Navigation

Tools

Category: HPC, Tools

The HPC-focused Julia programming language community grows day by day. Julia is developed by the Julia Lab at MIT's Computer Science and Artificial Intelligence Laboratory (CSAIL). Valentin Churavy, graduate student at MIT, created an interface to the LIKWID tool suite and library, developed by the ...

Category: HPC, Tools

MachineState is a python3 module and CLI application for documenting and comparing settings known to affect application performance: e.g., CPU/Uncore frequencies, hardware prefetchers, memory capacity, but also OS and software settings like NUMA balancing, writeback workqueues, scheduling, or the ve...

Category: HPC, Tools

Our paper "Automatic Throughput and Critical Path Analysis of x86 and ARM Assembly Kernels" has just won the "Best Late-Breaking Paper Award" at the 10th Workshop on Performance Modeling, Benchmarking and Simulation of High Performance Computer Systems (PMBS19), a renowned workshop co-located with t...

Category: Tools

We are happy to announce the release of a new version of LIKWID. Until now, LIKWID mainly focused on x86 processors. The new version 5 adds support for ARM and POWER processors as well as Nvidia GPUs.

Category: HPC, Tools

The Bandwidth Benchmark is a collection of simple streaming kernels. While it may be used for microbenchmarking, we mainly want to use it in teaching. It is heavily inspired by John McCalpin's STREAM benchmark. It comprises eight typical streaming kernels with different data access patterns for m...

Category: HPC, Tools

LIKWID 4.3.4 is a bugfix release. These are the relevant changes: For systems using Intel Cluster-on-Die (CoD) or Sub-NUMA Clustering (SNC): Fix for detecting PCI devices Workaround for topology detection. The Linux kernel does not detect it properly sometimes. Don't pin accessDa...

Category: HPC, Tools

LIKWID 4.3.2 has just been released. This is an important maintenance release if you need support for the latest architectures: Support for Intel Knights Mill (core, RAPL, Uncore) AMD Zen: Use RETIRED_INSTRUCTIONS instead of fixed-purpose counter for metric calculation Intel Skylake X: So...