auxFormat.h 6.95 KB
Newer Older
Wentao Zhang committed
1 2 3
#include"crypto_aead.h"
#include"api.h"
#include  <string.h>
Wentao Zhang committed
4 5
#include <stdio.h>
#include <stdlib.h>
Wentao Zhang committed
6 7 8 9 10 11 12 13 14
#define U32BIG(x) (x)

void P512(unsigned int *s, unsigned char *round, unsigned char rounds);

typedef unsigned char u8;
typedef unsigned int u32;
typedef unsigned long long u64;
void printU8(char name[], u8 var[], long len, int offset);

Wentao Zhang committed
15 16 17 18 19 20 21 22
#define puckU32ToFour(lo){\
u32 r0;\
r0 = (lo ^ (lo << 2)) & 0x30303030, lo ^= r0 ^ (r0 >> 2);\
r0 = (lo ^ (lo << 1)) & 0x44444444, lo ^= r0 ^ (r0 >> 1);\
r0 = (lo ^ (lo << 4)) & 0x0f000f00, lo ^= r0 ^ (r0 >> 4);\
r0 = (lo ^ (lo << 2)) & 0x30303030, lo ^= r0 ^ (r0 >> 2);\
r0 = (lo ^ (lo << 8)) & 0x00ff0000, lo ^= r0 ^ (r0 >> 8);\
r0 = (lo ^ (lo << 4)) & 0x0f000f00, lo ^= r0 ^ (r0 >> 4);\
Wentao Zhang committed
23
}
Wentao Zhang committed
24 25 26 27 28 29 30 31
#define unpuckU32ToFour(lo){\
u32 r0;\
r0 = (lo ^ (lo << 4)) & 0x0f000f00, lo ^= r0 ^ (r0 >> 4);\
r0 = (lo ^ (lo << 8)) & 0x00ff0000, lo ^= r0 ^ (r0 >> 8);\
r0 = (lo ^ (lo << 2)) & 0x30303030, lo ^= r0 ^ (r0 >> 2);\
r0 = (lo ^ (lo << 4)) & 0x0f000f00, lo ^= r0 ^ (r0 >> 4);\
r0 = (lo ^ (lo << 1)) & 0x44444444, lo ^= r0 ^ (r0 >> 1);\
r0 = (lo ^ (lo << 2)) & 0x30303030, lo ^= r0 ^ (r0 >> 2);\
Wentao Zhang committed
32
}
Wentao Zhang committed
33

Wentao Zhang committed
34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157
//t1
#define P_512_ARC(rci) \
  do { \
    __asm__ __volatile__ ( \
    		"/*add round const   s0 s1 s2 s3*/           \n\t"\
			"ands %[t1] ,  %[rci], #0xc0\n\t" \
			"eors %[S_3],  %[S_3], %[t1], LSR  #6 \n\t"   /*s[3] ^= (constant7Format_aead[lunNum] >> 6) & 0x3;*/\
			"ands %[t2] ,  %[rci], #0x30\n\t" \
			"eors %[S_2],  %[S_2], %[t2], LSR  #4 \n\t"   /*s[2] ^= (constant7Format_aead[lunNum] >> 4) & 0x3;*/\
			"ands %[t3] ,  %[rci], #0xc\n\t" \
			"eors %[S_1],  %[S_1], %[t3], LSR  #2 \n\t"   /*s[1] ^= (constant7Format_aead[lunNum] >> 2) & 0x3;*/\
			"ands %[t4] ,  %[rci], #0x3\n\t" \
			"eors %[S_0],  %[S_0], %[t4]       \n\t"      /*s[0] ^= constant7Format_aead[lunNum] & 0x3;*/\
			: /* output variables - including inputs that are changed */\
			  [t1] "=r" (t1),  [t2] "=r" (t2),  [t3] "=r" (t3),   [t4] "=r" (t9), [rci] "+r" (rci),\
			  [S_0] "+r" (s[0]), [S_1] "+r" (s[1]), [S_2] "+r" (s[2]),[S_3] "+r" (s[3])\
			  : : );\
}while (0)

