Why Output is different?
Output:
/home/kompeter/cuda-workspace/threadBlock/Debug/threadBlock Starting…
Using Device 0: GeForce 920M
gtid 0 result 1024
gtid 1024 result 1024
gtid 2047 result 1024
gtid 1023 result 1024
gtid 3072 result 2048
gtid 3071 result 2048
gtid 2048 result 2048
gtid 4095 result 2048
End
// System includes
#include <stdio.h>
#include <assert.h>
#include <math.h>
// CUDA runtime
#include <cuda_runtime.h>
#include <cuda_profiler_api.h>
// Helper functions and utilities to work with CUDA
#include <helper_functions.h>
#include <helper_cuda.h>
#include "../../common/common.h"
__device__ const int size = 4096;
__global__ void x(){
__shared__ float3 data;
int result = 0;
int gtid = blockIdx.x * blockDim.x + threadIdx.x;
data[gtid].x = 1;
__syncthreads();
for(int i=0; i<size;i++){
result = result + data[i].x;
}
if(gtid == 0 || gtid==1023 || gtid==1024 || gtid==2047)
printf("gtid %d result %d\n",gtid, result);
if(gtid == 2048 || gtid==3071 || gtid==3072 || gtid==4095)
printf("gtid %d result %d\n",gtid, result);
}
int main(int argc, char **argv){
int dev = 0;
cudaDeviceProp deviceProp;
printf("%s Starting...\n", argv[0]);
CHECK(cudaGetDeviceProperties(&deviceProp, dev));
printf("Using Device %d: %s\n", dev, deviceProp.name);
CHECK(cudaSetDevice(dev));
x << < 4, 1024 >> >();
CHECK(cudaDeviceSynchronize());
CHECK(cudaGetLastError());
CHECK(cudaDeviceReset());
printf("\nEnd\n");
return 0;
}
/* common.h
#include <sys/time.h>
#ifndef _COMMON_H
#define _COMMON_H
#define CHECK(call) \
{ \
const cudaError_t error = call; \
if (error != cudaSuccess) \
{ \
fprintf(stderr, "Error: %s:%d, ", __FILE__, __LINE__); \
fprintf(stderr, "code: %d, reason: %s\n", error, \
cudaGetErrorString(error)); \
exit(1); \
} \
}
#define CHECK_CUBLAS(call) \
{ \
cublasStatus_t err; \
if ((err = (call)) != CUBLAS_STATUS_SUCCESS) \
{ \
fprintf(stderr, "Got CUBLAS error %d at %s:%d\n", err, __FILE__, \
__LINE__); \
exit(1); \
} \
}
#define CHECK_CURAND(call) \
{ \
curandStatus_t err; \
if ((err = (call)) != CURAND_STATUS_SUCCESS) \
{ \
fprintf(stderr, "Got CURAND error %d at %s:%d\n", err, __FILE__, \
__LINE__); \
exit(1); \
} \
}
#define CHECK_CUFFT(call) \
{ \
cufftResult err; \
if ( (err = (call)) != CUFFT_SUCCESS) \
{ \
fprintf(stderr, "Got CUFFT error %d at %s:%d\n", err, __FILE__, \
__LINE__); \
exit(1); \
} \
}
#define CHECK_CUSPARSE(call) \
{ \
cusparseStatus_t err; \
if ((err = (call)) != CUSPARSE_STATUS_SUCCESS) \
{ \
fprintf(stderr, "Got error %d at %s:%d\n", err, __FILE__, __LINE__); \
cudaError_t cuda_err = cudaGetLastError(); \
if (cuda_err != cudaSuccess) \
{ \
fprintf(stderr, " CUDA error \"%s\" also detected\n", \
cudaGetErrorString(cuda_err)); \
} \
exit(1); \
} \
}
inline double seconds()
{
struct timeval tp;
struct timezone tzp;
int i = gettimeofday(&tp, &tzp);
return ((double)tp.tv_sec + (double)tp.tv_usec * 1.e-6);
}
#endif // _COMMON_H
*/
DeviceQuery:
/home/kompeter/cuda-workspace/DeviceInfo/Debug/DeviceInfo Starting…
CUDA Device Query (Runtime API) version (CUDART static linking)
Detected 1 CUDA Capable device(s)
Device 0: “GeForce 920M”
CUDA Driver Version / Runtime Version 8.0 / 8.0
CUDA Capability Major/Minor version number: 3.5
Total amount of global memory: 2004 MBytes (2101149696 bytes)
( 2) Multiprocessors, (192) CUDA Cores/MP: 384 CUDA Cores
GPU Max Clock rate: 954 MHz (0.95 GHz)
Memory Clock rate: 900 Mhz
Memory Bus Width: 64-bit
L2 Cache Size: 524288 bytes
Maximum Texture Dimension Size (x,y,z) 1D=(65536), 2D=(65536, 65536), 3D=(4096, 4096, 4096)
Maximum Layered 1D Texture Size, (num) layers 1D=(16384), 2048 layers
Maximum Layered 2D Texture Size, (num) layers 2D=(16384, 16384), 2048 layers
Total amount of constant memory: 65536 bytes
Total amount of shared memory per block: 49152 bytes
Total number of registers available per block: 65536
Warp size: 32
Maximum number of threads per multiprocessor: 2048
Maximum number of threads per block: 1024
Max dimension size of a thread block (x,y,z): (1024, 1024, 64)
Max dimension size of a grid size (x,y,z): (2147483647, 65535, 65535)
Maximum memory pitch: 2147483647 bytes
Texture alignment: 512 bytes
Concurrent copy and kernel execution: Yes with 1 copy engine(s)
Run time limit on kernels: No
Integrated GPU sharing Host Memory: No
Support host page-locked memory mapping: Yes
Alignment requirement for Surfaces: Yes
Device has ECC support: Disabled
Device supports Unified Addressing (UVA): Yes
Device PCI Domain ID / Bus ID / location ID: 0 / 1 / 0
Compute Mode:
< Default (multiple host threads can use ::cudaSetDevice() with device simultaneously) >
deviceQuery, CUDA Driver = CUDART, CUDA Driver Version = 8.0, CUDA Runtime Version = 8.0, NumDevs = 1, Device0 = GeForce 920M
Result = PASS