AxoyTO

#include <cuda.h>
#include <chrono>
#include <cstdlib>
#include <iostream>

__global__ void addVectorsKernel(const double* A, const double* B, double* C, double n) {
  int i = blockDim.x * blockIdx.x + threadIdx.x;
  if (i < n) {
    C[i] = A[i] + B[i];
  }

AxoyTO

#include <cuda.h>
#include <chrono>
#include <cstdlib>
#include <iostream>

__global__ void transposeKernel(const double* A, double* AT, int N) {
  int xIndex = blockDim.x * blockIdx.x + threadIdx.x;
  int yIndex = blockDim.y * blockIdx.y + threadIdx.y;

  int index = xIndex + N * yIndex;

AxoyTO

#include <cuda.h>
#include <cuda_runtime.h>
#include <device_launch_parameters.h>
#include <cstdlib>
#include <iostream>

__global__ void DivergencyKernel(float* a, int N) {
  int x = blockDim.x * blockIdx.x + threadIdx.x;

  if (x % 2 == 0) {

AxoyTO

#include <cuda.h>
#include <cuda_runtime.h>
#include <device_launch_parameters.h>
#include <chrono>
#include <cstdlib>
#include <iostream>

__global__ void reverseKernel(float* A, int N) {
  int i = blockDim.x * blockIdx.x + threadIdx.x;

AxoyTO

// UCSC CMPE220 Advanced Parallel Processing
// Prof. Heiner Leitz
// Author: Marcelo Siero.
// Modified from code by:: Andreas Goetz (agoetz@sdsc.edu)
// CUDA program to perform 1D stencil operation in parallel on the GPU
//
// /* FIXME */ COMMENTS ThAT REQUIRE ATTENTION

#include <cuda.h>
#include <device_launch_parameters.h>

AxoyTO

//
//  main.cpp
//
//
//  Created by Elijah Afanasiev on 25.09.2018.
//
//

// System includes
#include <assert.h>

AxoyTO

#include <cuda.h>
#include <cuda_runtime.h>
#include <device_launch_parameters.h>
#include <stdio.h>
#include <cstdlib>
#include <iostream>

__global__ void vectorAddGPU(float* a, float* b, float* c, int N) {
  int idx = blockIdx.x * blockDim.x + threadIdx.x;

AxoyTO

#include <cuda_profiler_api.h>
#include <cfloat>
#include <chrono>
#include <iostream>

using namespace std;

///////////////////////////////////////////////////////////////////////////////////////////////////////////

cudaError_t SAFE_CALL(cudaError_t result) {

AxoyTO

//
//  main.cpp
//
//
//  Created by Elijah Afanasiev on 25.09.2018.
//
//

// System includes
#include <assert.h>

AxoyTO

// High level matrix multiplication on GPU using CUDA with Thrust, CURAND and
// CUBLAS C(m,n) = A(m,k) * B(k,n)
#include <cublas_v2.h>
#include <curand.h>
#include <cstdlib>
#include <ctime>
#include <iostream>

#include <thrust/device_vector.h>
#include <thrust/host_vector.h>