Nvidia H100 cluster on Coreweave cloud sets new Graph500 record

Nvidia and Coreweave have set a new Graph500 breadth first search record using a commercially available H100 GPU cluster that more than doubles the performance of rival systems.

Nvidia has achieved the world’s top-performing result for large scale graph processing using a commercially available cluster hosted on the Coreweave cloud platform. The company reported a benchmark result of 410 trillion traversed edges per second (TEPS), which ranked No. 1 on the 31st Graph500 breadth-first search (BFS) list. The record setting run was executed on an accelerated computing cluster located in a Coreweave data center in Dallas.

The winning configuration used 8,192 Nvidia H100 GPUs to process a graph containing 2.2 trillion vertices and 35 trillion edges. This result is described as more than double the performance of comparable solutions listed on Graph500, including entries operated by national laboratories. The system demonstrates that a commercially available cloud cluster can outperform highly specialized installations in large scale graph analytics workloads.

To illustrate the scale, the article notes that if every person on Earth had 150 friends, this would correspond to 1.2 trillion edges in a social relationship graph. According to Nvidia and Coreweave, their system enables searching through every such friend relationship on Earth in just about three milliseconds. The article emphasizes that speed at this scale is only part of the achievement, with efficiency also highlighted, as a comparable top 10 Graph500 entry used about 9,000 nodes, while the Nvidia run used just over 1,000 nodes, delivering 3x better performance per dollar.

58

Impact Score

Google Cloud agent development kit brings structure to autonomous artificial intelligence

Google Cloud’s agent development kit introduces a structured framework for building autonomous artificial intelligence agents that can reason, act, and observe, tightly integrated with Vertex Artificial Intelligence for deployment and evaluation. The toolkit targets enterprises that need reliable, multi-step workflows rather than single-turn large language model calls.

AMD and Samsung explore 2 nm foundry deal for future Epyc and Ryzen chips

Samsung is in talks with AMD to manufacture next-generation Epyc and potentially Ryzen processors on its second-generation 2 nm SF2P process, a move that could give AMD a dual-foundry strategy alongside TSMC. The discussions build on a growing Artificial Intelligence hardware partnership that already spans high-bandwidth memory for AMD accelerators.

Nvidia introduces Nemotron 3 open models for multi agent artificial intelligence

Nvidia has launched the Nemotron 3 family of open models, data and libraries to support transparent and specialized multi agent artificial intelligence development, using a hybrid mixture-of-experts architecture. The lineup targets organizations moving from single chatbots to collaborative agent systems while aiming to reduce communication overhead, context drift and inference costs.

Contact Us

Got questions? Use the form to contact us.

Contact Form

Clicking next sends a verification code to your email. After verifying, you can enter your message.