Slashdot Mirror
AMD Roadmap for Coming Year and Beyond
nexex writes: "With a new year comes new products, and AMD certainly has some new toys for us to drool over. The first of 2002 will see the release of "Thoroughbred," a version of the Athlon XP chip made on the more advanced 130-nanometer manufacturing process. The chip will cover 80 square millimeters in area, or 65 percent of the space of the "Northwood" Pentium 4 coming from Intel in early January. That chip measures 116 square millimeters, according to AMD estimates.
For more, including info on Clawhammer, Sledgehammer, and all the Intel bashing you can handle, see here." I hope they don't really mean that "these new chips will also consume less heat than current AMD notebooks chips."
Hrm, the third paragraph is an intresting one. "Instead of a (Microsoft-Intel) duopoly, we are going to have a holy trinity," he said.
:P
I guess we know where AMD stands with regards to Linux
autopr0n is like, down and stuff.
Have to say I like horses better than rivers in No-Cal and Oregon.
Consume less heat? I believe they mean dissipate less heat.
Tired of free ipod spam sigs? Opt ou
"My biggest fear is that Intel will come out with a 32-bit processor with 64-bit extensions because it is the right thing to do," Sanders said. "The Itanium it turns out is a niche product...We are going to have a role in the industry because we better fulfill Microsoft's needs."
the Itanium is a niche product now. in a few years i expect its time will come. 64-bit is not cool now but eventually OEMs are going to lean that way for upward compatibility. remember that the PowerPC existed in relative obscurity for a while too, and now it's the basis for what are probably the best UNIX machines on the market.
Didn't you all know? AMD processors reverse entropy.
http://www.amd.com/us-en/Corporate/VirtualPressRoo m/0,,51_104_608,00.html
That link includes a pretty roadmap graphic. It also shows the Barton design following the Thoroughbred release.
Wait for next Windows release.
Grab suffix of Windows version.
Append suffix to the word "Athlon".
Market upcoming Athlon+windowssuffix chip.
"At the end of the day, we need to get a Compaq, Dell or HP," he said. "IBM is going to be tough."
On the consumer desktops and notebooks it will be hard for AMD to displace Intel. The "Oh it must be faster it says so" mantra will always be a key selling point in the retail world. The server side will be interesting with promise of less heat, smaller size and 64-bit application support, Intel chips will have more competition in the rack systems market. IMHO I would love to see dell ditch intel for all its notebooks and use the new AMD chips. The batteries have to discarge so fast it fries my PC cards with the heat.
"Get them before they get....
Tired of free ipod spam sigs? Opt ou
Won't the new first of the new throughbred core chips be used for portables?
They're just powered by a thermocouple now, instead of the power supply. Everyone knows that.
These new chips coming from AMD are nothing short of amazing. While Intel struggles with their attempts to force a slower, proprietary memory architecture on PC users and push a weaker processing architecture, AMD is leading the market and producing technology that is faster, more reliable, and cheaper.
Unfortunately for AMD, better technology often loses to superior marketing forces. Several of my friends went to work for Dell after graduation, and they told me that their employer is not going to be supporting these new AMD offerings out of allegiance to Intel. Dell (and many other manufacturers, such as Gateway) are afraid of Intel cutting them out of the loop when supplies are tight so they give AMD second-rate status or drop support altogether. The problem also exists that many customers buy Intel exclusively, despite its low performance/price ratio.
The future isn't nearly as bright for AMD and TMTA as it should be. If our government actually punished companies for anticompetitive practices, things would be different. Maybe in 2004 it will be a priority for the new administration. But I am not holding my breath.
~walter
I remember reading a comple of months ago that Dell would offer Athlons on thier laptops. Well, the other day I went to Dell's web site to check them out and gasp! no Athlons. And now that Dell discontinued Linux too, they are back to being the Wintel bitch they always were.
Anyway, I think Sanders is overly optimistic in his analysis. It doesn't matter that Pentium 4 is a dog -- it's made by Intel, therefore it will sell. Also, without support of large OEMs, AMD is going to have a tough time. I only hope that it doesn't end up like Alpha -- a great technology that's been effectively killed and buried.
