Ranking of the 500 most powerful supercomputers
POPULARITY
Estás Interfiriendo con mi Zen. You are messing with my Zen.
Volvo, Top500, Hudson Bay Company, Novios por IA, Waymo, Realismo Magico, St. Marys Fish Co, Aerotranstorno, Parker Wells, Abelardo, Amuletos, Simbolos y Espada de Bolivar, e Italia 2026.
Audio-Podcast – OrionX.net: Deep Insight, Market Execution, Customer Engagement
Analyst roundtable covering the big ideas in technology that are changing the world, with Adrian Cockcroft, Stephen Perrenod, Chris Kruell, and Shahin Khan. In this episode: - TOP500 - Bitcoin - AI - Space tech - Fusion energy [audio mp3="https://orionx.net/wp-content/uploads/2026/07/OXD038_ART-14_TOP500-BTC-AI-Space-Fusion_20260623.mp3"][/audio] The post Analyst RoundTable: TOP500, Bitcoin, AI, Space, Fusion – OXD38 appeared first on OrionX.net.
掌握前瞻趨勢與科技脈動,立即訂閱 IC之音電子報:https://pse.is/8wpwwx—日前公布的最新全球超級電腦TOP500榜單中,中國自主研製的超級電腦「靈晟」,超越美國的超級電腦「酋長岩」,為中國奪得世界第一。「靈晟」不使用輝達高階GPU、純靠國產CPU的架構設計,引發了全球科技界的熱烈討論。當美國全面管制先進AI晶片出口到中國,超級電腦「靈晟」的問世,代表中國已經有方法「繞過」美國的限制,建立自己的龐大算力嗎?本集特別邀請工研院產科國際所研究經理石立康,從這次超級電腦排行榜的公布,探討全球雲端運算與AI產業格局,是否將因此面臨洗牌?或者也不見得?台灣在這波浪潮中的定位在哪裡?台灣在雲端運算、AI伺服器供應鏈的優勢,會受到任何影響嗎?節目將從這次的排名,深入剖析超級電腦排行榜對我們的意義,以及台灣產業的相關AI應用方向。歡迎收聽。—製作團隊製作人:李知昂企劃團隊:李知昂 / 莊俐心
Samsung prepara una inversión gigante en Corea del Sur para chips, IA y robótica. DeepSeek presenta DSpark para acelerar la inferencia de V4, Google consolida la Interactions API de Gemini como infraestructura para agentes, China presume de LineShine en el TOP500 sin GPUs y Euclid publica una imagen del centro de la Vía Láctea con más de 60 millones de estrellas.Puedes seguirnos en YouTube en https://youtube.com/olivernabani y puedes unirte al Discord Mashain en https://olivernabani.com/discord
Android sauve des vies au Vénézuela • Apple augmente fortement les prix de ses Mac et iPad • Meta lance des lunettes connectées bon marché • Tesla conteste un accident attribué à son Autopilot • L'Europe avance sur l'euro numérique • Les cyberarnaques profitent de la Coupe du monde • Des innovations pour la transition énergétique récompensées par les Prix EDF Pulse⭐️ Découvrez Frogans, l'innovation française qui réinvente le Web : cliquez ici===============Des smartphones Android qui sauvent des vies lors du séisme au VenezuelaLe double séisme qui a frappé le Venezuela a montré l'efficacité du système Android Earthquake Alerts de Google. Des millions d'utilisateurs Android ont reçu une alerte quelques secondes avant les secousses grâce aux accéléromètres intégrés dans les smartphones, capables de détecter les premières ondes sismiques. Une démonstration spectaculaire du potentiel des technologies mobiles au service de la sécurité civile.Apple augmente brutalement le prix de ses Mac et de ses iPadFace à la crise mondiale des semi-conducteurs, Apple revoit les tarifs de presque toute sa gamme informatique. Les Mac voient leur prix grimper de 100 à 700 euros selon les modèles, tandis que les iPad prennent jusqu'à 150 euros. Seuls les iPhone échappent, pour l'instant, à cette hausse, conséquence directe de la pénurie de mémoire vive alimentée par l'explosion de la demande liée à l'intelligence artificielle.Meta démocratise les lunettes connectéesMeta lance une nouvelle génération de lunettes connectées à environ 300 dollars, moins chère que les modèles développés avec Ray-Ban. Elles intègrent caméra, micros, haut-parleurs, traduction instantanée et assistant IA Meta, tout en conservant une approche plus accessible pour accélérer l'adoption des wearables intelligents.Tesla : l'Autopilot mis en cause… mais l'enquête nuance les accusationsUne famille américaine poursuit Tesla après un accident mortel au Texas impliquant une Model 3. Le conducteur affirme que l'Autopilot était activé, mais les données enregistrées par le constructeur indiqueraient au contraire que le conducteur avait repris la main quelques instants avant l'impact. Une nouvelle affaire qui relance le débat sur les limites des systèmes d'aide à la conduite.Waymo rappelle 4 000 robotaxisLes véhicules autonomes de Waymo ont été surpris à plusieurs reprises sur des autoroutes fermées pour travaux. L'entreprise rappelle près de 4 000 véhicules afin de corriger un défaut d'interprétation des zones de chantier. Malgré ce sixième rappel, Waymo poursuit son expansion aux États-Unis et à l'international.Le supercalculateur chinois Line Shine devient numéro un mondialLa Chine reprend la tête du classement Top500 avec Line Shine, installé à Shenzhen. Cette machine de plus de 2 000 exaflops, entièrement basée sur des processeurs chinois, dépasse désormais le supercalculateur américain El Capitan et confirme les ambitions technologiques de Pékin dans le calcul haute performance.Euro numérique : l'Europe accélèreDans le Débrief transatlantique, Bruno Guglielminetti (Mon Carnet) revient sur l'avancée du projet d'euro numérique. La future monnaie numérique