Slashdot Mirror
AMD Shows Off 1.1 GHz Athlon
chamega writes "AMD demonstrated a 1.1 GHz processor Monday without any special cooling techniques. The processor is said to use "high-performance on-die Level 2 (L2) cache," whatever that means. " Perhaps, unlike Intel, they'll actually be able to /ship/ their high-end chips when they say they will.
This stor y tells what Dell think about AMD. One must wonder why on earth Michael Dell is considered a business genius!
This is inexact.
PPro had *integrated* L2 cache, but not on the same die as the processor itself. The PPro packaging contained the CPU core, and 1 or 2 dies of 256 (or 512 maybe) Kb of L2 cache, connected to the CPU core.
To say it short, you had 3 silicon dies inside the PPro. Celeron-A, K6-3, Coppermine and future Athlon (Select, Thunderbird and Mustang) pack all the fun (functional units + cache) on the same silicon die.
This makes the L2 on thoose processors more a huge-secondary-L1 than a real L2 cache, but I'm just nitpicking here ....
All wrong. 1 GB (base 2 definition, in most peoples opinion the real definition of disk size) is 2^30 = 1.073.741.824 bytes. 1 GB (base 10 definition, used mainly by harddisk producers to make their disks look bigger) is 10^9 = 1.000.000.000 bytes. 10^9 * 1024 is 10^9 kB, about 1000 GB, and not following any intelligent definition at all.
Mhz races are not a particularly good performance indicator, Apple are saying that the G3 does 1 Gigaflop, which might be a more interesting way of comparing chips, especially if the length of the flop is defined. to assess performance I think you need to consider: clock speed instruction set (RISC / CISC / MMX) word length any performance optimisation like code morphing.
AMD is working really hard trying to push a dual-proc chipset out, but are running behind schedule. Their first estimate was 'late 2000' and now it looks like 1H2001.
:(
I think they'll be called the Irongate 960 and 980 or something like that.
Oh well.
I want to play XMame games under KDE under ARM Linux under the arcem ARM emulator under Gnome/Enlightenment under OpenBSD under the 80x86 emulator under Linux 2.2! And I want 'em playable!
Seriously, this looks like one -very- nice processor. If they can get the scale down and have SMP on a single die, that would be even nicer!
It's a small world and it smells funny; I'd buy another if it wasn't for the money; Take back what I paid (SoM)
I'm waiting for the processor which will do this smoothly; my P6-200 with Voodoo2 gets a little slow in 'Fast' mode when there are more than a few people on.
--
Never hit your grandmother with a shovel, for it leaves a bad impression on her mind...
I think it will be this year.
Neither AMD nor VIA have announced a SMP chipset (AMD has stated the 750 is the only one they intend to do, they want other compines to to the "real" chipsets). I'm supprised VIA hasn't announced since they have done SMP PPro and other chipsets in the past.
That doesn't mean nobody is making them. Both Hotrail, and API (URL unknown) have announced SMP chipsets. They have given no firm dates that I know of. Hotrail initally said "in 2000", now they are saying in the second half, I think. They havn't blown a promised date yet, but they havn't made any strong promises.
Again I know nothing about API, but Hotrail has made noide about 2-way, 4-way, 8-way, and "more". Also there is the dark horse of Compaq, after all they have SMP (and much bigger then 8-way!) systems using the same bus, but with a diffrent form factor, and possably diffrent speed and voltage.
I don't know if it was a mistake for AMD not to do a sample multi-CPU chipset. Having a SMP chipset would let them sell more CPUs, and high-margin ones if they convince motherboard makers that it is too much trubble to get the non-Ultra Athalons to run more then two-way (they are claiming it is possable, but eletrical tolerences will be very tight, and for some reason it is easier with the Ultras).
That was HP's feelings through most of the '90s. They used only a L1 cache, and it was off-chip. It was huge for the time, and very fast for an off-chip cache. I think the last design they did that way had 2ns SRAM (500Mhz if you ignore overhead). In the last year and a half they have moved to an on-chip cache, sometimes with an off chip L2 cache. They have fought the good fight against the Alpha for the number one SPECfloat spot for years, sometimes winning, sometimes coming in second.
On the other hand the Alpha has almost allways had a small on-chip cache and a larger off chip one. Recent designs (21266) include a tiny "L0" cache (8K or 4K I think) and a larger L1 cache both on chip with a larger L2 off-chip cache. I expect your stament about having little predicability left by the time you get to a L3 cache really has less to do with the number of levels, but the size of each.
I expect these tradeoffs change as the cost of on-die transistors changes, and even the speed of them. Back when 100Mhz (10ns cycle time) was fast, taking a 1ns trip across wires off the die was cheap. Now it is still the same cost to go off the die (say 1ns), but we want to run at 500Mhz or 1000Mhz (2ns to 1ns cycle times!), so that off the chip cost is now huge compaired to doing it on-chip.
To moderators: please moderate the above post up. This guy knows what he's talking about.
:-)
And I just want to add one more thing. To all those whoe are saying bus speed is the bottleneck: did you actually run the benchmarks to compare the speeds? Where did you get this idea from? Perhaps you just assume higher bus speed will necessarily speed up the computer immensely.
Well, there have been many benchmarks that show quite the opposite. The CPU is *not* limited by the bus speed. Even the 66MHz bus is more then enough to supply all the memory bandwidth the CPU needs. And that is why Celeron, with its 66MHz bus runs just as fast as "true Pentium 3" with its 100MHz bus.
Statements like "processor speeds above 400MHz don't make that drastic difference" are made by really clueless people. Reality check: take a look at the actual benchmarks. Even when running 3d games like Q3, memory bandwidth is *not* a bottleneck. L2 cache compensates for slow RAM quite nicely.
Of course, on the other hand, you don't need a 1.1GHz CPU to run a word processor/browse the interent. Well, not yet anyway (right, Bill?
___
___
If you think big enough, you'll never have to do it.
These days the video card is the bottleneck, not the CPU. Get GeForce (IMHO the only 3d card worth getting) and you'll see *huge* improvement in speed, even with the same CPU. Of course there is no P6 board that has AGP slot...
