- vsli.64 d25,d20,#46
- vmov d29,d20
- vsli.64 d26,d20,#23
-#if 16<16 && defined(__ARMEL__)
- vrev64.8 ,
-#endif
- veor d25,d24
- vbsl d29,d21,d22 @ Ch(e,f,g)
- vshr.u64 d24,d16,#28
- veor d26,d25 @ Sigma1(e)
- vadd.i64 d27,d29,d23
- vshr.u64 d25,d16,#34
- vsli.64 d24,d16,#36
- vadd.i64 d27,d26
- vshr.u64 d26,d16,#39
- vadd.i64 d28,d0
- vsli.64 d25,d16,#30
- veor d30,d16,d17
- vsli.64 d26,d16,#25
- veor d23,d24,d25
- vadd.i64 d27,d28
- vbsl d30,d18,d17 @ Maj(a,b,c)
- veor d23,d26 @ Sigma0(a)
- vadd.i64 d19,d27
- vadd.i64 d30,d27
- @ vadd.i64 d23,d30
- vshr.u64 d24,d19,#14 @ 17
-#if 17<16
- vld1.64 {d1},[r1]! @ handles unaligned
-#endif
- vshr.u64 d25,d19,#18
-#if 17>0
- vadd.i64 d23,d30 @ h+=Maj from the past
-#endif
- vshr.u64 d26,d19,#41
- vld1.64 {d28},[r3,:64]! @ K[i++]
- vsli.64 d24,d19,#50
- vsli.64 d25,d19,#46
- vmov d29,d19
- vsli.64 d26,d19,#23
-#if 17<16 && defined(__ARMEL__)
- vrev64.8 ,
-#endif
- veor d25,d24
- vbsl d29,d20,d21 @ Ch(e,f,g)
- vshr.u64 d24,d23,#28
- veor d26,d25 @ Sigma1(e)
- vadd.i64 d27,d29,d22
- vshr.u64 d25,d23,#34
- vsli.64 d24,d23,#36
- vadd.i64 d27,d26
- vshr.u64 d26,d23,#39
- vadd.i64 d28,d1
- vsli.64 d25,d23,#30
- veor d30,d23,d16
- vsli.64 d26,d23,#25
- veor d22,d24,d25
- vadd.i64 d27,d28
- vbsl d30,d17,d16 @ Maj(a,b,c)
- veor d22,d26 @ Sigma0(a)
- vadd.i64 d18,d27
- vadd.i64 d30,d27
- @ vadd.i64 d22,d30
- vshr.u64 q12,q0,#19
- vshr.u64 q13,q0,#61
- vadd.i64 d22,d30 @ h+=Maj from the past
- vshr.u64 q15,q0,#6
- vsli.64 q12,q0,#45
- vext.8 q14,q1,q2,#8 @ X[i+1]
- vsli.64 q13,q0,#3
- veor q15,q12
- vshr.u64 q12,q14,#1
- veor q15,q13 @ sigma1(X[i+14])
- vshr.u64 q13,q14,#8
- vadd.i64 q1,q15
- vshr.u64 q15,q14,#7
- vsli.64 q12,q14,#63
- vsli.64 q13,q14,#56
- vext.8 q14,q5,q6,#8 @ X[i+9]
- veor q15,q12
- vshr.u64 d24,d18,#14 @ from NEON_00_15
- vadd.i64 q1,q14
- vshr.u64 d25,d18,#18 @ from NEON_00_15
- veor q15,q13 @ sigma0(X[i+1])
- vshr.u64 d26,d18,#41 @ from NEON_00_15
- vadd.i64 q1,q15
- vld1.64 {d28},[r3,:64]! @ K[i++]
- vsli.64 d24,d18,#50
- vsli.64 d25,d18,#46
- vmov d29,d18
- vsli.64 d26,d18,#23
-#if 18<16 && defined(__ARMEL__)
- vrev64.8 ,
-#endif
- veor d25,d24
- vbsl d29,d19,d20 @ Ch(e,f,g)
- vshr.u64 d24,d22,#28
- veor d26,d25 @ Sigma1(e)
- vadd.i64 d27,d29,d21
- vshr.u64 d25,d22,#34
- vsli.64 d24,d22,#36
- vadd.i64 d27,d26
- vshr.u64 d26,d22,#39
- vadd.i64 d28,d2
