E2E benchmark tests

[efajardo-nv]

Uses pytest-benchmark to perform E2E benchmarks on the following workflows:

• SID NLP
• Phishing Detection NLP
• ABP FIL
• HAMMAH

Input for these tests are pulled from LFS data already included in this repo. Hook is used to add the following information to the output JSON:

GPU:

"gpu_0": {
    "id": 0,
    "name": "Quadro RTX 8000",
    "load": "0.0%",
    "free_memory": "42444.0MB",
    "used_memory": "6156.0MB",
    "temperature": "61.0 C",
    "uuid": "GPU-dc32de82-bdaa-2d05-2abe-260a847e1989"
}

Morpheus config for each workflow:

• num_threads
• pipeline_batch_size
• model_max_batch_size
• feature_length
• edge_buffer_size

Additional benchmark stats for each workflow:

• input_lines
• min_throughput_lines
• max_throughput_lines
• mean_throughput_lines
• median_throughput_lines
• input_bytes
• min_throughput_bytes
• max_throughput_bytes
• mean_throughput_bytes
• median_throughput_bytes

Thoughputs were calculated by dividing input lines/bytes by total runtimes. These calculations will be replaced using tracer implementation developed by @drobison00. Tracer will be added in a separate PR.

[mdemoret-nv]

Lets get this merged and update when the SRF tracing has been fixed.

[mdemoret-nv]

Let move one file into a JSON

[mdemoret-nv]

LGTM

[mdemoret-nv]

@gpucibot merge