But in any case, the video card is the limiting factor, not the CPU. And now that GeForce and a few other cards include the geometry engine which takes *all* graphics-related work away from the CPU and lets it do other things (like AI), even a P6-200 would work just as well. Then again, too bad no P6-200 board has AGP slot...
___
___
If you think big enough, you'll never have to do it.
Uhhh... I'm getting so tired of this. No RAM technology is NOT becomming a bottleneck. Tom (www.tomshardware.com) tested p3-600MHz systems with standard pc100 SDRAM and 400MHz Rambus. Well, the Rambus systems were about 5% faster. But considering also that they had newer chipsets and, most importantly, on-die full-speed cache (as opposed to halh-speed cache of the old P3-600), one has to wonder what exactly caused the speed increase. Also, considering that Rambus is 6 *times* more expensive then SDRAM, the 5% speed increase does not look attractive at all.
___
___
If you think big enough, you'll never have to do it.
Theoretically, what you are saying is true. However in practice it does not happen precisely because the curent memory bandwidth is enough. You also mention latency -- and yes, decreasing latency would benefit performance, but this is not what Rambus, PC133 SDRAM and DDR DRAM are designed to accomplish. Their goal is to increase the memory bandwidth which has nothing to do with latency.
In the benchmark I mentioned, Tom used 400MHz Rambus -- the fastest one currently available. It has exactly twice the bandwidth of PC100 SDRAM (800MB/s vs 1.6GB/s). And yet the performance difference was a whopping 5% on *some* benchmarks, even less on most. Keep in mind that Rambus is no less then *six times* more expensive then standard SDRAM.
Furthermore, there have been quite a number of benchmarks that show *no* difference in overall speed between 66MHz and 100MHz bus Pentium 2, given that the CPU speed is the same. Surprise surprise, cache is actually quite effective.
Now, when you have a SMP system, you may eventually run into memory bandwidth problems as the clock speed and the number of the CPUs increase. But it is a non-issue when it comes to single-CPU machines, even when playing 3d Games (Q3 comes to mind).
The real bottleneck is currently the video cards. NVidia GeForce and a few others include the geometry engine which takes care of *all* graphics related work. This is a step in the right direction. Even now the video card matter much more to a 3d game performance then the CPU and bus speed combined. And I expect the trend to continue.
___
___
If you think big enough, you'll never have to do it.
I certainly agree with you here. It's nice to finally read a comment from somebody who actually understands what they are talking about.
However, I don't see how PC133 SDRAM or DDR DRAM would decrease latency. Wouldn't it just increase the bandwidth the same way Rambus does? Care to explain, please?
P.S. I should have said memory *bandwidth* is not the bottleneck. Lowering latency would certainly be helpful. Unfortunately Intel doesn't think so... or doesn't want to. Why does Intel insist on Rambus even now that it's clear the technology sucks?
___
___
If you think big enough, you'll never have to do it.
1 GHz = 1000 MHz. Hz are not specific to binary (i.e. computer) systems, so they use standard base 10.
Have you found an Athlon motherboard that runs the RAM at 133 MHz? I can't find one anywhere.
Not yet - but I plan to slap a serious cooler on it and do some overclocking. I have the Asus K7M board, which has support for higher bus speeds. So PC133 doesn't cost much more (about $10 for a 128 MB stick), and has a higher margin of tolerance.
I'm looking forward to the VIA chipset for Athlon (the Asus uses the AMD Northbridge, with a VIA Southbridge - the other current vendors use the full AMD chipset), as it should drive prices down and support PC133 RAM explicitly. But hey - I didn't want to wait. I can always build another Athlon system later on to run Linux on (my current one is my Win98 gaming PC and my Linux desktop is a PII-350).
- -Josh Turiel
-- Josh Turiel
"2. Do not eat iPod Shuffle."
Of course, I only paid $240 for my Athlon 600 processor, so I don't feel too deprived.
To the people wondering just how a system with only a 200 MHz bus (and PC100 RAM, at that) can be useful at 1.1 GHz:
First of all, if you're dropping the kind of change on one of these that is appropriate, you'll have more than a puny 64MB of RAM. It's liklier that you'll have at least 128 MB or probably 256 MB+. So you won't have a huge problem with disk thrashing. Just make sure if you were to use one of these beasts that the rest of the system is up to the task. That means a fast ATA or Ultra SCSI disk, a fast 3D card (don't be using no Rage Pro!), and the best memory that the system spec works with. I use all PC-133 nowadays.
On the other side of this is the processor itself. On-die cache (Celerons, CuMine PIII processors) is much faster than the variety that is mounted on the PCB (older PII and III and current Athlons). It can run at full processor clock instead of, say, 1/2 clock or 2/5 clock. Because of this speed advantage, less of it goes a long way. Older PII and PIII designs used 512k of on-board cache, which is replaced by 256k of on-die in the CuMines (128k in the Celery). With a big, fast L2 cache a lot of your instructions are fetched from cache and executed much faster - and of course a big L1 cache helps, too. Also, SDRAM does a better job of feeding data in bursts than older EDO and FP RAM did. But RAM technology is becoming the bottleneck lately. Rambus and DDR SDRAM is supposed to help, but DDR isn't really there yet, and Rambus has been a fiasco to date and the yields are allegedly horrible.
Ultimately, on-die cache allows the cache to run at either full CPU speed or a high divisor of it. PCB cache is more constrained. But faster processors will always make a difference no matter what - it's just that after you outrun the rest of the system it's a matter of diminishing returns. An Athlon 1000 is not necessarily exactly twice as fast as an Athlon 500 - but it's still wicked fast!
- -Josh Turiel
-- Josh Turiel
"2. Do not eat iPod Shuffle."
Hmmm. Well I've built and used systems with: AMD 386DX/40, AMD 486DX4/100 K5 100, K5 133, K6 233, K6-2 300, and a K6-3 400, all in 7x24 server functions. I only had problems with the K6-2 300, which was really sensitive to the efficency of it's CPU fan, but still ran flawlessly for about a year before I retired it.
All the rest (including the 386, minus the K6-2) are still in service somewhere in someone's computer and doing fine.
