Print 65 comment(s) - last by Sureshot324.. on May 28 at 11:59 AM

IBM's new POWER6 chip is a 64-bit, dual-core processor with 790 million transistors running at up to 4.7 GHz and 8 MB L2 cache

Cross section of a IBM POWER6, photographed using a scanning electron microscope, shows two transistors in gold
IBM claims to be launching the world's fastest chip for UNIX servers

IBM just launched the dual-core 64-bit POWER6 processor running at 4.7 GHz, which doubles the speed of the previous generation POWER5 while using nearly the same amount of electricity to run and cool it.

The POWER6 processor is a result of a five-year R&D period, is composed of 790 million transistors and is built using IBM’s 65nm process technology. IBM scientists targeted the way instructions are executed inside the chip to improve performance. For example, in the POWER6, the number of pipeline stages – the chunks of operations that must be completed in a single cycle of clock time – are kept static, but each stage is made faster, removing unnecessary work and doing more in parallel. As a result, execution time is reduced.

Earlier this year, IBM hinted that its new POWER6 architecture may hit frequencies higher than 5 GHz.

The POWER6 chip has a total cache size of 8 MB per chip – four times the POWER5 chip – to keep pace with the processor bandwidth. With 300 GB/s on tap, IBM boasts that its processor has so much bandwidth that the POWER6 chip could download the entire iTunes catalog in about 60 seconds. IBM believes that it has designed the POWER6 chip with a balanced amount of bandwidth and processing power.

“Like the victory of IBM’s Deep Blue chess-playing supercomputer 10 years ago this month, the debut of POWER6 processor-based systems proves that relentless innovation brings ‘impossible’ goals within reach,” said Bill Zeitler, senior vice president, IBM Systems and Technology Group. “The POWER6 processor forges blazing performance and energy conservation technologies into a single piece of silicon, driving unprecedented business value for our customers.”

To facilitate the lower energy demands of the new chip, the POWER6 designers separated circuits that can’t support low voltage operation onto their own power supply “rails,” allowing IBM to dramatically reduce power for the rest of the chip. IBM engineers also used a new method of chip design that enables POWER6 to operate at low voltages, allowing the same chip to be used in low power blade environments as well as large, high-performance symmetric multiprocessing machines.

In another design to reduce energy consumption and heat production, processor clocks can be dynamically turned off when there is no useful work to be done and turned back on when there are instructions to be executed. Also, the chip has configurable bandwidth, enabling customers to choose maximum performance or minimal cost.

Parts of the memory not being utilized are dynamically turned off and then turned back on when needed. In cases where an over-temperature condition is detected, the POWER6 chip can reduce the rate of instruction execution to remain within an acceptable, user-defined temperature envelope.

The chip is fast too, as a server built by IBM using the POWER6 architecture is the first ever to hold all four major benchmark speed records for business and technical performance. IBM says that its new 2- to 16-core server is multiple times faster than the HP Superdome or Itanium machines.   

The POWER6 chip is also aimed as being a midrange consolidation machine, containing special hardware and software that allows it to create many virtual servers on a single box. IBM calculates that 30 SunFire v890s can be consolidated into a single rack of the new IBM machine, saving more than $100,000 per year on energy costs.

IBM plans to introduce the POWER6 chip throughout the System p and System i server lines. The POWER6 chip in the new IBM System p 570 server is the first UNIX microprocessor able to calculate decimal floating point arithmetic in hardware. Until now, calculations involving decimal numbers with floating decimal points were done using software. The built-in decimal floating point capability gives tremendous advantage to enterprises running complex tax, financial and ERP programs.

Comments     Threshold

This article is over a month old, voting and posting comments is disabled

Power6 and C2D Benchmark comparison
By ralith on 5/22/2007 9:44:23 AM , Rating: 5
Man some people are so uptight, jeez. So C2D and Power6 won't compete in the same space. So what. They can still run the same benchmarks to see how badly the C2Ds and C2Qs get crushed by the Power6. If for no other reason than the amusement factor.

RE: Power6 and C2D Benchmark comparison
By Miggle on 5/22/2007 10:53:42 AM , Rating: 2

RE: Power6 and C2D Benchmark comparison
By Ringold on 5/22/2007 6:50:56 PM , Rating: 2
Plus, if it's the number cruncher (FP?) beast some seem to think it is, it'd be an awesome Linux F@H chip...

