Slashdot Mirror
Athlon 64 Debuts
SpinnerBait writes "AMD launches their Athlon 64 and Athlon 64 FX chips today and there is
a full analysis with benchmarks up at HotHardware. Interestingly
enough, Intel pulled a fast one (literally) and released a new breed of Pentium
4 chips with 2MB of on board L3 cache, just in time to boost their performance
in the benchmarks for this launch. Regardless, the performance levels for
AMD's new flagship look very strong." Tom's has a story, or Tech Report, or see info straight from AMD.
And Anandtech has a good article up, as well.
$8.95/mo web hosting
...how does it benchmark against the Commodore 64???
Here are some more benchmarks
AMDzone
AnandTech
XbitLabs
Ace Hardware
There are even more at AMDZones main page.
1) Application Programming
2) Ssytems Programming
3) General Purpose and System Instructions
4) 128-Bit Media Instructions
5) 64-Bit Media and x87 Floating-Point Instructions
Get them here.
Then go make your favorite compiler or windowing system work better on this.
See what I've been reading.
We saw Athlon XP get released when Windows XP was still "hot" and aggressively marketed by Microsoft.
We now see Athlon FX get released when the GeForce FX graphics card series is the state-of-the-art among hardcore gamers, along with ATI's Radeon series. Hardcore gamers are also coincidentally a target group for AMD's processors since they're known to look for the latest and greatest processor-wise.
I wonder if this is just coincidental, or if AMD is actually using the popularity of other brands to market their own? Are they even using dirty tacticts to try to fool people into thinking "Ooh, this Athlon XP should work especially well together with this newly released Windows XP then, right?" and "Oooh, great, I must have the Athlon FX for my latest video card!"
But perhaps they just happen to choose the same abbreviation as other popular brands at the time for the second time in a row. However, I still can't say AMD's Athlon marketing smell good to me at least.
Beware: In C++, your friends can see your privates!
Remember when the P4 came out and it was slower than the P3 at the same clock speed? Like P4 was then, the Athlon64 is designed with the future in mind, not blowing away everybody on day one and having no room to scale from then on.
The global economy is a great thing until you feel it locally.
I would hope that Tom's Hardware would at least try to keep the anti-Mac bias down to a tolerable level.
"At the same time, Apple laid claim that with the G5 model, it would offer the world's most powerful desktop system. Apparently there are users who will believe these kinds of claims. Whatever - at least the G5 also has 64-bit support with regard to the software. Nevertheless, there is still no final operating system available for it."
FUD, lack of evidence, and outright lies - they call this journalism? They dismiss the Apple's claims about the G5's performance without a) including it in their later benchmark or b) citing any references. Why am I suppose to believe someone who is trying to put down a group of users like they are petulent 2 year olds. Also, what is the crack about not having a "final operating system" out yet? 10.2.7 is a fine OS for the G5. If he means that there is no 64-bit OS, why not just come out and say it?
Pfff. I can't believe I took time away from constantly reloading my Fedex tracking page to read that drivel.
PS - FEDEX, BRING ME MY DAMN G5 ALREADY!!
Have they even created one yet?
Actually, no.
If you take a closer look at the pictures in the article, you will see that they've attached a wire to each and every pin of the processor. It's all a loose mess of wires and duct tape. If you want an Athlon 64, you'll probably have to do the same yourself, because there aren't scheduled any motherboards for it before sometime after christmas.
How small a thought it takes to fill a whole life
A benchmark of Linux on the following systems:
GCC Settings for each system should be optimized for the best possible stable performance. I'm so sick of seeing 32 bit windows benchmarks for testing 64bit processors.
...of both the new AMD-64 and the Pentium 4 Extreme is that the prices of the older chips should start dropping like a stone.
Learning HOW to think is more important than learning WHAT to think.
