/*
 * Copyright 1993-2008 NVIDIA Corporation.  All rights reserved.
 *
 * NOTICE TO USER:
 *
 * This source code is subject to NVIDIA ownership rights under U.S. and
 * international Copyright laws.  Users and possessors of this source code
 * are hereby granted a nonexclusive, royalty-free license to use this code
 * in individual and commercial software.
 *
 * NVIDIA MAKES NO REPRESENTATION ABOUT THE SUITABILITY OF THIS SOURCE
 * CODE FOR ANY PURPOSE.  IT IS PROVIDED "AS IS" WITHOUT EXPRESS OR
 * IMPLIED WARRANTY OF ANY KIND.  NVIDIA DISCLAIMS ALL WARRANTIES WITH
 * REGARD TO THIS SOURCE CODE, INCLUDING ALL IMPLIED WARRANTIES OF
 * MERCHANTABILITY, NONINFRINGEMENT, AND FITNESS FOR A PARTICULAR PURPOSE.
 * IN NO EVENT SHALL NVIDIA BE LIABLE FOR ANY SPECIAL, INDIRECT, INCIDENTAL,
 * OR CONSEQUENTIAL DAMAGES, OR ANY DAMAGES WHATSOEVER RESULTING FROM LOSS
 * OF USE, DATA OR PROFITS,  WHETHER IN AN ACTION OF CONTRACT, NEGLIGENCE
 * OR OTHER TORTIOUS ACTION,  ARISING OUT OF OR IN CONNECTION WITH THE USE
 * OR PERFORMANCE OF THIS SOURCE CODE.
 *
 * U.S. Government End Users.   This source code is a "commercial item" as
 * that term is defined at  48 C.F.R. 2.101 (OCT 1995), consisting  of
 * "commercial computer  software"  and "commercial computer software
 * documentation" as such terms are  used in 48 C.F.R. 12.212 (SEPT 1995)
 * and is provided to the U.S. Government only as a commercial end item.
 * Consistent with 48 C.F.R.12.212 and 48 C.F.R. 227.7202-1 through
 * 227.7202-4 (JUNE 1995), all U.S. Government End Users acquire the
 * source code with only those rights set forth herein.
 *
 * Any use of this source code in individual and commercial software must
 * include, in the user documentation and internal comments to the code,
 * the above Disclaimer and U.S. Government End Users Notice.
 */


// includes, system
#include <stdio.h>
#include <assert.h>

// Simple utility function to check for CUDA runtime errors
void checkCUDAError(const char* msg);

// Part3: implement the kernel
__global__ void reverseArrayBlock(int *d_out, int *d_in)
{
    int inOffset  = blockDim.x * blockIdx.x;
    int outOffset = blockDim.x * (gridDim.x - 1 - blockIdx.x);
    int in  = inOffset + threadIdx.x;
    int out = outOffset + (blockDim.x - 1 - threadIdx.x);
    d_out[out] = d_in[in];
}

////////////////////////////////////////////////////////////////////////////////
// Program main
////////////////////////////////////////////////////////////////////////////////
int main( int argc, char** argv) 
{
    // pointer for host memory and size
    int *h_a;
    int dimA = 256 * 1024; // 256K elements (1MB total)

    // pointer for device memory
    int *d_b, *d_a;

    // define grid and block size
    int numThreadsPerBlock = 256;

    // Part 1: compute number of blocks needed based on array size and desired block size
    int numBlocks = dimA / numThreadsPerBlock;  

    // allocate host and device memory
    size_t memSize = numBlocks * numThreadsPerBlock * sizeof(int);
    h_a = (int *) malloc(memSize);
    cudaMalloc( (void **) &d_a, memSize );
    cudaMalloc( (void **) &d_b, memSize );

    // Initialize input array on host
    for (int i = 0; i < dimA; ++i)
    {
        h_a[i] = i;
    }

    // Copy host array to device array
    cudaMemcpy( d_a, h_a, memSize, cudaMemcpyHostToDevice );

    // launch kernel
    dim3 dimGrid(numBlocks);
    dim3 dimBlock(numThreadsPerBlock);
    reverseArrayBlock<<< dimGrid, dimBlock >>>( d_b, d_a );

    // block until the device has completed
    cudaThreadSynchronize();

    // check if kernel execution generated an error
    // Check for any CUDA errors
    checkCUDAError("kernel invocation");

    // device to host copy
    cudaMemcpy( h_a, d_b, memSize, cudaMemcpyDeviceToHost );

    // Check for any CUDA errors
    checkCUDAError("memcpy");

    // verify the data returned to the host is correct
    for (int i = 0; i < dimA; i++)
    {
        assert(h_a[i] == dimA - 1 - i );
    }

    // free device memory
    cudaFree(d_a);
    cudaFree(d_b);

    // free host memory
    free(h_a);

    // If the program makes it this far, then the results are correct and
    // there are no run-time errors.  Good work!
    printf("Correct!\n");

    return 0;
}

void checkCUDAError(const char *msg)
{
    cudaError_t err = cudaGetLastError();
    if( cudaSuccess != err) 
    {
        fprintf(stderr, "Cuda error: %s: %s.\n", msg, cudaGetErrorString( err) );
        exit(EXIT_FAILURE);
    }                         
}