| ActiveMac | Anonymous | Create a User | Reviews | News | Forums | Advertise |
|
|
|
User Controls |
|
New User |
|
Login |
|
Edit/View My Profile |
|
|
|
|
|
|
|
ActiveMac |
|
Articles |
|
Forums |
|
Links |
|
News |
|
News Search |
|
Reviews |
|
|
|
|
|
|
|
News Centers |
|
Windows/Microsoft |
|
DVD |
|
ActiveHardware |
|
Xbox |
|
MaINTosh |
|
News Search |
|
|
|
|
|
|
|
ANet Chats |
|
The Lobby |
|
Special Events Room |
|
Developer's Lounge |
|
XBox Chat |
|
|
|
|
|
|
|
FAQ's |
|
Windows 98/98 SE |
|
Windows 2000 |
|
Windows Me |
|
Windows "Whistler" XP |
|
Windows CE |
|
Internet Explorer 6 |
|
Internet Explorer 5 |
|
Xbox |
|
DirectX |
|
DVD's |
|
|
|
|
|
|
|
TopTechTips |
|
Registry Tips |
|
Windows 95/98 |
|
Windows 2000 |
|
Internet Explorer 4 |
|
Internet Explorer 5 |
|
Windows NT Tips |
|
Program Tips |
|
Easter Eggs |
|
Hardware |
|
DVD |
|
|
|
|
|
|
|
Latest Reviews |
|
Applications |
|
Microsoft Windows XP Professional |
|
Norton SystemWorks 2002 |
|
|
|
Hardware |
|
Intel Personal Audio Player 3000 |
|
Microsoft Wireless IntelliMouse Explorer |
|
|
|
|
|
|
|
Site News/Info |
|
About This Site |
|
Affiliates |
|
ANet Forums |
|
Contact Us |
|
Default Home Page |
|
Link To Us |
|
Links |
|
Member Pages |
|
Site Search |
|
Awards |
|
|
|
|
|
|
|
Credits |
 |
Windows 7 on multicore: How much faster? | |
|
||
| Time: 13:56 EST/18:56 GMT | News Source: Yahoo News | Posted By: Kenneth van Surksum | ||
|
Microsoft's Windows 7 operating system is receiving raves in its pre-release testing. While much of the kernel that lies at the heart of the operating system is based on Vista code, several key advances have been made that get rid of Vista annoyances and greatly improve the user experience. Inside the kernel, one important change centers on how multithreaded applications are run. The threading advances provide benefits in energy reduction, scalability, and, in theory, performance. | ||
|
Write Comment
Return to News |
Displaying 1 through 25 of 437 Last | Next |
The time now is
4:58:41 PM
ET.
Any comment problems? E-mail us |
| #1 By 7754 (206.169.247.2) at 10/20/2009 4:14:32 PM |
|
There seems to be some major confusion in this article. SMT is the same as Intel's "hyperthreading," which is not analogous to SMP. Also, SMT is not the same as Turbo Mode (dynamic overclocking with a twist of lime), and it's not clear exactly what the author's understanding is of that--it looks like he may equate SMT with Turbo Mode.
A better example would be to compare a dual-core vs. a quad-core, or to take a quad-core machine and disable two (or more cores) and re-run the benchmarks. |
| #2 By 23275 (68.117.163.128) at 10/20/2009 5:46:27 PM |
| #1, a big influence over Intel's Turbo Mode depends upon the MB manufacturer and their implementations, and not all MB's form the same manufacturer implement it consistently, or as effectively from board to board. Ideally, Turbo Mode allows single threaded apps to clock a CPU higher to take fuller advantage of the proc's potential. |
| #3 By 15406 (99.240.77.173) at 10/20/2009 6:17:07 PM |
|
Back in the day, Turbo mode meant the button on the front of your system that boosted it from 4.77 MHz to 8 MHz (PC-XT), or 8 MHz to 12 MHz (PC-AT).
How the times have changed. |
| #4 By 20505 (216.102.144.11) at 10/20/2009 6:56:52 PM |
| So Latch, I guess I'm not the only old dog who hangs around here. |
| #5 By 13997 (68.118.60.164) at 10/20/2009 8:33:28 PM |
|
#4 Sadly nope... I remember 16K being huge years before the amazing Turbo button.