AMD created the 3DNow! extensions to the 80x86 instruction set architecture (ISA), also known as IA-32. They were a significant improvement over the original set of MMX extensions. However, later, Intel created the SSE (and SSE2) extensions. Guess what? AMD was forced to incorporate them into its future chips in addition to the 3DNow! extensions. Ignoring the SSE extensions would have cost AMD dearly in terms of marketshare. The fact of the matter is that Intel sets the global standard for the IA-32 ISA.
Now, AMD has created its own x86-64 extensions to the IA-32. You can be sure that Intel has created a different set of 64-bit extensions (which we shall call "INTEL-64") to the IA-32. After all, why would Intel support AMD in any way? Once Intel activates the INTEL-64 extensions in the upcoming Prescott, AMD will be forced to go back to the drawing board to incorporate the INTEL-64 into all future chips. The current Athlon64 will be like the K-5 -- interesting but without a future.
AMD will probably take an additional 2 years to produce an INTEL-64-compatiable chip. By that time, Intel would have locked 90% of the 64-bit desktop market with Prescott.
The worst news is for Sun. With Prescott, Intel has a 64 bit chip that will be significantly faster than the UltraSPARC III/IV. Right now, the Pentium 4 crushes the UltraSPARC III in performance. Please review the performance characteristics of the Pentium 4 at the SPEC web site. Since Prescott (successor to the Pentium 4) will be faster than its predecessor, Prescott will clean UltraSPARC's clock. Moreover, the number of applications that will run on Prescott -- the heir to the software empire of the x86 -- far exceeds the number of applications that run on UltraSPARC III/IV. On the key TPC-C benchmark, Prescott will clearly deliver outstanding performance, compared to the UltraSPARC III/IV.
In short, when Intel activates the INTEL-64 extensions in Prescott, Intel will force (1) AMD back to its usual state of borderline bankruptcy and (2) Sun into being a software company.
I think we can all see the wisdom of releasing the new processor before the new OS.
-Looking for a job as a materials chemist or multivariat
This sure looks like a motherboard that supports the Athlon64, shipping same business day.
Ita erat quando hic adveni.
Looking for a Linux/Windows/Mac admin/support tech monkey in the Los Angeles area? Please see my resume.
Though I am a die hard AMD supporter, i have to admit Intel has really pulled one up on AMD this time. The 64bit 3200+ is just about 15-20% faster than the stock and barrel Intel 32bit 3.2 GHz. Bad news for AMD this is, considering the retail price of these babies is 450 & 800$ (Normal and FX).
Yeah. I can't believe that you can get a brand new CPU that's 15-20% faster than the previous champion for only 25% less! Oh, and that's in 32-bit mode. If 64-bit computing takes hold then Intel is SOL at the moment - despite the rumors flying around about Prescott and 64-bit instructions.
Yeah, the Athlon64 3200+ is $465 (note, look at the retail price w/ heatsink to be fair), but the P4 3.2GHz is $619.
The Athlon64 FX-51 is certainly overpriced, given how miniscule the performance differences are, but that's hardly a surprise.
What Intel did pull wasn't a price/performance coup (because it isn't, by any means) but a paper launch debacle. Every single review I've seen thus far includes benchmarks for the P4 3.2EE -- which isn't available until November, and at prices similar to the Ath64-FX (based on preliminary 1000 CPU lot prices). The P4EE is competitive with the Ath64, but it's a smokescreen. You can buy an Athlon64 right now, but the P4EE is non-existant.
And BTW windows released XP 64bit Beta1 today.
Unfortunately it appears that there's a severe lack in available drivers. All the sites are having to use nVidia 5900FX's and even then can't bench any DX9 apps in Win64 due to no 64-bit DX9 being available.
I would take your post seriously if you had mentioned what part you believed Microsoft would play in the world of competing 64-bit extensions.
WXP for the Althon 64 is well on its way, as seen in the linked HotHardware review. Will Microsoft and the driver writing departments at hardware firms put up with a stealth announcement of another set of 64-bit extensions?