- vsli.64 d25,d22,#30
- veor d30,d22,d23
- vsli.64 d26,d22,#25
- veor d21,d24,d25
- vadd.i64 d27,d28
- vbsl d30,d16,d23 @ Maj(a,b,c)
- veor d21,d26 @ Sigma0(a)
- vadd.i64 d17,d27
- vadd.i64 d30,d27
- @ vadd.i64 d21,d30
- vshr.u64 d24,d17,#14 @ 19
-#if 19<16
- vld1.64 {d3},[r1]! @ handles unaligned
-#endif
- vshr.u64 d25,d17,#18
-#if 19>0
- vadd.i64 d21,d30 @ h+=Maj from the past
-#endif
- vshr.u64 d26,d17,#41
- vld1.64 {d28},[r3,:64]! @ K[i++]
- vsli.64 d24,d17,#50
- vsli.64 d25,d17,#46
- vmov d29,d17
- vsli.64 d26,d17,#23
-#if 19<16 && defined(__ARMEL__)
- vrev64.8 ,
-#endif
- veor d25,d24
- vbsl d29,d18,d19 @ Ch(e,f,g)
- vshr.u64 d24,d21,#28
- veor d26,d25 @ Sigma1(e)
- vadd.i64 d27,d29,d20
- vshr.u64 d25,d21,#34
- vsli.64 d24,d21,#36
- vadd.i64 d27,d26
- vshr.u64 d26,d21,#39
- vadd.i64 d28,d3
- vsli.64 d25,d21,#30
- veor d30,d21,d22
- vsli.64 d26,d21,#25
- veor d20,d24,d25
- vadd.i64 d27,d28
- vbsl d30,d23,d22 @ Maj(a,b,c)
- veor d20,d26 @ Sigma0(a)
- vadd.i64 d16,d27
- vadd.i64 d30,d27
- @ vadd.i64 d20,d30
- vshr.u64 q12,q1,#19
- vshr.u64 q13,q1,#61
- vadd.i64 d20,d30 @ h+=Maj from the past
- vshr.u64 q15,q1,#6
- vsli.64 q12,q1,#45
- vext.8 q14,q2,q3,#8 @ X[i+1]
- vsli.64 q13,q1,#3
- veor q15,q12
- vshr.u64 q12,q14,#1
- veor q15,q13 @ sigma1(X[i+14])
- vshr.u64 q13,q14,#8
- vadd.i64 q2,q15
- vshr.u64 q15,q14,#7
- vsli.64 q12,q14,#63
- vsli.64 q13,q14,#56
- vext.8 q14,q6,q7,#8 @ X[i+9]
- veor q15,q12
- vshr.u64 d24,d16,#14 @ from NEON_00_15
- vadd.i64 q2,q14
- vshr.u64 d25,d16,#18 @ from NEON_00_15
- veor q15,q13 @ sigma0(X[i+1])
- vshr.u64 d26,d16,#41 @ from NEON_00_15
- vadd.i64 q2,q15
- vld1.64 {d28},[r3,:64]! @ K[i++]
- vsli.64 d24,d16,#50
- vsli.64 d25,d16,#46
- vmov d29,d16
- vsli.64 d26,d16,#23
-#if 20<16 && defined(__ARMEL__)
- vrev64.8 ,
-#endif
- veor d25,d24
- vbsl d29,d17,d18 @ Ch(e,f,g)
- vshr.u64 d24,d20,#28
- veor d26,d25 @ Sigma1(e)
- vadd.i64 d27,d29,d19
- vshr.u64 d25,d20,#34
- vsli.64 d24,d20,#36
- vadd.i64 d27,d26
- vshr.u64 d26,d20,#39
- vadd.i64 d28,d4
- vsli.64 d25,d20,#30
- veor d30,d20,d21
- vsli.64 d26,d20,#25
- veor d19,d24,d25
- vadd.i64 d27,d28
- vbsl d30,d22,d21 @ Maj(a,b,c)
- veor d19,d26 @ Sigma0(a)
- vadd.i64 d23,d27
- vadd.i64 d30,d27
- @ vadd.i64 d19,d30
- vshr.u64 d24,d23,#14 @ 21
-#if 21<16
- vld1.64 {d5},[r1]! @ handles unaligned
-#endif
- vshr.u64 d25,d23,#18
