added example 02

README.md

@@ -15,7 +15,10 @@ curl https://www.khronos.org/registry/cl/api/1.2/cl.hpp -o CL/cl.hpp
 this example is based off of [this example](simpleopencl.blogspot.ca/2013/06/tutorial-simple-start-with-opencl-and-c.html) (example-ception), but it goes a bit further. In the blogspot example, two 10-element vectors are created and a thread is used for each pair of elements. In this example, 10 threads are spawned but two 100-element vectors are used, and it is shown how to split up a specific number of elements per thread.
 
 ## example 01
-See the README in the folder.
+Measures the duration of adding two vectors. See the README in the folder for more details.
+
+## example 02
+Demonstrates that one array can be modified several times without having to re-read and re-write data to and from the GPU.
 
 ## TODO
 

example02/main.cpp

@@ -0,0 +1,96 @@
+#include <iostream>
+#include <algorithm>
+#include <iterator>
+#include "../CL/cl.hpp"
+
+using namespace std;
+using namespace cl;
+
+
+int factorial(int n) {
+    return (n <= 1) ? 1 : n * factorial(n-1);
+}
+
+
+Platform getPlatform() {
+    /* Returns the first platform found. */
+    std::vector<Platform> all_platforms;
+    Platform::get(&all_platforms);
+
+    if (all_platforms.size()==0) {
+        cout << "No platforms found. Check OpenCL installation!\n";
+        exit(1);
+    }
+    return all_platforms[0];
+}
+
+
+Device getDevice(cl::Platform platform, int i, bool display=false) {
+    /* Returns the deviced specified by the index i on platform.
+     * If display is true, then all of the platforms are listed.
+     */
+    std::vector<Device> all_devices;
+    platform.getDevices(CL_DEVICE_TYPE_ALL, &all_devices);
+    if(all_devices.size()==0){
+        cout << "No devices found. Check OpenCL installation!\n";
+        exit(1);
+    }
+
+    if (display) {
+        for (int j=0; j<all_devices.size(); j++)
+            printf("Device %d: %s\n", j, all_devices[j].getInfo<CL_DEVICE_NAME>().c_str());
+    }
+    return all_devices[i];
+}
+
+
+int main() {
+    const int n = 1024;    // size of vectors
+    const int c_max = 5;   // max value to iterate to
+    const int coeff = factorial(c_max);
+
+    int A[n], B[n], C[n];     // A is initial, B is result, C is expected result
+    for (int i=0; i<n; i++) {
+        A[i] = i;
+        C[i] = coeff * i;
+    }
+    Platform default_platform = getPlatform();
+    Device default_device     = getDevice(default_platform, 1);
+    Context context({default_device});
+    Program::Sources sources;
+
+    // calculates for each element; C = A + B
+    std::string kernel_code=
+        "void kernel multiply_by(global int* A, const int c) {"
+        "   A[get_global_id(0)] = c * A[get_global_id(0)];"
+        "}";
+    sources.push_back({kernel_code.c_str(), kernel_code.length()});
+
+    Program program(context, sources);
+    if (program.build({default_device}) != CL_SUCCESS) {
+        cout << "Error building: " << program.getBuildInfo<CL_PROGRAM_BUILD_LOG>(default_device) << std::endl;
+        exit(1);
+    }
+
+    Buffer buffer_A(context, CL_MEM_READ_WRITE, sizeof(int) * n);
+    CommandQueue queue(context, default_device);
+    queue.enqueueWriteBuffer(buffer_A, CL_TRUE, 0, sizeof(int)*n, A);
+
+    Kernel multiply_by = cl::Kernel(program, "multiply_by");
+    multiply_by.setArg(0, buffer_A);
+
+    for (int c=2; c<=c_max; c++) {
+        multiply_by.setArg(1, c);
+        queue.enqueueNDRangeKernel(multiply_by, cl::NullRange, cl::NDRange(n), cl::NDRange(32));
+    }
+
+    queue.enqueueReadBuffer(buffer_A, CL_TRUE, 0, sizeof(int)*n, B);
+
+    if (std::equal(std::begin(B), std::end(B), std::begin(C)))
+        cout << "Arrays are equal!" << endl;
+    else
+        cout << "Uh-oh, the arrays aren't equal!" << endl;
+
+    return 0;
+}
+