NVIDIA Grace Hopper Superchip Dominates MLPerf Inference Benchmarks

NVIDIA has made quite a splash in the world of artificial intelligence (AI) and high-performance computing with its latest unveiling – the NVIDIA GH200 Grace Hopper Superchip. This recent offering has shown outstanding performance in the MLPerf benchmarks, demonstrating NVIDIA's prowess in cloud and edge AI. (more…)
Read More

Habana Gaudi2 AI Accelerators Outperforms NVIDIA H100 on BridgeTower Models

Earlier this year, Intel published performance results between Intel Habana Gaudi2 and GPU market leader NVIDIA that illustrated Intel's commitment to AI and proved AI is not a one-size-fits-all category. At the same time, a joint development between Intel AI researchers and Microsoft Research created BridgeTower, a pre-trained multimodal transformer delivering state-of-the-art vision-language tasks. Hugging Face has integrated this model into its open-source library for machine learning. (more…)
Read More

From SLI to NVLink: The Evolution of Gaming and Multi-GPU Technologies and Their Influence on AI

The landscape of graphics processing units (GPUs) has experienced seismic shifts over the past two decades, much more recently with the surge of AI. A significant part of this evolution has been the development of technologies that allow multiple GPUs to work in tandem. NVIDIA, a frontrunner in the GPU space, has been at the forefront of this revolution with two pivotal technologies: Scalable Link Interface (SLI) and NVIDIA NVLink. This article traces the journey from SLI to NVLink, highlighting how NVIDIA continually adapts to ever-changing computing demands. (more…)
Read More