Slashdot Mirror


AMD Back in the Black

XaXXon writes "CNN reports that AMD had a profitable quarter for the first time in over two years. According to the story this is mostly because of their 64-bit line of chips (both Opterons and Athlon-64). AMD has forced both HP and Intel to change long-standing plans of only supporting Itanium, with HP coming out with Opteron-based systems and Intel releasing chips mimicking the 32/64-bit behaviour of the Opteron. According to the story, 64-bit processors are better than 32-bit ones because 32-bit processors 'can't take advantage of more than 4 megabytes (sic) of memory at a time.'"

37 of 359 comments (clear)

  1. Intel, 32x64? by arivanov · · Score: 4, Informative

    As far as I recall, Intel has not released anything yet. They put something on the roadmap, but they are still 100% behind Itanic. They released an improved 32bit emulation environment for the latter though

    --
    Baker's Law: Misery no longer loves company. Nowadays it insists on it
    http://www.sigsegv.cx/
    1. Re:Intel, 32x64? by sbennett · · Score: 5, Informative

      See this. Of course, there were the standard rumours going around before Prescott's launch that it was going to have a 64-bit layer, but that didn't happen.

      What I find interesting is that Intel said before Opteron's launch that they weren't going to make any form of 64-bit x86 processor, and now it's on the roadmap.

      Earlier this week, Intel's President and COO, Paul Otellini, confirmed in a web-cast interview that a move into the 64-bit desktop market was certain, but that the company would nevertheless wait for the arrival of operating system and application support. "You can be fairly confident that when there is software from an application and operating system standpoint, we'll be there," he said.

      You mean once the OS and application developers have started using AMD's 64-bit extensions, Intel will come up with something to compete?

  2. Why 64-bit is better by Decaff · · Score: 2, Informative

    64-bit processors are better than 32-bit ones because 32-bit processors 'can't take advantage of more than 4 megabytes (sic) of memory at a time'.

    Well, yes, but the real reason that 64-bit is better is that software should be able to move data around more quickly, typically twice as fast as 32-bit given a well-designed data bus external to the chip.

    1. Re:Why 64-bit is better by pesc · · Score: 4, Informative

      the real reason that 64-bit is better is that software should be able to move data around more quickly, typically twice as fast as 32-bit given a well-designed data bus external to the chip.

      No.

      You can move data around fast if you have a good memory architecture. A wide data bus to external memory. And a bus clocked at high speed. And larger caches.

      You can have all of that with both 32-bit and 64-bit processors. The 64-bittness doesn't help here. If everything else is equal (in the memory architecture), I would expect the 64-bit processor to lose slightly since it has wider pointers. That puts more pressure on the caches and uses more memory bandwidth.

      64 bit processors are good because they can easily adress more than 4GB virtual memory.

      --

      )9TSS
    2. Re:Why 64-bit is better by Anonymous Coward · · Score: 1, Informative

      Well, yes, but the real reason that 64-bit is better is that software should be able to move data around more quickly, typically twice as fast as 32-bit given a well-designed data bus external to the chip.



      No, as such there is no guarantee that 64-bit means a 64-bit data bus (e.g. Amiga had 16 bit data bus but 32-bit (well 24-bit on A500) address space). It means the amount of address space you can offset using one segment register. It's really just the same segment:offset pair as with the "640 kB" crowd, it's just that the offset is so much bigger nowadays: 32-bit addresses 4 GB and 64-bit a lot more.



      Also, the 64-bitness implies pointers are double size, 64-bit. So moving a pointer can be just as fast versus the 32-bit chip even though you have a 64-bit bus. But I do agree that in principle you have a possibility of doing more work in one cycle (e.g. copying strings), and the speed increase will also work out in practice.


  3. 4gigs of ram by phreak03 · · Score: 4, Informative

    you can adress more than 4 gigs of ram with a 32bit prossessor You just need a cludge (kinda expensive/slow) but itspossible speaking of lots of ram, anyone seen those Ram Harddrives they had at CES a couple years ago

    --
    come comment on the madness at http://slashdot.org/~phreak03/journal/
  4. Re:Profitable by betelgeuse-4 · · Score: 5, Informative

    When I went to nanotech lab open day, one of the speakers said that 98%-99% of the chips on each wafer must work for the CPU company to make a profit.

