Performances of 2D integration vs 1D integration#
This is dependent on:
Number of azimuthal bins
Pixel splitting
Algorithm
Implementation (i.e. programming language)
Hardware used
Thus there is no general answer. But here is a quick benchmark to evaluate the penalty on performances:
import sys import os import time import numpy import fabio import pyFAI from pyFAI.test.utilstest import UtilsTest import pyFAI.method_registry import pyFAI.integrator.azimuthal print(f”Python version: {sys.version}”) print(f”PyFAI version: {pyFAI.version}”) start_time = time.perf_counter()
import sys
import os
import time
os.environ["PYOPENCL_COMPILER_OUTPUT"] = "0"
start_time = time.perf_counter()
import fabio
import pyFAI
from pyFAI.test.utilstest import UtilsTest
import pyFAI.method_registry
import pyFAI.integrator.azimuthal
print(f"Python version: {sys.version}")
print(f"PyFAI version: {pyFAI.version}")
Python version: 3.14.0 | packaged by conda-forge | (main, Oct 22 2025, 23:24:08) [GCC 14.3.0]
PyFAI version: 2026.8.0-dev0
print("Number of way to performing integration:", len(pyFAI.method_registry.IntegrationMethod.list_available()))
Number of way to performing integration: 95
ai = pyFAI.load(UtilsTest.getimage("Pilatus1M.poni"))
img = fabio.open(UtilsTest.getimage("Pilatus1M.edf")).data
ai
Detector Pilatus 1M PixelSize= 172µm, 172µm BottomRight (3)
Wavelength= 1.000000 Å
SampleDetDist= 1.583231e+00 m PONI= 3.341702e-02, 4.122778e-02 m rot1=0.006487 rot2=0.007558 rot3=0.000000 rad
DirectBeamDist= 1583.310 mm Center: x=179.981, y=263.859 pix Tilt= 0.571° tiltPlanRotation= 130.640° λ= 1.000Å
%%time
#Tune those parameters to match your needs:
kw1 = {"data": img, "npt":1000}
kw2 = {"data": img, "npt_rad":1000}
#Actual benchmark:
res = {}
for k,v in pyFAI.method_registry.IntegrationMethod._registry.items():
print(k)
if k.dim == 1:
res[k] = %timeit -o ai.integrate1d(method=v, **kw1)
else:
res[k] = %timeit -o ai.integrate2d(method=v, **kw2)
Method(dim=1, split='no', algo='histogram', impl='python', target=None)
30.3 ms ± 74.9 μs per loop (mean ± std. dev. of 7 runs, 10 loops each)
Method(dim=2, split='no', algo='histogram', impl='python', target=None)
143 ms ± 324 μs per loop (mean ± std. dev. of 7 runs, 10 loops each)
Method(dim=1, split='no', algo='histogram', impl='cython', target=None)
11.4 ms ± 13.4 μs per loop (mean ± std. dev. of 7 runs, 100 loops each)
Method(dim=2, split='no', algo='histogram', impl='cython', target=None)
16.7 ms ± 36 μs per loop (mean ± std. dev. of 7 runs, 100 loops each)
Method(dim=1, split='bbox', algo='histogram', impl='cython', target=None)
26.6 ms ± 51.2 μs per loop (mean ± std. dev. of 7 runs, 10 loops each)
Method(dim=2, split='bbox', algo='histogram', impl='cython', target=None)
33.1 ms ± 42.5 μs per loop (mean ± std. dev. of 7 runs, 10 loops each)
Method(dim=1, split='full', algo='histogram', impl='cython', target=None)
140 ms ± 78.8 μs per loop (mean ± std. dev. of 7 runs, 10 loops each)
Method(dim=2, split='full', algo='histogram', impl='cython', target=None)
282 ms ± 1.47 ms per loop (mean ± std. dev. of 7 runs, 1 loop each)
