Slashdot Mirror

Anything starting with a 6 uses the same basic technology.

Only if you mean "generally (but not always) uses the same mask size", because that's about the only thing that stays similar on a AMD "series", especially if you compare everything from the Nx3x to the N99x models.

The 69xx series is radically differ from the 68xx series. A small snippet from the Tom's Hardware review:

Whereas the Barts GPUs used to build Radeon HD 6870 and 6850 centered on the same VLIW5 architecture that earned Radeon HD 5870 a place in infamy, the Cayman GPU consolidates functionality into a VLIW4 design, incorporating fewer ALUs per thread processor, but improving performance per square millimeter of die space.

There's more detail in the rest of the review.

As for the 6970 and 6950, they are AMAZING deals.

As single cards, they are OK, but AMD was suffering badly on tesselation benchmarks, and the 69xx series was supposed to be a lot better. Unfortunately, a pair of 6850s do better on tesselation benchmarks than the 6970.

With the 6970 MSRP running $10 more than actual pricing on a pair of 6850s, and the real world pricing of the 6970 likely to be higher for a while until demand is met, you're better off with the older cards. Also, if you are on a bit of a budget, the 6850 doesn't suck as a single card, but gives you the ability to upgrade later by adding a card.

Unless you have some sort of performance chart you can't tell shit.

http://www.videocardbenchmark.net/ gives a pretty comprehensive overview of just about every video card out there... this new AMD/ti video card will probably be added within the next few days. It's a great starting point before heading over to http://tomshardware.com/ or http://anandtech.com/ to read about all the details, caveats, and more comprehensive benchmark results.

Also, it tends to be the only good resource out there when trying to make comparisons between different market segments (what notebook GPU could keep up with my desktop GPU?) or completely different generations (would this cheap embedded GPU actually be a decent upgrade from my ancient media player box?)

It doesn't work with Western Digitals. I hate Western Digital.

A random discussion of this issue.

It's pretty obvious why from
http://www.tomshardware.com/reviews/radeon-hd-5970,2474-2.html

A 5970 is sorta like 2x 5870 chips SLI'd together on one board, and they had to downclock it slightly to make it stable. Yeah, the benchmark / driver doesn't appear to make use of the additional shader unit... but then that means most games probably don't either. But at least now you know where to go from here.

Hence I look at the videobenchmark.net rank first to get an overview.

Well this is using the exact logo, they've sued over far less infringing uses of apples in logos before - and arguably much more idiotic.

Right. The really interesting chips will arrive when you run between four and sixteen cores with the entirety of main RAM for those cores (in a NUMA configuration with other sockets, starting with maybe a gigabyte or so per die). You could then use SDRAM for both a paging file and for cache between the storage system and the processor/memory die.

You could map registers straight to portions of the on-chip memory if necessary for backwards compatibility. You'd probably be better off, though, compiling nearly everything to just use memory addressing. You'd only hit the SDRAM to load a new entire page into the on-chip RAM. On-chip cache and the circuitry to minimize misses in the cache could mostly go away, and the cores themselves could be simplified. You might even get away with moving the SDRAM controller back off-chip at first to free up some space on the die since the working memory would be so fast once the data was in it.

Unfortunately, this assumes billions of switches just for the main memory and probably quality control nightmares in the first several models.

However, it's the logical conclusion for the way forward. Caches keep taking more die space to deal with the fact that memory is so much slower than processors. Once you get over a certain size cache, you're just wasting circuitry on managing a large block of memory in little chunks that's better treated as a large single block of memory. The virtual to physical mapping already figures out what's in main RAM and what's out in the swap. Just let it do that with the on-die memory and eliminate the extra cache logic to make more on-die memory.

Intel has mentioned putting main memory on the die already. They even mentioned that they could do it with a form of DRAM rather than with SRAM.

OK, I'll bite.
http://en.wikipedia.org/wiki/AMD_K6
"The AMD K6 is based on the Nx686 microprocessor that NexGen was designing when it was acquired by AMD. Despite the name implying a design evolving from the K5, it is in fact a totally different design that was created by the NexGen team"

Also, it was more than competitive with the Intel processors of its time.
http://www.tomshardware.com/reviews/intel,22-10.html
The K6 was a turning point in the x86 wars, after which AMD slowly started taking the performance lead away from Intel with the Athlon, Athlon XP and Athlon 64, the latter having total dominance over Intel's competing Pentium 4.

For the record (and to avoid starting a flame war), the Core2 was the turning point where Intel started coming back, and Intel is currently firmly holding the performance lead with the Core i7.