Again this article has major flaws, but sadly it is one of the 'better' articles technically I have seen in a long time, and yet it still mixes up the basic concepts of SMP and even how the locking mechanisms work. You would think with the economy there would be some old timers that actually understand the techology out there willing to write solid techincal articles. I know things are vastly complex compared to 5, 10, 15, 20, 25 years ago, but there is no excuse for the level of technical articles that don't exist. The first thing I always did in teaching was start everyone out with 'history' of the subject I was teaching, so that even an assembly class would have to learn about CPU architecture going back to long before they were born, why it was important now, and how it affects computing today. I'm kind of an 'olddog' that is getting tired of the lack of technical understanding in the journalistic side of computing of late. There is no excuse for even one good editor or 'friend' reviewing or fact checking some of these articles or blogs. Some of these horrible articles and their errors can be referenced on Wiki even, and Wiki is horrid when it comes to technical accuracy/understanding. This post was edited by thenetavenger on Tuesday, October 20, 2009 at 20:34. |
| #6 By 15406 (99.240.77.173) at 10/20/2009 9:02:12 PM |
| I remember when ATI was a dinky Canadian company that sold one product, the Graphic Solution. It let you play CGA colour games on a TTL monochrome monitor. Back then I was building and selling clones. My first hard disk was 5 MB Miniscribe. |
| #7 By 20505 (216.102.144.11) at 10/20/2009 9:15:42 PM |
|
#5
Perhaps I'm a critic but, what passes for "journalism" is quite frankly shameful. This is a matter that does not just affect technical/scientific reporting. Moreover, it seems to be getting worse with the democratization of media via the internet. More and more the sensational is glorified to "grab eyeballs" at the expense of accurate reporting. The problem, as I see it, is compounded by commercial and political interests which become more invasive by the day. The effect is corrosive and at some point you just stop believing what you read. Now, where did I put the password for my bomb shelter? |
| #8 By 23275 (68.117.163.128) at 10/20/2009 9:52:56 PM |
|
I recall manually loading "baskets" - the metal dies we used to load character sets, which provided readable text vice Baudot code, or undulator tape - signal inscribed on gummed paper. Programs were written that one day we expected we would be able to run on computers that didn't exist yet. Mountains of graph paper and cans of pencils were the primary tools of the trade. It would be 20 years before the first tapes entered service and like flight engineers, teams of people would operate 'parts' of a computer.
Interestingly, nothing new, as it emerged, was much of a surprise - it was all expected and designed and visualized decades before things became so much as a prototype. The most interesting thing one embraces as they get "old" is their own irrelevance - where the world changes rather slowly and in predictable ways. Technical, political, and journalistic theorists think it is all "new" when none of it is and the underlying philosophies upon which behaviors and policies are based, are all too familiar. I've seen and heard all the arguments before as once again the world embraces socialism and pretends that this time they'll get it right. The only question that remains is how many millions of lives it will cost this time - sadly it seems that the numbers are low it will be in the billions. It feels as much like 37 as it did 77 and in very similar ways. All the old words are there - just change the dates. This time there is no Churchill, or America to fall back on as we witness the latest attempt to re-colonize the US and much of the world. That's all this is. This time they may succeed and if they do, count on another thousand years of darkness. I send TINA. If you know what that means, you're old enough to share a grin with an old man. |
| #9 By 230538 (74.219.160.9) at 10/21/2009 7:05:06 AM |
|
#3 Latch:
Don't forget the LED which lit when you were running in Turbo mode. Things would be running "slow", look down and then realize that the LED was off and you weren't in turbo mode. Turbo mode ahhhh, so much better and faster.. ha-ha.. |
| #10 By 15406 (216.191.227.68) at 10/21/2009 8:13:29 AM |
| #9: I glued a million of those (green for power, red for hard disk, yellow for turbo) onto the case using Krazy Glue. You even had to hand wire the power supply to the on/off switch. Stuff the board with a ton of little RAM chips with oh-so-easy-to-break pins. Set a dozen little jumpers on the mainboard or it wouldn't work right. Math coprocessors cost over $1000 and didn't have a keyed socket so it was extremely easy to plug it in wrong and fry it. Those were the days. |
| #11 By 143 (96.28.65.208) at 10/21/2009 1:15:16 PM |
| I remember when the earth was flat. lol |
|
Write Comment
Return to News |
Displaying 1 through 25 of 437 Last | Next |
The time now is
4:58:41 PM
ET.
Any comment problems? E-mail us |
