NVIDIA at SC23

Name: NVIDIA at Supercomputing 2023 (SC23) Conference
Start: 2023-11-12
End: 2023-11-17

2023 年 11 月 12 - 17 日

科羅拉多州丹佛 Colorado 會議中心

立即觀看特別演講

活動議程
技術展示
開發人員計劃
DLI
大學招募

活動議程
技術展示
開發人員計劃
DLI
大學招募

在線上與我們一同參與 Supercomputing 2023 (SC23)，瞭解 GPU 運算和高效能網路如何改變運算科學和人工智慧。我們將舉辦來自產業龍頭和尖端領域的演講者的開創性會議、技術演示、以及其他相關內容。

NVIDIA SC23 特別演講

11 月 13 日晚上10:00 (台灣時間)，將由 Ian Buck (NVIDIA)、Kristel Michielsen (Jülich Research Center)、Kimberly Powell (NVIDIA)、Thomas Schulthess (Swiss National Supercomputing Centre) 和 Dan Stanzione (Texas Advanced Computing Center)，分享關於運算科學的最新資訊。

立即觀看

精選新聞

NVIDIA Grace Hopper 超級晶片支援 JUPITER，定義可推進科學探索人工智慧的全新等級超級電腦

NVIDIA GH200 Grace Hopper™ 超級晶片象徵超級運算邁入新時代，可解決材料科學、氣候研究、藥物研發等領域的巨大挑戰。

閱讀新聞稿

NVIDIA 大幅提升全球頂尖人工智慧運算平台 Hopper

NVIDIA 推出 NVIDIA HGX™ H200，大幅強化領先全球的人工智慧運算平台。全球頂尖伺服器製造商和雲端服務供應商即將推出 HGX H200 系統和雲端執行個體，具備先進記憶體，可處理生成人工智慧和高效能運算 (HPC) 工作負載的大量資料。

閱讀新聞稿

遍布全球研究中心、系統製造商和雲端供應商的 40 多台人工智慧超級電腦，皆採用 NVIDIA Grace Hopper 超級晶片

採用 NVIDIA GH200 的中心可達到 200 exaflops 的人工智慧效能，持續推動科學創新，並讓科學家和研究人員有能力解決世界上部份最具挑戰性的難題。

閱讀部落格文章

研究人員準備運用 NVIDIA CUDA Quantum 取得進展

眾多組織以採用 NVIDIA 程式設計環境和 GPU 的混合式量子運算技術取得洞察，全球最大的化學公司也不例外。瞭解 BASF 的量子運算團隊如何模擬相當於 24 個量子位元的量子電腦處理引擎，以展示量子運算如何協助克服巨大挑戰。

閱讀部落格文章

基因體生成式人工智慧：大型語言模型預測 COVID 變異的特徵

廣受讚譽的基因體資料大型語言模型 (LLM) 可產生非常類似於 SARS-CoV-2 的基因序列，亦即現實中 COVID-19 變異後的病毒。透過新的技術展示，使用者可以探索阿貢國家實驗室、芝加哥大學、NVIDIA 和其他協作單位的基因體規模語言模型視覺化。

閱讀部落格文章

AWS 和 NVIDIA 合作提升雲端高效能運算的能源效率

企業在本機執行高效能運算工作負載時，會面臨電力成本上升、能源分配有限，以及 3D 模擬和人工智慧模型日益複雜的問題。瞭解 AWS 和 NVIDIA 如何透過全方位加速運算，針對雲端高效能運算提升能源效率、降低成本和擴充工作負載。