Original announcement of the project:

http://techcrunch.com/2008/07/21/we-want-a-dead-simple-web-tablet-help-us-build-it/

Prototype A:

http://techcrunch.com/2008/08/30/update-on-the-techcrunch-tablet-prototype-a/

Prototype B:

http://techcrunch.com/2009/01/19/techcrunch-tablet-update-prototype-b/

After this, the story gets murky. According to Arrington, his "partners" (Rathakrishnan - Fusion Garage) changed their mind and decided that they wanted to cut him out of the project. Who knows what really happened.

Some commentary here: http://gawker.com/5415320/the-sad-premature-death-of-the-techcrunch-tablet

and here

http://www.tomshardware.com/news/TechCrunch-CrunchPad-Dead-Chandra-Rathakrishnan,9174.html

They are likely pissed because Microsoft is likely still in the "We are subsidizing this hardware to ensure a market footprint for the XBox" mode and every Kinetic sold today that isn't used to play Gears of Violence is money out of their pocket with zero 'return'.

The Air Force had plans to build an HPC cluster using about 2,500 PS3s plus spares. Air Force Unhappy With Removal of Linux from PS3

That sort of thing takes a lot of product off retail shelves and it cannibalizes sales of your own HPC product.

Exit the OtherOS.

That lesson can't have been lost on Microsoft -- or anyone else in this business.

You're picking Intel's most expensive chip to try and prove a point, and failing horribly. Intel has a $279.99 offering on Newegg that beats the living shit out of the AMD processor for things normal people do on their home computers, and is damn close in the rest. Oh, and it uses far less power both at idle and at load. (Tom's didn't have power numbers for the i7-860).

Now, you might have a point about code "not being optimized for AMD blahblahblah", but here's a newsflash: Not only do the testing suites use libraries compiled with the Intel compiler, but so do nearly all the programs a home user runs on a normal basis. That means the argument is moot, because your average person doesn't give a shit what compiler Microsoft decided to use, and the ones who do can't just go "oh, let's use the AMD-optimized binaries!" - Intel performs better for the same price and lower wattage on real-world applications for this reason, period.

You're picking Intel's most expensive chip to try and prove a point, and failing horribly. Intel has a $279.99 offering on Newegg that beats the living shit out of the AMD processor for things normal people do on their home computers, and is damn close in the rest. Oh, and it uses far less power both at idle and at load. (Tom's didn't have power numbers for the i7-860).

Now, you might have a point about code "not being optimized for AMD blahblahblah", but here's a newsflash: Not only do the testing suites use libraries compiled with the Intel compiler, but so do nearly all the programs a home user runs on a normal basis. That means the argument is moot, because your average person doesn't give a shit what compiler Microsoft decided to use, and the ones who do can't just go "oh, let's use the AMD-optimized binaries!" - Intel performs better for the same price and lower wattage on real-world applications for this reason, period.

You're picking Intel's most expensive chip to try and prove a point, and failing horribly. Intel has a $279.99 offering on Newegg that beats the living shit out of the AMD processor for things normal people do on their home computers, and is damn close in the rest. Oh, and it uses far less power both at idle and at load. (Tom's didn't have power numbers for the i7-860).

Now, you might have a point about code "not being optimized for AMD blahblahblah", but here's a newsflash: Not only do the testing suites use libraries compiled with the Intel compiler, but so do nearly all the programs a home user runs on a normal basis. That means the argument is moot, because your average person doesn't give a shit what compiler Microsoft decided to use, and the ones who do can't just go "oh, let's use the AMD-optimized binaries!" - Intel performs better for the same price and lower wattage on real-world applications for this reason, period.

You're picking Intel's most expensive chip to try and prove a point, and failing horribly. Intel has a $279.99 offering on Newegg that beats the living shit out of the AMD processor for things normal people do on their home computers, and is damn close in the rest. Oh, and it uses far less power both at idle and at load. (Tom's didn't have power numbers for the i7-860).

Now, you might have a point about code "not being optimized for AMD blahblahblah", but here's a newsflash: Not only do the testing suites use libraries compiled with the Intel compiler, but so do nearly all the programs a home user runs on a normal basis. That means the argument is moot, because your average person doesn't give a shit what compiler Microsoft decided to use, and the ones who do can't just go "oh, let's use the AMD-optimized binaries!" - Intel performs better for the same price and lower wattage on real-world applications for this reason, period.

You're picking Intel's most expensive chip to try and prove a point, and failing horribly. Intel has a $279.99 offering on Newegg that beats the living shit out of the AMD processor for things normal people do on their home computers, and is damn close in the rest. Oh, and it uses far less power both at idle and at load. (Tom's didn't have power numbers for the i7-860).

Now, you might have a point about code "not being optimized for AMD blahblahblah", but here's a newsflash: Not only do the testing suites use libraries compiled with the Intel compiler, but so do nearly all the programs a home user runs on a normal basis. That means the argument is moot, because your average person doesn't give a shit what compiler Microsoft decided to use, and the ones who do can't just go "oh, let's use the AMD-optimized binaries!" - Intel performs better for the same price and lower wattage on real-world applications for this reason, period.

