Cool. Thanks for your help. BTW> I feel proud of myself. I bought Gobe Productive, Opera, and actually registered SoundPlay:) As for putting the money into BeOS, that's probably what I'll do. I mean, I can always get Win2K burned for me. (Of course if MS comes asking, I never said that;)
You bring up an interesting point, one that is very important for SMP computers and OSs. You see, there is only a few reasons why BeOS is better than Linux at SMP. One is that it was designed for it, but in the end, that isn't the biggest reason. The major reason is because of the way the BeOS API is designed. It is designed in such a way that it is not only easy for an application designer to use multiple threads, but is often EASIER. For example, the protocol used to allow direct access to the screen. Conventional wisdom dictates that an application locks the buffer, draws to it, and then unlocks it. However, in BeOS, the system sends messages whenever the state of a buffer changes. The application must respond to this change inside a function that may not run for more than 3 seconds. Thus, the application designer is forced to use a seperate rendering thread to update the window. Not only does this improve performance (since the surface isn't being constantly locked and unlocked) but it allows the load of the application to be distributed between multiple processors. Of course, this API dictates a lot of policy, which is quite unUNIXish. However, it really is the most effective way to end up with a good SMP system. I see the GTK and Qt people missing a tremendous opportunity in what they are doing. GTK and Qt are entire OS-level APIs in their own right, and thus they have the opportinity to force developers to use threads (and do other desirable things like support application scripting.) However, not only do GTK and Qt NOT force developers to use threads, in general they are (especially GTK) pretty thread unfriendly. Developers are almost by definition lazy. Even if SMP machines were very common, it still wouldn't be as much of an incentive as an API that made it easier for them to use threads than not. (BTW> The Be API is not at all hard. It is just designed in a way to make threads a more desirable choice than no threads. Even with the extensive threading it is still easier to program for than most other APIs. I say this because there is no reason to scare any programmers away from the OS;)
Well, consider this. What about stuff like voice recognition? Given the correct software, people could be immensly more productive if they could have a computerized assistant to do stuff for them. If there was software that would provide the equivilant of an assistant (archive this file, send this document to this person, take these notes, get info about this topic, etc) then businesses would immediatly buy the fastest computers availabe if that was what was needed to run this software (because speech recognition and AI are pretty big CPU hogs.) That's what this increase in power amounts to. As for the "cute crap," that offends me. Sure you can buy a perfectly functional Toyota, but given the option any sane man would buy a Boxter with tons of chrome trim, no? Asthetics counts for a lot to most people. Some people manage without them (anyone who still uses TWM for example) but to most people working in a nice computing GUI is just like having nice office furniture. Sure you can do without it, but its so much nicer on the eyes.
So you've used Windows 2K. I'm thinking of shelling out the money for it, but I'm not quite sure how it will run. I've got a similar config to yours, and NT4 WKS runs quite fast on my machine. However, all the sites seem to say that you need a lot more hardware for Win2K. In your opinion, how does the speed of Win2K compare to Win98 in terms of interactive performance? Also, I heard there were troubles Quake and other 3D shooters running a lot slower in Win2K than in 98. Are any of those substantiated? Any advise you could offer would be appreciated.
Th reason why stuff isn't always clustered, mutli-proced is that somethings just aren't parallaziable. Say if your doing, I don't know, a very large domino simulation, the thing would run the same speed on a 500way computer as on a 1 way computer. As for 3D, it will always need more power. The NVIDIA guys said it pretty well. It was to the effect of "with 3D you can't ever have enough power because you're trying to model reality." Then he went on to say something about making a tree "so real that it couldn't possibly exist in real life, but is believable because of how well rendered it is."
I agree with you entirely (exept the part of programmers. Even on 50GHz procs I want to see those programmers slaving away for every last clock cycle;) However, I think that if I said EVERYONE can use more power I'd get 500 responses from people still using 386s saying I was an idiot.
Well, SMP works only to a point. If the stuff you're doing is easily parallizable then it works pretty great, but otherwise it really doesn't. For actualy desktop use SMP is great if the OS you use is really good with it (ahem, BeOS) but if you're running an OS that really isn't (ahem, MacOS) then you don't see much of a performance enhancement. In the end, clockspeed really is the best way to go. Doubling clockspeed will always give you a bigger payoff than doubling the number of CPUs.
