C++ 执行少量插入/移位的并行算法
假设我有一个由8个数字组成的数组a，我有另一个由数字组成的数组B来确定a中的数字应该向右移动多少个位置 A 3,6,7,8,1,2,3,5 b0,1,0,0,0,0,0,0,0,0 0表示有效，1表示此数字应在后1位，输出数组应在后3位之间插入0，输出数组C应为： C:3,0,6,7,8,1,2,3 是否插入0或其他内容并不重要，关键是3之后的所有数字都移动了一个位置。出站号码将不再在数组中 另一个例子： A 3,6,7,8,1,2,3,5 b0,1,0,0,2,0,0,0,0 c3,0,6,7,8,0,1,2 A 3,6,7,8,1,2,3,5 b0,1,0,0,1,0,0,0 c3,0,6,7,8,1,2,3 我正在考虑使用扫描/前缀和或类似的方法来解决这个问题。而且这个阵列很小，我应该能够在一个扭曲中适应阵列（一种可能的方法） 由于移位的模糊性（C++ 执行少量插入/移位的并行算法,c++,algorithm,cuda,parallel-processing,gpu,C++,Algorithm,Cuda,Parallel Processing,Gpu,假设我有一个由8个数字组成的数组a，我有另一个由数字组成的数组B来确定a中的数字应该向右移动多少个位置 A 3,6,7,8,1,2,3,5 b0,1,0,0,0,0,0,0,0,0 0表示有效，1表示此数字应在后1位，输出数组应在后3位之间插入0，输出数组C应为： C:3,0,6,7,8,1,2,3 是否插入0或其他内容并不重要，关键是3之后的所有数字都移动了一个位置。出站号码将不再在数组中 另一个例子： A 3,6,7,8,1,2,3,5 b0,1,0,0,2,0,0,0,0 c3,0,6,7
0,1,0,10,1,1,10,1,0,00, 1, 0, 0 (shift pattern)
0, 1, 1, 1 (offset pattern)
0, 1, 0, 0, 2, 0, 0, 0
0, 1, 1, 1, 2, 2, 2, 2
\u ballot（） 1 0 1 1 0 1 1 1 (this is a single binary 8-bit value in this case)
+ 0 0 0 0 0 0 1 0 (the only 1 bit in this value will be at the lane index)
= 1 0 1 1 1 0 0 1
= 0 0 0 0 1 1 1 0
\uuu popc（）2\uuu shfl\u down（） 0, 1, 1, 1, 2, 2, 2, 2
\uuuu device\uuuumydelta$ cat t475.cu
#include <stdio.h>
#define DSIZE 8
#define cudaCheckErrors(msg) \
do { \
cudaError_t __err = cudaGetLastError(); \
if (__err != cudaSuccess) { \
fprintf(stderr, "Fatal error: %s (%s at %s:%d)\n", \
msg, cudaGetErrorString(__err), \
__FILE__, __LINE__); \
fprintf(stderr, "*** FAILED - ABORTING\n"); \
exit(1); \
} \
} while (0)
__device__ int mydelta(const int shift){
unsigned nz = __ballot(shift == 0);
unsigned mylane = (threadIdx.x & 31);
unsigned lanebit = 1<<mylane;
unsigned temp = nz + lanebit;
temp = nz ^ temp;
unsigned delta = __popc(temp);
return delta-1;
}
__global__ void mykernel(const int *data, const unsigned *shift, int *result, const int limit){ // limit <= 32
if (threadIdx.x < limit){
unsigned lshift = shift[(limit - 1) - threadIdx.x];
unsigned delta = mydelta(lshift);
unsigned myshift = __shfl_down(lshift, delta);
myshift = __shfl(myshift, ((limit -1) - threadIdx.x)); // reverse offset pattern
result[threadIdx.x] = 0;
if ((myshift + threadIdx.x) < limit)
result[threadIdx.x + myshift] = data[threadIdx.x];
}
}
int main(){
int A[DSIZE] = {3, 6, 7, 8, 1, 2, 3, 5};
unsigned tc1B[DSIZE] = {0, 1, 0, 0, 0, 0, 0, 0};
unsigned tc2B[DSIZE] = {0, 1, 0, 0, 2, 0, 0, 0};
unsigned tc3B[DSIZE] = {0, 1, 0, 0, 1, 0, 0, 0};
int *d_data, *d_result, *h_result;
unsigned *d_shift;
h_result = (int *)malloc(DSIZE*sizeof(int));
if (h_result == NULL) { printf("malloc fail\n"); return 1;}
cudaMalloc(&d_data, DSIZE*sizeof(int));
cudaMalloc(&d_shift, DSIZE*sizeof(unsigned));
cudaMalloc(&d_result, DSIZE*sizeof(int));
cudaCheckErrors("cudaMalloc fail");
cudaMemcpy(d_data, A, DSIZE*sizeof(int), cudaMemcpyHostToDevice);
cudaMemcpy(d_shift, tc1B, DSIZE*sizeof(unsigned), cudaMemcpyHostToDevice);
cudaCheckErrors("cudaMempcyH2D fail");
mykernel<<<1,32>>>(d_data, d_shift, d_result, DSIZE);