  5. AMD HEAT PROBLEM by Anonymous Coward · · Score: 1, Informative

    The heating problem with AMD processors is a BIG MYTH! It' is simple not TRUE. I can attest to this.

    3 of my 4 computers at home, run on AMD processors. My File Server runs on an AMD K6-2+ 500Mhz and Win2000 Pro, and has never flickered. Never crashed. Never hot. After 4yrs of faithful service. I keep it on most of the time... all day, all night...

    I just retired my Original AMD Athlon 800 slot A workstation. I bought this when they first came out... and believe me, it is still good to go. I has never failed me... for the last 4yrs...

    My next box will definately be an AMD OPTERON. If i'm paying for a computer, I like to know that I am getting the most performance for my money... and that the product is simply RIGID and VERY STURDY... and that is AMD.

    You can't go wrong with AMD.

    1. Re:AMD HEAT PROBLEM by rale,+the · · Score: 3, Informative

      I just finished a game of UT2K4 on my Athlon64 3000 (2000mhz, currently overclocked to 2150mhz). Processor temp reads a cool 34.6'C - and thats air-cooled. Compare that to the new Prescott P4's that are setting records for hottest running cpu's... The Athlon64 is an amazing piece of hardware.

  6. Re:hmm. by Anonymous Coward · · Score: 1, Informative

    No, it should be (for newer Pentiums at least) be 64GB.

  7. Re:Does AMD have anything to compete with Centrino by phusnikn · · Score: 4, Informative

    Humm I have an Athlon 64 mobility in my emachine and it rocks... I get about 3 hours of juice 2 1/2 w/wifi and this thing flys.

    --
    - I came I saw I Conquered
  8. Re:32, 64,... by moro_666 · · Score: 2, Informative

    check out the playstation2 from sony, there you have the 128bit cpu, wonder what does the pc market take so long
    here are the ps2 specs (a bit long but still) :

    CPU : 128-bit CPU
    System Clock Frequency: 294.912 MHz
    Cache Memory : Instruction: 16KB, Data: 8KB + 16 K(ScrP)
    Main Memory : Direct Rambus (Direct RDRAM)
    Memory Size : 32MB
    Memory Bus Bandwidth : 3.2GB per second
    Co-processor : FPU (Floating Point Unit) Floating Point Multiply Accumulator x 1 Floating Point Divider x 1
    Vector Units : VU0 and VU1 Floating Point Multiply Accumulator x 9 Floating Point Divider x 3 Floating Point Performance : 6.2 GFLOPS 3D CG Geometric Transformation: 66 million Polygons per Second Compressed Image Decoder : MPEG2
    GRAPHICS- Clock Frequency : 147.456MHz Embedded DRAM : 4MB DRAM Bus Bandwidth : 48GB per second DRAM Bus Width : 2,560 bits Pixel Configuration : RGB:Alpha:Z Buffer (24:8:32) Polygon Drawing Rate: 75 million Polygons per second Screen Resolution : Variable from 256 x 224 to 1280 x 1024

    now go and compare it to your pc and get stunned

    --

    I'd tell you the chances of this story being a dupe, but you wouldn't like it.
  9. The reason you don't want socket 940 by ColourlessGreenIdeas · · Score: 5, Informative

    Socket 940 arranges the pins so that it's easy to lay out multiprocessor systems with a 6 layer motherboard (expensive, but you'll want it in a server anyway for reliability reasons). Sockey 939 (real soon now) will work with 4-layer motherboards and so will result in cheaper systems. Both the Athalon 64 and Athalon FX will soon be socket 939, differentiated by the ammount of cache. Opteron will remain as it is, as otherwise your 4 and 8 way boxes won't work. Given that Opteron 8xx is absurdly cheap compared to any other 64 bit 8-way server, I can't see why AMD would want to lower prices.

    --
    In soviet russia stale jokes recycle you!
  10. Re:32, 64,... by Anonymous Coward · · Score: 3, Informative

    The 128 bits there are referring to the size of the data bus and registers, not the address bus. With only 32MB of memory, the PS2 doesn't need more than 25 bits to address it (it does however use a 32 bit address bus.)

    So really, it is a 32bit/128bit hybrid.

