Intel Unveils Next-Generation AI Solutions with the Launch of Xeon 6 and Gaudi 3
Intel has unveiled next-generation AI solutions with the launch of Xeon 6 and Gaudi 3. The Xeon 6 with Performance-cores (P-cores) doubles the performance for AI and HPC workloads, while Gaudi 3 AI accelerators offer up to 20% more throughput and 2x price/performance vs H100 for inference of LLaMa 2 70B.
Key features of Xeon 6 include increased core count, double the memory bandwidth, and AI acceleration capabilities in every core. Gaudi 3 boasts 64 Tensor processor cores, 8 matrix multiplication engines, 128GB of HBM2e memory, and 24 200Gb Ethernet ports.
Intel is collaborating with IBM to deploy Gaudi 3 as a service on IBM Cloud, aiming to lower TCO and enhance performance. The company is also partnering with OEMs like Dell Technologies and Supermicro to develop co-engineered AI systems.
Intel ha svelato soluzioni AI di nuova generazione con il lancio di Xeon 6 e Gaudi 3. Il Xeon 6 con Performance-cores (P-cores) raddoppia le prestazioni per carichi di lavoro AI e HPC, mentre gli acceleratori AI Gaudi 3 offrono fino al 20% di maggiore throughput e un rapporto prezzo/prestazioni 2x rispetto all'H100 per l'inferenza di LLaMa 2 70B.
Le principali caratteristiche di Xeon 6 includono un numero maggiore di core, il doppio della larghezza di banda della memoria e capacità di accelerazione AI in ogni core. Gaudi 3 vanta 64 core di elaborazione Tensor, 8 motori per moltiplicazione di matrici, 128 GB di memoria HBM2e e 24 porte Ethernet da 200 Gb.
Intel sta collaborando con IBM per implementare Gaudi 3 come servizio su IBM Cloud, con l'intento di ridurre il TCO e migliorare le prestazioni. L'azienda sta anche collaborando con OEM come Dell Technologies e Supermicro per sviluppare sistemi AI co-ingegnerizzati.
Intel ha presentado soluciones de IA de próxima generación con el lanzamiento de Xeon 6 y Gaudi 3. El Xeon 6 con núcleos de rendimiento (P-cores) duplica el rendimiento para cargas de trabajo de IA y HPC, mientras que los aceleradores de IA Gaudi 3 ofrecen hasta un 20% más de rendimiento y el doble de relación precio/rendimiento en comparación con el H100 para la inferencia de LLaMa 2 70B.
Las características clave de Xeon 6 incluyen un aumento en el número de núcleos, el doble del ancho de banda de memoria y capacidades de aceleración de IA en cada núcleo. Gaudi 3 cuenta con 64 núcleos de procesador Tensor, 8 motores de multiplicación de matrices, 128 GB de memoria HBM2e y 24 puertos Ethernet de 200 Gb.
Intel está colaborando con IBM para desplegar Gaudi 3 como servicio en IBM Cloud, con el objetivo de reducir el TCO y mejorar el rendimiento. La compañía también se asocia con OEMs como Dell Technologies y Supermicro para desarrollar sistemas de IA co-ingenierizados.
인텔은 Xeon 6 및 Gaudi 3의 출시를 통해 차세대 AI 솔루션을 공개했습니다. 성능 코어(P-cores)를 갖춘 Xeon 6는 AI와 HPC 작업에 대한 성능을 두 배로 늘리며, Gaudi 3 AI 가속기는 LLaMa 2 70B의 추론을 위해 H100에 비해 최대 20% 더 높은 처리량과 2배의 가격 대비 성능을 제공합니다.
Xeon 6의 주요 특징으로는 증가된 코어 수, 두 배의 메모리 대역폭, 모든 코어의 AI 가속 능력이 포함됩니다. Gaudi 3는 64개의 텐서 프로세서 코어, 8개의 행렬 곱셈 엔진, 128GB의 HBM2e 메모리 및 24개의 200Gb 이더넷 포트를 자랑합니다.
인텔은 IBM과 협력하여 IBM Cloud에서 Gaudi 3를 서비스로 배포하여 TCO를 낮추고 성능을 향상시키는 것을 목표로 하고 있습니다. 이 회사는 Dell Technologies 및 Supermicro와 같은 OEM과 협력하여 공동 설계된 AI 시스템을 개발하고 있습니다.
Intel a dévoilé des solutions d'IA de nouvelle génération avec le lancement de Xeon 6 et Gaudi 3. Le Xeon 6 avec des cœurs de performance (P-cores) double les performances pour les charges de travail d'IA et HPC, tandis que les accélérateurs IA Gaudi 3 offrent jusqu'à 20 % de bande passante supplémentaire et un rapport qualité/prix multiplié par 2 par rapport à l'H100 pour l'inférence de LLaMa 2 70B.
