{ "cells": [ { "cell_type": "markdown", "id": "adc648cd-421d-4b62-8e6f-a24200a4fcca", "metadata": {}, "source": [ "# Performances of 2D integration vs 1D integration\n", "\n", "This is dependant on:\n", "* Number of azimuthal bins\n", "* Pixel splitting\n", "* Algorithm\n", "* Implementation (i.e. programming language)\n", "* Hardware used\n", "\n", "Thus there is no general answer. But here is a quick benchmark to evaluate the penality on performances:" ] }, { "cell_type": "code", "execution_count": 1, "id": "9215b540-b06d-4ca5-aa01-288379e165b5", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Python version: 3.13.1 | packaged by conda-forge | (main, Jan 13 2025, 09:53:10) [GCC 13.3.0]\n", "PyFAI version: 2025.4.0-dev0\n" ] } ], "source": [ "import sys\n", "import os\n", "import time\n", "import numpy\n", "import fabio\n", "import pyFAI\n", "from pyFAI.test.utilstest import UtilsTest\n", "import pyFAI.method_registry\n", "import pyFAI.integrator.azimuthal\n", "print(f\"Python version: {sys.version}\")\n", "print(f\"PyFAI version: {pyFAI.version}\")\n", "start_time = time.perf_counter()" ] }, { "cell_type": "code", "execution_count": 3, "id": "b3a6bd65-9b17-4c20-ad4a-870242eeed1b", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "81\n" ] } ], "source": [ "print(len(pyFAI.method_registry.IntegrationMethod.list_available()))" ] }, { "cell_type": "code", "execution_count": 4, "id": "1479c126-f758-42e0-9209-3c6af91ada5a", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "Detector Pilatus 1M\t PixelSize= 172µm, 172µm\t BottomRight (3)\n", "Wavelength= 1.000000e-10 m\n", "SampleDetDist= 1.583231e+00 m\tPONI= 3.341702e-02, 4.122778e-02 m\trot1=0.006487 rot2=0.007558 rot3=0.000000 rad\n", "DirectBeamDist= 1583.310 mm\tCenter: x=179.981, y=263.859 pix\tTilt= 0.571° tiltPlanRotation= 130.640° 𝛌= 1.000Å" ] }, "execution_count": 4, "metadata": {}, "output_type": "execute_result" } ], "source": [ "ai = pyFAI.load(UtilsTest.getimage(\"Pilatus1M.poni\"))\n", "img = fabio.open(UtilsTest.getimage(\"Pilatus1M.edf\")).data\n", "ai" ] }, { "cell_type": "code", "execution_count": 5, "id": "aea1ab6d-afc5-4152-a60b-8b25dc7d460b", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Method(dim=1, split='no', algo='histogram', impl='python', target=None)\n", "32.2 ms ± 153 μs per loop (mean ± std. dev. of 7 runs, 10 loops each)\n", "Method(dim=2, split='no', algo='histogram', impl='python', target=None)\n", "99.7 ms ± 314 μs per loop (mean ± std. dev. of 7 runs, 10 loops each)\n", "Method(dim=1, split='no', algo='histogram', impl='cython', target=None)\n", "12.4 ms ± 17.9 μs per loop (mean ± std. dev. of 7 runs, 100 loops each)\n", "Method(dim=2, split='no', algo='histogram', impl='cython', target=None)\n", "21.1 ms ± 159 μs per loop (mean ± std. dev. of 7 runs, 10 loops each)\n", "Method(dim=1, split='bbox', algo='histogram', impl='cython', target=None)\n", "26.9 ms ± 41.4 μs per loop (mean ± std. dev. of 7 runs, 10 loops