-#if 21>0
- vadd.i64 d19,d30 @ h+=Maj from the past
-#endif
- vshr.u64 d26,d23,#41
- vld1.64 {d28},[r3,:64]! @ K[i++]
- vsli.64 d24,d23,#50
- vsli.64 d25,d23,#46
- vmov d29,d23
- vsli.64 d26,d23,#23
-#if 21<16 && defined(__ARMEL__)
- vrev64.8 ,
-#endif
- veor d25,d24
- vbsl d29,d16,d17 @ Ch(e,f,g)
- vshr.u64 d24,d19,#28
- veor d26,d25 @ Sigma1(e)
- vadd.i64 d27,d29,d18
- vshr.u64 d25,d19,#34
- vsli.64 d24,d19,#36
- vadd.i64 d27,d26
- vshr.u64 d26,d19,#39
- vadd.i64 d28,d5
- vsli.64 d25,d19,#30
- veor d30,d19,d20
- vsli.64 d26,d19,#25
- veor d18,d24,d25
- vadd.i64 d27,d28
- vbsl d30,d21,d20 @ Maj(a,b,c)
- veor d18,d26 @ Sigma0(a)
- vadd.i64 d22,d27
- vadd.i64 d30,d27
- @ vadd.i64 d18,d30
- vshr.u64 q12,q2,#19
- vshr.u64 q13,q2,#61
- vadd.i64 d18,d30 @ h+=Maj from the past
- vshr.u64 q15,q2,#6
- vsli.64 q12,q2,#45
- vext.8 q14,q3,q4,#8 @ X[i+1]
- vsli.64 q13,q2,#3
- veor q15,q12
- vshr.u64 q12,q14,#1
- veor q15,q13 @ sigma1(X[i+14])
- vshr.u64 q13,q14,#8
- vadd.i64 q3,q15
- vshr.u64 q15,q14,#7
- vsli.64 q12,q14,#63
- vsli.64 q13,q14,#56
- vext.8 q14,q7,q0,#8 @ X[i+9]
- veor q15,q12
- vshr.u64 d24,d22,#14 @ from NEON_00_15
- vadd.i64 q3,q14
- vshr.u64 d25,d22,#18 @ from NEON_00_15
- veor q15,q13 @ sigma0(X[i+1])
- vshr.u64 d26,d22,#41 @ from NEON_00_15
- vadd.i64 q3,q15
- vld1.64 {d28},[r3,:64]! @ K[i++]
- vsli.64 d24,d22,#50
- vsli.64 d25,d22,#46
- vmov d29,d22
- vsli.64 d26,d22,#23
-#if 22<16 && defined(__ARMEL__)
- vrev64.8 ,
-#endif
- veor d25,d24
- vbsl d29,d23,d16 @ Ch(e,f,g)
- vshr.u64 d24,d18,#28
- veor d26,d25 @ Sigma1(e)
- vadd.i64 d27,d29,d17
- vshr.u64 d25,d18,#34
- vsli.64 d24,d18,#36
- vadd.i64 d27,d26
- vshr.u64 d26,d18,#39
- vadd.i64 d28,d6
- vsli.64 d25,d18,#30
- veor d30,d18,d19
- vsli.64 d26,d18,#25
- veor d17,d24,d25
- vadd.i64 d27,d28
- vbsl d30,d20,d19 @ Maj(a,b,c)
- veor d17,d26 @ Sigma0(a)
- vadd.i64 d21,d27
- vadd.i64 d30,d27
- @ vadd.i64 d17,d30
- vshr.u64 d24,d21,#14 @ 23
-#if 23<16
- vld1.64 {d7},[r1]! @ handles unaligned
-#endif
- vshr.u64 d25,d21,#18
-#if 23>0
- vadd.i64 d17,d30 @ h+=Maj from the past
-#endif
- vshr.u64 d26,d21,#41
- vld1.64 {d28},[r3,:64]! @ K[i++]
- vsli.64 d24,d21,#50
- vsli.64 d25,d21,#46
- vmov d29,d21
- vsli.64 d26,d21,#23
-#if 23<16 && defined(__ARMEL__)
- vrev64.8 ,
-#endif
- veor d25,d24
- vbsl d29,d22,d23 @ Ch(e,f,g)
- vshr.u64 d24,d17,#28
- veor d26,d25 @ Sigma1(e)
