Slashdot Mirror
AMD Delays Hammer
TeJarz writes "C|Net reports that their next processor (Hammer) has been rescheduled from its original Q4 release to Q1 2003. To quote C|Net: 'The delays are occurring to accommodate the release of a new version of Athlon with a 333MHz bus, said Crank. Current Athlons come with a 200MHz bus and 256KB of secondary cache.' Let's hope this doesn't get moved again."
U can't touch this
U can't touch this
U can't touch this
U can't touch this
My-my-my-my (U can't touch this) music hits me so hard
Makes me say,"oh my lord thank you for blessing me
With a mind to rhyme and two hyped feet"
It feels good
When you know you're sown
A superdope homeboy from the Oaktown
And I'm known as such
And this is a beat-uh!
U can't touch this
I told you homeboy
U can't touch this
Yeah, that's how we livin' and you know
U can't touch this
Look in my eyes,man
U can't touch this
Yo, let me bust the funky lyrics
U can't touch this
...have a 266MBz bus
AMD = All Microprocessors Delayed
...that these days have come about because they're working Palladium support into their processors? I for one am glad I bought an Intel chip for my computer; at least they aren't in Microsoft's back pocket.
Loneliness is a power that we possess to give or take away forever
200 Bus?
I thought they had a 266 bus???
My Pentium 4 has got thirdary and fourthary caches.
My Athlon has a 266 MHz bus. The from the linked article:
..so I'm not sure where the 200 MHz number came from.
Current Athlons come with a 266MHz bus and 256KB of secondary cache
Current Athlons have 266 bus. You can still get the older 200 bus, but it died out about a year ago. Sorted in price on pricewatch
Current Athlons come with double-pumped 133MHz FSB. (effectively equal to 266MHz single-pumped)
Comment removed based on user account deletion
Anybody here have stock in AMD? I've been long on the company for like two years now, but it never seems to finally launch the Hammer!!! I was hoping for a christmas release, but that's not gonna happen now...... my stocks will get beaten tomorrow!!! :(
this was moderated funny, but now its not. it makes me upset.
I feel your pain, here, read this, it may help to cheer you up some.
The government has a defect: it's potentially democratic. Corporations have no defect: they're pure tyrannies. -Chomsky
who works at AMD, we were talking about this tuesday, that the Hammer chips will be released next year, and I told him I thought late this year. Well, looks like he was right.
Well they can take this time to perfect Hammer and drum up more software as well as hardware support.
:-)
As for the 333mhz bus, I heard somewhere that the memory bus speed isn't the bottleneck for the Athlon processors... Well, it's a chance to buy a new motherboard I guess
There are only 10 kinds of people in this world... those who understand binary and those who don't
Because the sooner it comes out, the sooner I get to play with a 64-bit OS development on a machine that gets top performance and doesn't cost $20,000. That alone is reason enough for AMD to ship it sooner.
A deep unwavering belief is a sure sign you're missing something...
And what are you?
Obsessive-compulsive? A nag? An asshole?
Do you really care so much about that one-liner? Elaborate.
STOP . AMERICA . NOW
I, for one, am hoping to replace our Alphas with cpus from the AMD Hammer series. We're about to buy a bunch of P4-based machines despite the problems we've had with certain tight loops in scientific code performing 80 times slower than a similarly clocked Athlon (according to Athlon advertised "speed", not actual clock). No, I'm not exaggerating, and this has been verified independently -- the P4 cpu has some huge weak spots that really suck if you hit them. If Hammer were out and working properly, we probably wouldn't buy the P4 machines to hold us over.
We need 64 bit machines to accomodate massive memory for our research. I'm really hoping the Hammer can provide a relatively inexpensive and *commoditized* 64 bit platform for us to work on, compared to existing 64 bit (workstation/server) platforms. And I want it yesterday. Actually, I want it last year.
I have no idea what the editors or submitter meant, of course.
-Paul Komarek
"Let's hope this doesn't get moved again."
There's a damn good reason I want this to come out soon. The sooner AMD comes out with Hammer the sooner Intel has some extremely serious competition. If Hammer can stand up to its hype the P4 won't look so hot, especially if Hammer ramps well in clock speed. Strong competition = lowering of prices. Also, Athlon XPs would then be pushed into the value market. So not only would Intel be forced to drop prices on their desktop and server CPUs, but AMD's old lineup would become and absolute steal. Sounds good for the average consumer, eh? Lets hope for no more delays.
-Yoweigh
What is the reason for the delay? Can it really be that it's just a business decision (as they seem to say) rather than a technological problem? It seems that AMD _needs_ this jump in 64 bit computing, the sse2 registers, and boost in performance on Intel. So to me, if it is a business decision, it is a poor one.
Everything I have seen shows that Intel is doing much better in performance and climbing. AMD claims there is no real technological reason, yet there must be. Anyone have insights? It seems that it would be prudent for AMD to issue better explanations -- how could it hurt to be honest? I want to see competition, if they are going to lag in performance, then they present no reason for people to buy. (A similarly performing Intel chip is close in price right now)
Guess what? I got a fever! And the only prescription.. is more cowbell!
A delay from palladium which will be included by default starting with the Hammer. It was probably delayed because longhorn aka drm-Windows was delayed and its needed to actually use the cyptography in the cpu.
http://saveie6.com/
"Current Athlons come with a 200MHz bus and 256KB of secondary cache."
Really? I thought I had an Athlon XP with a 266 MHZ bus.... oh wait, if Cnet says 200, I must be wrong!
Well they are losing 6 months of retail time. 6 months that software companies could be ironing out bugs and problems with REAL people on REAL computers, not the test labs at AMD. Also if you follow the CPU game at all you know that these chips are AMDs largest chance of gaining market share against Intel. The same chip can be used for 32 bit desktop computing and 64 bit server oriented computing. More marketshare equals more competition. Also Intel publicly has no plans to release a 64 bit desktop CPU, so this is AMDS chance to be have their foot in the door and then later have Intel respond, ok we were wrong, desktop computing DOES need a 64 bit proc. And to cut off responses, I do not have any stock in AMD. I do however believe in a non-monopolistic system. Competition in the CPU market is good. Also you know I will be buying myself a hammer setup. As soon as I can afford a 4 proc motherboard.
Incidently, you can get a nice new dual Alpha 21264 667 4u rackmount with 4GB ram and 18GB scsi (64 bit) for = $14,000 these days. With educational discount, you can buy a Compaq ES40 (with single cpu to start) for $20K. I have no idea what the used 21164 machines are selling for these days.
I don't have the same motivation for 64 bit machines (I need them for cycle servers with big memory), but I'm just as anxious for a commoditized 64 bit platform to emerge.
-Paul Komarek
So I move out and figure I wont need a stove because I dont cook much. Then I realize I like eggs but have a pentium chip. So I figured I'd buy a new box w/ the new athlon, over clock it and figure i could fry up my eggs that way. So basically this means I starve and use an old box for another 3-5 months? What a crap deal that is.
Check out my life
Any place I can look for some doc on that issue ? :( The fingers have all been pointed at software optimization and we are doing some heavy duty examinations but it sounds all too pat to me...