Let's take this to an individual chip level, so my point comes through crystal clear.

Intel Core i7-975 Extreme Edition Bloomfield 3.33GHz 4 x 256KB L2 Cache 8MB L3 Cache LGA 1366 130W Quad-Core Processor BX80601975 - $1,039.99

AMD Phenom II X6 1090T Black Edition Thuban 3.2GHz 6 x 512KB L2 Cache 6MB L3 Cache Socket AM3 125W Six-Core Desktop Processor HDT90ZFBGRBOX $229.00

This is a direct comparison of the "best" Intel desktop chip on newegg.com and the "best" AMD desktop chip on newegg.com. I didn't research this too terribly hard, so I may have missed some uber something or other, but I feel fairly confident that these chips are the best in class for the same class, using newegg as my only source.

I've looked up some reviews and benchmarks online, (here and here - I wanted to find someone who had reviewed both, in order to get a "fair" reviewing process) and I can't claim the AMD is faster, although I suspect that a "fair" test (using software that isn't compiled using anything from Intel (who was proven to have rigged their compiler to give themselves a performance advantage against any other chip manufacturer), and using as many cores simultaneously as is possible) would tell a slightly different story.

Silliness and rumor-mongering aside...

Yes, the Intel chip is slightly faster in single-threaded applications, and even (surprisingly) in the multi-threaded apps.

On the other hand... spending four times the money for a gain of approximately 3-4 fps seems kinda silly.

Oh, and that garbage you're spewing about power consumption (heat output) is an outright fabrication. If you're going to lie, do it in a fashion that is less likely to be easily disproven. To be perfectly clear, the "under load" numbers are similar (of course), but the AMD chips idle with a much lower power consumption. In other words, the Intel chips actually put off more heat than the AMD chips. Yes, I just called you a liar. To your face.

TL;DR:
On the one hand, the Intel chip is slightly better (for many values of "better").
On the other hand, it's 4x the price for roughly 1.04x the performance.

I don't know how you arrived at your pricing figures unless you went with sale prices TBH

I went to newegg.com, and looked at the current pricing. If they were sales, I didn't notice. My current response (the one you're reading, since I appear to have to spell everything out to you twice) is not based on any sale pricing to my knowledge.

Let's take this to an individual chip level, so my point comes through crystal clear.

Intel Core i7-975 Extreme Edition Bloomfield 3.33GHz 4 x 256KB L2 Cache 8MB L3 Cache LGA 1366 130W Quad-Core Processor BX80601975 - $1,039.99

AMD Phenom II X6 1090T Black Edition Thuban 3.2GHz 6 x 512KB L2 Cache 6MB L3 Cache Socket AM3 125W Six-Core Desktop Processor HDT90ZFBGRBOX $229.00

This is a direct comparison of the "best" Intel desktop chip on newegg.com and the "best" AMD desktop chip on newegg.com. I didn't research this too terribly hard, so I may have missed some uber something or other, but I feel fairly confident that these chips are the best in class for the same class, using newegg as my only source.

I've looked up some reviews and benchmarks online, (here and here - I wanted to find someone who had reviewed both, in order to get a "fair" reviewing process) and I can't claim the AMD is faster, although I suspect that a "fair" test (using software that isn't compiled using anything from Intel (who was proven to have rigged their compiler to give themselves a performance advantage against any other chip manufacturer), and using as many cores simultaneously as is possible) would tell a slightly different story.

Silliness and rumor-mongering aside...

Yes, the Intel chip is slightly faster in single-threaded applications, and even (surprisingly) in the multi-threaded apps.

On the other hand... spending four times the money for a gain of approximately 3-4 fps seems kinda silly.

Oh, and that garbage you're spewing about power consumption (heat output) is an outright fabrication. If you're going to lie, do it in a fashion that is less likely to be easily disproven. To be perfectly clear, the "under load" numbers are similar (of course), but the AMD chips idle with a much lower power consumption. In other words, the Intel chips actually put off more heat than the AMD chips. Yes, I just called you a liar. To your face.

TL;DR:
On the one hand, the Intel chip is slightly better (for many values of "better").
On the other hand, it's 4x the price for roughly 1.04x the performance.

I don't know how you arrived at your pricing figures unless you went with sale prices TBH

I went to newegg.com, and looked at the current pricing. If they were sales, I didn't notice. My current response (the one you're reading, since I appear to have to spell everything out to you twice) is not based on any sale pricing to my knowledge.

Let's take this to an individual chip level, so my point comes through crystal clear.