- vadd.i64 d27,d29,d16
- vshr.u64 d25,d17,#34
- vsli.64 d24,d17,#36
- vadd.i64 d27,d26
- vshr.u64 d26,d17,#39
- vadd.i64 d28,d7
- vsli.64 d25,d17,#30
- veor d30,d17,d18
- vsli.64 d26,d17,#25
- veor d16,d24,d25
- vadd.i64 d27,d28
- vbsl d30,d19,d18 @ Maj(a,b,c)
- veor d16,d26 @ Sigma0(a)
- vadd.i64 d20,d27
- vadd.i64 d30,d27
- @ vadd.i64 d16,d30
- vshr.u64 q12,q3,#19
- vshr.u64 q13,q3,#61
- vadd.i64 d16,d30 @ h+=Maj from the past
- vshr.u64 q15,q3,#6
- vsli.64 q12,q3,#45
- vext.8 q14,q4,q5,#8 @ X[i+1]
- vsli.64 q13,q3,#3
- veor q15,q12
- vshr.u64 q12,q14,#1
- veor q15,q13 @ sigma1(X[i+14])
- vshr.u64 q13,q14,#8
- vadd.i64 q4,q15
- vshr.u64 q15,q14,#7
- vsli.64 q12,q14,#63
- vsli.64 q13,q14,#56
- vext.8 q14,q0,q1,#8 @ X[i+9]
- veor q15,q12
- vshr.u64 d24,d20,#14 @ from NEON_00_15
- vadd.i64 q4,q14
- vshr.u64 d25,d20,#18 @ from NEON_00_15
- veor q15,q13 @ sigma0(X[i+1])
- vshr.u64 d26,d20,#41 @ from NEON_00_15
- vadd.i64 q4,q15
- vld1.64 {d28},[r3,:64]! @ K[i++]
- vsli.64 d24,d20,#50
- vsli.64 d25,d20,#46
- vmov d29,d20
- vsli.64 d26,d20,#23
-#if 24<16 && defined(__ARMEL__)
- vrev64.8 ,
-#endif
- veor d25,d24
- vbsl d29,d21,d22 @ Ch(e,f,g)
- vshr.u64 d24,d16,#28
- veor d26,d25 @ Sigma1(e)
- vadd.i64 d27,d29,d23
- vshr.u64 d25,d16,#34
- vsli.64 d24,d16,#36
- vadd.i64 d27,d26
- vshr.u64 d26,d16,#39
- vadd.i64 d28,d8
- vsli.64 d25,d16,#30
- veor d30,d16,d17
- vsli.64 d26,d16,#25
- veor d23,d24,d25
- vadd.i64 d27,d28
- vbsl d30,d18,d17 @ Maj(a,b,c)
- veor d23,d26 @ Sigma0(a)
- vadd.i64 d19,d27
- vadd.i64 d30,d27
- @ vadd.i64 d23,d30
- vshr.u64 d24,d19,#14 @ 25
-#if 25<16
- vld1.64 {d9},[r1]! @ handles unaligned
-#endif
- vshr.u64 d25,d19,#18
-#if 25>0
- vadd.i64 d23,d30 @ h+=Maj from the past
-#endif
- vshr.u64 d26,d19,#41
- vld1.64 {d28},[r3,:64]! @ K[i++]
- vsli.64 d24,d19,#50
- vsli.64 d25,d19,#46
- vmov d29,d19
- vsli.64 d26,d19,#23
-#if 25<16 && defined(__ARMEL__)
- vrev64.8 ,
-#endif
- veor d25,d24
- vbsl d29,d20,d21 @ Ch(e,f,g)
- vshr.u64 d24,d23,#28
- veor d26,d25 @ Sigma1(e)
- vadd.i64 d27,d29,d22
- vshr.u64 d25,d23,#34
- vsli.64 d24,d23,#36
- vadd.i64 d27,d26
- vshr.u64 d26,d23,#39
- vadd.i64 d28,d9
- vsli.64 d25,d23,#30
- veor d30,d23,d16
- vsli.64 d26,d23,#25
- veor d22,d24,d25
- vadd.i64 d27,d28
- vbsl d30,d17,d16 @ Maj(a,b,c)
- veor d22,d26 @ Sigma0(a)
- vadd.i64 d18,d27
- vadd.i64 d30,d27