When the K7 SMP systems arrive, that will be my next system. I've used almost nothing but AMD chips for the last 7 years (currently I'm running a dual 433 celeron system) and have nothing but good things to say about them. The only down side I can really find is that supporting chipsets (Via, SIS, etc) do not do some functions as well as the Intel equivilents, like PCI DMA throughput. Nothing wrong with the AMD chip, though..
jf
The two of them have been playing "tit-for-tat" for some time now... I wonder how long Intel will be able to keep up that game. Not long, I'd wager. I wouldn't be suprised to find that they have no answer for this. Wilamette might be Intel's answer further down the road, but it is hard to say what with the K8 (and, yes, the K9) looking so nice. About production... That has been AMD's problem for a while. Anyone got any links indicating how well they have been able to meet the demand for K7's?
The enemies of Democracy are
Actually, I meant hard disks were a bottleneck in general, not necessarily in games. Sorry if it was a bit ambiguous.
You also mention latency -- and yes, decreasing latency would benefit performance, but this is not what Rambus, PC133 SDRAM and DDR DRAM are designed to accomplish
Actually, you are correct that the goal of Rambus is not to decrease latency, but rather to increase bandwidth. You incorrect, however, when you state that PC133 and DDR SDRAM also have that goal. PC133 and DDR RAM have the goal of decreasing the latency, *not* increasing the bandwidth. Increasing the clock speed of the RAM (as PC133 does, and as DDR "fakes" by using both clock edges rather than just one) should cut the response time for the memory (latency). It doesn't affect the volume of data transferred on a clock cycle (bandwidth).
Rambus increases bandwidth, yes, but at a cost to latency. This is why sometimes using Rambus memory will actually slow down the system - bandwidth (as you stated) is not the bottleneck. Latency, however, is more of a bottleneck. Accessing a piece of data from memory can take hundreds of CPU clock cycles, during which the CPU is often forced to stall and do nothing. Reducing this will certainly help performance, though how much depends on the specific application (and for many benchmarks, you will see little improvement - many of the benchmarks out there are intended to stress CPU performance, and as such are computation-heavy rather than I/O heavy. Applications that are more biased towards I/O operations will benefit more than others that are not). Heavy-duty multimedia can fall into the category of applications that will really benefit, since often the volume and rate of data being processed is so large that it means a smaller percentage of the data is accessed from the cache, and more from main memory.
The real bottleneck is currently the video cards
For games, I'd certainly agree. In general, hard disks are also an often-overlooked bottleneck.
Agreed. I was just reading some stuff about the testing being done at those resolutions at IBM and realized that it was getting into the "within 5 years" realm. Can someone refresh my memory as to what the current lithography limit is? I mean, we're getting down into traces that are hundreds of atoms wide that we need to avoid voids in over wafer scale surfaces. I believe I also just read that Intel was just moving into .18 so AMD s leading the technology curve since they're already in copper production as well.
And this is made on .18 fab lines which leaves .13 and .07 yet to come. This processor is going to have so much more in it that Intel isn't going to be able to play the matching gigahertz game much longer. You do have to admire a company that not so long ago had been totally written off and now has processors in most of the Intel strongholds. What's next? PPC overtaking Intel marketshare?
Oops! My bad. Sorry about that.
First of all, "k" should always be lowercase when used as a prefix. (Note that "k" should always be a PREFIX to a unit. "K" being used alone as you do above is merely colloquial and non-standard.)
Secondly, he was talking about the distinction between computer prefixes and SI prefixes. (Ever notice how 1kb is 1024 bytes?) He was joking about the silliness of the computer industry (especially the hard-drive industry) in using two different definitions interchangeably, whichever suits them best.
It makes you look really bad to put people down when you don't even seem to know what you're talking about yourself.
Actually, Michael Dell does have a point.
Anandtech, Tom's Hardware and Sharky Extreme reported that the early Athlon motherboards had compatibility problems, notably with AGP implementation and some tests failing altogether. ZD Labs reported that their 3D Winbench 2000 and other benchmark tests failed on these motherboards.
Fortunately, the arrival of the VIA Apollo KX133 chipset may alleviate this problem (motherboards based on the KX133 chipset should be available in the next 30 days).
Raymond in Mountain View, CA
I cannot wait to see what Kryotech is going to do with this bad boy.
If their past patterns hold true, we should see anything from 1.5Ghz to 2Ghz.
Of course, lights will go off all down your street when you fire it up, and you'll be able to go get pizza and Jolt while you're waiting for it come up when you turn it on...
Unless you're program is so small that it runs entirely from the cache, today's smoking fast CPU will spend quite some time twidling their thumbs waiting for data...
You assume that Rambus is far better than current SDRAM well, that's not sure at all, remenber that initially Rambus memory was supposed to work at far higher speed, and that many articles compared today RAM and Rambus and said that while the Rambus has a far higher maximum theoretical bandwith their latency wasn't very good, so in fact using Rambus may SLOW DOWN your system...
Ironical don't you think ?
Read Hennesy & Patterson "Computer architecture" to see why saying RAM is not a bottleneck is stupid, if we could afford it, there would be no DRAM, we would use only SRAM, unfortunately it costs much more... And even in this case a small memory is usually faster than a bigger memory so we would still have to use cache to profit of the locality of references...
Ok, Mr. Jesus killer, if you think you're so smart, what's better, an Audi A6 or a SAAB 9-5?
Oh then I guess it must be jmott@fuckingstupidasss.edu!
Dell could have been right here. There were some problems with Irongate boards initially. For example most of the first FIC batches had to be recalled. I would also avoid calling VIA the best chipset in the world ;-)
While Intel used to beat everyone because of their chipsets. Unfortunetly sinse the venerable BX they have not produced anything as stable as they used to...
Baker's Law: Misery no longer loves company. Nowadays it insists on it
http://www.sigsegv.cx/
This could be a Dell playing friends with Intel so he doesn't get short changed in chips when processor shortages come around, but none the less, his opinion will matter with big business about Intel being better than AMD.
He goes on in the article to say that the chipsets are what is lacking for AMD.