RE: Power6 and C2D Benchmark comparison
By InsaneScientist on 5/22/2007 10:05:39 PM , Rating: 2
F@H is mainly Floating Point Ops, yes, but number crunching generally is integer ops, which are handled by a completely different execution portion of the CPU (and usually a much narrower path.)

This page might be of some help in differentiating between the two... it's not the best, though... I can't find anything really good. :-S

By InsaneScientist on 5/24/2007 3:58:21 AM , Rating: 2
My brain was obviously on vacation this morning... I guess this is what happens when you finish your finals. :D

Anyhoo... it's the FPops specific portion of the CPU that's usually the narrower path... not the integer part like my last post implies (and I'm not entirely sure where I was going with that line of thought, either...)

RE: Power6 and C2D Benchmark comparison
By AMDfreak on 5/22/2007 11:12:00 AM , Rating: 5
Actually, they could compete in the server market. We currently have some beefy p570 boxes that we're seriously considering replacing with clustered Dells running Prescott Xeons and Linux. There's no question that Power5 and Power6 are computing monsters, but we can replace the whole solution for what it would cost us to upgrade the memory in a p570. Think I'm exaggerating? The quote we got to go to 32GB RAM would cost as much as a small house here.....

By Tsuwamono on 5/22/2007 7:04:27 PM , Rating: 2
alcatel has boards that run 40 CPUs on it... WITHOUT the chips in their BGA slots the board sells for $35 000 US roughly... Thats a board for industrial use. Believe me... your C2D or prescott rig costs are chump change

Speed over Cores
By crystal clear on 5/22/07, Rating: 0
RE: Speed over Cores
By Goty on 5/22/2007 12:10:28 PM , Rating: 2
Each individual CPU only has two cores and can only execute four threads, but you have to consider that these are meant to run in parallel with anywhere from 1-15 additional CPUs in the same system.

RE: Speed over Cores
By crystal clear on 5/23/2007 2:39:17 AM , Rating: 1
Hi !Goty, I made the above comment in a big hurry(minutes before boarding my flight).

I think the below will clear some issues-

The trend to multicore processors is clearly the future but "not all customer workloads are multithreaded yet," said McCredie, explaining why the company pushed speed over cores with Power6. The CPU supports two threads on each of its two cores.;jsessionid=ALUL0Y...


SAN JOSE, Calif. — IBM Corp. will go back to the future with its next-generation Power6 design by pushing raw speed rather than trying to pack more cores on a die.

The CPU will run at speeds between 4-5GHz with a total of 8Mbytes L2 cache and a 75Gbyte/second link to external memory.

The Power6 doubles the frequency and bandwidth of the existing Power5 without increasing its power consumption or the depth of its execution pipeline. The move lets IBM ship the chip as a mid-2007 refresh for its existing p-series server line.

"We needed to scale the whole system. When you just pack on more cores and don't scale the cache and memory bandwidth you can't really scale CPU performance as well," said Brad McCredie, a fellow in IBM's Systems and Technology Group.

The Power6 will essentially follow the pattern set by IBM with the Power4 and 5 CPUs. The Power4 was among the first computer CPUs to put two cores on a single die. The company packed two dice on a single module for high-end versions of the chip. Intel Corp. likewise plans to use multi-chip modules to pack two dual-core dice on a family of quad-core chip modules it will start introducing in November.

IBM may surpass Intel in the speed race, although it has not determined exact speeds for shipping parts yet. Intel currently ships versions of its single-core Pentium running at up to 3.8GHz, but it slows its dual-core CPUs down to 2.93GHz or less to keep power and heat in check.

Thus the big news for IBM is how it can double frequency while holding the line on power consumption and pipeline depth. New circuit designs and process technology improvements plow the way for the advances. The chip uses "new and highly complex latch and static gate circuits," said McCredie.

The processor is built in a 65-nm process using IBM's silicon-on-insulator (SOI) and strained silicon technology. IBM applied new techniques in variable gate lengths and variable threshold voltages to squeeze maximum performance per Watt at the transistor level. The chip can be fully operated at as little as 0.8V.

"That enables us to take this chip into many low-end environments" said McCredie.