Method(dim=2, split='pseudo', algo='histogram', impl='cython', target=None)
370 ms ± 2.45 ms per loop (mean ± std. dev. of 7 runs, 1 loop each)
Method(dim=1, split='no', algo='csr', impl='cython', target=None)
15.3 ms ± 256 μs per loop (mean ± std. dev. of 7 runs, 100 loops each)
Method(dim=2, split='no', algo='csr', impl='cython', target=None)
15.8 ms ± 252 μs per loop (mean ± std. dev. of 7 runs, 100 loops each)
Method(dim=1, split='bbox', algo='csr', impl='cython', target=None)
15.3 ms ± 434 μs per loop (mean ± std. dev. of 7 runs, 100 loops each)
Method(dim=2, split='bbox', algo='csr', impl='cython', target=None)
15.2 ms ± 303 μs per loop (mean ± std. dev. of 7 runs, 100 loops each)
Method(dim=1, split='no', algo='csr', impl='python', target=None)
10.2 ms ± 81.1 μs per loop (mean ± std. dev. of 7 runs, 100 loops each)
Method(dim=2, split='no', algo='csr', impl='python', target=None)
15.2 ms ± 144 μs per loop (mean ± std. dev. of 7 runs, 100 loops each)
Method(dim=1, split='bbox', algo='csr', impl='python', target=None)
13.8 ms ± 75.8 μs per loop (mean ± std. dev. of 7 runs, 100 loops each)
Method(dim=2, split='bbox', algo='csr', impl='python', target=None)
18.1 ms ± 105 μs per loop (mean ± std. dev. of 7 runs, 1 loop each)
Method(dim=1, split='no', algo='csc', impl='cython', target=None)
7.12 ms ± 44.4 μs per loop (mean ± std. dev. of 7 runs, 100 loops each)
Method(dim=2, split='no', algo='csc', impl='cython', target=None)
9.82 ms ± 16.4 μs per loop (mean ± std. dev. of 7 runs, 100 loops each)
Method(dim=1, split='bbox', algo='csc', impl='cython', target=None)
9.48 ms ± 28.4 μs per loop (mean ± std. dev. of 7 runs, 100 loops each)
Method(dim=2, split='bbox', algo='csc', impl='cython', target=None)
12.9 ms ± 41 μs per loop (mean ± std. dev. of 7 runs, 1 loop each)
Method(dim=1, split='no', algo='csc', impl='python', target=None)
11.5 ms ± 14.6 μs per loop (mean ± std. dev. of 7 runs, 100 loops each)
Method(dim=2, split='no', algo='csc', impl='python', target=None)
14.8 ms ± 177 μs per loop (mean ± std. dev. of 7 runs, 100 loops each)
Method(dim=1, split='bbox', algo='csc', impl='python', target=None)
15.2 ms ± 14.7 μs per loop (mean ± std. dev. of 7 runs, 100 loops each)
Method(dim=2, split='bbox', algo='csc', impl='python', target=None)
22.7 ms ± 60.3 μs per loop (mean ± std. dev. of 7 runs, 1 loop each)
Method(dim=1, split='bbox', algo='lut', impl='cython', target=None)
15.5 ms ± 144 μs per loop (mean ± std. dev. of 7 runs, 100 loops each)
Method(dim=2, split='bbox', algo='lut', impl='cython', target=None)
19.5 ms ± 1.09 ms per loop (mean ± std. dev. of 7 runs, 1 loop each)
Method(dim=1, split='no', algo='lut', impl='cython', target=None)
15.7 ms ± 233 μs per loop (mean ± std. dev. of 7 runs, 100 loops each)
Method(dim=2, split='no', algo='lut', impl='cython', target=None)
16 ms ± 181 μs per loop (mean ± std. dev. of 7 runs, 100 loops each)
Method(dim=1, split='full', algo='lut', impl='cython', target=None)
16.4 ms ± 2.05 ms per loop (mean ± std. dev. of 7 runs, 1 loop each)
Method(dim=2, split='full', algo='lut', impl='cython', target=None)