  11. No. by Anonymous Coward · · Score: 1, Informative

    Irony, as in an "incongruity between the actual result of a sequence of events and the normal or expected result"? I see no irony in that all.

    As far as I know, this claim is premature as well. Intel is clearly preparing itself to respond to 64 bit x86 when it feels compelled to but that hasn't happened yet. If and when it does, it will not be "ironic".

  12. Re:Profitable by iezhy · · Score: 1, Informative

    IMHO, these figures are a bit bloated According to this article in Toms hardware, prodution yield is about 30%, it it expected to rise up to 60% after two years of production CPU's are just too complicated to be produced with yield of 98%-99%. Maybe this spokesman was speaking about some other, simplier in design, chips?

  13. A Centrino system is nothing special... by cnelzie · · Score: 3, Informative

    ...all you need to slap 'Centrino' onto a laptop is the following...

    A Pentium IV Mobility Processor

    A Particular Intel Mainboard Chipset

    Intel's WiFi Internal Card

    I also believe that it needs a certain Graphics processor, also from Intel.

    The 'Centrino' label is nothing spectacular. It is just another marketing line that 'creates' a new Intel Line without really engineering a whole new line. The whole 'Centrino' line is a marketing thing to get people excited about mobile computing and is designed to get people out and buying laptop computers. It gives people a sense of having 'teh' best laptop, even if they really don't have the best laptop.

    Really, which would you rather have...

    An HP Laptop with a Mobil Pentium IV, Wireless Access and a 3D Graphics Chip?

    or...

    An HP Laptop Equipped with Centrino Technology?

    They are both basically the same thing, one just has a shorter 'catchy' name attached to it, nothing more, nothing less.

    --
    If you ignore the other uses of a tool, does that make the tool less useful, or you less useful?
  14. No, actually it should be 4 gibibytes... by blorg · · Score: 2, Informative
    shouldn't that be 4 gigabyte ;)

    ...Seriously, I wasn't paying attention and until I saw this post thought that the SI vs IEC prefix thing was the reason for the (sic) in the story. Talk about missing the wood for the trees ;-)

    (-1, Pedantic)

  15. Do the math... by sultanoslack · · Score: 3, Informative

    2^32 bit = 4294967296 bytes of address space

    Converting to gigabytes...

    4294967296 / 1024 = 4194304 (kb)
    419304 / 1024 = 4096 (mb)
    4096 / 1024 = 4 (gb)

    Of course there's a much easier way of doing that by figuring out that 1024 = 2^10, so you could just do:

    2^32 / 2^10 / 2^10 / 2^10 = 2^(32 - 30) = 2^2 = 4

    You can't address more than 4 GB of virtual memory with a 32 bit address. So regardless of how much memory you can afford that means that you can't have more than 4 GB of physical memory plus swap. Even then you typically allocate at least 1 GB of address space to the kernel leaving you with 3 GB of addressable space for applications. Now add up your swap and physical memory and you realize that we're getting pretty close to that limit on newer desktops.

    1. Re:Do the math... by Dr.+Evil · · Score: 3, Informative

      Sort-of. There are four more addressing lines giving you up to 64GB, internally, the kernel can address up to 64TB virtual memory with segment/offset stuff, and of course the 64GB physical memory.

      It's similar to the 8088/8086 with a 16 bit cpu, and 1MB of addressable RAM.

      Time to dust off the far pointers!

      http://www.prism.gatech.edu/~gte213x/LinuxMM/rpt.h tml

  16. Re:32, 64,... by pesc · · Score: 4, Informative

    It really isn't a FULL 64 bit implementation. In it's current incarnation it supports 40 bit physical and 48 bit virtual address spaces, as I recall. Even the Itanium has only a 44 bit address bus.

    Please don't propagate this kind of FUD.

    The ISA (Instruction Set Architecture) is fully 64 bits. The pointers really are 64 bits wide. The programs you compile now will be able to fully use a 64-bit wide virtual and physical (will we ever see one?) memory architecture.

    This is similar to nearly all previous 64 bit architectures such as Alpha and Sparc (and maybe Power and HP-PA and MIPS?). Most of the actual machines used don't really have 64 bit physical adresses.

    You have to distinguish between a ISA and a physical implementation of it. Most motherboards can't host more than a couple of GB memory anyway. But the ISA of the processor is still a true 64 bit architecture.

