Benchmarks: Add Feature - Add GPU-Burn as microbenchmark

[rafsalas19]

Description
Modifications adding GPU-Burn to SuperBench.

• added third party submodule
• modified Makefile to make gpu-burn binary
• added/modified microbenchmarks to add gpu-burn python scripts
• modified default and azure_ndv4 configs to add gpu-burn

[yzygitzh]

@rafsalas19 Thanks a lot for the PR! Overall it looks good to me. I have some general comments:

1. Please help provide a unit-test (which should be both CUDA/ROCm test) that checks the output parsing logic. test_gpu_copy_bw_performance.py can be a reference.
2. Please help add an example usage file for gpu-burn microbenchmark. gpu_copy_bw_performance.py can be a reference.
3. Please help add description for new metrics in micro-benchmarks.md.

[abuccts]

pls run python3 setup.py lint to check lint issues, python3 setup.py format may help fix part of lint issues automatically.

[abuccts]

pls run python3 setup.py format and commit changes to pass the pipeline.

[codecov]

Codecov Report

Merging #324 (bc5a79a) into main (84359fd) will decrease coverage by 0.16%.
The diff coverage is 77.77%.

@@            Coverage Diff             @@
##             main     #324      +/-   ##
==========================================
- Coverage   88.78%   88.61%   -0.17%     
==========================================
  Files          77       78       +1     
  Lines        4593     4665      +72     
==========================================
+ Hits         4078     4134      +56     
- Misses        515      531      +16     

Flag	Coverage Δ
cpu-unit-test	73.30% <77.77%> (+0.07%)	⬆️
cuda-unit-test	88.55% <77.77%> (-0.17%)	⬇️

Flags with carried forward coverage won't be shown. Click here to find out more.

Impacted Files	Coverage Δ
...bench/benchmarks/micro_benchmarks/gpu_burn_test.py	77.46% <77.46%> (ø)
superbench/benchmarks/micro_benchmarks/__init__.py	100.00% <100.00%> (ø)

---

Continue to review full report at Codecov.

Legend - Click here to learn more
Δ = absolute <relative> (impact), ø = not affected, ? = missing data
Powered by Codecov. Last update 84359fd...bc5a79a. Read the comment docs.