each)\n", "Method(dim=2, split='bbox', algo='histogram', impl='cython', target=None)\n", "35.7 ms ± 208 μs per loop (mean ± std. dev. of 7 runs, 10 loops each)\n", "Method(dim=1, split='full', algo='histogram', impl='cython', target=None)\n", "152 ms ± 639 μs per loop (mean ± std. dev. of 7 runs, 10 loops each)\n", "Method(dim=2, split='full', algo='histogram', impl='cython', target=None)\n", "215 ms ± 104 μs per loop (mean ± std. dev. of 7 runs, 1 loop each)\n", "Method(dim=2, split='pseudo', algo='histogram', impl='cython', target=None)\n", "370 ms ± 1.93 ms per loop (mean ± std. dev. of 7 runs, 1 loop each)\n", "Method(dim=1, split='no', algo='csr', impl='cython', target=None)\n", "7.6 ms ± 455 μs per loop (mean ± std. dev. of 7 runs, 100 loops each)\n", "Method(dim=2, split='no', algo='csr', impl='cython', target=None)\n", "8.34 ms ± 1e+03 μs per loop (mean ± std. dev. of 7 runs, 100 loops each)\n", "Method(dim=1, split='bbox', algo='csr', impl='cython', target=None)\n", "8.23 ms ± 1.57 ms per loop (mean ± std. dev. of 7 runs, 100 loops each)\n", "Method(dim=2, split='bbox', algo='csr', impl='cython', target=None)\n", "8.48 ms ± 399 μs per loop (mean ± std. dev. of 7 runs, 100 loops each)\n", "Method(dim=1, split='no', algo='csr', impl='python', target=None)\n", "10.2 ms ± 21.2 μs per loop (mean ± std. dev. of 7 runs, 100 loops each)\n", "Method(dim=2, split='no', algo='csr', impl='python', target=None)\n", "15.1 ms ± 28 μs per loop (mean ± std. dev. of 7 runs, 100 loops each)\n", "Method(dim=1, split='bbox', algo='csr', impl='python', target=None)\n", "13.4 ms ± 20.8 μs per loop (mean ± std. dev. of 7 runs, 100 loops each)\n", "Method(dim=2, split='bbox', algo='csr', impl='python', target=None)\n", "18.2 ms ± 29.6 μs per loop (mean ± std. dev. of 7 runs, 100 loops each)\n", "Method(dim=1, split='no', algo='csc', impl='cython', target=None)\n", "7.98 ms ± 14.1 μs per loop (mean ± std. dev. of 7 runs, 100 loops each)\n", "Method(dim=2, split='no', algo='csc', impl='cython', target=None)\n", "10.5 ms ± 59.3 μs per loop (mean ± std. dev. of 7 runs, 100 loops each)\n", "Method(dim=1, split='bbox', algo='csc', impl='cython', target=None)\n", "10.6 ms ± 9.6 μs per loop (mean ± std. dev. of 7 runs, 100 loops each)\n", "Method(dim=2, split='bbox', algo='csc', impl='cython', target=None)\n", "14.8 ms ± 39.5 μs per loop (mean ± std. dev. of 7 runs, 100 loops each)\n", "Method(dim=1, split='no', algo='csc', impl='python', target=None)\n", "11.5 ms ± 251 μs per loop (mean ± std. dev. of 7 runs, 100 loops each)\n", "Method(dim=2, split='no', algo='csc', impl='python', target=None)\n", "14.6 ms ± 122 μs per loop (mean ± std. dev. of 7 runs, 100 loops each)\n", "Method(dim=1, split='bbox', algo='csc', impl='python', target=None)\n", "14.9 ms ± 23.6 μs per loop (mean ± std. dev. of 7 runs, 100 loops each)\n", "Method(dim=2, split='bbox', algo='csc', impl='python', target=None)\n", "21.9 ms ± 50.3 μs per loop (mean ± std. dev. of 7 runs, 1 loop