In addition, IBM will link its Power CPU for the first time to an external embedded controller. The controller will monitor and adjust power and performance parameters on the CPU based on set power management policies.

IBM is now in a systems test and debug phase using the Power6 in high-end, midrange and cluster computers for its p-series servers.

(10/10/2006 12:01 AM EDT);?articleI...

RE: Speed over Cores
By psychobriggsy on 5/23/2007 9:06:34 AM , Rating: 3
"Intel currently ships versions of its single-core Pentium running at up to 3.8GHz, but it slows its dual-core CPUs down to 2.93GHz or less to keep power and heat in check."

Well done eetimes for failing to differentiate between Intel's speed-racer but low IPC Pentium 4 design, and their high-IPC but slower Core 2 architecture. Indeed Intel did sell dual-core Pentium Ds at 3.4GHz at least, they failed to mention that.

It seems from the benchmark results that POWER6 retains a large amount of IPC whilst also being extremely fast. It's by far the speediest CPU available on the market (and I'm sure POWER6 will be made in a >5GHz version in due course as well). Single thread IPC is lower than Core 2 it appears from the SPEC results (4.7GHz POWER6 ˜ 3.3GHz Core 2), but run two threads on the core and it will compare very nicely to a Core 2 core overall.

RE: Speed over Cores
By psychobriggsy on 5/23/2007 9:18:19 AM , Rating: 3
Actually from rythie's post, a 4.7 GHz POWER6 running a single thread seems to be ~= 3.5 GHz Core 2 in integer, and ~= 4.2 GHz Core 2 in floating point. That's pretty good IPC.

Add in the second thread on that core and the per-core IPC might even be higher than Core 2 in floating point, although this is purely speculative and assuming that there is an overall improvement of 20% when running the second thread (no way do I think IBM's SMP implementation is going to suck like HyperThreading).

RE: Speed over Cores
By IntelUser2000 on 5/24/2007 10:50:37 PM , Rating: 2
Actually from rythie's post, a 4.7 GHz POWER6 running a single thread seems to be ~= 3.5 GHz Core 2 in integer, and ~= 4.2 GHz Core 2 in floating point. That's pretty good IPC.

Power 6 performs like a Core Duo(Yonah) in integer except it runs at 4.7GHz. It is really impressive. I estimate Intel needs a 3.7GHz Core 2 in SpecInt2006 and 5.2GHz Core 2 in SpecFP2006 to equal the 4.7GHz Power 6. Power 6 has better performance per clock in FP than Core 2. Sure, Power 6 does have massive bandwidth advantage so if we assume the same happens for Core 2, Core 2 should gain performance advantage per clock in SpecFP2006.

Add in the second thread on that core and the per-core IPC might even be higher than Core 2 in floating point, although this is purely speculative and assuming that there is an overall improvement of 20% when running the second thread (no way do I think IBM's SMP implementation is going to suck like HyperThreading).

Actually, Intel's HT isn't bad for the amount of resources and time it took for Intel. IBM's SMT in Power 5 and Power 6 is vastly more complex. Intel's HT is probably more efficient at same die size space than the IBM's version.

RE: Speed over Cores
By crystal clear on 5/23/2007 8:32:46 AM , Rating: 1
"The transition to multicore is happening even faster than the move to 64-bit, and Windows Server 2008 is multicore-ready. Microsoft is also licensing by socket, not cores, on a chip," said Bill Laing, general manager for Microsoft's Windows Server division, told attendees here at WinHEC on May 16.

Point to note-
"Microsoft is also licensing by socket, not cores, on a chip,"

Power6 wasn't built for desktops
By UNCjigga on 5/22/2007 2:57:49 PM , Rating: 2
I don't believe this technology was ever meant to power a desktop. Since Apple announced the switch to Intel, IBM new this architecture would be for professional server/workstation use only so they designed/packaged the new chip accordingly. Also, it may crush C2E/C2Q in performance-per-watt, but might be more evenly matched in performance-per-dollar.

RE: Power6 wasn't built for desktops
By minasbeede on 5/22/2007 5:02:47 PM , Rating: 2
I don't know. We (former employer - I'm retired) purchased two of the original Power processor systems. One was deskside, one was desktop. At that time we got the most bang for the buck from the Power systems (we also bought some MIPS-based DEC systems and a Stardent.) The bang for the buck was enhanced because we got the developer price on the IBM systems: 50% discount.

