parallel processing - 어레이와의 CUDA 병렬화 작업

CUDA가 처음인데 CUDA에 대한 NVIDIA 교사를 읽었으며 도움이 필요합니다. 다음 코드가 있습니다 :

//some includes
#define NUM_OF_ACCOMS 3360
#define SIZE_RING 16
#define NUM_OF_BIGRAMMS 256
//...some code...
    for (i = 1; i <= SIZE_RING; i++) {
        for (j = 1; j <= SIZE_RING; j++) {
            if (j == i) continue;
            for (k = 1; k <= SIZE_RING; k++) {
                if (k == j || k == i) continue;
                accoms_theta[indOfAccoms][0] = i - 1; accoms_theta[indOfAccoms][1] = j - 1; accoms_theta[indOfAccoms][2] = k - 1;
                accoms_thetaFix[indOfAccoms][0] = i - 1; accoms_thetaFix[indOfAccoms][1] = j - 1; accoms_thetaFix[indOfAccoms][2] = k - 1;
                results[indOfAccoms][0] = results[indOfAccoms][1] = results[indOfAccoms][2] = 0;
                indOfAccoms++;
            }
        }
    }   
    for (i = 0; i < SIZE_RING; i++)
        for (j = 0; j < SIZE_RING; j++) {
            bigramms[indOfBigramms][0] = i; bigramms[indOfBigramms][1] = j;
            indOfBigramms++;
        }
        for (i = 0; i < NUM_OF_ACCOMS; i++) {
            thetaArr[0] = accoms_theta[i][0]; thetaArr[1] = accoms_theta[i][1]; thetaArr[2] = accoms_theta[i][2];
            d0 = thetaArr[2] - thetaArr[1]; d1 = thetaArr[2] - thetaArr[0];
            if (d0 < 0)
                d0 += SIZE_RING;
            if (d1 < 0)
                d1 += SIZE_RING;
            for (j = 0; j < NUM_OF_ACCOMS; j++) {
                theta_fixArr[0] = accoms_thetaFix[j][0]; theta_fixArr[1] = accoms_thetaFix[j][1]; theta_fixArr[2] = accoms_thetaFix[j][2];
                d0_fix = theta_fixArr[2] - theta_fixArr[1]; d1_fix = theta_fixArr[2] - theta_fixArr[0];
                count = 0;
                if (d0_fix < 0)
                    d0_fix += SIZE_RING;
                if (d1_fix < 0)
                    d1_fix += SIZE_RING;
                for (k = 0; k < NUM_OF_BIGRAMMS; k++) {
                    diff0 = subst[(d0 + bigramms[k][0]) % SIZE_RING] - subst[bigramms[k][0]];
                    diff1 = subst[(d1 + bigramms[k][1]) % SIZE_RING] - subst[bigramms[k][1]];
                    if (diff0 < 0)
                        diff0 += SIZE_RING;
                    if (diff1 < 0)
                        diff1 += SIZE_RING;
                    if (diff0 == d0_fix && diff1 == d1_fix)
                        count++;
                }
                if (max < count) {
                    max = count;
                    results[indResults][0] = max; results[indResults][1] = i; results[indResults][2] = j;
                    count = 0;
                    indResults++;
                }
            }
        }

내 장치에 대한 정보가 있습니다

2^30