Performances of 2D integration vs 1D integration#
This is dependant 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 penality 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()
[1]:
import sys
import os
import time
import numpy
os.environ["PYOPENCL_COMPILER_OUTPUT"] = "0"
start_time = time.perf_counter()
[2]:
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: 3.13.1 | packaged by conda-forge | (main, Jan 13 2025, 09:53:10) [GCC 13.3.0]
PyFAI version: 2025.12.0
[3]:
print("Number of way to performing integration:", len(pyFAI.method_registry.IntegrationMethod.list_available()))
Number of way to performing integration: 95
[4]:
ai = pyFAI.load(UtilsTest.getimage("Pilatus1M.poni"))
img = fabio.open(UtilsTest.getimage("Pilatus1M.edf")).data
ai
[4]:
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
[5]:
%%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)
30.1 ms ± 436 μs per loop (mean ± std. dev. of 7 runs, 10 loops each)
Method(dim=2, split='no', algo='histogram', impl='python', target=None)
115 ms ± 734 μs per loop (mean ± std. dev. of 7 runs, 10 loops each)
Method(dim=1, split='no', algo='histogram', impl='cython', target=None)
11.2 ms ± 29.2 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 ± 1.16 ms per loop (mean ± std. dev. of 7 runs, 100 loops each)
Method(dim=1, split='bbox', algo='histogram', impl='cython', target=None)
26.1 ms ± 94.7 μs per loop (mean ± std. dev. of 7 runs, 10 loops each)
Method(dim=2, split='bbox', algo='histogram', impl='cython', target=None)
32.5 ms ± 48.4 μs per loop (mean ± std. dev. of 7 runs, 10 loops each)
Method(dim=1, split='full', algo='histogram', impl='cython', target=None)
169 ms ± 3.85 ms per loop (mean ± std. dev. of 7 runs, 10 loops each)
Method(dim=2, split='full', algo='histogram', impl='cython', target=None)
319 ms ± 3.8 ms per loop (mean ± std. dev. of 7 runs, 1 loop each)
Method(dim=2, split='pseudo', algo='histogram', impl='cython', target=None)
358 ms ± 2.7 ms per loop (mean ± std. dev. of 7 runs, 1 loop each)
Method(dim=1, split='no', algo='csr', impl='cython', target=None)
8.54 ms ± 804 μs per loop (mean ± std. dev. of 7 runs, 100 loops each)
Method(dim=2, split='no', algo='csr', impl='cython', target=None)
16.8 ms ± 6.51 ms per loop (mean ± std. dev. of 7 runs, 100 loops each)
Method(dim=1, split='bbox', algo='csr', impl='cython', target=None)
10.7 ms ± 4.21 ms per loop (mean ± std. dev. of 7 runs, 100 loops each)
Method(dim=2, split='bbox', algo='csr', impl='cython', target=None)
12.2 ms ± 2.75 ms per loop (mean ± std. dev. of 7 runs, 100 loops each)
Method(dim=1, split='no', algo='csr', impl='python', target=None)
10.4 ms ± 325 μs per loop (mean ± std. dev. of 7 runs, 100 loops each)
Method(dim=2, split='no', algo='csr', impl='python', target=None)
14.7 ms ± 247 μs per loop (mean ± std. dev. of 7 runs, 100 loops each)
Method(dim=1, split='bbox', algo='csr', impl='python', target=None)
14.2 ms ± 389 μs per loop (mean ± std. dev. of 7 runs, 100 loops each)
Method(dim=2, split='bbox', algo='csr', impl='python', target=None)
16.6 ms ± 106 μs per loop (mean ± std. dev. of 7 runs, 1 loop each)
Method(dim=1, split='no', algo='csc', impl='cython', target=None)
8.14 ms ± 30.4 μs per loop (mean ± std. dev. of 7 runs, 100 loops each)
Method(dim=2, split='no', algo='csc', impl='cython', target=None)
10.6 ms ± 26.2 μs per loop (mean ± std. dev. of 7 runs, 100 loops each)
Method(dim=1, split='bbox', algo='csc', impl='cython', target=None)
10.5 ms ± 59.6 μs per loop (mean ± std. dev. of 7 runs, 100 loops each)
Method(dim=2, split='bbox', algo='csc', impl='cython', target=None)