Apple used the Power architecture for years, when IBM and Motorola both produced power chips.

There surely are a number of ways IBM could use the Power 6 processor for a desktop machine, if they chose to do so. If the software vendors for computationally-intense desktop applications were to supply Power-processor versions of their products then the IBM desktop would be the system of choice for those applications, or at least that would seem to be so. Why wait 2 minutes for something to be done if you can get it in 1 minute on a faster system? There's a reason to seek faster processors and that reason isn't solely confined to the server market.

RE: Power6 wasn't built for desktops
By Zandros on 5/22/2007 5:56:39 PM , Rating: 2
While PowerPC is POWER-derived, they are not the same thing, and Apple has never used a Power µ-arch processor in their computers.

By Hoser McMoose on 5/22/2007 9:19:47 PM , Rating: 3
While PowerPC is POWER-derived

While that was true in 1993, it's not exactly meaningful anymore. The PowerPC instruction set was derived from the original POWER instruction set. However POWER-branded chips haven't used the POWER instruction set for a decade. IBM killed off that ISA in favor of PowerPC from their POWER3 processor onwards.

Like the POWER3, 4 and 5, this new POWER6 is actually a PowerPC chip and NOT a POWER chip. Yup, thanks IBM for making things clear as mud!

While Apple never used any POWER-branded PowerPC chips from IBM, the chips are (mostly) instruction-set compatible. The reason they didn't use one wasn't because they weren't the same, but rather because the POWER line of chips is IBM's REALLY expensive PowerPC chips. Since Apple didn't want to sell $10,000 desktops they instead stuck to IBM's cheaper offerings like the PPC 970 (aka G5).

By ixelion on 5/22/2007 10:08:05 AM , Rating: 2
IBM boasts that its processor has so much bandwidth that the POWER6 chip could download the entire iTunes catalog in about 60 seconds.

Anyone else think this seems a little silly, this assumes there would be nothing bottlenecking the performance, i.e. hard disk write speed.

RE: wha?
By FITCamaro on 5/22/2007 10:33:22 AM , Rating: 2
Oh little things.

RE: wha?
By tdawg on 5/22/2007 11:01:03 AM , Rating: 2
This is just a theoretical statement since they're just stating the capacity of the chips bandwidth (300Gb/s), as if it were download bandwidth. If there were no bottlenecks, 300Gb/s equals the entire iTunes catalogue in 60 seconds, if I'm understanding correctly.

RE: wha?
By deeznuts on 5/22/2007 6:41:16 PM , Rating: 2
Well let's say there was an equal amount of solid state memory to hold all the songs in the itunes catalog ... say RAM. It didn't say it was storing it in HDD. Of course it's silly, but it's a frame of reference.

In addition
By crystal clear on 5/22/2007 9:54:20 AM , Rating: 2

This is also the first time that IBM is rolling out a new software virtualization capability that allows customers to move live virtual machines from one physical Unix server to another while maintaining continuous availability. Called the Power6 Live Partition Mobility function, the technology allows a system administrator to move active virtualized partitions without temporarily suspending them. Previously, the same action would have required a reboot of the Unix system and software stack. IBM said the software is in beta with general availability planned for later this year.

This could be interesting...

RE: In addition
By EarthsDM on 5/22/2007 11:10:45 AM , Rating: 2
A classmate of mine worked for IBM last year. They had him working on a system of redundant virtual machines to handle the hard drive I/O of the other machines. I think IBM has gone full-bore with its new generation of machines.

RE: In addition
By crystal clear on 5/23/2007 4:03:05 AM , Rating: 2
Power6 has a total of 20 different virtualization enhancements that Mauri said will be fully realized once the update version of AIX is released later this year

I did not include this in my original comment-(I was in hurry).

IBM executives also announced that an updated version of the company's AIX operating system, called 6.1, will be available in the fourth quarter of this year. IBM said customers can start downloading the beta of its new Unix OS in July.