We are migrating from our Alphas to dual P4's and seeing a serious drop in performance that should not exist
errr....umm...*whooosh* *whoosh* Is this thing on ?
The biggest problem with current processors is that to design such devices we *have* to use dynamic logic. Ask any VLSI design engineer.. that is no joke. Infact many multipliers and dividers have to be hand edited! So delays are expected and it does reflect upon the desigers and companiesd in any way.
Before you ask.. I do now work for AMD, i work in another VLSI company, thats why i say.. its tough. Millions of gates thousands to be hand edited its a bitch.. but as they say the fruits of labour are sweet... and for AMD hammer is going to be the sweetest
My Aurora : http://www.youtube.com/watch?v=o91ZsGwJYyg
FB : https://www.facebook.com/TanveersPhotography
I'm betting they're adding Palladium. It seems likely, since these days you must make sacrifices to gain things. XP Service Pack 1 will fix a few security holes, but at the cost of your privacy. Hammer will be 64-bit and more powerful than anything you've got now, but will probably be Palladium-enabled. Or maybe I'm being a pessimist and they're not adding Palladium. Lets hope not :|
Happy New Year, it's 1984!
Comment removed based on user account deletion
struct conspiracy theory {
;-)
real : MS;
int : palladium;
int * : hammer;
hmmm is it for integrating palladuim support!
};//end of struct
Sorry... couldnt help it
My Aurora : http://www.youtube.com/watch?v=o91ZsGwJYyg
FB : https://www.facebook.com/TanveersPhotography
The hammer is a critical product for AMD that they would never delay unless there were *major* problems with it.
1) AMD is currently losing huge amounts of money. The hammer would have allowed them to sell at the high-performance end of the market again where the sales prices are higher and might have helped them reduce the flow of red ink.
2) The delay will badly hurt AMD partners such as motherboard and chipset vendors who have developed supporting products for hammer.
3) The hammer had a potential performance lead over Intel that will be greatly eroded by the time it finally appears.
4) Critical software development for hammer will be slowed which will slow eventual market acceptance of hammer.
5) The delay will build momentum for Itanium.
6) The delay will greatly reduce the pressure on Microsoft to support hammer and will give Microsoft the opportunity to also build momentum for Itanium. Depending on market conditions when the hammer finally appears, it is now even possible that Microsoft will never need to support hammer.
7) This delay is so serious that it creates real doubts that hammer will *ever* be a viable product.
Hmm basically the old, here's a quarter (35 cents, or whatever) call someone who cares for the new age and the /. crowd?
Check out my life
AMD needs to marshall its resources in preparation for a knock-down drag-out lawsuit against the Adequacy
Intel will always be one step ahead of AMD. Where do you think AMD has originations from? I'm all for competition, but intel has billions into R&D whereas amd only has millions.
And we have seen time and time again as intel puts out something that is more intuitive, faster, more stable, etc. I'm sure you can argue one of those last points, sure, but you get my drift - that i'm sure of also. And you would be your money amd knows it too.
Hard as that may be to believe, some people use their computers for real work. And some of those people run into that dreaded 4G limit--4G is not a lot of memory anymore these days. And many of these people would love to have the choice of a Hammer over Itanium.
The poster dies in a fit of agony...
A feeling of having made the same mistake before: Deja Foobar
That seams to be the exact reason they are deleying it, from the /. front page (and no deeper research). If they think they can tweak a bit more of high performance out of the XP, why doom it to low end prematurly? I mean if I ran the company I would do the same thing, actually I might keep the XP where it is and then release the Hammer as a cut above with the whatever those wierd Intel things are, then drop it to the PC market as soon as I got all I could out of the XP. Though what they are doing is at least reasonable.
Wow, sent an e-mail as suggested when clicking on "use classic" banner, and got a fast response that addressed my msg
They're waiting so they can ship the new chip bundled with Duke Nukem Forever. ;)
All movements for social change begin as missions, evolve into businesses, and end up as rackets.
This guy is quite rude, offensive and disrespectfull to others and is very arrogant. Ignore him and add him to your foe list like me. Also he has been very supportive of drm in a troll like way and feels free to flame other people who actually like their fair use rights.
http://saveie6.com/
I am a big computer geek. I'm 20 years old and I've been into these things since I was 12. I learned BASIC and HTML in 8th grade, and C an C++ sometimes around 10th grade, which was also when I got into using Linux (Slackware '98!). I have a big history in gaming, networking, programming, and fiddling around with other general random stuff, including lots of multimedia. Over the years, I've gone from a 486SX 25MHz, to a DX2 66MHz, to a Cyrix 6x86 166 (don't ask what I was thinking), to a K6 233, and finally, to a Celeron 366 which I have been running for two years and am currently running at 550MHz. This CPU works great, and it does everything I need it to do. It compiles kernels fast, it works with multimedia and video editing at a decent speed, it encodes MP3 and Ogg at a good rate, and it can handle the games I like (Quake III and Unreal Tournament, mostly). Why haven't I upgraded, you ask? Well, I did for a while, to an Athlon 900, and the performance was great, but I killed it myself. Ever since then, I've just stuck to the Celeron. Now, after Athlons have been out for a long, LONG time, I have an Athlon XP 2000+ sitting around, patiently waiting for me to get a motherboard and case to go along with it's RAM and 80GB hard drive. But I am patient, I'm not worried, I'm not some kinda freak that believes extremely strongly that without this boost in performance I'm gonna freakin die. That said, I will probably not be getting an AMD Hammer CPU until one or two years after it's been in the market. I might get it sooner, who knows, but I am not in a hurry for this thing. There is no rush for me. Why? I don't know... I mean, I do a lot more with computers than most people I know running processors operating at over 1GHz or 2GHz, and I'm really happy with my simple, old, yet still fast, robust, and fully-functional Celeron 550 CPU. Upgrades are overrated, and anyone sweating diesel because this thing has been pushed back a few times, needs to take a chill pill, and calm down. A good thing... a TRULY good thing... is well worth waiting for.
Comment removed based on user account deletion
Now, after Athlons have been out for a long, LONG time, I have an Athlon XP 2000+ sitting around, patiently waiting for me to get a motherboard and case to go along with it's RAM and 80GB hard drive.
.. but then you blow your entire "i don't need to waste money" premise by buying a state-of-the-art processor and then sitting on it until it's middle of the road? i don't get it.
dude - if you've got an Athlon2000+ that's "patiently waiting around" then you must have bought the thing when it was brand new -- and paid a hell of a premium to let it sit doing nothing. same chip's probably half price now. i can almost buy your "my 550 celeron runs everything i need!" story
i could live a little longer in this prison
If I recall correctly the original release timeframe was Q4-Q1.
I've only had it sitting around for a month. It still only cost $100 back then, ya know. It's gone down to what, $90? Ooh!!! Second argument about the Celeron 550 doing everything I need... yes it does, but I am beginning to want it done faster, especially since applications have finally become taxing enough to require more resources.
I can probably send you some test code (same for anyone else who asks), but I'll have to check with my advisor first. The smallest I've made the test code is a bit under 300 lines. It's been run on Alpha 21264 EV67, Athlon C, Athlon XP, P4, and P-III, and one other Pentium-ish platform. At least two (I believe it's actually three) profilers have been run to find the bottleneck; it appears to be the floating point unit stalling for data.