de la Banque centrale européenne vise à renforcer la souveraineté européenne face aux géants américains du paiement tout en promettant un haut niveau de protection de la vie privée. Le Canada réfléchit également à un dispositif comparable, même si le sujet suscite d'importantes interrogations.Les lunettes IA de Meta : au service de l'accessibilitéINTERVIEW - Matthew Sanders, directeur de l'accessibilité et de l'impact pour les wearables IA chez Meta, explique pourquoi les lunettes intelligentes sont appelées à compléter le smartphone plutôt qu'à le remplacer. Il détaille les progrès réalisés en matière d'accessibilité grâce à l'IA, notamment pour les personnes malvoyantes, ainsi que les défis techniques liés à l'autonomie, la miniaturisation et la protection de la vie privée.Cybercriminalité : les escrocs profitent de la Coupe du mondeINTERVIEW [PARTENARIAT] - Benoît Grunemwald, expert cybersécurité chez ESET, alerte sur la multiplication des arnaques liées à la Coupe du monde de football : faux sites de billetterie, faux produits dérivés, IPTV frauduleuses et campagnes de phishing. Il explique également comment les cybercriminels développent désormais des outils capables de neutraliser les logiciels de sécurité, rendant indispensable une surveillance permanente des systèmes.EDF Pulse 2026 : six innovations pour accélérer la transition énergétiqueINTERVIEW [PARTENARIAT] - Julien Villeret, directeur de l'innovation d'EDF, présente les lauréats des Prix EDF Pulse 2026. Au programme : des vêtements rafraîchissants pour les travailleurs exposés aux fortes chaleurs, des solutions de stockage thermique pour l'industrie, le reconditionnement de batteries, l'inspection industrielle assistée par IA, un dirigeable électrique pour surveiller les infrastructures et un drone élagueur destiné à sécuriser les réseaux électriques. Autant d'innovations appelées à accompagner la transition énergétique.Hébergé par Audiomeans. Visitez audiomeans.fr/politique-de-confidentialite pour plus d'informations.
Dopo i Ray-Ban e gli Oackley arrivano i Meta Glasses, i nuovi occhiali smart prodotti da EssilorLuxottica in un mercato ancora contenuto ma che cresce a ritmi elevati, soprattutto fuori dalla UE. Gli smart glasses saranno il nuovo smartphone? Ne parliamo con Paolo Centofanti, esperto di tecnologia della redazione di Dday.it.Con Lorenzo Fiorillo, direttore Tecnologia di Eni, commentiamo la classifica mondiale TOP500 che valuta i calcolatori più potenti al mondo e che assegna al super computer HPC7 di Eni il 6 posto al mondo, il secondo in Europa e il primo a livello globale per potenza di calcolo ad uso industriale.È stato inaugurato in Val di Non “Intacture” il primo data center al mondo realizzato all’interno di una miniera attiva. Per capire cos’è, come funziona e quali sono le caratteristiche uniche di Intacture, Enrico Pagliarini ha visitato l’infrastruttura e intervistato Dennis Bonn, AD di Trentino DataMine; Roberto Covi, AD di Tassullo e Marco Podini, AD e presidente di Dedagroup.E come sempre in Digital News le notizie di innovazione e tecnologia più importanti della settimana.
China's LineShine computer in Shenzhen displaced top-ranked US computer El Capitan on the TOP500 ranking, marking the first time since 2017 that a Chinese computer has topped a list sometimes viewed as a measure of a nation's technological prowess.
The new TOP500 list of the most powerful supercomputers was released today at the ISC conference, with a surprising new system in the top spot. After nearly a decade of staying on the sidelines, China re-entered the race with the first system to exceed 2 exaflops in 64-bits on the HPL benchmark. As usual, Shahin and Doug go through the list and the stats with their commentary and analysis, looking at key takeaways, how continents, companies, and architectures fare, and they cover HPL, Green500, HPL-MxP, and HPCG. [audio mp3="https://orionx.net/wp-content/uploads/2026/06/109@HPCpodcast_ID_TOP500_ISC26_20260623.mp3"][/audio] The post @HPCpodcast-109: TOP500 at ISC26, China Re-Enters Race in Top Spot – In Depth appeared first on OrionX.net.
- Electron-on-helium qubits - Is the new Huawei Kirin chip equivalent of a TSMC 3nm chip? - Intel launches 18A-P node, with Power Boost dual-contact transistor - Intersect360 announces market size and forecast - TOP500 analysis coming later this week [audio mp3="https://orionx.net/wp-content/uploads/2026/06/HPCNB_20260622.mp3"][/audio] The post HPC News Bytes – 20260622 appeared first on OrionX.net.
Join Shahin and Doug as they analyze and discuss the new TOP500 list. They go over HPL, HPL-MxP, HPCG, Green500, geographical distribution, vendor distribution, and other observations. [audio mp3="https://orionx.net/wp-content/uploads/2025/11/106@HPCpodcast_SP_TOP500_SC25_20251119.mp3"][/audio] The post @HPCpodcast-106: TOP500 at SC25 Conference appeared first on OrionX.net.