How is a 1133 MHz processor unstable? If you have any proof that they're are serious problems then please tell me, but as far as I can see, the high performance PIII/Athlons have been quite stable. Especially the GHz PIIIs which produce about the same heat as a 800/850 MHz Athlon. My point isn't (there really is a use buying 1133 instead of 1033) but (there really is a use for CPU power continuing to grow) Right now I admit, it is pretty silly because the increases in clockspeed are so small, but a lot of people say that processers are fast enough, the busses are too slow, etc. To those people I'm saying that "no, processors aren't fast enough" and "the limitations of the bus depends on what you're doing." Sure saying that there really isn't a use ging 1133 vs. 1000 is a sane thing, but saying "do we really need more power?" is just stupid.
Isn't the irony beautiful? I can just imagine the 386 days some guy saying "But of the 50-odd people that work where I work, only 3 (including myself) woulrd regularly max-out a PC regardless of power, with maybe another 6 requiring PCs faster than the ones on their desk/ We've probably got 20 people that could do everything they want on a 1 MB 8086, with the rest (50-20-6-3=21) probably never needing anything more powerful than a 286" People have said that forever. GUIs necessitated the 486 and Pentium for regular business desktops. Multimedia, 3D, etc required home users to own PIIs (btw the home market is quite huge and very influental) Something will come along. My first guess is probably a voice user interface. Coupled with a mouse, a voice interface really could make web browsing really accessible to a larger group of people. Instead of icons,etc, you could say "PC dictate an email for my daughter." You can do that to some extent, but you still need to train it etc. For a really fluid voice UI you need a lot of horsepower for AI algorithms that can understand nuances of speech, figure out how to adapt to the same command said in a different manner, etc. Or maybe something else entirely will come out, you never know. However, the most dangerous thing you can do is be satisfied with what exists, and be closed to new concepts because that way you really miss out on what COULD be.
True, but to some extent. I, for one, feel much more constrained by CPU than my internet (DSL) I tend to be a big 3D/audio/video person, and for me, renderings are still to damn slow. Maybe I have no patience...
I don't know what the exact limitations are, but as I remember it, there have been many times before in processor history where people said "silicon just can't go any faster." However, everytime the barrier was about to be hit, somebody came up with a way around it.
Sometimes I think/. is the home of people who don't get it. Sure, given current software, there's not a need for the power. But, as I remember it, Word processing, and email have worked fine since the 286 days. However, something always comes around to use additional power. The GUI word processors demanded more power. Who knows, maybe when chips get fast enough to do really good voice recognition without slowing to a crawl people will upgrade to P5 4GHz's so they can use the new voice powered user interfaces. Telling the what to do certainly makes things easier for these people, right?
Yes, BillG is pretty clever. He certainly has marketing sense. And I don't know what spurred demand for the 386, but I do remember multimedia being the reason we bought a 486. Either way, it's a moot point. People were saying nobody would use this power, and somebody did.
You don't seem to understand what Mustang is. I just looked at the AMD faq. It says that Mustang is an enhanced version of Athlon based on a.18 micron process and with a larger cache. However, the Thunderbird Athlons are already.18 micron " Q6:Does the new version of the AMD Athlon processor use a 0.18 micron manufacturing process? A6:Yes. All of the AMD Athlon processor wafer starts are now on 0.18 micron process technology. The die size of the new AMD Athlon processor is 120mm square " The other quote, from the same FAQ is this " A15: "Mustang" Enhanced version of AMD Athlon processor with reduced core size, lower power requirements, and up to 1MB of on-chip, performance-enhancing L2 cache memory. Manufactured on a 0.18 micron copper process technology. Multiple derivatives of the Mustang core are planned to address the requirements of the high-performance server/workstation, value/performance desktop and mobile mark" If you carefully read past the marketing speak, you'll notice this. Both the current Athlon (Thunderbird) and the next Athlon Ultra (Mustang) are based on the same.18 micron copper process. This is where the "enhanced with reduced core size and power consumption" part comes in. The only difference is the case of the Mustang where it has up to 1MB of full speed L2 cache. I don't see why this is so hard to understand. My original point was that AMD doesn't have a processor that can compete with Willamette if Willamette's performance is as high as expected. I said AMDs real next gen design is the Sledgehammer chip. You put for Mustang as AMD's next chip. However, Mustang is simply an AMD Athlon Thunderbird with more cache. It is almost exactly like a PIII Xeon. Same core, same copper process, same everything except cache. Sure there may be changes in circuit layout to accomodate the cache, but no real performance benifets will come from that. It is doubtful that AMD's.18 micron process will scale to 1.5+ GHz given the limitations of the process. Even the.18 micron Thunderbirds are already producing huge amounts of heat. You can't argue that Mustang is a next-gen processor, so where's your ground? If Willamette is a big 3D powerhouse, AMD doesn't have a leg to stand on. If you actually go out and read the articles that are comming out, they say the same thing. ZDNet even said that AMD may have to go back into the value market if Intel can pull off the whole Willamette thing. (Get developers to recode, be able to get decent performance on non 3D apps, get good yeilds, etc.)
