/*
 * Copyright 1993-2012 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.
 */

/* This example demonstrates how to use the CUBLAS library
 * by scaling an array of floating-point values on the device
 * and comparing the result to the same operation performed
 * on the host.
 */

/* Includes, system */
#include <stdio.h>
#include <stdlib.h>
#include <string.h>

/* Includes, cuda */
#include <cuda_runtime.h>
#include <cublas_v2.h>
//#include <shrQATest.h>

/* Matrix size */
#define N  (275)

/* Host implementation of a simple version of sgemm */
static void simple_sgemm(int n, float alpha, const float *A, const float *B,
                         float beta, float *C)
{
    int i;
    int j;
    int k;
    for (i = 0; i < n; ++i) {
        for (j = 0; j < n; ++j) {
            float prod = 0;
            for (k = 0; k < n; ++k) {
                prod += A[k * n + i] * B[j * n + k];
            }
            C[j * n + i] = alpha * prod + beta * C[j * n + i];
        }
    }
}

/* Main */
int main(int argc, char** argv)
{    
    cublasStatus_t status;
    float* h_A;
    float* h_B;
    float* h_C;
    float* h_C_ref;
    float* d_A = 0;
    float* d_B = 0;
    float* d_C = 0;
    float alpha = 1.0f;
    float beta = 0.0f;
    int n2 = N * N;
    int i;
    
    cublasHandle_t handle;

  
    /* Initialize CUBLAS */
    printf("simpleCUBLAS test running..\n");

    cublasCreate(&handle);

    /* Allocate host memory for the matrices */
    h_A = (float*)malloc(n2 * sizeof(h_A[0]));
    h_B = (float*)malloc(n2 * sizeof(h_B[0]));
    h_C = (float*)malloc(n2 * sizeof(h_C[0]));
    
    
    /* Fill the matrices with test data */
    for (i = 0; i < n2; i++) {
        h_A[i] = rand() / (float)RAND_MAX;
        h_B[i] = rand() / (float)RAND_MAX;
        h_C[i] = rand() / (float)RAND_MAX;
    }

    /* Allocate device memory for the matrices */
    cudaMalloc((void**)&d_A, n2 * sizeof(d_A[0]));
    cudaMalloc((void**)&d_B, n2 * sizeof(d_B[0]));
    cudaMalloc((void**)&d_C, n2 * sizeof(d_C[0]));

    /* Initialize the device matrices with the host matrices */
    cublasSetVector(n2, sizeof(h_A[0]), h_A, 1, d_A, 1);
    cublasSetVector(n2, sizeof(h_B[0]), h_B, 1, d_B, 1);
    cublasSetVector(n2, sizeof(h_C[0]), h_C, 1, d_C, 1);

    /* Performs operation using plain C code */
    simple_sgemm(N, alpha, h_A, h_B, beta, h_C);
    h_C_ref = h_C;

    /* Performs operation using cublas */
    cublasSgemm(handle, CUBLAS_OP_N, CUBLAS_OP_N, N, N, N, &alpha, d_A, N, d_B, N, &beta, d_C, N);

    /* Allocate host memory for reading back the result from device memory */
    h_C = (float*)malloc(n2 * sizeof(h_C[0]));
    /* Read the result back */
    cublasGetVector(n2, sizeof(h_C[0]), d_C, 1, h_C, 1);

    /* Check result against reference */
    for (i = 0; i < 10; ++i) {
      printf("%1.20f %1.20f\n", h_C_ref[i], h_C[i]);
    }


    /* Memory clean up */
    free(h_A);
    free(h_B);
    free(h_C);
    free(h_C_ref);

    cudaFree(d_A);
    cudaFree(d_B);
    cudaFree(d_C);
  
    /* Shutdown */
    cublasDestroy(handle);
  
    return EXIT_SUCCESS;
}