Audio-Podcast – OrionX.net: Deep Insight, Market Execution, Customer Engagement
Analyst roundtable covering the big ideas in technology that are changing the world, with Adrian Cockcroft, Stephen Perrenod, Chris Kruell, and Shahin Khan. In this episode: AI Agent Swarm Coding, IoT, Bitcoin, HPC, TOP500, PCIe, UCE, 5G, Cloud, Cybersecurity, Post-Quantum Cryptography, Quantum Computing, Nuclear Energy [audio mp3="https://orionx.net/wp-content/uploads/2025/07/OXD030_ART-6_20250708.mp3"][/audio] The post Analyst Roundtable: AI Agent Swarm Coding, PCIe, UEC, BTC – OXD30 appeared first on OrionX.net.
On This Week in HPC, Addison Snell and Doug Eadline recap their visit to Hamburg for ISC25 and look forward to the future of technology in HPC and AI.
Was sagt die Top500-Liste der Supercomputer noch aus, seit es vielfach stärkere KI-Cluster gibt? Folge 2025/13 des Podcasts Bit-Rauschen.
The new TOP500 list of the most powerful supercomputers was released today at the ISC conference, with a new addition to the top 10. Tune in as Shahin and Doug go through the list with their commentary and analysis as they go over the details, key takeawats, how continents, companies, and architectures fair, and cover the full suite of benchmarks: HPL, Green500, HPCG, HPL-MxP (AI), IO500, and MLPerf. [audio mp3="https://orionx.net/wp-content/uploads/2025/06/102@HPCpodcast_SP_TOP500_ISC25_20250610.mp3"][/audio] The post @HPCpodcast-102: TOP500 at ISC25 Conference appeared first on OrionX.net.
スーパーコンピュータ「富岳」、世界7位に 10期連続1位だった「HPCG」では2位。 富士通は6月10日、理化学研究所と共同開発したスーパーコンピュータ「富岳」が、世界のスーパーコンピュータの性能ランキング「TOP500」で7位になったと発表した。大規模グラフ解析に関する「Graph500」では11期連続の1位を維持。一方、シミュレーション計算を想定した「HPCG」は、前回まで10期連続1位だったが、今回は2位だった。
Pour rejoindre le programme "Epargner et Investir en Afrique (même sans y vivre)", avec une réduction exclusive de 250€ (uniquement jusqu'au 6 avril), avec le code *"TOP500"* (sans guillemets) c'est par ici : https://bit.ly/ESOA-Invest ---------Pour ceux qui souhaitent rejoindre la #TribuESOA c'est par ici : https://bit.ly/ESOATribeVoici ce que vous obtenez en rejoignant la tribu ESOA :✅ Echangez quotidiennement avec Kahi, Moulaye pour co-construire le podcast mais aussi sur vos difficultés, interrogations et l'actualité en toute simplicité !✅ Accès d'un an à la communauté privée ESOA (La tribe): un réseau exclusif de 200 membres dans 15 pays entrepreneurs et professionnels africains partout dans le monde pour développer votre réseau, échanger, et vous entraider.✅ Accès à tous nos Masterminds, Book Clubs, Meetups, et événements ESOA exclusifs et à tarifs réduits: participez à des sessions interactives avec Kahi, Moulaye, et des experts invités pour enrichir vos connaissances et votre réseau.✅ Le Template du Life Plan de Moulaye et Kahi: des outils concrets pour clarifier vos objectifs professionnels et personnels, adaptés à tous les profils.✅ Le Replay unique du Mastermind du 18 Décembre “Construire son plan de vie”Un contenu exclusif pour vous guider dans la création de votre plan de vie et de carrière.---------Le Podcast "#Entrepreneur State Of Africa" dit tout haut ce que les #entrepreneurs pensent tout bas, avec Kahi Lumumba (Co-Founder & CEO Totem Experience, Adicomdays) et Moulaye Tabouré (Co-Founder & CEO de ANKA (ex-Afrikrea) ). Dans cet épisode, Kahi et Moulaye analysent le TOP 500 des entreprises ivoiriennes sur tous les angles: Chiffre d'Affaires, Profits et les autres benchmarks à connaitre pour comparer son entreprise aux meilleurs. Que vous cherchiez des clients ou un futur emploi, ce sont les entreprises méconnues mais mastodontes régionaux que vous devriez connaitre !-----Ce podcast est produit par Totem Factory by Totem Experience que vous pouvez joindre pour tous vos besoins de production
Jack Dongarra is an American computer scientist who is celebrated for his pioneering contributions to numerical algorithms and high-performance computing. He developed essential software libraries like LINPACK and LAPACK, which are widely used for solving linear algebra problems on advanced computing systems. Dongarra is also a co-creator of the TOP500 list, which ranks the world's The post Turing Award Special: A Conversation with Jack Dongarra appeared first on Software Engineering Daily.
Jack Dongarra is an American computer scientist who is celebrated for his pioneering contributions to numerical algorithms and high-performance computing. He developed essential software libraries like LINPACK and LAPACK, which are widely used for solving linear algebra problems on advanced computing systems. Dongarra is also a co-creator of the TOP500 list, which ranks the world's The post Turing Award Special: A Conversation with Jack Dongarra appeared first on Software Engineering Daily.
Review of SC24, RISC-V Summit, and AWS Reinvent. Topics include: HPC and AI Clouds, CXL, Liquid Cooling, Optical Interconnects, Optical Computing, Novel CPUs and GPUs, the state of RISC-V in servers and supercomputers, TOP500, Chiplets, AWS CPU and GPU strategies. [audio mp3="https://orionx.net/wp-content/uploads/2025/01/095@HPCpodcast_SP_Adrian-Cockcroft_SC24-RISCV_AWS-Reinvent-Q2B-Events_20250108.mp3"][/audio] The post @HPCpodcast-95: Adrian Cockcroft on SC24, RISC-V Summit, AWS Reinvent appeared first on OrionX.net.