___
If you think big enough, you'll never have to do it.
I have been an Intel fan for years because I want quality even if it's at a higher price.
AMD processors used be cheaper and slower. But lately this has changed. Athlon XP + DDRAM make a killer combination because they are faster much cheaper than the P4 + RDRAM option.
I will be upgrading my system from P3 733 + i815-powered motherboard to Athlon XP 1800 + KT266A.
If Intel doesn't lower prices, they're going to lose, and that would suck.
I've been thinking about what keeps Intel alive. If the decisions were made on a strict technical basis, what would keep Intel alive? Considering that AMD processors are much cheaper and equally fast, there is no reason to buy Intel these days. Mabye the free market rules are not applied to computers?
Mikael
Vintage computer adverts: http://www.vintageadbrowser.com/computers-and-software-ads
Has VALinux, um, I mean, VA, decided to cut corners starting with making sense? Hey, Timothy, I believe you either meant "consume less energy" or "produce less heat". Both has different meanings, but, yes, in regards to CPUs these days, they're mutual. Not to nitpick...
is that AMD is a huge supporter of Linux, compared with Intel. In their press releases, they do need to stress Windows compatiblility because they do need to sell to that part of the market to survive (and their sales are traditionally extremely strong in the Linux community anyway, because Linux users are more informed buyers).
Intel has been in bed with Microsoft for years, as can be seen from their use of the PE32 format in their bootloader code. AMD has not (despite naming their chips after Windows XP) been in a position or had the goal of reinforcing Microsoft.
AMD's success is crucial to Linux's success. Without a major hardware vendor who supports us, we will be left out in the cold. It is nice to see that AMD is headed for market dominance with this fast new hardware so that Linux can continue to thrive in the mass market.
-sting3r
MS props them up. Not many MS ads out their without the IntelInside blurb.
Why is AMD making these things so sensitive to heat? I'll bet they're also sensitive to vibration, electricity, and about anything that its competitors handle every day. Most thoroughbred hammers can resist hundreds of degrees before they melt/disentigrate
.
It's a well known fact that Dell wont touch AMD with a 10 foot pole due to it's stability problems. If AMD really wants large OEM acceptance they need to take seriously the problem with the junk motherboards coming out of Taiwan.
...as far as I know.
They would however (as I'm sure a lot of other people will point out) consume less electricity. Therefore their power consumption will go down, which in turn will lower the heat emission.
"Appaloosa, a discount version of Thoroughbred."
they must have been smoking something really heavy when they named that.
If AMD managed to release their x86 with 64bit extensions in 2002, Intel would be big trouble. Too bad that they missed their targte again.
AMD is doing fine. Their market share is rising, and Intel's is falling, albeit slowly (based on numerous reports released in October 2001).
My Thunderbird 1200MHz is reliable, you just have to be careful about the operating temperature.
AMD's are less expensive than the comparable Intel chips.
I have seen no evidence whatsoever that current AMD chips are less reliable. The fact that AMD chips use a lower clock rate and generate less heat strongly suggest the opposite. In fact, reliability of processors does not seem to be a significant factor in overall PC reliability at all: disk drives, fans, memory, motherboards, and ports all usually go first.
If Dell would ship AMDs, we'd buy them. Instead, they are shipping souped up versions of the Pentium 3 to their corporate customers because that's the only thing they can ship from Intel. I really wonder whether the cosy relationships between, say, Dell and Intel, are merely friendly or whether there are some other arrangements...
I've said it once, I'll say it again... No one ever wants to flat out say that the motherboards for AMD chips are a lot less well supported than the motherboards for Intel chips because they're so busy cheering for the underdog.
s p4-15.html [tomshardware.com])
But if you dig deep into, say, Tom's Hardware Guide: Another factor is the stability and product quality of a system: while all Athlon processors suffered from occasional instability in our tests, the Pentium 4 platform ran without a glitch. (http://www6.tomshardware.com/cpu/01q4/011031/xpv
Now, for me and I'm guessing a lot of people, system stability is far more important than a few percent performance increase. Since these machines are so closely matched and overpowered anyway, I'd like to see more emphasis on other factors like stability. More than a single sentence buried in one review, anyway. If these things are crashing during the tests, I want to know about it with a big red X on the graph...
