Become a fan of Slashdot on Facebook

 



Forgot your password?
typodupeerror

Comment Facebook Says Thanks! (Score 1) 98

Fine, you think you've got a cozy little electronic commons where everything will be unicorns and rainbows if we are all just willing to show our beautiful selves to one another. In the meantime, Facebook and its partners are making bank data mining your junk and marketing to you. And they say, "Thanks!"

Comment Summary Incorrect (Score 0) 290

The B-52 did not "[drop] the first hydrogen bomb in the Bikini Islands in 1956" as the summary states. The first hydrogen bomb was much too heavy to fly, resembling a locomotive in size and weight. "Ivy Mike" was the first hydrogen bomb tested, detonated by the United States at Enewetak Atoll on November 1, 1952. It weighed 80 tons and yielded about 10 megatons.

Comment Re:Visual Studio RT? No. (Score 1) 182

So more busted old shit is constantly created and ported to the current MS platform to become the new 'busted old shit' that people need to be able to run on new machines.

Interesting. This makes me think that Apple may have discovered the "secret sauce", albeit accidentally. With each processor transition, Apple has provided a compatibility window that slammed shut at a point in time not too far from the transition; but, far enough to satisfy the vast majority of their customers. The Intel transition featured Rosetta, for a while (until 10.6), then dropped it. This effectively flushed the 'busted old shit' straight down the pipes.

Comment Re:Amdahl's Law (Score 1) 281

Gene Amdahl and Fred Brooks were both important players at IBM, each making essential contributions to the System 360. That's an interesting connection between MMM and Amdahl's law, undoubtedly they talked.

As for TFA, misquoting Al Swearengen, "someone open a window, it smell like cat piss in here."

Comment Re:A gap not normally considered (Score 1) 92

Good idea. So good, in fact, you're getting close to how it's actually done: data is moved in parallel in bulk. For example, when your program accesses an 8-bit byte, the 256-bit (or larger) chunk (called a cache line containing it gets read from DRAM into cache. There is no address space sacrifice because once the cache line is read, additional logic selects the desired byte from the cache line using the low-order bits of the address.

Comment Re:How do people optimise their designs? (Score 1) 213

You kids make me feel really old. My first assembly language was written for the IBM 1130. It unloaded an IBM 2315 disk cartridge (512k x 16 bit word) to punched cards. It chewed up about 1/3 less cards than the IBM supplied utility, and so ran about 1/3 faster, the limiting factor being the speed of the card punch.

Comment Re:Faster..? (Score 3, Informative) 85

Absolutely. Another huge problem is skew, where dissimilar wire lengths result in signals (for example, the bits making up a word) arriving at their destination at different times. This is not a problem exclusive to integrated circuits: Seymour Cray addressed this problem in the CDC 6600 (circa 1964, discrete Si transistors) by using wires of identical lengths for interconnections. If you look for a photo of the CDC 6600 back plane, you'll readily see what I mean.

Comment Williams Tube Memory (Score 4, Informative) 85

Could this not be done the same way CRTs scan a grid of pixels, just on a micro scale with higher resolution?

This reminds me of an early computer memory, the Williams tube, that enjoyed a brief period of popularity in some first generation machines. It worked by storing bits as charged spots on the phosphor face plate of an oscilloscope tube. Although access was random and fast (12 microsecond read/write cycle as implemented by the IBM 701), its refresh requirements effectively halved its performance, and it was notoriously unreliable. Positioning the electron beam was by electrostatic deflection, requiring accurate sub-microsecond switching of high voltages. IBM's implementation used precision counter-wound resistors to achieve the required control, the counter-winding preventing the resistors from also behaving like inductors. Unfortunately, the counter-winding also led to occasional electrical arcing inside the resistors, mispositioning the beam and causing the "Navajo Blanket" effect where the resulting data corruption had a visual appearance like its namesake woven blanket. Error-free operation seldom exceeded a handful of hours, and the Williams tube was quickly supplanted by magnetic core memory.

Slashdot Top Deals

10.0 times 0.1 is hardly ever 1.0.

Working...