cudaDeviceSynchronize();
cudaCheckErrors("kernel fail");
cudaMemcpy(h_result, d_result, DSIZE*sizeof(int), cudaMemcpyDeviceToHost);
cudaCheckErrors("cudaMempcyD2H fail");
printf("index: ");
for (int i = 0; i < DSIZE; i++)
printf("%d, ", i);
printf("\nA: ");
for (int i = 0; i < DSIZE; i++)
printf("%d, ", A[i]);
printf("\ntc1 B: ");
for (int i = 0; i < DSIZE; i++)
printf("%d, ", tc1B[i]);
printf("\ntc1 C: ");
for (int i = 0; i < DSIZE; i++)
printf("%d, ", h_result[i]);
cudaMemcpy(d_shift, tc2B, DSIZE*sizeof(unsigned), cudaMemcpyHostToDevice);
cudaCheckErrors("cudaMempcyH2D fail");
mykernel<<<1,32>>>(d_data, d_shift, d_result, DSIZE);
cudaDeviceSynchronize();
cudaCheckErrors("kernel fail");
cudaMemcpy(h_result, d_result, DSIZE*sizeof(int), cudaMemcpyDeviceToHost);
cudaCheckErrors("cudaMempcyD2H fail");
printf("\ntc2 B: ");
for (int i = 0; i < DSIZE; i++)
printf("%d, ", tc2B[i]);
printf("\ntc2 C: ");
for (int i = 0; i < DSIZE; i++)
printf("%d, ", h_result[i]);
cudaMemcpy(d_shift, tc3B, DSIZE*sizeof(unsigned), cudaMemcpyHostToDevice);
cudaCheckErrors("cudaMempcyH2D fail");
mykernel<<<1,32>>>(d_data, d_shift, d_result, DSIZE);
cudaDeviceSynchronize();
cudaCheckErrors("kernel fail");
cudaMemcpy(h_result, d_result, DSIZE*sizeof(int), cudaMemcpyDeviceToHost);
cudaCheckErrors("cudaMempcyD2H fail");
printf("\ntc3 B: ");
for (int i = 0; i < DSIZE; i++)
printf("%d, ", tc3B[i]);
printf("\ntc2 C: ");
for (int i = 0; i < DSIZE; i++)
printf("%d, ", h_result[i]);
printf("\n");
return 0;
}
$ nvcc -arch=sm_35 -o t475 t475.cu
$ ./t475
index: 0, 1, 2, 3, 4, 5, 6, 7,
A: 3, 6, 7, 8, 1, 2, 3, 5,
tc1 B: 0, 1, 0, 0, 0, 0, 0, 0,
tc1 C: 3, 0, 6, 7, 8, 1, 2, 3,
tc2 B: 0, 1, 0, 0, 2, 0, 0, 0,
tc2 C: 3, 0, 6, 7, 8, 0, 1, 2,
tc3 B: 0, 1, 0, 0, 1, 0, 0, 0,
tc2 C: 3, 0, 6, 7, 8, 1, 2, 3,
$
$cat t475.cu
#包括
#定义DSIZE 8
#定义cudaCheckErrors（msg）\
做{\
cudaError\u t\u err=cudaGetLastError（）\
如果（_err！=cudaSuccess）{\
fprintf（标准，“致命错误：%s（%s位于%s:%d）\n”\
msg，cudaGetErrorString（_err）\
__文件（行）\
fprintf（stderr，“***失败-中止\n”）\
出口（1）\
} \
}而（0）
__设备_uuint mydelta（常数int移位）{
未签署的新西兰=无记名投票（shift=0）；
无符号mylane=（threadIdx.x&31）；
unsigned lanebit=1I我认为您的示例中存在一些歧义。假设在上一个示例中，我使用了b0,1,0,0,0,0
，是输出（C
）有什么不同吗？如果没有，对于b0，2，1，0，0，0，0，0，0
，输出数组应该是什么样子？当然没有我建议的模糊性，这个问题很容易用B
上的包含前缀和来解决。第一个问题：没有区别，第二个问题我忘了提到。不会发生的，数组A是“排序”的为了保证这一点。我觉得前缀和是一个解决方案，但我搞不懂。我不习惯考虑这种并行算法。非常感谢你的时间和努力！
$ cat t475.cu
#include <stdio.h>
#define DSIZE 8
#define cudaCheckErrors(msg) \
do { \
cudaError_t __err = cudaGetLastError(); \
if (__err != cudaSuccess) { \
fprintf(stderr, "Fatal error: %s (%s at %s:%d)\n", \
msg, cudaGetErrorString(__err), \
__FILE__, __LINE__); \
fprintf(stderr, "*** FAILED - ABORTING\n"); \
exit(1); \
} \
} while (0)
__device__ int mydelta(const int shift){
unsigned nz = __ballot(shift == 0);
unsigned mylane = (threadIdx.x & 31);
unsigned lanebit = 1<<mylane;
unsigned temp = nz + lanebit;
temp = nz ^ temp;
unsigned delta = __popc(temp);
return delta-1;
}
