insideBIGDATA

MARCH 21, 2023

NVIDIA and key partners today announced the availability of new products and services featuring the NVIDIA H100 Tensor Core GPU — the powerful GPU for AI — to address rapidly growing demand for generative AI training and inference.

AI 150

AI AI Azure AWS 150

Flipboard

AUGUST 15, 2023

There's a new hot commodity in AI: a $40,000 workhorse chip that goes by the name of Hopper. Named after pioneering computer scientist Grace Hopper, it's an ultra-expensive little chip, which is officially called the H100 tensor core GPU and is the hot property of Silicon Valley … Move aside, ChatGPT.

AI 120

AI AI Artificial Intelligence Artificial Intelligence 120

Analytics Vidhya

MAY 30, 2023

The company has introduced the NVIDIA DGX GH200, a groundbreaking AI supercomputer powered by the state-of-the-art NVIDIA GH200 Grace Hopper Superchips and the NVLink Switch System. NVIDIA, a leader in artificial intelligence (AI) technology, has made an exciting announcement that is set to revolutionize the field.

Artificial Intelligence 266

Artificial Intelligence Artificial Intelligence AI AI 266

Hacker News

DECEMBER 14, 2023

In 11th grade, I wrote my first program, Dingo Hopper. Dingo Hopper was not fu. In the game, the player controls a png of a dingo as it jumps over gray boxes.

100

100

Hacker News

JULY 30, 2023

This white paper details how NVIDIA DGX GH200 connects 256 Grace Hopper Superchips into a singular, 1-Exaflop, 144TB shared memory GPU for giant terabyte-class AI models powering generative AI, recommender systems, and data processing.

AI 123

AI AI 123

Flipboard

JUNE 7, 2023

Early last week at COMPUTEX, Nvidia announced that its new GH200 Grace Hopper "Superchip"—a … It takes a lot of computing power to pretend to be human.

AI 123

AI AI Computer Science Computer Science 123

Hacker News

JULY 26, 2023

From 1961 to 1967, Hopper transformed from a stalled-out actor to an omnipresent chronicler of a country in transition.

123

123

Hacker News

DECEMBER 24, 2023

When Laura Hopper was a kid, her mother had a friend who lived in a tree.

112

112

Flipboard

MAY 28, 2023

announced early Monday that its most powerful artificial intelligence chip yet, the GH200 Grace Hopper Superchip, is now in full … Nvidia Corp.

Artificial Intelligence 88

Artificial Intelligence Artificial Intelligence AI AI 88

Hacker News

MARCH 21, 2023

Comments (..)

123

123

Hacker News

FEBRUARY 26, 2024

Nvidia's H200 product relies on the Hopper architecture and offers the same computing performance as the H100. Compared to HBM3, HBM3E increases data transfer rate and peak memory bandwidth by a whopping 44%, which is particularly important for bandwidth-hungry processors like Nvidia's H200. TB/s bandwidth in the case of the H100.

Artificial Intelligence 177

Artificial Intelligence Artificial Intelligence AI AI 177

Dataconomy

NOVEMBER 14, 2023

This latest innovation from Nvidia is tailored to power supercomputers that drive generative AI models, showcasing the prowess of the Nvidia Hopper architecture. Nvidia H200 emerges as a groundbreaking chip, marking a significant leap in supercomputing technology. What does Nvidia H200 offer? terabytes per second.

AI 103

AI AI Natural Language Processing Azure 103

Dataconomy

APRIL 19, 2016

Check out Berlin, London or Amsterdam and you’ll be met with a striking number of founders, start-up hoppers, and entrepreneurs. Start-up admiration and entrepreneurship are alive and well outside of Silicon Valley. Silicon Valley does reign supreme, but the tides are continuing to turn outside of the California-bubble.

130

130

Hacker News

JUNE 27, 2023

We’ll be making submissions on NVIDIA Grace Hopper systems in future MLPerf rounds as well. The benchmarks enjoy backing from a broad group that includes Arm, Baidu, Facebook AI, Google, Harvard, Intel, Microsoft, Stanford and the University of Toronto.

AI 182

AI AI Clustering Machine Learning 182

Women in Big Data

SEPTEMBER 22, 2022

She also covered how her entrepreneurial journey took a left turn when she became the founding CEO of the Anita Borg Institute and scaled the organization and the Grace Hopper Celebration to have global reach and impact. 3] Telle is also the former CEO and President of the Anita Borg Institute for Women and Technology.