each)\n", "Method(dim=1, split='bbox', algo='lut', impl='cython', target=None)\n", "7.47 ms ± 482 μs per loop (mean ± std. dev. of 7 runs, 100 loops each)\n", "Method(dim=2, split='bbox', algo='lut', impl='cython', target=None)\n", "11.8 ms ± 224 μs per loop (mean ± std. dev. of 7 runs, 1 loop each)\n", "Method(dim=1, split='no', algo='lut', impl='cython', target=None)\n", "8.75 ms ± 2.52 ms per loop (mean ± std. dev. of 7 runs, 100 loops each)\n", "Method(dim=2, split='no', algo='lut', impl='cython', target=None)\n", "7.67 ms ± 341 μs per loop (mean ± std. dev. of 7 runs, 100 loops each)\n", "Method(dim=1, split='full', algo='lut', impl='cython', target=None)\n", "7.89 ms ± 474 μs per loop (mean ± std. dev. of 7 runs, 100 loops each)\n", "Method(dim=2, split='full', algo='lut', impl='cython', target=None)\n", "12.6 ms ± 674 μs per loop (mean ± std. dev. of 7 runs, 1 loop each)\n", "Method(dim=1, split='full', algo='csr', impl='cython', target=None)\n", "8.12 ms ± 1.78 ms per loop (mean ± std. dev. of 7 runs, 100 loops each)\n", "Method(dim=2, split='full', algo='csr', impl='cython', target=None)\n", "8.72 ms ± 1.29 ms per loop (mean ± std. dev. of 7 runs, 1 loop each)\n", "Method(dim=1, split='full', algo='csr', impl='python', target=None)\n", "12.6 ms ± 34.3 μs per loop (mean ± std. dev. of 7 runs, 100 loops each)\n", "Method(dim=2, split='full', algo='csr', impl='python', target=None)\n", "17.1 ms ± 73.3 μs per loop (mean ± std. dev. of 7 runs, 1 loop each)\n", "Method(dim=1, split='full', algo='csc', impl='cython', target=None)\n", "10.4 ms ± 89.5 μs per loop (mean ± std. dev. of 7 runs, 100 loops each)\n", "Method(dim=2, split='full', algo='csc', impl='cython', target=None)\n", "14.4 ms ± 99.1 μs per loop (mean ± std. dev. of 7 runs, 1 loop each)\n", "Method(dim=1, split='full', algo='csc', impl='python', target=None)\n", "14.9 ms ± 238 μs per loop (mean ± std. dev. of 7 runs, 100 loops each)\n", "Method(dim=2, split='full', algo='csc', impl='python', target=None)\n", "22.7 ms ± 1.57 ms per loop (mean ± std. dev. of 7 runs, 1 loop each)\n", "Method(dim=1, split='no', algo='histogram', impl='opencl', target=(0, 0))\n", "9.88 ms ± 166 μs per loop (mean ± std. dev. of 7 runs, 1 loop each)\n", "Method(dim=2, split='no', algo='histogram', impl='opencl', target=(0, 0))\n", "2.68 ms ± 41.2 μs per loop (mean ± std. dev. of 7 runs, 100 loops each)\n", "Method(dim=1, split='no', algo='histogram', impl='opencl', target=(0, 1))\n", "12.6 ms ± 206 μs per loop (mean ± std. dev. of 7 runs, 1 loop each)\n", "Method(dim=2, split='no', algo='histogram', impl='opencl', target=(0, 1))\n", "4.14 ms ± 38.5 μs per loop (mean ± std. dev. of 7 runs, 100 loops each)\n", "Method(dim=1, split='no', algo='histogram', impl='opencl', target=(1, 0))\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "/users/kieffer/.venv/py313/lib/python3.13/site-packages/pyopencl/cache.py:420: CompilerWarning: Non-empty compiler output encountered. Set the environment variable PYOPENCL_COMPILER_OUTPUT=1 to see more.