Les principales caractéristiques du Xeon 6 incluent un nombre de cœurs accru, le double de la bande passante mémoire et des capacités d'accélération d'IA dans chaque cœur. Gaudi 3 se vante de 64 cœurs de processeur Tensor, 8 moteurs de multiplication de matrices, 128 Go de mémoire HBM2e et 24 ports Ethernet de 200 Gb.
Intel collabore avec IBM pour déployer Gaudi 3 en tant que service sur IBM Cloud, visant à réduire le TCO et à améliorer les performances. L'entreprise s'associe également à des OEM tels que Dell Technologies et Supermicro pour développer des systèmes d'IA co-ingenierés.
Intel hat nächste Generation AI-Lösungen mit der Einführung von Xeon 6 und Gaudi 3 präsentiert. Der Xeon 6 mit Performance-Kernen (P-cores) verdoppelt die Leistung für AI- und HPC-Arbeitslasten, während die Gaudi 3 AI-Beschleuniger bis zu 20% mehr Durchsatz und ein 2x Preis-Leistungs-Verhältnis im Vergleich zu H100 für die Inferenz von LLaMa 2 70B bieten.
Die Hauptmerkmale des Xeon 6 umfassen eine erhöhte Kernanzahl, das Doppelte der Speicherbandbreite und AI-Beschleunigungsmöglichkeiten in jedem Kern. Gaudi 3 verfügt über 64 Tensor-Prozessor-Kerne, 8 Matrizenmultiplikationsmotoren, 128 GB HBM2e-Speicher und 24 200Gb Ethernet-Ports.
Intel arbeitet mit IBM zusammen, um Gaudi 3 als Dienst auf IBM Cloud bereitzustellen, mit dem Ziel, die TCO zu senken und die Leistung zu steigern. Das Unternehmen kooperiert auch mit OEMs wie Dell Technologies und Supermicro, um gemeinsam entwickelte AI-Systeme zu entwickeln.
- Xeon 6 doubles performance for AI and HPC workloads compared to its predecessor
- Gaudi 3 offers up to 20% more throughput and 2x price/performance vs H100 for LLaMa 2 70B inference
- Collaboration with IBM to deploy Gaudi 3 as a service on IBM Cloud
- Partnerships with Dell Technologies and Supermicro for co-engineered AI systems
- Launch of Intel Tiber Developer Cloud for tech evaluation and testing of Xeon 6
- None.
Insights
Intel's launch of Xeon 6 and Gaudi 3 AI accelerators marks a significant leap in enterprise AI capabilities. The Xeon 6 with P-cores doubles performance for AI and HPC workloads, while Gaudi 3 offers up to 20
Key advancements include:
- Xeon 6: Increased core count, double memory bandwidth and embedded AI acceleration
- Gaudi 3: 64 Tensor processor cores, 8 matrix multiplication engines, 128GB HBM2e memory and 24 200Gb Ethernet ports
These innovations position Intel to compete strongly in the AI hardware market, potentially disrupting NVIDIA's dominance. The focus on TCO benefits and performance per watt could appeal to cost-conscious enterprises scaling AI deployments.
Intel's strategic move into high-performance AI hardware comes at a important time. With the AI market booming, this launch could significantly impact Intel's market position and financial performance. Key points for investors:
- Potential for increased data center revenue as enterprises adopt these new AI solutions
- Improved competitiveness against NVIDIA in the AI accelerator market
- Collaboration with IBM Cloud could expand Intel's reach in cloud AI services
- Partnerships with Dell and Supermicro for co-engineered systems may drive adoption
The 73
Intel enables a new era of high-performance enterprise AI systems and solutions.
NEWS HIGHLIGHTS
- Intel launches Xeon 6 with Performance-cores (P-cores), doubling the performance for AI and HPC workloads.
- New Gaudi 3 AI accelerators offer up to 20 percent more throughput and 2x price/performance vs H100 for inference of LLaMa 2 70B1.
“Demand for AI is leading to a massive transformation in the data center, and the industry is asking for choice in hardware, software and developer tools,” said Justin Hotard, Intel executive vice president and general manager of the Data Center and Artificial Intelligence Group. “With our launch of Xeon 6 with P-cores and Gaudi 3 AI accelerators, Intel is enabling an open ecosystem that allows our customers to implement all of their workloads with greater performance, efficiency and security.”