Here are the timings. Note that these are just via "time" on GNU/Linux or a wall clock on Windows (or something -- I didn't do the Windows tests).
P4 dual Xeon 1.7GHz/gcc: 82 seconds
P3 1000/msvc: 18 seconds
Athlon C 600/msvc: 2 seconds
P3 1000/msvc, using floats and sse:
2 seconds
Alpha 667/gcc: 2 seconds
Athlon XP 1900+ 0.88 seconds
I guess the Athlon's clock was closer to the P4's clock than I recalled in my original post. Either way, the slowdown on the Pentiums can be easily seen.
-Paul Komarek
but it turns out you can't touch this.
There's nothing Intelligent about Intelligent Design.
We need 64 bit machines to accomodate massive memory for our research. I'm really hoping the Hammer can provide a relatively inexpensive and *commoditized* 64 bit platform for us to work on, compared to existing 64 bit (workstation/server) platforms. And I want it yesterday. Actually, I want it last year.
Have you considered IA-64? HP's Itanium 2 machines should finally be available for purchase (if not now, within the next month or 2), and if you're writing your own code, compatibility should be a non-issue.
The zx6000 is the SPEC2000 workstation performance leader.
Using Intel's and/or HP's compilers, you can generate some killer floating point code, if you know what you're doing. Itanium 2 demonstrated pretty clearly that IA-64 can potentially offer unbeatable performance and it's a 64-bit architecture with support for massive amounts of memory. A bit pricey, but it should meet your technical requirements far better than a Hammer would.
But judging from the benchmarks you posted further below, I question your know-how. You compare a GCC-compiled program running on a Pentium 4 to MSVC-compiled programs running on Athlons?
What other environmental factors are we unaware of? Why would you use an optimizing compiler of such poor quality as GCC? Have you tried Intel's compiler? It provides a speed boost for both Intel and AMD processors (the Intel compiler is just a really good compiler -- it's not all about optimizing for a specific CPU.)
May I ask why you are going to P4s instead of just getting more Alphas? You yourself said you are loosing quite a bit of performance with the P4 compared with the Alpha, but you don't say why more Alphas aren't an option.
Slashdot gets worse every day... Pipedot: News for nerds, without the corporate slant
SickRick: stop feeding the trolls. It just makes you look like a moron.
Oh, and most of us grew out of the "I know you are, but what am I?" style of insults in sixth grade. If you're going to insult someone, at least do a good job of it. (Look at the trolls above for some pointers.)
How can we continue to believe in a just universe and freedom to eat crackers if we have no ale?
Any place I can look for some doc on that issue ?
Darek Mihocka of emulators.com has written a whole bunch of stuff about the Pentium 4. He has examples of code that performs badly on Pentium 4, although I'm not sure how the most recent versions of the P4 would work on his code samples.
http://www.emulators.com/pentium4.htm
steveha
lf(1): it's like ls(1) but sorts filenames by extension, tersely
I'm right there with you. I have this fantasy of making a 10k volume ebook library full-text searchable, so the promise of added memory one the hammer, plus the performance, makes me salivate.
Previously, I'd have had to shell out for serious hardware (and charge a subscriber fee), but the possiblity of DP Hammer servers, leasing for less than $2k a month (I lease, but I majored in English lit., and my ISP doesn't charge extra for bandwidth), makes it just barely possible.
For years, before I found a solid revenue stream for my site, I gutted it out with a little cash from advertising, and a Cobalt RAQ with a 300 or 450mhz AMD K6-2 (revolutionized webhosting for dumbasses like myself).
I hope AMD takes the time to get it right, and I also hope AMD can hold up well in the meanwhile...
(Also agree with your point about the PIVs, my server now is dual PIII-933s, as is any other server I'd consider, wouldn't touch a PIV for a thing that needs to be up 24-7, and can't really afford Alpha...)
Paul, go with Itaniums2 running HP-UX. On scientific codes, those are the fastest machines available today, and will still be when Hammer is released.
Hell, I got a 500MHz Alpha system for $300, used.
You are thinking about this all wrong. You seem to believe that a thousand dollar AMD chip is going to perform like a mainframe. You may be seriously disappointed when you figure out that these new 64-bit chips aren't going to make your current systems obsolete at all.
Slashdot gets worse every day... Pipedot: News for nerds, without the corporate slant
I live in Austin, and have friends who work at AMD. AMD may make a great processor, but their motherboards suck because the motherboard testing department's manager tries very hard not to find any bugs. (Test stuff that you know will work. Never install an OS, just use a ghost image of preinstalled windows XP copied through the network onto the hard drive. Testing with linux is a no-no, because you actually find reproducible bugs in the hardware! We can't have that, we're a testing department...)
At least one woman was fired for making a Linux test CD and distributing it internally around the company, against that manager's wishes. Her name's on the test CD, and it was still being used inside AMD last week, but she answered too many Linux questions for people outside her department and as such was labeled "not a team player" in the internal politics. As far as I can tell, that was the most knowledgeable linux person they had anywhere near that area.
AMD makes great processors, but until they get a new motherboard testing department, they'll have nothing to put them in.
Price/performance on the Alphas is low for most of our applications, making the only Alpha selling point it's 64-bitness for big memory. Many of our apps don't need that much space and can run on x86. The few apps that do need 64-bitness will be run on our existing Alphas. If we could get dual Alpha 1GHz machines for the same price as dual P4 Xeons, we would.
There's also the issue that finding replacement sysadmins for the Alphas isn't as easy as it is for the x86 machines. Alphas aren't much different to admin, but it can be a bit of a speedbump.
-Paul Komarek
Wow, my bullshit sensor just went full-tilt. A certain tight loop, huh? Like this maybe:
while (true) {}
Seriously - there's no such "tight loop". It's bad code, or it can be done another way. Poor compiler optimization is no reason to go around half-cocked claiming the P4 performs '80 times slower'. Recompile with a real compiler, or optimize it.
And you think Hammer is going to mystically solve your problem? Either rewrite, reoptimize, or get a PA-RISC, or Sparc based machine. What kind of crap is this?
I'm glad your happy with your slow Celeron, but don't assume that for the rest of us we don't need the fastest CPU possible. Time is money and the faster myself or someone else can get their work done the better. There are a ton of apps out there right now where that speed CPU is just no longer a viable solution.
I do happen to agree with not freaking out about a processor release date. But do realize that people are excited about this cpu for a reason.
BTW many of us here were using computers and programming before you were born. Your only 20 for Pete's sake.
If you wanna get rich, you know that payback is a bitch
We've sort of considered IA-64, but don't really want to make that expensive of leap into that performance mess. We're not going to buy into a *radically* new architecture weeks after its release, either. And we can't afford to spend lots of time tuning our code for one platform or another -- portability is key. gcc is our compiler of choice because we don't have to screw with (as many) platform-specific issues.
;-) The Windows tests were done by a different person, on his own time, 2500 miles from me. I did the P4, Athlon XP, and Alpha tests using gcc. You can at least compare those numbers. And in the end, the compiler (in general) should not make a 200% to 8000% performance difference.