Fix that headline!
By redbone75 on 5/22/2007 10:49:43 AM , Rating: 2
IBM claims to have launched the world's fastest chip for UNIX servers

Now that I have that out of my system, it amuses me that every time a new processor is released people want comparisons to the current "champ." You can't get comparisons and benchmarks all the time because sometimes it just doesn't apply. It's like wanting to compare a Bugatti Veyron to a Ford Fiesta: you could, but why? Completely different markets for the intended product. I'm not saying, though, that it's not an intriguing thought:)

RE: Fix that headline!
By redbone75 on 5/22/2007 10:50:48 AM , Rating: 2
Damn, you guys are quick! Fixed it while I was writing my post. Good job;)

The Good News...........
By cheetah2k on 5/22/07, Rating: 0
RE: The Good News...........
By Treckin on 5/23/2007 1:06:58 AM , Rating: 2
yeah... now I can pump like 64 of these processors I bought though newegg in octal-SLI with a 10 petabyte SSD to play WOW 4!!!

I hope you were being sarcastic... because that was idiotic.
Barcelona's architecture is basically locked in, minus debugging.

I was intrigued by the comment about combining the specialized Cell core and a POWER6 core... Almost reminds me of some of the AMD jaw jacking and slides.

RE: The Good News...........
By crystal clear on 5/23/2007 6:29:15 AM , Rating: 2
socket compatible ?

They are completely different.
By greylica on 5/22/2007 12:32:22 PM , Rating: 2
The markets for X86 or X86_64 are completely different than the market for specialized tasks. Cell BE in conjunction with others make a better system for number cruch because have O.S redundancy guaranteed by the specialized processors that we use today. May be they want to put Cell BE and Power6 together to form REAL number Crunch systems. There will be no bottlenecks if the interface is connected directly one over another. In fact I guess they will fuse all of the technology into one processor, capable of handling redundancy with Unix/Linux and nunber crunching.

Just how much is that ?
By crystal clear on 5/23/2007 3:51:06 AM , Rating: 2
POWER6 chip could download the entire iTunes catalog in about 60 seconds

Just how much is that ?

20TB of information-That gives you an exact indication of what it means.

The IBM statergy
By crystal clear on 5/23/2007 4:14:52 AM , Rating: 2
I think if you put all the below items/objectives,you will understand the direction IBM is going into(POWER 6 is just one of them)-IBM has use the USERS in FOCUS.

1) POWER 6 is the first to fit in with IBM's announcement last week that it will redirect $1 billion per year across its businesses to increase energy efficiency in information technology under a program called "Project Big Green." The plan includes new products and services to reduce corporate data center energy consumption

Analyst firm IDC (IDC) estimates that roughly 50 cents is spent on energy for every dollar of computer hardware. This is expected to increase by 54% to 71 cents over the next four years.

an IDC survey of chief information officers and facilities managers found providing power and floor space are becoming increasingly important

POWER6 chip, which operates at 4.7 gigahertz, will allow businesses to consolidate servers and handle substantially larger workloads, doubling the speed of the previous generation POWER5 chip while using the same amount of electricity for running and cooling. This means customers can use the new processor either to increase their performance by 100% or cut their power consumption in half .

2)USER Experience-

IBM's SOA (service-oriented architecture) strategy .
IBM is serious about service-oriented architecture. It's so serious that the company is holding an entire conference around SOA this week in Orlando, the Impact 2007 event.
IBM lays out the importance of and its plans for service-oriented architecture.

"It's not just the user interface, but the overall experience of using the system,"
The Nielsen Norman Group, a Fremont, Calif., company that focuses on user experience and helping companies design human-centered products, defines user experience as encompassing "all aspects of the end user's interaction with the company, its services and its products. The first requirement for an exemplary user experience is to meet the exact needs of the customer, without fuss or bother. Next comes simplicity and elegance that produce products that are a joy to own, a joy to use. True user experience goes far beyond giving customers what they say they want, or providing checklist features."

3) Virtualization & AIX operating system -

IBM executives also announced that an updated version of the company's AIX operating system, called 6.1, will be available in the fourth quarter of this year. IBM said customers can start downloading the beta of its new Unix OS in July.

Along with the release of the AIX 6.1, IBM has added several new features into Power6 designed to enhance the virtualization of its systems, including a new feature called Live Partition Mobility, which allows users to move a virtual machine from one physical box to another while maintaining continuous availability.

