私はこのカーネルを持っています
__global__ void kernel1(int keep, int include, int width, int* d_Xco,
int* d_Xnum, bool* d_Xvalid, float* d_Xblas)
{
int i, k;
i = threadIdx.x + blockIdx.x * blockDim.x;
if(i < keep){
for(k = 0; k < include ; k++){
int val = (d_Xblas[i*include + k] >= 1e5);
int aux = d_Xnum[i];
d_Xblas[i*include + k] *= (!val);
d_Xco[i*width + aux] = k;
d_Xnum[i] +=val;
d_Xvalid[i*include + k] = (!val);
}
}
}
で起動
int keep = 9000;
int include = 23000;
int width = 0.2*include;
int threads = 192;
int blocks = keep+threads-1/threads;
kernel1 <<< blocks,threads >>>( keep, include, width,
d_Xco, d_Xnum, d_Xvalid, d_Xblas );
これkernel1
は正常に機能しますが、完全に最適化されているわけではありません。内側のループをなくすのは簡単だと思いましたk
が、どういうわけかうまくいきません。私の最初のアイデアは:
__global__ void kernel2(int keep, int include, int width,
int* d_Xco, int* d_Xnum, bool* d_Xvalid,
float* d_Xblas)
{
int i, k;
i = threadIdx.x + blockIdx.x * blockDim.x;
k = threadIdx.y + blockIdx.y * blockDim.y;
if((i < keep) && (k < include) ) {
int val = (d_Xblas[i*include + k] >= 1e5);
int aux = d_Xnum[i];
d_Xblas[i*include + k] *= (float)(!val);
d_Xco[i*width + aux] = k;
atomicAdd(&d_Xnum[i], val);
d_Xvalid[i*include + k] = (!val);
}
}
2Dグリッドで起動:
int keep = 9000;
int include = 23000;
int width = 0.2*include;
int th = 32;
dim3 threads(th,th);
dim3 blocks ((keep+threads.x-1)/threads.x, (include+threads.y-1)/threads.y);
kernel2 <<< blocks,threads >>>( keep, include, width, d_Xco, d_Xnum,
d_Xvalid, d_Xblas );
アイデアは素晴らしいと思いますが、うまくいかず、ここでアイデアが不足しています。ここで私を助けてくれませんか?d_Xco
また、位置k
を小さな配列に格納し、それらを配列の先頭にプッシュするという問題もあると思います。そのため、順序が重要になります。
d_Xco
-------------------------------
| 2|3 |15 |4 |5 |5 | | | | | | .......
-------------------------------