18.8 ms ± 2.62 ms per loop (mean ± std. dev. of 7 runs, 1 loop each)
Method(dim=1, split='full', algo='csr', impl='cython', target=None)
15.5 ms ± 147 μs per loop (mean ± std. dev. of 7 runs, 100 loops each)
Method(dim=2, split='full', algo='csr', impl='cython', target=None)
14.1 ms ± 3.41 ms per loop (mean ± std. dev. of 7 runs, 1 loop each)
Method(dim=1, split='full', algo='csr', impl='python', target=None)
13.2 ms ± 58.2 μs per loop (mean ± std. dev. of 7 runs, 100 loops each)
Method(dim=2, split='full', algo='csr', impl='python', target=None)
17.8 ms ± 346 μs per loop (mean ± std. dev. of 7 runs, 1 loop each)
Method(dim=1, split='full', algo='csc', impl='cython', target=None)
9.14 ms ± 8.53 μs per loop (mean ± std. dev. of 7 runs, 100 loops each)
Method(dim=2, split='full', algo='csc', impl='cython', target=None)
12.8 ms ± 72.8 μs per loop (mean ± std. dev. of 7 runs, 1 loop each)
Method(dim=1, split='full', algo='csc', impl='python', target=None)
15.2 ms ± 126 μs per loop (mean ± std. dev. of 7 runs, 100 loops each)
Method(dim=2, split='full', algo='csc', impl='python', target=None)
22.1 ms ± 68.9 μs per loop (mean ± std. dev. of 7 runs, 1 loop each)
Method(dim=1, split='no', algo='histogram', impl='opencl', target=(0, 0))
8.97 ms ± 31.5 μs per loop (mean ± std. dev. of 7 runs, 100 loops each)
Method(dim=2, split='no', algo='histogram', impl='opencl', target=(0, 0))
2.75 ms ± 12.2 μs per loop (mean ± std. dev. of 7 runs, 100 loops each)
Method(dim=1, split='no', algo='histogram', impl='opencl', target=(0, 1))
8.26 ms ± 21.7 μs per loop (mean ± std. dev. of 7 runs, 100 loops each)
Method(dim=2, split='no', algo='histogram', impl='opencl', target=(0, 1))
4.22 ms ± 22 μs per loop (mean ± std. dev. of 7 runs, 100 loops each)
Method(dim=1, split='no', algo='histogram', impl='opencl', target=(1, 0))
1 error generated.
WARNING:pyFAI.opencl.azim_hist:Your OpenCL compiler wrongly claims it support 64-bit atomics. Degrading to 32 bits atomics!
15.8 ms ± 1.71 ms per loop (mean ± std. dev. of 7 runs, 1 loop each)
Method(dim=2, split='no', algo='histogram', impl='opencl', target=(1, 0))
1 error generated.
WARNING:pyFAI.opencl.azim_hist:Your OpenCL compiler wrongly claims it support 64-bit atomics. Degrading to 32 bits atomics!
/users/kieffer/.venv/py314/lib/python3.14/site-packages/pyopencl/cache.py:527: CompilerWarning: Non-empty compiler output encountered. Set the environment variable PYOPENCL_COMPILER_OUTPUT=1 to see more.
_create_built_program_from_source_cached(
/users/kieffer/.venv/py314/lib/python3.14/site-packages/pyopencl/cache.py:531: CompilerWarning: Non-empty compiler output encountered. Set the environment variable PYOPENCL_COMPILER_OUTPUT=1 to see more.
prg.build(options_bytes, devices)
WARNING:pyFAI.opencl.azim_hist:Your OpenCL compiler wrongly claims it support 64-bit atomics. Degrading to 32 bits atomics!
10.1 ms ± 843 μs per loop (mean ± std. dev. of 7 runs, 1 loop each)
Method(dim=1, split='no', algo='histogram', impl='opencl', target=(2, 0))
WARNING:pyFAI.opencl.azim_hist:Your OpenCL compiler wrongly claims it support 64-bit atomics. Degrading to 32 bits atomics!