Power6 has a total of 20 different virtualization enhancements that Mauri said will be fully realized once the update version of AIX is released later this year

Conclusion-Its all about Service-Oriented Architecture (SOA)

UNIX microprocessor?
By Proteusza on 5/24/2007 6:32:20 AM , Rating: 2
the new IBM System p 570 server is the first UNIX microprocessor able to calculate decimal floating point arithmetic in hardware

Surely there's no such thing as a UNIX microprocessor? An x86 can run UNIX and so can a PowerPC. RISC CPU designed for use in UNIX environments maybe, but UNIX microprocessor?

By crystal clear on 5/25/2007 4:11:02 AM , Rating: 2
The first public indication of IBM's Power6 muscle has arrived courtesy of Oracle.

You can catch all the benchmarks here until Oracle notices this story (Update: Oracle has removed the results). We've also taken the liberty of copying a PDF report on the results for you here.

Courtesy-The Register & Oracle

By Sureshot324 on 5/28/2007 11:59:47 AM , Rating: 2
How many FPS can this get in Counterstrike?

By Miggle on 5/22/07, Rating: -1
RE: Wow!
By lufoxe on 5/22/2007 8:25:36 AM , Rating: 3
it wouldn't compete with the c2d, different type of processor. From the article (and looking at the Power5) it's a totally different architecture. (not x86 like the c2d and athlon 64).

RE: Wow!
By fliguy84 on 5/22/2007 8:26:38 AM , Rating: 2
Or even against IBM's own Cell

RE: Wow!
By James Holden on 5/22/2007 8:34:41 AM , Rating: 2
Cool thing is, you know any really big advancements in power6 will end up in Cell and its derivatives (Xbox 3???)

RE: Wow!
By FITCamaro on 5/22/2007 9:28:49 AM , Rating: 2
Not really. For one just because Microsoft and Sony used a PowerPC core for their console CPUs this time around, that doesn't mean they will next time. Also, the PowerPC core inside both the 360 and the PS3 is no where even as good as the Power5 processor. It's a PowerPC based architecture but nothing like what say a Mac had in it. If it was, the systems would be much better.

RE: Wow!
By wingless on 5/22/2007 11:48:12 AM , Rating: 5
So if we actually had a gaming machine based on these Power6's then our eyes would bleed from such boundless badassedry?

IBM makes damn good processors and its a damn shame us PC users cannot directly benefit from their great products. I would love to see an M$ OS made for these processors that used DX9/10. If the PS3 and Xbox can run games with IBM's processors, and IBM's stuff is great for servers and workstations, then I see a reason for IBM to pursue mainstream status with their products. An IBM Workstation/Gaming rig would be super sweet to own.

RE: Wow!
By theapparition on 5/22/07, Rating: -1
RE: Wow!
By tjr508 on 5/22/2007 12:59:23 PM , Rating: 5
Jobs also said the dual g5 was twice as fast as 2x 3.8ghz xeons. I don't think the math adds up.

RE: Wow!
By IvanAndreevich on 5/22/2007 1:02:29 PM , Rating: 5
Why do you talk about something you have no knowledge about?

This is Power 5 - on an MCM with 144MB L3 cache and 16 cores.

This is what Apple used -

And no, even then you won't be right. Apple didn't only use G5 in laptops because it ran too hot and used too much power.

Power 6 is MUCH better than any x86 CPU in what it is designed for.

RE: Wow!
By IntelUser2000 on 5/24/2007 11:37:14 PM , Rating: 2

I couldn't find the most recent articles from IBM about Power 6, but from RealWorldtech, it says it has 75GB/s bandwidth PER CPU . It has dual memory controllers, one 64-bit and one 32-bit. We can expect that there is 8 channel for each memory controller, the 64-bit memory controller delivering 51.2GB/s bandwidth with DDR2-800 and 32-bit memory controller delivering 25.6GB/s bandwidth with DDR2-800. And its all on-die. It has more than twice the bandwidth of Intel's upcoming Tigerton system with quad 1066MHz FSB, on a single chip. It has more than 7x the bandwidth per core than Penryn.

RE: Wow!
By Hoser McMoose on 5/22/2007 9:05:26 PM , Rating: 3
All Mac's used IBM's Power5 processors until the switch to Intel's Core.

The Apple G5 processor was not a Power5 processor. Rather it was a PowerPC 970. There was some relation between the two chips, but they definitely weren't the same. Roughly speaking the PPC 970 was a VERY stripped down desktop version of the Power5, offering about half the performance of the real-deal.