"But judging from the benchmarks you posted further below, I question your know-how. You compare a GCC-compiled program running on a Pentium 4 to MSVC-compiled programs running on Athlons?"
I could snottily retort that I question your reading know-how, since msvc was for P-III and Athlon C, while gcc was for all the rest; but I won't.
For the tests, I used the same compilers we use for development and distrobution. We don't have time to screw with the industry's popularity contests. We do algorithmic and data structure work, aiming for 10000% speed-ups that just aren't available through compiler cleverness. The Intel compiler won't help us when compiling on Alpha, MIPS, or PA-Risc.
-Paul Komarek
If you weren't anonymous, I might take you more seriously. =-) I'm very interested in price/performance and maintainability. I think the Itaniums will lose on price/performance for a long time. Since Itanium(2) is so far from being a commodity processor (like our Alphas), we'd have to expend extra effort to maintain them and train others to maintain them.
The bottom line is that Itaniums only seem to make sense for people who get them for free.
-Paul Komarek
>Also Intel publicly has no plans to release a 64 bit desktop CPU
Right - we haven't heard that one before?
"No one needs a [insert MHz here] CPU on the desktop, so they'll only be used in servers."
Bulldookey. Bovine excrement. Ruminant evacuation.
If they price it right (and eventually they will HAVE TO if Moore's Law continues) everybody will have one in their machine, desktop, laptop, PDA, whatever...
Richard Steven Hack - This sig is TOO GODDAMN SHORT TO DO ANYTHING USEFUL WITH! MORONS!
Your repsonse is not particularly well-related to my post. I hope for the Hammer to replace our Alphas in providing big memory per process. I didn't claim that the P4 performs 80 times slower. In fact, the P4 Xeon 1.7GHz generally outperforms my Athlon XP 1900+; of course, it also costs more. But on a bit of code I wrote for my research, it goes 80 times slower.
I can't spend all my research time optimizing for one silly cpu. My code is run on about 4 different cpus (only two different instruction sets, though) at present. Another cpu (with another instruction set) will be added soon. If Intel wants my code to run fast on the P4 Xeon, they can contribute to GCC; but I don't care. I'm happy to recommend that users of my code buy Athlons or Alphas.
-Paul Komarek
Everyone always makes the same really annoying mistake when it comes to athlon fsbs. Athlon front side busses do not run at 200MHz and 266MHz. They offer bandwidth equivalent to 200MHz and 266MHz by using both sides of the clock (DDR) on 100MHz and 133MHz fsbs. All new athlons use 133MHz DDR fsbs. The hammers will support 166MHz DDR memory busses, offering performance equivalent to 333MHz SDR memory.
However, the notion of "fsb" is a little blurred with the hammer. Hammers will be directly connected to dimm banks and have integrated memory controllers, so the speed of the fsb will no longer be a determining factor in memory bandwidth. (* see mp note below) The traditional fsb to the traditional northbridge will be replaced by a "high speed" hypertransport link to a chip that connects to the agp slot, and has another (slower) hypertransport link to what could be called the south bridge. This "south bridge" will then connect the pci bus, serial ports, hard drives, usb ports, and any other devices that need to talk to the processor or main memory.
*What does this mean for MP systems? Well, that's actually the really cool part. By moving the memory controller onto the processor and providing communication between processors over a hypertransport link (3.2GB/sec for dual, 6.4GB/sec for quad and above), memory bandwidth actually increases as more cpus are added! This is in contrast to a normal MP system where as more cpus are added, there is increased competition for a fixed resource (main memory) which is already the bottleneck in many single processor applications.
That's my rant on terminology. Here's the question:
I'm no kernel hacker, and I certainly don't know anything about writing schedulers, but it seems like this would require a change in how processes are handled in hammer mp systems. In traditional mp systems, every processor has equal access to main memory. If a process gets moved from one cpu to another, there's initial overhead to do the moving, but after that it can still get to its areas in memory without any problems. On a hammer mp system, migrating a process from one cpu to another would mean that in order to access its memory it would have to reach out of its cpu's hypertransport link, into another cpu's memory controller (which may or may not be busy) and into the attached ram. Considering there would not be enough bandwidth available on the 3.2GB/sec hypertransport bus (in the case of a dp system) for both processors to reach into eachothers 166MHz DDR memory at the same time without suffering a performance hit, it seems like there would definitely be an advantage to keeping processes close to their data.
What changes would this require to scheduling and process management code, if any? Has this already been addressed, or are there people working on it in the linux kernel?
The P4's x87 FPU and x86 ALU are just plain slow compared to P3s and Athlons. Though I am surprised your code is running 82x slower. I'd expect more like 2-8x slower for compute bound code. You can get a somewhat sensationalistic overview of why it's so slow at this link.
If you want more in-depth numbers you can compare appendix C of the Intel Pentium 4 Optimaztion Manual with chapter 29 of Agner Fog's Pentium/II/III Optimization Manual. You can see the Athlon numbers in Appendix F of AMD's Athlon Optimization Manual.
If you want to do number crunching with Pentium 4s your best bet is to use the SSE2 instructions/registers. You should be able to get a noticable speedup by using the Intel C++ compiler and telling it to use SSE2 instructions. If you want to eek out max performance you'll have to use assembly language. Though you can probably get most of the way there using the Intel C++ Compiler's SSE2 intrinsics.
I'm curious as to why your code is so much slower on a P4 than on an Athlon. The best way to find out would be to look at the assembly code that gcc is producing. You can do that by using gcc's -S option. If you'd like send me the C code and the output from -S and I'll see if I see anything obvious.
I'm somewhat paranoid about posting my email address. My paranoia seems to work, as I've received no more than the occasional spam in the last few years. My email address is my slashdot user name at woh.rr.com.
You ever notice how all the Hammers are clock speed locked at 800MHz? Yea, there's a reason for that. They're having problems cranking the clock speed up. For 800MHz they're fast as hell, beating P4 with twice the frequency, but they're not gonna release them until they clock faster than current Athlons so they're trying different types of transitors and what not.
How the hell do I know that??? Look where I live, take a guess...The birds outside my window know things.
it appears to be the floating point unit stalling for data.
2 /p4_240 0-01.htmlt hwood.htme ct.htm
s or.htm ?iid=Homepage+Find_Products_Processors&
Well, if it's stalling for data, your problem is probably that the P4 has a *tiny* L1 data cache compared to... uh... anything. It's only 8K, compared to the Athlons 64K. See the following URLs:
http://www.tomshardware.com/cpu/02q2/02040
http://www.geek.com/procspec/intel/nor
http://www.geek.com/procspec/amd/k7sel
It's probably also worth noting that Intel does NOT list the P4 as a "server processor". The P4 is listed as a desktop or workstation processor. Only P3, Xeon, and Itanium chips are recommended for server use:
http://www.intel.com/products/browse/proces
You might want to show that to management and reconsider your purchase of P4 equipment. Even a P3 is likely to perform better.
You can post this part of the code for us? ;^)
I would like to show for a friend. He isn't convinced with 80% less performance for clock. 80000% I think is sufficient for him
What compiler you use?
Thanks.
Even a P3 is likely to perform better.
:-) I just mean that if the P4 is performing like crap for your applications, then you shouldn't use that processor.