13.9 ms ± 69.6 μs per loop (mean ± std. dev. of 7 runs, 100 loops each)
Method(dim=1, split='no', algo='csc', impl='python', target=None)
10.9 ms ± 13 μs per loop (mean ± std. dev. of 7 runs, 100 loops each)
Method(dim=2, split='no', algo='csc', impl='python', target=None)
14.2 ms ± 31 μs per loop (mean ± std. dev. of 7 runs, 100 loops each)
Method(dim=1, split='bbox', algo='csc', impl='python', target=None)
14.7 ms ± 22.3 μs per loop (mean ± std. dev. of 7 runs, 100 loops each)
Method(dim=2, split='bbox', algo='csc', impl='python', target=None)
21.6 ms ± 34.2 μs per loop (mean ± std. dev. of 7 runs, 1 loop each)
Method(dim=1, split='bbox', algo='lut', impl='cython', target=None)
10.4 ms ± 3.01 ms per loop (mean ± std. dev. of 7 runs, 100 loops each)
Method(dim=2, split='bbox', algo='lut', impl='cython', target=None)
15.7 ms ± 2.81 ms per loop (mean ± std. dev. of 7 runs, 1 loop each)
Method(dim=1, split='no', algo='lut', impl='cython', target=None)
11.9 ms ± 2.52 ms per loop (mean ± std. dev. of 7 runs, 100 loops each)
Method(dim=2, split='no', algo='lut', impl='cython', target=None)
10.9 ms ± 3.15 ms per loop (mean ± std. dev. of 7 runs, 100 loops each)
Method(dim=1, split='full', algo='lut', impl='cython', target=None)
16.6 ms ± 5.81 ms per loop (mean ± std. dev. of 7 runs, 1 loop each)
Method(dim=2, split='full', algo='lut', impl='cython', target=None)
11.6 ms ± 170 μs per loop (mean ± std. dev. of 7 runs, 1 loop each)
Method(dim=1, split='full', algo='csr', impl='cython', target=None)
12.7 ms ± 4.05 ms per loop (mean ± std. dev. of 7 runs, 100 loops each)
Method(dim=2, split='full', algo='csr', impl='cython', target=None)
21.1 ms ± 2.35 ms per loop (mean ± std. dev. of 7 runs, 1 loop each)
Method(dim=1, split='full', algo='csr', impl='python', target=None)
12.8 ms ± 11.1 μs per loop (mean ± std. dev. of 7 runs, 100 loops each)
Method(dim=2, split='full', algo='csr', impl='python', target=None)
17.1 ms ± 82 μs per loop (mean ± std. dev. of 7 runs, 1 loop each)
Method(dim=1, split='full', algo='csc', impl='cython', target=None)
10.3 ms ± 9.66 μs per loop (mean ± std. dev. of 7 runs, 100 loops each)
Method(dim=2, split='full', algo='csc', impl='cython', target=None)
14.1 ms ± 20.8 μs per loop (mean ± std. dev. of 7 runs, 1 loop each)
Method(dim=1, split='full', algo='csc', impl='python', target=None)
15 ms ± 68.6 μs per loop (mean ± std. dev. of 7 runs, 100 loops each)
Method(dim=2, split='full', algo='csc', impl='python', target=None)
22 ms ± 42.7 μs per loop (mean ± std. dev. of 7 runs, 1 loop each)
Method(dim=1, split='no', algo='histogram', impl='opencl', target=(0, 0))
9.41 ms ± 5.63 μs per loop (mean ± std. dev. of 7 runs, 100 loops each)
Method(dim=2, split='no', algo='histogram', impl='opencl', target=(0, 0))
2.71 ms ± 13 μs per loop (mean ± std. dev. of 7 runs, 100 loops each)
Method(dim=1, split='no', algo='histogram', impl='opencl', target=(0, 1))
8.48 ms ± 24.7 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 ± 9.5 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!
1 error generated.
WARNING:pyFAI.opencl.azim_hist:Your OpenCL compiler wrongly claims it support 64-bit atomics. Degrading to 32 bits atomics!
14.9 ms ± 523 μs per loop (mean ± std. dev. of 7 runs, 1 loop each)
Method(dim=2, split='no', algo='histogram', impl='opencl', target=(1, 0))
/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.
_create_built_program_from_source_cached(
/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.
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!
11.2 ms ± 960 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!