\n", " prg.build(options_bytes, [devices[i] for i in to_be_built_indices])\n", "WARNING:pyFAI.opencl.azim_hist:Your OpenCL compiler wrongly claims it support 64-bit atomics. Degrading to 32 bits atomics!\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "11.1 ms ± 497 μs per loop (mean ± std. dev. of 7 runs, 1 loop each)\n", "Method(dim=2, split='no', algo='histogram', impl='opencl', target=(1, 0))\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "WARNING:pyFAI.opencl.azim_hist:Your OpenCL compiler wrongly claims it support 64-bit atomics. Degrading to 32 bits atomics!\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "7.08 ms ± 698 μs per loop (mean ± std. dev. of 7 runs, 1 loop each)\n", "Method(dim=1, split='bbox', algo='csr', impl='opencl', target=(0, 0))\n", "661 μs ± 837 ns per loop (mean ± std. dev. of 7 runs, 1,000 loops each)\n", "Method(dim=2, split='bbox', algo='csr', impl='opencl', target=(0, 0))\n", "2.59 ms ± 59.1 μs per loop (mean ± std. dev. of 7 runs, 1 loop each)\n", "Method(dim=1, split='no', algo='csr', impl='opencl', target=(0, 0))\n", "621 μs ± 3.02 μs per loop (mean ± std. dev. of 7 runs, 1,000 loops each)\n", "Method(dim=2, split='no', algo='csr', impl='opencl', target=(0, 0))\n", "2.55 ms ± 1.57 μs per loop (mean ± std. dev. of 7 runs, 100 loops each)\n", "Method(dim=1, split='bbox', algo='csr', impl='opencl', target=(0, 1))\n", "1.2 ms ± 29.7 μs per loop (mean ± std. dev. of 7 runs, 1 loop each)\n", "Method(dim=2, split='bbox', algo='csr', impl='opencl', target=(0, 1))\n", "6.09 ms ± 39.1 μs per loop (mean ± std. dev. of 7 runs, 1 loop each)\n", "Method(dim=1, split='no', algo='csr', impl='opencl', target=(0, 1))\n", "1.04 ms ± 295 ns per loop (mean ± std. dev. of 7 runs, 1,000 loops each)\n", "Method(dim=2, split='no', algo='csr', impl='opencl', target=(0, 1))\n", "6.01 ms ± 23.8 μs per loop (mean ± std. dev. of 7 runs, 100 loops each)\n", "Method(dim=1, split='bbox', algo='csr', impl='opencl', target=(1, 0))\n", "2.78 ms ± 101 μs per loop (mean ± std. dev. of 7 runs, 1 loop each)\n", "Method(dim=2, split='bbox', algo='csr', impl='opencl', target=(1, 0))\n", "82 ms ± 193 μs per loop (mean ± std. dev. of 7 runs, 1 loop each)\n", "Method(dim=1, split='no', algo='csr', impl='opencl', target=(1, 0))\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "/users/kieffer/.venv/py313/lib/python3.13/site-packages/pyopencl/cache.py:496: CompilerWarning: Non-empty compiler output encountered. Set the environment variable PYOPENCL_COMPILER_OUTPUT=1 to see more.\n", " _create_built_program_from_source_cached(\n", "/users/kieffer/.venv/py313/lib/python3.13/site-packages/pyopencl/cache.py:500: CompilerWarning: Non-empty compiler output encountered. Set the environment variable PYOPENCL_COMPILER_OUTPUT=1 to see more.