Intel Core i7-975 Extreme Edition Bloomfield 3.33GHz 4 x 256KB L2 Cache 8MB L3 Cache LGA 1366 130W Quad-Core Processor BX80601975 - $1,039.99

AMD Phenom II X6 1090T Black Edition Thuban 3.2GHz 6 x 512KB L2 Cache 6MB L3 Cache Socket AM3 125W Six-Core Desktop Processor HDT90ZFBGRBOX $229.00

This is a direct comparison of the "best" Intel desktop chip on newegg.com and the "best" AMD desktop chip on newegg.com. I didn't research this too terribly hard, so I may have missed some uber something or other, but I feel fairly confident that these chips are the best in class for the same class, using newegg as my only source.

I've looked up some reviews and benchmarks online, (here and here - I wanted to find someone who had reviewed both, in order to get a "fair" reviewing process) and I can't claim the AMD is faster, although I suspect that a "fair" test (using software that isn't compiled using anything from Intel (who was proven to have rigged their compiler to give themselves a performance advantage against any other chip manufacturer), and using as many cores simultaneously as is possible) would tell a slightly different story.

Silliness and rumor-mongering aside...

Yes, the Intel chip is slightly faster in single-threaded applications, and even (surprisingly) in the multi-threaded apps.

On the other hand... spending four times the money for a gain of approximately 3-4 fps seems kinda silly.

Oh, and that garbage you're spewing about power consumption (heat output) is an outright fabrication. If you're going to lie, do it in a fashion that is less likely to be easily disproven. To be perfectly clear, the "under load" numbers are similar (of course), but the AMD chips idle with a much lower power consumption. In other words, the Intel chips actually put off more heat than the AMD chips. Yes, I just called you a liar. To your face.

TL;DR:
On the one hand, the Intel chip is slightly better (for many values of "better").
On the other hand, it's 4x the price for roughly 1.04x the performance.

I don't know how you arrived at your pricing figures unless you went with sale prices TBH

I went to newegg.com, and looked at the current pricing. If they were sales, I didn't notice. My current response (the one you're reading, since I appear to have to spell everything out to you twice) is not based on any sale pricing to my knowledge.

Let's take this to an individual chip level, so my point comes through crystal clear.

Intel Core i7-975 Extreme Edition Bloomfield 3.33GHz 4 x 256KB L2 Cache 8MB L3 Cache LGA 1366 130W Quad-Core Processor BX80601975 - $1,039.99

AMD Phenom II X6 1090T Black Edition Thuban 3.2GHz 6 x 512KB L2 Cache 6MB L3 Cache Socket AM3 125W Six-Core Desktop Processor HDT90ZFBGRBOX $229.00

This is a direct comparison of the "best" Intel desktop chip on newegg.com and the "best" AMD desktop chip on newegg.com. I didn't research this too terribly hard, so I may have missed some uber something or other, but I feel fairly confident that these chips are the best in class for the same class, using newegg as my only source.

I've looked up some reviews and benchmarks online, (here and here - I wanted to find someone who had reviewed both, in order to get a "fair" reviewing process) and I can't claim the AMD is faster, although I suspect that a "fair" test (using software that isn't compiled using anything from Intel (who was proven to have rigged their compiler to give themselves a performance advantage against any other chip manufacturer), and using as many cores simultaneously as is possible) would tell a slightly different story.

Silliness and rumor-mongering aside...

Yes, the Intel chip is slightly faster in single-threaded applications, and even (surprisingly) in the multi-threaded apps.

On the other hand... spending four times the money for a gain of approximately 3-4 fps seems kinda silly.

Oh, and that garbage you're spewing about power consumption (heat output) is an outright fabrication. If you're going to lie, do it in a fashion that is less likely to be easily disproven. To be perfectly clear, the "under load" numbers are similar (of course), but the AMD chips idle with a much lower power consumption. In other words, the Intel chips actually put off more heat than the AMD chips. Yes, I just called you a liar. To your face.

TL;DR:
On the one hand, the Intel chip is slightly better (for many values of "better").
On the other hand, it's 4x the price for roughly 1.04x the performance.

I don't know how you arrived at your pricing figures unless you went with sale prices TBH

I went to newegg.com, and looked at the current pricing. If they were sales, I didn't notice. My current response (the one you're reading, since I appear to have to spell everything out to you twice) is not based on any sale pricing to my knowledge.

It won't eclipse Unreal Engine's status. id Tech 5 will not be licensed to 3rd party developers and publishers. You want to license id Tech 5? You have to publish through Bethesda.

The first is that most "Nettops" have terrible graphics cards. [...] games that aren't set up to use [gamepads] often need some pretty nasty hacks to get it to work right.