11.1 ms ± 241 μs per loop (mean ± std. dev. of 7 runs, 100 loops each)
Method(dim=2, split='no', algo='histogram', impl='opencl', target=(2, 0))
5.84 ms ± 47.7 μs per loop (mean ± std. dev. of 7 runs, 100 loops each)
Method(dim=1, split='bbox', algo='csr', impl='opencl', target=(0, 0))
728 μs ± 2.73 μs per loop (mean ± std. dev. of 7 runs, 1,000 loops each)
Method(dim=2, split='bbox', algo='csr', impl='opencl', target=(0, 0))
2.67 ms ± 67.7 μs per loop (mean ± std. dev. of 7 runs, 1 loop each)
Method(dim=1, split='no', algo='csr', impl='opencl', target=(0, 0))
680 μs ± 894 ns per loop (mean ± std. dev. of 7 runs, 1,000 loops each)
Method(dim=2, split='no', algo='csr', impl='opencl', target=(0, 0))
2.47 ms ± 23.8 μs per loop (mean ± std. dev. of 7 runs, 100 loops each)
Method(dim=1, split='bbox', algo='csr', impl='opencl', target=(0, 1))
1.22 ms ± 1.2 μs per loop (mean ± std. dev. of 7 runs, 1,000 loops each)
Method(dim=2, split='bbox', algo='csr', impl='opencl', target=(0, 1))
6.13 ms ± 32.7 μs per loop (mean ± std. dev. of 7 runs, 1 loop each)
Method(dim=1, split='no', algo='csr', impl='opencl', target=(0, 1))
1.09 ms ± 865 ns per loop (mean ± std. dev. of 7 runs, 1,000 loops each)
Method(dim=2, split='no', algo='csr', impl='opencl', target=(0, 1))
6.02 ms ± 12.1 μs per loop (mean ± std. dev. of 7 runs, 100 loops each)
Method(dim=1, split='bbox', algo='csr', impl='opencl', target=(1, 0))
3.72 ms ± 25.2 μs per loop (mean ± std. dev. of 7 runs, 100 loops each)
Method(dim=2, split='bbox', algo='csr', impl='opencl', target=(1, 0))
9.17 ms ± 319 μs per loop (mean ± std. dev. of 7 runs, 1 loop each)
Method(dim=1, split='no', algo='csr', impl='opencl', target=(1, 0))
2.84 ms ± 24.2 μs per loop (mean ± std. dev. of 7 runs, 100 loops each)
Method(dim=2, split='no', algo='csr', impl='opencl', target=(1, 0))
6.16 ms ± 40.6 μs per loop (mean ± std. dev. of 7 runs, 100 loops each)
Method(dim=1, split='bbox', algo='csr', impl='opencl', target=(2, 0))
2.89 ms ± 147 μs per loop (mean ± std. dev. of 7 runs, 1 loop each)
Method(dim=2, split='bbox', algo='csr', impl='opencl', target=(2, 0))
83.7 ms ± 87.5 μs per loop (mean ± std. dev. of 7 runs, 1 loop each)
Method(dim=1, split='no', algo='csr', impl='opencl', target=(2, 0))
2.22 ms ± 114 μs per loop (mean ± std. dev. of 7 runs, 1 loop each)
Method(dim=2, split='no', algo='csr', impl='opencl', target=(2, 0))
89.7 ms ± 5.76 ms per loop (mean ± std. dev. of 7 runs, 1 loop each)
Method(dim=1, split='full', algo='csr', impl='opencl', target=(0, 0))
724 μs ± 2.26 μs per loop (mean ± std. dev. of 7 runs, 1,000 loops each)
Method(dim=2, split='full', algo='csr', impl='opencl', target=(0, 0))
2.65 ms ± 74.9 μs per loop (mean ± std. dev. of 7 runs, 1 loop each)
Method(dim=1, split='full', algo='csr', impl='opencl', target=(0, 1))
