.endr
.align 2
+
+.global rotate64_1bit_left
+rotate64_1bit_left:
+ bst r25, 7
+ rol r18
+ rol r19
+ rol r20
+ rol r21
+ rol r22
+ rol r23
+ rol r24
+ rol r25
+ bld r18, 0
+ ret
+
+.global rotate64_1bit_right
+rotate64_1bit_right:
+ bst r18, 0
+ ror r25
+ ror r24
+ ror r23
+ ror r22
+ ror r21
+ ror r20
+ ror r19
+ ror r18
+ bld r25, 7
+ ret
+
+.global rotate64_nbit_autodir
+rotate64_nbit_autodir:
+ lsr r16
+ brcc rotate64_nbit_left
+.global rotate64_nbit_right
+rotate64_nbit_right:
+ ldi r30, pm_lo8(rotate64_1bit_right)
+ ldi r31, pm_hi8(rotate64_1bit_right)
+ rjmp icall_r16_times
+.global rotate64_nbit_left
+rotate64_nbit_left:
+ ldi r30, pm_lo8(rotate64_1bit_left)
+ ldi r31, pm_hi8(rotate64_1bit_left)
+icall_r16_times:
+1: dec r16
+ brmi 2f
+ icall
+ rjmp 1b
+2:
+ ret
+
+rotate64_1byte_left:
+ mov r0, r25
+ mov r25, r24
+ mov r24, r23
+ mov r23, r22
+ mov r22, r21
+ mov r21, r20
+ mov r20, r19
+ mov r19, r18
+ mov r18, r0
+ ret
+
+rotate64_2byte_left:
+ movw r0, r24
+ movw r24, r22
+ movw r22, r20
+ movw r20, r18
+ movw r18, r0
+ ret
+
+rotate64_3byte_left:
+ mov r0, r25
+ mov r25, r22
+ mov r22, r19
+ mov r19, r24
+ mov r24, r21
+ mov r21, r18
+ mov r18, r23
+ mov r23, r20
+ mov r20, r0
+ ret
+
+rotate64_4byte_left:
+ movw r0, r24
+ movw r24, r20
+ movw r20, r0
+ movw r0, r22
+ movw r22, r18
+ movw r18, r0
+ ret
+
+rotate64_5byte_left:
+ mov r0, r25
+ mov r25, r20
+ mov r20, r23
+ mov r23, r18
+ mov r18, r21
+ mov r21, r24
+ mov r24, r19
+ mov r19, r22
+ mov r22, r0
+ ret
+
+rotate64_6byte_left:
+ movw r0, r18
+ movw r18, r20
+ movw r20, r22
+ movw r22, r24
+ movw r24, r0
+ ret
+
+rotate64_7byte_left:
+ mov r0, r18
+ mov r18, r19
+ mov r19, r20
+ mov r20, r21
+ mov r21, r22
+ mov r22, r23
+ mov r23, r24
+ mov r24, r25
+ mov r25, r0
+ ret
+
+
+byte_rot_jmp_table:
+ ret
+ rjmp rotate64_1byte_left
+ rjmp rotate64_2byte_left
+ rjmp rotate64_3byte_left
+ rjmp rotate64_4byte_left
+ rjmp rotate64_5byte_left
+ rjmp rotate64_6byte_left
+ rjmp rotate64_7byte_left
+
+.global rotate64left_code
+rotate64left_code:
+ ldi r30, pm_lo8(byte_rot_jmp_table)
+ ldi r31, pm_hi8(byte_rot_jmp_table)
+ mov r0, r16
+ andi r16, 0x70
+ swap r16
+ add r30, r16
+ adc r31, r1
+ mov r16, r0
+ andi r16, 0x0f
+ icall
+ clr r1
+ rjmp rotate64_nbit_autodir
+
+
/*
void keccak_theta (uint64_t *a, uint64_t *b){
// uint64_t b[5][5];
movw ZL, r2
lpm r16, Z+
movw r2, ZL
- call rotate64left_code
+ rcall rotate64left_code
movw ZL, r4
lpm r16, Z+
movw r4, ZL
#endif
-/*
-const uint64_t rc[] PROGMEM = {
- 0x0000000000000001LL, 0x0000000000008082LL,
- 0x800000000000808ALL, 0x8000000080008000LL,
- 0x000000000000808BLL, 0x0000000080000001LL,
- 0x8000000080008081LL, 0x8000000000008009LL,
- 0x000000000000008ALL, 0x0000000000000088LL,
- 0x0000000080008009LL, 0x000000008000000ALL,
- 0x000000008000808BLL, 0x800000000000008BLL,
- 0x8000000000008089LL, 0x8000000000008003LL,
- 0x8000000000008002LL, 0x8000000000000080LL,
- 0x000000000000800ALL, 0x800000008000000ALL,
- 0x8000000080008081LL, 0x8000000000008080LL,
- 0x0000000080000001LL, 0x8000000080008008LL
-};
-*/
const uint8_t keccak_rc_comp[] PROGMEM = {
0x01, 0x92, 0xda, 0x70,
0x52, 0xc0, 0x1a, 0x6a,
0xf1, 0xd0, 0x21, 0x78,
};
-/*
-const uint8_t keccak_rotate_codes[5][5] PROGMEM = {
- { ROT_CODE( 0), ROT_CODE(36), ROT_CODE( 3), ROT_CODE(41), ROT_CODE(18) },
- { ROT_CODE( 1), ROT_CODE(44), ROT_CODE(10), ROT_CODE(45), ROT_CODE( 2) },
- { ROT_CODE(62), ROT_CODE( 6), ROT_CODE(43), ROT_CODE(15), ROT_CODE(61) },
- { ROT_CODE(28), ROT_CODE(55), ROT_CODE(25), ROT_CODE(21), ROT_CODE(56) },
- { ROT_CODE(27), ROT_CODE(20), ROT_CODE(39), ROT_CODE( 8), ROT_CODE(14) }
-};
-*/
+
const uint8_t keccak_rotate_codes[5][5] PROGMEM = {
{ ROT_CODE( 0), ROT_CODE( 1), ROT_CODE(62), ROT_CODE(28), ROT_CODE(27) },
{ ROT_CODE(36), ROT_CODE(44), ROT_CODE( 6), ROT_CODE(55), ROT_CODE(20) },