True, the GeForce 9400 is roughly halfway between the GeForce 3 in the Xbox and the Radeon X1900 in the 360. My solution for this would be to develop and sell PC games with a mode designed around HTPC use patterns and the ION chipset. However, other Slashdot users appear to think that the market of geeks with HTPCs isn't big enough to make adding an HTPC mode to a PC game viable. Otherwise, the major labels would have already done it in more than a few token cases.

Power savings is largely a myth.

As I've said, I've tried this. Firefox's memory use tops 200 MB after two weeks. Other browsers go over 200 MB in a few days. I'm not attacking you, just stating for the record that I cannot see a problem. Perhaps on your computer that problem exists. Do not assume that every other Firefox user in the world sees the same problem. I do not. If you don't believe me, look at any number of memory tests that show Firefox using less memory than other browsers: 1 2 3 4, and many more!

Not quite:

http://www.tomshardware.com/reviews/short-stroking-hdd,2157-9.html

Yes it does show that 4 short stroked SAS 15K RPM drives are beating out a single SSD by getting 2500 IOPs in the DB test. But those are older SSDs. Compare to newer SSDs in similar/same benchmark:

http://www.xbitlabs.com/articles/storage/display/corsair-ssd-roundup_6.html#sect0

You will see they are bottoming out @ 4K IOPS in worst case scenarios.

Also contrary to what was suggested earlier, short stroking does not make HDD seek time negligible:

http://www.tomshardware.com/reviews/short-stroking-hdd,2157-5.html

3.8ms for HDD vs 0.1ms for SSD. That's still a big difference.

You are correct about the low level nature of flash memory, but there are many ways to mitigate this. SSD controllers use multiple channels to read/write banks of flash memory. They have large internal buffers & they also have "waste space", meaning they have extra flash memory that the device can read/write to so as to not hold up the drive. SandForce controllers also use compression and other methods to enhance performance. With proper trim support you do not need to run garbage collection, thus it's really not much different in operation than how a HDD will act, just faster. No modern SSD will make you wait one second while it erases a block of data, they just don't work that way now.

Even worst case random write speeds outpace standard HDDs. Yes if you short stroke your 15k RPM and buy 6 of them then yipee maybe you can exceed the performance of a single SSD, but then any arguments about saving money buying 6x $400 drives + controller so you can use 5% of their capacity go out the window.

Not quite:

http://www.tomshardware.com/reviews/short-stroking-hdd,2157-9.html

Yes it does show that 4 short stroked SAS 15K RPM drives are beating out a single SSD by getting 2500 IOPs in the DB test. But those are older SSDs. Compare to newer SSDs in similar/same benchmark:

http://www.xbitlabs.com/articles/storage/display/corsair-ssd-roundup_6.html#sect0

You will see they are bottoming out @ 4K IOPS in worst case scenarios.

Also contrary to what was suggested earlier, short stroking does not make HDD seek time negligible:

http://www.tomshardware.com/reviews/short-stroking-hdd,2157-5.html

3.8ms for HDD vs 0.1ms for SSD. That's still a big difference.

You are correct about the low level nature of flash memory, but there are many ways to mitigate this. SSD controllers use multiple channels to read/write banks of flash memory. They have large internal buffers & they also have "waste space", meaning they have extra flash memory that the device can read/write to so as to not hold up the drive. SandForce controllers also use compression and other methods to enhance performance. With proper trim support you do not need to run garbage collection, thus it's really not much different in operation than how a HDD will act, just faster. No modern SSD will make you wait one second while it erases a block of data, they just don't work that way now.

Even worst case random write speeds outpace standard HDDs. Yes if you short stroke your 15k RPM and buy 6 of them then yipee maybe you can exceed the performance of a single SSD, but then any arguments about saving money buying 6x $400 drives + controller so you can use 5% of their capacity go out the window.

1. Core 2 Duo > Atom. For reference see: http://www.tomshardware.com/reviews/dual-core-atom-330,2141.html
That review only covers the 1.6GHz version, but without architecture changes a 1.8GHz atom processor won't be making up much ground. So the Macbook Air offers a (substantially) faster processor with comparable battery life to many netbooks (though not a replaceable battery, I miss those).

2. This one has me stumped, you really think a plastic case beats a metal case in sturdiness? Have you ever seen an aluminum case Macbook Pro or Air from the past few years other than photos online? It's not thin like a beer can, it's more comparable to an aluminum desktop case (and thicker in some places). I have had no issues with mine, and I've not heard any complaints of the case falling apart under normal conditions.

3. http://www.apple.com/macbookair/specs.html, or, you know, google it or read any of the previews.

The price is what makes this not a netbook in my opinion. Whenever anyone has asked me in the past what a netbook was (compared to any other laptop) I used the definition that seemed to be the industry standard: small, cheap.

This one isn't quite small enough to compare to netbooks (with screen sizes between 7-10"), and it certainly isn't cheap enough.