Or just the chance to stop having to download freakin' 4-in-1 drivers for my KT7A... if I had known about the KT7A Faq (http://www.viahardware.com/faq/kt7/kt7faq.htm) before buying one, I probably would've passed... but all the "review" sites just a good things to say about it...
They're not idiot zealots bent on mentioning an insignificant player in the big picture of chip sales.
AMD marketing: Optimized for Windows! Optimized for Linux! Runs BeOS! Minix too! CP/M! AtheOS! FreeBSD! DOS!
Of course Linux is bigger than any of the others, but you get the picture....
Intel designed the i845 with DDR to be slow because they own 25% of Rambus. (duh) Compare PC133 SDRAM in a Tbird to RDRAM in a P4 and the Tbird will win hands down.
These new processors actually do consume heat as they operate, turning it into valuable CPU cycles. These processors require the use of a whole new CPU packaging technology that pumps heat into, rather than out of, the CPU core. Initial tests in laptop configurations have proven uncomfortable to use, due to the fact that the laptop begins to condense water out of the air, and eventually frost over as it runs. AMD expects that these problems will be solved by the time these processors reach the marketplace.
They will no doubt use this new technology to bury Intel, Microsoft, AOL Time Warner and the Soviet Union. Having vanquished these foes, they will split their company into a half dozzen competing CPU manufacturers that compete fairly with one another. Each of these new chip makers will pour billions of dollars into Linux development. Their executives and directors will use their extra income to feed starving children and help build a better public education system.
Oh, wait. That would break the laws of thermodynamics. Never mind.
In spite of the suggestions and all the tests that I have made, I have not cavato a spider from the hole.
So what do you think is for the intelligent?
A while back hotmail.com(!) actually expired.
I used to bulls-eye womp-rats in my pants
AMD has apparently found a way to reverse the third law of thermo-dynamics. Their CPUs literally 'consume heat' That must be why they've been beating Intel, and now they let it slip
autopr0n is like, down and stuff.
The AMDs consume heat? Whoa! No more worries of a heat sink and noisy fan. I guess by reducing the amount of heat they consume you don't have to worry about your laptop freezing your lap.
Intel only manages to produce heat. Wonder how much power the chips consume?
well...just read what OEM's packages of 1K chips run at. I think you will find that AMD's are cheaper for similar chips. Read the article, it says they produce cheaper... As to fewer customer returns, unreliability, etc...I don't know. personally I've had all kinds of trouble with Intel, but my Athlon 500 and 1.2-C have worked beautifully. (shrug). Just 2c...
Who is this Anonymous Coward character, how does he post so much, and why is he always such a whore?
I hope they don't really mean that "these new chips will also consume less heat than current AMD notebooks chips.
fear using your AMD notebook to check your e-mail and simultaneously toast your english muffins in the morning.
Yeah, everything2.com too. Weird.
Sure, I use the things. They are fast compared to
Intel, clock cycle for cycle. They ARE NOT Alphas
like 21264's clock cycle for cycle! I would love
see a really good 64-bit chip that makes a really
good computer and doesn't give a damn for Micro$oft!
Maybe the big challenge is making a good
motherboard? Not much matters when win32 is what
your design is aimed at. Do I really have to pay
$10k for anything that comes close to a modern
computer?
They consume less heat?!?! Cool!!
How about something similar to the "full support of the p4" code set that XP has for Athlon proc's?
...ahem...talents for pushing/pulling/dragging the industry over to AMD chip/sets.
In a twisted way, it would be leveraging a duopoly for the greater good. Use Microsoft's
I forget off hand if this was an OEM thing or a MS thing, but it would be quite nice.
Call up a OEM or Screwdrive shop and say "I'd like a 6bay tower, AMD/Intel, MB (speed/stability) and XXX amt of memory, disk space, OS, etc, etc.
At this moment we can do exactly that, save for OS and Processor.
After all, it is not called the Wintel duopoly for nothing, and if AMD's holy trinity dream is to come to fruition, the'd better act fast while the trial drags on or join the fray.
(let's just hope the trinity does not equate to an equilateral triagle whose side length is 6).
