WOW WOW New Intel CPU rockssssssssss - byebye AMD

[hoa nam anh]

Tôi thực sự vẫn hài lòng với AMD, "một kẻ nhỏ bé" mà làm nên đại sự mới là điều đáng nể, còn "một gã to lớn" mà làm nên đại sự mới là là chuyện bình thường???. Phải không các anh em...

[tienril]

Chờ X2 5200 và FX 62 ra đã đi rồi mới biết chứ ,AMD mà chít là Intel sẽ thành độc quyền và các bác tiêu hết luôn ,lúc đó tha hồ mà cuời nhé

bạn wên bên Mỹ cóa luật chống độc quyền rùi hả ? ~~> AMD sẽ ko bao giờ chít (cao lắm cũng chỉ là đổi chủ mùh thui) . Các bác đừng nóng vội cho AMD suy nghĩ 6 tháng nữa ....:ak:

[nguyennhu]

Chuyện CPU tương lai vượt trội CPU tốt nhất của thời hiện tại là chuyện bình thường,tui nghĩ là như vậy.Lúc P4 1.3GHz sắp ra mắt,người ta bench và so sánh với P3 1.13GHz,kết quả cũng y như bây giờ,P4 hoàn toàn vượt trôi P3.
6 tháng là 1 khoảng thời gian dài.AMD ko muốn sụt giảm thị phần và thua lỗ thì bắt buộc phải tung ra quảng cáo thế hệ CPU mới sớm hơn dự kiến thôi.

[thanhtruc02]

Trong tháng đóa AMD khỏi cần ra mới chi ! chỉ cần giảm giá mấy em X2 xuống là.... :them: hay làm ra em X2 xung 1.6G , 128K cache thui , giá > 120$ <~~ hấp hẫn ko ? :sun:

[lacdasaysua]

Tôi thực sự vẫn hài lòng với AMD, "một kẻ nhỏ bé" mà làm nên đại sự mới là điều đáng nể, còn "một gã to lớn" mà làm nên đại sự mới là là chuyện bình thường???. Phải không các anh em...

AMD là "một kẻ nhỏ bé" ^^! cách đây chừng 10-15 năm thì nó ngang ngửa Intel đấy.Từ khi intel trình diễn nền tảng Pentium pro thì AMD mới bị lép vế thôi.hãng này mà là kẻ tí hòn thì muôn đời chẳng làm được cái gi.

Tóm lại thì tùy sở thích mỗi người thôi.thích gì thì sài nấy chứ đừng nói thằng này hơn thằng kia;mệt lắm.Công nghệ nó vèo vèo vèo vèo...nhanh như gió ấy.Hôm nay thằng này làm vua ,mai thang kía soán ngôi rồi.Tui tuy ủng hộ intel nhưng về góc độ tình cảm thôi chứ mua hàng thì luôn chon cái tốt nhất :"tình cảm và công việc là 2 việc khác nhau".cái gì ngon bổ rẻ ;hiệu suất cao nhất so với số tiền mình có thể bỏ ra là buy không càn suy nghĩ nhìu .

Trên mặt trận công nghệ chỉ có một người khổng lồ đúng nghĩa thôi:IBM
:vgt::vgt::vgt::vgt::vgt::vgt::vgt::vgt::vgt:
:vgt::vgt::vgt::vgt::vgt::vgt::vgt::vgt::vgt:

[zinzin8x]

chuyện gì cũng phải từ từ.... nếu ko bằng ng ta thì cách nhanh nhất là phải theo đuôi nó thôi.....

ko còn cách nào khác.......

[hoa nam anh]

Đợi AMD ra AM2 sử dụng DDRII 1066Mz rồi sẽ biết chứ bây giờ cứ bàn cải cũng chả được kết quả gì.