And by saying that, I don't mean to imply that I think the P3 is a good choice, (I like the Athlons
Poor compiler optimization is no reason to go around half-cocked
1 &cid=4249 911
It's not poor compiler optimization. The P4 has a *minute* L1 data cache. It just isn't suitable for complex computations. See this commment and its parent:
http://slashdot.org/comments.pl?sid=3983
Something I've never seen a good explanation of -- is there performance-wise any difference between a 266 MHz clock with data transferred once per clock and a 133 MHz clock with data transferred twice per clock (despite the actual clock ticking rate of course)?
10 PRINT CHR$(205.5+RND(1)); : GOTO 10
that's much bigger news than some delay - even bigger news is that it is not the first processor they produced :) "C|Net reports that their next processor (Hammer)". How low can you go :)
Is the delay of the Hammer CPU due to design- and production-issues? Also some notes on AMD's financial situation.
Site & blog: http://www.mayaposch.com
iNTEL does have their own compiler, that they sell, I guess they rather have you running their compiler than gcc.
That said, which version of gcc did you use? There seems to be vast differences between them (and certain companies seems to like 2.96.x which is NOT a valid gcc version. If gcc -v gives you the 2.96.x version, get a new gcc) and there are reports about speen increases in the 3.x series.
I was mostly curious, I really would like to see that code of yours, but I realise that you wouldn't wanna give it away. Any chance you could write some dummy code that gives the same results (as far as the P4 being slow that is)?
I may be able to give the testing code away; I'm waiting for a response from my advisor (GMT-5, so it will be a few more hours before he's even awake =-). Send me an email if you'd like the code.
The P4 used gcc 3x, while the Alpha and Athlon XP used gcc 2.96. =-) If anything, this should give the P4 an advantage.
The Athlon C and P-III results were all msvc. I don't know which version was used, because I didn't do the tests.
-Paul Komarek
Maybe AMD are geting ready for the pre-Christmas ruch to buy PCs. Remember that most of their customers don't know and don't care about the difference between 32- and 64-bit. It will also be easier for AMD to make bigger margins on these 32-bit athlons, since the change in process to make them is much smaller. It's just a small evolutionary step, rather than a revolution.
The 3 months up to Christmas has never been a good time to buy a PC. Prices remain relatively flat from September on until New Year.
Stick Men
I didn't have any of those fancy schmancy optical mice. No! Back in my day we had to use real mice. And then they'd run away so you had to use the stick as a pointer. And you don't know the meaning of upgrade. Heck, I'd have to walk uphill in the snow to get a new stick to use. It wasn't one of them fancy Maple sticks. No, it was one of those that were green and had thorns and moss growing on it.
You young people make me sick. Give me the good ol' days I say.
Why should they rush the Hammer when the Itanium is failing as is? They know they can't push people to use their 64-bit capabilities, just like people didn't switch to Alphas. Squeeze every ounce of strength from the Athlon as they possibly can for now. Let Intel push the IA64 standard on everyone first to create a demand to migrate from 32-bit to 64-bit. That's where AMD plans to make their killing.
I would imagine it would be better to release Hammer ASAP and create the 64-bit market themselves. Then again, I don't know the logistics required for such a launch, nor do I know exactly how much better, if any better, x86-64 would perform. Let's face it, not many people care about 64-bit versus 32-bit, they only know what the dork at CompUSA tells them. And if Hammers can't outscore P4's in the 32-bit apps that very short-sighted people care about, then there is really no place for Hammer in the consumer market.
From what I've heard, mostly from internet gossip, is that AMD is having problems making Hammer scale high enough to beat the P4 in 32-bit apps, although it only requires roughly 1 Hammer MHz to beat 3 P4 MHz. I've also heard that AMD is having problems making Hammers run above 800MHz. With the expected debut of the P4 at clock speeds above 3GHz, the Hammer doesn't stand much of a chance in 32-bit apps.
In short, don't expect to see Hammers until Intel manages to salvage the Itanic.
Still running a K7-500 and it works fine. The only taxing app _most_ people run are wild 3D games that will just eat as much machine as possible (good software engineering I reckon - nicely scalable). But..... It won't hurt AMD. Itanium2 isn't gonna sink them, the PC market is in recession, anyone who bought a machine in the last 5 years won't need to upgrade for a while.
All I want from Hammer is the 64bit address space. If you write apps with big data (like simulators) you'll be hapy for that address space - hey! just map the whole harddrive into memory the memory space.
I think people need to find _better_ things to do with technology not just _faster_.
Matthew.
"None of this shit works" -W.Shatner
::shakes fist::
I belong to the ______ generation.
"In the world of tools, there are only two kinds;implements of persuasion and implements of destruction. A hammer combines these tasks."
It will happen after computers routinely need to address more than 2 GB of RAM. Which for PCs just means a couple more generations.
All of the jostling that you see now is to make sure that when consumers start realizing that they can't use that much RAM on a 32-bit CPU that they have somewhere to migrate to.
This isn't a particulary new requirement. You have to be careful about selecting pages for processes today even on single CPU systems to avoid cache thrashing. Because of the way first or second-level CPU-caches map to physical memory, certain memory-access pattern lead to constand reloading of the cache, making it pretty ineffective, even worse if it wasn't there in the first place. By carefully mapping physical pages to virtual memory the OS can avoid this problem. Solaris does this, I don't know about Linux. Probably.
So, this is one new requirement for the memory management code. No problem, we just make sure all process pages belong to one particular CPU and schedule this process to this CPU only. Everything is fast and nice. Intel is doomed. Or is it? Not so fast, all this is probably a bad idea:
We can't make sure pages on the right CPU a even available. What if they are not? Give out wrong pages? This would lead to results in running time which are not reproducable. This is really bad. It gets worse. What it the right CPU is not available because it's running some other process?
Probably it's best to allocate evenly distributed pages (some fast, some not so fast) to processes and not schedule them special in any way.
Easy ;)
It is conceivable that Hammer could have weak spots as well. But so far AMD has been pretty good about not banking on anything too wild or crazy, so I agree that these could be a real improvement for scientific applications. (Whenever they finally become available.)
...a hammer in the morning...
:-)
Sorry, couldn't resist
I feel so sig.
Not only that, but there seems to be a little barb at the end of MANY summaries. Frankly, I agree, many times it's either uncalled for, unexplained, or vague to the point of misinterpretation.
I know it's a small issue, but it bugs me too!
Anything with 64-bit doom is good enough for me :)
/^[A-Z0-9._%+-]+@[A-Z0-9.-]+\.[A-Z]{2,4}$/i
I am also invested in amd but I have to say this. Look at the valuation (book value) of the chips. Every intel share you buy is worth about $0.33 worth of assets. So you have to hope they triple their worth for your share to be worth the $1 you invest per share.
Amd's book value is about $1.40 for every $1 you invest. So if they liquidated and sold everything for their market value (I know, a stretch) you would gain 40% on your investment.
And even though I love dell, their book value is about 16x its stock price. So people are betting Dell takes over the market from what I can gather.
As not to be out-done by Intel.
Another Melted Device.
I'm just kidding! (sorta) I like AMD, I use mainly AMD myself, but they have in the past been hot beasties.
