|
Yeah, when the measurements are "a data center's worth" and "refrigerator-size" it's time to move on.
|
|
|
|
|
Computer rack (a refrigerator-sized machine) filled data-center room will be replaced by a refrigerator-sized machine filled room with much higher performance. I think it's usually called an upgrade.
|
|
|
|
|
Having read the article, what it is is HP's R&D doubling down on memristors; if they fulfill their promise of creating SSD non-volatile sized storage with DRAM speed, a dozens or hundreds to one condensation of IO bound servers is plausible. I suspect most applications would end up on the lower end of the range; the memristers might be 100x faster, but that much speedup would end up making lots of tasks that were IO bound become bottle necked on something else (compute, network, etc).
Edit: For reference, early SSDs were maybe 10x faster than HDDs in random IO (~2x as fast in sequential IO); and often generated 2-4:1 server count reductions for IO bound servers in data centers. Potential rackspace savings were often larger, since many of the servers targeted in early switchovers had very large disk arrays to boost IO parallelism (not capacity) as much as possible allowing a single SSD to replace 5 or 10 HDDs (the hdds only had tiny partitions to minimize seek time, leaving most of the drive empty). In practice, like with virtualization, they were often less as increased power density meant that the racks couldn't be fully packed without facility upgrades.
Did you ever see history portrayed as an old man with a wise brow and pulseless heart, waging all things in the balance of reason?
Is not rather the genius of history like an eternal, imploring maiden, full of fire, with a burning heart and flaming soul, humanly warm and humanly beautiful?
--Zachris Topelius
Training a telescope on one’s own belly button will only reveal lint. You like that? You go right on staring at it. I prefer looking at galaxies.
-- Sarah Hoyt
modified 11-Jun-14 17:07pm.
|
|
|
|
|
"One meeelyun dollars."
You'll never get very far if all you do is follow instructions.
|
|
|
|
|
Decima Technologies bought a few early prototypes to run Samaritan...
|
|
|
|
|
Figures from the Linux Foundation suggest skills shortages across disciplines and throughout Europe. Your latest in "Company funds study showing company's product loved"
|
|
|
|
|
ZDNet wrote: Seven out of 10 Europe-based Linux professionals have received calls where they were pitched new positions in the past six months, and a third said they had received more calls than in the previous six months. Well, there is the problem. There is only 10 Linux professionals in all of Europe.
|
|
|
|
|
Following broad security scares like that caused by the Heartbleed bug, it can be frustratingly difficult to find out if a site you use often still has gaping flaws. But a little known community of software developers is trying to change that, by creating a searchable, public index of websites with known security issues. I'm sure nothing bad will come of this
|
|
|
|
|
Here's a list with all houses that don't have a decent lock..
Bastard Programmer from Hell
If you can't read my code, try converting it here[^]
|
|
|
|
|
Google announced a suite of tools this morning for business owners, offering them a one-stop shop to update their business information, add photos, read and reviews and, of course, use Google+. Be a shame if no one could find your business, eh squire?
|
|
|
|
|
The new programming language is not faring well in some benchmarks compared to Objective-C, but Swift's easier syntax still gets a thumbs-up. There are four kinds of lies: Lies, damned lies, statistics, and benchmark tests.
|
|
|
|
|
Quote: Without leveraging optimizations in Apple's Xcode tool set, Splasm found that Swift was between six and 40 times slower than Objective-C, Splasm official Keith Gugliotto said. "
...
Even after turning on the optimizations, Splasm found that Swift ran 10 to 20 percent slower than the original test numbers in some cases and 10 to 20 percent faster in other cases. But Swift was still slower than Objective-C.
0) Benchmarks without the compiler optimizations turned on are worthless. The only value this have is as clickbait. Oh wait...
1) Do "original test numbers" refer to the objective C benchmarks or the un-optimized swift benchmarks? That's a huge difference in performance between the two but the article doesn't tell you which or give an easy way to find out because...
2) It breaks the cardinal rule of web news by talking about splasm's benchmarks but not linking to them.