    --

    )9TSS
  17. Re:Go, Go AMD by Short+Circuit · · Score: 2, Informative

    The whole stigma about "equivalent performance" is really unwarranted. Cyrix used to name their processors things like "P-100" or "P-120" to rate them as equivalent with the Pentium 100MHz or Pentium 120MHz. And they did perform to those standards.

    In a logical sense, there shouldn't be any problem with AMD using numbers like "3200+" ...Of course, nobody ever said the Megahertz Myth was logical. It only seems to be.

  18. AMD Athlon Processor Build & Installation Guid by Futurepower(R) · · Score: 5, Informative


    Haven't seen any problem with AMD processors. It's necessary to follow the Cooling Guidelines, of course.

    Make sure you have a good power supply. We use KingWin 350 Watt supplies that have two fans. (Ignore the language, "Extreme Series". That's there just to appeal to gamers, who expect every product to include some reference to violence or games. There is nothing extreme about them, and they are reasonably priced.)

    Note that power supply manufacturers sell power supplies that have 100 Watts more rated power for sometimes close to twice the price. That's to take advantage of the "more is better" people.

  19. Re:32, 64,... by dreamchaser · · Score: 2, Informative

    How is it FUD? I pointed out that neither the Athlon 64 NOR Itanium is a FULL 64 bit implementation. Internally yes. ISA wise, yes. Address bus wise, no.

    Stop the knee jerk reactions. You sound like a zealot :)

  20. Re:Profitable by Anonymous Coward · · Score: 4, Informative

    It depends on the chip and the market. Production yields for ARM CPUs would often be at 95%, a level undreamable by x86 chips.

  21. No - it's the physical memory that's key. by Anonymous Coward · · Score: 2, Informative

    64 bit processors are good because they can easily adress more than 4GB virtual memory.

    NO!

    The bottleneck on all modern [isolated, not networked] computer systems, which dwarfs all other bottlenecks, is precisely virtual memory. Calls to the hardrive are many, many orders of magnitude slower than calls to any other system.

    Now while it's generally true that you can't have more than 2^32 bytes of total [physical + virtual] memory on a 32-bit machine, 64-bit machines are faster than 32-bit machines precisely because they allow for more than 4GB of true, physical memory.

    Calls to virtual memory are so slow that you can practically beat them by hand - if, for instance, you have a big database of phone numbers and addresses, so big that it bleeds over into virtual memory, then you can just about find a phone number by hand from The Real Yellow Pages themselves faster than your computer can retrieve it for you from virtual memory.

    A 64-bit platform with less than or equal to 4GB of physical memory is utterly worthless: As you yourself have pointed out, it's almost certainly slower than an equivalent 32-bit system.

  22. 'sic' Latin for 'thus' - indicates error in quote by blorg · · Score: 4, Informative

    Dictionary.com. It is used when quoting, to indicate that the transcriber has faithfully reproduced a possible mistake in the source. This is because it is considered bad form to modify a quote, at least without indication through square parantheses, which are generally used for explanatory additions due to loss of context, not corrections. And if 'sic' wasn't put in, it would likely look like an error on the transcriber's part. It's certainly not a /. thing ;-)

  23. Re:AMD have been better than Intel for some time.. by grondu · · Score: 4, Informative

    Yeah, that Prescott is a cool running chip.

    --

    I'm the urban spaceman babe, but here comes the twist... I don't exist

  24. Old news! by CTho9305 · · Score: 2, Informative

    This was announced on January 20th.

  25. Re:AMD have been better than Intel for some time.. by Glock27 · · Score: 5, Informative
    They don't have a bigger marketshare because even though the chips perform well, their construction hasn't (in the past) been up to that of Intel. Take, for example, the cooling required for AMD chips. Compare it to that of their pentium equivalents. When said cooling falls off (or stops working) - the pentiums don't burst into flames. That's the difference - higher manufacturing quality.

    Modded +5 Insightful? Now that shows the weakness of the Slashdot moderation system...

    Athlon, Athlon 64 and Opteron all have thermal protection, just like the P4s...and have had it for some time.

    Further, current P4s dissipate more power than the AMD solutions, due to high clockspeeds that don't equate to better performance except for a slight edge in multimedia codec performance.

    In short, at this point AMD is flat out better - and a much better deal to boot. You can pick up an Athlon 64 3000+ for about $210...that's a steal!