If you actually want the industry (and 64-bit computing as a whole) to move forward -- then go out and buy a chip...if nobody buys these because no OS/Software manufacturer writes 64-bit code, then there will be big trouble for little AMD. The idea was to build a chip that runs 32 and 64 bit code very quickly. What it sounds like you're saying is that you're waiting for Intel to release a 64-bit chip so that everyone optimizes their code for that. I, for one would rather back the company who was innovative and was first to market with a pretty cool product than the biggest guy on the block (er...industry...whatever).
From the benchmarks I've seen -- it does a pretty damn good job at both 32 and 64 bit code (especially for a first release without a good 64-bit clean codebase). It manages to beat the existing 3.2 Ghz P4 for cheaper.
I hear what you're saying about waiting on at least one level though -- I can't remember ever spending $400 on a CPU, but I'm confident that in 6 months, those things will be selling for quite a bit less than they are now...they'll be a good bargain.
Finally, I have a 1.4Ghz Thunderbird as my primary desktop. At this point, it should be called a 1.4Ghz Shitbird. I intend to replace it -- the only questions are: when, and replace with what? I know that if I decide to get an Athlon64-ish chip, I won't be making that decision based on whether or not there are 64-bit apps/OS'es for it. For what you pay, it works great...I'll make my decision based on price:performance ratio on what's available now...and from what I can see, it already shines against a much more mature platform.
-Turkey
I read several of the reviews, and all stuck with 32 bit code for the comparition between the Intel P4 and the AMD Athalon 64. Linux runs on the Atahlon in 64 bit mode, wouldn't be hard to compile PovRay and Doom on a 64 bit compiler and see if anything changes. Thats just for an easy test.
Many real world (science?) applications benifit from 64 bit processors, find some (presumably running on UltraSparc, PPC, Alpha, or such) and port them over to see how the 64bit abilities of this chip compares to the other existing chips.
I run open source OSes, and open Source applications. I don't care about 32 bit performance because I'm fairly sure that if I did have an Athalon 64 I wouldn't run 32 bit code very often. I can choose between many chips, compatable instruction sets to me means gcc (or other compiler) has an output for them. 32 bit x86 compatiabily is nice for the few times I have to run something 32 bit (normally in Wine) and that doesn't happen very often.
Intel's chip is the better choice for the user who wants performance in apps that actually exist today.
Based on what?
The Athlon64 outperforms the P4 in virtually every benchmark, often by a hefty margin.
Ignore the results from the P4EE chip -- you said you wanted something that actually exists today. The P4EE will not be available until sometime in November.
On top of that the AMD Athlon64 3200+ costs ~$465, while the P4 3.2 costs ~$620. So you get slightly more power for considerably less cash. The motherboards appear to be roughly the same price for a Socket 754 board and a 865PE-based board (or you can drop more money for a 875-based board and get virtually no performance improvement -- your choice).
All of that said, if you want to buy the best x86 chip right now and money's no object -- buy Intel. Not because it's faster (it isn't), but because it's probably going to be more stable. We're talking about a 1st generation CPU on 1st generation motherboards. Not a great prescription for stability there. If money is an issue, but you still have to have the fastest thing out there, then buy an AthlonXP -- the 3200+ is about the same price as the Athlon64, but the MB's are cheaper and more stable (just as stable as P4 chips/mobo's).
If you want to be a realist and get the best bang for your buck then stop looking at the fastest chips available and start looking at the best price point -- a P42.6C or AthlonXP 2800+.
I ran across this article today... apparently someone is already trying to put together a mobile system around AMD's new 64-bit offering.
64 bits words have an advantage I would not have realized before programming compilers for dynamically-typed languages:
In a DT language , you need some way to 'mark' information to say wether it is a number, a pointer, etc. The usual technique is to mark the bit field with a 1 or 2 bit tag at the end.
Also, for garbage collection (ie Mark-And-Sweep) you need to be able to 'mark' the object that needs to stay alive so they are not reclaimed by the gc.
That being said, taking 2 or 3 bits on a 32 bit field is a lot, but it is very interesting to realize that that cost go away on a 64 bit machine.