"Gamers aren't going to buy a Mac because paying $2500 for a computer with a mid-range graphics card from two generations ago with zero support for end-user upgrades is patently retarded."

$2499
One 2.8GHz Quad-Core Intel Xeon “Nehalem”
3GB (3x1GB)
1TB 7200-rpm Serial ATA 3Gb/s hard drive
ATI Radeon HD 5770 1GB
One 18x SuperDrive

It is a year old right now, Apple can be slow at upgrading their lines, but it's not two generations old

http://www.tomshardware.com/reviews/radeon-hd-5770,2446.html

The thought that someone doesn't deserve to make what independent people are willing to pay them is one of the most bone-chilling authoritarian sentiments that have the misfortune of being popular on this site.

I have no problem with them making money from independent people willing to pay them. I have a problem with them taking more than half of what people are due. Yes, yes, they have expenses, but the biggest one (in many cases) is paying themselves.

Also, just because people are willing to pay doesn't make what they're doing OK. See: price fixing. Example: Samsung, Toshiba, Etc Fined For Price Fixing. Lots of people were willing to pay the price, but it still isn't right.

I'm not saying lawyers are colluding and demanding higher prices than they deserve, I'm saying there should be more restrictions on what kind of payout lawyers are entitled to in any case. The result of which would most likely be lawyers not being one of the highest paid professions, but still well-compensated.

Why does everyone blow this kind of stuff out of proportion and automatically go to authoritarian/socialist/etc?

I run Windows 7 on my my new Revo box 64-bit 2core, 4GB, Nvidia, 500GB Hard Drive. Runs so slow. I spent £300 on it because of lies like yours.

Alrighty. I run Windows 7 on my old Dell Inspiron 1520 with 64 bit dual core, 4GB (aftermarket), Nvidia and 120GB Hard Drive. Bought it in Feb 08 with XP on it. This was during the reign of Vista and this was the only laptop Dell still sold with XP on it.

Got hit by a virus (damn AVG Free did not protect me; even though I scanned the suspect file thoroughly before trying to use it. Switched to Avira, we'll see how that does ;D) and had to re-install. I had already tried Win7 during RC and decided it is marginally better than XP, just not better enough to switch unless you're rolling a new OS anyway.. and now I was. So I switched from 32 bit XP to 64 bit 7.

Now it seems to run every bit as fast as XP did, with Aero turned on. It eats more RAM (900MB used at startup instead of 350MB, overhead appears constant after days of uptime) and this is after applying most of Black Viper's recommended service tweaks to both OSen. I find win+tab is handy when you've got a ton of browser windows open (each with tabs; I generally run one window per distinct project) and want to quickly get to one which is visually distinct.

so tuppe, does my counter-example anecdote mean that you're the liar now? Or perhaps we should yeild the predictive power of all of our personal one-off experiences in favor of actual research?

ZDnet's benchmarks maintain that Windows 7 is faster than XP for standard use, although XP remains more capable for devices with limited memory and outdated graphics.

Maximum PC's benchmarks claim that Win7 simply feels faster than XP on the hardware they tested.

Tom's Hardware's netbook benchmarks show that Windows 7 does not beat XP on the netbook but that it is quite responsive, and would probably surpass XP with better driver support.

TechRadar's benchmark includes many plusses and minuses for Windows 7 with a net plus, but clearly states that it provides "better performance than XP can deliver on today's hardware."

I'm not picking up on any benchmarks that have the same trouble you've had, so unfortunately I have no way to confirm you did not just misconfigure your machine.

This is the article I was referring to (read through the comments for discussion about AM3+ compatability):

http://www.anandtech.com/show/3937/amds-fall-refresh-new-phenom-ii-and-athlon-ii-cpus-balance-price-and-performance

Here's another blurb about the same issue:

http://www.tomshardware.com/forum/289211-28-official-socket-support-bulldozer

i5 starts at $180. So IF (big IF) you want to spend $180+ on CPU then yeah you really can't go wrong with Intel i5-xxx series.

However for many users they aren't CPU limited. CPU power makes very little difference in game performance once you get past dual core 2.5Ghz. It makes a difference but not as much as a GPU.

In the $100 to $200 segment is where AMD really shines.

From tomshardware.
http://www.tomshardware.com/reviews/best-gaming-cpu-core-i5-760-core-i7-970,2698.html

Best Gaming CPU for ~$70 - Athlon II X3 425
Best Gaming CPU for ~$85 - Athlon II x3 445
Best Gaming CPU for ~$115 - Core i3-530
Best Gaming CPU for ~$140 - Phenom II x4 945
Best Gaming CPU for ~$160 - Phenom II x4 955
Best Gaming CPU for ~$180 - Phenom II x4 965
Best Gaming CPU for ~$200 - Core i5-760
Best Gaming CPU for ~$290 - Core i5-930

When someone has a fixed budget spending $50 to $100 LESS on CPU allows them to buy $50 to $100 more GPU and that system will offer better overall game performance.

