NVIDIA Announces Tesla T4 Tensor Core GPU

Published by

Click here to post a comment for NVIDIA Announces Tesla T4 Tensor Core GPU on our message forum
#5584047
https://forums.guru3d.com/data/avatars/m/243/243702.jpg
Marketing: "Tesla T4 GPUs, which process queries up to 40x faster than CPUs alone." Did they compare it to iP3@800MHz? Random C2Q? Or 28C/56T chilled core chip? But I hope everyone sees how much they fit in... Someone should start getting info about sizes of each unit. I bet quite few people here would rather have GPU with 1/2 of SPs RTX2080Ti has and double tensor/RT cores. (That's if they can be decoupled.)
#5584058
data/avatar/default/avatar37.webp
They are probably talking about parallel or OpenCL type operations and not x86 code. In those cases, GPUs are vastly superior for highly paralleled compute code.
#5584059
https://forums.guru3d.com/data/avatars/m/243/243702.jpg
Valken:

They are probably talking about parallel or OpenCL type operations and not x86 code. In those cases, GPUs are vastly superior for highly paralleled compute code.
Once more, read slowly... What are they comparing that GPU to? Till we know that, their entire statement is irrelevant.
#5584066
data/avatar/default/avatar26.webp
I don't want to argue with you but its right there in their statement. We can guess what data centers use so many processors, CPU or GPU streams for: AI data processing... "AI data center platform that delivers the industry’s most advanced inference acceleration for voice, video, image and recommendation services." It says on a cloud with queries, lets say AI derived web searchs or photo retouching or map generation or scientific calculations, those are highly paralleled tasks and as per my statement, GPUs in general, regardless of any vendors are usually better than x86 CISC CPUs, multicore, multithread or not. Hell, better than RISC CPUs as well due to pure scaling of stream "processors". Google is listed as a test case for trial runs... No need to be hostile about a discussion.
#5584067
https://forums.guru3d.com/data/avatars/m/243/243702.jpg
Valken:

I don't want to argue with you but its right there in their statement. We can guess what data centers use so many processors, CPU or GPU streams for: data processing... It says on a cloud with queries, lets say search engine lookups, those are highly paralleled tasks and as per my statement, GPUs in general, regardless of any vendors are usually better than x86 CISC CPUs, multicore, multithread or not. Hell, better than RISC CPUs as well due to pure scaling of stream "processors". Google is listed as a test case for trial runs... No need to be hostile about a discussion.
CPU in my cellphone is up to 200times faster than PC CPU. It is true, but moment you get what CPU I compared it to... yes, this statement I made is baseless because it makes comparison to "smoke" same way nVidia did. If I was to guess what is relevant comparison in case no contestants in comparison are shown, it would be 1CU in GPU vs 1CU in CPU. But I am sure that they did compare quite a few SMs (CUs) to something like intel's 4C/8T low power server chip. In best case scenario (as close to relevant as possible) they took some 75W server CPU and compared it to their 75W GPU in some very specific workload where that GPU excels and CPUs generally suck.
#5584069
https://forums.guru3d.com/data/avatars/m/273/273969.jpg
It's at the bottom of the slide Xeon Gold 6140
#5584115
data/avatar/default/avatar36.webp
Oh thank christ somebody here actually reads the source material before commenting.
#5584150
https://forums.guru3d.com/data/avatars/m/271/271560.jpg
i'm laughing so hard right now. of course Google is the target...and any other big data/AI company. they can fill an entire production run just from companies in a 40km radius from where i live. this is the money market, they will receive higher priority than any AIB gaming manufacturer by a factor of at least two in shipments. cost is literally no object (from a gamer perspective) to these companies as they're paid by the data they crunch, mo' data mo' money. i would even go so far as to say the gaming market is tertiary to Nvidia at this point, as they are making more money from automotive than AIB's.
#5584167
data/avatar/default/avatar39.webp
asder:

It's at the bottom of the slide Xeon Gold 6140
Actually reading before commenting seems too much for many nowadays
#5584172
data/avatar/default/avatar31.webp
tunejunky:

i'm laughing so hard right now. of course Google is the target...and any other big data/AI company. they can fill an entire production run just from companies in a 40km radius from where i live. this is the money market, they will receive higher priority than any AIB gaming manufacturer by a factor of at least two in shipments. cost is literally no object (from a gamer perspective) to these companies as they're paid by the data they crunch, mo' data mo' money. i would even go so far as to say the gaming market is tertiary to Nvidia at this point, as they are making more money from automotive than AIB's.
It does not, more than half of the revenue of NVIDIA came from gaming alone
#5584188
https://forums.guru3d.com/data/avatars/m/263/263710.jpg
.............the first customer (one of them) is GOOGLE.... Check this: early access program ----------------------------------------------------------------------------------------------- “AI is becoming increasingly pervasive, and inference is a critical capability customers need to successfully deploy their AI models,” said Chris Kleban, product manager at Google Cloud, “so we’re excited to support NVIDIA’s Turing Tesla T4 GPUs on Google Cloud Platform soon.” Source: https://nvidianews.nvidia.com/news/new-nvidia-data-center-inference-platform-to-fuel-next-wave-of-ai-powered-services
#5584532
https://forums.guru3d.com/data/avatars/m/271/271560.jpg
Stefem:

It does not, more than half of the revenue of NVIDIA came from gaming alone
if you analyze the trends and the marketplace, that gaming revenue is sliding more rapidly than the growth of the two segments i mentioned. furthermore, the profitability is far greater in every other segment. in 2019 the graph chart will have flipped. AIB sales are down and they've been trending down for years as simpler games (i.e. android/ iOS) dominate the gaming market by revenue. concurrently, Big Data discovered Pascal gpu's (by the thousands) as did A.I. and the auto industries. as an investor invested in Nvidia (with Intel, TSMC, Qualcomm and AMD) i keep abreast of these things. go read some quarterly reports and listen in on earnings calls first.