Additional speed benchmarks

All methods are benchmarked using their default parameters, with the following exceptions:

  • basex(var) and daun(var) mean “variable regularization”, that is changing the regularization parameter for each transformed image.

  • direct_C and direct_Python correspond to the “direct” method using its C (Cython) and Python backends respectively.

  • linbasex and rbasex show whole-image (n × n) transforms, while all other methods show half-image (n rows, (n + 1)/2 columns) transforms.

  • rbasex(None) means no output-image creation (only the transformed radial distributions).

Intel i7-9700 (Linux)

CPU:

Intel Core i7-9700 (8 cores, 8 threads; 3.0 GHz base, 4.7 GHz max)

RAM:

32 GB DDR4-2666

OS:

Ubuntu 20.04 LTS

Libraries:
  • NumPy 1.18.1

  • SciPy 1.4.1

  • MKL 2020

  • daz

Results

../../../_images/benchmarks-1.svg
../../../_images/benchmarks-2.svg
../../../_images/benchmarks-3.svg

Intel i7-6700 (Linux)

CPU:

Intel Core i7-6700 (4 cores, 8 threads; 3.4 GHz base, 4.0 GHz max)

RAM:

32 GB DDR4-2133

OS:

Ubuntu 19.10

Libraries:
  • NumPy 1.18.1

  • SciPy 1.4.1

  • MKL 2019 Update 5

  • daz

Results

../../../_images/benchmarks-4.svg
../../../_images/benchmarks-5.svg
../../../_images/benchmarks-6.svg

AMD Ryzen 5 5600G (Linux)

CPU:

AMD Ryzen 5 5600G (6 cores, 12 threads; 3.9 GHz base, 4.4 GHz max)

RAM:

32 GB DDR4-3200

OS:

Debian GNU/Linux 12

Libraries:
  • NumPy 1.24.2

  • SciPy 1.10.1

  • OpenBLAS 0.3.21

Results

../../../_images/benchmarks-7.svg
../../../_images/benchmarks-8.svg
../../../_images/benchmarks-9.svg

AMD Ryzen 5 5600G (Windows)

CPU:

AMD Ryzen 5 5600G (6 cores, 12 threads; 3.9 GHz base, 4.4 GHz max)

RAM:

32 GB DDR4-3200

OS:

Microsoft Windows 11

Libraries:
  • NumPy 1.26.0

  • SciPy 1.11.2

  • OpenBLAS 0.3.23

Results

../../../_images/benchmarks-10.svg
../../../_images/benchmarks-11.svg
../../../_images/benchmarks-12.svg

Raspberry Pi 4B (Linux)

CPU:

Broadcom BCM2711 (4 cores; 1.5 GHz)

RAM:

4 GB LPDDR4-3200

OS:

Raspbian GNU/Linux 10

Libraries:
  • NumPy 1.16.2

  • SciPy 1.1.0

  • Reference BLAS 3.8.0

Results

../../../_images/benchmarks-13.svg
../../../_images/benchmarks-14.svg
../../../_images/benchmarks-15.svg