1.23 ms ± 688 ns per loop (mean ± std. dev. of 7 runs, 1,000 loops each)
Method(dim=2, split='full', algo='csr', impl='opencl', target=(0, 1))
6.13 ms ± 38 μs per loop (mean ± std. dev. of 7 runs, 1 loop each)
Method(dim=1, split='full', algo='csr', impl='opencl', target=(1, 0))
4.06 ms ± 33.8 μs per loop (mean ± std. dev. of 7 runs, 100 loops each)
Method(dim=2, split='full', algo='csr', impl='opencl', target=(1, 0))
8.84 ms ± 604 μs per loop (mean ± std. dev. of 7 runs, 1 loop each)
Method(dim=1, split='full', algo='csr', impl='opencl', target=(2, 0))
3.33 ms ± 85.2 μs per loop (mean ± std. dev. of 7 runs, 1 loop each)
Method(dim=2, split='full', algo='csr', impl='opencl', target=(2, 0))
84.6 ms ± 1.26 ms per loop (mean ± std. dev. of 7 runs, 1 loop each)
Method(dim=1, split='bbox', algo='lut', impl='opencl', target=(0, 0))
3.18 ms ± 3.83 μs per loop (mean ± std. dev. of 7 runs, 100 loops each)
Method(dim=2, split='bbox', algo='lut', impl='opencl', target=(0, 0))
365 ms ± 15.4 ms per loop (mean ± std. dev. of 7 runs, 1 loop each)
Method(dim=1, split='no', algo='lut', impl='opencl', target=(0, 0))
1.61 ms ± 2.32 μs per loop (mean ± std. dev. of 7 runs, 1,000 loops each)
Method(dim=2, split='no', algo='lut', impl='opencl', target=(0, 0))
197 ms ± 22.8 ms per loop (mean ± std. dev. of 7 runs, 1 loop each)
Method(dim=1, split='bbox', algo='lut', impl='opencl', target=(0, 1))
3.15 ms ± 8.53 μs per loop (mean ± std. dev. of 7 runs, 100 loops each)
Method(dim=2, split='bbox', algo='lut', impl='opencl', target=(0, 1))
512 ms ± 5.17 ms per loop (mean ± std. dev. of 7 runs, 1 loop each)
Method(dim=1, split='no', algo='lut', impl='opencl', target=(0, 1))
1.82 ms ± 624 ns per loop (mean ± std. dev. of 7 runs, 1,000 loops each)
Method(dim=2, split='no', algo='lut', impl='opencl', target=(0, 1))
212 ms ± 3.17 ms per loop (mean ± std. dev. of 7 runs, 1 loop each)
Method(dim=1, split='bbox', algo='lut', impl='opencl', target=(1, 0))
4.81 ms ± 93.2 μs per loop (mean ± std. dev. of 7 runs, 100 loops each)
Method(dim=2, split='bbox', algo='lut', impl='opencl', target=(1, 0))
372 ms ± 20.6 ms per loop (mean ± std. dev. of 7 runs, 1 loop each)
Method(dim=1, split='no', algo='lut', impl='opencl', target=(1, 0))
3.75 ms ± 38.5 μs per loop (mean ± std. dev. of 7 runs, 100 loops each)
Method(dim=2, split='no', algo='lut', impl='opencl', target=(1, 0))
238 ms ± 18.6 ms per loop (mean ± std. dev. of 7 runs, 1 loop each)
Method(dim=1, split='bbox', algo='lut', impl='opencl', target=(2, 0))
3.49 ms ± 114 μs per loop (mean ± std. dev. of 7 runs, 100 loops each)
Method(dim=2, split='bbox', algo='lut', impl='opencl', target=(2, 0))
447 ms ± 37.2 ms per loop (mean ± std. dev. of 7 runs, 1 loop each)
Method(dim=1, split='no', algo='lut', impl='opencl', target=(2, 0))
2.77 ms ± 60.6 μs per loop (mean ± std. dev. of 7 runs, 100 loops each)