[gahocseo]

Lúc nào cũng thế, mới ra 1 tí rùi đồn ầm lên, cái nào thực sự tốt thì sau cùng cũng ra mặt thôi

AMD chưa hề động đậy, nhường Intel 1 bước . Anyway cái nào tốt rẻ thì quá hay, cạnh tranh thế càng tốt :lacmong:

<<< Nxqd3051990 >>>

[quynhhoa]

.........Anyway cái nào tốt rẻ thì quá hay, cạnh tranh thế càng tốt :lacmong:

<<< Nxqd3051990 >>>

AMD hay INTEL cái nào rẻ & ngon thì chơi ............, còn cái nào không phải của mình thì đừng thổi nó lên giống như của mình mới phát mình ra rùi chê bai cái khác kỳ lém :lay: :lacmong:

[hunghk]

tui tin AMD chắc chắn sẽ có cpu đối trọng với Conroe/Woodcrest ! thế hệ này có thể xuất hiện vào nửa đầu năm 2007 với tên là K8L, với số đơn vị tính toán dấu chấm động (Floating Point) gấp 2 lần thế hệ hiện tại và hiệu suất tăng 1.5 lần ! Woodcrest có thể mạnh trong tính toán số nguyên (Int) nhưng vẫn hơi yếu trong tính toán dấu chấm động !
source : http://www.theinquirer.net/?article=29890
http://theinquirer.net/?article=30250

Sau đây là phần 1 bài trả lời phỏng vấn của Digitimes của Henri Richard (AMD executive vice president and chief officer for marketing and sales)
(sỡ dĩ tui phải copy nội dung vì sau vài ngày thông tin này không được công bố một cách public bởi Digitimes)

tay này khá tự tin trước sự xuất hiện của Conroe và cho rằng kiến trúc của Conroe là sự kết hợp chủ yếu của kiến trúc Pentium III và một phần kiến trúc NetBurst của P4, và kiến trúc K8 có khả năng mở rộng tốt và AMD vẫn thường giấu kín các kế hoạch phát triển của mình => AMD có thể đã có vũ khí bí mật để chống lại Conroe !

DigiTimes recently named two companies as International News Makers in 2005. One of those companies was Advanced Micro Devices (AMD).

After a long period of being considered the under-dog of the microprocessor world, AMD emerged, particularly with its K7 generation of processors, as a company that could provide formidable competition on price-performance. AMD didn't stop there; it made a bold move in advancing the industry to 64-bit performance, at a time when the competition (read: Intel) was preoccupied with thermal issues.

The success of the Athlon64, and with it, the elevation of the AMD Opteron processor to a key role in the server space, then followed. The important role of the HyperTransport interconnect, the on-chip integration of the memory controller, the ability of the Opteron processor to scale to multi-processing configurations, the adoption of silicon-on-insulator (SOI) fabrication technology – these are just a few of the contributing factors in AMD's ongoing re-definition of the microprocessor landscape.

DigiTimes.com spoke with Henri Richard, AMD executive vice president and chief officer for marketing and sales, when he visited Taipei earlier this month and accepted DigiTimes.com's International News Maker 2005, award.

This is Part I of a five-part interview. Part II will follow on 14 March.

Q: It's generally acknowledged that AMD has a technology lead over Intel, currently, if only for two reasons, HyperTransport and the move to AMD64, which clearly took Intel by surprise and really left it no option but to use AMD64 technology. However, later this year we expect Intel to fight back with the Merom /Conroe /Woodcrest core, which some industry analysts expect to take the performance lead. A year from now, who will be the performance leader in microprocessors for the three major segments: notebooks, desktop systems, and the server space?

A: Actually, I pride myself on what I call intellectual honesty, and it would be foolish for AMD to believe that Intel is going to suffer from a lack of execution forever. Clearly, they made the wrong decision with Itanium. They made the wrong decision with Prescott, but they're not going to continue to make mistakes all the time. Today, they don't have a good architecture; that's widely accepted and recognized. In fact, Intel themselves recognize that at some point they are going to have to move to an integrated memory controller. One of their scientists has just acknowledged that publicly.

So what I think we are seeing right now are traditional marketing tactics – if you don't have a good product, you talk about your future, and that's what they're doing. There's no doubt in my mind that on paper, their new products are going to be better than their existing products. Where I think they're rather pushing the envelope is in claiming that, without having seen any of our products, they're going to have better products than ours. I think that's pretentious, and I think what we're seeing there is the old Intel.

