Update

GPU-Introduction.ipynb

@@ -18,9 +18,13 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": 1,
    "id": "6d20c462-711f-4f72-abbf-8bab4117e9d7",
-   "metadata": {},
+   "metadata": {
+    "vscode": {
+     "languageId": "python"
+    }
+   },
    "outputs": [],
    "source": [
     "import numpy as np\n",
@@ -30,15 +34,19 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": 2,
    "id": "99ad7f98-138d-45e4-9268-f42cb3a98f21",
-   "metadata": {},
+   "metadata": {
+    "vscode": {
+     "languageId": "python"
+    }
+   },
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "120 μs ± 0 ns per loop (mean ± std. dev. of 1 run, 1 loop each)\n"
+      "3.93 ms ± 0 ns per loop (mean ± std. dev. of 1 run, 1 loop each)\n"
      ]
     }
    ],
@@ -48,15 +56,19 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": 3,
    "id": "0d3af9b3-f418-44ed-8a23-e30aa188fd98",
-   "metadata": {},
+   "metadata": {
+    "vscode": {
+     "languageId": "python"
+    }
+   },
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "0.000225 s\n"
+      "0.000097 s\n"
      ]
     }
    ],
@@ -71,9 +83,13 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 9,
+   "execution_count": 4,
    "id": "02440471-d8c6-4ba8-8a89-e3f8c0dcca0a",
-   "metadata": {},
+   "metadata": {
+    "vscode": {
+     "languageId": "python"
+    }
+   },
    "outputs": [
     {
      "name": "stdout",
@@ -99,21 +115,9 @@
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "Python [conda env:base] *",
+   "display_name": "Python 3 (ipykernel)",
    "language": "python",
-   "name": "conda-base-py"
-  },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.12.2"
+   "name": "python3"
   }
  },
  "nbformat": 4,

GPU-Lab C 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
+}

GPU-Lab Kernel.ipynb

-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "id": "7efd9f5e-2046-4727-b611-fefdd2f05238",
-   "metadata": {},
-   "source": [
-    "# Your First GPU Kernel"
-   ]
-  },
-  {
-   "cell_type": "raw",
-   "id": "8d1a297e-6e49-4cbc-9142-442dc60f6598",
-   "metadata": {},
-   "source": [
-    "ref: https://carpentries-incubator.github.io/lesson-gpu-programming/first_program.html"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 1,
-   "id": "d8d4a6a3-aeb6-4cb4-a61d-8bb52f4849dc",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "def vector_add(A, B, C, size):\n",
-    "    for item in range(0, size):\n",
-    "        C[item] = A[item] + B[item]\n",
-    "    \n",
-    "    return C"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "54efe984-e538-47bf-a3ad-5fc808f7b1c7",
-   "metadata": {},
-   "outputs": [],
-   "source": []
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "Python [conda env:base] *",
-   "language": "python",
-   "name": "conda-base-py"
-  },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.12.2"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 5
-}