PS> It isn't possible to change the process without changing the layout, but steppings almost never result in performance increases, just better yeilds. Case in point. A.35 micron PII overclocked to 333 gives the exact same performance as a 333 MHz.25 micron PII.
I'm tired of hearing all these people saying we don't need more power. It all depends on what you use. There will always be those who need more power, and not just in a "Tim Allen-esque testosterone induced" way, but genuinely. People have been saying that nobody needs more power ever since the 386 days. Even Intel used to say that the 386 wasn't really meant for consumer space, it was a server/workstation chip. Yet always, some clever dude found a use for that power. Back in the 386/486 days it was multimedia and video. Just when the Pentiums seemed fast enough, those crazy gaming guys came up with 3D, which needed a lot more proc power. I think 3D will carry processors until the 50+GHz region, at which point somebody will find something else to use the proc for. Even then there will be morons saying "oh, is there really a USE for this 100GHz proc?"
Re:Ugg, massive uncalled for waste of screen space
on
KDE 2.0 Beta 3 Is Out
·
· Score: 2
Ah, but not KDE 2.0, it never pops up correctly because it is treated as a window, and when it pops up, it doesn't get focus, so it ends up behind the top window.
But my point is that AMD's new CPU is simply an Athlon with more cache. No new features, no rearchitecturing of the pipeline. Don't you think they would put it in the FAQ is the actual chip was going to be changed? All along it has been known that the Athlon Ultra would be an Athlon with more cache, just like the Xeon chips are compared to the Pxx chips. The FAQ doesn't say anything about changes, just a new process. AMD has already done this process change. The Thunderbird Athlon is simply an Athlon with 256K of L2 cache, and based on a.18 micron process. Plus, it is already based on copper. Aside from the change in L2 size and speed (and any changes in circuit layout), there are no other changes. Same thing with Mustang. The Mustang will actually be less of a change than Athlon -> Thunderbird. It will be based on the same Thunderbird core (Most 900MHz+ Athlons are based on this core) with 1MB of L2. Process changes HAVE been made without architectural changes. Take PII Klamath to PII Deschutes. In that case the process was moved from.35 to.25 with no other changes. Athlon Ultra (Mustang) is the same way. Anyone without any preconceptions would read the FAQ as talking about an Athlon with more cache. Everything the FAQ talks about, (except the 1MB of cache) is already implemented in the regular Thunderbird Athlon.
Re:Ugg, massive uncalled for waste of screen space
on
KDE 2.0 Beta 3 Is Out
·
· Score: 1
I HATE autohide panels. They're so inconvenient. Both KDE1 AND GNOME are still aweful screen hogs compared to Win9x. You can make the panels smaller, but then they look ugly. You can make it auto-hide, but that never works correctly with netscape.
I know, but if you leave it out, you should be able to run Win32 applications perfectly. Windows NT, for example, runs most mainstream Windows applications, but is 100% 32bit code. The 16bit code you're talking about is in Windows 9x, where major portions of the OS (like the GDI) are simply cut-and-pasted Win 3.1 code. NT does't have any of this code, but still can run Windows applications, which means that a new OS without any 16bit code or support for 16bit apps should still be able to run Win32 applications.