I do agree that $200+ Intel dominates and AMD doesn't really have anything that answers but that is a small segment of the market. One also has to consider that i5 boards tend to run $10 to $20 more than comparable AMD board and i7 boards run $60 to $100 more.

I have no idea where those cards sit in the hierarchy of graphics cards. How can I easily find out if my laptops nVidia GeForce 8600M GT good enough or not. It has a higher number, but somehow I doubt that is a reliable indicator.

Please see the chart at Tom's. Xbox is like a GeForce 3; Xbox 360 is like a Radeon X1900.

The problem is that those bugs are in the "WORKSFORME" category, and they're hard to reproduce in the devs' machines. But Windows and the MacOSX have similar problems, they just have more resources to test hundreds of configurations, something that Ubuntu will never have.

I would think that the ability to run linux *again* might be of more interest here on /.
Having to crack a console to get functionality back sounds like a joke but I suspect few are laughing.

To get back to the topic at hand, given John Carmac's view of the PS3 architecture, it's likely that porting emulators for the more modern consoles (i.e., those that require 3D accelleration) may be a lot more trouble than it was for, say, the original Xbox.

John: I never liked the Cell architecture. You can get high peak numbers out of it, but software development time matters a lot, and not having caches and virtual memory makes development take a lot longer, especially for the majority of applications that don't fit neatly into the DMA pipeline model.

From http://www.tomshardware.com/news/ps3-playstation-3-linux-john-carmack,10035.html

It is not as good as the GPU in the Xbox 360.

http://www.tomshardware.com/reviews/gaming-graphics-card-geforce-gtx-480,2598-6.html

In this chart, the Xbox 360's GPU is about the same as the X1900.

Well their is this Android 2.2 device coming out:

"The one that will garner most attention is the Archos 101. Packing a 10.1-inch (1024 x 600) touchscreen, the device has the same 1GHz ARM Cortex A8 processor as the 70 and 43 and shares a lot of other specs with its lower-end counterparts, including HDMI, USB, WiFi, Micro-SD and a kick stand. This one is the most expensive of the line and it's priced at $299."

With competition like this, prices will probably drop for everyone else.

Except in most jurisdictions Sony DID do something legally wrong. That is why in most of the EU, retailers selling PS3s have offered partial refunds upon request. That is just one example. Here is a link so you don't have to Google it:

http://www.tomshardware.com/news/PS3-playstation-Linux-Rebate-Amazon,10140.html

If the propagation speed of an electrical signal is .96C in an uninsulated chunk of copper and only .66C in a coaxial cable, what is it reduced to in an on-chip environment? On a computer bus? I have seen the figure .33C, but I can't find any primary source for this.

Let's assume the 0.33C for the moment, and consider what this means. A CPU contains some fairly large functional units that need to be run synchronously - meaning that all transistors within the unit switch are synchronized by a master clock signal. If this is to work, the propagation delay across the unit must be significantly less than 1/2 of a clock cycle. Taking .33C figure as correct, and limiting delay to 1/4 of a clock cycle, the maximum size of a functional unit is about 8mm. This is not far removed from the size of structure on modern CPU chips. You can make functional units accept larger delays (that's one application of pipelines), but this carries the price of complexity.

The point: power consumption is an important problem, but signal propagation is also very relevant. If 3GHz isn't the limit, from a signal propagation point of view, it is not so far away from that limit...

Here's a chart showing how the race to ever-faster processors came to a screeching halt a few years ago.

Overclockers have gone above 6ghz here and above 7ghz here and dont forget over 8ghz here

In each case, its always about the heat.

Pretty much all CPU's sold today (even "2.x ghz" chips) can go over 4ghz with proper air cooling. The reason they dont sell 4ghz+ chips is because chips have warranties and require a proper cooling setup in order to not fail at those speeds. Most important of course is heat sink and cpu fan which Intel and AMD do have some control over, but also of considerable importance is case fans and case ventilation, which they do not have control over.

Just moving my case fan from the stock front position (intake) to the back (exhaust) gave me 10 degrees C more headroom at load, allowing my AMD 1055T to go from 2.8ghz to 4.1ghz (before moving the case fan, I was only stable up to 3.36ghz) ..

Microsoft Windows 95 was released on August 24th, 1995.

http://www.tomshardware.com/forum/173161-48-windows-release-date

http://www.washingtonpost.com/wp-srv/business/longterm/microsoft/stories/1995/debut082495.htm

http://www.wired.com/science/discoveries/news/2007/08/dayintech_0824

So, either all of those places (and a good chunk more) have been "fixed", or you're the one trying to change reality.