- @ vadd.i64 d22,d30
- vshr.u64 q12,q4,#19
- vshr.u64 q13,q4,#61
- vadd.i64 d22,d30 @ h+=Maj from the past
- vshr.u64 q15,q4,#6
- vsli.64 q12,q4,#45
- vext.8 q14,q5,q6,#8 @ X[i+1]
- vsli.64 q13,q4,#3
- veor q15,q12
- vshr.u64 q12,q14,#1
- veor q15,q13 @ sigma1(X[i+14])
- vshr.u64 q13,q14,#8
- vadd.i64 q5,q15
- vshr.u64 q15,q14,#7
- vsli.64 q12,q14,#63
- vsli.64 q13,q14,#56
- vext.8 q14,q1,q2,#8 @ X[i+9]
- veor q15,q12
- vshr.u64 d24,d18,#14 @ from NEON_00_15
- vadd.i64 q5,q14
- vshr.u64 d25,d18,#18 @ from NEON_00_15
- veor q15,q13 @ sigma0(X[i+1])
- vshr.u64 d26,d18,#41 @ from NEON_00_15
- vadd.i64 q5,q15
- vld1.64 {d28},[r3,:64]! @ K[i++]
- vsli.64 d24,d18,#50
- vsli.64 d25,d18,#46
- vmov d29,d18
- vsli.64 d26,d18,#23
-#if 26<16 && defined(__ARMEL__)
- vrev64.8 ,
-#endif
- veor d25,d24
- vbsl d29,d19,d20 @ Ch(e,f,g)
- vshr.u64 d24,d22,#28
- veor d26,d25 @ Sigma1(e)
- vadd.i64 d27,d29,d21
- vshr.u64 d25,d22,#34
- vsli.64 d24,d22,#36
- vadd.i64 d27,d26
- vshr.u64 d26,d22,#39
- vadd.i64 d28,d10
- vsli.64 d25,d22,#30
- veor d30,d22,d23
- vsli.64 d26,d22,#25
- veor d21,d24,d25
- vadd.i64 d27,d28
- vbsl d30,d16,d23 @ Maj(a,b,c)
- veor d21,d26 @ Sigma0(a)
- vadd.i64 d17,d27
- vadd.i64 d30,d27
- @ vadd.i64 d21,d30
- vshr.u64 d24,d17,#14 @ 27
-#if 27<16
- vld1.64 {d11},[r1]! @ handles unaligned
-#endif
- vshr.u64 d25,d17,#18
-#if 27>0
- vadd.i64 d21,d30 @ h+=Maj from the past
-#endif
- vshr.u64 d26,d17,#41
- vld1.64 {d28},[r3,:64]! @ K[i++]
- vsli.64 d24,d17,#50
- vsli.64 d25,d17,#46
- vmov d29,d17
- vsli.64 d26,d17,#23
-#if 27<16 && defined(__ARMEL__)
- vrev64.8 ,
-#endif
- veor d25,d24
- vbsl d29,d18,d19 @ Ch(e,f,g)
- vshr.u64 d24,d21,#28
- veor d26,d25 @ Sigma1(e)
- vadd.i64 d27,d29,d20
- vshr.u64 d25,d21,#34
- vsli.64 d24,d21,#36
- vadd.i64 d27,d26
- vshr.u64 d26,d21,#39
- vadd.i64 d28,d11
- vsli.64 d25,d21,#30
- veor d30,d21,d22
- vsli.64 d26,d21,#25
- veor d20,d24,d25
- vadd.i64 d27,d28
- vbsl d30,d23,d22 @ Maj(a,b,c)
- veor d20,d26 @ Sigma0(a)
- vadd.i64 d16,d27
- vadd.i64 d30,d27
- @ vadd.i64 d20,d30
- vshr.u64 q12,q5,#19
- vshr.u64 q13,q5,#61
- vadd.i64 d20,d30 @ h+=Maj from the past
- vshr.u64 q15,q5,#6
- vsli.64 q12,q5,#45
- vext.8 q14,q6,q7,#8 @ X[i+1]
- vsli.64 q13,q5,#3
- veor q15,q12
- vshr.u64 q12,q14,#1
- veor q15,q13 @ sigma1(X[i+14])
- vshr.u64 q13,q14,#8
- vadd.i64 q6,q15
- vshr.u64 q15,q14,#7