Okay, I reread the docs. You're right, Willamette only has one FP pipe and one load/store pipe. However, the single 128bit wide pipe should be faster than P3's double 64bit wide pipes, and we already know taht SSE is as fast or faster than 3DNow!. An intersting article covers these, you can find it here.
Read the FAQ carefully. The thing is simply an Athlon with.18 micron technology and 1MB of cache. The reduced core size and lower power requirements are simply a byproduct of the.18 micron process. Considering that the Thunderbird Athlon already runs a.18 micron process, it already has the reduced core size and lower power requirements. And instead of "1MB of on-chip, performance enhancing L2 cache memory" Thunderbird is "256KB of on-chip performance enhancing L2 cache memory." Thus, it IS simply an Athlon with more L2 cache.
As for Willamette and the MaximumPC artice, it is quite accurate. You can find similar articles on ZDnet, and yes, Intel HAS been quoted as saying it is aimed at the high end, but it HAS done focus shifts before. In fact, the article in the latest MaximumPC even mentions that quote, but says they may aim it at the lower to middle end to compete with Athlon. Ans since Willamette itself won't really come out in volume till very late this year, the SDRAM chipset isn't very far off. In fact, it is very reminiscent of the whole PII, where Intel aimed PII at more mainstream applications quite quickly.
Ugg, massive uncalled for waste of screen space.
on
KDE 2.0 Beta 3 Is Out
·
· Score: 1
Is it just me, or are Linux DE's moving dangerously into the realm of "screen space wasters" where MS apps in general look selvte, (if drab) the new Linux DE's look much more, umm, crappy. KDE2 is the most egregious offendor. On the bottom of Konqueror, there is a thick status Window that nobody ever uses and you can't get rid of. Then, the frames themselves are thick. Even the scrollbar is thick. There is too much spacing between icons, and a lot of dead space in apps like KWord. What are they CODING on? 21 inch monitors?
As far as I remember, this thing STILL is Windows-only. Since it is going Opensource, it might be possible to port gMax to Linux, but I doubt the OSS version is going to be one usable for "real" 3D artists designing games. What most likely will happen, is that someone will take the OSS gMax code, port it to Linux (which makes for a pretty easy port to BeOS I might add) and then Kinetix will use that code to port the rest of 3D Studio over to compete at the lower end of the high end 3D modelers on Linux. Quite clever, really, let the OSS community do the port for you without actually releasing important code. Of course this is good for both parties. Kinetix gets a linux port without expending much effor (since any of the other stuff in 3D Studio MAX will probably be high level stuff dependant on the lower already-ported layers rather than on the OS) and the OSS community gets a 3D modeler that doesn't have a braindead interface. Say what you will for the "efficiency" of Blender, 3D Studio MAX has a nice interface, great workflow, AND an assload of hotkeys.
1) SSE2 doesn't have 2 instructions per cycle. I said it is twice as fast as 3DNow! Since SSE2 is 128bits wide (meaning 4 32bit floats per instruction) and 3DNow! is 64bits wide (2 32bit floats per cycle) that's true. Look it up. It's not two instructions per cycle, but 4 operations per instruction. 2) You've got me on the yield problems. However, Intel has rarely had yield problems, and if AMD can take it, I'm pretty sure Intel will make it. 3) AMD cannot migrate down the Mustang since it is the same exact (K7) core with more cache. Source: Sharky Extreme (www.sharkyextreme.com) AMD/VIA roadmap, 6th page. 4) Willamette actually will be targeted at mainstream systems. Check www.zdnet.com for several articles. Additionally they are supporting PC133 SDRAM for these lower-end systems. Lastly, <a href="http://www.maximumpc.com/content/2000/05/08/ 11344">this article </a> and MaximumPC proves it. Now what were you saying about not being totally sure?
Not necessarily. Most Win32 applications aren't hideously tied to the OS. Thus, you can implement the actual OS any way you want as long as you're complient with the API. NT is proof that the OS needn't look any particular way to work with Win32. As for Win32 itself, it isn't a turd. The OS that it's driving is a turd. (Though NT is a pretty damn good OS.) Win32 itself, coupled with DirectX and COM is actually a pretty good API, certainly one that is worth putting up with for the sake of compatability.