MHz is starting to become insignifacant compared to the overall system since the bus, hard drive, network, and RAM can't keep up. Once these technologies are sped up by an order of magnitude, we will see real dividends by these MHz increases.
Oh come on, we all know what you really mean. Just say it: the Quake 3 market.
---
As copyright owner of this comment, I authorize everyone to defeat any technological measure which limits access to it.
Heck, I've got Karma coming out the wazoo!
$|4$|=||>0+ $|_|><
Glückwünsche, haben Sie Slashdot ermordet, indem Sie zum korporativen Druck beugten und Subskriptionen einlei
Didn't Intel make a move to kill off VIA recently?
I don't remember the specifics, but the gist of it was a lawsuit Intel brought against VIA when they bought Cyrix for its x86 compatible chip designs. Ostensibly the lawsuit was over the old "microcode patent infringement" bruhaha, but a couple of articles in the press said the real motive was to scuttle the AMD chipsets that VIA is bringing to market.
Anyone with better knowledge of this care to comment?
Life is a tale told by an idiot, full of sound and fury, signifying nothing.
William Shakespeare
I dont think michigan is in the Eastern time zone. Not sure about it but I think they're in Central.
___________________
rooooar
this map shows the time zones, but i'm not sure where Michigan is on the map... I know, I should know my geography,
<sarcasm>
but... it's Michigan for god's sake.
</sarcasm>
___________________
rooooar
This is not just a demo of a new product! This is demonstration of leading edge technology(.18u with copper interconnects) for their market segment. This also shows that their huge loans for building Fab30 in dresden paid off.
I might be wrong, but whether in volume or not wouldn't this be the first real product to come off the Dresden fab?
It would seem they have learned a valuable lesson: don't flaunt chips that don't exist. I got burned real bad last year when everyone thought they were doing so well, and they were. It was just at the expense of revenue, which hurt a lot of stock holders(like myself). Before the K7(erm, 'scuse me. Athlon) was released, I as a personal investor tried to find about it as much as possible. Info was out there, but not too much was said until they taped out. Now they don't really warn us, they just spring new products on us and that is good!
You can't legislate goodness. Let each to his own destiny, by will of his freely made choices.
Microwave ovens uses 2.405Ghz. Perhaps in 2-3 years.... would be fun though. Just imagine having to use radiation shielding in a PC...
Actually, the Federal Communications Commission is starting to worry about this sort of thing. As I understand it, internal lock isn't quite so important, but now that the front-side bus is getting into the 200 - 400 MHz range, RF emissions from leakage could be a serious threat to certain existing radio systems. With so many PCs being built by random people who don't care about RF sheilding, they are not sure what to do, but limitations on what do-it-yourself'ers can do have been discussed.
dragonhawk@iname.microsoft.com
I do not like Microsoft. Remove them from my email address.
Grumble accually I was more trying to make a point, and an inquiry. As there is a chance that AMD could have defined GHz to be 1024 MHz, incorrectly. But, just to let you know, I generally start out with a mod of 2, and I guess somebody thought it was an interesting point, and if nothing else, there was a conversation surrounding it, one of which some people might find "interesting," or even "insightful." Because frankly when using points to sort the comments I see, I'm not always as interested in the comment itself, but the conversation below that comment as well, which will only be generally seen promenently(spelling?) if the base thread comment has a high enough score.
Just curious, but are we talking Ghz as in 1024 Mhz or Ghz, as in 1000 Mhz.. :)
What company do you know that doesn't advertise its products before they are released?
Transmeta's the closest. (..and even they put up info on their website before then)
Here's how to fix it - get an account, then you too could become a moderator!!!
/. - I use /. more than Usenet now exactly because in general, the moderated comments are usually better than the lower ranked ones and thus I can get more interesting reading in a shorted time than I can in just about any Usenet group.
/.'s best features, and it's why I keep coming back.
Moderators are just readers. They could be me, they could be you, they could be a six year old. If you don't like the current make-up of the moderation pool, then by joining you can change the makeup of the moderation pool and thus how posts are moderated.
I also have to disagree with you on Usenet being a much better model than
/. moderation is by no means perfect, but I'll take it any day over the complete chaos that is a normal usenet group, or the total control imposed by moderated newsgroups. I think of the user contributed moderation as being one of
"There is more worth loving than we have strength to love." - Brian Jay Stanley
That's standard legal mumbo jumbo, and not applicable at that. The chips aren't produced in the USA, but in Dresden, Germany, using wafersteppers from ASML, from Holland.
Produced in the EC, America has lost yet another lead in electronics.
----------------------------------------------
the pun is mightier than the sword
besides, with little memory, when system starts to swap, all the MHz don't matter all of the sudden because hard drive is *slow*. So, all the speed is reduced to the hd's speed.
with these two constraints, bus speed and hard drive's speed, processor speed doesn't play that big role anymore, unless there are newer (faster) system bus / hd technologies or different architechture comes about.
God did not appoint us to suffer wrath but to receive salvation through our Lord Jesus Christ --1Thes5:9
AMD DEMONSTRATES 1.1GHz AMD ATHLONâ PROCESSOR
- AMD Athlonâ Processor Built on Advanced Copper Technology Shatters GigaHertz (1000MHz) Barrier-
SUNNYVALE, CA--February 7, 2000--AMD today demonstrated a 1.1 GHz(1100 MHz) version of the AMD Athlonâ processor...
From the AMD Press Release (Emphasis mine)
Put that in your Furby and smoke it!
On the Coppermine (PIII 'E'), when the processor asks for a specific portion of memory, if it's in L1 then it takes 3 cycles to be retrieved. If it's in L2 instead, then it takes 7 cycles (or so?) to be retrieved.
... if you had L2 cache running at 800MHz on an 800MHz processor, but that L2 cache was only 8 bits wide and took eighty cycles to retrieve a piece of memory (eg, making it probably even slower than SDRAM), should you really refer to it as "full speed"?
... in an earlier post, I referred to Willamette's bus as being 128-bit. I was very incorrect. The correct width is 64-bit (incidentally making Willamette's bus less cool than I thought).
That's basically the difference. They both 'tick' at the same clock rate, but one just happens to be able to deliver data in less than half the time.
