Author: Thomas Gruber

Today, shortly before Christmas, we are happy to announce a new LIKWID release, version 5.5.1. Fixes for AMD RAPL units Fixes for AMD Zen4/4c/5/5c memory controllers Updated help text formats The new version can be downloaded from our FTP and on GitHub. It will be available soon in...

Today, the LIKWID team has released a new major version. Version 5.5.0 comes with new architectures, some fixes and some changes to internals: Added support for AMD Zen5 Topdown metrics for Intel Sapphire Rapids, Emerald Rapids, and Granite Rapids Update for Nvidia GPU support Less s...

We are happy to announce a bugfix release of LIKWID (5.4.1). This is what got fixed: Fixes linking errors due to missing bstrlib.h Fix for likwid-bench kernel stream_mem Fix builds with CUDA for versions 11.2 to 12.6 Fix sysfeatures with ACCESSMODE=perf_event Add AMD Zen1 to Zen...

After a year without an update, we are happy to release the new version 5.4.0 of LIKWID. This is what's new: Support for Intel Granite Rapids (core, energy, uncore) Support for Intel Sierra Forest (core, energy, uncore) Support for AMD Bergamo (core, energy, uncore) Support for Nvi...

We are happy to release version 5.3.0 of LIKWID, the tools suite for performance oriented programmers. Thanks to all the contributors, especially HPE for the AMD ROCm backend. You can download it from our FTP server or the GitHub repository. Changelog for 5.3.0: - Support for Intel SapphireRa...

We are happy to announce the new version 5.2.2 of the LIKWID toolsuite. It contains bugfixes for various architectures and execution modes. You can download it from our FTP server or the GitHub repository. Changelog: Fix pin string parsing in pinning library Make SBIN path configurable...

We are happy to announce that the Julia wrapper LIKWID.jl now supports all features of the LIKWID library

We are happy to release a new bugfix release of the LIKWID toolsuite (version 5.2.1). Add support for Intel Rocketlake and AMD Zen3 variant (Family 19, Model 0x50) Fix for perf_event multiplexing (important!) Fix for potential deadlock in MarkerAPI (thx @jenny-cheung) Build and runtime...

Since June 2020, the Top500 list is led by the supercomputer Fugaku, which comprises over 7.5 million Fujitsu A64FX cores. Besides their raw computational power, the cores are equipped with features that support parallel execution on the systems: hardware barrier, sector cache (cache partitioning), ...

We are happy to announce a major release LIKWID 5.2.0.