11.5 ms ± 254 μs per loop (mean ± std. dev. of 7 runs, 100 loops each)
Method(dim=2, split='no', algo='histogram', impl='opencl', target=(2, 0))
7.7 ms ± 220 μs per loop (mean ± std. dev. of 7 runs, 100 loops each)
Method(dim=1, split='bbox', algo='csr', impl='opencl', target=(0, 0))
704 μs ± 2.68 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))
2.68 ms ± 69.8 μs per loop (mean ± std. dev. of 7 runs, 1 loop each)
Method(dim=1, split='no', algo='csr', impl='opencl', target=(0, 0))
660 μs ± 1.57 μs per loop (mean ± std. dev. of 7 runs, 1,000 loops each)
Method(dim=2, split='no', algo='csr', impl='opencl', target=(0, 0))
2.59 ms ± 14.1 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 ± 3.48 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))
6.12 ms ± 33.3 μs per loop (mean ± std. dev. of 7 runs, 1 loop each)
Method(dim=1, split='no', algo='csr', impl='opencl', target=(0, 1))
1.08 ms ± 1.54 μs per loop (mean ± std. dev. of 7 runs, 1,000 loops each)
Method(dim=2, split='no', algo='csr', impl='opencl', target=(0, 1))
6.06 ms ± 12 μs per loop (mean ± std. dev. of 7 runs, 100 loops each)
Method(dim=1, split='bbox', algo='csr', impl='opencl', target=(1, 0))
3.78 ms ± 40.2 μs per loop (mean ± std. dev. of 7 runs, 100 loops each)
Method(dim=2, split='bbox', algo='csr', impl='opencl', target=(1, 0))
7.71 ms ± 208 μs per loop (mean ± std. dev. of 7 runs, 1 loop each)
Method(dim=1, split='no', algo='csr', impl='opencl', target=(1, 0))
3.06 ms ± 57.4 μs per loop (mean ± std. dev. of 7 runs, 100 loops each)
Method(dim=2, split='no', algo='csr', impl='opencl', target=(1, 0))
6.21 ms ± 95.1 μs per loop (mean ± std. dev. of 7 runs, 100 loops each)
Method(dim=1, split='bbox', algo='csr', impl='opencl', target=(2, 0))
3.94 ms ± 1.22 ms per loop (mean ± std. dev. of 7 runs, 1 loop each)
Method(dim=2, split='bbox', algo='csr', impl='opencl', target=(2, 0))
82.4 ms ± 118 μs per loop (mean ± std. dev. of 7 runs, 1 loop each)
Method(dim=1, split='no', algo='csr', impl='opencl', target=(2, 0))
2.38 ms ± 398 μs per loop (mean ± std. dev. of 7 runs, 1 loop each)
Method(dim=2, split='no', algo='csr', impl='opencl', target=(2, 0))
84.1 ms ± 2.83 ms per loop (mean ± std. dev. of 7 runs, 1 loop each)
Method(dim=1, split='full', algo='csr', impl='opencl', target=(0, 0))
705 μs ± 1.02 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))
2.62 ms ± 80.4 μs per loop (mean ± std. dev. of 7 runs, 1 loop each)
Method(dim=1, split='full', algo='csr', impl='opencl', target=(0, 1))
1.22 ms ± 804 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))
6.11 ms ± 39 μs per loop (mean ± std. dev. of 7 runs, 1 loop each)
Method(dim=1, split='full', algo='csr', impl='opencl', target=(1, 0))
4.2 ms ± 22.4 μs per loop (mean ± std. dev. of 7 runs, 100 loops each)
Method(dim=2, split='full', algo='csr', impl='opencl', target=(1, 0))
7.68 ms ± 304 μs per loop (mean ± std. dev. of 7 runs, 1 loop each)
Method(dim=1, split='full', algo='csr', impl='opencl', target=(2, 0))
3.41 ms ± 698 μs per loop (mean ± std. dev. of 7 runs, 1 loop each)
Method(dim=2, split='full', algo='csr', impl='opencl', target=(2, 0))
83 ms ± 802 μs 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 ± 1.02 μs per loop (mean ± std. dev. of 7 runs, 100 loops each)
Method(dim=2, split='bbox', algo='lut', impl='opencl', target=(0, 0))
301 ms ± 4.76 ms per loop (mean ± std. dev. of 7 runs, 1 loop each)