Computer Science 52

Computer Science Computer Science Big Data Big Data 52

Hacker News

MARCH 17, 2024

The B200 is capable of delivering four times the training performance, up to 30 times the inference performance, and up to 25 times better energy efficiency, compared to its predecessor, the Hopper H100 GPU. B200’s memory is the latest variety, HBM3e, and it totals 192 GB (up from 141 GB for the second generation Hopper chip, H200).

AI 181

AI AI Database Analytics 181

ODSC - Open Data Science

NOVEMBER 30, 2023

The H200 Tensor Core is based on the NVIDIA Hopper architecture the GPU features HBM3e, providing an unprecedented 141 gigabytes of memory at an astounding 4.8 This GPU hopes to set a new benchmark as the world’s most powerful GPU designed to supercharge artificial intelligence and high-performance computing or HPC workloads.

AI 52

AI AI Data Science Artificial Intelligence 52

Towards AI

SEPTEMBER 6, 2023

Far from being just a large machine, its unparalleled capability offers a stunning 144TB of shared memory across 256 NVIDIA Grace Hopper Superchips (GH200). This empowers developers with nearly 500x more memory, enabling the creation of complex, large-scale models to tackle today’s most challenging problems.

Deep Learning 114

Deep Learning Deep Learning AI AI 114

Hacker News

NOVEMBER 15, 2023

The NVIDIA GH200 Grace Hopper Superchip , with its 288GB of fast HBM3e memory and 8 petaflops of compute, is ideal — it can deliver a 150x speedup over using a CPU. Getting the best performance for RAG workflows requires massive amounts of memory and compute to move and process data.

Database 181

Database AI AI Natural Language Processing 181

Hacker News

DECEMBER 6, 2023

The chip offers both contrasts and similarities to competing approaches such as Nvidia’s Grace-Hopper superchip and Intel’s supercomputer accelerator Ponte Vecchio. Nvidia’s Grace-Hopper is such a superchip combination linking the Grace CPU to the Hopper GPU through Nvidia’s Nvidia NVLink Chip-2-Chip interconnects.

AI 181

AI AI Machine Learning Machine Learning 181

ODSC - Open Data Science

MAY 1, 2023

She is the recipient numerous awards, including the 2021 ACM Grace Murray Hopper Award, a Sloan Foundation Fellowship award, Jay Lepreau Best Paper Award at OSDI 2021, Distinguished Paper Award at IEEE Euro S&P 2022 and was recognized by Technology Review as one of the 35 Innovators under 35.

Data Science 52

Data Science Machine Learning Machine Learning Azure 52

Hacker News

JANUARY 5, 2023

The most notable of which is likely NVIDIA’s Grace Hopper superchip , which combines an NVIDIA Armv9 Grace CPU with a Hopper GPU. When it launches in the later half of 2023, AMD’s MI300 is expected to be going up against a few competing products. capacity).

AI 182

AI AI 182

O'Reilly Media

NOVEMBER 29, 2022

There’s no shortage of suggested remedies in the hopper. The Center for Applied Artificial Intelligence at the University of Chicago Booth School of Business , ? LA Tech4Good , The AI Hub at McSilver , AI4ALL , and the Algorithmic Justice League.

Artificial Intelligence 111

Artificial Intelligence Artificial Intelligence AI AI 111

BAIR

APRIL 20, 2022

D4RL Gym The first suite is D4RL Gym, which contains the standard MuJoCo halfcheetah, hopper, and walker robots. Overall Performance After identifying these key design decisions, we study the overall performance of RvS in comparison to previous methods. This blog post will overview results from two of the suites we consider in the paper.

Supervised Learning 52

Supervised Learning Algorithm 52

Heartbeat

DECEMBER 5, 2023

H100 — Performance and Optimization for Generative AI The fourth-generation Tensor Core H100 of the Hopper architecture family introduced NVIDIA’s commitment to innovation. Developed based on Hopper architecture, the H200 stands out with its groundbreaking HBM3e memory. With a mind-blowing 141GB memory capacity at 4.8

Natural Language Processing 52

Natural Language Processing Deep Learning Deep Learning AI 52

BAIR

SEPTEMBER 19, 2022

Example evaluation of ours and baseline methods on a hopper control task for different values of constraint thresholds (x- axis).

Machine Learning 45

Machine Learning Machine Learning Algorithm 45

phData

AUGUST 8, 2023

This GPU utilizes the Hopper microarchitecture to boost large language model inference by 30x and training by 4x compared to the A100 and supports trillion-parameter models via a dedicated Transformer Engine. Most recently, NVIDIA released the H100, which represents the latest advance in GPU computing.

AI 52

AI AI Deep Learning Deep Learning 52