- vsli.64 q12,q14,#63
- vsli.64 q13,q14,#56
- vext.8 q14,q2,q3,#8 @ X[i+9]
- veor q15,q12
- vshr.u64 d24,d16,#14 @ from NEON_00_15
- vadd.i64 q6,q14
- vshr.u64 d25,d16,#18 @ from NEON_00_15
- veor q15,q13 @ sigma0(X[i+1])
- vshr.u64 d26,d16,#41 @ from NEON_00_15
- vadd.i64 q6,q15
- vld1.64 {d28},[r3,:64]! @ K[i++]
- vsli.64 d24,d16,#50
- vsli.64 d25,d16,#46
- vmov d29,d16
- vsli.64 d26,d16,#23
-#if 28<16 && defined(__ARMEL__)
- vrev64.8 ,
-#endif
- veor d25,d24
- vbsl d29,d17,d18 @ Ch(e,f,g)
- vshr.u64 d24,d20,#28
- veor d26,d25 @ Sigma1(e)
- vadd.i64 d27,d29,d19
- vshr.u64 d25,d20,#34
- vsli.64 d24,d20,#36
- vadd.i64 d27,d26
- vshr.u64 d26,d20,#39
- vadd.i64 d28,d12
- vsli.64 d25,d20,#30
- veor d30,d20,d21
- vsli.64 d26,d20,#25
- veor d19,d24,d25
- vadd.i64 d27,d28
- vbsl d30,d22,d21 @ Maj(a,b,c)
- veor d19,d26 @ Sigma0(a)
- vadd.i64 d23,d27
- vadd.i64 d30,d27
- @ vadd.i64 d19,d30
- vshr.u64 d24,d23,#14 @ 29
-#if 29<16
- vld1.64 {d13},[r1]! @ handles unaligned
-#endif
- vshr.u64 d25,d23,#18
-#if 29>0
- vadd.i64 d19,d30 @ h+=Maj from the past
-#endif
- vshr.u64 d26,d23,#41
- vld1.64 {d28},[r3,:64]! @ K[i++]
- vsli.64 d24,d23,#50
- vsli.64 d25,d23,#46
- vmov d29,d23
- vsli.64 d26,d23,#23
-#if 29<16 && defined(__ARMEL__)
- vrev64.8 ,
-#endif
- veor d25,d24
- vbsl d29,d16,d17 @ Ch(e,f,g)
- vshr.u64 d24,d19,#28
- veor d26,d25 @ Sigma1(e)
- vadd.i64 d27,d29,d18
- vshr.u64 d25,d19,#34
- vsli.64 d24,d19,#36
- vadd.i64 d27,d26
- vshr.u64 d26,d19,#39
- vadd.i64 d28,d13
- vsli.64 d25,d19,#30
- veor d30,d19,d20
- vsli.64 d26,d19,#25
- veor d18,d24,d25
- vadd.i64 d27,d28
- vbsl d30,d21,d20 @ Maj(a,b,c)
- veor d18,d26 @ Sigma0(a)
- vadd.i64 d22,d27
- vadd.i64 d30,d27
- @ vadd.i64 d18,d30
- vshr.u64 q12,q6,#19
- vshr.u64 q13,q6,#61
- vadd.i64 d18,d30 @ h+=Maj from the past
- vshr.u64 q15,q6,#6
- vsli.64 q12,q6,#45
- vext.8 q14,q7,q0,#8 @ X[i+1]
- vsli.64 q13,q6,#3
- veor q15,q12
- vshr.u64 q12,q14,#1
- veor q15,q13 @ sigma1(X[i+14])
- vshr.u64 q13,q14,#8
- vadd.i64 q7,q15
- vshr.u64 q15,q14,#7
- vsli.64 q12,q14,#63
- vsli.64 q13,q14,#56
- vext.8 q14,q3,q4,#8 @ X[i+9]
- veor q15,q12
- vshr.u64 d24,d22,#14 @ from NEON_00_15
- vadd.i64 q7,q14
- vshr.u64 d25,d22,#18 @ from NEON_00_15
- veor q15,q13 @ sigma0(X[i+1])
- vshr.u64 d26,d22,#41 @ from NEON_00_15
- vadd.i64 q7,q15
- vld1.64 {d28},[r3,:64]! @ K[i++]
- vsli.64 d24,d22,#50
