Peter Zhang
Nov 20, 2024 14:09
NVIDIA technology now accelerates 384 of the world’s top supercomputers, enabling breakthroughs in climate forecasting, drug discovery, and quantum simulation, according to the latest TOP500 list.
NVIDIA’s dominance in the field of accelerated computing continues to grow, as highlighted by the latest TOP500 list of the world’s most powerful supercomputers. According to NVIDIA, 384 of these systems now operate on its technology, facilitating significant breakthroughs in areas such as climate forecasting, drug discovery, and quantum simulation.
Accelerated Computing’s Role in Scientific Progress
Since the introduction of CUDA in 2006, NVIDIA has been at the forefront of advancements in artificial intelligence and accelerated computing. The recent TOP500 list underscores the company’s achievements, with 87% of the 53 new entries being accelerated systems, 85% of which utilize NVIDIA Hopper GPUs. These systems are pivotal in driving research in critical areas, from climate modeling to drug development.
At the SC24 conference, NVIDIA unveiled cuPyNumeric, a CUDA-X library that enables developers to scale their applications seamlessly across computing clusters without modifying their Python code. Additionally, updates to the NVIDIA CUDA-Q platform were announced, empowering researchers to simulate quantum devices on an unprecedented scale.
Mixed Precision and AI: New Tools for Researchers
Mixed-precision floating-point operations and AI are increasingly becoming essential tools for modern scientific research. At SC24, two projects nominated for the Gordon Bell Prize demonstrated how these technologies are advancing genomics and protein design. Using mixed precision, researchers like David Keyes and Arvind Ramanathan have achieved remarkable results in genomics and protein design, respectively, leveraging NVIDIA’s powerful computing platforms.
NVIDIA’s BioNeMo framework, now open source, further supports AI-driven drug discovery, enabling rapid creation and deployment of AI models for pharmaceutical applications. This reflects a broader shift towards AI and mixed-precision operations across the TOP500, with 249 exaflops of AI performance now accessible to these systems.
Sustainability in Accelerated Computing
As computational demands increase, so does the need for sustainability. NVIDIA’s solutions rank among the most energy-efficient, with systems like the JEDI at EuroHPC/FZJ setting benchmarks in energy efficiency. The company also introduced new NIM microservices for its Earth-2 platform, significantly accelerating climate modeling and simulation.
In an era of heightened environmental awareness, NVIDIA’s advancements in accelerated computing offer a balance between performance and sustainability, paving the way for a future where high-performance computing can coexist with energy efficiency.
For more insights, visit the NVIDIA blog.
Image source: Shutterstock