\n", " prg.build(options_bytes, devices)\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "2.47 ms ± 366 μs per loop (mean ± std. dev. of 7 runs, 1 loop each)\n", "Method(dim=2, split='no', algo='csr', impl='opencl', target=(1, 0))\n", "81.4 ms ± 1.45 ms per loop (mean ± std. dev. of 7 runs, 1 loop each)\n", "Method(dim=1, split='full', algo='csr', impl='opencl', target=(0, 0))\n", "663 μs ± 1.44 μs per loop (mean ± std. dev. of 7 runs, 1,000 loops each)\n", "Method(dim=2, split='full', algo='csr', impl='opencl', target=(0, 0))\n", "2.59 ms ± 78 μs per loop (mean ± std. dev. of 7 runs, 1 loop each)\n", "Method(dim=1, split='full', algo='csr', impl='opencl', target=(0, 1))\n", "1.18 ms ± 986 ns per loop (mean ± std. dev. of 7 runs, 1,000 loops each)\n", "Method(dim=2, split='full', algo='csr', impl='opencl', target=(0, 1))\n", "6.1 ms ± 35.6 μs per loop (mean ± std. dev. of 7 runs, 1 loop each)\n", "Method(dim=1, split='full', algo='csr', impl='opencl', target=(1, 0))\n", "2.68 ms ± 122 μs per loop (mean ± std. dev. of 7 runs, 1 loop each)\n", "Method(dim=2, split='full', algo='csr', impl='opencl', target=(1, 0))\n", "82.5 ms ± 80 μs per loop (mean ± std. dev. of 7 runs, 1 loop each)\n", "Method(dim=1, split='bbox', algo='lut', impl='opencl', target=(0, 0))\n", "3.32 ms ± 50.7 μs per loop (mean ± std. dev. of 7 runs, 1 loop each)\n", "Method(dim=2, split='bbox', algo='lut', impl='opencl', target=(0, 0))\n", "300 ms ± 4.8 ms per loop (mean ± std. dev. of 7 runs, 1 loop each)\n", "Method(dim=1, split='no', algo='lut', impl='opencl', target=(0, 0))\n", "1.66 ms ± 64.2 μs per loop (mean ± std. dev. of 7 runs, 1 loop each)\n", "Method(dim=2, split='no', algo='lut', impl='opencl', target=(0, 0))\n", "180 ms ± 5.29 ms per loop (mean ± std. dev. of 7 runs, 1 loop each)\n", "Method(dim=1, split='bbox', algo='lut', impl='opencl', target=(0, 1))\n", "3.12 ms ± 27.2 μs per loop (mean ± std. dev. of 7 runs, 1 loop each)\n", "Method(dim=2, split='bbox', algo='lut', impl='opencl', target=(0, 1))\n", "298 ms ± 5.47 ms per loop (mean ± std. dev. of 7 runs, 1 loop each)\n", "Method(dim=1, split='no', algo='lut', impl='opencl', target=(0, 1))\n", "1.8 ms ± 26.9 μs per loop (mean ± std. dev. of 7 runs, 1 loop each)\n", "Method(dim=2, split='no', algo='lut', impl='opencl', target=(0, 1))\n", "178 ms ± 665 μs per loop (mean ± std. dev. of 7 runs, 1 loop each)\n", "Method(dim=1, split='bbox', algo='lut', impl='opencl', target=(1, 0))\n", "3.5 ms ± 293 μs per loop (mean ± std. dev. of 7 runs, 1 loop each)\n", "Method(dim=2, split='bbox', algo='lut', impl='opencl', target=(1, 0))\n", "205 ms ± 567 μs per loop (mean ± std. dev. of 7 runs, 1 loop each)\n", "Method(dim=1, split='no', algo='lut', impl='opencl', target=(1, 0))\n", "2.72 ms ± 166 μs per loop (mean ± std. dev. of 7 runs, 1 loop each)\n", "Method(dim=2, split='no', algo='lut', impl='opencl', target=(1, 0))\n", "175 ms ± 816 μs per loop (mean ± std. dev. of 7 runs, 1 loop each)\n", "Method(dim=1, split='full', algo='lut', impl='opencl', target=(0, 0))\n", "2.71 ms ± 53.5 μs per loop (mean ± std. dev. of 7 runs, 1 loop