Slashdot Mirror
Cool. Thanks for your help. :) ;)
BTW> I feel proud of myself. I bought Gobe Productive, Opera, and actually registered SoundPlay
As for putting the money into BeOS, that's probably what I'll do. I mean, I can always get Win2K burned for me. (Of course if MS comes asking, I never said that
You bring up an interesting point, one that is very important for SMP computers and OSs. You see, there is only a few reasons why BeOS is better than Linux at SMP. One is that it was designed for it, but in the end, that isn't the biggest reason. The major reason is because of the way the BeOS API is designed. It is designed in such a way that it is not only easy for an application designer to use multiple threads, but is often EASIER. For example, the protocol used to allow direct access to the screen. Conventional wisdom dictates that an application locks the buffer, draws to it, and then unlocks it. However, in BeOS, the system sends messages whenever the state of a buffer changes. The application must respond to this change inside a function that may not run for more than 3 seconds. Thus, the application designer is forced to use a seperate rendering thread to update the window. Not only does this improve performance (since the surface isn't being constantly locked and unlocked) but it allows the load of the application to be distributed between multiple processors. Of course, this API dictates a lot of policy, which is quite unUNIXish. However, it really is the most effective way to end up with a good SMP system. I see the GTK and Qt people missing a tremendous opportunity in what they are doing. GTK and Qt are entire OS-level APIs in their own right, and thus they have the opportinity to force developers to use threads (and do other desirable things like support application scripting.) However, not only do GTK and Qt NOT force developers to use threads, in general they are (especially GTK) pretty thread unfriendly. Developers are almost by definition lazy. Even if SMP machines were very common, it still wouldn't be as much of an incentive as an API that made it easier for them to use threads than not.
(BTW> The Be API is not at all hard. It is just designed in a way to make threads a more desirable choice than no threads. Even with the extensive threading it is still easier to program for than most other APIs. I say this because there is no reason to scare any programmers away from the OS;)
Well, consider this. What about stuff like voice recognition? Given the correct software, people could be immensly more productive if they could have a computerized assistant to do stuff for them. If there was software that would provide the equivilant of an assistant (archive this file, send this document to this person, take these notes, get info about this topic, etc) then businesses would immediatly buy the fastest computers availabe if that was what was needed to run this software (because speech recognition and AI are pretty big CPU hogs.) That's what this increase in power amounts to. As for the "cute crap," that offends me. Sure you can buy a perfectly functional Toyota, but given the option any sane man would buy a Boxter with tons of chrome trim, no? Asthetics counts for a lot to most people. Some people manage without them (anyone who still uses TWM for example) but to most people working in a nice computing GUI is just like having nice office furniture. Sure you can do without it, but its so much nicer on the eyes.
So you've used Windows 2K. I'm thinking of shelling out the money for it, but I'm not quite sure how it will run. I've got a similar config to yours, and NT4 WKS runs quite fast on my machine. However, all the sites seem to say that you need a lot more hardware for Win2K. In your opinion, how does the speed of Win2K compare to Win98 in terms of interactive performance? Also, I heard there were troubles Quake and other 3D shooters running a lot slower in Win2K than in 98. Are any of those substantiated? Any advise you could offer would be appreciated.
Th reason why stuff isn't always clustered, mutli-proced is that somethings just aren't parallaziable. Say if your doing, I don't know, a very large domino simulation, the thing would run the same speed on a 500way computer as on a 1 way computer. As for 3D, it will always need more power. The NVIDIA guys said it pretty well. It was to the effect of "with 3D you can't ever have enough power because you're trying to model reality." Then he went on to say something about making a tree "so real that it couldn't possibly exist in real life, but is believable because of how well rendered it is."
I agree with you entirely (exept the part of programmers. Even on 50GHz procs I want to see those programmers slaving away for every last clock cycle ;) However, I think that if I said EVERYONE can use more power I'd get 500 responses from people still using 386s saying I was an idiot.
