Skip to main content

Android SoC benchmarking CLI for latency, loaded latency, and memory subsystem characterization

Project description

BenchmarkingCLI

A command-line tool for running latency benchmarks on Android devices. This tool automates the process of pushing benchmark binaries to connected Android devices, executing latency tests, and collecting performance metrics in CSV format.

Features

  • Latency Testing: Measure memory latency across different buffer sizes on a specific core
  • Loaded Latency Testing (v0.3+): Measure latency under concurrent bandwidth loads with configurable kernel modes and thread settings
  • GPU Loaded Latency Testing (v0.4+): Measure memory latency under concurrent GPU load
  • CSV Export: Results are automatically parsed and exported to timestamped CSV files
  • CLI Interface: Easy-to-use command-line interface

Requirements

Host Machine

  • Python: 3.8 or higher
  • Android Debug Bridge (ADB): Version 1.0.40+
    • Linux: apt-get install android-tools-adb
    • macOS: brew install android-platform-tools
    • Windows: Download the SDK Platform Tools and add to PATH
    • Verify installation: adb version

Android Device

  • USB debugging must be enabled on the device. To enable it:
    1. Go to Settings → About Phone
    2. Tap Build Number 7 times until you see "You are now a developer"
    3. Go to Settings → Developer Options
    4. Enable USB Debugging
  • Connect the device via USB and accept the "Allow USB Debugging" prompt on the device
  • Confirm the device is detected: adb devices

Installation

Install directly from PyPI:

pip install benchmarkingcli

Usage

Latency Test

Run a basic latency benchmark on a specific core:

# Run on default core (7)
benchmarkingcli latency

# Run on a specific core
benchmarkingcli latency --core 4

Parameters:

  • --core: CPU core to run the latency test on (default: 7)
  • --output-dir: Directory to save results (default: current directory)

Output

Results are exported as CSV files with the following columns:

  • buffer_size_kb: Size of the buffer tested (in KB)
  • min_ns: Minimum latency (nanoseconds)
  • mean_ns: Mean latency (nanoseconds)
  • max_ns: Maximum latency (nanoseconds)

Example output file: latency_results_20260427_115540.csv

Loaded Latency Test (v0.3+)

Run a latency benchmark under concurrent bandwidth load:

# Run with default settings
benchmarkingcli loadedlatency

# Run with custom configuration
benchmarkingcli loadedlatency --lat-buffer-mb 128 --bw-buffer-mb 128 --latency-core 7 --bw-cores 0,1,2,3 --kernel-mode TRIAD --ilp 4 --injection-rate desc --output-dir ./results

Parameters:

  • --lat-buffer-mb: Latency buffer size in MB (default: 128)
  • --bw-buffer-mb: Bandwidth buffer size in MB (default: 128)
  • --latency-core: Core to run latency thread on (default: 7)
  • --bw-cores: Comma-separated cores for bandwidth threads (default: 0,1,2,3,4,5)
  • --kernel-mode: Kernel mode: SUM/COPY/UPDATE/TRIAD or 1/2/3/4 (default: TRIAD)
  • --ilp: Unroll factor: 1/2/4/8/16/32 (default: 4)
  • --injection-rate: Injection rate: asc or desc (default: asc)
  • --output-dir: Directory to save results (default: current directory)

Important Update (v0.4+): The --tile-delay-sweep-order parameter has been renamed to --injection-rate. Supported values are asc and desc.

GPU Loaded Latency Test (v0.4+)

Run a latency benchmark under concurrent GPU load:

# Run with default settings
benchmarkingcli gpuloadedlatency

# Run with custom configuration
benchmarkingcli gpuloadedlatency --latency-core 7 --lat-buffer-mb 128 --gpu-buffer-mb 128 --kernel-mode TRIAD --output-dir ./results

Parameters:

  • --latency-core: Core to run latency thread on (default: 7)
  • --lat-buffer-mb: Latency buffer size in MB (default: 128)
  • --gpu-buffer-mb: GPU workload buffer size in MB (default: 128)
  • --kernel-mode: Kernel mode: SUM/COPY/UPDATE/TRIAD or 1/2/3/4 (default: TRIAD)
  • --output-dir: Directory to save results (default: current directory)

Troubleshooting

"No ADB devices found"

  • Check that your Android device is connected: adb devices
  • Ensure USB debugging is enabled on the device
  • Try: adb kill-server then adb start-server

"Latency test binary not found"

  • Reinstall the package: pip install --force-reinstall benchmarkingcli

Binary push fails

  • Check device storage: adb shell df /data/local/tmp
  • Verify ADB permissions: adb shell ls -la /data/local/tmp

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

benchmarkingcli-0.4.1.tar.gz (2.1 MB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

benchmarkingcli-0.4.1-py3-none-any.whl (2.1 MB view details)

Uploaded Python 3

File details

Details for the file benchmarkingcli-0.4.1.tar.gz.

File metadata

  • Download URL: benchmarkingcli-0.4.1.tar.gz
  • Upload date:
  • Size: 2.1 MB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.13.5

File hashes

Hashes for benchmarkingcli-0.4.1.tar.gz
Algorithm Hash digest
SHA256 e2a90342a1bb7a93df53b30595bd965905448b2693dbaa0ee79ef5d0764225b6
MD5 5369cbddc2076e599cd9e19e1d65eccb
BLAKE2b-256 48f842b676646da1c785037482f0bf5c7f895ce21e89d42460555a75d6b86601

See more details on using hashes here.

File details

Details for the file benchmarkingcli-0.4.1-py3-none-any.whl.

File metadata

File hashes

Hashes for benchmarkingcli-0.4.1-py3-none-any.whl
Algorithm Hash digest
SHA256 d01fb264acedf9d3853a80849a03f91122018e6e395a3603e197b80918e0e53c
MD5 92bba20f7c830db6d4c76e9e5f7505db
BLAKE2b-256 7b654898f2ea2a14e5a742939a1e567c862404745a010a1d7711643d7956d2ab

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page