- vsli.64 d25,d22,#46
- vmov d29,d22
- vsli.64 d26,d22,#23
-#if 30<16 && defined(__ARMEL__)
- vrev64.8 ,
-#endif
- veor d25,d24
- vbsl d29,d23,d16 @ Ch(e,f,g)
- vshr.u64 d24,d18,#28
- veor d26,d25 @ Sigma1(e)
- vadd.i64 d27,d29,d17
- vshr.u64 d25,d18,#34
- vsli.64 d24,d18,#36
- vadd.i64 d27,d26
- vshr.u64 d26,d18,#39
- vadd.i64 d28,d14
- vsli.64 d25,d18,#30
- veor d30,d18,d19
- vsli.64 d26,d18,#25
- veor d17,d24,d25
- vadd.i64 d27,d28
- vbsl d30,d20,d19 @ Maj(a,b,c)
- veor d17,d26 @ Sigma0(a)
- vadd.i64 d21,d27
- vadd.i64 d30,d27
- @ vadd.i64 d17,d30
- vshr.u64 d24,d21,#14 @ 31
-#if 31<16
- vld1.64 {d15},[r1]! @ handles unaligned
-#endif
- vshr.u64 d25,d21,#18
-#if 31>0
- vadd.i64 d17,d30 @ h+=Maj from the past
-#endif
- vshr.u64 d26,d21,#41
- vld1.64 {d28},[r3,:64]! @ K[i++]
- vsli.64 d24,d21,#50
- vsli.64 d25,d21,#46
- vmov d29,d21
- vsli.64 d26,d21,#23
-#if 31<16 && defined(__ARMEL__)
- vrev64.8 ,
-#endif
- veor d25,d24
- vbsl d29,d22,d23 @ Ch(e,f,g)
- vshr.u64 d24,d17,#28
- veor d26,d25 @ Sigma1(e)
- vadd.i64 d27,d29,d16
- vshr.u64 d25,d17,#34
- vsli.64 d24,d17,#36
- vadd.i64 d27,d26
- vshr.u64 d26,d17,#39
- vadd.i64 d28,d15
- vsli.64 d25,d17,#30
- veor d30,d17,d18
- vsli.64 d26,d17,#25
- veor d16,d24,d25
- vadd.i64 d27,d28
- vbsl d30,d19,d18 @ Maj(a,b,c)
- veor d16,d26 @ Sigma0(a)
- vadd.i64 d20,d27
- vadd.i64 d30,d27
- @ vadd.i64 d16,d30
- bne .L16_79_neon
-
- vadd.i64 d16,d30 @ h+=Maj from the past
- vldmia r0,{d24-d31} @ load context to temp
- vadd.i64 q8,q12 @ vectorized accumulate
- vadd.i64 q9,q13
- vadd.i64 q10,q14
- vadd.i64 q11,q15
- vstmia r0,{d16-d23} @ save context
- teq r1,r2
- sub r3,#640 @ rewind K512
- bne .Loop_neon
-
- VFP_ABI_POP
- bx lr @ .word 0xe12fff1e
-.size sha512_block_data_order_neon,.-sha512_block_data_order_neon
-#endif
-.asciz "SHA512 block transform for ARMv4/NEON, CRYPTOGAMS by <appro@xxxxxxxxxxx>"
-.align 2
-#if __ARM_MAX_ARCH__>=7 && !defined(__KERNEL__)
-.comm OPENSSL_armcap_P,4,4
-#endif
--
2.27.0

Next message: Masahiro Yamada: "[PATCH 2/4] crypto: arm: use a pattern rule for generating *.S files"
Previous message: Masahiro Yamada: "[PATCH 4/4] crypto: arm64: use a pattern rule for generating *.S files"
Next in thread: Masahiro Yamada: "[PATCH 4/4] crypto: arm64: use a pattern rule for generating *.S files"
Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]