waltner

// 1D grid of 1D blocks
__device__ int getGlobalIdx_1D_1D()
{
	return blockIdx.x *blockDim.x + threadIdx.x;
}

// 1D grid of 2D blocks
__device__ int getGlobalIdx_1D_2D()
{
	return blockIdx.x * blockDim.x * blockDim.y + threadIdx.y * blockDim.x + threadIdx.x;

waltner

// GPU timing example
// uses CUDA_SAFE_CALL [https://gist.github.com/waltner/ece68738c42d38c5e9bd1862c43b1146.js]

float elapsed_time = 0.0;

cudaEvent_t start, stop;
CUDA_SAFE_CALL(cudaEventCreate(&start));
CUDA_SAFE_CALL(cudaEventCreate(&stop));
CUDA_SAFE_CALL(cudaEventRecord(start,0));

waltner

#ifndef CUDABASE_H_
#define CUDABASE_H_

#include <cuda.h>
#include <iostream>
#include <stdio.h>

#  define CUDA_SAFE_CALL_NO_SYNC( call) do {                                 \
    cudaError err = call;                                                    \
    if( cudaSuccess != err) {                                                \