Well, SMP works only to a point. If the stuff you're doing is easily parallizable then it works pretty great, but otherwise it really doesn't. For actualy desktop use SMP is great if the OS you use is really good with it (ahem, BeOS) but if you're running an OS that really isn't (ahem, MacOS) then you don't see much of a performance enhancement. In the end, clockspeed really is the best way to go. Doubling clockspeed will always give you a bigger payoff than doubling the number of CPUs.
How is a 1133 MHz processor unstable? If you have any proof that they're are serious problems then please tell me, but as far as I can see, the high performance PIII/Athlons have been quite stable. Especially the GHz PIIIs which produce about the same heat as a 800/850 MHz Athlon. My point isn't (there really is a use buying 1133 instead of 1033) but (there really is a use for CPU power continuing to grow) Right now I admit, it is pretty silly because the increases in clockspeed are so small, but a lot of people say that processers are fast enough, the busses are too slow, etc. To those people I'm saying that "no, processors aren't fast enough" and "the limitations of the bus depends on what you're doing." Sure saying that there really isn't a use ging 1133 vs. 1000 is a sane thing, but saying "do we really need more power?" is just stupid.
Isn't the irony beautiful? I can just imagine the 386 days some guy saying
"But of the 50-odd people that work where I work, only 3 (including myself) woulrd regularly max-out a PC regardless of power, with maybe another 6 requiring PCs faster than the ones on their desk/ We've probably got 20 people that could do everything they want on a 1 MB 8086, with the rest (50-20-6-3=21) probably never needing anything more powerful than a 286"
People have said that forever. GUIs necessitated the 486 and Pentium for regular business desktops. Multimedia, 3D, etc required home users to own PIIs (btw the home market is quite huge and very influental) Something will come along. My first guess is probably a voice user interface. Coupled with a mouse, a voice interface really could make web browsing really accessible to a larger group of people. Instead of icons,etc, you could say "PC dictate an email for my daughter." You can do that to some extent, but you still need to train it etc. For a really fluid voice UI you need a lot of horsepower for AI algorithms that can understand nuances of speech, figure out how to adapt to the same command said in a different manner, etc. Or maybe something else entirely will come out, you never know. However, the most dangerous thing you can do is be satisfied with what exists, and be closed to new concepts because that way you really miss out on what COULD be.
True, but to some extent. I, for one, feel much more constrained by CPU than my internet (DSL) I tend to be a big 3D/audio/video person, and for me, renderings are still to damn slow. Maybe I have no patience...
I don't know what the exact limitations are, but as I remember it, there have been many times before in processor history where people said "silicon just can't go any faster." However, everytime the barrier was about to be hit, somebody came up with a way around it.
Sometimes I think /. is the home of people who don't get it. Sure, given current software, there's not a need for the power. But, as I remember it, Word processing, and email have worked fine since the 286 days. However, something always comes around to use additional power. The GUI word processors demanded more power. Who knows, maybe when chips get fast enough to do really good voice recognition without slowing to a crawl people will upgrade to P5 4GHz's so they can use the new voice powered user interfaces. Telling the what to do certainly makes things easier for these people, right?
Yes, BillG is pretty clever. He certainly has marketing sense. And I don't know what spurred demand for the 386, but I do remember multimedia being the reason we bought a 486. Either way, it's a moot point. People were saying nobody would use this power, and somebody did.
You don't seem to understand what Mustang is. I just looked at the AMD faq. It says that Mustang is an enhanced version of Athlon based on a .18 micron process and with a larger cache. However, the Thunderbird Athlons are already .18 micron .18 micron copper process. This is where the "enhanced with reduced core size and power consumption" part comes in. The only difference is the case of the Mustang where it has up to 1MB of full speed L2 cache. I don't see why this is so hard to understand. My original point was that AMD doesn't have a processor that can compete with Willamette if Willamette's performance is as high as expected. I said AMDs real next gen design is the Sledgehammer chip. You put for Mustang as AMD's next chip. However, Mustang is simply an AMD Athlon Thunderbird with more cache. It is almost exactly like a PIII Xeon. Same core, same copper process, same everything except cache. Sure there may be changes in circuit layout to accomodate the cache, but no real performance benifets will come from that. It is doubtful that AMD's .18 micron process will scale to 1.5+ GHz given the limitations of the process. Even the .18 micron Thunderbirds are already producing huge amounts of heat. You can't argue that Mustang is a next-gen processor, so where's your ground? If Willamette is a big 3D powerhouse, AMD doesn't have a leg to stand on. If you actually go out and read the articles that are comming out, they say the same thing. ZDNet even said that AMD may have to go back into the value market if Intel can pull off the whole Willamette thing. (Get developers to recode, be able to get decent performance on non 3D apps, get good yeilds, etc.)