Partiamo dallo Spazio e dal sesto test di volo per Starship che, come spiega Luigi Bignami, giornalista scientifico ed esperto del settore, è un tassello fondamentale per la riconquista della Luna da parte degli USA.Ci occupiamo di supercalcolatori in occasione dell’aggiornamento della classifica Top500. Mentre gli Stati Uniti mantengono la leadership con i primi 4 sistemi a livello globale, al quinto posto si posiziona HPC6 di ENI, il supercomputer industriale più potente al mondo. Enrico Pagliarini ne parla con Lorenzo Fiorillo, Director Technology, R&D & Digital di ENI.Torna “in onda” Gianfranco Giardina, direttore del magazine digitale Dday.it per parlare dell’importanza delle soundbar, di una innovazione presentata da Sonos e per commentare la notizia dell’acquisizione di McIntosh Group, azienda importante del settore hi-fi, e di Sonus Faber da parte di Bose.E come sempre, le notizie di innovazione e tecnologia più importanti della settimana nelle nostre Digital News.
SC24 is off to a great start with over 17,000 attendees, 480 exhibitors from 29 countries, and new TOP500 list that features a new champion! "The new El Capitan system at the Lawrence Livermore National Laboratory in California, U.S.A., has debuted as the most powerful system on the list with an HPL score of 1.742 EFlop/s." Join Shahin and Doug as they analyze and discuss the new list. As usual, they go over notable additions, performance efficiency, power efficiency in the Green500 list, the difficult HPCG benchmark that usually sets the lower bound of system performance. [audio mp3="https://orionx.net/wp-content/uploads/2024/11/093@HPCpodcast_TOP500-SC24_20241118.mp3"][/audio] The post @HPCpodcast-93: TOP500 at SC24 Conference appeared first on OrionX.net.
- Nvidia to build GPUs specially for the Chinese market to comply with export control - Morgan Stanley report projects 60,000 to 70,000 Nvidia AI racks in 2025 - China and TOP500, no new news - NTT and U. Tokyo use Graphene Plasmon in pursuit of faster opto-electronics [audio mp3="https://orionx.net/wp-content/uploads/2024/07/HPCNB_20240729.mp3"][/audio] The post HPC News Bytes – 20240729 appeared first on OrionX.net.
In this episode we are looking at computers going fast. ‘Exascale' means a computer is running a billion, billion operations every second. At the 2024 ISC high-performance conference in Hamburg, Germany, the world's second exascale machine was officially recognised: The Aurora supercomputer at Argonne National Laboratory officially broke the exascale barrier at 1.012 exaflops. So why does exascale matter, and why is it so difficult to achieve? Joining us to discuss is Susan Coghlan, Project Director of the Aurora exascale computer at the Argonne Leadership Computing Facility at Argonne National Laboratory in Lemont, Illinois.This is Technology Now, a weekly show from Hewlett Packard Enterprise. Every week we look at a story that's been making headlines, take a look at the technology behind it, and explain why it matters to organizations and what we can learn from it. Do you have a question for the expert? Ask it here using this Google form: https://forms.gle/8vzFNnPa94awARHMA About the expert: https://www.anl.gov/profile/susan-m-coghlan Sources and statistics cited in this episode:Top500 list of the fastest supercomputers: https://top500.org/Argonne National Laboratory: https://www.anl.gov/Quantum navigation flight: https://www.gov.uk/government/news/un-jammable-quantum-tech-takes-flight-to-boost-uks-resilience-against-hostile-actors
Tech behind the Trends on The Element Podcast | Hewlett Packard Enterprise
In this episode we are looking at computers going fast. ‘Exascale' means a computer is running a billion, billion operations every second. At the 2024 ISC high-performance conference in Hamburg, Germany, the world's second exascale machine was officially recognised: The Aurora supercomputer at Argonne National Laboratory officially broke the exascale barrier at 1.012 exaflops. So why does exascale matter, and why is it so difficult to achieve? Joining us to discuss is Susan Coghlan, Project Director of the Aurora exascale computer at the Argonne Leadership Computing Facility at Argonne National Laboratory in Lemont, Illinois.This is Technology Now, a weekly show from Hewlett Packard Enterprise. Every week we look at a story that's been making headlines, take a look at the technology behind it, and explain why it matters to organizations and what we can learn from it. Do you have a question for the expert? Ask it here using this Google form: https://forms.gle/8vzFNnPa94awARHMA About the expert: https://www.anl.gov/profile/susan-m-coghlan Sources and statistics cited in this episode:Top500 list of the fastest supercomputers: https://top500.org/Argonne National Laboratory: https://www.anl.gov/Quantum navigation flight: https://www.gov.uk/government/news/un-jammable-quantum-tech-takes-flight-to-boost-uks-resilience-against-hostile-actors