Jonathan
I guess C|Net doesn't proofread their articles before they send them out. No need to go any further, we all know it.
-- Liberalism is a mental disorder.
Folks,
While AMD works out the bugs of their Hammer line of CPU's, don't forget that AMD still has a card to play in terms of CPU competition with Intel: the Barton-core Athlon CPU due later this fall.
Unlike the Athlon CPU core designs since the original Thunderbird-core Athlon's, the Barton-core Athlon sports a larger 512 KB L2 cache on the CPU die, which will offer dramatic performance increases, especially with memory-intensive programs. Remember, the current Thoroughbred-core Athlon CPU rated at 2600+ already has reached parity with the Intel Pentium 4 2.53 GHz part, and that's with only 256 KB of L2 cache on the CPU die and using DDR266 DDR-SDRAM! What will the Barton-core Athlon do?
AMD has decided to put off at least one customer for yet another period amount of time. I am patient. I will get what I want or I simply won't buy anything. I waited patiently for the palomino so that I could build my dual system. The palomino came out so late that I thought to myself, "Hmmm, I think I am gonna hold off until this fall when hammer comes out." Sadly, it appears as if Intel isn't AMD's only enemy. Their inability to release a chip on time will hurt them more than Intel will.
Russian Russian Russian RussianDollSig DollSig DollSig DollSig
It uses separate write and read paths, each of them being DDR. This can improve performance, if the CPU can schedule write and read transactions at the same time. I would expect that there is no 2x difference between QDR and DDR busses.
There may be a need to tune this specifically to Hammer/Opteron though (and even this could have been done already - need to look again at x86-64 port)
Have you tried powerpc ? G4's altivec unit might be able to give you a performance boost, i've considered them at work, but since we dont write our own code, we cant, since the program isnt avaible on ppc. A vector unit is good for some types of computations, maybe yours is one of them.
JonB
Fascinating read! Thanks for the link.
it's in my head
If this means Barton sooner rather than later, I'm happy... although from what I've read Barton (166 MHz FSB, 512k cache) is still slated for Q1'03. Sigh.
Why? Because I'd like to get a Barton CPU for my next computer. I'm already in the waiting game for the NV30 and (to a much lesser extent) Serial ATA, so putting a better CPU on the list isn't a big deal.
Why not Hammer? Because I know better than to buy a first generation CPU with first generation motherboards. Barton is just a mild revision to a 4 year old CPU core, and the motherboards are now hitting their 6th generation (KT133, KT133A, KT266, KT266A, KT333, KT400).
For those who need the speed, power, and addressibility of a 64-bit chip this announcement sucks, but for those just looking for a faster current generation chip it's not entirely bad.
I'm hoping it comes out sooner because that will obsolete their current lines that much sooner and start the fire sale on older, slower (but still fast) XP's.
Trailing edge of technology, can't beat the cost to value ratio!
ACHTUNG! Das computermachine ist nicht fuer gefingerpoken und mittengrabben. Ist nicht fuer gewerken bei das dumpkopfen.
Something I'm going to throw in here that's probably not related to the problem you're seeing:
Hyperthreading in Intel's Xeon processors are supposed to speed everything up, but are slowing down some apps we use here at work. I have no hard data aside from some benchmarks, but what I suspect is happening is this: hyperthreading enables "virtual" CPUs; so much so that the BIOS sees 4 procs on our dual proc machines. So what happens if you have two CPU intensive threads what happen to get loaded onto two separate virtual CPUs, but the same physical CPU?
I would think that the hyperthreading would be smart enough to account for this case, but it's my best guess as to the slowdown we're seeing.
We have an animation/AI/machine vision program that runs dog slow on the P4. More specifically it runs at 35 "fps" (AI and rendered frames) on the P4 (xenon) 1.8ghz, 41 fps on the P3 (T) 1.2 ghz, and 51 fps on the Athlon (mp) 1.53 ghz.
All systems were dual with one gb of memory (rd, sd, ddr, respectivly).We tested with MS and Intel compilers (these #'s are the best for each cpu).
Is life so dear, or peace so sweet, as to be purchased at the price of chains and slavery?
The sad part, particularly for those of us who came in on the cusp of home computers, games, etc., is we've been waiting on vapor or late products for years and know the feeling too well.
"It's really great and it's gonna be so awesomely good that you'll roll around on the floor in the packaging! .. Oh, and it's not finished yet, so we're pushing it back a few more months, but it'll really be worth the wait! Yow!"
At least AMD is more likely to bring it forth than a lot of things I never saw and hung on the edge of my seat for. Ah, well, hopefully MB makers and software people put the extra time to good use, i.e. Q/A.
A feeling of having made the same mistake before: Deja Foobar
Err, I have no such illusions. I expect the Hammer to be about 20-30% faster at a given clock than existing chips, which is somewhat optimistic, but entirely within the expectations for the chip. I want a 64-bit machine because there are some things in OS development that are more fun when you have 64-bits of address space. Things like single-address space operating systems and persistant virtual memory stores become feasible when with 64-bits of address space while they aren't so nice to implement with only 32 bits.
A deep unwavering belief is a sure sign you're missing something...
Well, people want the hammer released because every program made for x86 can run on the hammer as it is an x86 processor with a 64-bit Processor Word (the amount of data the processor can process per click, tick or cycle) capacity, over the typical 32-bit Process Word.
Intel's Itanium processor (and Itanium2) are IA-64. This is a NEW architecture, and does not offer the same support for software because it doesn't work like an x86 processor. Even though some operating systems support IA-64, not many operating systems do, because to write in assembly for this processor would be radically different then writing assembly code for the x86 that most programmers presently run.
Assembly works by controlling exactly what data goes to what register inside the processor, and with a completely different specification, you would have to relearn Assembly for the IA-64.
With the hammer, since it is x86, programmers wont have to relearn anything. They will just be able to get a motherboard and processor, and they will be able to start coding immediately. Since the x86 is typically associated with 32-bit words (the 8088, the x86 predecessor could only handle 8-bit words, the 286 family could handle 16-bit words and the 386 family was the first x86 processor to handle a 32-bit word.), engineers have termed the Hammer and processors like it as x86-64 processors. Eventually they will just become x86 processors, once they become standard.
So, That is why people want it now. They want the improved processing capability because it will offer more speed than the current processors available on the market. I still have a P3 (had an Athlon MP system with 1gb of registered DDR133 (PC2100) memory, but it got power surged into submission) because I want to have an updated processor.
But I will say this: If Intel makes a Pentium 5 processor, than it will most likely be x86-64.
All that schooling and they never taught you how to write. What a shame.
It's probably also worth noting that Intel does NOT list the P4 as a "server processor". The P4 is listed as a desktop or workstation processor.
Quite honestly, I think workstations tend to be more floating-point intensive than servers. For example, how many floating-point calculations does 3D CAD software do vs. Sendmail or LDAP?
So, new PC customers should be buying "servers" for any graphics, mathematics, or scientific work. This only increases my dislike of Intel's marketing tactics.
Perhaps Intel should market the P4 as an administrative assistant's toy, and let the engineers and scientists go to Sun, SGI, HP, and IBM for real workstations?