    --
    Galileo: "The Earth revolves around the Sun!"
    Score: -1 100% Flamebait
  26. Re:Go, Go AMD by Zak3056 · · Score: 4, Informative

    AMD won't have won until Intel starts rating its processors in "equivalent Athlon64 performance". ;)

    I'm assuming you're referring to AMD's "Performance Rating." If you are, you might be interested to know that AMD compares their CPUs to a 1Ghz Duron, and NOT any sort of intel chip.

    PR3200+ would be 3.2x faster than a 1Ghz Duron.

    --
    What part of "shall not be infringed" is so hard to understand?
  27. Re:this isn't exactly correct.... by Slugworth01 · · Score: 5, Informative
    Neither statement is exactly correct. The economics of semiconductor manufacturing are pretty complex. You typically have a certain set of variables to work with. You can invest in line yield, process quality, new processes, automation, capacity, marketing, new device design, retooling, and any number of other areas. You can build cheaper, less complex fabs, build in locations with cheaper labor rates or lower startup costs. You can outsource some or all your manufacturing to a foundry who can make your designs for a contracted price.

    AMD has an approach that says they will "build smarter" than their competition. Their flagship fabs (Fab 30 in Dresden, for example) are highly automated with very tight process control, ensuring the right work gets done at the right time. The focus is on equipment utilization; reduction of tool idle time. Further, they focus on minimizing the number of non-product wafers in the line, which take tool time but don't directly produce any chips that can be sold. The management of all this is done through software.

    They also have to focus on fab uptime ... since they don't necessarily have the back up manufacturing capability to allow them to recover if their fab is down. For example, AMD makes about two-thirds their revenue from processor sales according to a recent 10-Q filing. Most recent quarter for which there is data (for the period ending 12/28/2003) shows $1,205M in quarterly revenue. You can estimate around $800M in revenue from their processor lines. Fab 30 make nearly all their processors. If Fab 30 were to go down for one hour, that's one hour in the 730 hours in a quarter that they can't make chips. If they have demand that is greater than or equal to capacity, and they're running at full capacity, they would loose roughly $1M due to potential finished goods that could not be made. A cost of $1M per hour of fab down time is pretty typical in the market where AMD competes and for fabs that compare to Fab 30.

    A single tool going down is a problem. The entire fab going down is a huge problem. Things that can bring an entire fab down include utilities (electricity, water, gasses, etc.) contamination of facility-wide services like vacuum line, DI water, and various gasses, labor strikes, natural disasters, fires, and plant-wide software.

    When you rely on software to manage your manufacturing to the degree that AMD and other high-end semiconductor manufacturers do, you tend to pay a lot of attention to the software.

  28. Oh no. by Carl+T · · Score: 3, Informative
    Virtual memory is not the same thing as swapped out memory.
    There are a couple of points here:
    • Even a 32-bit machine may have more than 4 GB of physical RAM, just as a 16-bit machine may have more than 64 kB. It's just that it cannot be mapped into a single block of virtual memory, so without ugly workarounds there's no way a process can address more than 4 GB.
    • It's not uncommon to (for various reasons) allocate more memory than needed, and never touch part of it. These allocations don't consume physical memory, but they dos count towards the 4 GB virtual memory limit for the process. Since the kernel must be able to produce the memory when asked for it, the amount of available swap space may decrease, but that doesn't mean that anything is actually written to the swap.
    --

    This signature is not in the public domain.
  29. Re:Profitable (WTF?!?!?!) by hackstraw · · Score: 3, Informative

    I don't know what bothers me more. People stating their uninformed opinion as fact, or people actually buying it and modding it up.

    They make their profit on Xeons, where until recently they have had no competition.

    Huh? Intel is the largest manufacturere of CPUs in the world. They have had a net income of about $1b per quarter for the last 4 quarters, they have $16b in the bank. Thier stock has remained pretty stable (aside from the .bomb inflation), etc.

    Being that were I work (a university) and there are THOUSANDS of p3, p4, etc chips and way less than 100 zeons, if they are making all of their profits on those 100 chips that only cost a few dollars more than the other thousands of chips.... Whatever, obviously your wrong.

    Take a look at what they're doing - they're going after Xeon - and trying to get a piece of the profit in a market that's consistent with their fab capacity.