Splasm's benchmarks[^] are Googleable though. Enabling optimization to both builds resulted in order of magnitude shifts in relative performance; but the closest swift ever came to obj-C was 6.4x slower.
With Android using Java that's only ~2x slower than native code in typical cases, unless Apple can make some really big optimization gains to the toolchain their newest and shinyest has performance poor enough that they risk the internet snark gallery abusing iOS apps as being slow and laggy compared to the competition in the future.
Did you ever see history portrayed as an old man with a wise brow and pulseless heart, waging all things in the balance of reason?
Is not rather the genius of history like an eternal, imploring maiden, full of fire, with a burning heart and flaming soul, humanly warm and humanly beautiful?
--Zachris Topelius
Training a telescope on one’s own belly button will only reveal lint. You like that? You go right on staring at it. I prefer looking at galaxies.
-- Sarah Hoyt
|
|
|
|
|
If it doesn’t benefit the user it should not be done. This can be a new feature, a better user interface, a clearer wording, better performance, robustness, … Not all improvements have immediate value but they must have a value at some time. Coders of the world, unite!
|
|
|
|
|
Hmm, spending a day refactoring code doesn't benefit the user, but it sure as hell benefits the developer, sometimes halfing their Gin intake, isn't that important?
|
|
|
|
|
Halfing Gin intake is a good thing?
I say, "NO" good sir!
TTFN - Kent
|
|
|
|
|
Aren't the people who work at the distillery users?
Did you ever see history portrayed as an old man with a wise brow and pulseless heart, waging all things in the balance of reason?
Is not rather the genius of history like an eternal, imploring maiden, full of fire, with a burning heart and flaming soul, humanly warm and humanly beautiful?
--Zachris Topelius
Training a telescope on one’s own belly button will only reveal lint. You like that? You go right on staring at it. I prefer looking at galaxies.
-- Sarah Hoyt
|
|
|
|
|
Blog sez: You need to talk to your users, your fellow developers and other project partners. That's assuming that the end-user has strong analytical skills and knows the entire proces. In SDM one researches what the user needs, as opposed to asking what he/she wants that week.
..now here[^]'s a manifesto.
Bastard Programmer from Hell
If you can't read my code, try converting it here[^]
|
|
|
|
|
When Google engineers John Sirois, Travis Crawford, and Bill Farner left the internet giant and went to work for Twitter, they missed Borg.
Borg was the sweeping software system that managed the thousands of computer servers underpinning Google’s online empire. With Borg, Google engineers could instantly grab enormous amounts of computing power from across the company’s data centers and apply it to whatever they were building–whether it was Google Search or Gmail or Google Maps. As Sirois, Crawford, and Farner created new web services at Twitter, they longed for the convenience of this massive computing engine. "Freedom is irrelevant. Self-determination is irrelevant. You must comply."
|
|
|
|
|
First Skynet, now the Borg. Sheesh! There's no messing with them.
|
|
|
|
|
Microsoft is among the many cloud and Linux vendors supporting the first release of the open-source Docker application-deployment engine. Uhm. Yay?
|
|
|
|
|
New data reveals in which countries developers make the most money, and where they can most live like royalty. Unfortunately, you get paid in chocolate (and cuckoo clocks)
Sorry for the national stereotype.
Yes. That was another national stereotype. Thanks for noticing, eh.
|
|
|
|
|
I went to Switzerland once. I have never since felt so poor...nor so individual.
|
|
|
|
|
I thought that might be the case: high salary, but higher prices?
TTFN - Kent
|
|
|
|
|
Those dollar incomes were calculated with the market exchange rate. One Swiss Franc is exchanged to more than one US Dollar. But go shopping in Switzerland and the US: you'll see that one Swiss Franc buys far less in Switzerland than does one US Dollar in the US. That holds extremely true for items/services produced locally, like food at a restaurant or housing.
|
|
|
|
|
Quote: To make the most money as a software engineer, move to Switzerland Singapore
FTFY.
Don't mind those people who say you're not HOT. At least you know you're COOL.
I'm not afraid of falling, I'm afraid of the sudden stop at the end of the fall! - Richard Andrew x64
|
|
|
|