Introducing Intel Xeon 6 with P-cores and Gaudi 3 AI accelerators
Intel’s latest advancements in AI infrastructure include two major updates to its data center portfolio:
- Intel® Xeon® 6 with P-cores: Designed to handle compute-intensive workloads with exceptional efficiency, Xeon 6 delivers twice the performance of its predecessor2. It features increased core count, double the memory bandwidth and AI acceleration capabilities embedded in every core. This processor is engineered to meet the performance demands of AI from edge to data center and cloud environments.
- Intel® Gaudi® 3 AI Accelerator: Specifically optimized for large-scale generative AI, Gaudi 3 boasts 64 Tensor processor cores (TPCs) and eight matrix multiplication engines (MMEs) to accelerate deep neural network computations. It includes 128 gigabytes (GB) of HBM2e memory for training and inference, and 24 200 Gigabit (Gb) Ethernet ports for scalable networking. Gaudi 3 also offers seamless compatibility with the PyTorch framework and advanced Hugging Face transformer and diffuser models. Intel recently announced a collaboration with IBM to deploy Intel Gaudi 3 AI accelerators as a service on IBM Cloud. Through this collaboration, Intel and IBM aim to lower the total cost of ownership to leverage and scale AI, while enhancing performance.
Enhancing AI Systems with TCO Benefits
Deploying AI at scale involves considerations such as flexible deployment options, competitive price-performance ratios and accessible AI technologies. Intel’s robust x86 infrastructure and extensive open ecosystem position it to support enterprises in building high-value AI systems with an optimal TCO and performance per watt. Notably,
Intel partners with leading OEMs including Dell Technologies and Supermicro to develop co-engineered systems tailored to specific customer needs for effective AI deployments. Dell Technologies is currently co-engineering RAG-based solutions leveraging Gaudi 3 and Xeon 6.
Bridging the Gap from Prototypes to Production with Co-Engineering Efforts
Transitioning generative AI (Gen AI) solutions from prototypes to production-ready systems presents challenges in real-time monitoring, error handling, logging, security and scalability. Intel addresses these challenges through co-engineering efforts with OEMs and partners to deliver production-ready retrieval-augmented generation (RAG) solutions.
These solutions, built on the Open Platform Enterprise AI (OPEA) platform, integrate OPEA-based microservices into a scalable RAG system, optimized for Xeon and Gaudi AI systems, designed to allow customers to easily integrate applications from Kubernetes, Red Hat OpenShift AI and Red Hat Enterprise Linux AI.
Expanding Access to Enterprise AI Applications
Intel’s Tiber portfolio offers business solutions to tackle challenges such as access, cost, complexity, security, efficiency and scalability across AI, cloud and edge environments. The Intel® Tiber™ Developer Cloud now provides preview systems of Intel Xeon 6 for tech evaluation and testing. Additionally, select customers will gain early access to Intel Gaudi 3 for validating AI model deployments, with Gaudi 3 clusters to begin rolling out next quarter for large-scale production deployments.
New service offerings include SeekrFlow, an end-to-end AI platform from Seekr for developing trusted AI applications. The latest updates feature Intel Gaudi software’s newest release and Jupyter notebooks loaded with PyTorch 2.4 and Intel oneAPI and AI tools 2024.2, which include new AI acceleration capabilities and support for Xeon 6 processors.
1 See intel.com/processorclaims: Intel Gaudi 3. Results may vary.
2 See intel.com/processorclaims: Intel Xeon 6. Results may vary.
3 Source: IDC Server Tracker report, based on Q1’24 system volume.
About Intel
Intel (Nasdaq: INTC) is an industry leader, creating world-changing technology that enables global progress and enriches lives. Inspired by Moore’s Law, we continuously work to advance the design and manufacturing of semiconductors to help address our customers’ greatest challenges. By embedding intelligence in the cloud, network, edge and every kind of computing device, we unleash the potential of data to transform business and society for the better. To learn more about Intel’s innovations, go to newsroom.intel.com and intel.com.
© Intel Corporation. Intel, the Intel logo and other Intel marks are trademarks of Intel Corporation or its subsidiaries. Other names and brands may be claimed as the property of others.
View source version on businesswire.com: https://www.businesswire.com/news/home/20240924255313/en/
Bats Jafferji
+1 603-809-5145
bats.jafferji@intel.com
Source: Intel Corporation
FAQ
What are the key features of Intel's new Xeon 6 processor for AI workloads?
How does Intel Gaudi 3 AI Accelerator compare to NVIDIA's H100 for LLaMa 2 70B inference?
What collaboration has Intel announced with IBM regarding Gaudi 3 AI accelerators?