Healthcare article at Kuro5hin
By moving the memory controller onto the processor and providing communication between processors over a hypertransport link (3.2GB/sec for bandwidth actually increases as more cpus are added! This is in contrast to a normal MP system where as more cpus are added, there is increased competition for a fixed resource (main memory) which is already the bottleneck in many single processor applications.
This is true only if the processors are running tasks with unrelated working sets (and if the data for each task is in that processor's memory).
If you have tasks that require memory managed by another processor, you have to go through the hypertransport link and the other processor's memory controller to get it. This will be _slow_. HT is decent, but nowhere near as good as a direct connection to memory, and there _will_ be delays due to arbitration on the second chip and the various buffering stages the data transfer has to go through.
So, for multiple processors working on a shared workload, you're screwed.
The only way to ameliorate this is to have very smart OS-level memory management that can duplicate shared-but-not-modified pages across multiple memory banks, and both OS and processor support for update-based coherence between the banks. The hardware support for this is a bit tricky, and the OS support will be a nightmare if the OS wasn't NUMA-friendly to begin with.
And under some cases - like tasks on multiple processors competing for access to a lock or all heavily modifying the same data page - you're screwed no matter what you do.
So, don't rejoice yet. We'll only know for sure how well this will work when we have Hammer systems on our desks.
I haven't tried the ppc yes, but we've considered ppc machines. Vector processing could really improve parts of our algorithms. However we can't afford to spend time on things like altivec and sse, and must remain portable.
-Paul Komarek
We've sort of considered IA-64, but don't really want to make that expensive of leap into that performance mess.
What performance mess? You mean to say unbeatable performance is now a bad thing?
From what I understand, the integer performance is stinky, and that it's going to take a *long* time before gcc really produces good code for Itanium, and that the Itanium is *really* expensive. Is Itanium really outdoing Alpha or PA-RISC on Spec? I haven't seen news of such a result.
And in the end, I'm interested in price/performance. As I replied to another poster, the Itanium only seems to make price/performance sense if your lucky enough to have Intel give you one for free.
-Paul Komarek
You can't believe how much I agree with you. I'm very tired of having to wade through "server" literature just to find a good workstation. OTOH, if you think of the workstation as a "cycle server", well .... =-)
-Paul Komarek
I now have permission to send the code, but I don't have an email address for you.
-Paul Komarek
The only situation in which book value means anything is when a company is going to be taken over and sold off in pieces, as happened a lot in the 80's. Even so it is not worth what you might want, for instance if AMD was in trouble there are very few possible buyers for their factories, and those buyers won't buy assets at book value, they will wait for AMD to get into worse trouble and try to get a bargain. Many investors have been burned when their holdings liquidated below book, and creditors were first in line for the proceedings.
When liquidation is not a current risk, how should you value a company? The economists answer is that the value of a company is the estimated current value of the future returns from owning it. Those returns come out of profits made. You shouldn't strongly care whether those profits are reinvested in the company (for bigger profits later), paid out in dividends (immediate cash) or spent in stock buybacks (raise the stock price to pay you back indirectly).
Given that the present is the best guide we have for the future, the best estimate of future profits are current profits (also called earnings). So the ratio between current earnings (aka profits) and the price of the stock is a pretty good guide to how over or under priced a company that you expect to continue along is. The importance of this ratio is justified by basic economics, whether or not the company is one which has huge fixed investments it needs that show up as a large book value (eg Intel) or whether it has low inventories and depends on rapid turnover with many small profits (eg Dell).
This ratio will, of course, mean less if you expect to see the company sold off in pieces, or if the company is growing and you expect larger future profits. But overall in the long term you tend to see most companies with P/E ratios in the range 15-20. Now let us look at the P/Es of the companies you listed:
AMD: N/A (no earnings!)
Dell: 38.33
Intel: 18.45
Which means that unless you expect AMD to turn around, it isn't worth much. Dell is historically overpriced, but by a much smaller factor than book value lead you to think, and Intel is at a historically reasonable price. Of course the current market is historically way overvalued - still. (You may wonder at how stocks could be overvalued after several years of being hammered. Well that was the size of the bubble preceeding.)
An excellent introdution to how this all works is How to Buy Stocks by Louis Engel.
Of course the wise technology investor will focus on 2 questions when it comes to chip companies. The first is who will survive to see the standard consumer PC face the 32-bit barrier. The second is whose 64-bit strategy is more likely to win in the market.
I don't know if AMD will survive. If they do, then their 64-bit strategy is much better. Intel will definitely survive but breaking backwards compatibility is a darned big iceberg for the Itanic. Transmeta is in serious trouble, but they have the best 64-bit strategy. (It is, "We can ship whatever wins!" They literally implemented AMD's instruction set before AMD could.)
It's called Market Share. It's a term referring to who is winning in the game of industry. If you've got it, you've got the power. The 64-bit desktop market is new, and AMD needs to get the Hammer out first to establish it's presence in this market. If they are second, they have a harder time getting market share. The fact that intel already has such a strong mindshare with home computers is something that may be overcome with the new market, but only if AMD makes a good processor first.
the "middle" means you don't have the guts to choose you silly little troll
For current Athlons, the FSB speed isn't a major problem. Tests of a 2400+ with 166Mhz (333 effective) FSB have shown little to no performance improvement over 133Mhz FSB (both with PC2700). However, as CPU/L1/L2 clock speed rises, the speed difference between this and the 133Mhz FSB will grow. This means that though a 166Mhz DDR FSB won't help the 2400+ much, it will make more of a difference for a 2800+ or 3000+ (assuming no differences in cache design - larger cache should reduce dependence on external memory speed).
The Sanitations (Sung to the tune of "My Girl," by The Temptations)
"My Ass"
I've got indigestion
On a smelly day
When its brewing inside
I've got pain like a gay
Well, I guess you'll say
What can make me feel this way?
MY ASS. (Choral) My assss, My assss.
Talkin' 'bout MY ASS. (Choral) Oooooh.
I've got so much dysentery
No one envies me.
I've got a nastier rump roast
Than dogs with worms
Well, I guess you'll say
What can make me feel this way?
MY ASS. (Choral) My assss, My assss.
Talkin' 'bout MY ASS. (Choral) Oooooh.
Ooooh, Hoooo. Hey, hey, hey. Hey, hey, hey.
I don't need no EX-LAX
Senna or a fleet
I've got all the diarrhea, baby,
One man can lay
Well, I guess you'll say
What can make me feel this way?
MY ASS. (My ass, my ass)
Talkin' 'bout my ass. (My ass)
Talkin' bout my ass.
I've got diarrhea after Imodium AD
With my ass.
I've even got a month of loose stools
With my ass.
Talkin' bout, talkin' bout my ass . . .
Patience my troll, good things come to those who wait. Better things come to those who wait longer. Besides, not like you never delayed anything in your life. No one is perfect...
In college, really poor, need a flatscreen.
How pissed is Leonard Nimoy about the delay. He's only wanted one for 33 years.
Current Athlons come with a 133 Mhz DDR bus and 256 Kb of L2 cache (plus 128 Kb of L1).
New Athlons coming soon feature a 166 Mhz DDR bus (166*2=333) and 512 Kb of L2 cache.
the 100 Mhz DDR was only used for the first K7 processors
There is a reason they call them 'Engineering Samples.'