Method(dim=2, split='no', algo='lut', impl='opencl', target=(2, 0))
317 ms ± 21.2 ms per loop (mean ± std. dev. of 7 runs, 1 loop each)
Method(dim=1, split='full', algo='lut', impl='opencl', target=(0, 0))
2.61 ms ± 4.94 μs per loop (mean ± std. dev. of 7 runs, 100 loops each)
Method(dim=2, split='full', algo='lut', impl='opencl', target=(0, 0))
342 ms ± 24.1 ms per loop (mean ± std. dev. of 7 runs, 1 loop each)
Method(dim=1, split='full', algo='lut', impl='opencl', target=(0, 1))
2.77 ms ± 115 μs per loop (mean ± std. dev. of 7 runs, 100 loops each)
Method(dim=2, split='full', algo='lut', impl='opencl', target=(0, 1))
506 ms ± 139 ms per loop (mean ± std. dev. of 7 runs, 1 loop each)
Method(dim=1, split='full', algo='lut', impl='opencl', target=(1, 0))
5.04 ms ± 179 μs per loop (mean ± std. dev. of 7 runs, 100 loops each)
Method(dim=2, split='full', algo='lut', impl='opencl', target=(1, 0))
254 ms ± 49.6 ms per loop (mean ± std. dev. of 7 runs, 1 loop each)
Method(dim=1, split='full', algo='lut', impl='opencl', target=(2, 0))
3.83 ms ± 80.3 μs per loop (mean ± std. dev. of 7 runs, 100 loops each)
Method(dim=2, split='full', algo='lut', impl='opencl', target=(2, 0))
335 ms ± 23.9 ms per loop (mean ± std. dev. of 7 runs, 1 loop each)
CPU times: user 2h 10min 38s, sys: 7min 25s, total: 2h 18min 3s
Wall time: 8min 6s
print("-"*80)
print(f"{'Split':5s} | {'Algo':9s} | {'Impl':6s}| {'1d (ms)':8s} | {'2d (ms)':8s} | {'ratio':6s} | Device")
print("-"*80)
for k in res:
if k.dim == 1:
k1 = k
k2 = k._replace(dim=2)
if k2 in res:
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} | ",
end="")
if k.target:
print(pyFAI.method_registry.IntegrationMethod._registry.get(k).target_name)
else:
print()
print("-"*80)
--------------------------------------------------------------------------------
Split | Algo | Impl | 1d (ms) | 2d (ms) | ratio | Device
--------------------------------------------------------------------------------
no | histogram | python| 30.255 | 142.694 | 4.7 |
no | histogram | cython| 11.390 | 16.706 | 1.5 |
bbox | histogram | cython| 26.570 | 33.027 | 1.2 |
full | histogram | cython| 140.251 | 280.317 | 2.0 |
no | csr | cython| 14.934 | 15.385 | 1.0 |
bbox | csr | cython| 14.379 | 14.719 | 1.0 |
no | csr | python| 10.095 | 14.901 | 1.5 |
bbox | csr | python| 13.706 | 18.006 | 1.3 |
no | csc | cython| 7.037 | 9.792 | 1.4 |
bbox | csc | cython| 9.452 | 12.825 | 1.4 |
no | csc | python| 11.449 | 14.555 | 1.3 |
bbox | csc | python| 15.218 | 22.616 | 1.5 |
bbox | lut | cython| 15.319 | 17.738 | 1.2 |
no | lut | cython| 15.157 | 15.744 | 1.0 |
full | lut | cython| 14.131 | 15.101 | 1.1 |
full | csr | cython| 15.200 | 7.991 | 0.5 |
full | csr | python| 13.053 | 17.323 | 1.3 |
full | csc | cython| 9.129 | 12.678 | 1.4 |
full | csc | python| 15.027 | 21.956 | 1.5 |