So, 64 bits = more memory (larger address space) but it also means some techniques becomes much more viable in terms of feasability of implementation, which is a very exciting (for some loose definition of exciting) prospect!
A message from the system administrator: 'I've upped my priority. Now up yours.'
I don't want to bother going over the implications here...those that know them, do...
Fortunately, you're not one of those.
64-bit computing is not a clear win in and of iteself. If you're merely doing 32-bit calculations then odds are a true 64-bit CPU will be slower, because to do the same work you have to move twice as much data to do it -- you have to fetch a 64-bit operation instead of a 32-bit one, and ditto for data. Presuming that the actual operation takes the exact same amount of time per bit then your 64-bit CPU would be half the speed of the 32-bit CPU because it has to do twice as much work for the exact same result.
Of course, that's the simplistic case and ignores the actual case at hand. AMD's x86-64 is not a pure 64-bit CPU because it doesn't need to be. The x86 ISA is ungodly ugly (which is why nobody implements it anymore -- it may look like x86 ISA on the surface, but there isn't a modern CPU that actually implements the x86 ISA in the CPU core) and x86-64 operators are only ~10-15% longer than traditional x86 operators on average. So your operator length didn't double, and you don't need to double your instruction or combined cache just to maintain parity with old CPUs. Additionally, the current x86-64 spec only implements 48-bit addressing, which should be more than adequate for about a decade or so, so address fetches only increase in size by 50%, not 100%. Still an increase, but one that's fairly acceptable and it's a vast improvement for anytime you have to address anything >4GB in size (which is increasinly common, particularly for databases). On top of that, x86-64 adds 4 general purpose registers, which doubles or more the numper of GPRs available (the "or more" bit depends on the operation you're performing, since some of the GPR's in x86 aren't entirely GP). Yes, all modern systems have register renaming. Doesn't help much when you still only have a handful of registers available to a single process and it has to deal with only those -- the assembly code cannot know about the virtual registers, otherwise they wouldn't be virtual!
As far as the data goes, you don't have to perform 64-bit operations on all the data, nor does all of the data have to be 64-bits wide. Clearly how much impact this has will vary from program to program, but unless you're doing a bunch of operations on long long's (64-bit integers) then you probably won't see much performance difference in raw computing speed. In fact, because of the slightly larger operator size and the increased address size you're more likely to see a performance decrease, albeit a slight one.
I wonder if or how Apple Computer, Inc. will modify its marketing efforts. Will it continue to ignore AMD like they did with G4 ads, neglecting the fact that the "megahertz myth" had existed for years in the PC world in the competition between the Athlon and Pentium processors? Which led to numerous Mac users enlightening us lowly PC peons about how processor clock alone does not determine processor performance, a fact which many of us had been aware of long before the release of the Motorola G4.
It is true that the G5 was the first 64bit desktop computer processor. Now there is a second. Apple should show some G5 vs. Athlon 64 benchmarks, which should be a much more competitive comparison price-performance wise than one dealing with G5's and Xeons. And much more realistic, with both catering to (roughly) the same market.
Ha! good article my ass.
The anandtech article runs a measly 18 pages, while tom's runs 53. So it is clear that the THG article is 194% better than the anandtech one (see fig.1).What's more, in our second test, "pretty pictures on the first page of the article" the beleaguered news site falls even further behind. While THG has 4 pictures on the first page, including one of the athlon XP (oh shiny!) anandtech has none. This could be due to a browser incompatibility or a hyper-active web-filter but we couldn't be bothered to check. (see fig.2)As we can see, the THG article has !DIVISION_BY_ZERO! times the images of the anandech one, and so it must be much better.
[I am quite surprised that this post passes the lameness filter, considering the amount of ugly ASCII art. The fact that
this page you will see the following stupid comment...
Two dumb things about this...
1. UT2003 is made by Epic
2. UT2003 was a premier product that AMD was showing off as a 64bit application running under SUSE linux on the Opteron when it was released.
Two big mistakes