/*
* Function: grain_keystream
*
* Synopsis
* Generates a new bit and updates the internal state of the cipher.
*/
u8 grain_keystream(ECRYPT_ctx* ctx) {
u32 x0 = get3(S),
x1 = get25(S),
x2 = get46(S),
x3 = get64(S),
x4 = get63(B);
u32 Z = get1(B) ^ get2(B) ^ get4(B) ^ get10(B) ^ get31(B) ^ get43(B) ^ get56(B) ^ h(x0,x1,x2,x3,x4);
u32 S80 = get62(S) ^ get51(S) ^ get38(S) ^ get23(S) ^ get13(S) ^ get0(S);
#if !defined(COMBINE_TERMS)
u32 B80 =(get0(S)) ^ (get62(B)) ^ (get60(B)) ^ (get52(B)) ^ (get45(B)) ^ (get37(B)) ^ (get33(B)) ^ (get28(B)) ^ (get21(B))^
(get14(B)) ^ (get9(B)) ^ (get0(B)) ^ (get63(B)&get60(B)) ^ (get37(B)&get33(B)) ^ (get15(B)&get9(B))^
(get60(B)&get52(B)&get45(B)) ^ (get33(B)&get28(B)&get21(B)) ^ (get63(B)&get45(B)&get28(B)&get9(B))^
(get60(B)&get52(B)&get37(B)&get33(B)) ^ (get63(B)&get60(B)&get21(B)&get15(B))^
(get63(B)&get60(B)&get52(B)&get45(B)&get37(B)) ^ (get33(B)&get28(B)&get21(B)&get15(B)&get9(B))^
(get52(B)&get45(B)&get37(B)&get33(B)&get28(B)&get21(B));
#else
u32 B33_28_21 = (get33(B)&get28(B)&get21(B)); /* 3 */
u32 B52_45_37 = (get52(B)&get45(B)&get37(B)); /* 2 */
u32 B52_37_33 = (get52(B)&get37(B)&get33(B)); /* 2 */
u32 B60_52_45 = (get60(B)&get52(B)&get45(B)); /* 2 */
u32 B63_60 = (get63(B)&get60(B)); /* 3 */
u32 B37_33 = (get37(B)&get33(B)); /* 3 */
u32 B45_28 = (get45(B)&get28(B)); /* 2 */
u32 B15_9 = (get15(B)&get9(B)); /* 2 */
u32 B21_15 = (get21(B)&get15(B)); /* 2 */
u32 B80 =(get0(S)) ^ (get62(B)) ^ (get60(B)) ^ (get52(B)) ^ (get45(B)) ^ (get37(B)) ^ (get33(B)) ^ (get28(B)) ^ (get21(B))^
(get14(B)) ^ (get9(B)) ^ (get0(B)) ^ (B63_60) ^ (B37_33) ^ (B15_9)^
(B60_52_45) ^ (B33_28_21) ^ (get63(B)&B45_28&get9(B))^
(get60(B)&B52_37_33) ^ (B63_60&B21_15)^
(B63_60&B52_45_37) ^ (B33_28_21&B15_9)^
(B52_45_37&B33_28_21);
#endif
SHIFT_FSR(S);
SHIFT_FSR(B);
set79(S,S80);
set79(B,B80);
return Z&1;
}
void strassen_8thread_mult(matrix a, matrix b, matrix c){
matrix quar[12];
matrix m[7];
struct work_struct *jobs[7];
int size = a.size/2;
int i, j;
if(size==0){
c.rows[0][0] = a.rows[0][0] * b.rows[0][0];
return;
}
/*
if (a.size <= BREAK) {
int i, j, k;
for (i = 0; i < (a.size); i++) {
for (k = 0; k < (a.size); k++) {
for (j = 0; j < (a.size); j++) {
c.rows[i][j] += a.rows[i][k] * b.rows[k][j];
}
}
}
return;
}
*/
job_init();
quar[0]=get00(a); quar[1]=get01(a);
quar[2]=get10(a); quar[3]=get11(a);
quar[4]=get00(b); quar[5]=get01(b);
quar[6]=get10(b); quar[7]=get11(b);
quar[8]=get00(c); quar[9]=get01(c);
quar[10]=get10(c); quar[11]=get11(c);
for(i=0;i<7;i++){
m[i] = new_matrix(size);
}
for (i = 0; i < 7; i++) {
jobs[i] = malloc(sizeof(struct work_struct));
if (jobs[i] == NULL) {
perror(NULL);
exit(1);
}
}
jobs[0]->a_1 = quar[0];
jobs[0]->a_2 = quar[3];
jobs[0]->b_1 = quar[4];
jobs[0]->b_2 = quar[7];
jobs[0]->c = m[0];
jobs[0]->tid = 0;
job_create(thread_main, jobs[0], 0);
jobs[1]->a_1 = quar[2];
jobs[1]->a_2 = quar[3];
jobs[1]->b_1 = quar[4];
jobs[1]->c = m[1];
jobs[1]->tid = 1;
job_create(thread_main, jobs[1], 0);
jobs[2]->a_1 = quar[0];
jobs[2]->b_1 = quar[5];
