Merge pull request #3 from gjbex/development

Fix environments

Author: gjbex

source-code/README.md

@@ -6,7 +6,5 @@ Sample code for performing computations on a GPU.
 ## What is it?
 
 1. `pycuda`: directory illustrating pyCUDA.
-1. `scikit_cuda`: code illustrating linear algebra on a GPU device.  This is an
-   older library and has been at least partially superceded by CuPy.
 1. `numba`: code illustrating using numba for GPU computing.
 1. `cupy`: Jupyter notebook illustrating some aspects of the `cupy` package.

source-code/cupy/cupy.ipynb

@@ -10,7 +10,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 15,
+   "execution_count": 1,
    "id": "c5430b2b-a033-4d85-a76a-eb9c958eb66d",
    "metadata": {},
    "outputs": [],
@@ -67,8 +67,8 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "CPU times: user 975 ms, sys: 1.03 s, total: 2.01 s\n",
-      "Wall time: 127 ms\n"
+      "CPU times: user 1.93 s, sys: 211 ms, total: 2.14 s\n",
+      "Wall time: 136 ms\n"
      ]
     }
    ],
@@ -87,8 +87,8 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "CPU times: user 427 ms, sys: 2.04 s, total: 2.47 s\n",
-      "Wall time: 1.26 s\n"
+      "CPU times: user 1.55 s, sys: 293 ms, total: 1.84 s\n",
+      "Wall time: 1.79 s\n"
      ]
     }
    ],
@@ -116,8 +116,8 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "CPU times: user 964 ms, sys: 2.58 s, total: 3.55 s\n",
-      "Wall time: 3.67 s\n"
+      "CPU times: user 113 ms, sys: 79.7 ms, total: 193 ms\n",
+      "Wall time: 195 ms\n"
      ]
     }
    ],
@@ -136,8 +136,8 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "CPU times: user 2.44 ms, sys: 37 µs, total: 2.48 ms\n",
-      "Wall time: 2.05 ms\n"
+      "CPU times: user 3.14 ms, sys: 400 μs, total: 3.54 ms\n",
+      "Wall time: 2.58 ms\n"
      ]
     }
    ],
@@ -164,8 +164,8 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "CPU times: user 360 ms, sys: 15 ms, total: 375 ms\n",
-      "Wall time: 378 ms\n"
+      "CPU times: user 197 ms, sys: 29.6 ms, total: 227 ms\n",
+      "Wall time: 227 ms\n"
      ]
     }
    ],
@@ -185,8 +185,8 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "CPU times: user 432 µs, sys: 1.49 ms, total: 1.92 ms\n",
-      "Wall time: 1.08 ms\n"
+      "CPU times: user 2.03 ms, sys: 259 μs, total: 2.29 ms\n",
+      "Wall time: 1.72 ms\n"
      ]
     }
    ],
@@ -203,6 +203,14 @@
     "## Matrix power"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "id": "8f38d6ea-b522-4eb6-930b-0f577c3a4277",
+   "metadata": {},
+   "source": [
+    "Since there seems to be an issue with `%%timeit` in combination with `cp.linalg.matrix_power` `%%time` is used in this section."
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": 10,
@@ -223,17 +231,19 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "30.3 ms ± 5.26 ms per loop (mean ± std. dev. of 7 runs, 10 loops each)\n"
+      "CPU times: user 1.5 s, sys: 424 ms, total: 1.93 s\n",
+      "Wall time: 130 ms\n"
      ]
     }
    ],
    "source": [
-    "%timeit np.linalg.matrix_power(D, 10)"
+    "%%time\n",
+    "p = np.linalg.matrix_power(D, 10);"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 21,
+   "execution_count": 12,
    "id": "2cca5817-c795-4240-8a56-6361aade49cf",
    "metadata": {},
    "outputs": [],
@@ -251,12 +261,14 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "43.7 ms ± 2.55 µs per loop (mean ± std. dev. of 7 runs, 1,000 loops each)\n"
+      "CPU times: user 143 ms, sys: 10.6 ms, total: 153 ms\n",
+      "Wall time: 7.04 ms\n"
      ]
     }
    ],
    "source": [
-    "%timeit cp.linalg.matrix_power(D_dev, 10)"
+    "%%time\n",
+    "p_dev = cp.linalg.matrix_power(D_dev, 10);"
    ]
   },
   {
@@ -269,15 +281,15 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 16,
+   "execution_count": 14,
    "id": "dbae0849-7d44-4d8e-8a2a-104d08e63016",
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "261 ms ± 81.5 ms per loop (mean ± std. dev. of 7 runs, 1 loop each)\n"
+      "497 ms ± 89.1 ms per loop (mean ± std. dev. of 7 runs, 1 loop each)\n"
      ]
     }
    ],
@@ -288,15 +300,15 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 22,
+   "execution_count": 15,
    "id": "33e09563-e5a0-47ca-b860-7b0581d7a11d",
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "728 ms ± 16.7 ms per loop (mean ± std. dev. of 7 runs, 1 loop each)\n"
+      "554 ms ± 18.3 ms per loop (mean ± std. dev. of 7 runs, 1 loop each)\n"
      ]
     }
    ],
@@ -307,15 +319,15 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 17,
+   "execution_count": 16,
    "id": "2552a033-b7b0-423f-a162-ad559d696821",
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "49.8 ms ± 4.96 ms per loop (mean ± std. dev. of 7 runs, 10 loops each)\n"
+      "132 ms ± 22.4 ms per loop (mean ± std. dev. of 7 runs, 10 loops each)\n"
      ]
     }
    ],
@@ -326,15 +338,16 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 23,
+   "execution_count": 17,
    "id": "b74986ef-b699-40db-ae50-c759b5c5a9f7",
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "34 ms ± 36.5 µs per loop (mean ± std. dev. of 7 runs, 10 loops each)\n"
+      "The slowest run took 16.34 times longer than the fastest. This could mean that an intermediate result is being cached.\n",
+      "14.5 ms ± 16 ms per loop (mean ± std. dev. of 7 runs, 1 loop each)\n"
      ]
     }
    ],
@@ -360,7 +373,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.11.6"
+   "version": "3.12.8"
   }
  },
  "nbformat": 4,

source-code/pycuda/curand.ipynb

@@ -54,7 +54,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 48,
+   "execution_count": 2,
    "id": "122a78d1-9d07-4484-8f30-a01ed58a9715",
    "metadata": {},
    "outputs": [],
@@ -96,7 +96,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 44,
+   "execution_count": 3,
    "id": "71134a08-5195-4205-ae1c-51c7298704e7",
    "metadata": {},
    "outputs": [],
@@ -118,7 +118,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 45,
+   "execution_count": 4,
    "id": "a872e28c-9256-4d50-b46c-f8381131eda1",
    "metadata": {},
    "outputs": [],
@@ -128,7 +128,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 46,
+   "execution_count": 5,
    "id": "53ddbb43-0f22-427e-83a6-c6d0264e958e",
    "metadata": {},
    "outputs": [],
@@ -146,7 +146,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 47,
+   "execution_count": 6,
    "id": "f86f0258-64c8-44a0-b8b3-5a6f5d24e362",
    "metadata": {},
    "outputs": [
@@ -191,7 +191,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.9.7"
+   "version": "3.12.8"
   }
  },
  "nbformat": 4,