This is why I'm always pissed at people who ignore every other factor when they refer to "full speed" cache. I mean
-JC
PC News'n'Links
http://www.jc-news.com/pc
PS: Apologies
As has been posted on every Athlon thread since the beginning of time, the chip is ready for SMP, but the chipset isn't. The chipset for Athlon SMP is far more complicated (and higher performance) than that for the intel SMP structure. Check out the Alpha bus documentation for a little more flavor on this - its the same bus the Athlon uses, and the idea is to implement a crossbar switch rather than a shared bus. Cool, but costly.
"It's tough to be bilingual when you get hit in the head."
For the same reason it's not likely (but you never know) that there's any advantage to adding an off-chip L3 cache.
A price/performance advantage or a performance advantage? I would imagine that for a chip running at 1.1 GHz that access to a L3 cache running at 500 MHz would be far more perferable to access of some PC-266 Double Rate DRAM. The inhibiting factor becomes how much that 500 MHz DDR-DRAM is going to set you back, plus the complexity costs in you northbridge design, and that zingers that throws into cache coherenecy in multiple CPU designs.
Even the performance advantage disappears if the hit rate isn't pretty high, because you insert at least one cycle into your access latency while you check tags for a hit. I'm not familiar with the studies themselves but from second-hand sources it looks like there's precious little predictability left in the access stream once L1+L2 get done with it.
dpilot argued that the L3 cache on K6-3 systems adds measurably to performance; I certainly can't prove dpilot wrong. I do know that there's a pretty fierce tradeoff between complexity and speed, though, and sometimes you get more milage out of keeping it simple but screaming fast.
Lacking <sarcasm> tags,
L1 cache is the memory closest to the actual computing functions. It runs at CPU speed, but because larger => slower it can't be very big; usually measured in Kbytes. It caches the most-used memory addresses.
L2 cache is larger and slower than L1. Until recently, L2 was implemented by separate RAM devices attached to the CPU. The original Pentium (socket 7) L2 cache was on the processor's front-side bus, between it and the system controller. This became a serious speed limiter and newer processors added a back-side bus strictly for cache (one reason that the CPU modules appeared.) Back-side bus cache runs around 400 MHz plus three or so bus cycles added latency. At 800 MHz this starts to get ugly.
Moving the L2 cache on-chip may not let it run much faster (typically CPU/2 or CPU/2.5) but it cuts the pipeline latency, and latency reduction is what cache is all about. Also, being on-chip makes it much less expensive to use wide busses so the L2 could, for instance, transfer an entire cache line to the L1 in a single cycle.
L1+L2 cache is so good at removing nonrandom accesses from the memory stream that appears on the front-side bus that what actually makes it to the DRAM is almost completely random-access. That's why packet-based memory (e.g., RAMBUS) do so poorly compared to their sustained bandwidth: the bandwidth is never sustained, it's just the first cycle that counts.
For the same reason it's not likely (but you never know) that there's any advantage to adding an off-chip L3 cache. The hit rate would be too low to be worth the trouble of checking for a hit.
Lacking <sarcasm> tags,
... is a *dual* Athlon system instead of MHz's.
Is it just me or they are delaying SMP Athlon solutions for a bit too long? Or they simply don't care about server market?
Why don't you make an account, stop posting anonymously, earn a little "karma" and moderate for yourself?
Time to go back to school puppy.
CPU vendors do not test. CPU vendors sell.
IC manufacturers test.
You friend was joking. The only binning Motorola
does regulary is for ancient commodity devices and
I dont think there is much of that around anymore.
Binning is a violation of SPC. Motorolas SPC
program called Six Sigma is very stringent. It
leaves little wiggle room for binning. Intel is
ridiculed by the rest of the industry because of
its continued use of multiple bins, 3, 4 or more
bins!
There are some instances when 2 bins can be used
and still have a process that is in control. In
any case in the 10 years I worked for Motorola,
in IC Test engineering, did I ever see any
binning.
SCSI Ultra3 (U160) is faster than Fibre Channel.
SCSI Ultra4 will be faster than 2Gig Fibre Channel, and will show up before it.
1.21 Gigawatts!! Of course =)
God Fucking Damnit
Our ES box is positively aenemic in the clock speed department compared to our desktop intel boxen. And yes, when I do CPU intensive tasks, the desktop intel boxes will cream our rather old 167 MHz Ultra. However:
- Our Sun boxes are reliable.
- I think there's still a (narrowing) advantage on the IO/throughput side of things.
- Other stuff
Case point: A map I just did displays allmost instantly off our cruddy old ES box onto my even older Sparc5 desktop. Same map takes several minutes on a PII 300.
Yes, I think Sun and SGI's lofty ground is being eroded, but there's more to big computing than clock speed.
Xix.
"Everything is adjustable, provided you have the right tools"
You weren't too far off. I just upgraded to a 450-MHz K6-III over the weekend and got these results from CacheChk (installed on an FIC VA-503+ v1.2 with the latest BIOS and 64 megs of PC66 SDRAM pushed to 100 MHz):
CACHECHK V7 11/23/98 Copyright (c) 1995-98 by Ray Van Tassle. (-h for help) :-) )
CMOS reports: conv_mem= 640K, ext_mem= 64,448K, Total RAM= 65,088K
BIOS reports: ext_mem= 64,448K Total mem: 63 MB
"AuthenticAMD" AMD-K6(tm) 3D+ Processor Clocked at 451.1 MHz
Reading from memory.
(timings snipped for some brevity
This machine seems to have 3 caches! [reading] (This can't be right.)
L1 cache is 32KB--1876.5 MB/s 0.6 ns/byte (1179%)
L2 cache is 256KB--1257.8 MB/s 0.8 ns/byte (790%)
L3 cache is 1024KB-- 480.1 MB/s 2.2 ns/byte (301%)
Main memory speed -- 159.1 MB/s 6.6 ns/byte (100%) [reading] 11.3 clks
Effective RAM access time (read ) is 52ns (a RAM bank is 8 bytes wide).
Effective RAM access time (write) is 91ns (a RAM bank is 8 bytes wide).