jobs[2]->b_2 = quar[7];
jobs[2]->c = m[2];
jobs[2]->tid = 2;
job_create(thread_main, jobs[2], 0);
jobs[3]->a_1 = quar[3];
jobs[3]->b_1 = quar[6];
jobs[3]->b_2 = quar[4];
jobs[3]->c = m[3];
jobs[3]->tid = 3;
job_create(thread_main, jobs[3], 0);
jobs[4]->a_1 = quar[0];
jobs[4]->a_2 = quar[1];
jobs[4]->b_1 = quar[7];
jobs[4]->c = m[4];
jobs[4]->tid = 4;
job_create(thread_main, jobs[4], 0);
jobs[5]->a_1 = quar[2];
jobs[5]->a_2 = quar[0];
jobs[5]->b_1 = quar[4];
jobs[5]->b_2 = quar[5];
jobs[5]->c = m[5];
jobs[5]->tid = 5;
job_create(thread_main, jobs[5], 0);
jobs[6]->a_1 = quar[1];
jobs[6]->a_2 = quar[3];
jobs[6]->b_1 = quar[6];
jobs[6]->b_2 = quar[7];
jobs[6]->c = m[6];
jobs[6]->tid = 6;
job_create(thread_main, jobs[6], 0);
for(i=0;i<7;i++){
job_join(jobs[i]);
}
for(i=0;i<size;i++){
for(j=0;j<size;j++){
quar[8].rows[i][j] = m[0].rows[i][j] + m[3].rows[i][j] - m[4].rows[i][j] + m[6].rows[i][j];
quar[9].rows[i][j] = m[2].rows[i][j] + m[4].rows[i][j];
quar[10].rows[i][j] = m[1].rows[i][j] + m[3].rows[i][j];
quar[11].rows[i][j] = m[0].rows[i][j] - m[1].rows[i][j] + m[2].rows[i][j] + m[5].rows[i][j];
}
}
for(i=0;i<12;i++){
delete_matrix(quar[i]);
}
for(i=0;i<7;i++){
delete_matrix(m[i]);
}
}
//expects c to be initialized
void strassen_mult(matrix a, matrix b, matrix c){
matrix quar[12];
matrix m[7];
matrix temp1, temp2;
int size = a.size/2;
int i,j;
// if(size==0){
// c.rows[0][0] = a.rows[0][0] * b.rows[0][0];
// return;
// }
if (a.size <= BREAK) {
int i, j, k;
for (i = 0; i < (a.size); i++) {
for (k = 0; k < (a.size); k++) {
for (j = 0; j < (a.size); j++) {
c.rows[i][j] += a.rows[i][k] * b.rows[k][j];
}
}
}
}
quar[0]=get00(a); quar[1]=get01(a);
quar[2]=get10(a); quar[3]=get11(a);
quar[4]=get00(b); quar[5]=get01(b);
quar[6]=get10(b); quar[7]=get11(b);
quar[8]=get00(c); quar[9]=get01(c);
quar[10]=get10(c); quar[11]=get11(c);
for(i=0;i<7;i++){
m[i] = new_matrix(size);
}
if (a.size <= BREAK)
goto group;
temp1 = new_matrix(size);
temp2 = new_matrix(size);
plus(quar[0], quar[3], temp1);
plus(quar[4], quar[7], temp2);
strassen_mult(temp1,temp2,m[0]);
plus(quar[2], quar[3], temp1);
strassen_mult(temp1, quar[4], m[1]);
minus(quar[5], quar[7], temp2);
strassen_mult(quar[0], temp2, m[2]);
minus(quar[6], quar[4], temp2);
strassen_mult(quar[3], temp2, m[3]);
plus(quar[0], quar[1], temp1);
strassen_mult(temp1, quar[7], m[4]);
minus(quar[2], quar[0], temp1);
plus(quar[4], quar[5], temp2);
strassen_mult(temp1, temp2, m[5]);
minus(quar[1], quar[3], temp1);
plus(quar[6], quar[7], temp2);
strassen_mult(temp1, temp2, m[6]);
delete_matrix(temp1);
delete_matrix(temp2);
group:
for(i=0;i<size;i++){
for(j=0;j<size;j++){
quar[8].rows[i][j] = m[0].rows[i][j] + m[3].rows[i][j] - m[4].rows[i][j] + m[6].rows[i][j];
quar[9].rows[i][j] = m[2].rows[i][j] + m[4].rows[i][j];
quar[10].rows[i][j] = m[1].rows[i][j] + m[3].rows[i][j];
quar[11].rows[i][j] = m[0].rows[i][j] - m[1].rows[i][j] + m[2].rows[i][j] + m[5].rows[i][j];
}
}
for(i=0;i<12;i++){
delete_matrix(quar[i]);
}
for(i=0;i<7;i++){
delete_matrix(m[i]);
}
}
