A comprehensive and architecture-agnostic performance analysis tool addressing your software, hardware, and system needs. Both today and tomorrow. Formerly AdaptivePerf.
Get started with the early development versionNews updates on and pull requests of the new Adaptyst release (4 Jul 2025)
New Adaptyst release delayed (23 Jun 2025)
Preliminary NVIDIA GPU support will be available by 23 June (15 Jun 2025)
Adaptyst profiles and produces code-detailed analyses (such as flame graphs) for both on-CPU and off-CPU activity of any software on Linux, with full stack traces (frame pointers required) and all threads/processes properly traced. Low-level computer interactions can also be processed to the extent supported by your hardware (e.g. cache misses).
Intel? AMD? ARM? RISC-V? Something else? Don't worry, Adaptyst works everywhere where Linux and "perf" runs. There is also active work in progress to go beyond "perf" and add support for other configurations.
Adaptyst is under active development as an open-source project at CERN, currently within the EU-funded SYCLOPS initiative. It is available free of charge on GitHub and development and roadmap implementation news is posted at least weekly!
Programming microcontrollers or bare-metal systems? Designing custom hardware at the edge? Using GPUs? Running calculations on standard computers? Working on large-scale computations? Anything in-between? Adaptyst will get you covered. See our roadmap.
Algorithmic optimisations alone are becoming insufficient. Given your workflow, requirements, and constraints, Adaptyst will propose the best compute solution covering all sides of computation: software + hardware + systems. This includes not just code optimisation, but also selecting and customising compute units (CPUs, GPUs, FPGAs etc.), OS, memory, storage, networking, etc. See our roadmap.
The technological landscape is changing very rapidly and tools relevant today may become obsolete tomorrow. Adaptyst will be always up-to-date with the market thanks to its envisaged modular design and API for both workflows and systems/hardware. See our roadmap.