Method(dim=1, split='no', algo='lut', impl='opencl', target=(0, 0))
1.59 ms ± 2.57 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))
181 ms ± 2.71 ms per loop (mean ± std. dev. of 7 runs, 1 loop each)
Method(dim=1, split='bbox', algo='lut', impl='opencl', target=(0, 1))
3.19 ms ± 39.5 μs per loop (mean ± std. dev. of 7 runs, 100 loops each)
Method(dim=2, split='bbox', algo='lut', impl='opencl', target=(0, 1))
304 ms ± 11.9 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 ± 13 μs per loop (mean ± std. dev. of 7 runs, 1,000 loops each)
Method(dim=2, split='no', algo='lut', impl='opencl', target=(0, 1))
182 ms ± 774 μs per loop (mean ± std. dev. of 7 runs, 1 loop each)
Method(dim=1, split='bbox', algo='lut', impl='opencl', target=(1, 0))
4.63 ms ± 24 μs per loop (mean ± std. dev. of 7 runs, 100 loops each)
Method(dim=2, split='bbox', algo='lut', impl='opencl', target=(1, 0))
170 ms ± 2.29 ms per loop (mean ± std. dev. of 7 runs, 1 loop each)
Method(dim=1, split='no', algo='lut', impl='opencl', target=(1, 0))
3.68 ms ± 30.6 μs per loop (mean ± std. dev. of 7 runs, 100 loops each)
Method(dim=2, split='no', algo='lut', impl='opencl', target=(1, 0))
139 ms ± 2.45 ms per loop (mean ± std. dev. of 7 runs, 1 loop each)
Method(dim=1, split='bbox', algo='lut', impl='opencl', target=(2, 0))
4.07 ms ± 164 μs per loop (mean ± std. dev. of 7 runs, 100 loops each)
Method(dim=2, split='bbox', algo='lut', impl='opencl', target=(2, 0))
212 ms ± 1.92 ms per loop (mean ± std. dev. of 7 runs, 1 loop each)
Method(dim=1, split='no', algo='lut', impl='opencl', target=(2, 0))
2.83 ms ± 223 μs per loop (mean ± std. dev. of 7 runs, 100 loops each)
Method(dim=2, split='no', algo='lut', impl='opencl', target=(2, 0))
182 ms ± 3.39 ms per loop (mean ± std. dev. of 7 runs, 1 loop each)
Method(dim=1, split='full', algo='lut', impl='opencl', target=(0, 0))
2.6 ms ± 2 μs per loop (mean ± std. dev. of 7 runs, 100 loops each)
Method(dim=2, split='full', algo='lut', impl='opencl', target=(0, 0))
298 ms ± 2.01 ms per loop (mean ± std. dev. of 7 runs, 1 loop each)
Method(dim=1, split='full', algo='lut', impl='opencl', target=(0, 1))
2.78 ms ± 152 μs per loop (mean ± std. dev. of 7 runs, 100 loops each)
Method(dim=2, split='full', algo='lut', impl='opencl', target=(0, 1))
301 ms ± 1.99 ms per loop (mean ± std. dev. of 7 runs, 1 loop each)
Method(dim=1, split='full', algo='lut', impl='opencl', target=(1, 0))
4.64 ms ± 18.7 μs per loop (mean ± std. dev. of 7 runs, 100 loops each)
Method(dim=2, split='full', algo='lut', impl='opencl', target=(1, 0))
168 ms ± 1.24 ms per loop (mean ± std. dev. of 7 runs, 1 loop each)
Method(dim=1, split='full', algo='lut', impl='opencl', target=(2, 0))
3.49 ms ± 177 μs per loop (mean ± std. dev. of 7 runs, 100 loops each)
Method(dim=2, split='full', algo='lut', impl='opencl', target=(2, 0))
215 ms ± 2.96 ms per loop (mean ± std. dev. of 7 runs, 1 loop each)
CPU times: user 1h 50min 47s, sys: 7min 40s, total: 1h 58min 28s
Wall time: 7min 41s
[6]:
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| 29.819 | 113.944 | 3.8 |
no | histogram | cython| 11.131 | 16.140 | 1.5 |
bbox | histogram | cython| 25.982 | 32.473 | 1.2 |
full | histogram | cython| 166.489 | 313.909 | 1.9 |
no | csr | cython| 7.103 | 7.166 | 1.0 |
bbox | csr | cython| 7.468 | 8.253 | 1.1 |
no | csr | python| 9.785 | 14.210 | 1.5 |
