Update

GPU-Lab Py Kernel.ipynb

+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "b6d3aebb",
+   "metadata": {
+    "vscode": {
+     "languageId": "plaintext"
+    }
+   },
+   "outputs": [],
+   "source": [
+    "ref:https://cuda-tutorial.readthedocs.io/en/latest/tutorials/tutorial01/"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "c8eff613",
+   "metadata": {
+    "vscode": {
+     "languageId": "plaintext"
+    }
+   },
+   "outputs": [],
+   "source": [
+    "import cupy\n",
+    "\n",
+    "# size of the vectors\n",
+    "size = 1024\n",
+    "\n",
+    "# allocating and populating the vectors\n",
+    "a_gpu = cupy.random.rand(size, dtype=cupy.float32)\n",
+    "b_gpu = cupy.random.rand(size, dtype=cupy.float32)\n",
+    "c_gpu = cupy.zeros(size, dtype=cupy.float32)\n",
+    "\n",
+    "# CUDA vector_add\n",
+    "vector_add_cuda_code = r'''\n",
+    "extern \"C\"\n",
+    "__global__ void vector_add(const float * A, const float * B, float * C, const int size)\n",
+    "{\n",
+    "    int item = threadIdx.x;\n",
+    "    C[item] = A[item] + B[item];\n",
+    "}\n",
+    "'''\n",
+    "vector_add_gpu = cupy.RawKernel(vector_add_cuda_code, \"vector_add\")\n",
+    "\n",
+    "vector_add_gpu((1, 1, 1), (size, 1, 1), (a_gpu, b_gpu, c_gpu, size))"
+   ]
+  }
+ ],
+ "metadata": {
+  "language_info": {
+   "name": "python"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

README.md

+# GPU Programming
+
+A collection of notebooks for learning and practicing GPU programming with CUDA.
+
+## Contents
+
+### Notebooks
+
+- **GPU-Introduction.ipynb** - Introduction to GPU computing concepts and fundamentals
+- **GPU-Check ENV.ipynb** - Verify and check GPU environment setup and CUDA configuration
+- **GPU-HW CUDA Programming.ipynb** - HomeWrok CUDA programming exercises
+- **GPU-Lab C Kernel.ipynb** - CUDA kernel programming with C language
+- **GPU-Lab Py Kernel.ipynb** - CUDA kernel programming using CuPy in Python
+
+## Overview
+
+This workspace contains practical exercises and examples for GPU programming, including:
+- Vector operations on GPU
+- CUDA kernel implementation and execution
+- GPU memory management
+- Performance optimization techniques
+
+## Requirements
+
+- CUDA Toolkit installed
+- CuPy (for Python CUDA programming)
+- Jupyter notebook environment
+
+## Getting Started
+
+Start with `GPU-Introduction.ipynb` for foundational concepts, then progress through the other notebooks to practice implementing CUDA kernels and GPU operations.