[TR] Graphcore AI chip competes with Nvidia A100 - Page 2 - Overclock.net - An Overclocking Community

Forum Jump: 

[TR] Graphcore AI chip competes with Nvidia A100

Reply
 
Thread Tools
post #11 of 15 (permalink) Old 07-19-2020, 07:22 AM
New to Overclock.net
 
guttheslayer's Avatar
 
Join Date: Apr 2015
Posts: 3,912
Rep: 112 (Unique: 66)
Quote: Originally Posted by ToTheSun! View Post
That makes more sense. So, basically, it's more expensive and less performant. What a great product!
If this chip came out 2 years earlier, it will make V100 look real bad.

guttheslayer is offline  
Sponsored Links
Advertisement
 
post #12 of 15 (permalink) Old 07-19-2020, 08:50 AM - Thread Starter
Vandelay Industries
 
maltamonk's Avatar
 
Join Date: May 2015
Location: US/UK
Posts: 1,782
Rep: 85 (Unique: 63)
Adding additional info

Quote:
Graphcore's IPU technology uses "graph" processing, which processes all the data mapped across a single graph at once. It claims the IPU structure processes machine-learning tasks more efficiently than CPUs and GPUs. Many machine-learning frameworks -- including TensorFlow, MXNet, and Caffe -- already support graph processing.

Graphcore claims the vector processing model used by GPUs is "far more restrictive" than the graph model, which can allow researchers to "explore new models or reexplore areas" in AI research.
Quote:
“Our Colossus IPUs are unique in having support for Stochastic Rounding on the arithmetic that is supported in hardware and runs at the full speed of the processor,” said Nigel Toon, CEO of Graphcore. “This allows the Colossus Mk2 IPU to keep all arithmetic in 16-bit formats, reducing memory requirements, saving on read and write energy and reducing energy in the arithmetic logic, while delivering full accuracy Machine Intelligence results.”

Customers who need more performance can also order IPU-POD64 systems powered by 16 IPU-M2000 machines (and therefore providing 16 PetaFLOPS), whereas large organizations can scale out to 64,000 IPUs for 16 ExaFLOPS at FP16.16/FP16.SR.
maltamonk is offline  
post #13 of 15 (permalink) Old 07-19-2020, 09:05 AM
mfw
 
ToTheSun!'s Avatar
 
Join Date: Jul 2011
Location: Terra
Posts: 8,499
Rep: 521 (Unique: 240)
Quote: Originally Posted by guttheslayer View Post
If this chip came out 2 years earlier, it will make V100 look real bad.
If my grandma had balls, she'd be my granddad.

CPU
Intel 6700K
Motherboard
Asus Z170i Pro Gaming
GPU
Gigabyte 2070 Super Windforce OC
RAM
G.skill Trident Z 3200CL14 8+8
Hard Drive
Samsung 850 EVO 1TB
Hard Drive
Crucial M4 256GB
Power Supply
Corsair SF600
Cooling
Noctua NH C14S
Case
Fractal Design Core 500
Operating System
Windows 10 Education
Monitor
ViewSonic XG2703-GS
Keyboard
Vortex Race 3 RGB
Mouse
Glorious Model O Glossy White v2.0
Mousepad
SteelSeries QcK+
Audio
Fiio E17K v1.0 + Beyerdynamic DT 1990 PRO (Dekoni pads)
▲ hide details ▲
ToTheSun! is offline  
Sponsored Links
Advertisement
 
post #14 of 15 (permalink) Old 07-19-2020, 10:20 AM
LTSC for life crew
 
speed_demon's Avatar
 
Join Date: Nov 2006
Location: Wisconsin
Posts: 2,732
Rep: 158 (Unique: 108)
Lol.

Seems like there are a few companies actively developing AI compute products like the one in the OP. Must be where the big bucks are these days.

CPU
Ryzen 1600 AF
Motherboard
MSI X470 Gaming Plus
GPU
MSI R9 390 8GB
RAM
16GB DDR4-3000
Hard Drive
120GB HP M700 SSD
Hard Drive
Samsung Spintpoint M9T 2TB
Hard Drive
Seagate Barracuda 500GB
Power Supply
Corsair HX1200 (2017)
Cooling
Thermalright True Spirit 140
Case
Fractal Define S
Operating System
Windows 10 LTSC
Keyboard
Alienware W/Cherry MX Switches
Mouse
Logitech G5
▲ hide details ▲


speed_demon is offline  
post #15 of 15 (permalink) Old 07-19-2020, 10:27 AM
sudo apt install sl
 
Join Date: Dec 2009
Posts: 7,038
Rep: 197 (Unique: 133)
Quote: Originally Posted by speed_demon View Post
Lol.

Seems like there are a few companies actively developing AI compute products like the one in the OP. Must be where the big bucks are these days.
Exactly, it's the reason why AMD released Instinct cards and ROCm in 2016 Intel is pushing AVX-512, making GPUs and purchased Habana.

Titan/GeForce cards are dirt cheap compared to all the other options though. Nvidia caught on and banned GeForce drivers in the data center along getting rid of the blower style heatsinks.

Silent
(20 items)
CPU
Core i9 9900K... CoffeeTime! @ 5.1Ghz w/ 1.36v
Motherboard
Maximus VIII Formula
GPU
Titan RTX @ 2100Mhz/2075Mhz
RAM
TeamGroup Xtreem 32GB 3200Mhz CL15
Hard Drive
HP EX950 2TB
Hard Drive
Samsung 850 Evo 1TB
Hard Drive
Samsung 850 Evo 1TB
Power Supply
EVGA SuperNova 1200w P2
Cooling
EK Supremacy Full Copper Clean
Cooling
XSPC D5 Photon v2
Cooling
Black Ice Gen 2 GTX360 x2
Cooling
EK-Vector RTX RE Ti - Copper + Plexi
Case
Thermaltake Core X5 Tempered Glass Edition
Operating System
Solus Linux
Monitor
Acer XF270HUA
Keyboard
Cherry MX Board 6.0
Mouse
Logitech G600
Mouse
Alugraphics GamerArt
Audio
Definitive Technology Incline
Audio
SMSL M8A
▲ hide details ▲

Last edited by WannaBeOCer; 07-19-2020 at 10:32 AM.
WannaBeOCer is online now  
Reply

Quick Reply
Message:
Options

Register Now

In order to be able to post messages on the Overclock.net - An Overclocking Community forums, you must first register.
Please enter your desired user name, your email address and other required details in the form below.
User Name:
If you do not want to register, fill this field only and the name will be used as user name for your post.
Password
Please enter a password for your user account. Note that passwords are case-sensitive.
Password:
Confirm Password:
Email Address
Please enter a valid email address for yourself.
Email Address:

Log-in



Currently Active Users Viewing This Thread: 1 (0 members and 1 guests)
 
Thread Tools
Show Printable Version Show Printable Version
Email this Page Email this Page


Forum Jump: 

Posting Rules  
You may post new threads
You may post replies
You may not post attachments
You may not edit your posts

BB code is On
Smilies are On
[IMG] code is On
HTML code is Off
Trackbacks are Off
Pingbacks are Off
Refbacks are Off