621 annotations
Page 22 of 32
recognizing the beginning of this transition and diverting their capital investment to accelerated computing and generative AI
(No comment added)
Transcript
2024 Q2
24 Aug 23
we're already planning the next-generation infrastructure with the leading CSPs and data center builders
(No comment added)
Transcript
2024 Q2
24 Aug 23
L40S is really designed for a different type of scale-out
(No comment added)
Transcript
2024 Q2
24 Aug 23
H100 is designed for large-scale language models and processing just very large models and a great deal of data
(No comment added)
Transcript
2024 Q2
24 Aug 23
L40S' focus is to be able to fine-tune models, fine-tune pretrained models
(No comment added)
Transcript
2024 Q2
24 Aug 23
It seems like we're introducing a new architecture every two years.
Now we're introducing a new architecture, a new product just about every six months.
(No comment added)
Transcript
2024 Q2
24 Aug 23
H100s go out really as HGXs sent to the world’s hyperscalers and they’re really, really quite large system components
(No comment added)
Transcript
2024 Q2
24 Aug 23
the largest driver of our revenue within this last quarter was definitely the HGX system
(No comment added)
Transcript
2024 Q2
24 Aug 23
The rest of the GPUs, we have new GPUs coming to market that we talk about the L40S, and they will add continued growth going forward.
(No comment added)
Transcript
2024 Q2
24 Aug 23
our HGX systems were a very significant part of our Data Center as well as our Data Center growth that we had seen
(No comment added)
Transcript
2024 Q2
24 Aug 23
The world has something along the lines of about $1 trillion worth of data centers installed, in the cloud, in enterprise and otherwise. And that $1 trillion of data centers is in the process of transitioning into accelerated computing and generative AI.
(No comment added)
Transcript
2024 Q2
24 Aug 23
Spectrum-X couples the Spectrum or Ethernet switch with the BlueField-3 DPU, achieving 1.5x better overall AI performance and power efficiency versus traditional Ethernet.
(No comment added)
Transcript
2024 Q2
24 Aug 23
NVIDIA Spectrum-X, an accelerated networking platform designed to optimize Ethernet for AI workloads
(No comment added)
Transcript
2024 Q2
24 Aug 23
It is the network of choice for leading AI practitioners.
(No comment added)
Transcript
2024 Q2
24 Aug 23
only InfiniBand can scale to hundreds of thousands of GPUs
(No comment added)
Transcript
2024 Q2
24 Aug 23
Strong networking growth was driven primarily by InfiniBand infrastructure to connect HGX GPU systems.
(No comment added)
Transcript
2024 Q2
24 Aug 23
InfiniBand delivers more than double the performance of traditional Ethernet for AI
(No comment added)
Transcript
2024 Q2
24 Aug 23
DGX GH200 systems are expected to be available by the end of the year, Google Cloud, Meta and Microsoft among the first to gain access.
(No comment added)
Transcript
2024 Q2
24 Aug 23
enabling all of its 256 Grace Hopper Superchips to work together as one, a huge jump compared to our prior generation connecting just eight GPUs over [indiscernible]
(No comment added)
Transcript
2024 Q2
24 Aug 23
The second generation version of our Grace Hopper Superchip with the latest HBM3e memory will be available in Q2 of calendar 2024.
(No comment added)
Transcript
2024 Q2
24 Aug 23