If it is not on fire, it is a software problem.
Level 2 cache is more significant than more people realize. It's also insanely expensive compared to system RAM because cache RAM is often static, rather than dynamic, requiring more circuitry (actually, an entire flip-flop) than dynamic RAM requires (which is a single transistor and capacitor). Interesting naming convention nonetheless.
Tired of free ipod spam sigs? Opt ou
amd rocks, but w/ linux2.4? just saw this on #kernelnewbies [irc.openprojects.net]
:-P is this normal behavior ?
;)
user: 2.4.14 is crashing on my athlon after half an minute
geek: I would hope not
those times those times..lets forget about 2.5 as we really can forget 2.4 currently
Before going goo-goo-ga-ga over the future AMD processors, how about some technical specifications of the current MP processor, and also some "real" clarifications between MP and XP. And while at it, they should replace their voodoo doctors, and hire some real tech people to explain the SMP feature of the XP, as detailed in XP's specifications
So not only is AMD part of the trinity - I guess it must be the holy ghost -, but they are also the head of the church since they seem charge for the blessings of MP.
Maybe AMD has a new angle on power consumption. Maybe their proccessors extract thermal energy from the surrounding atmosphere to power the chip.
Or maybe not.
Yes I have a 8K series and a 7500 inspiron. That article is a little off though. The 7500 was the first dell laptop w/speedstep, but it would throttle down only if it was running off batteries when it booted. The 8K series changed speeds in realtime(?) I ended up patching both and disabling speedstep. But dell is much better than gateway's attempt with the 750 Mhz solo. Not only did it fry PC cards, and occassionlly make a burn mark on my desk. It would power up and down the so much, it crapped out the little HD after 3 months, burned up the internal modem and then the onboard video card went. That notebook (9300) went through 3 HD, 2 MB and about a gig of notebook RAM. Talk about a lemon.
"Get them before they get....
is more like HP eating up and spitting out Compaq.
Life at work has not been the same since...
NetBSD, OpenBSD, FreeBSD
The Irongate Chipset (AMD 751 / 761) has a serious hardware flaw that causes the motherboard to stop responding about 75% of the time the AGPGart is activated.
About 13 months ago, AMD confirmed this flaw affected all Irongate chipsets. 1 month later, all Windows drivers for Irongate chipsets had work-arounds implemented. 3 months after this, nVidia had incorporated similar work-arounds into their binary-only NVDriver.
And that just leaves the kernel agpgart.o.
AMD have been repeatedly emailed by me and apparently everyone else with Linux + Irongate + non-nVidia card, and sometimes receive a carbon-copy of AMD's standard response:
"AMD are aware of this issue, and are currently hashing out a solution with various distributions of Linux".
Until this issue is fixed (which it never will be), AMD can suck me off while enjoying the negative publicity their non-existant customer support gains them.
The Irongate Chipset (AMD 751 / 761) has a serious hardware flaw that causes the motherboard to stop responding about 75% of the time the AGPGart is activated.
About 13 months ago, AMD confirmed this flaw affected all Irongate chipsets. 1 month later, all Windows drivers for Irongate chipsets had work-arounds implemented. 3 months after this, nVidia had incorporated similar work-arounds into their binary-only NVDriver.
And that just leaves the kernel agpgart.o.
AMD have been repeatedly emailed by me and apparently everyone else with Linux + Irongate + non-nVidia card, and sometimes receive a carbon-copy of AMD's standard response:
"AMD are aware of this issue, and are currently hashing out a solution with various distributions of Linux".
Until this issue is fixed (which it never will be), AMD can suck me off while enjoying the negative publicity their non-existant customer support gains them.
Buying an Athlon gives you that fuzzy feeling that you're supporting the underdog. Even if the prices were the same I would choose AMD. We NEED 2 competitors (or more) beating each other to have low prices and fast progress in technology.
The Register (my favorite news website) has an article titled "AMD plans to beat 4.4GHz desktops".
;-)
I can't imagine what a 4.4 GHz would be like to run. If bus and hard drive speeds keep improving, maybe a hog OS like Windows could boot in only a couple of seconds.