.35 micron PII overclocked to 333 gives the exact same performance as a 333 MHz .25 micron PII.
"
Q6:Does the new version of the AMD Athlon processor use a 0.18 micron manufacturing process?
A6:Yes. All of the AMD Athlon processor wafer starts are now on 0.18 micron process technology. The die size of the new
AMD Athlon processor is 120mm square
"
The other quote, from the same FAQ is this
"
A15:
"Mustang"
Enhanced version of AMD Athlon processor with reduced core size, lower power requirements, and up to 1MB of on-chip,
performance-enhancing L2 cache memory. Manufactured on a 0.18 micron copper process technology. Multiple
derivatives of the Mustang core are planned to address the requirements of the high-performance server/workstation,
value/performance desktop and mobile mark"
If you carefully read past the marketing speak, you'll notice this. Both the current Athlon (Thunderbird) and the next Athlon Ultra (Mustang) are based on the same
PS> It isn't possible to change the process without changing the layout, but steppings almost never result in performance increases, just better yeilds. Case in point. A
I'm tired of hearing all these people saying we don't need more power. It all depends on what you use. There will always be those who need more power, and not just in a "Tim Allen-esque testosterone induced" way, but genuinely. People have been saying that nobody needs more power ever since the 386 days. Even Intel used to say that the 386 wasn't really meant for consumer space, it was a server/workstation chip. Yet always, some clever dude found a use for that power. Back in the 386/486 days it was multimedia and video. Just when the Pentiums seemed fast enough, those crazy gaming guys came up with 3D, which needed a lot more proc power. I think 3D will carry processors until the 50+GHz region, at which point somebody will find something else to use the proc for. Even then there will be morons saying "oh, is there really a USE for this 100GHz proc?"
Ah, but not KDE 2.0, it never pops up correctly because it is treated as a window, and when it pops up, it doesn't get focus, so it ends up behind the top window.
But my point is that AMD's new CPU is simply an Athlon with more cache. No new features, no rearchitecturing of the pipeline. Don't you think they would put it in the FAQ is the actual chip was going to be changed? All along it has been known that the Athlon Ultra would be an Athlon with more cache, just like the Xeon chips are compared to the Pxx chips. The FAQ doesn't say anything about changes, just a new process. AMD has already done this process change. The Thunderbird Athlon is simply an Athlon with 256K of L2 cache, and based on a .18 micron process. Plus, it is already based on copper. Aside from the change in L2 size and speed (and any changes in circuit layout), there are no other changes. Same thing with Mustang. The Mustang will actually be less of a change than Athlon -> Thunderbird. It will be based on the same Thunderbird core (Most 900MHz+ Athlons are based on this core) with 1MB of L2. Process changes HAVE been made without architectural changes. Take PII Klamath to PII Deschutes. In that case the process was moved from .35 to .25 with no other changes. Athlon Ultra (Mustang) is the same way. Anyone without any preconceptions would read the FAQ as talking about an Athlon with more cache. Everything the FAQ talks about, (except the 1MB of cache) is already implemented in the regular Thunderbird Athlon.
I HATE autohide panels. They're so inconvenient. Both KDE1 AND GNOME are still aweful screen hogs compared to Win9x. You can make the panels smaller, but then they look ugly. You can make it auto-hide, but that never works correctly with netscape.
I know, but if you leave it out, you should be able to run Win32 applications perfectly. Windows NT, for example, runs most mainstream Windows applications, but is 100% 32bit code. The 16bit code you're talking about is in Windows 9x, where major portions of the OS (like the GDI) are simply cut-and-pasted Win 3.1 code. NT does't have any of this code, but still can run Windows applications, which means that a new OS without any 16bit code or support for 16bit apps should still be able to run Win32 applications.