__global__ void mykernel(const int *data, const unsigned *shift, int *result, const int limit){ // limit <= 32
if (threadIdx.x < limit){
unsigned lshift = shift[(limit - 1) - threadIdx.x];
unsigned delta = mydelta(lshift);
unsigned myshift = __shfl_down(lshift, delta);
myshift = __shfl(myshift, ((limit -1) - threadIdx.x)); // reverse offset pattern
result[threadIdx.x] = 0;
if ((myshift + threadIdx.x) < limit)
result[threadIdx.x + myshift] = data[threadIdx.x];
}
}
int main(){
int A[DSIZE] = {3, 6, 7, 8, 1, 2, 3, 5};
unsigned tc1B[DSIZE] = {0, 1, 0, 0, 0, 0, 0, 0};
unsigned tc2B[DSIZE] = {0, 1, 0, 0, 2, 0, 0, 0};
unsigned tc3B[DSIZE] = {0, 1, 0, 0, 1, 0, 0, 0};
int *d_data, *d_result, *h_result;
unsigned *d_shift;
h_result = (int *)malloc(DSIZE*sizeof(int));
if (h_result == NULL) { printf("malloc fail\n"); return 1;}
cudaMalloc(&d_data, DSIZE*sizeof(int));
cudaMalloc(&d_shift, DSIZE*sizeof(unsigned));
cudaMalloc(&d_result, DSIZE*sizeof(int));
cudaCheckErrors("cudaMalloc fail");
cudaMemcpy(d_data, A, DSIZE*sizeof(int), cudaMemcpyHostToDevice);
cudaMemcpy(d_shift, tc1B, DSIZE*sizeof(unsigned), cudaMemcpyHostToDevice);
cudaCheckErrors("cudaMempcyH2D fail");
mykernel<<<1,32>>>(d_data, d_shift, d_result, DSIZE);
cudaDeviceSynchronize();
cudaCheckErrors("kernel fail");
cudaMemcpy(h_result, d_result, DSIZE*sizeof(int), cudaMemcpyDeviceToHost);
cudaCheckErrors("cudaMempcyD2H fail");
printf("index: ");
for (int i = 0; i < DSIZE; i++)
printf("%d, ", i);
printf("\nA: ");
for (int i = 0; i < DSIZE; i++)
printf("%d, ", A[i]);
printf("\ntc1 B: ");
for (int i = 0; i < DSIZE; i++)
printf("%d, ", tc1B[i]);
printf("\ntc1 C: ");
for (int i = 0; i < DSIZE; i++)
printf("%d, ", h_result[i]);
cudaMemcpy(d_shift, tc2B, DSIZE*sizeof(unsigned), cudaMemcpyHostToDevice);
cudaCheckErrors("cudaMempcyH2D fail");
mykernel<<<1,32>>>(d_data, d_shift, d_result, DSIZE);
cudaDeviceSynchronize();
cudaCheckErrors("kernel fail");
cudaMemcpy(h_result, d_result, DSIZE*sizeof(int), cudaMemcpyDeviceToHost);
cudaCheckErrors("cudaMempcyD2H fail");
printf("\ntc2 B: ");
for (int i = 0; i < DSIZE; i++)
printf("%d, ", tc2B[i]);
printf("\ntc2 C: ");
for (int i = 0; i < DSIZE; i++)
printf("%d, ", h_result[i]);
cudaMemcpy(d_shift, tc3B, DSIZE*sizeof(unsigned), cudaMemcpyHostToDevice);
cudaCheckErrors("cudaMempcyH2D fail");
mykernel<<<1,32>>>(d_data, d_shift, d_result, DSIZE);
cudaDeviceSynchronize();
cudaCheckErrors("kernel fail");
cudaMemcpy(h_result, d_result, DSIZE*sizeof(int), cudaMemcpyDeviceToHost);
cudaCheckErrors("cudaMempcyD2H fail");
printf("\ntc3 B: ");
for (int i = 0; i < DSIZE; i++)
printf("%d, ", tc3B[i]);
printf("\ntc2 C: ");
for (int i = 0; i < DSIZE; i++)
printf("%d, ", h_result[i]);
printf("\n");
return 0;
}
$ nvcc -arch=sm_35 -o t475 t475.cu
$ ./t475
index: 0, 1, 2, 3, 4, 5, 6, 7,
A: 3, 6, 7, 8, 1, 2, 3, 5,
tc1 B: 0, 1, 0, 0, 0, 0, 0, 0,
tc1 C: 3, 0, 6, 7, 8, 1, 2, 3,
tc2 B: 0, 1, 0, 0, 2, 0, 0, 0,
tc2 C: 3, 0, 6, 7, 8, 0, 1, 2,
tc3 B: 0, 1, 0, 0, 1, 0, 0, 0,
tc2 C: 3, 0, 6, 7, 8, 1, 2, 3,
$