In this episode we are looking at computers going fast. ‘Exascale' means a computer is running a billion, billion operations every second. At the 2024 ISC high-performance conference in Hamburg, Germany, the world's second exascale machine was officially recognised: The Aurora supercomputer at Argonne National Laboratory officially broke the exascale barrier at 1.012 exaflops. So why does exascale matter, and why is it so difficult to achieve? Joining us to discuss is Susan Coghlan, Project Director of the Aurora exascale computer at the Argonne Leadership Computing Facility at Argonne National Laboratory in Lemont, Illinois.This is Technology Now, a weekly show from Hewlett Packard Enterprise. Every week we look at a story that's been making headlines, take a look at the technology behind it, and explain why it matters to organizations and what we can learn from it. Do you have a question for the expert? Ask it here using this Google form: https://forms.gle/8vzFNnPa94awARHMA About the expert: https://www.anl.gov/profile/susan-m-coghlan Sources and statistics cited in this episode:Top500 list of the fastest supercomputers: https://top500.org/Argonne National Laboratory: https://www.anl.gov/Quantum navigation flight: https://www.gov.uk/government/news/un-jammable-quantum-tech-takes-flight-to-boost-uks-resilience-against-hostile-actors
The June 2024 Top500 supercomputer list was released at ISC 2024, and there is a lot to unpack. The latest Top 500 Supercomputers list highlights significant trends in the supercomputing landscape, as NVIDIA takes 7 spots with Grace-based systems, including 3 of the top 20. Although the balance between Intel and AMD remains static, there is a shift towards co-packaged CPUs and accelerators just as Intel announces they will sunset Ponte Vecchio, their entry in this space, and skip the next generation. Interestingly, HPE was a big winner here, leading in new systems and enabling 8 of the 10 Grace and MI300A entrants. And we see Arm well-represented here, with 8 new servers on the list. Time Stamps: 0:00 - Welcome to the Rundown 3:03 - Zscaler Reportedly Breached by Profit-Minded Criminals 5:06 - Adam Selipsky Steps Down from AWS 7:45 - F5 BIG-IP Suffers a Big Breach 9:53 - VMware Makes Workstation Pro and Fusion Free for Personal Use 12:41 - GPT-4o Launched by OpenAI 15:05 - NetApp Announces New All-Flash Storage and StorageGRID for the AI Era 18:18 - Top500 Supercomputing 31:55 - The Weeks Ahead 33:40 - Thanks for Watching Hosts: Stephen Foskett: https://www.linkedin.com/in/sfoskett/ Mitch Ashley, Techstrong Group: https://www.linkedin.com/in/mitchellashley/ Follow Gestalt IT Website: https://www.GestaltIT.com/ Twitter: https://www.twitter.com/GestaltIT LinkedIn: https://www.linkedin.com/company/Gestalt-IT Tags: #Rundown, #Top500Supercomputing, #AWS, @Zscaler, @AWSCloud, @VMware, @OpenAI, @NetApp, #StorageGRID, #SC2024, @Intel, @IntelBusiness, @TechstrongTV, @GestaltIT, @TechFieldDay, @SFoskett, @TheFuturumGroup,
The new TOP500 at ISC24 conference is here with a new addition to the Exaflop Club, a new HPL-MxP (AI) champion, new top three in Green500, and also a look at HPCG, the difficult benchmark that usually sets the lower bound of system performance. Tune in as Shahin and Doug go through the list with their commentary and analysis. [audio mp3="https://orionx.net/wp-content/uploads/2024/05/084@HPCpodcast_TOP500-ISC24_20240513.mp3"][/audio] The post @HPCpodcast-84: TOP500 at ISC24 Conference appeared first on OrionX.net.
Addison Snell and Kevin Jackson analyze the latest TOP500 list, plus Intersect360 Research's launch of the new HPC-AI Leadership Organization (HALO).
Dr. Luke Wilson (Chief Data Scientist and Senior Partner at Vizias. Vice President of the Board of Directors at Austin AI Alliance) has been a leading figure in high-performance computing and artificial intelligence for over two decades, with a distinguished career spanning academia, finance, and tech. Starting at the Texas Advanced Computing Center, he significantly contributed to the design and deployment of numerous Top500 systems, later enhancing TACC's educational offerings as Director of Training. At Dell Technologies, he pioneered groundbreaking work in HPC/AI infrastructure, earning him the title of Chief Data Scientist. Recently, at Optiver, he has been at the forefront of developing cutting-edge research infrastructure for high-frequency trading. With a PhD from the University of Texas at San Antonio, Luke has been instrumental in projects that have shaped the future of AI, including work that contributed to the Nobel Prize-winning LIGO project and optimizations for early transformer neural networks. An author of numerous research papers, Luke's work continues to influence the evolving landscape of technology and AI
Adrian Cockcroft joins us again after SC23 to discuss TOP500 trends, the AI-HPC crossover, chiplets, and the emergence of UCIe and CXL advancements. Be sure to listen to previous episodes with Adrian; Episode 36 on HPC in cloud and sustainability data and Episode 55 on decarbonization and ESG. [audio mp3="https://orionx.net/wp-content/uploads/2023/11/077@HPCpodcast_Adrian-Cockcrofy_Future-Architectures_20231130.mp3"][/audio] The post @HPCpodcast-77: Adrian Cockcroft on Future Architectures appeared first on OrionX.net.
We provide details and our analysis of the latest TOP500 list of the most powerful supercomputers in the world. This round sees quite a shake-up in the top 10 and reveals interesting changes in the market. [audio mp3="https://orionx.net/wp-content/uploads/2023/11/076@HPCpodcast_TOP500-SC23_20231113.mp3"][/audio] The post @HPCpodcast-76: TOP500 at SC23 appeared first on OrionX.net.
- SC23 Starts, TOP500 later today - Storage at Scale, DAOS, Aurora, Linux Foundation - Sandia National Lab and DDN - TSMC 1.4nm, SMIC financials [audio mp3="https://orionx.net/wp-content/uploads/2023/11/HPCNB_20231113.mp3"][/audio] The post HPC News Bytes – 20231113 appeared first on OrionX.net.
