clpeak
github.com
What it is
clpeak is free GPL-3.0 software that benchmarks peak compute throughput, memory bandwidth, and latency on CPUs, GPUs, and NPUs. It runs the same tests through available device APIs so results can be compared between machines. Coverage includes compute, matrix engines, vendor libraries, bandwidth, latency, AI workloads, and CPU-specific operations. GPU backends include CUDA, ROCm/HIP, Metal, oneAPI/SYCL, Vulkan, and OpenCL; AI runtimes include ONNX Runtime, Core ML, and LiteRT. The app detects devices, streams measurements, and keeps renameable run history that can be exported as JSON. Its CLI selects devices, backends, and test categories, describes measurements, saves JSON runs, and compares saved runs. It runs on Windows, macOS, Linux, iOS, and Android. Releases include platform archives, a macOS DMG, Snap distribution, and Google Play availability.
Spec sheet
- Purpose
- clpeak measures peak compute throughput, memory bandwidth and latency on CPUs, GPUs and NPUs.Read 11 Oct 2026 · krrishnarraj.github.io
- Platforms
- The project describes its app as running on Windows, macOS, Linux and Android.Read 11 Oct 2026 · krrishnarraj.github.io
- Support
- The project directs users to open a GitHub issue and attach verbose run diagnostics when reporting bugs.Read 11 Oct 2026 · krrishnarraj.github.io
- License
- The project is GPL-3.0 licensed.Read 11 Oct 2026 · krrishnarraj.github.io
- AI runtimes
- AI runtime backends include ONNX Runtime, Core ML and LiteRT.Read 11 Oct 2026 · krrishnarraj.github.io
- App features
- The app lists detected devices, streams results as measured, and keeps run history that users can rename and export as JSON.Read 11 Oct 2026 · krrishnarraj.github.io
- Benchmark coverage
- Tests cover compute, matrix engines, vendor libraries, bandwidth, latency, AI workloads and CPU-specific operations.Read 11 Oct 2026 · krrishnarraj.github.io
- CLI or automation
- YesRead 23 Sep 2026 · github.com
- Command line
- The CLI can select devices, backends and test categories, describe measurements, save runs as JSON and compare against saved runs.Read 11 Oct 2026 · krrishnarraj.github.io
- Comparison
- It runs the same tests through available device APIs so results from one machine can be compared side by side.Read 11 Oct 2026 · krrishnarraj.github.io
- Comparison database
- NoRead 23 Sep 2026 · github.com
- Distribution
- Releases provide platform zip files containing the CLI and app, backend variants, and a macOS app DMG; Linux is also available through Snap and Android through Google Play.Read 11 Oct 2026 · krrishnarraj.github.io
- GPU backends
- GPU backends include CUDA, ROCm/HIP, Metal, oneAPI/SYCL, Vulkan and OpenCL.Read 11 Oct 2026 · krrishnarraj.github.io
- Operating systems
- Windows; macOS; Linux; iOS; AndroidRead 23 Sep 2026 · github.com
- Result export formats
- JSONRead 23 Sep 2026 · github.com
- Security detail
- The release binaries are not signed with a developer certificate, so Windows and macOS prompt users before first launch.Read 11 Oct 2026 · krrishnarraj.github.io
- Workload areas
- compute throughput; memory bandwidth; matrix throughput; kernel launch latency; AI inferenceRead 23 Sep 2026 · github.com
Plans and prices
Strong points and limits
Strong points
- Measures compute, bandwidth, and latency
- Supports many GPU and AI backends
- Runs on five operating system families
- CLI supports saved-run comparisons
- Results export as JSON
Limits
- No comparison database is provided
- Unsigned binaries may trigger launch warnings
- GPL-3.0 licensing may not suit every project
Who it suits
clpeak suits developers and technical users comparing hardware performance across CPUs, GPUs, and NPUs. Its CLI and JSON export also fit automated benchmark workflows.
Verdict
clpeak offers broad cross-platform benchmarking with both graphical and command-line workflows. Its backend coverage and JSON run handling support repeatable comparisons, though releases are unsigned.
Where Specifiction places it
- PC Benchmark Software#11 of 738.4
- PC benchmark tools#33 of 708.0