"AuthenticAMD" AMD-K6(tm) 3D+ Processor Clocked at 451.1 MHz. Cache ENABLED.
Options: -t0 -z
With the K6-III at least, L2 cache runs at about two-thirds of the speed of L1 cache. L3 cache, at 100 MHz, takes a big hit--it's only a little more than a fourth of the speed of L1 cache. L3 cache is still three times faster than main memory, though.
(What's really funny is the comment about how it can't be right that there are three caches in this computer.)
20 January 2017: the End of an Error.
K = 2^10, M = 2^20, G = 2^30 etc..
k = 10^3, m = 10^6, g = 10^g etc..
As many people have pointed out, powers of two have no special meaning when refering to frequency, which is analogue, so there's no point in using big G. So the number will be 1.1 gHz (= 1.02 GHz). Also it's in AMD's interest to quote gHz because the number is higher!
perl -e 'fork||print for split//,"hahahaha"'
And true to form, you engineers 'borrowed' someone elses design. Which is why you can't sell it outside of mother Russia.
Then you don't know how to set one up right. Somehow I doubt you were using a good power supply -- those 200watters don't cut it when your cpu draws in excess of 50watts.
Mine has been running perfectly since I've gotten it.
I haven't had an AMD processor yet I haven't had to underclock to make stable for server use. I stopped using AMD back when the first athlons appeared.
This is a good thing. It means that in addition to the typical L1 cache which is on the chip, the L2 cache (probably smaller than offboard) is there as well. This dramatically decreases L2 access time, and can improve performance significantly.
Note that I say can. There are a lot of factors that go into cache design, so it really depends on the relative sizes of the L1 and L2 caches as well as stuff like the block size, associativity, and application running on the processor.
When you start clocking a chip around 1Ghz, you need L2 cache with latency of 2ns, instead of 3+ns. This depends a lot on the clock ratio you want to set the cache to. L2 cache that can handle 1Ghz is either way too expensive for anyone to afford, or doesn't exist yet.
AMD has to invest quite a lot in the material needed for 2 nanosecond L2 cache, and it can't possibly run at full chip speed.
Intel ran into a similar problem with the Pentium Pro - that's why the clock speeds stopped at 200mhz, the L2 cache wasn't reliable much past that (don't bother to say you can OC your Pro to 233, so can i). Intel released the p2 with half-chip-speed L2 cache to address this.
AMD is releasing Athlons with 1/3, 5/8, and some goofy ratios to maintain the reliability of their chips.
Hm, I think I will take that to mean that the cache has finally been migrated onto the same die as the CPU core itself, a la Intel's Coppermine generation P-IIIs. Great, since that should mean that the L2 cache no longer needs to run at 2/5 of the speed of the core, as was previously the case with the higher-speed Athlons... Hm, perhaps it's time to start lobbying the boss to replace my Athlon-550 from early December. Naah... ;^)
main(O){10<putchar(4^--O?77-(15&5128 >>4*O):10)&&main(2+O);}
Just an afterthought, but as AMD continues to win the speed war with Intel, one must remember that most people have boards that use Intel chipsets. It could seem feasible that Intel could/will try to further the rift of chipset compatibility when/if AMD contiues to win the speed war. I am somewhat in the dark about topic, so please don't use my ignorance as flame bait.
its a public demonstration that their facility can and will produce 1.1Ghsz chips, and they have demonstrated this before Intel has.
confidence in the minds of the industry is the key to AMDs survival. OEMS, shareholders, consumers, etc. all need to believe that AMD is da bomb, or they wont trust AMD and go with tried and true Intel.
-I go to Rice, so figure out my email address
1. a real world benchmark with your favorite applications
2. The SPEC series of benchmarks. even these arent perfect, (people have been known to unfairly optimize for some of the benchmarks from time to time) but they are pretty good, and a much better measure than how many gigaflops (a number which can be EXTREMELY meaningless) a processor can do under some contrived situation (lets divide 2 by 1.0 a billion times!)
Last I checked the SPEC, the PowerPCs had slightly better scores than an Intel P2 in integer performance at the same Mhz (and I do mean slightly) integer applications. In floating point the P2 was faster, again, slightly.
So basically Mhz per Mhz, it depends which one will be faster.
Now the Athlon is faster than a similarly clocked and cached Intel chip at everything. I havent checked the SPEC marks on Athlon vs the latest G4 marks, but I bet it does just fine.
-I go to Rice, so figure out my email address
Whats your point?
I dont understand why this upsets you....
its not a marketing PLOY. AMD isnt being dishonest, they didnt say they were coming out with this thing tomorrow. All they said, and all the demo implies, is look, here we are, we smacked out a 1.1Ghsz chip. Well be refining out process and making more of these, selling them so, so invest in us, stick with us, we are pretty good.
whats the problem? Nobody with half a brain is being misled by this demo in ANY way. when was the last time you head of a chip being demoed at X mhz and not actually seeing them in the store within a year?
calm down guys =)
-I go to Rice, so figure out my email address
Cache. A big load of on die cache possibly supplemented by a bigger load of not on die cache.
The other answer is DDR ram, so you can jump from PC 133, to PC266 memory, wooha!
yes, memory speed is a problem in PC world, but still, upping the MHZ is a good thing, especialyy when you have a sizable cache to work with. Remember back in the days when computer had a mere 640k of memory in TOTAL to work with? Well now we have about the much in cache running at the SAME SPEED as the processor =) which aint such a bad situation really. Clearly a large set of problems can be solved by code that almost totally fits in cache.
-I go to Rice, so figure out my email address
Don't you know what timezones are? If it was posted in a time zone one hour ahead of you then it would be correct. Like if you're in Colorado and Slashdot is in Michigan.
Nascantur in Admiratione. (Let them be born in Wonder)
The AMD-750 chipset doesn't do SMP, and neither does Via's new KX133 chipset -- the chip itself is ready for multiprocessor configurations, but nobody's made it feasible yet, and don't expect it for a while.
--
E2 IN2 IE?
... is execution time. How long it takes to perform the function(s) you're interested it. Everything else (MHZ, Flops, Instructions per clock) considered only by themselves is misleading.