Ooooh, 2003, please get here fast
I need a mission critical server that is x86 based? Forget intel chipsets, forget VIA, forget SiS, I go with Serverworks chipsets With pentium III processors, Serverworks are proven reliable chipsets vendor, and while the cost of the motherboard is a bit (well a big bit :) ) higher, it's still way cheaper than goind into most other platforms.
I need building an x86 renderfarm? NOTHING beats the power of a tigerMP with dual athlon price/performance wise. Stability? it is, it's simply rendering, not running quake while processing SETI units and running beta video drivers with leaked chipsets drivers.
The processors are a tool, you don't see people fighting over mastercraft vs black and decker when they come to buy a screwdriver, why you guys gets so religious about processors? I remember how happy most of you were when celerons with cache came out, overclocking that 300A to 450... you didn't think about AMD back then (well most of you didn't).. you were just saying "the k6 sucks, celeron rules" (I own a dual 366->550 that I'll probably change to a tigerMP). Of course most of what intel did to get flamed happened after that (rambus, crappy chipsets after BX, patent crap with via, etc), It's still pathetic to see how people react so badly...
Don't get me wrong, I find what intel did (especially with the rambus and via case) disgusting, but buisness is buisness, if they deliver good stuff at a decent price, I'll still get it, I have a company to maintain and a job to do. Of course if in the process I can do something about it as a IT manager, I will do it, but NOT at the demise of the company that employs me. There are alternatives to Rambus (serverworks gives a nice memory bandwidth with standard PC133 ram, they should come out with the same technology with DDR memory soon so that WILL kick hard). This is where I voice my opinion. Still, I wouldn't pay 50% more for AMD if intel would offer a similar technology same specs, same performance for less, this is where it becomes religious and pathetic.
If tomorrow I could get dual 2.2GHZ intel processors with rambus, 33% cheaper than an AMD based solution with DDR ram, I'd go for it, right now, it's AMD that has the upper hand, so these are the guys that I buy from for general computing/renderfarming.
--- Metamoderating abusive downgraders since my 300th post.
Yes, just swap VCC and VDD. Can't see why this hasn't been thought of before. (-:
Disclaimer for the idiots: trying this will almost certainly popcorn your entire computer.
Got time? Spend some of it coding or testing
"I think Intel is trapped. When they designed the Pentium 4, they didn't expect to have a real competitor in the marketplace with a meaningful alternative," Sanders said. "They always underestimate us, and being underestimated is a good thing."
Being underestimated by consumers, howver is a very BAD thing.
Standard RAM? You mean like the SDRAM and DDR SDRAM that AMD motherboards can use while P4s have to use Rambus?
Not like Dell, Compaq, etc... care about standards. I once tried to put a motherboard I had into a Compaq case, and I couldn't because (A) the case didn't conform to the ATX standard (the board wouldn't fit in physically - and it wasn't even a full size ATX board) and (B) the case headers (wires from the power button, power LED, etc....) were all on one ribbon in some weird fashion that wouldn't plug into the motherboard.
Tim
Omnia vestra castrorum habetur nobis.
while you're compiling your code
I better not type what I was planning to type next, otherwise I'd get a moderated lame.
The best case for VLIW (Intel calls it EPIC, because VLIW has a bad rep, but it's VLIW) is inner number-crunching loops. Think rendering, audio/video compression and decompression, and similar stuff. But most computing isn't about tightly coded inner loops any more. Least of all on servers. Mostly, it's about calling lots of little subroutines that call more little subroutines. That's the worst case for explicit parallelism. Unless the compiler optimizes over subroutine call boundaries (which typically means very heavy inlining), explicit concurrency stalls at each subroutine call. Not good. The HP compiler guys working on the Itanium compiler admitted a few years back that it was going to take a major breakthrough to generate good Itanium code.
Three times in the past, Intel has tried to move away from the x86 architecture to a new, more modern one. The iAPX 432, the i860, and the i960 were all moves in that direction. All three were dismal flops. In Andy Grove's book, Only the Paranoid Survive, he takes this as a lesson that Intel should't try to force an architecture change on its customers.
I would have expected Intel to come up with the Sledgehammer and somebody else to be pushing the Itanium.