each)\n", "Method(dim=2, split='full', algo='lut', impl='opencl', target=(0, 0))\n", "293 ms ± 1.43 ms per loop (mean ± std. dev. of 7 runs, 1 loop each)\n", "Method(dim=1, split='full', algo='lut', impl='opencl', target=(0, 1))\n", "2.75 ms ± 149 μs per loop (mean ± std. dev. of 7 runs, 1 loop each)\n", "Method(dim=2, split='full', algo='lut', impl='opencl', target=(0, 1))\n", "294 ms ± 1.43 ms per loop (mean ± std. dev. of 7 runs, 1 loop each)\n", "Method(dim=1, split='full', algo='lut', impl='opencl', target=(1, 0))\n", "3.81 ms ± 546 μs per loop (mean ± std. dev. of 7 runs, 1 loop each)\n", "Method(dim=2, split='full', algo='lut', impl='opencl', target=(1, 0))\n", "207 ms ± 901 μs per loop (mean ± std. dev. of 7 runs, 1 loop each)\n", "CPU times: user 1h 2min 12s, sys: 16.2 s, total: 1h 2min 29s\n", "Wall time: 5min 40s\n" ] } ], "source": [ "%%time\n", "#Tune those parameters to match your needs:\n", "kw1 = {\"data\": img, \"npt\":1000}\n", "kw2 = {\"data\": img, \"npt_rad\":1000}\n", "#Actual benchmark:\n", "res = {}\n", "for k,v in pyFAI.method_registry.IntegrationMethod._registry.items():\n", " print(k)\n", " if k.dim == 1:\n", " res[k] = %timeit -o ai.integrate1d(method=v, **kw1)\n", " else:\n", " res[k] = %timeit -o ai.integrate2d(method=v, **kw2)" ] }, { "cell_type": "code", "execution_count": 10, "id": "cf37152a-27df-4105-a372-7d8d21366fc7", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "--------------------------------------------------------------------------------\n", "Split | Algo | Impl | 1d (ms) | 2d (ms) | ratio | Device\n", "--------------------------------------------------------------------------------\n", "no | histogram | python| 31.905 | 99.215 | 3.1 | \n", "no | histogram | cython| 12.397 | 20.965 | 1.7 | \n", "bbox | histogram | cython| 26.785 | 35.607 | 1.3 | \n", "full | histogram | cython| 150.790 | 214.578 | 1.4 | \n", "no | csr | cython| 7.120 | 7.573 | 1.1 | \n", "bbox | csr | cython| 7.213 | 8.136 | 1.1 | \n", "no | csr | python| 10.184 | 15.043 | 1.5 | \n", "bbox | csr | python| 13.421 | 18.183 | 1.4 | \n", "no | csc | cython| 7.973 | 10.450 | 1.3 | \n", "bbox | csc | cython| 10.585 | 14.801 | 1.4 | \n", "no | csc | python| 11.299 | 14.427 | 1.3 | \n", "bbox | csc | python| 14.845 | 21.879 | 1.5 | \n", "bbox | lut | cython| 6.978 | 11.554 | 1.7 | \n", "no | lut | cython| 6.939 | 7.410 | 1.1 | \n", "full | lut | cython| 7.070 | 11.674 | 1.7 | \n", "full | csr | cython| 7.035 | 8.100 | 1.2 | \n", "full | csr | python| 12.507 | 16.947 | 1.4 | \n", "full | csc | cython| 10.292 | 14.216 | 1.4 | \n", "full | csc | python| 14.767 | 21.966 | 1.5 | \n", "no | histogram | opencl| 9.648 | 2.646 | 0.3 | NVIDIA CUDA / NVIDIA RTX A5000\n", "no | histogram | opencl| 12.399 | 4.108 | 0.3 | NVIDIA CUDA / Quadro P2200\n", "no | histogram | opencl| 10.550 | 6.308 | 0.6 | Intel(R) OpenCL / AMD Ryzen Threadripper PRO 3975WX 32-Cores\n", "bbox | csr | opencl| 0.660 | 2.559 | 3.9 | NVIDIA CUDA / NVIDIA RTX