Forgot your password?
typodupeerror

Comment: Re:FPGAs ... (Score 1) 118

by Jepler (#34749982) Attached to: Researchers Claim 1,000 Core Chip Created

Indeed. 1000 simple CPUs will fit in a FPGA, though it might require one near the top of the line. (e.g., picoblaze reportedly needs 96 "slices" and 1.5 "block RAMs"; the biggest Virtex-7 FPGA has more than 1400x as many block RAMs and 3100x as many "slices") There's little doubt that you could program a DCT for a picoblaze, if you wanted to.

It's hard to tell what 5.0GBps refers to -- the bitrate of the incoming, uncompressed, RGB video data? If so, that's maybe about 800FPS of 1080P video. In a circa 2002 paper, FPGAs were doing 100FPS HDTV DCT; an improvement of only a factor of 8 in the intervening 8 years would be frankly disheartening. Especially given that DCT of a frame of video is embarassingly parallel. The FPGA I mentioned earlier could hold 180 copies of the DCT from this paper; right there you have 18kFPS without even raising the clock. But the multipliers can probably also be clocked faster now...

Comment: Re:What about an all core chip? (Score 1) 118

by Jepler (#34749692) Attached to: Researchers Claim 1,000 Core Chip Created

You've just described the FPGA. Large areas of an FPGA are devoted to thousands of almost-identical functional blocks ("slices" in xilinx parlance). For instance, in one Xilinx family, a slice contains a 4-input LUT, a flip-flop (1 bit of memory, called an FF), and other specific gates that help implement things like carry chains, shift registers, and some 5+input functions the chip designers thought were commonly encountered.

Other areas contain "block RAMs" and "DSP cores" (basically, dedicated multipliers).

But now you've got yourself a lot of hard problems to solve: how to dice a program into something that is represented by essentially LUTs and FFs. how to recognize when a special function outside the LUT, like a carry chain, should be used. how to efficiently route the signals from where they're produced to where they're consumed. how to actually implement an efficient LUT where the contents are field-programmed. how to figure figure out what speed to clock the whole thing at so that it operates properly. how to read in the configuration to the chip. This is an enormous investment in research and software, and you still have to target the chip with languages that are totally alien to your typical C/C++ programmer.

As far as I know there is no production FPGA that you can write software for without using proprietary software. (though often the software can be obtained at no cost, at least for the non-flagship FPGA chips) This is partially because the details of bitstream structure are trade secrets of the respective FPGA companies, but also partially due to the inherent difficulty of the task.

Mozilla

Mozilla Plans Mobile App Store 118

Posted by samzenpus
from the one-of-many dept.
dkd903 writes "Mozilla wants to make it big in the Mobile world and has revealed its plans for a unique mobile app store in its annual report — 'The State of Mozilla,' which was released recently. Mozilla has already brought the desktop Firefox experience to mobile devices as the Fennec browser, which was initially launched for the Maemo platform on Nokia N900. Mozilla has designed a prototype of a mobile app store and plans to call it a 'Open Web App ecosystem.' The aim is to create an open app store platform that would consist of apps that can run on all mobile devices: — A 'Mobile Device Independent' App Store."
Technology

New Microscope Reveals Ultrastructure of Cells 58

Posted by samzenpus
from the no-glasses-needed dept.
An anonymous reader writes "For the first time, there is no need to chemically fix, stain or cut cells in order to study them. Instead, whole living cells are fast-frozen and studied in their natural environment. The new method delivers an immediate 3-D image, thereby closing a gap between conventional microscopic techniques. The new microscope delivers a high-resolution 3-D image of the entire cell in one step. This is an advantage over electron microscopy, in which a 3-D image is assembled out of many thin sections. This can take up to weeks for just one cell. Also, the cell need not be labeled with dyes, unlike in fluorescence microscopy, where only the labeled structures become visible. The new X-ray microscope instead exploits the natural contrast between organic material and water to form an image of all cell structures. Dr. Gerd Schneider and his microscopy team at the Institute for Soft Matter and Functional Materials have published their development in Nature Methods (abstract)."
Biotech

Central Dogma of Genetics May Not Be So Central 196

Posted by Soulskill
from the can-we-blame-aol-for-this dept.
Amorymeltzer writes "RNA molecules aren't always faithful reproductions of the genetic instructions contained within DNA, a new study shows (abstract). The finding seems to violate a tenet of genetics so fundamental that scientists call it the central dogma: DNA letters encode information, and RNA is made in DNA's likeness. The RNA then serves as a template to build proteins. But a study of RNA in white blood cells from 27 different people shows that, on average, each person has nearly 4,000 genes in which the RNA copies contain misspellings not found in DNA."
Advertising