Benchmarks certainly testify that the AMD 3.2 ghz hexacore is not three times slower than the Intel. At three times the price even twice as fast is a rip off, and Intel isn't even that far ahead.

Based on previous advances it seems unlikely to me that a 5x increase in density would give rise to anywhere near a 5x increase in throughput. See for example http://www.tomshardware.com/reviews/1tb-hdd-storage,2563.html
Fundamentally a spinning disk has a disadvantage in seek times, and that is a key metric for day to day uses. It's clearly very unlikely in the long term that SSDs will have inferior performance in any way when you consider the relative maturities of the two technologies, and the R&D money being spent on each.

>>Opera should NOT be used on low-end machines.

That's been my experience. Opera X 10.0 was okay, but something went wrong with 10.5. When I'm running it, Opera uses more memory than Firefox 3.5 on my Windows PC. I've also noticed an annoying Opera habit where it loads 99% of the page and then never finished, especially on pages with lots of scripts.

Still better than IE. Oh and here's the direct link to the memory usage of each browser: http://www.tomshardware.com/reviews/opera-chrome-firefox,2689-10.html

Actually, my freind, I read an article today that suggests Opera should NOT be used on low-end machines. It's a memory hog, without decent memory management. Lemme find that link - - - - http://www.tomshardware.com/reviews/opera-chrome-firefox,2689.html

Opera has a lot of good things going for it, but compatibility with low end machines and low memory isn't one of them.

>There are SATA 6GB/s disks out there with >400MB/s rates,

Right, that's why the charts top out at 158, Enterprise 2010 chart tops out at 200 and it's all SAS.

Caught reading the specs again?

I'm not sure what about 50% of your rambling there means. The math in my previous comment stands for itself as I'm sure other readers can see. If you care to contest the fact that 2 bytes * x = 9MB and 6 bytes * x = 4MB are fundamentally inconsistent, please do so directly and succinctly (for example by providing a value for x for which both those equations work).

Also, I repeat my assertion that I have not posted as AC in this thread. Those you claim are impersonating you, are not me.

Making a HOSTS file smaller with 0's is not an abuse of HOSTS. In fact, I never contested your assertion that smaller HOSTS files are quicker to read. Go ahead and tout that as another "win". The fact is, HOSTS files were simply not designed for millions of lines (no, I don't have a cite... it's common sense). DNS servers were designed for that. You are abusing HOSTS by using it to replace the functionality of a DNS server. Because the OS is not designed for such huge HOSTS files, it will be slower than using DNS as intended (even for example a DNS server running on your local machine to blackhole all those domains for you)

See here (and other google results if you care) for Microsoft MVPs stating that having a large HOSTS file is a known cause for the DNS Cache service (which handles that file) consuming 100% CPU

http://www.tomshardware.com/forum/117268-45-svchost-consumes-startup

This will be my last reply to you in this thread. Consider yourself victorious if you so desire. Those reading the thread can decide for themselves.

Reminds me of this video from Tom's Hardware, circa 2001.

Looks no more crowded than any western site I have ever seen, if you view all the chars as text then it is relatively clean and simple ?

Or at least similar to Western sites. For example http://www.tomshardware.com/us/ looks just as cluttered, especially with Japanese characters: http://translate.google.com/translate?js=y&prev=_t&hl=en&ie=UTF-8&layout=1&eotf=1&u=http://www.tomshardware.com/us/%23redir&sl=en&tl=ja

With the speed of todays computers, though, you shouldnt (usually) need that amount of optimization.

After about eight years stuck at the same speed, I wonder what do you mean by "today".

Yes, yes, I know all about the Megahertz Myth. But that's the marketese speech for evading the issue. The fact is that the "Megahertz Myth" is a myth. It's obvious that, all other parameters being equal, doubling the CPU clock will double your performance. It was only when some companies couldn't keep increasing the CPU clock that they invented this lie that megahertz don't matter.

The problem with increasing performance by other ways than raw CPU clock is that it will not necessarily translate in performance increases for all applications. Apple and AMD had to carefully construct their benchmarks to justify this pseudo-myth.

It's true that, with the CPUs we have had for a decade now, many tasks can be done easily with interpreted languages that weren't possible before. That may be true for many corporate desktop applications, no one will care too much if it takes one or two seconds to get a list of how many "snibbo" widgets were returned for maintenance last month.

However, there are still many applications where CPU performance still falls short of the ideal. Improving those applications demands a language like C, because with "higher level" languages it's harder to get increased performance from parallelization. It's not always obvious which operations can be done in parallel and unless interpreters become a lot more efficient at this, there will always be room for compiled languages at the top.

Do you mean besides Charlie Miller frequent pwn2own winner? He uses fuzzers and source code, and even reverse engineers binaries.