As SC23 approaches, we were fortunate to catch up with Rick Stevens and Mike Papka of Argonne National Lab for a wide ranging discussion. In addition to an update on the Aurora supercomputer and TOP500, we also discuss the need and challenged of building a national exascale capability, developing teams and bench strength, the risks and opportunities of AI for science and society, the trend towards integrated research infrastructure (IRI), and what's next for the exascale initiative. [audio mp3="https://orionx.net/wp-content/uploads/2023/11/075@HPCpodcast_Rick-Stevens_Mike-Papka_ANL_20231110.mp3"][/audio] The post @HPCpodcast-75: Rick Stevens, Mike Papka – Argonne National Lab (ANL) appeared first on OrionX.net.
- HPE Cray at Crusoe Flared Gas Data Centers - IBM NorthPole AI Chip - TSMC financials: AI, 3nm, Inventory - AI Frenzy, AGI, Brain Waves as Input - Exascale, Aurora, TOP500 [audio mp3="https://orionx.net/wp-content/uploads/2023/10/HPCNB_20231023.mp3"][/audio] The post HPC News Bytes – 20231023 appeared first on OrionX.net.
- Linux Wars continue as Oracle, SUSE, and CIQ form Open Enterprise Linux Association - China's tech companies place $5 billion of orders on US chips - Intel improves on-chip vector instructions - 2023 Gordon Bell Prize Finalists also point to TOP500 [audio mp3="https://orionx.net/wp-content/uploads/2023/08/HPCNB_20230814.mp3"][/audio] The post HPC News Bytes – 20230814 appeared first on OrionX.net.
Welcome to The Nonlinear Library, where we use Text-to-Speech software to convert the best writing from the Rationalist and EA communities into audio. This is: Takeaways from the Metaculus AI Progress Tournament, published by Javier Prieto on July 27, 2023 on The Effective Altruism Forum. In 2019, Open Philanthropy commissioned a set of forecasts on AI progress from Metaculus. The forecasting questions had time horizons between 6 months and >6 years. As of June 2023, 69 of the 111 questions had been resolved unambiguously. In this post, I analyze the accuracy of these forecasts as a function of question (sub)category, crowd size, and forecasting horizon. Unless otherwise indicated, my analyses are about Metaculus' proprietary aggregate forecast ("the Metaculus prediction") evaluated at the time the question closed. Related work Feel free to skip to the next section if you're already familiar with these analyses. This analysis published 2 years ago (July 2021) looked at 64 resolved AI questions and concluded there was weak but ultimately inconclusive evidence of bias towards faster progress. A more recent analysis from March 2023 found that Metaculus had a worse Brier score on (some) AI questions than on average across all questions and presented a few behavioral correlates of accuracy within AI questions, e.g. accuracy was poorer on questions with more updates and when those updates were less informative in a certain technical sense (see post for details). Metaculus responded to the previous post with a more comprehensive analysis that included all resolved AI questions (152 in total, 64 of which were binary and 88 continuous). They show that performance is significantly better than chance for both question types and marginally better than was claimed in the previous analysis (which relied on a smaller sample of questions), though still worse than the average for all questions on the site. The analysis I present below has some overlaps with those three but it fills an important gap by studying whether there's systematic over- or under-optimism in Metaculus's AI progress predictions using data from a fairly recent tournament that had monetary incentives and thus (presumably) should've resulted in more careful forecasts. Key takeaways NB: These results haven't been thoroughly vetted by anyone else. The conclusions I draw represent my views, not Open Phil's. Progress on benchmarks was underestimated, while progress on other proxies (compute, bibliometric indicators, and, to a lesser extent, economic indicators) was overestimated. [more] This is consistent with a picture where AI progresses surprisingly rapidly on well-defined benchmarks but the attention it receives and its "real world" impact fail to keep up with performance on said benchmarks. However, I see a few problems with this picture: It's unclear to me how some of the non-benchmark proxies are relevant to AI progress, e.g. The TOP500 compute benchmark is mostly about supercomputers that (AFAICT) are mostly used to run numerical simulations, not to accelerate AI training and inference. In fact, some of the top performers don't even have GPUs. The number of new preprints in certain ML subfields over short (~6-month) time horizons may be more dependent on conference publication cycles than underlying growth. Most of these forecasts came due before or very soon after the release of ChatGPT and GPT-4 / Bing, a time that felt qualitatively different from where we are today. Metaculus narrowly beats chance and performs worse in this tournament than on average across all continuous questions on the site despite the prize money. This could indicate that these questions are inherently harder, or that they drove less or lower-quality engagement. [more] There's no strong evidence that performance was significantly worse on questions with longer horizons (
Doug is in Hamburg, Germany for the ISC23 conference where the 61st edition of the TOP500 list has just been published. 30+ years of systematic data on the highest performing computer architecture and configurations is a treasure trove and we look at the top line insights from this installment, including the GREEN500, HPCG, and the AI-inspired mixed precision benchmark HPL-MxP. This episode is sponsored by Lenovo. [audio mp3="https://orionx.net/wp-content/uploads/2023/05/060@HPCpodcast_TOP500-ISC23_20230522.mp3"][/audio] The post @HPCpodcast-60: TOP500 at ISC23 Conference appeared first on OrionX.net.
