Ivan Goldwasser – NVIDIA Technical Blog News and tutorials for developers, data scientists, and IT admins 2025-05-20T19:43:02Z http://www.open-lab.net/blog/feed/ Ivan Goldwasser <![CDATA[NVIDIA 800 V HVDC Architecture Will Power the Next Generation of AI Factories]]> http://www.open-lab.net/blog/?p=100571 2025-05-20T19:43:02Z 2025-05-20T17:56:58Z The exponential growth of AI workloads is increasing data center power demands. Traditional 54 V in-rack power distribution, designed for kilowatt (KW)-scale...]]>

The exponential growth of AI workloads is increasing data center power demands. Traditional 54 V in-rack power distribution, designed for kilowatt (KW)-scale racks, isn’t designed to support the megawatt (MW)-scale racks coming soon to modern AI factories. NVIDIA is leading the transition to 800 V HVDC data center power infrastructure to support 1 MW IT racks and beyond, starting in 2027.

Source

]]>
Ivan Goldwasser <![CDATA[Integrating Semi-Custom Compute into Rack-Scale Architecture with NVIDIA NVLink Fusion]]> http://www.open-lab.net/blog/?p=100146 2025-05-19T05:01:01Z 2025-05-19T04:54:31Z Data centers are being re-architected for efficient delivery of AI workloads. This is a hugely complicated endeavor, and NVIDIA is now delivering AI factories...]]>

Data centers are being re-architected for efficient delivery of AI workloads. This is a hugely complicated endeavor, and NVIDIA is now delivering AI factories based on the NVIDIA rack-scale architecture. To deliver the best performance for the AI factory, many accelerators need to work together at rack-scale with maximal bandwidth and minimal latency to support the largest number of users in the…

Source

]]>
Ivan Goldwasser <![CDATA[NVIDIA ConnectX-8 SuperNICs Advance AI Platform Architecture with PCIe Gen6 Connectivity]]> http://www.open-lab.net/blog/?p=99991 2025-05-19T04:07:42Z 2025-05-19T04:07:33Z As AI workloads grow in complexity and scale��from large language models (LLMs) to agentic AI reasoning and physical AI��the demand for faster, more scalable...]]>

As AI workloads grow in complexity and scale—from large language models (LLMs) to agentic AI reasoning and physical AI—the demand for faster, more scalable compute infrastructure has never been greater. Meeting these demands requires rethinking system architecture from the ground up. NVIDIA is advancing platform architecture with NVIDIA ConnectX-8 SuperNICs, the industry’s first SuperNIC to…

Source

]]>
Ivan Goldwasser <![CDATA[Building the Modular Foundation for AI Factories with NVIDIA MGX]]> http://www.open-lab.net/blog/?p=100010 2025-05-15T17:34:45Z 2025-05-16T15:00:00Z The exponential growth of generative AI, large language models (LLMs), and high-performance computing has created unprecedented demands on data center...]]>

The exponential growth of generative AI, large language models (LLMs), and high-performance computing has created unprecedented demands on data center infrastructure. Traditional server architectures struggle to accommodate the power density, thermal requirements, and rapid iteration cycles of modern accelerated computing. This post explains the benefits of NVIDIA MGX…

Source

]]>
Ivan Goldwasser <![CDATA[Efficient ETL with Polars and Apache Spark on NVIDIA Grace CPU]]> http://www.open-lab.net/blog/?p=96807 2025-04-23T00:33:58Z 2025-03-11T18:30:00Z The NVIDIA Grace CPU Superchip delivers outstanding performance and best-in-class energy efficiency for CPU workloads in the data center and in the cloud. The...]]>

The NVIDIA Grace CPU Superchip delivers outstanding performance and best-in-class energy efficiency for CPU workloads in the data center and in the cloud. The benefits of NVIDIA Grace include high-performance Arm Neoverse V2 cores, fast NVIDIA-designed Scalable Coherency Fabric, and low-power high-bandwidth LPDDR5X memory. These features make the Grace CPU ideal for data processing with…

Source

]]>
Ivan Goldwasser <![CDATA[NVIDIA Grace CPU Integrates with the Arm Software Ecosystem]]> http://www.open-lab.net/blog/?p=95638 2025-04-23T02:52:39Z 2025-02-10T18:45:22Z The NVIDIA Grace CPU is transforming data center design by offering a new level of power-efficient performance. Built specifically for data center scale, the...]]>

The NVIDIA Grace CPU is transforming data center design by offering a new level of power-efficient performance. Built specifically for data center scale, the Grace CPU is designed to handle demanding workloads while consuming less power. NVIDIA believes in the benefit of leveraging GPUs to accelerate every workload. However, not all workloads are accelerated. This is especially true for those…