In fact, there's a "performance equation" which gives you execution time:
Execution time for a certain function = Instructions/Function * average Cycles/Instruction * Time/clock cycle + hardware or IO delays
Specific Application performance, or performance suites like SPEC, while far from perfect, are still much better indicators of performance than theoretical garbage such as flops or mtops or analysis of instruction architecture or whatnot.
-------------
The following sentence is true.
The following sentence is true. The preceding sentence was false.
1 Gflop is not the measure of a "supercomptuer" no matter what steve jobs says.
T M
Computers that have a CTP (composite theoretical performance) of over 2000 MTOP/s (millions of theoretical operations per second) qualify for export ban to certain sensitive countries. Jobs decided that this export ban meant they were a "supercomputer." Unfortunately I can't find specific info on the G3/G4's mtops ratings, nor for AMD. Intel has theirs here: http://support.intel.com/support/processors/CTP.H
-------------
The following sentence is true.
The following sentence is true. The preceding sentence was false.
Overclocking, by definition, is setting the clock rate higher than the manufacturer's rating.
:P
The manufacturer, therefore, can never actually "overclock" their own chips -- they always run them at their own rating.
Heat has *NOTHING* to do with this. Or is there some magical heat threshold in your world which separates overclocked chips from non-overclocked chips? What exactly is it, how much is required to burn your finger when you touch the heat sink?
-------------
The following sentence is true.
The following sentence is true. The preceding sentence was false.
Sorry, I replied to the wrong post. I meant to reply to the one titled "Latest, fastest chip is *always* an OC'ed model" which is a reply to your post. /me slaps himself around a bit with a large trout
-------------
The following sentence is true.
The following sentence is true. The preceding sentence was false.
If there's a problem with slashdot's time, or slashdot's moderation system, or if you have any other such gripe about slashdot, either email someone, or wait for an appropriate article to come around (they've been here in the past). *Don't* clutter the message boards with your complaints.
<i>Oh, and I said moderators suck in the title, and gave a valid reason for it. That's gotta be worth -1, troll as well.[/sarcasm]</i>
Your post has nothing to do with the topic of the article, therefore it is Offtopic, therefore -1. It makes perfect sense.
-------------
The following sentence is true.
The following sentence is true. The preceding sentence was false.
Heck, you can boil the hot water for your coffee on top of the CPU - then use the CDROM tray as a cup holder!
Where can I get a dual Athlon mobo that'll run with this things speed?
threadeds blog
How can AMD ship this thing on time? They haven't even announced a shipping date for this thing yet.
It's nothing more than a marketing gimmick.
The wafer stepper is not a yield killer in IC manufacturing, not even close. That would be contaminants and poorly calibrated equipment.
Nor is it the limiting factor when you want to go from e.g. .18 microns to .13 microns. There you have all sorts of problems, most of them related to transistor design (whats to say that a .13 micron transistor will work even if you manufactured it perfectly?)
but I get so disillusioned at promised dates (read Intel) that always get missed.
Bah, if you want disillusionment, try being one of the people that still want to play ION Storm's Daikatana.
--Have a Johsonville brat.
Nah...
Still a way to go. Microwave ovens uses 2.405Ghz. Perhaps in 2-3 years.... would be fun though.
Just imagine having to use radiation shielding in a PC...
Ost99
---- Sig. gone.
Just as a bit of information on the side, this was shown at the International Solid State Circuits Conference. This is the yearly brag, boast, watch, learn and schmooz fest organized by the IEEE. It is a prestigious conference so everybody shows of their latest and greatest. Yesterday it was Intel with 1Ghz today it was AMD. It is not like this is in production allready, just guys showing off.
What I find interesting is that these are made by wafer-steppers from ASM-Lithography. These guys have been leading the way the last couple of years. I wonder how much Intel is being held back by sticking to their current wafer-stepper producer (Canon? or was it Nikon?)
Use Adsense for Charity
I wouldn't say suing overclockers was an example of AMD being bastard-like. They didn't want people buying their products after being modified. They were concerned about consumers buying overclocked processors and coming to AMD for support when the warranty had already been voided. AMD has very clearly stated that they do not care what you do with your processor after you buy it.
I find it fascinating that this press release had 164 words of real meat, and 169 words of stock lawsuit disclaimer. I find that sad.
Of course, when I brought this up on alt.folklore.urban, somebody compared it to saying, "So if I bought a sofa about the size of my car, I could drive that sofa down to the supermarket."
--Fesh
--Fesh
Kill -9 'em all, let root@localhost sort 'em out.
There are still a few niggly compatibility errors which puts some people and organisations off, that added to the fact that Intel is using its corporate/marketing weight to convince Joe Public that AMD is not a viable alternative. The corporate world, it seems, just cannot come round to the idea that a monolith like Intel, which, through fair means or foul, has led the x86 CPU market for a decade, is suddenly under serious threat from a company that was considered relatively small-fry just a few years ago. They just can't understand that money, marketing and influence can't be on top all the time (I must admit that my jaded mind took a while to convince too).
I just hope that AMD continue with their tactic of consistently undercutting Intel's prices, even with superior equipment, and lower volume production. Now it would be all too easy for them to hike prices, simply because they have the better product.
If they up the production runs without adversely affecting prices, it will be interesting to note the colour of Intel exec's trousers in a few months......
- "How do we do it? Volume!" - The Bursar of Unseen University.
My friend's K6-2-300 had problems with a lot of Steinberg software (Cubase VST and WaveLab 2 to be precise). Hopefully they've been sorted now (as I'm an *admittedly lousy* musician). I didn't say these problems would affect everyone, but they do exist. Don't get me wrong, I'm going for an Athlon this time round!
- "How do we do it? Volume!" - The Bursar of Unseen University.
I think it has been more than Linux challenging MS recently tho.....More like the combined effort of millions of users, over the last decade, desperate to put Microsoft in their place, regardless of whether they run Linux, FreeBSD, MacOS, BeOS, AmigaOS or whatever.