I'll give you a hint. It has something to do with them being samples and not production units.
HyperThreading works by letting 2 threads execute at the same time. So basically, if one thread stalls, then the other runs. Or if one thread is only using the FPU then the other can use the integer ALU. Basically it increases the efficiency of the processor.
But it's not always going to work, one major problem with the whole idea is that it requires a TON of cache on the proc to work well. If one thread is stalled, then it slaps the other thread in the processor, of course it has to be in the cache, which means that they have to somehow decide how to divide up the internal caches between two processes. Which means that you will probably get more missed cache hits.
So if you are writing code that you think is stalling already, the I would venture to state that trying to use hyperthreading on the same proc will not increase your performance.
The longer x86-64 is delayed, the less useful x86 compatibility becomes.
Most people are running MS OS's and, if MS pushes dot-net successfuly then all new dot-net programs will work on Itainium/Opteron (IA64/x86-64) out of the box. Part of dot-net is packaging software as byte-code (like java) and compiling it at run-time (like java) or install-time (like gentoo).
This will make the fact that x86-64 lets old x86 run at full speed a non-issue, as "dot-Net" programs will be native binaries. Legacy software support, and the need for it, is a major key to why I belive(ed) that x86-64 will be (or could have been) successful.
Is life so dear, or peace so sweet, as to be purchased at the price of chains and slavery?
hey, that's my new fraternity's initiation song!
-sdem
it's going to take a *long* time before gcc really produces good code for Itanium,
In my experience, gcc does not do a good job of optimizing on anything other than oldfashioned x86. If the gcc developers are fond of athlons, it is not too surprising that p4 performance will suck. (although a factor of 80 is really something!)
But as you already know, the great advantage of gcc is that you can expect it to work identically on many platforms. So even though I am accustomed to a factor of 2-3 speedup when using Sun's cc rather than gcc, getting a nontrivial amount of code to work with both is really not worth the trouble.
Sorry. I'm a Anonymous Coward ;^)
Now I create my account (but not confirmed yet).
You can't put this peace of code on your page?
If you can't, please send to me: cleberlr@uol.com.br
Paul, thanks for your attention.
Now I see the code in your page. I will test it. Thanks
I've received a lot of email about my test code. I obtained permission to distribute my test code, and have made a web page with it. For those who are interested, please see http://www.andrew.cmu.edu/~komarek/work/RobustChol eskyPerf/RobustCholeskyPerf.html.
-Paul Komarek
It competes against the Pentium 4. If the K7 tops out at "3000+" as I've read, AMD is going to need Hammer to compete with 3GHz+ Pentium 4s.
Just getting to 333?
If you have two Xeons doing HT, you ought to try Ingo Molnar's new HT-aware scheduler, which deals with exactly this issue (and a few related ones).
If you aren't running Linux, well, never mind.
"How can you claim that you are anti-crack, while still writing a window manager?" — Metacity README
The P4 does indeed do 4 transfers per clock on it's bus. It does this by having two clocks 90 deg out of phase with one another, and sending data on the rising and falling edges of both clocks. It's definitely trickier, from both a conceptual point of view and from a design point of view then DDR, but it's not magic, and it's definitely not just a marketing term to try to hide things or anything like that.
FWIW AGP 4x mode uses the same basic technology.
The whole "Wintel" relationship is mostly just a huge myth. At best, Intel and Microsoft are forced-friends.
Both Intel and Microsoft have realized for quite some time that they need each other to survive, at least for the time being, but neither of them are happy about that fact, and both are striving to change it. Microsoft has been a fairly strong supporter of AMD for some time now, while Intel was one of the first major hardware companies to jump on the Linux bandwagon.
Think about it, Intel is pretty much the dominant force in PC hardware, being not only the primary supplier of processors, but also the #1 supplier of motherboard chipsets, video solutions, and being well up there if not #1 when it comes to audio and NICs (most of this is now integrated into motherboards). They are also the driving force behind most buses and interconnects, ie PCI and AGP (AMD's Hypertransport is a notable exception here), not to mention the fact that they defined the ATX form factor that virtually all current PCs make use of (albeit in a somewhat basterdized format for some of the big OEMs).
Microsft, on the other hand, is the dominant force in software, having the most common operating system, office software, web browser, e-mail program, etc. etc. ad nauseum.
The end result is that Microsoft is the only company in the PC world that Intel doesn't have a fair degree of control over (AMD fights, but ends up adopting Intel-compatible technology in the end, ie MMX/SSE/SSE2). Similarly Intel is the only company that Microsoft doesn't exert a signicant amount of control over in the PC world, though even there I'd say that MS mostly won that battle a while back.
Anyway, long story short, MS and Intel, not so much allies as simply two companies forced together by circumstance.
then it wouldnt be a one liner =)
Exactly... "Engineering samples" they haven't been able to stably clock up, which is why the release of the "production" units is being delayed until they rectify this. Don't get me wrong, they're making progress, and the 800MHz were a batch from the first go round, but this is why they're delaying the release of the "productions units." I'm talking about the unlocked "engineering samples" in AMD's lab as not clocking up, not what hardware sites get to look at. The 800MHz limit was based on what AMD's lab could stably clock their "engineering samples" to. I have faith though, Hammers will own.
How does this work architecturally? Does each CPU have its own (fast) address space and can access the address spaces of other CPUs more slowly? Or is there an intermediate translation layer, so that all of memory now looks like a cache of one big address space? Or, most likely, does the OS have to manage the logical address/CPU mapping problem as if it were virtual memory? It's not quite like paging, though, because you can still read memory on the other CPU; it's just slow. So only big or frequently accessed stuff needs to be copied. I think. The VM system is going to have to be very, very clever to manage this beast well.
Some early mainframes had memory arrangements like this. The CDC 6600, the IBM 360/90, and the UNIVAC 1110 all had both "fast" and "slow" memory. But they didn't have paged virtual memory, so the fast/slow memory thing had to be managed explicitly. Mostly, this didn't work, and as a result, mixed speed memory got a bad name.
But now, we've probably got to go there, simply because speed of light lag and crossbar bottlenecking limits the speed of multiprocessors.
The notion of machines with really fast memory to memory copying hardware has some interesting implications. It may lead to some new OS architectures for large systems. But I'm too tired to think this through.
What's the bottleneck you encountered? Are you doing mostly floating-point operations? I read @ many places that the Athlon's FPU blows P4's away. It'd be kewl to hear your first-hand experiences.
see link below for feedback8 0033931
http://www.aceshardware.com/forum?read=
also, you can download the intel linx compiler off their developer site if you are interested
Thanks for that link! I'm going to try to watch that thread; there seems to be at least a handful of sharp people posting there.
-Paul Komarek
Don't waste your time. Altivec is single precision only.
You are such a fag. Why haven't you come back, fag?
OMFG... I just want to thank everyone for he past 40 minutes of laughter you have provided me. I like to thank the poetic troll for his witty, if not slighty neanderthalian rhetoric. God you make me laugh! This is what happens on jerry springer after the credits! The fact that so many words have been written, so much inspiration from such an uninspiring original post, I must thank slick rick for allowing himself to be brutalized for so long.
me