閱讀解決方案介紹

時程表

參與 SC23 大會，探索加速運算領域的重大突破。歡迎瀏覽今年規劃的 NVIDIA 系列演講。

教學、實作坊及參展商論壇
座談會、論文及英雄會

Sunday 11/12	Monday 11/13	Tuesday 11/14	Wednesday 11/15	Thursday 11/16	Friday 11/17
Portable GPU Acceleration of Applications With Standard C++ 8:30 a.m.–12:00 p.m. MT Tutorial	From Zero to Hero: Conquering the Arm® Neoverse 8:30 a.m.–12:00 p.m. MT Tutorial				Digital Twins: Practices and Principles for High-Performance Computing 8:30 a.m.–12:00 p.m. MT Workshop
Performance Tuning With the Roofline Model on GPUs and CPUs 8:30 a.m.–5:00 p.m. MT Tutorial	Deep Learning at Scale 8:30 a.m.–5:00 p.m. MT Tutorial				First International Workshop on HPC Testing and Evaluation of Systems, Tools, and Software (HPCTESTS 2023) 8:30 a.m.–12:00 p.m. MT Workshop
Using Containers to Accelerate HPC 8:30 a.m.–5:00 p.m. MT Tutorial	2023 International Workshop on Performance, Portability, and Productivity in HPC (P3HPC) 9:00 a.m.–12:30 p.m. MT Workshop
Leveraging SmartNICs for HPC Applications 1:30–5:00 p.m. MT Tutorial	Efficient Distributed GPU Programming for Exascale 8:30 a.m.–5:00 p.m. MT Tutorial			Accelerating Scientific Workflows With the NVIDIA Grace Hopper™ Platform 1:30–2:00 p.m. MT Exhibitor Forum
	WHPC@SC23: 16th International Women in HPC Workshop 9:00 a.m.–5:30 p.m. MT Workshop	A Deep Dive into the Latest NVIDIA HPC Software 4:00–4:30 p.m. MT Exhibitor Forum	Digital Twins for Science 4:00–4:30 p.m. MT Exhibitor Forum
	Fourth International Workshop on Quantum Computing Software 9:00 a.m.–5:30 p.m. MT Workshop	Defining the Quantum Accelerated Supercomputer 4:30–5:00 p.m. MT Exhibitor Forum

Sunday 11/12	Monday 11/13	Tuesday 11/14	Wednesday 11/15	Thursday 11/16	Friday 11/17
					Understanding the Performance, Reproducibility, Validation, Portability, and Sustainability of Coupled HPC Simulation and Deep Learning Calculations 8:30–10:00 a.m. MT Panel
		Legate Sparse: Distributed Sparse Computing in Python 10:30–11:00 a.m. MT Paper		Calculon: a Methodology and tool for High-Level Codesign of Systems and Large Language Models 11:00–11:30 a.m. MT Paper
		27th Graph500 List 12:15–1:15 p.m. MT Birds of a Feather	Unity ECC: Unified Memory Protection Against Bit and Chip Errors 11:30 a.m.–12:00 p.m. MT Paper
		Accelerating Storage IO to GPUs 12:15–1:15 p.m. MT Birds of a Feather	Americas HPC Collaboration: Global Actions 12:15–1:15 p.m. MT Birds of a Feather
		First Steps Toward Adopting Direct-Liquid-Cooled HPC 12:15–1:15 p.m. MT Birds of a Feather	Applications, Libraries, and Tools in Modern Fortran (alt.fortran) 12:15–1:15 p.m. MT Birds of a Feather
		Mixed Feelings About Mixed Precisions 12:15–1:15 p.m. MT Birds of a Feather		Advanced Architecture “Playgrounds”—Past Lessons and Future Access of Testbeds 12:15–1:15 p.m. MT Birds of a Feather
		SmartNICs: Exploring the Future of In-Network Computation With the HPC Community 12:15–1:15 p.m. MT Birds of a Feather		Parallel Top-K Algorithms on GPU: A Comprehensive Study on New Methods 1:30–2:00 p.m. MT Paper
		Workflows Community: Modern Workflows for Continuum and Cross-Facility Computing 12:15–1:15 p.m. MT Birds of a Feather		Scalable and Adaptable Architectures for AI/HPC Advancement 1:30–3:00 p.m. MT Panel
		Arm in HPC: Experiences and Lessons Learned in Operating Arm-Based HPC Systems 5:15–6:45 p.m. MT Birds of a Feather	Scientific Software and the People Who Make It Happen: Building Communities of Practice 5:15–6:45 p.m. MT Birds of a Feather
		OpenACC Users Forum 5:15–6:45 p.m. MT Birds of a Feather	The Future of Benchmarks in Supercomputing 5:15–6:45 p.m. MT Birds of a Feather
		Unified Communication X (UCX) Community 5:15–6:45 p.m. MT Birds of a Feather	Two Worlds Collide: Forging Sustainable Coupled HPC Simulation/Deep Learning Applications From Hardware to Algorithm 5:15–6:45 p.m. MT Birds of a Feather