A5000\n", "no | csr | opencl| 0.618 | 2.547 | 4.1 | NVIDIA CUDA / NVIDIA RTX A5000\n", "bbox | csr | opencl| 1.173 | 6.071 | 5.2 | NVIDIA CUDA / Quadro P2200\n", "no | csr | opencl| 1.040 | 5.996 | 5.8 | NVIDIA CUDA / Quadro P2200\n", "bbox | csr | opencl| 2.647 | 81.763 | 30.9 | Intel(R) OpenCL / AMD Ryzen Threadripper PRO 3975WX 32-Cores\n", "no | csr | opencl| 2.178 | 80.642 | 37.0 | Intel(R) OpenCL / AMD Ryzen Threadripper PRO 3975WX 32-Cores\n", "full | csr | opencl| 0.661 | 2.546 | 3.9 | NVIDIA CUDA / NVIDIA RTX A5000\n", "full | csr | opencl| 1.179 | 6.078 | 5.2 | NVIDIA CUDA / Quadro P2200\n", "full | csr | opencl| 2.504 | 82.328 | 32.9 | Intel(R) OpenCL / AMD Ryzen Threadripper PRO 3975WX 32-Cores\n", "bbox | lut | opencl| 3.277 | 297.263 | 90.7 | NVIDIA CUDA / NVIDIA RTX A5000\n", "no | lut | opencl| 1.621 | 175.541 | 108.3 | NVIDIA CUDA / NVIDIA RTX A5000\n", "bbox | lut | opencl| 3.098 | 292.775 | 94.5 | NVIDIA CUDA / Quadro P2200\n", "no | lut | opencl| 1.781 | 176.326 | 99.0 | NVIDIA CUDA / Quadro P2200\n", "bbox | lut | opencl| 3.215 | 204.729 | 63.7 | Intel(R) OpenCL / AMD Ryzen Threadripper PRO 3975WX 32-Cores\n", "no | lut | opencl| 2.484 | 174.308 | 70.2 | Intel(R) OpenCL / AMD Ryzen Threadripper PRO 3975WX 32-Cores\n", "full | lut | opencl| 2.683 | 289.591 | 107.9 | NVIDIA CUDA / NVIDIA RTX A5000\n", "full | lut | opencl| 2.669 | 290.825 | 109.0 | NVIDIA CUDA / Quadro P2200\n", "full | lut | opencl| 3.250 | 205.200 | 63.1 | Intel(R) OpenCL / AMD Ryzen Threadripper PRO 3975WX 32-Cores\n", "--------------------------------------------------------------------------------\n" ] } ], "source": [ "print(\"-\"*80)\n", "print(f\"{'Split':5s} | {'Algo':9s} | {'Impl':6s}| {'1d (ms)':8s} | {'2d (ms)':8s} | {'ratio':6s} | Device\")\n", "print(\"-\"*80)\n", "for k in res:\n", " if k.dim == 1:\n", " k1 = k\n", " k2 = k._replace(dim=2)\n", " if k2 in res:\n", " print(f\"{k1.split:5s} | {k1.algo:9s} | {k1.impl:6s}| {res[k1].best*1000:8.3f} | {res[k2].best*1000:8.3f} | {res[k2].best/res[k1].best:6.1f} | \",\n", " end=\"\")\n", " if k.target:\n", " print(pyFAI.method_registry.IntegrationMethod._registry.get(k).target_name)\n", " else:\n", " print()\n", "print(\"-\"*80)" ] }, { "cell_type": "code", "execution_count": 9, "id": "4d1e3ab4-aabd-4429-b1b2-818eb1f386a9", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Total runtime: 618.791s\n" ] } ], "source": [ "print(f\"Total runtime: {time.perf_counter()-start_time:.3f}s\")" ] }, { "cell_type": "code", "execution_count": null, "id": "07889dbc-2d6c-4978-811f-0f118b0ed5e2", "metadata": {}, "outputs": [], "source": [] } ], "metadata": { "kernelspec": { "display_name": "Python 3 (ipykernel)", "language": "python", "name": "python3" }, "language_info": { "codemirror_mode": { "name": "ipython", "version": 3 }, "file_extension": ".py", "mimetype": "text/x-python", "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", "version": "3.13.1" } }, "nbformat": 4, "nbformat_minor": 5 }