Source

]]>
Ivan Goldwasser <![CDATA[Advancing Ansys Workloads with NVIDIA Grace and NVIDIA Grace Hopper]]> http://www.open-lab.net/blog/?p=92496 2024-12-12T19:38:41Z 2024-11-21T17:30:00Z Accelerated computing is enabling giant leaps in performance and energy efficiency compared to traditional CPU computing. Delivering these advancements requires...]]>

Accelerated computing is enabling giant leaps in performance and energy efficiency compared to traditional CPU computing. Delivering these advancements requires full-stack innovation at data-center scale, spanning chips, systems, networking, software, and algorithms. Choosing the right architecture for the right workload with the best energy efficiency is critical to maximizing the performance and…

Source

]]>
Ivan Goldwasser <![CDATA[NVIDIA Grace CPU Delivers World-Class Data Center Performance and Breakthrough Energy Efficiency]]> http://www.open-lab.net/blog/?p=90087 2024-11-06T02:26:22Z 2024-10-09T19:00:00Z NVIDIA designed the NVIDIA Grace CPU to be a new kind of high-performance, data center CPU��one built to deliver breakthrough energy efficiency and optimized...]]>

NVIDIA designed the NVIDIA Grace CPU to be a new kind of high-performance, data center CPU—one built to deliver breakthrough energy efficiency and optimized for performance at data center scale. Accelerated computing is enabling giant leaps in performance and energy efficiency compared to traditional CPU computing. To deliver these speedups, full-stack innovation at data center scale is…

Source

]]>
Ivan Goldwasser <![CDATA[Low Latency Inference Chapter 2: Blackwell is Coming. NVIDIA GH200 NVL32 with NVLink Switch Gives Signs of Big Leap in Time to First Token Performance]]> http://www.open-lab.net/blog/?p=88938 2024-11-29T21:06:06Z 2024-09-26T21:44:00Z Many of the most exciting applications of large language models (LLMs), such as interactive speech bots, coding co-pilots, and search, need to begin responding...]]>

Many of the most exciting applications of large language models (LLMs), such as interactive speech bots, coding co-pilots, and search, need to begin responding to user queries quickly to deliver positive user experiences. The time that it takes for an LLM to ingest a user prompt (and context, which can be sizable) and begin outputting a response is called time to first token (TTFT).

Source

]]>
Ivan Goldwasser <![CDATA[NVIDIA GH200 Grace Hopper Superchip Delivers Outstanding Performance in MLPerf Inference v4.1]]> http://www.open-lab.net/blog/?p=89401 2024-11-06T02:27:00Z 2024-09-24T16:36:57Z In the latest round of MLPerf Inference �C a suite of standardized, peer-reviewed inference benchmarks �C the NVIDIA platform delivered outstanding...]]>

In the latest round of MLPerf Inference – a suite of standardized, peer-reviewed inference benchmarks – the NVIDIA platform delivered outstanding performance across the board. Among the many submissions made using the NVIDIA platform were results using the NVIDIA GH200 Grace Hopper Superchip. GH200 tightly couples an NVIDIA Grace CPU with an NVIDIA Hopper GPU using NVIDIA NVLink-C2C…

Source

]]>
Ivan Goldwasser <![CDATA[Spotlight: Petrobras Speeds Up Linear Solvers for Reservoir Simulation Using NVIDIA Grace CPU]]> http://www.open-lab.net/blog/?p=89245 2024-10-23T23:37:35Z 2024-09-24T15:00:00Z Reservoir simulation helps reservoir engineers optimize their resource exploration approach by simulating complex scenarios and comparing with real-world field...]]>

Reservoir simulation helps reservoir engineers optimize their resource exploration approach by simulating complex scenarios and comparing with real-world field data. This extends to simulation of depleted reservoirs that could be repurposed for carbon storage from operations. Reservoir simulation is crucial for energy companies aiming to enhance operational efficiency in exploration and production.

Source

]]>
Ivan Goldwasser <![CDATA[NVIDIA GH200 Superchip Delivers Breakthrough Energy Efficiency and Node Consolidation for Apache Spark]]> http://www.open-lab.net/blog/?p=87567 2024-08-22T18:24:50Z 2024-08-20T20:00:00Z With the rapid growth of generative AI, CIOs and IT leaders are looking for ways to reclaim data center resources to accommodate new AI use cases that promise...]]>

With the rapid growth of generative AI, CIOs and IT leaders are looking for ways to reclaim data center resources to accommodate new AI use cases that promise greater return on investment without impacting current operations. This is leading IT decision makers to reassess past infrastructure decisions and explore strategies to consolidate traditional workloads into fewer…

