CRC Calculation Of A Mostly Static Data Stream

Question

Background:

I have a section of memory, 1024 bytes. The last 1020 bytes will always be the same. The first 4 bytes will change (serial number of a product). I nee

Answer 1

Below is example C code for an alternative approach for CRC(A0). Rather than working with a matrix, a CRC can be cycled forward n bits by muliplying (CRC · ((2^n)%POLY)%POLY . So the repeated squaring is performed on an integer rather than a matrix. If n is constant, then (2^n)%POLY can be pre-computed.

/*  crcpad.c  - crc - data has a large number of trailing zeroes */

#include 
#include 

typedef unsigned char       uint8_t;
typedef unsigned int       uint32_t;

#define POLY (0x04c11db7u)

static uint32_t crctbl[256];

void GenTbl(void)                       /* generate crc table */
{
uint32_t crc;
uint32_t c;
uint32_t i;
    for(c = 0; c < 0x100; c++){
        crc = c<<24;
        for(i = 0; i < 8; i++)
            /* assumes twos complement */
            crc = (crc<<1)^((0-(crc>>31))&POLY);
        crctbl[c] = crc;
    }
}

uint32_t GenCrc(uint8_t * bfr, size_t size) /* generate crc */
{
uint32_t crc = 0u;
    while(size--)
        crc = (crc<<8)^crctbl[(crc>>24)^*bfr++];
    return(crc);
}

/* carryless multiply modulo crc */
uint32_t MpyModCrc(uint32_t a, uint32_t b) /* (a*b)%crc */
{
uint32_t pd = 0;
uint32_t i;
    for(i = 0; i < 32; i++){
        /* assumes twos complement */
        pd = (pd<<1)^((0-(pd>>31))&POLY);
        pd ^= (0-(b>>31))&a;
        b <<= 1;
    }
    return pd;
}

/* exponentiate by repeated squaring modulo crc */
uint32_t PowModCrc(uint32_t p)          /* pow(2,p)%crc */
{
uint32_t prd = 0x1u;                    /* current product */
uint32_t sqr = 0x2u;                    /* current square */
    while(p){
        if(p&1)
            prd = MpyModCrc(prd, sqr);
        sqr = MpyModCrc(sqr, sqr);
        p >>= 1;
    }
    return prd;
}

/* # data bytes */
#define DAT  ( 32)
/* # zero bytes */
#define PAD  (992)
/* DATA+PAD */
#define CNT (1024)

int main()
{
uint32_t pmc;
uint32_t crc;
uint32_t crf;
uint32_t i;
uint8_t *msg = malloc(CNT);

    for(i = 0; i < DAT; i++)           /* generate msg */
        msg[i] = (uint8_t)rand();
    for( ; i < CNT; i++)
        msg[i] = 0;
    GenTbl();                           /* generate crc table */
    crc = GenCrc(msg, CNT);             /* generate crc normally */
    crf = GenCrc(msg, DAT);             /* generate crc for data */
    pmc = PowModCrc(PAD*8);             /* pmc = pow(2,PAD*8)%crc */
    crf = MpyModCrc(crf, pmc);          /* crf = (crf*pmc)%crc */
    printf("%08x %08x\n", crc, crf);
    free(msg);
    return 0;
}

Example C code using intrinsic for carryless multiply, pclmulqdq == _mm_clmulepi64_si128:

/*  crcpadm.c  - crc - data has a large number of trailing zeroes */
/*                     pclmulqdq intrinsic version                */

#include 
#include 
#include 

typedef unsigned char       uint8_t;
typedef unsigned int       uint32_t;
typedef unsigned long long uint64_t;

#define POLY  (0x104c11db7ull)
#define POLYM ( 0x04c11db7u)

static uint32_t crctbl[256];

static __m128i poly;                    /* poly */
static __m128i invpoly;                 /* 2^64 / POLY */

void GenMPoly(void)                     /* generate __m12i8 poly info */
{
uint64_t N = 0x100000000ull;
uint64_t Q = 0;
    for(size_t i = 0; i < 33; i++){
        Q <<= 1;
        if(N&0x100000000ull){
            Q |= 1;
            N ^= POLY;
        }
        N <<= 1;
    }
    poly.m128i_u64[0] = POLY;
    invpoly.m128i_u64[0] = Q;
}

void GenTbl(void)                       /* generate crc table */
{
uint32_t crc;
uint32_t c;
uint32_t i;
    for(c = 0; c < 0x100; c++){
        crc = c<<24;
        for(i = 0; i < 8; i++)
            /* assumes twos complement */
            crc = (crc<<1)^((0-(crc>>31))&POLYM);
        crctbl[c] = crc;
    }
}

uint32_t GenCrc(uint8_t * bfr, size_t size) /* generate crc */
{
uint32_t crc = 0u;
    while(size--)
        crc = (crc<<8)^crctbl[(crc>>24)^*bfr++];
    return(crc);
}

/* carryless multiply modulo crc */
uint32_t MpyModCrc(uint32_t a, uint32_t b) /* (a*b)%crc */
{
__m128i ma, mb, mp, mt;
    ma.m128i_u64[0] = a;
    mb.m128i_u64[0] = b;
    mp = _mm_clmulepi64_si128(ma, mb, 0x00);      /* p[0] = a*b */
    mt = _mm_clmulepi64_si128(mp, invpoly, 0x00); /* t[1] = (p[0]*((2^64)/POLY))>>64 */
    mt = _mm_clmulepi64_si128(mt, poly, 0x01);    /* t[0] = t[1]*POLY */
    return mp.m128i_u32[0] ^ mt.m128i_u32[0];     /* ret =  p[0] ^ t[0] */
}

/* exponentiate by repeated squaring modulo crc */
uint32_t PowModCrc(uint32_t p)          /* pow(2,p)%crc */
{
uint32_t prd = 0x1u;                    /* current product */
uint32_t sqr = 0x2u;                    /* current square */
    while(p){
        if(p&1)
            prd = MpyModCrc(prd, sqr);
        sqr = MpyModCrc(sqr, sqr);
        p >>= 1;
    }
    return prd;
}

/* # data bytes */
#define DAT  ( 32)
/* # zero bytes */
#define PAD  (992)
/* DATA+PAD */
#define CNT (1024)

int main()
{
uint32_t pmc;
uint32_t crc;
uint32_t crf;
uint32_t i;
uint8_t *msg = malloc(CNT);

    GenMPoly();                         /* generate __m128 polys */
    GenTbl();                           /* generate crc table */
    for(i = 0; i < DAT; i++)            /* generate msg */
        msg[i] = (uint8_t)rand();
    for( ; i < CNT; i++)
        msg[i] = 0;
    crc = GenCrc(msg, CNT);             /* generate crc normally */
    crf = GenCrc(msg, DAT);             /* generate crc for data */
    pmc = PowModCrc(PAD*8);             /* pmc = pow(2,PAD*8)%crc */
    crf = MpyModCrc(crf, pmc);          /* crf = (crf*pmc)%crc */
    printf("%08x %08x\n", crc, crf);
    free(msg);
    return 0;
}