Satoshi Matsuoka (https://en.wikipedia.org/wiki/Satoshi_Matsuoka) from April 2018 has been the director of Riken Center for Computational Science (R-CCS), the Tier-1 national HPC center for Japan, developing and hosting Japan's flagship ‘Fugaku' supercomputer which has become the fastest supercomputer in the world in all four major supercomputer rankings in 2020 and 2021 (Top500, HPCG, HPL-AI, Graph500), along with multitudes of ongoing cutting edge HPC research being conducted, including investigating Post-Moore era computing, especially the future FugakuNEXT supercomputer. He was the leader of the TSUBAME series of supercomputers that had also received many international acclaims, at the Tokyo Institute of Technology, where he still holds a professor position, to continue his research activities in HPC as well as scalable Big Data and AI. His longtime contribution was commended with the Medal of Honor with Purple ribbon by his Majesty Emperor Naruhito of Japan in 2022. Other accolades include the Fellow positions in societies/conferences ACM, ISC, and the JSSST; the ACM Gordon Bell Prizes in 2011 & 2021; the IEEE-CS Sidney Fernbach Award in 2014 as well as the IEEE-CS Computer Society Seymour Cray Computer Engineering Award in 2022, both being the highest awards in the field of HPC, and the only individual to receive both awards; the Technical Papers Chair and the Program Chair for ACM/IEEE Supercomputing 2009 and 2013 (SC09 and SC13) respectively as well as many other conference chairs, and the ACM Gordon Bell Prize selection committee chair in 2018. In this interview, Professor Satoshi Matsuoka shared some of the highlights from his talk at SuperComputingAsia 2023 (Singapore), including the supercomputing developments in Japan, and Fugaku, the largest in Japan and one of the first 'exascale' supercomputers of the world. With applications ranging from manufacturing, disaster prevention to creating new drugs, he noted that supercomputers allow us to investigate the past, and to predict the future. To give the audience context, Professor compares Fugaku supercomputer to everyday applications such as gaming (create “virtual worlds, but much more in a scientific way”), and smart phones (20 million times more powerful than a smartphone). In terms of power consumption, it is equivalent to running the Tokyo Disney Resort, and as such, power efficiency is critical in the overall management and operations of Fugaku – especially with carbon neutrality as a key agenda topic today. Professor Satoshi Matsuoka also touched on cybersecurity and how privacy and anonymisiation are growing areas of focus with the increasing adoption of digital twins in medical sciences. Wrapping up, he pointed out some short term goals for supercomputing in Japan to realise further synergies with the “IT” industry, and the efforts for the successor of Fugaku, FugakuNEXT, to be deployed around 2029. Recorded 28th February 2023, 12noon, SuperComputingAsia 2023, Singapore Expo.
Addison Snell, Tiffany Trader, and Oliver Peckham talk over the top stories of SC22.
Il lancio della prima missione del programma Artemis scrive una pagina importante della storia dello spazio e della ri-conquista della Luna. La capsula Orion, priva di equipaggio umano, testerà le manovre che serviranno per riportare l'uomo sulla Luna. Enrico Pagliarini ne parla con Luigi Bignami, giornalista esperto di scienza e spazio. Ha appena conquistato il quarto posto nella TOP500, la classifica dei supercalcolatori più potenti al mondo. Parliamo di Leonardo, il nuovo supercomputer installato a Bologna con il Prof. Francesco Ubertini, presidente del Cineca (il Consorzio interuniversitario per il supercalcolo che gestisce Leonardo). Con Roberto Pezzali, esperto di tecnologia della redazione di Dday.it parliamo di evoluzione dei processori per smartphone e scopriamo quali sono le novità di Qualcomm, appena presentate. Industrial IoT, tecnologie che rendono digitali i processi chiave della produzione industriale. Un ambito molto dinamico che sta innovando il settore manifatturiero e che attira l'interesse degli investitori. Ci racconta di più Gabriele Montelisciani, Ceo di Zerynth; spin off dell'Università di Pisa, che ha recentemente raccolto investimenti per oltre 5 milioni di euro. E come sempre le nostre Digital News, una selezione delle notizie più importanti di innovazione e tecnologia.
The 60th edition of the TOP500 list is here, reresenting 30 years of systematic data on the highest performing computer architecture and configurations. We look at the highlights of what changed and what can be expected to change in systems, technologies, and geographies. [audio mp3="https://orionx.net/wp-content/uploads/2022/11/043@HPCpodcast_TOP500-Nov22_60th-Edition_20221114.mp3"][/audio] The post @HPCpodcast-43: TOP500 at SC22 appeared first on OrionX.net.