no | histogram | opencl| 8.936 | 2.741 | 0.3 | NVIDIA CUDA / NVIDIA RTX A5000
no | histogram | opencl| 8.232 | 4.204 | 0.5 | NVIDIA CUDA / Quadro P2200
no | histogram | opencl| 13.981 | 9.243 | 0.7 | Portable Computing Language / cpu-haswell-AMD Ryzen Threadripper PRO 3975WX 32-Cores
no | histogram | opencl| 10.681 | 5.756 | 0.5 | Intel(R) OpenCL / AMD Ryzen Threadripper PRO 3975WX 32-Cores
bbox | csr | opencl| 0.725 | 2.626 | 3.6 | NVIDIA CUDA / NVIDIA RTX A5000
no | csr | opencl| 0.679 | 2.454 | 3.6 | NVIDIA CUDA / NVIDIA RTX A5000
bbox | csr | opencl| 1.223 | 6.115 | 5.0 | NVIDIA CUDA / Quadro P2200
no | csr | opencl| 1.088 | 6.007 | 5.5 | NVIDIA CUDA / Quadro P2200
bbox | csr | opencl| 3.686 | 8.512 | 2.3 | Portable Computing Language / cpu-haswell-AMD Ryzen Threadripper PRO 3975WX 32-Cores
no | csr | opencl| 2.818 | 6.107 | 2.2 | Portable Computing Language / cpu-haswell-AMD Ryzen Threadripper PRO 3975WX 32-Cores
bbox | csr | opencl| 2.721 | 83.607 | 30.7 | Intel(R) OpenCL / AMD Ryzen Threadripper PRO 3975WX 32-Cores
no | csr | opencl| 2.054 | 84.036 | 40.9 | Intel(R) OpenCL / AMD Ryzen Threadripper PRO 3975WX 32-Cores
full | csr | opencl| 0.721 | 2.613 | 3.6 | NVIDIA CUDA / NVIDIA RTX A5000
full | csr | opencl| 1.226 | 6.107 | 5.0 | NVIDIA CUDA / Quadro P2200
full | csr | opencl| 4.021 | 8.111 | 2.0 | Portable Computing Language / cpu-haswell-AMD Ryzen Threadripper PRO 3975WX 32-Cores
full | csr | opencl| 3.186 | 83.693 | 26.3 | Intel(R) OpenCL / AMD Ryzen Threadripper PRO 3975WX 32-Cores
bbox | lut | opencl| 3.174 | 351.847 | 110.9 | NVIDIA CUDA / NVIDIA RTX A5000
no | lut | opencl| 1.612 | 165.985 | 103.0 | NVIDIA CUDA / NVIDIA RTX A5000
bbox | lut | opencl| 3.140 | 507.098 | 161.5 | NVIDIA CUDA / Quadro P2200
no | lut | opencl| 1.815 | 207.240 | 114.2 | NVIDIA CUDA / Quadro P2200
bbox | lut | opencl| 4.701 | 342.116 | 72.8 | Portable Computing Language / cpu-haswell-AMD Ryzen Threadripper PRO 3975WX 32-Cores
no | lut | opencl| 3.699 | 219.792 | 59.4 | Portable Computing Language / cpu-haswell-AMD Ryzen Threadripper PRO 3975WX 32-Cores
bbox | lut | opencl| 3.349 | 403.993 | 120.6 | Intel(R) OpenCL / AMD Ryzen Threadripper PRO 3975WX 32-Cores
no | lut | opencl| 2.707 | 273.430 | 101.0 | Intel(R) OpenCL / AMD Ryzen Threadripper PRO 3975WX 32-Cores
full | lut | opencl| 2.610 | 309.023 | 118.4 | NVIDIA CUDA / NVIDIA RTX A5000
full | lut | opencl| 2.709 | 381.123 | 140.7 | NVIDIA CUDA / Quadro P2200
full | lut | opencl| 4.668 | 210.364 | 45.1 | Portable Computing Language / cpu-haswell-AMD Ryzen Threadripper PRO 3975WX 32-Cores
full | lut | opencl| 3.753 | 299.781 | 79.9 | Intel(R) OpenCL / AMD Ryzen Threadripper PRO 3975WX 32-Cores
--------------------------------------------------------------------------------
print(f"Total runtime: {time.perf_counter()-start_time:.3f}s")
Total runtime: 488.307s