Power6 sounds impressive, but is not in any way trying to compete with "windows" systems.

Generally speaking no, it's main competitor would be Sun UltraSparc and HP Itanium systems running Unix or Linux. However there are going to be some areas where the Power5 and now the Power6 will overlap with the Windows systems, including those running Intel or AMD x86 chips.

RE: Wow!
By wallijonn on 5/22/2007 12:51:12 PM , Rating: 3
An IBM Workstation/Gaming rig would be super sweet to own.

IBM's problem has always been one of capacity - they just can't make enough of the chips. So, while they could conceivably be able to meet the server demand, they would probably not be able to meet workstation demands. Because they can't make enough chips they can keep the prices high. It's the fastest server chip available, therefore it will command a high price.

RE: Wow!
By RjBass on 5/22/2007 4:43:05 PM , Rating: 2
The could do it if they finally opened up all those closed buildings in Boca again.

RE: Wow!
By johnsonx on 5/22/2007 5:51:50 PM , Rating: 3

Word of the Day!

RE: Wow!
By augiem on 5/22/2007 11:52:52 AM , Rating: 3
I can see his point though. They're bound to have developed some new technology and processes that will trickle down into lower end parts some day. Just like the space race gave us computers...

RE: Wow!
By kingpotnoodle on 5/22/2007 8:36:48 AM , Rating: 5
It won't even compete much with Xeon nevermind C2D (you will NEVER see this on the desktop), its aimed sqaurely at a different market - very high performance, very expensive server equipment for big business and scientific research, it's major competitors will be Itanium and UltraSPARC I would think. It won't compete with Cell either because its a general purpose CPU not a special "only for number crunching" CPU.

Its not using the x86 instruction set, it uses IBMs POWER architecture and instruction set. Only supported by flavours of Linux and Unix...

Still, a great step forward for IBM in terms of computing density, expect to see this crop up in some super computer's near you soon...

RE: Wow!
By James Holden on 5/22/2007 8:39:23 AM , Rating: 2
AMD is in the HPC space, K10 and Opteron. You can sure bet we will see benchmarks of this against K10.

RE: Wow!
By Master Kenobi on 5/23/2007 8:29:26 AM , Rating: 2
No, you fail.

There are two lines of processors.
K10 and Opteron use X86 instruction sets.
C2D and Xeon use X86 instruction sets.

On the dedicated high end server side we had originally just RISC processors, but then some variants of RISC popped in as well.
Itanium from Intel.
ultraSPARC from Sun.
Power from IBM.

These guys hash it out on the top level. AMD currently has no microprocessor to support the kind of parallelization required for servers on this magnitude. There is a reason X86 chips from Intel and AMD do not compete in this line, they are inferior for the heavy computational work specific to this environment.

In any case, put your pants back on, AMD does not compete in this arena and we will never see benchmarks for an AMD chip against one of these high class server chips. AMD's chip would take a pounding and then some since these are specialized chips, not general purpose like the K10 and Opteron.

RE: Wow!
By squishborka on 5/24/2007 10:18:59 AM , Rating: 2
I don't think the facts support you. The #6 supercomputer worldwide uses 9,000+ x86 Xeons. #9 uses 11,000+ Opterons.

RE: Wow!
By TomZ on 5/22/07, Rating: 0
RE: Wow!
By surt on 5/22/2007 10:52:03 AM , Rating: 2
I'm sure he meant: you won't see Power6 on the desktop, which seems likely. Very few people will own Power6 desktop workstations, if anyone even manufactures any.

We'll have as much processing power on the desktop in a year or less. But it won't be a Power6 inside.

RE: Wow!
By feelingblue on 5/22/2007 3:14:19 PM , Rating: 2
good, my watch is running a little slow ;-)

Actually, slinging VMs araound on the fly would be useful for low end servers and some development desktop configs.

RE: Wow!
By aquraishi on 5/22/2007 11:05:40 AM , Rating: 2
Not 'big business' - this is targeted squarely at medium-sized businesses in the $10MM-$50MM profit range. A fantastic server product for those of us who run UNIX. We run 19 instances of AIX on p-servers - this puts out a ton of heat and sucks a lot of power. I'd love to start over and buy 2 570s which could be expanded as needed - and provide hot failover from one to the other à la VMotion. 16 of these CPUs go a very, very long way.