Avez-vous déjà entendu parler du classement des supercalculateurs les plus puissant ? On vous l'a déjà présenté à plusieurs reprises dans ce podcast pour mettre en avant les machines les plus puissantes du monde. Mais à quoi correspond-il réellement ? Toutes les réponses à cette question, l'historique de ce classement et le décryptage des enjeux dans cet épisode.Concrètement, ce classement correspond surtout à une mesure de performance basée sur un benchmark appelé HPLinpack. Sur le site du fameux Top 500, il est précisé que ce benchmark ne saurait refléter les véritables capacités et performances des machines, mais plutôt je cite « les performances d'un système pour résoudre de nombreux équations linéaires » fin de citation. À noter que les calculs qu'ont besoin d'effectuer ces ordinateurs surpuissants sont bien différents d'un domaine à l'autre, qu'il s'agisse de simulation météo ou nucléaire, d'entraîner une IA, ou de casser des clés de sécurités par exemple.L'un des principaux critères de ce classement n'est autre que l'arrivée de nouveaux composants comme les puces ou les cartes graphiques, ce qui permet aux entreprises justement de montrer leur puissance. Comme nous vous en avions parlé il y a quelque temps dans ce podcast, AMD a récemment propulsé le premier supercalculateur exaflopique de l'Histoire tout en haut du classement. Difficile donc de savoir si le supercalculateur serait arrivé à la première place sans les nouvelles puce du constructeur. Éternel challenger d'Intel sur tous les composants électroniques, AMD vient donc marcher sur les plates-bandes, alors qu'Intel a dominé le Top500 durant des années. Impossible de passer également à côté des enjeux géopolitiques. Car ce classement met aussi en avant des entreprises, des universités et des gouvernements. Investir et communiquer sur ce sujet revient alors à mettre en avant la puissance, l'attractivité, le niveau de qualification des équipes et le niveau d'équipement de ces différentes entités et donc de montrer les muscles face à la concurrence. Si les Etats-Unis dominent historiquement ce classement, l'Europe avec Adastra (10e du classement) et Lumi (3e) tente de renverse ce rapport de force quand la Chine elle, n'est pas vraiment présente dans les première places, malgré le fait qu'elle possède le plus grand nombre de machine au Top500.Ceci dit, il est également tentant de penser que certaines puissances gouvernementales ne cherchent pas la première place et préfère rester dans l'ombre. Si le premier supercalculateur exaflopique officiel a été mis en avant récemment, on peut également se dire que la Chine et les Etats-Unis ont depuis bien longtemps dépassé cette puissance de manière officieuse, avec des budgets inimaginables, mais surtout sans le dire à personne. Ainsi, le TOP500 des supercalculateurs permet de mesurer la popularité de certaines architectures avec certains composants, les ambitions et les moyens des différents acteurs, mais ne permet pas de savoir qui dispose réellement du plus puissant ordinateur au monde, ou tout du moins de montrer uniquement ce que l'on veut bien rendre public. Hébergé par Acast. Visitez acast.com/privacy pour plus d'informations.
Samsung Display chiude la produzione di schermi LCD, che ha prezzi in caduta libera ed è ormai una tecnologia super matura a bassa marginalità, e si concentra solo sugli Oled con la nuova tecnologia Quantum Dots. Enrico Pagliarini ne parla con Paolo Centofanti, ingegnere esperto di audio e video della redazione di Dday.it che ha da poco provato e testato gli schermi con la nuova tecnologia appena arrivati sul mercato. E' possibile geolocalizzare trasmissioni radio attraverso piccoli satelliti per ascoltare le comunicazioni di attività illecite in aree geografiche determinate. Federico Gardosi, ingegnere di Kleos, start up lussemburghese che opera nel settore spazio, spiega come funziona questa tecnologia e quali sono gli ambiti di applicazione. Parliamo anche del primo super calcolatore exascale della storia, che secondo la nuova classifica Top500.org è il sistema Frontier di HPE installato presso lo Oak Ridge National Laboratory in Tennessee (USA). Ne parliamo con Mauro Colombo, Technology & Innovation Director HPE Italia e con Paolo Cappuccio, Marketing Director & Partner Manager di Doit Systems, specializzata in soluzioni di calcolo ad alte prestazioni (HPC) anche per aziende. E come sempre le nostre Digital News, una selezione delle notizie più importanti di innovazione e tecnologia.
Addison Snell, Tiffany Trader, and Oliver Peckham cover the top stories coming out of ISC22 this week, including Frontier's exascale success and interesting new technologies topping the Green500 list.
Each year computer scientists at KAUST engage with peers at the annual SC conference, the largest supercomputing event of its kind in the world. Long-time friend to KAUST Jack Dongarra is a familiar face there. The veteran computer scientist and Top500 list producer was recently awarded the 2022 Turing Award, considered to be “the Noble Prize of Computing,” for contributions that have significantly shaped the field. Jack has also influenced HPC developments at KAUST. In this profile, recorded at SC21 in St. Louis, he talks about connections made here and throughout his career in conversation with KAUST computer scientists Hatem Ltaief and Bilel Hadri, his former postdoctoral students, and David Keyes, KAUST founding faculty member and Director of the Extreme Computing Research Center. Jack retires this summer after 32-years of service as a professor at the University of Tennessee. See acast.com/privacy for privacy and opt-out information.
Winner of the Purple Ribbon Medal, one of Japan's highest honors, Prof. Satoshi Matsuoka oversaw the development and launch of the Fugaku supercomputer, currently number 1 on the TOP500 list. He joins us in a super fun conversation covering a wide range of topics. [audio mp3="http://orionx.net/wp-content/uploads/2022/05/025@HPCpodcas_Purple-Ribbon-Award_Fugaku_Satoshi-Matsukoa_20220525.mp3"][/audio] The post @HPCpodcast-25: Satoshi Matsuoka, TOP500, Fugaku Supercomputer, Nintendo appeared first on OrionX.net.
We cover the Turing Award, TOP500, the state of HPC benchmarks, China's Exascale systems, and future directions in algorithms. We also talk about future of supercomputing and AI systems, and discuss proliferation of new architectures. This is another episode you'd want to listen to more than once! [audio mp3="http://orionx.net/wp-content/uploads/2022/05/023@HPCpodcas_ACM-Tunring-Award-Jack-Dongarra_20220503.mp3"][/audio] The post @HPCpodcast-23: ACM Turing Award Winner Jack Dongarra appeared first on OrionX.net.
TOP500 at SC21 was highly anticipated but failed to ignite. Rumored high-end systems opted not to play while entering the conversation anyway. However, the list is about more than the TOP10 or whether there are systems that should be there and those that should not. Looking at the whole list, we saw a few surprises. [audio mp3="http://orionx.net/wp-content/uploads/2021/11/002@HPCpodcast_TOP500_20211116.mp3"][/audio] The post @HPCpodcast-2: TOP500 at SC21 appeared first on OrionX.net.