AMD Gains In the TOP500 List

MojoKid writes "AMD recently announced its share of the TOP500 supercomputer list has grown 15 percent in the past six months. The company credits industry trends, upgrade paths, and competitive pricing for the increase. Of the 68 Opteron-based systems on the list, more than half of them use the Opteron 6100 series processors. The inflection point was marked by AMD's launch of their Magny-Cours architecture more than a year ago and includes the twelve-core Opteron 6180 SE at 2.5GHz at one end and two low-power parts at the other. Magny-Cours adoption is important. Companies typically don't upgrade HPC clusters with new CPUs, but AMD is billing their next-gen Interlagos architecture as a drop-in option for Magny-Cours. As such, it'll offer up to 2x the cores as well as equal-to or faster clock speeds."

Re:Congratulations

[the linux geek]

It's not standard SPARC. The VIIIfx's commercial-workload performance would probably be pretty bad - the cores themselves are more or less identical to the existing VII cores, which have less than impressive performance. The VIIIfx derives its HPC performance, which is admittedly good, from some extensions (called HPC-ACE) that are not part of the normal SPARC instruction set. In a lot of ways, the VIIIfx is closer to a vector processor than a conventional SPARC chip. This isn't inherently a bad thing, but it is certainly not a general-purpose processor.

My Company Contributed to This

[friedmud]

The supercomputer I use daily is one of these new AMD based ones in the TOP500. It is a sweet machine. My software (custom engineering simulation written in C++) scales perfectly on it all the way out to over 10,000 cores.

The memory architecture is really excellent as well. With our old Intel based cluster we wouldn't load up every core on the node because of memory contention. But hyper-transport with NUMA completely negates the need to do that. We routinely fully load the nodes on the new machine without any trouble at all.

If AMD keeps it up they are going to find a lot of business in the high-end computing segment.

Re:So?

[MacTO]

Well, it is of interest to people who are interested in supercomputers.

People who develop software for those beasts like to know how things are changing. They may not need to know the intimate details since compilers and libraries will handle most of that, but they may want to throw together a small cluster to test emerging technologies. (This is particularly true in recent years since small clusters based upon AMD/Intel CPUs and AMD/Nvidia GPUs are within reach of individuals.)

Stockholders though couldn't care less. The number of units is too small and the prestige counts for nothing unless it translates into sales in other markets.

Re:some proof would be nice

[godrik]

"Any proof of these claims of compiler tampering?"

This is a well known issue with the intel compiler which has been fixed since. The story is told on wikipedia in the criticism section of http://en.wikipedia.org/wiki/Intel_C%2B%2B_Compiler [wikipedia.org]

The problem is so well known, that people wrote software to patch the code produced by the intel compiler to make it work properly on AMD processors such as http://code.google.com/p/patch-authenticamd/ [google.com]

"So why would you be using an intel compiler on AMD cpus?"

One of the interest in using the x86 instruction set is to be binary compatible so that you can use the code generated by any compiler. The intel compiler is a very good compiler, why not use it ? VIA also produces x86 processors you can use the binaries generated by the intel compiler on it. These technologies are designed to be compatible.

"Does AMD not write one?"

AMD contributes to http://en.wikipedia.org/wiki/Open64 [wikipedia.org] and to GCC.

"Your third paragraph reads like an advertisement,"

I agree on that one.

Re:I want to like AMD.

[Ecuador]

Hmm, you make a couple of very bad points.
1) The "MUCH higher failure rate for motherboards" is something I have never heard before. Especially when you go on saying "at the same price point as Intel" - are you still referring to motherboards, it is very hard to find Intel motherboards as cheap as AMD. Anyway, I have experience with hundreds of systems both Intel and AMD based over the years and I can't agree there is any sort of significant failure rate on motherboards of any of the two (although I have seen many integrated ethernet controllers go bad). With one exception. Around 2003-2004 a lab bought a dozen Dell Precision slim desktops with a Prescott. When I saw them I told the people who had ordered them that I found it suicidal to put 3.2GHz P4s (I don't remember if they were Prescott or Northwood) in such small enclosures. Sure enough, about 1.5 year later half of them had blown their motherboards, I don't know how it went from there.
2) Your basic argument is that regardless of how much money you throw on AMD, you can't get the performance of Intel, which is, well, moot as AMD unfortunately (for consumers) is not competitive in the high-end. Then you go on comparing an i5 750 which is TWICE the price of the Phenom 955 (newegg: $214 vs $113 - free $15 gift card), has much more expensive motherboards and you pair it with 3 times the RAM. Yet, *surprisingly*, the i5 is faster. Gee, who would have guessed? AMD still is price-competitive, at the price points they cover there is nothing you can get from Intel that has the same performance (esp. if you include motherboard price).

Furthermore, I would like to add that for some of us that run custom 64bit software, AMD still seems to hold strong. Example: Last year I built a Phenom 955 based system which went for under $1000, even if it had the highest quality components (best mobo with USB3, eSATA, my favorite Antec case & PSU etc). I chose an AMD on an otherwise not budget system, since it would serve mainly as a HTPC. Half a year later I bought a $4000 Mac Pro with a 3.2GHz Bloomfield quad-core Xeon. Guess my surprise when most of my own software (most doing string processing in C and Perl) are about 10% faster on my AMD-based HTPC!!! The only way to get more performance out of the several times more expensive Xeon is to manage to get over 4 concurrent threads running so I can get some benefit from HT! Not to mention that for a that much money the Mac Pro isn't even giving me USB3 or esata, which is absurd... but I digress... the point is that AMD machine which was not chosen for its high-end computation power, still holds strong against some of Intel's finest, even if more common workloads show a big preference to Intel.

In the end, I hope AMD gets back in the game. I always buy what is the best (or best value) at any time, and, historically, AMD has been my choice more often than not, but the only reason we have things like Sandy Bridge coming out of Intel right now is because AMD is pushing them. In fact, if Intel's big pockets had not prevented AMD from dominating the market like they were dominating in performance during the 2000-2005 era, we would have a much stronger AMD now and more competitive products for us consumers.