#define P_512_SR(S4,S8,S9,S10,S11,S12,S13,S14,S15) \
  do { \
    __asm__ __volatile__ ( \
    	"ROR      %[S_4]  ,   #31     \n\t"\
		"ROR    %[S_11]  ,   #28      \n\t"\
		"ROR    %[S_10]  ,   #28      \n\t"\
		"ROR     %[S_9]   ,   #28      \n\t"\
		"ROR     %[S_8]   ,   #28        \n\t"\
    	"ROR     %[S_12] ,   #25        \n\t"\
    	"ROR     %[S_13] ,   #26      \n\t"\
    	"ROR     %[S_14] ,   #26      \n\t"\
    	"ROR     %[S_15] ,   #26        \n\t"\
    : /* output variables - including inputs that are changed */\
	  [S_4] "+r" (S4),\
	 [S_12] "+r" (S12), [S_8] "+r" (S8)  ,\
	 [S_13] "+r" (S13), [S_9] "+r" (S9)  ,\
	 [S_14] "+r" (S14), [S_10] "+r" (S10),\
	 [S_15] "+r" (S15), [S_11] "+r" (S11)\
	 : : );\
}while (0)
unsigned char constant7Format_aead[100];
#define P_512_SBOX2_ROR(S1,S2,S3,S4) \
  do { \
    __asm__ __volatile__ ( \
			"/*sbox first column  0,3,4,7           sbox1(s[0], ROR(s[3], 31),ROR(s[4], 28),  ROR(s[7], 25)); */         \n\t"      \
			"mvns    %[S_0],     %[S_0]            \n\t"      \
			"ands    %[t1],    %[S_0], %[S_3] ,  ROR #31       \n\t"      \
			"eors    %[t1],   %[t1], %[S_4] ,  ROR #28     \n\t"      \
			"orrs    %[S_4],     %[S_4], %[S_3] ,  ROR #3        \n\t"      \
			"eors    %[S_0],     %[S_0], %[S_7] ,  ROR #25       \n\t"      \
			"eors    %[S_4],     %[S_0], %[S_4] ,  ROR #28  /* 31-28=3*/    \n\t"      \
			"eors    %[t2],    %[S_7], %[S_3] ,  ROR #6        \n\t"      \
			"eors    %[S_7],     %[t1],%[S_7] ,  ROR #25       \n\t"      \
			"ands    %[S_0],     %[t1],%[S_0]        \n\t"      \
			"eors    %[S_0],     %[S_0], %[t2] ,  ROR #25    /* 31-25=6*/    \n\t"      \
			"ands    %[S_3],     %[S_4], %[t2] ,  ROR #25     /* 31-25=6*/   \n\t"      \
			"eors    %[S_3],     %[t1],%[S_3]        \n\t"        \
	: /* output variables - including inputs that are changed */\
		[t1] "=r" (t1), [t2] "=r" (t2),\
		[S_0] "+r" (S1), [S_3] "+r" (S2), [S_4] "+r" (S3), [S_7] "+r" (S4) \
		: : );\
}while (0)
#define P_512_SBOX3_ROR(S1,S2,S3,S4) \
  do { \
	    __asm__ __volatile__ ( \
		"/*sbox first column  0,3,4,7           sbox1(s[0], s[3],ROR(s[4], 28),  ROR(s[7], 26)); */         \n\t"     \
		"mvns    %[S_0],     %[S_0]            \n\t"      \
		"ands    %[t1],    %[S_3], %[S_0]        \n\t"      \
		"eors    %[t1],    %[t1],    %[S_4] , ROR #28       \n\t"      \
		"orrs    %[S_4],     %[S_3], %[S_4] , ROR #28       \n\t"      \
		"eors    %[S_0],     %[S_0], %[S_7] , ROR #26        \n\t"      \
		"eors    %[S_4],     %[S_4], %[S_0]        \n\t"      \
		"eors    %[t2],    %[S_3], %[S_7]  , ROR #26      \n\t"      \
		"eors    %[S_7],    %[t1] ,     %[S_7]  , ROR #26     \n\t"      \
		"ands    %[S_0],     %[t1],%[S_0]        \n\t"      \
		"eors    %[S_0],     %[t2],%[S_0]        \n\t"      \
		"ands    %[S_3],     %[S_4], %[t2]       \n\t"      \
		"eors    %[S_3],     %[t1], %[S_3]        \n\t"      \
	: /* output variables - including inputs that are changed */\
		[t1] "=r" (t1), [t2] "=r" (t2),\
		[S_0] "+r" (S1), [S_3] "+r" (S2), [S_4] "+r" (S3), [S_7] "+r" (S4) \
		: : );\
}while (0)

#define P_512_SBOX1(S1,S2,S3,S4) \
  do { \
    __asm__ __volatile__ ( \
            "/*sbox   column*/         \n\t"\
   	        "mvns    %[S_0],     %[S_0]            \n\t"\
   	        "ands    %[t1],      %[S_2], %[S_0]        \n\t"\
   	        "eors    %[t1],      %[S_4], %[t1]        \n\t"\
   	        "orrs    %[S_4],     %[S_2], %[S_4]        \n\t"\
   	        "eors    %[S_0],     %[S_6], %[S_0]        \n\t"\
   	        "eors    %[S_4],     %[S_4], %[S_0]        \n\t"\
   	        "eors    %[t2],      %[S_2], %[S_6]        \n\t"\
   	        "eors    %[S_6],     %[S_6], %[t1]        \n\t"\
   	        "ands    %[S_0],     %[t1] , %[S_0]        \n\t"\
   	        "eors    %[S_0],     %[t2] , %[S_0]        \n\t"\
   	        "ands    %[S_2],     %[S_4], %[t2]       \n\t"\
   	        "eors    %[S_2],     %[t1] , %[S_2]        \n\t"\
    : /* output variables - including inputs that are changed */\
		[t1] "=r" (t1), [t2] "=r" (t2),\
		[S_0] "+r" (S1), [S_2] "+r" (S2), [S_4] "+r" (S3), [S_6] "+r" (S4) \
		: : );\
}while (0)
#define P_512_SR(S4,S8,S9,S10,S11,S12,S13,S14,S15) \
  do { \
    __asm__ __volatile__ ( \
    	"ROR      %[S_4]  ,   #31     \n\t"\
		"ROR    %[S_11]  ,   #28      \n\t"\
		"ROR    %[S_10]  ,   #28      \n\t"\
		"ROR     %[S_9]   ,   #28      \n\t"\
		"ROR     %[S_8]   ,   #28        \n\t"\
    	"ROR     %[S_12] ,   #25        \n\t"\
    	"ROR     %[S_13] ,   #26      \n\t"\
    	"ROR     %[S_14] ,   #26      \n\t"\
    	"ROR     %[S_15] ,   #26        \n\t"\
    : /* output variables - including inputs that are changed */\
	  [S_4] "+r" (S4),\
	 [S_12] "+r" (S12), [S_8] "+r" (S8)  ,\
	 [S_13] "+r" (S13), [S_9] "+r" (S9)  ,\
	 [S_14] "+r" (S14), [S_10] "+r" (S10),\
	 [S_15] "+r" (S15), [S_11] "+r" (S11)\
	 : : );\
}while (0)