Breaking News
Newest First | Oldest First | Threaded View
Page 1 / 2   >   >>
User Rank
Micron Automata Processor
rhfish   12/6/2013 4:05:04 PM
The Micron AP is a pretty important innovation.  

If Micron marketing does its job, in 3 or 4 years there will be an AP chip in every cell phone and tablet offloading facial and speech recognition.  There will be multiple AP chips in every new automobile for collision avoidance.  Finally, every robot, drone, and autonomous device will have a handfull.  These things will cost about $2 each if the die sizes are to be believed.

The AP is not a computer even though Micron claims it is a processor.  It is a computer peripheral, more like a GPU for patterns.  There will never be thousands of programmers coding for it.  Rather there will be a set of state libraries to perform common API functions.

They do seem to have adopted the processor on DIMM technique we proposed about 6 years ago for our CPU in DRAM.

Russell Fish
CTO, Venray

Caleb Kraft
User Rank
Re: Cool processors we can't program
Caleb Kraft   11/25/2013 2:14:31 PM
That is absolutely a good point. As much as I love seeing these pop up, I can't say I've seen anything else on most of them after the initial hoopla.

Caleb Kraft
User Rank
Re: Any update on Micron's Hybrid Memory Cube
Caleb Kraft   11/25/2013 2:13:12 PM
Aw man, I wish I could have seen that!

User Rank
architecture of an AP vs CPLD
Sanjib.A   11/25/2013 11:24:42 AM
Don't know much about Automata Processor (AP)...please forgive me for a novice question. "Its design is based on an adaptation of memory array architecture"...sounds more like an architecture similar to that of a does a AP architecture compare to that of a CPLD or FPGA?

rick merritt
User Rank
Cool processors we can't program
rick merritt   11/25/2013 10:20:24 AM
I've lost count of how many novel and ground breaking parallel processors I've written about in 20 years at EE Times that have died quiet deaths because no one could write code for them. Is this any different?

User Rank
ckachris   11/25/2013 8:35:56 AM
According to the article, the AP architecture is data-flow based. In the past, dataflow architecture was also proposed for network procesing applications (e.g. xelerated dataflow network processor) but the main challenge is the programming complexity and the programming restrictions of these architectures.

Also it looks similar to the transputer processors architecture that were targetting parallel computing. 

However, this automata processor seems to have included both an efficient programming framework/SDK and an efficient silicon implementation.

User Rank
the sweet spot for parallel processing
DrQuine   11/24/2013 3:02:05 PM
Processing big data sounds like an ideal application for parallel processing: huge quantities of data each of which nbeed to be processed through the same algorithms.  I used a massively parallel processor (32,000 processors as I recall) in 1979 for image processing and was amazed at the work that could be done with just a 1 MHz clocked system. The pixels in images are just a special case of big data.

User Rank
Re: Does anyone proofread this stuff?
Araucaria   11/24/2013 6:54:21 AM
Also "Automata has been in development for seven years, spurned by customer requests". Did they spurn the customer's requests?? Do they mean "spurred on by customer requests"?

User Rank
A new way of accessing memories
Kinnar   11/24/2013 5:16:10 AM
At most it is a new way of accessing the memories, in digital systems dealing with data is nothing but dealing with memories, Big Data Problems still demands a universal way to handle any problem associated with it, but still this solutions if claiming good results in certain directions, let's see how much it actually becomes effective.

Derick Carmen
User Rank
Re: Any update on Micron's Hybrid Memory Cube
Derick Carmen   11/23/2013 10:12:16 PM
I am thankful for the newest ideas they introduced. This way they could come up something better if successful and many can even adapt the ideas for betterment. - Derrick Strauss

Page 1 / 2   >   >> Parts Search

185 million searchable parts
(please enter a part number or hit search to begin)

What are the engineering and design challenges in creating successful IoT devices? These devices are usually small, resource-constrained electronics designed to sense, collect, send, and/or interpret data. Some of the devices need to be smart enough to act upon data in real time, 24/7. Are the design challenges the same as with embedded systems, but with a little developer- and IT-skills added in? What do engineers need to know? Rick Merritt talks with two experts about the tools and best options for designing IoT devices in 2016. Specifically the guests will discuss sensors, security, and lessons from IoT deployments.
Like Us on Facebook
Special Video Section
LED lighting is an important feature in today’s and future ...
The LT8602 has two high voltage buck regulators with an ...
The quality and reliability of Mill-Max's two-piece ...
Why the multicopter? It has every thing in it. 58 of ...
Security is important in all parts of the IoT chain, ...
Infineon explains their philosophy and why the multicopter ...
The LTC4282 Hot SwapTM controller allows a board to be ...
This video highlights the Zynq® UltraScale+™ MPSoC, and sho...
Homeowners may soon be able to store the energy generated ...
The LTC®6363 is a low power, low noise, fully differential ...
See the Virtex® UltraScale+™ FPGA with 32.75G backplane ...
Vincent Ching, applications engineer at Avago Technologies, ...
The LT®6375 is a unity-gain difference amplifier which ...
The LTC®4015 is a complete synchronous buck controller/ ...
The LTC®2983 measures a wide variety of temperature sensors ...
The LTC®3886 is a dual PolyPhase DC/DC synchronous ...
The LTC®2348-18 is an 18-bit, low noise 8-channel ...
The LT®3042 is a high performance low dropout linear ...