(Maybe the Highlander quote will get me modded up :-) For processor manufacturers the secrets to eternal life are popular software support and fabrication capacity. Try this little exercise: suppose that Intel immediately closed all fabrication facilities, could demand for processors be filled? I'd suspect not for several years (maybe two years minimum just to build the fabs and get it on line). The days of hobbyists designing processors and starting their own production are long gone, only the big boys can do that.
On a side note, I'm a big fan of AMD's new technology and AMD has made tremendous strides, but the weak economy may find them overextended.
The EPIC instruction set architecture of Itanium/McKinley is not a good match for Java Virtual Machines....at least thats what I read in a technical article about IBM's Power4 architecture. Apparently JVM's can't take advantage of VLIW as well as compiled code can, and this makes sense because Java is compiled to machine-code on the fly. Like it or not, Java is a major player in today's software technology. If AMD continues to excel with IA-32 (which is a decent match for Java), it will help Java as well as AMD...
amd's 64bit hammer CPU and intel's itanium targets the server market where all the $$$ are.
for a server the main concern is: reliability, redundancy, and scalability
performance is just secondary.
for the intel itanium, intel has made very good profusion chipsets that will give very high I/O (PCI-X with lots of channels) and memory bandwidth (quad interleaved with chipkill) that will feed the fast CPU. just as serverworks is right now, we buy those expensive systems because we need the reliability and bandwidth. although serverworks is a 3rd party company (and intel tried to buy it from broadcom but to no avail,) it has a somewhat allegiance to the intel platform. they also make the best chipsets for pentium iii, pentium iii-s, pentium iii xeon CPUS. intel also designs very very very good motherboards and chipsets. like their new releases for the tualatin CPU, when you see the design and placements, it is far off from the asus, gigabyte, msi, etc... intel also creates server CPU that can handle big L2/L3 on-die caches running at core speed. they are also able to scale their processor to 9632 (have you seen any amd processors used in supercomputers not clusters such as beowulf?)
for amd, they may have a good cpu (better performance) but the problem is who manufactures the board and chipsets? for boards, they will most likely rely on asus, gigabyte, msi, etc... but i will not trust my money on them since they do not have features such as management, high i/o, and expertise in creating server boards. moreover, the chipset right now for the dual athlon is supposed to be amd but it flops big time. so motherboard manufacturers use the via chipset. you do not get all the performance (I/O, PCI) and reliability. so since this is the current situation for their workstation, what more for server?
so if amd wins the war with intel in the CPU arena, amd needs lots of resources to develop very good platform for servers (motherboard, chipset, memory controllers, compilers) before they can penetrate the real server market.
lastly, marketing is very important. if do-it-yourself servers are just the target of amd, they will not penetrate the real server market compared to intel, which is backed up by companies such as unisys, ibm, dell, sgi, hp, compaq, microsoft, and linux?.
i will say it is like intel offers end-to-end solutions for server platforms compared to amd that does only cpu and relies on partners to support their cpu.
Live your life each day as if it was your last.
I was at the computer markets today & I could've sword I saw a old SCSI/RAID controller, or something, with a i960 chipset.
>>The chip will cover 80 square millimeters in >>area, or 65 percent of the space of >>the "Northwood" Pentium 4 coming from Intel in >>early January...
With Die Sizes going down and transistor count reaching stratosphere,When does the heat become unmanageble??
Wanted : A Signature.
'while Intel chipsets have usually being pretty consistent'
If they can shrink the die so much they should take advantage and add a real nice size L1/L2 cache. Say 5 to 10 MB. With GB main memory becomming common cache should be scaled too.
Most of the wasted time with a processor is "cache miss" so, PLEASE AMD take the plunge and add a really big cache.
It's even had to subcontract production with its competition.
Even with the risk of the sub-contractors bringing out unbranded clones.
Which has occured in the past, when Asus & Epox sub-contracted some of their board manufacturing to others.
All of a sudden you could buy unbranded clones made from the same plant as the sub-contracted boards. Because those plants were making more boards than what they told Asus & Epox.
As those boards didn't go through Asus's testing process, Asus had to send out world wide warnings over the clones.