Okay, I reread the docs. You're right, Willamette only has one FP pipe and one load/store pipe. However, the single 128bit wide pipe should be faster than P3's double 64bit wide pipes, and we already know taht SSE is as fast or faster than 3DNow!. An intersting article covers these, you can find it here.
.18 micron technology and 1MB of cache. The reduced core size and lower power requirements are simply a byproduct of the .18 micron process. Considering that the Thunderbird Athlon already runs a .18 micron process, it already has the reduced core size and lower power requirements. And instead of "1MB of on-chip, performance enhancing L2 cache memory" Thunderbird is "256KB of on-chip performance enhancing L2 cache memory." Thus, it IS simply an Athlon with more L2 cache.
Read the FAQ carefully. The thing is simply an Athlon with
As for Willamette and the MaximumPC artice, it is quite accurate. You can find similar articles on ZDnet, and yes, Intel HAS been quoted as saying it is aimed at the high end, but it HAS done focus shifts before. In fact, the article in the latest MaximumPC even mentions that quote, but says they may aim it at the lower to middle end to compete with Athlon. Ans since Willamette itself won't really come out in volume till very late this year, the SDRAM chipset isn't very far off. In fact, it is very reminiscent of the whole PII, where Intel aimed PII at more mainstream applications quite quickly.
Is it just me, or are Linux DE's moving dangerously into the realm of "screen space wasters" where MS apps in general look selvte, (if drab) the new Linux DE's look much more, umm, crappy. KDE2 is the most egregious offendor. On the bottom of Konqueror, there is a thick status Window that nobody ever uses and you can't get rid of. Then, the frames themselves are thick. Even the scrollbar is thick. There is too much spacing between icons, and a lot of dead space in apps like KWord. What are they CODING on? 21 inch monitors?
As far as I remember, this thing STILL is Windows-only. Since it is going Opensource, it might be possible to port gMax to Linux, but I doubt the OSS version is going to be one usable for "real" 3D artists designing games. What most likely will happen, is that someone will take the OSS gMax code, port it to Linux (which makes for a pretty easy port to BeOS I might add) and then Kinetix will use that code to port the rest of 3D Studio over to compete at the lower end of the high end 3D modelers on Linux. Quite clever, really, let the OSS community do the port for you without actually releasing important code. Of course this is good for both parties. Kinetix gets a linux port without expending much effor (since any of the other stuff in 3D Studio MAX will probably be high level stuff dependant on the lower already-ported layers rather than on the OS) and the OSS community gets a 3D modeler that doesn't have a braindead interface. Say what you will for the "efficiency" of Blender, 3D Studio MAX has a nice interface, great workflow, AND an assload of hotkeys.
What fun is pirating music if you have to PAY for it?
1) SSE2 doesn't have 2 instructions per cycle. I said it is twice as fast as 3DNow! Since SSE2 is 128bits wide (meaning 4 32bit floats per instruction) and 3DNow! is 64bits wide (2 32bit floats per cycle) that's true. Look it up. It's not two instructions per cycle, but 4 operations per instruction./ 11344">this article </a> and MaximumPC proves it.
2) You've got me on the yield problems. However, Intel has rarely had yield problems, and if AMD can take it, I'm pretty sure Intel will make it.
3) AMD cannot migrate down the Mustang since it is the same exact (K7) core with more cache. Source: Sharky Extreme (www.sharkyextreme.com) AMD/VIA roadmap, 6th page.
4) Willamette actually will be targeted at mainstream systems. Check www.zdnet.com for several articles. Additionally they are supporting PC133 SDRAM for these lower-end systems. Lastly, <a href="http://www.maximumpc.com/content/2000/05/08
Now what were you saying about not being totally sure?
Not necessarily. Most Win32 applications aren't hideously tied to the OS. Thus, you can implement the actual OS any way you want as long as you're complient with the API. NT is proof that the OS needn't look any particular way to work with Win32. As for Win32 itself, it isn't a turd. The OS that it's driving is a turd. (Though NT is a pretty damn good OS.) Win32 itself, coupled with DirectX and COM is actually a pretty good API, certainly one that is worth putting up with for the sake of compatability.