Source

]]>
Ivan Goldwasser <![CDATA[Revolutionizing Data Center Efficiency with the NVIDIA Grace Family]]> http://www.open-lab.net/blog/?p=86550 2024-10-09T20:01:54Z 2024-08-02T15:00:00Z The exponential growth in data processing demand is projected to reach 175 zettabytes by 2025. This contrasts sharply with the slowing pace of CPU performance...]]>

The exponential growth in data processing demand is projected to reach 175 zettabytes by 2025. This contrasts sharply with the slowing pace of CPU performance improvements. For more than a decade, semiconductor advancements have not kept up with the pace predicted by Moore’s Law, leading to a pressing need for more efficient computing solutions. NVIDIA GPUs have emerged as the most efficient…

Source

]]>
Ivan Goldwasser <![CDATA[NVIDIA GB200 NVL72 Delivers Trillion-Parameter LLM Training and Real-Time Inference]]> http://www.open-lab.net/blog/?p=79550 2024-07-12T14:47:47Z 2024-03-18T23:00:00Z What is the interest in trillion-parameter models? We know many of the use cases today and interest is growing due to the promise of an increased capacity for:...]]>

What is the interest in trillion-parameter models? We know many of the use cases today and interest is growing due to the promise of an increased capacity for: The benefits are‌ great, but training and deploying large models can be computationally expensive and resource-intensive. Computationally efficient, cost-effective, and energy-efficient systems, architected to deliver real-time…

Source

]]>
13
Ivan Goldwasser <![CDATA[Deploying Retrieval-Augmented Generation Applications on NVIDIA GH200 Delivers Accelerated Performance]]> http://www.open-lab.net/blog/?p=74632 2024-09-22T15:11:34Z 2023-12-18T17:00:00Z Large language model (LLM) applications are essential in enhancing productivity across industries through natural language. However, their effectiveness is...]]>

Large language model (LLM) applications are essential in enhancing productivity across industries through natural language. However, their effectiveness is often limited by the extent of their training data, resulting in poor performance when dealing with real-time events and new knowledge the LLM isn’t trained on. Retrieval-augmented generation (RAG) solves these problems.

Source

]]>
3
Ivan Goldwasser <![CDATA[One Giant Superchip for LLMs, Recommenders, and GNNs: Introducing NVIDIA GH200 NVL32]]> http://www.open-lab.net/blog/?p=74208 2023-12-14T19:27:37Z 2023-11-28T18:19:07Z At AWS re:Invent 2023, AWS and NVIDIA announced that AWS will be the first cloud provider to offer NVIDIA GH200 Grace Hopper Superchips interconnected with...]]>

At AWS re:Invent 2023, AWS and NVIDIA announced that AWS will be the first cloud provider to offer NVIDIA GH200 Grace Hopper Superchips interconnected with NVIDIA NVLink technology through NVIDIA DGX Cloud and running on Amazon Elastic Compute Cloud (Amazon EC2). This is a game-changing technology for cloud computing. The NVIDIA GH200 NVL32, a rack-scale solution within NVIDIA DGX Cloud or an…

Source

]]>
0
Ivan Goldwasser <![CDATA[NVIDIA Grace CPU Superchip Architecture In Depth]]> http://www.open-lab.net/blog/?p=59829 2023-12-06T23:46:07Z 2023-01-20T19:30:00Z The NVIDIA Grace CPU is the first data center CPU developed by NVIDIA. Combining NVIDIA expertise with Arm processors, on-chip fabrics, system-on-chip (SoC)...]]>

The NVIDIA Grace CPU is the first data center CPU developed by NVIDIA. Combining NVIDIA expertise with Arm processors, on-chip fabrics, system-on-chip (SoC) design, and resilient high-bandwidth low-power memory technologies, the Grace CPU was built from the ground up to create the world’s first superchip for computing. At the heart of the superchip, lies the NVLink Chip-2-Chip (C2C).

Source

]]>
2
Ivan Goldwasser <![CDATA[Optimizing NVIDIA AI Performance for MLPerf v0.7 Training]]> http://www.open-lab.net/blog/?p=19195 2023-07-05T19:38:22Z 2020-07-29T17:00:00Z MLPerf is an industry-wide AI consortium that has developed a suite of performance benchmarks covering a range of leading AI workloads that are widely in use...]]>

MLPerf is an industry-wide AI consortium that has developed a suite of performance benchmarks covering a range of leading AI workloads that are widely in use today. The latest MLPerf v0.7 training submission includes vision, language, recommenders, and reinforcement learning. NVIDIA submitted MLPerf v0.7 training results for all eight tests and the NVIDIA platform set records in all…

Source

]]>
0
���˳���97caoporen����