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.
when will we see some serious APPS that utilize this technology?? why would joe user go buy one? to check their mail?
although not intended to be a troll, its looking that way....
if the OS, AND the Apps run 64bit - i'll buy one...till then, i'll stick with my original thunderbird, 1.4ghz.
We're like rats, in some experiment! -- George Costanza
I'll wait until they actually come out with applications that use the 64-bit extensions to the x86 instruction set. Doesn't seem like its worth it to pay big bucks and buy this for 32-bit applications
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).
And BTW windows released XP 64bit Beta1 today.My Aurora : http://www.youtube.com/watch?v=o91ZsGwJYyg
FB : https://www.facebook.com/TanveersPhotography
First, we still don't have a mass market consumer OS for native x86-64, and even when Windows XP for x86-64 does come out (the word from the betas is that it's very very good and solid), we still need to wait for x86-64 compatible drivers to be developed and released by the various manufacturers, and it would be no small feat to even have a small core sampling of drivers available by say, summer 2004. Personally, I'm hoping that Nforce3 and ATI Catalyst drivers will be ready very early on.
Mad props to AMD, but they're not out of the woods yet on this release.
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!
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!!
A physical address space that can support systems with up to one terabyte of installed RAM, shattering the 4 gigabyte RAM barrier present on all current x86 implementations.
If you implement x86 with PAE then you get 8gb.
It's only 4gb if you exclude dirty hacks - but if you did that then you would have to rule out x86 in it's entirety.
Beep beep.
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.
A troll but I will bite. Did you happen to read that it was not running any applications optimized for it? The pentium 4 is all about just tossing in more cache and higher clock speeds where as the AMD chips are about efficiency. A 2.2ghz chip directly compeating with a 3.2ghz chip with a shat load of L3 cache shows that it is mearly just a smoke screen. Not only that but the 3.2ghz Pentium 4 costs a bundle more. What about the lower memory access times? I'd prefer lower memory access times.
Although the numbers look impressive, I personally would wait till their are more 64 bit applications in the market. If you are a gamer there would be modest increases in performance but really waiting a few more months will not hurt if you are more interested in value.
I love the fact that AMD is competing, this bodes well for all computer users. A technology war will definitely keep prices down. In the same sense, I am hoping that Intel comes out with a "decent" 64 bit chip. Not that I am fond of Intel, I prefer AMD but still the fact remains that whenever their is conflict we see the most marked increases in technology.
Tom's hardware has got another article, called The Intel v. AMD Performance War: You Lose , about the more cynical, money-making sides of the launch. Perhaps it's a bit conspiratory, but certainly worth a read, as it raises many valid points.
All of my OS's software can make use of that chip. I'm sorry that yours cannot.
Still, even when running 32-bit code, the fact that the Athlon 64 can normally do it as fast (if not faster) than the "XTREME!!!" P4 really says something. The chip runs at less than 70% of the Intel chip's clockspeed... Take 64-bit into consideration, and how much greater is this margin? It's no contest.
I watched the live webcast and they said that the intial wave of adopters would be able to register their processor and receive free games.
The microsoft rep also said that there is a site where folks can download the WinXP 64bit BETA.
Where are these things? If I could download WinXP64 (Even in BETA) and get free 64-bit games, I'd be willing to give it a whirl since I need an excuse to upgrade my PC anyway.
[move
fortunately for SUNW shareholders, Sun released some rather good news yesterday about a breakthrough they had in CPU interconnects. So, the ultrasparc3/4 might be devalued, but Sun was about to devalue them with their own stuff anyway. In addition, the ultraspac3/4 are still very solid chips, and its easier to have an E15k with zillions of them than to try to figure out how to get zillions of p4's to operate in the same space.
Check out the new info posted about sun's interconnect tech here (free reg, blah blah). With the new tech, processors and/or memory can be directly connected to each other.
I still wish my wife had let me buy AMD a couple months ago when it was in the 5's. They're losing money fast, but...since the stock is up 140% from its price in late June, I guess investors still have hopes for them...
The poster of this troll included a link to AMD's website. According to AMD, they have no competition!? What about Sparc and Apple and all of the reviews showing Intel EE beating the majority of their benchmarks? Oh, and AMD's website says they have the largest cache...uh, not true. AMD is grasping for straws here.
r ma tion/0,,30_118_9485_9488%5E9494,00.html
http://www.amd.com/us-en/Processors/ProductInfo
Your argument that AMD is not the market leader and has to follow Intel's lead has been true in the past, but this particular situation is a bit different. Intel has sunk all of their resources into the Itanium project for 64-bit computing, and although the rumored Yamhill project may still yet come to pass now that Athlon 64's performance leadership is unquestionable, I haven't heard a single mention of anything other than the EPIC architecture for Intel, while AMD has been push x86-64 for years now and letting compiler writers and programmers become used to the instruction set. It takes a good amount of time for programmers to utilize a new instruction set effectively after it comes out (look at MMX when it was first introduced), and even if Intel reveals Yamhill extensions, if they're not x86-64 compatible, it's going to take a while for non-Intel programmers to catch up.
Personally, if Intel does reveal Yamhill, it'll be all the better for the industry. More competition will just mean lower prices for us - the consumers.
I ran across this article today... apparently someone is already trying to put together a mobile system around AMD's new 64-bit offering.
My friend Boris informed me that Costco is selling one of these.
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.'
Modern processors already use massive register renaming tricks internally, so it's not as if these extra registers will be completely unused. There is an advantage to letting the compiler (as opposed to just the processor) pick registers, and in 32-bit mode, that will be lost.
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.
I agree with you in your description of Intel's business practices, and while I see several refuting posts against INTEL-64, I'd like to point out a couple things:
First, if Intel was going to launch a 32-bit compatible processor with their own 64-bit extensions, they really ought to have announced it by now, to get people to put off buying AMD's Opteron and Athlon64.
On the other hand, if Prescott was going to support AMD-64, then they really ought to have announced it by now, to bring back attention over to them. The less press AMD gets, the better. (for them.)
Their strategy could make sense, if they wer planning some sort of massive surprise. If you read the Inquirer's article, you'll notice that Intel has been denying that Prescott is 64-bit.
tasks(723) drafts(105) languages(484) examples(29106)
The Power4/Itanium/UltraSPARC advantage has always been in their scalability. They have point to point links with gobs of bandwidth to handle many parallel CPUs which are capable of handling large transaction-oriented workloads.
Now that Opteron has Hypertransport -- a highly scalable big bandwidth point to point link protocol, what exactly is the advantage of the other RISC contenders in the high end enterprise space?
A nice instruction set? Sorry, that doesn't cut it anymore. The only thing holding back x86 in the enterprise is the lack of an enterprise class OS. Linux will be dominant here in a few years thanks to large investments made by IBM.
As much as people don't like to admit it. x86 will become the dominant instruction set across all computing sectors with the exception of embedded.