I think the market is becoming so complex, that claiming absolute dominance across all segments and all usage models is just impossible. So you may have an AMD product, or an Intel product, claiming the crown in a particular segment, for a particular usage, but then you start factoring in performance-per-watt, and then that changes. Then you start factoring in the overall thermal design power (TDP) of the platform, and that changes again. You move on to heavy floating-point performance, and that changes again. You go into applications that are memory-intensive, and those change again. So I think that the market is so complex, that while they've been claiming that they're going to improve their performance significantly, it's when new products are rolled out in the marketplace that we'll see how they fare. It seems logical to me that a company with their resources will, over a period of time, stop mis-executing, and we'll get better products in the market.

But frankly, they've made so many claims in the past – you know, the Netburst architecture was supposed to scale to 10GHz, and look at where we are today. Then their new-generation micro-architecture (NGMA), is, quite frankly, a quick fix on the front-side bus. I don't think that's the future of the Intel architecture. I think it's another quick fix until 2008 or later, when they're going to come out with a genuinely new architecture. So again, from a pure technology perspective, my assessment is that it's a lot of marketing – it's clever marketing, but it's not revolutionary. And calling it a new-generation microarchitecture is a little bit out of balance.

Q: Based on what you've seen of the architecture, do you want to add any further comment on just how old or even new it is?

A: Well, the general picture is of back-to-the-future. My understanding is that it's a Pentium III resurgence, mixed with some of the capability of the Pentium IV.

We've seen, at least in a couple of areas, Intel acknowledge that AMD was right. And it's important to note that finally they have x86-64 across their entire product range. And I'm happy about that because I think I can legitimately claim that if it wasn't for AMD, that wouldn't be the case. And second, I see a clearer acknowledgement that their current architectures are completely out of control when it comes to power utilization. At least there's now a focus on getting that power envelope under control. There again, I think that that's an indirect acknowledgement of AMD's leadership – leadership in thought – because we clearly drove the industry to x86-64, and we increasingly drove the industry away from ever-increasing power envelopes.

I think that's good, and, I think by the way, that's good for the industry. I'm glad they're aligning on us because I think that will help the industry as a whole to be more effective.

I saw recently a comparison of what's been disclosed of the NGMA, compared to what's been disclosed of the AMD K8 architecture, in the sense of predictive branching, buffering, pipelining and so on. And when you look at their NGMA, it looks like the K8 more than anything else. As they move away from Prescott and into their new products, it's really a mirror, a much closer mirror image of the K8 than previously, with the exception of course of the integrated memory controller.

But I think also that Intel has demonstrated to a certain degree, by concentrating their new design around one team, that they had a structural problem of development efficiency. You know, it's the old thing of you can't take nine women and put them all together to get a baby in one month. I think Intel has pursued a lot of development and lost efficiency in the R&D spend. It's noticeable because you really have a whole new generation of Intel products coming out of one single team. You start to wonder, what are the rest of the people doing?

Q: There have been reports, notably on The Inquirer website, that AMD will in fact return fire with its own new core in 2007, the K8L. One Inquirer report suggested that there will probably be several iterations of this processor in 2007, and that it will emphasize floating point (FP) performance. Can you confirm any of this?

A: Well, I acknowledge or I recognize that we are disclosing less of our future plans than people would like us to, and part of that is because of the competitive nature of the industry. It doesn't help us to give too much heads up to the competition. That said, we have a very solid architecture, one that's scaling well. It's scaling well in terms of multicores, and it's scaling even better in terms of multi-sockets. That's excellent because clearly the industry is going towards multicore designs, and although the software part of it will always trail the hardware, that move is resulting in greater parallelization of applications.

You've picked up on an 8KL, so you could say it seems as though AMD is tending to follow more of an evolutionary design path than a revolutionary one, and I think that's a correct view of where we're taking the technology in 2007. We have a good technology base, so it's easy for us to expand it, without having to re-invent the wheel, unlike Intel, which has to try to claim that the NGMA is something new.

We don't need something new, we just need to continue down the path of improving memory bandwidth through new technologies, improving speed, through faster clock rates, larger caches, and, in certain areas that are driven by customers who demand improvement, absolute performance. It's clear that we will improve both the integer and floating-point performance of our cores, independently of improvements in transistor technology, manufacturing technology and so forth.