[Experiment] Make resize block sizes tweakable via environment variables.

[mzient]

Category:

Other Performance tuning

Description:

The logical blocks seem to have been too large for resize and resulted in GPU underutilization. This PR adds two environment variables that control the block sizes: DALI_RESIZE_CUDA_BLOCK - for the CUDA block DALI_RESIZE_MAX_ELEMENTS_PER_BLOCK - for the logical block

Previous defaults were: For 2D: 768 and unlimited (32image_width for vertical pass and/ 32image_height for horizontal pass). For 3D: 256 and 262,144

Additional information:

Affected modules and functionalities:

Key points relevant for the review:

Tests:

Resampling kernel tests and Python tests for Resize operator

• [X] Existing tests apply
• [ ] New tests added
  • [ ] Python tests
  • [ ] GTests
  • [ ] Benchmark
  • [ ] Other
• [ ] N/A

Checklist

Documentation

• [ ] Existing documentation applies
• [ ] Documentation updated
  • [ ] Docstring
  • [ ] Doxygen
  • [ ] RST
  • [ ] Jupyter
  • [ ] Other
• [X] N/A

DALI team only

Requirements

• [ ] Implements new requirements
• [ ] Affects existing requirements
• [X] N/A

REQ IDs: N/A

JIRA TASK: N/A

[dali-automaton]

CI MESSAGE: [12516031]: BUILD STARTED

[dali-automaton]

CI MESSAGE: [12516031]: BUILD PASSED

[stiepan]

!build

[dali-automaton]

CI MESSAGE: [12818339]: BUILD STARTED

[stiepan]

!build

[dali-automaton]

CI MESSAGE: [12818707]: BUILD STARTED

[dali-automaton]

CI MESSAGE: [12818707]: BUILD FAILED

[stiepan]

!build

[dali-automaton]

CI MESSAGE: [13028849]: BUILD STARTED

[dali-automaton]

CI MESSAGE: [13028849]: BUILD FAILED

[mzient]

The tweaks have been used to establish optimum settings. The adjustment is merged as #5382 .