October was Performance Month for Chameleon Cloud. We're excited to share a variety of performance upgrades for various testbed services, a new Trovi feature, new webinars, user resources, and awesome Trovi artifacts developed by our users!
Reproducibility is a cornerstone of scientific computing, yet achieving consistent results across different hardware environments remains a significant challenge in HPC research. The MINCER project tackles this problem head-on by providing researchers with an automated performance measurement appliance on Chameleon Cloud. Using Docker containers and the PAPI framework, MINCER enables standardized collection of performance metrics across CPUs, NVIDIA GPUs, and AMD GPUs, making it easier to compare results and understand how system-level factors influence computational performance. This post explores how MINCER is helping make HPC experiments more reproducible and accessible to the research community.
Not sure whether to use bare metal or KVM for your next Chameleon experiment? You're not alone. With KVM's recent addition of H100 GPUs and advance reservations, the choice isn't always obvious. This comprehensive comparison walks you through the practical trade-offs: when you need the isolation of bare metal for accurate benchmarking, when KVM's 6-month leases and resource sharing make more sense, and how to navigate the different storage and networking options. Make informed infrastructure decisions that accelerate your research.
This month we have some exciting updates to Trovi’s dashboard, support for 4xGPU instances on KVM@TACC, improvements to cc-snapshot, and a new webinar series!
This summer, three talented students used Chameleon to tackle challenges ranging from wildlife conservation to reproducibility and AI-assisted documentation. Their innovative work earned them spots at the ACM Student Research Competition at SC'25, where they'll present posters on autonomous bioacoustic monitoring, snapshot performance optimization, and intelligent documentation systems. Discover how Hudson Reynolds, Alex Tuecke, Zahra Temori, and Saieda Ali Zada leveraged Chameleon's infrastructure to create impactful solutions.
Join us at the CARLA Latin America High Performance Computing Conference for the keynote presentation by Kate Keahey, Scientist at Argonne National Laboratory and University of Chicago. Kate will deliver her keynote, “Infrastructure for New Ideas,” at 9:10 AM on Thursday in the Talk of the Town venue. Don’t miss this opportunity to learn about building scientific instruments for computer science innovation and hear insights from the leader of the Chameleon project.
Don't let authentication problems derail your research momentum. This practical guide demystifies Chameleon's login system and arms you with clear, step-by-step solutions for the authentication challenges that frustrate users most. Learn to confidently navigate multiple accounts, identity provider changes, and stubborn login issues.
New H100 hardware on KVM@TACC, and good news about KVM lease limits, quotas, and SU cost. Additionally, we have SU changes for baremetal, an improved the resource browser, and are announcing the deprecation of TACC login.
Traditional distributed databases are often slowed down by network communication overhead. The Tigon project introduces a new database design that tackles this bottleneck using Compute Express Link (CXL), a technology that allows multiple computer hosts to access a shared memory pool. Tigon employs a hybrid approach, keeping most data in fast, local host memory while moving only actively shared data to the CXL memory. This results in significant performance gains, achieving up to 2.5 times higher throughput than traditional databases. Since the multi-host CXL hardware required for this research was not yet commercially available, the project was brought to life …
Have you completed the Chameleon Getting Started guide and are wondering what comes next? This post will help you dive deeper by moving beyond the basics. You will learn how to interact with the Chameleon API from the command line on an instance and from your laptop. We'll also cover how to use tools like rclone and cc-snapshot to securely save and manage your valuable research data.