    They are going after the HPC market, because that is the only market for cheap 64bit CPUs. You don't need a 1.457THz 128bit processor to check passwords on your domain. Sorry all of you Windows admins, being a domain controller is not that big of a deal.

    Crunching numbers across 20 processors for 5 days at a time is a big deal. Being able to do that in 2.5 days is a real big deal. Not being able to do that because you can't address more than 4Gigs of memory at a time is a show stopper.

    Think before you mod people.

  30. Re:AMD have been better than Intel for some time.. by Loki_1929 · · Score: 2, Informative

    "Take, for example, the cooling required for AMD chips. Compare it to that of their pentium equivalents. When said cooling falls off (or stops working) - the pentiums don't burst into flames."

    Wow, another TomBot, I see. Listen, reading dumbed-down consumer grade articles from a propaganda rag like Tom's makes you neither smart, nor informed. First of all, the problem was NOT with the AMD CPUs, but rather with the mainboard's non-spec design. Had the manufacturer designed the board to AMD's specifications, this would not have been a problem at all. The computer would have locked up, just like the Pentium 3 did. Why does it act like a Pentium 3? Because the K7 came out about the same time the P3 did. AMD's board specs called for specific thermal protection circutry on the board itself to help protect the board and the CPU. Arguably, AMD should have put all the thermal protection circutry inside the CPU itself, but the fact remains that Tom's took a board that was not built correctly, and used it to make an example out of AMD. In journalism, the technical term for doing this is, "bullshit".

    Secondly, the chances of a heatsink falling off are virtually nil. Your statement is the equivelent of saying, "When the radiator falls off my Chevy, it still works semi ok - not like those Fords". Yeah, I sure do hate it when the radiator falls off my car. Happens what, 'bout once a week at least?

    "their construction hasn't (in the past) been up to that of Intel." .. "That's the difference - higher manufacturing quality." ... "They make cheap [quality] chips"

    This just shows your complete lack of knowledge of the CPU industry's past. Or perhaps you're actually 10-second Tom from 50 First Dates, and you've forgotten all the many, many problems and recalls Intel has had over the years. That being said, I don't remember a single recall of AMD's Athlon chips. Let's see if I can remind you of Intel's shady past, shall we? Go read this from last year. I actually did my homework before opening my mouth - as opposed to reading some sellout's online rag (Tom's).

    --
    -- "Government is the great fiction through which everybody endeavors to live at the expense of everybody else."
  31. Re:32, 64,... by Hoser+McMoose · · Score: 4, Informative

    The Playstation2 does NOT use a 128-bit CPU!!!

    The PS2 has a 32-bit CPU core with 128-bit vector units. The Pentium3 also uses a 32-bit CPU core with 128-bit vector units (SSE), as does the Apple/Motorola G4 chip (with Altivec). There has never been a 128-bit CPU used in ANY gaming console, and I'm only aware of 1 64-bit CPU ever used (Nintendo64).

    Of course, the reason for this is that going to more bits makes a CPU SLOWER! All else being equal, a 64-bit is 5-10% slower than a 32-bit CPU, and a 128-bit CPU is 10-20% slower than a 64-bit one. Since games don't need to address more than 4GB of memory, it's totally pointless to use a 64-bit CPU in a gaming console. The only other thing that a 64-bit CPU buys you is an integer range of more than 4 billion, and that's RARELY used outside of cryptopgraphy (how often do you do cryptography on your gaming console?).

    Of course, all else usually isn't equal (eg AMD64 adds 8 more general purpose registers and cleans up some cruft when compared to IA32). Also PCs often do need to address more than 4GB of memory (virtual + physical).

    PCs do not, however, need to address more than 10^19 bytes of memory, and they definitely don't need more than 10^19 integer range for much of anything, so 128-bit CPUs get you absolutely NO positives but you still would have to deal with the 10-20% performance loss.

  32. Re:Profitable by Loki_1929 · · Score: 3, Informative

    "I still go there for the forums, as there are a few people there who have good insight."

    I think you'd enjoy the forums at Ace's a lot more. The folks tend to be more intelligent, less 'fanboyish', and come out with insights you won't find anywhere else.

    --
    -- "Government is the great fiction through which everybody endeavors to live at the expense of everybody else."