RE: Wow!
By Hoser McMoose on 5/22/2007 9:30:27 PM , Rating: 3
It won't even compete much with Xeon nevermind C2D

While the two aren't going to see TOO much overlap, there will be some competition between them. Particularly in the HPC space, though also in more general purpose servers. The high-end of x86 servers and the low-end of POWER servers definitely overlap.

Generally speaking though you're correct, IBM's main competitors are Sun UltraSparc and HP Itanium systems.

(you will NEVER see this on the desktop)

Well "desktop" might be stretching it a bit, but they are likely to show up in high-end workstations. IBM's IntelliStation Power 285 uses a Power5+ processor. It's likely that it's successor will use some form of Power6 processor. Mind you, those workstations start at $8,000, so again it's not quite a "desktop" system by most normal definitions.

Its not using the x86 instruction set, it uses IBMs POWER architecture and instruction set.

Actually it uses the PowerPC instruction set. IBM hasn't used the POWER instruction set since the POWER2 chip back in the early 90's. From their POWER3 onward they have switched to the PowerPC ISA.

RE: Wow!
By rythie on 5/22/2007 10:55:36 AM , Rating: 3
For single thread performance you can use IBM's figures, they state
a SPECint2006 result of 21.6 and
a SPECfp2006 22.3
By Comparison a Dell 3.0Ghz Xeon 5160 does
18.1 in SPECint2006
and 15.6 in SPECfp2006
so 43% and 19% speed ups respectively.
IBM figures (see footnote point 1)

RE: Wow!
By fic2 on 5/22/2007 12:01:50 PM , Rating: 2
so 43% and 19% speed ups respectively.

should be 19% (int) and 43% (fp)...

RE: Wow!
By ralith on 5/22/2007 10:38:00 PM , Rating: 2
Assuming those benchmarks are apples to apples they are A LOT closer than I expected to see. Guess it really does make more sense to just get a few more X86 chips and double up on the memory and still end up paying less overall. Of course all that assumes you don't need those neat new ultra advanced features they built into the OS and chip or a very large SMP machine.

Cool to see anyway.

RE: Wow!
By rythie on 5/23/2007 5:29:40 AM , Rating: 2
Intel don't seem to want to compete in this market with x86_64 at the moment since they have no modern 4 socket box (i.e. one supporting Core based Xeons) and therefore can only do 8 cores using two sockets. However, you can already buy a AMD 16-core machine from Sun based on 8 sockets and when the K10 stuff comes out they will be able to do 32-core machines with potentially very similar single thread speed to these POWER6 processors.

RE: Wow!
By psychobriggsy on 5/23/2007 8:42:55 AM , Rating: 2
It's the SPEC_rate results you want to be comparing in these systems. Running a single threaded benchmark is barely worthwhile on a CPU designed to run 4 threads over two cores, and you are comparing that with a CPU designed to run 1 thread/core. Of course it is nothing like Sun's Niagara CPUs with 32 threads over 8 simple cores!

Scalability to 8, 16, 128 cores is what matters, and having the bandwidth to feed them. This is where the Xeon based systems fall down, and why IBM can charge a boat-load for their CPUs and systems.

The 8-core results show a 4.7GHz POWER6 getting over twice the scores (both int_rate and fp_rate) of an 8-core 3GHz Opteron system (which beat the 8-core Xeon system and an 8-core 1.6GHz Itanium system).

"People Don't Respect Confidentiality in This Industry" -- Sony Computer Entertainment of America President and CEO Jack Tretton
Related Articles

Most Popular ArticlesAre you ready for this ? HyperDrive Aircraft
September 24, 2016, 9:29 AM
Leaked – Samsung S8 is a Dream and a Dream 2
September 25, 2016, 8:00 AM
Inspiron Laptops & 2-in-1 PCs
September 25, 2016, 9:00 AM
Snapchat’s New Sunglasses are a Spectacle – No Pun Intended
September 24, 2016, 9:02 AM
Walmart may get "Robot Shopping Carts?"
September 17, 2016, 6:01 AM

Copyright 2016 DailyTech LLC. - RSS Feed | Advertise | About Us | Ethics | FAQ | Terms, Conditions & Privacy Information | Kristopher Kubicki