matrixmul_gold.cpp

采用GPU通用计算API（CUDA）实现矩阵相乘。

/*
 * Copyright 1993-2007 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.
 */

////////////////////////////////////////////////////////////////////////////////
// export C interface
extern "C"
void computeGold( float*, const float*, const float*, unsigned int, unsigned int, unsigned int);

////////////////////////////////////////////////////////////////////////////////
//! Compute reference data set
//! C = A * B
//! @param C          reference data, computed but preallocated
//! @param A          matrix A as provided to device
//! @param B          matrix B as provided to device
//! @param hA         height of matrix A
//! @param wB         width of matrix B
////////////////////////////////////////////////////////////////////////////////
void
computeGold(float* C, const float* A, const float* B, unsigned int hA, unsigned int wA, unsigned int wB)
{
    for (unsigned int i = 0; i < hA; ++i)
        for (unsigned int j = 0; j < wB; ++j) {
            double sum = 0;
            for (unsigned int k = 0; k < wA; ++k) {
                double a = A[i * wA + k];
                double b = B[k * wB + j];
                sum += a * b;
            }
            C[i * wB + j] = (float)sum;
        }
}