adding Jupyter Notebooks for cuda to sycl migration learning path (#1439)

Author: krisrak

DirectProgramming/C++SYCL/Jupyter/cuda-to-sycl-migration-training/00_SYCL_Migration_Introduction/00_SYCL_Migration_Introduction.ipynb

@@ -0,0 +1,8 @@
+Copyright Intel Corporation
+
+Permission is hereby granted, free of charge, to any person obtaining a copy of this software and associated documentation files (the "Software"), to deal in the Software without restriction, including without limitation the rights to use, copy, modify, merge, publish, distribute, sublicense, and/or sell copies of the Software, and to permit persons to whom the Software is furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
+

DirectProgramming/C++SYCL/Jupyter/cuda-to-sycl-migration-training/00_SYCL_Migration_Introduction/assets/steps.png

@@ -0,0 +1,28 @@
+## Title
+ CUDA_To_SYCL_Migration - Module 1: Simple VectorAdd
+  
+## Requirements
+| Optimized for                     | Description
+|:---                               |:---
+| OS                                | Linux* Ubuntu 18.04, 20 Windows* 10
+| Hardware                          | Skylake with GEN9 or newer
+| Software                          | Intel® oneAPI DPC++ Compiler, Jupyter Notebooks, Intel Devcloud
+  
+## Purpose
+The hands-on exercises in this notebook show how to implement migrate CUDA source to SYCL source using SYCLomatic Tool
+
+## License  
+Code samples are licensed under the MIT license. See [License.txt](https://github.com/oneapi-src/oneAPI-samples/blob/master/License.txt) for details.
+
+Third party program Licenses can be found here: [third-party-programs.txt](https://github.com/oneapi-src/oneAPI-samples/blob/master/third-party-programs.txt)
+
+## Install Directions
+
+The Jupyter notebooks are tested and can be run on Intel Devcloud.
+Below are the steps to access these Jupyter notebooks on Intel Devcloud
+1. Register on [Intel Devcloud](https://devcloud.intel.com/oneapi)
+2. Go to the "Terminal" in the Intel Devcloud
+3. Type in the below command to download the oneAPI-essentials series notebooks into your Devcloud account
+    /data/oneapi_workshop/get_jupyter_notebooks.sh
+4. Navigate to CUDA_To_SYCL_Migration folder and open the Welcome.ipynb
+

DirectProgramming/C++SYCL/Jupyter/cuda-to-sycl-migration-training/00_SYCL_Migration_Introduction/assets/syclomatic_workflow.png

@@ -0,0 +1,50 @@
+//==============================================================
+// Copyright © Intel Corporation
+//
+// SPDX-License-Identifier: MIT
+// =============================================================
+
+#include <cuda.h>
+#include <iostream>
+#include <vector>
+#define N 16
+
+//# kernel code to perform VectorAdd on GPU
+__global__ void VectorAddKernel(float* A, float* B, float* C)
+{
+        C[threadIdx.x] = A[threadIdx.x] + B[threadIdx.x];
+}
+
+int main()
+{
+        //# Initialize vectors on host
+        float A[N] = {1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1};
+        float B[N] = {2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2};
+        float C[N] = {0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0};
+
+        //# Allocate memory on device
+        float *d_A, *d_B, *d_C;
+        cudaMalloc(&d_A, N*sizeof(float));
+        cudaMalloc(&d_B, N*sizeof(float));
+        cudaMalloc(&d_C, N*sizeof(float));
+
+        //# copy vector data from host to device
+        cudaMemcpy(d_A, A, N*sizeof(float), cudaMemcpyHostToDevice);
+        cudaMemcpy(d_B, B, N*sizeof(float), cudaMemcpyHostToDevice);
+
+        //# sumbit task to compute VectorAdd on device
+        VectorAddKernel<<<1, N>>>(d_A, d_B, d_C);
+
+        //# copy result of vector data from device to host
+        cudaMemcpy(C, d_C, N*sizeof(float), cudaMemcpyDeviceToHost);
+
+        //# print result on host
+        for (int i = 0; i < N; i++) std::cout<< C[i] << " ";
+        std::cout << "\n";
+
+        //# free allocation on device
+        cudaFree(d_A);
+        cudaFree(d_B);
+        cudaFree(d_C);
+        return 0;
+}