Thread replies: 31
Thread images: 3
Thread images: 3
File: Processors.jpg (982KB, 3600x2025px) Image search:
[Google]
982KB, 3600x2025px
http://www.prnewswire.com/news-releases/inspur-will-unveil-its-new-ai-supercomputer-and-aistation-at-gtc-2017-300452957.html
>During GTC 2017, Inspur and NVIDIA and will jointly present a cutting-edge AI supercomputer, AGX-2, with the NVLink™ 2.0 enabled. The AGX-2 is designed to provide maximum throughput for superior application performance for science and engineering computing - taking AI computing to the next level.
>C.J. Muse - Evercore Group LLC
>Very helpful. I guess as my follow-up, on the inventory side, that grew I think 3% sequentially. Can you walk through the moving parts there? What's driving that, and is foundry diversification part of that? Thank you.
>Jen-Hsun Huang - NVIDIA Corp.
>The driving reasons for inventory growth is new products, and that's probably all I ought to say for now. I would come to GTC. Come to the keynote tomorrow. I think it will be fun.
TESLA VOLTA CONFIRMED LAUNCHING AT GTC TODAY
NVLINK 2.0 ONLY ON VOLTA, PASCAL ONLY HAS NVLINK 1.0
THANK YOU BASED NVIDIA
AYYMD IS FINISHED & BANKRUPT
>>
>>60307640
>IBM POWER CPU
INTEL IS FINISHED & BANKRUPT
>>
Happy to see IBM back.
How are they bank reserves nowadays?
>>
P100 was unveiled at GTC as well and only came out in December.
Even Nvidia said at that time that volume shipping won't be before Q4
>>
So that a real volta die shot ?
>>
>>60308637
> imblying physical incarnation of big volta even close to existing
it's 10+ months out, anon
>>
>>60307640
Plz Nvidia, kickstart the coming singularity. We need superintelligent AI to save humanity from itself.
>>
AMD BTFO
>>
File: 33638687283_76d7fde10d_k.jpg (2MB, 2048x1365px) Image search:
[Google]
2MB, 2048x1365px
>>60307640
AMD should literally hang the CEO by now lol.
>>
>>60307640
>TESLA VOLTA CONFIRMED LAUNCHING AT GTC TODAY
It's going to be meme shit.
>>60309355
>>60309428
Hope you like Nvidia blue balls after you've spent all day jerking yourself raw.
>>
Oh lord. Nice to see IBM still be relevant.
>>
so nvidia had to go to IBM for CPU due to all-in-one package that AMD unfolded
because:
a) intel hates them
b) AMD hates them
c)half of industry hates them because they got fucked by them at some point or other
d)IBM soon to hate them
for some reason consumers love them even though they got fucked the most of everyone
a mystery!
>>
>>60310378
t.butthurt
>>
>>60308637
No, that's good ol' Kepler GK110
>>
>>60310462
t.shill
>>
>>60310515
t.butthurt fanboy
>>
>>60310524
t.nvidia bootlicker
>>
>>60310540
t.butthurtayyamdrone
>>
>AI Supercomputer
>The fucking faggots on /g/ are instead talking about the fucking GPU inside it
I fucking hate this board and every fucking faggot in it. Fucking kill yourselves.
>>
>>60310651
You're not a true /g/ poster unless you play games
>>
>>60310683
Die /v/ermin cancer.
>>
>>60310651
lol, chillax kid
>>
>>60310651
What do you expect? They only like jerking off over GPUs while jumping around like retards proclaiming how doomed AMD is for the 10,000th time.
>>
>>60310651
If you want to discuss the AI part then you need to discuss Radeon Instinct, and even go as far as discussing IBM's Synapase stuff
Obviously this doesn't fit the shills narrative of Nvidia dominance
>>
>>60310651
>muh """"AI""""
>muh supercomputers
they're not very relevant to the average person and they won't be any time soon
>>
>>60307640
Kek.
AMD Is shipping 3 petaflops mi25 racks already.
Probably five times cheaper than Nvidiots do.
Poor Volta is DOA
>>
>>60314507
Stop interrupting the circlejerk. How are the Nvidiots supposed to get themselves off like that?
>>
File: amdvega.jpg (156KB, 633x758px) Image search:
[Google]
156KB, 633x758px
AMD BROS HOLD ME
>>
>>60314507
And running what?
Nidia has great support with cuDNN for Torch, Theano, Tensorflow, and Caffe.
What does AMD have again?
>>
>>60314651
async compute
freesync
#radeonrebellion
>>
>>60315947
kek
Thread posts: 31
Thread images: 3
Thread images: 3