Did Google Go Instant Just To Show More Ads? 250

Posted by Soulskill
from the faster-than-the-speed-of-marketing dept.
eldavojohn writes "Google, already the largest search engine in the United States, went instant a few weeks ago. MIT's Tech Review asks why Google went instant and is skeptical that users actually look at search results before they finish typing their query. Othar Hansson, Google's lead on the initiative, informs them otherwise and claims that Google's traffic monitors didn't even blink at the extra data being sent across — primarily because of its insignificance next to streaming one video on YouTube. Hansson also reveals that Google's search engine is no longer stateless and therefore takes up a little more memory in their server hives. The Tech Review claims that 'sources at the company say Google Instant's impact on ad sales was a primary focus in testing the service. Google only gets paid for an advertisement, or sponsored link, when a user clicks on the ad, and ads are targeted to specific searches. By displaying a search's ads onscreen a couple of seconds sooner, the frequency of users clicking on those ads could only go up.' So money seemed to be the prime motivator and the article also coyly notes that the average length of time a user spends between typing in any two characters is 300 milliseconds — much too fast for old JavaScript engines. Of course, you might recall Google's efforts to change all that with JavaScript speed wars. Do you find Google Instant to be useful in any way, or does it strike you as just more ad gravity for your mouse?"
Image

Gubernatorial Candidate Wants to Sell Speeding Passes for $25 825 Screenshot-sm

Posted by samzenpus
from the pay-to-play dept.
If Nevada gubernatorial candidate Eugene "Gino" DiSimone gets his way, $25 will buy you the right to drive up to 90mph for a day. DiSimone estimates his "free limit plan" will raise $1 billion a year for Nevada. From the article: "First, vehicles would have to pass a safety inspection. Then vehicle information would be loaded into a database, and motorists would purchase a transponder. After setting up an account, anyone in a hurry could dial in, and for $25 charged to a credit card, be free to speed for 24 hours."
Data Storage

Israeli Startup Claims SSD Breakthrough 159

Posted by kdawson
from the believe-in-what-you-write dept.
Lucas123 writes "Anobit Technologies announced it has come to market with its first solid state drive using a proprietary processor intended to boost reliability in a big way. In addition to the usual hardware-based ECC already present on most non-volatile memory products, the new drive's processor will add an additional layer of error correction, boosting the reliability of consumer-class (multi-level cell) NAND to that of expensive, data center-class (single-level cell) NAND. 'Anobit is the first company to commercialize its signal-processing technology, which uses software in the controller to increase the signal-to-noise ratio, making it possible to continue reading data even as electrical interference increases.' The company claims its processor, which is already being used by other SSD manufacturers, can sustain up to 4TB worth of writes per day for five years, or more than 50,000 program/erase cycles — as contrasted with the 3,000 cycles typically achieved by MLC drives. The company is not revealing pricing yet."
Linux

Adobe (Temporarily?) Kills 64-Bit Flash For Linux 272

Posted by Soulskill
from the how-rude dept.
An anonymous reader writes "It seems that with the release of the 10.1 security patches, Adobe has, at least temporarily, killed 64-bit Flash for Linux. The statement says: 'The Flash Player 10.1 64-bit Linux beta is closed. We remain committed to delivering 64-bit support in a future release of Flash Player. No further information is available at this time. Please feel free to continue your discussions on the Flash Player 10.1 desktop forums.' The 64-bit forum has been set to read-only."
Communications

Twitter API ToS To Force Routing Clicks To Twitter 92

Posted by CmdrTaco
from the too-big-for-their-britches dept.
An anonymous reader writes "Twitter has announced that it will change the way it handles URLs in tweets. This has been widely reported, including the likely consequences for bit.ly. What has not received much attention, and was not in the official blog announcement (but in the Google Twitter developers mailing list instead) is that the Terms of Service for all applications that use the Twitter API will be changed to require that any click on a URL in a tweet be routed through a Twitter gateway, allowing Twitter to see exactly which links are followed and by whom."
Cellphones

The Shortcomings of Google's Open Handset Alliance 208

Posted by Soulskill
from the modeled-off-the-un dept.
eldavojohn writes "Former T-Mobile and Apple executive Leslie Grandy reports some pretty harsh words about Google's Open Handset Alliance. We've heard grumblings before about control in open source projects, but now an unnamed former leader of an OHA member company is calling the OHA 'oligarchical,' and said, 'The power is concentrated with the Google employees who manage the open source project. The Open Handset Alliance is another myth. Since Google managed to attract sufficient industry interest in 2008, the OHA is simply a set of signatures with membership serving only as a VIP Club badge.' But what privileges do they have? Not many. The OHA's problems don't stop there; Grandy maintains that 'many OHA members are developing proprietary user experiences, which they are not contributing back into Android — as is standard for open source projects — for fear of losing competitive advantage in the marketplace.' She goes on to paint the OHA as toothless and directionless, with a nearly abandoned message board. It's been around for almost three years, and while Android has become more prevalent, the OHA's contributions seemingly have not. Do you agree that the OHA has amounted to nothing but a checkbox for manufacturers?"
Biotech

"Vegetative State" Patients Can Communicate 347

Posted by samzenpus
from the hello-in-there dept.
Kittenman writes "The BBC is carrying a story about researchers in the UK and Belgium who can detect the thinking processes within a patient previously thought to be in a vegetative state. The researchers ask the patient verbally to think in certain ways to indicate a 'yes', in other ways to indicate a 'no' — and have successfully communicated with 4 out of 23 patients previously thought to be in a coma."

Today's scientific question is: What in the world is electricity? And where does it go after it leaves the toaster? -- Dave Barry, "What is Electricity?"

Working...