bbox | csr | python| 13.559 | 16.487 | 1.2 |
no | csc | cython| 8.101 | 10.589 | 1.3 |
bbox | csc | cython| 10.463 | 13.837 | 1.3 |
no | csc | python| 10.874 | 14.124 | 1.3 |
bbox | csc | python| 14.671 | 21.500 | 1.5 |
bbox | lut | cython| 7.437 | 11.805 | 1.6 |
no | lut | cython| 8.069 | 7.759 | 1.0 |
full | lut | cython| 7.155 | 11.516 | 1.6 |
full | csr | cython| 8.101 | 16.944 | 2.1 |
full | csr | python| 12.732 | 16.990 | 1.3 |
full | csc | cython| 10.287 | 14.022 | 1.4 |
full | csc | python| 14.935 | 21.987 | 1.5 |
no | histogram | opencl| 9.404 | 2.698 | 0.3 | NVIDIA CUDA / NVIDIA RTX A5000
no | histogram | opencl| 8.459 | 4.209 | 0.5 | NVIDIA CUDA / Quadro P2200
no | histogram | opencl| 14.044 | 10.007 | 0.7 | Portable Computing Language / cpu-haswell-AMD Ryzen Threadripper PRO 3975WX 32-Cores
no | histogram | opencl| 11.260 | 7.409 | 0.7 | Intel(R) OpenCL / AMD Ryzen Threadripper PRO 3975WX 32-Cores
bbox | csr | opencl| 0.702 | 2.646 | 3.8 | NVIDIA CUDA / NVIDIA RTX A5000
no | csr | opencl| 0.658 | 2.571 | 3.9 | NVIDIA CUDA / NVIDIA RTX A5000
bbox | csr | opencl| 1.217 | 6.083 | 5.0 | NVIDIA CUDA / Quadro P2200
no | csr | opencl| 1.076 | 6.044 | 5.6 | NVIDIA CUDA / Quadro P2200
bbox | csr | opencl| 3.725 | 7.421 | 2.0 | Portable Computing Language / cpu-haswell-AMD Ryzen Threadripper PRO 3975WX 32-Cores
no | csr | opencl| 2.993 | 5.990 | 2.0 | Portable Computing Language / cpu-haswell-AMD Ryzen Threadripper PRO 3975WX 32-Cores
bbox | csr | opencl| 2.915 | 82.315 | 28.2 | Intel(R) OpenCL / AMD Ryzen Threadripper PRO 3975WX 32-Cores
no | csr | opencl| 2.003 | 82.015 | 41.0 | Intel(R) OpenCL / AMD Ryzen Threadripper PRO 3975WX 32-Cores
full | csr | opencl| 0.704 | 2.565 | 3.6 | NVIDIA CUDA / NVIDIA RTX A5000
full | csr | opencl| 1.219 | 6.083 | 5.0 | NVIDIA CUDA / Quadro P2200
full | csr | opencl| 4.180 | 7.451 | 1.8 | Portable Computing Language / cpu-haswell-AMD Ryzen Threadripper PRO 3975WX 32-Cores
full | csr | opencl| 2.789 | 82.252 | 29.5 | Intel(R) OpenCL / AMD Ryzen Threadripper PRO 3975WX 32-Cores
bbox | lut | opencl| 3.174 | 297.997 | 93.9 | NVIDIA CUDA / NVIDIA RTX A5000
no | lut | opencl| 1.590 | 178.964 | 112.6 | NVIDIA CUDA / NVIDIA RTX A5000
bbox | lut | opencl| 3.149 | 298.830 | 94.9 | NVIDIA CUDA / Quadro P2200
no | lut | opencl| 1.811 | 181.036 | 100.0 | NVIDIA CUDA / Quadro P2200
bbox | lut | opencl| 4.596 | 167.232 | 36.4 | Portable Computing Language / cpu-haswell-AMD Ryzen Threadripper PRO 3975WX 32-Cores
no | lut | opencl| 3.617 | 135.159 | 37.4 | Portable Computing Language / cpu-haswell-AMD Ryzen Threadripper PRO 3975WX 32-Cores
bbox | lut | opencl| 3.778 | 210.177 | 55.6 | Intel(R) OpenCL / AMD Ryzen Threadripper PRO 3975WX 32-Cores
no | lut | opencl| 2.601 | 178.323 | 68.5 | Intel(R) OpenCL / AMD Ryzen Threadripper PRO 3975WX 32-Cores
full | lut | opencl| 2.600 | 294.105 | 113.1 | NVIDIA CUDA / NVIDIA RTX A5000
full | lut | opencl| 2.702 | 299.181 | 110.7 | NVIDIA CUDA / Quadro P2200
full | lut | opencl| 4.621 | 166.068 | 35.9 | Portable Computing Language / cpu-haswell-AMD Ryzen Threadripper PRO 3975WX 32-Cores
full | lut | opencl| 3.341 | 213.092 | 63.8 | Intel(R) OpenCL / AMD Ryzen Threadripper PRO 3975WX 32-Cores
--------------------------------------------------------------------------------
[7]:
print(f"Total runtime: {time.perf_counter()-start_time:.3f}s")
Total runtime: 462.969s