Trick is, if and when MS are toppled, it's going to be a hard fight to try and stop it from happening again. Remember, we have a new Evil Empire every 15 years or so..... (IBM, MS et al....) You've got to stop these companies getting too big for their boots early on. We've also got to stop players like RedHat and Apple wanting to follow MS-type strategy as soon as they have achieved dominance one way or another (more a problem with the latter at the moment, but CEOs change......)
- "How do we do it? Volume!" - The Bursar of Unseen University.
AFAIK the K6-3 had L2 on board at cpu speed
and is using the mainboard cache as L3
"THERE ARE BETTER THINGS IN THE WORLD THAN ALCOHOL, ALBERT"-Death
42
Reminds of the old r.h.f. (rec.humor.funny, for you non-useneters) usenet posts about "my cup holder broke off" tech support calls from stupid customers. Makes me want to show them the "any" key, yes, that one on the front of the case with the green light just above it...
"It's better to keep your mouth shut and be thought a fool than to open it and remove all doubt."
Ummm, I thought SGI and NVIDIA were working closely together now. Therefore it is redundant to compare the two in a competitive sense.
Project Steve
The ties betwixt the big Q, AMD, and Alpha are pretty close, and the K7 does use the same EV6 bus as the Alpha CPU.
WMBC freeform/independent online radio.
Designing a mobo chipset takes lots of work, in order to ensure stability. Designing a stable SMP chipset is a LOT more difficult; even then, you must design the board around it to be stable. Even a tiny bit of instability is unacceptable in the target market for SMP systems, so AMD has to take their time or they'll get their bad old reputation of incompatibility/instability back--and the corporations are very slow to forgive/forget.
Some mobo manufacturer had vowed to produce a dual Athlon board, but I don't remember which one it was (Tyan?) I'm not sure who will design the chipset, though...I would bet more on AMD than VIA.
WMBC freeform/independent online radio.
AMD continues to expect first revenues from AMD Athlon family processors produced in Fab 30 utilizing its leading edge HiP6L 0.18 copper interconnect technology at the end of the second quarter of 2000.
The at the bottom of the article they state:
Cautionary Statement .
This release contains forward-looking statements, which are made pursuant to the safe harbor provisions of the United States Private Securities Litigation Reform Act of 1995. Forward-looking statements are generally preceded by words such as "plans," "expects," "believes," "anticipates" or "intends." Investors are cautioned that all forward-looking statements in this release involve risks and uncertainty that could cause actual results to differ materially from current expectations.. .
Although I think this will be great (when the prices come down) and all, but I get so disillusioned at promised dates (read Intel) that always get missed. I hope they deliver relatively on time so that maybe by summer we'll have a chance to use the newfound speed.
More race stuff in one place,
than any one place on the net.
...might be to build investor confidence and drive their stock up a tetch to make any retooling they need to do to produce the new processors in bulk just a tiny bit more affordable.... ;)
-- WhiskeyJack
My understanding (a bit dated?) was that they intended to offer more than one flavor of on-die, having one proc. with full speed and another with maybe 1/2. I think the T-bird was the full-speed. Anyone?? -Tranq
hmm... the sun neither rises nor sets by east coast time. it was 2 pm in Germany...
With Athlon, AMD has carried the competition to Intel's doorstep. This is the idea. This is what the marketplace is supposed to do. We are supposed to be the beneficiaries.
So I wonder when mainstream PC makers will quit considering AMD to be the cheapo alternative and realize that, at least for the present, they are the performance leaders.
The living have better things to do than to continue hating the dead.
Athlon 2, 4, and even 8 processor motherboards are coming soon! imagine - 8.8ghz! No stopping amd now! And if this baby runs this fast without any cooling, think how well it could be overclocked with one of those kryotech freon systems - probably 1.5!!
"Make it idiot proof, and someone will make a better idiot."
How can AMD ship this thing on time?
By shipping it and then announcing a shipping date:)
you could pop open that case and throw it in and get that almost microwave-like heat from the almost 2GHz CPU :-).
Oh wait but then the cooling in there is so
much that might no be possible. Whatever.
............ no.
I need to know, too! I'd like to start heating my grits with this! :)
--
We have fought the AC's, and they have won.
2.2 gigahertz for my 2.2 kernel.. when will i be able to set this system up ? This month ?
I believe the clock on the slashdot server is One Hour ahead.... This story apparently was posted at 8:58 AM... but it's only 8:20 here right now... maybe my clock is off ???
I'm no moderater but that should knock your post up to +1 for a while :)
email me sometime okay and we'll setup a slashdot usenet group where we just mirror new stories on slashdot.. usenet would be much better than this moderator crap (especially the Free BSD moderators, theyre the worst of them all)
The world time isn't US time ... Dresden is in Germany.
Relinquish
Hey Killer, That little blub has been on ALL press releases since the 1930's. In fact most of the blubs say "In accodance with the so and so law of 1930 something...". Its a legal thing. You know always gotta cover your fanny nowadays. -Justin
The question now is, what am I going to do with a 1 ghz processor? I guess I could take up raytracing again......
Normally I don't like to scream "troll" when I see things I don't like, but I just recognised this post as being a cut and paste from another discussion on CPU's.
I can't cry plagarism, because it may be the same A/C who wrote the first one. And I can't seem to be able to pull up the old article.
Baseless as my claim is, my memory is still pretty good. Does anyone else remember this post, or should I lay off the mushrooms??
(Apologies if I am in error.)
thanks i know its really big... but thanks...
fsck micro$oft... thats all i have to say about it
Acording to jc-news.com the processor was actually a athlon thunderbird and the cache is on die. But I also found some confilicting stuff at a very nice current an future processors page thats states that the on die cache is only going to be on the spitfire. Wonder who is right?
fsck micro$oft... thats all i have to say about it
we all have our own definitions of our requirements, and there are degrees of openness. Domino does have a number of well documented APIs the c API allowing full access to the internal data structures, the other APIs protect you a bit more from doing yourself an injury. All software is layered, some layers are sometimes open source. My databases on domino are always released with source (although most are not free or freely copyable outside of the client I sell them to). If you are using Apache on Linux then you have your web sites(open) on top of Apache(open) on Linux(open) on an x86 processor which is closed. I am using my databases(open) on domino(closed) on Linux(open) on an Intel chip (closed)