Supercomputer Index

New Processors

02Sep2004: Dual Core Opterons and Horus = 32 Processor SMP Systems

Horus is a chip designed by Newisys that sits above a quad Opteron board and synchronizes those four caches with other Horus chips. Initial Horus chips will synchronize the caches on four quad processor boards, and dual core Opterons will enable 32 processors in a tightly coupled system.

The importance of this is that it makes the Opteron capable of competing with other large Symmetric MultiProcessor (SMP) systems from Sun, HP and IBM at a new level of economy. This will chip away at the profitable middle of the large SMP systems market where a fully shared memory is required. For certain kinds of problems where a clustered system introduces too much delay in accessing memory in other systems, a fully shared memory SMP system is the only answer.

More info on Horus, and some specs for the Dual Core Opteron. See also the SGI and NASA Altix system using twenty 512 processor SMP systems for the largest ever SMP system in 19Aug2004 Supercomputer News.

07Apr2004: Angstrom Delivers 2X Opteron Blades

While supercomputers get most of the press, blade systems will be the core of future data centers and utility computing efforts. Up to 130 blades in a rack is the highest curent density for Opteron processors. A single rack will have enough compute capacity to power a medium size business.

While this is not a new processor per se, the density of the arrangement is remarkable, with up to 16GB memory per blade. Check out Titan 64 Blades.

01Apr2004: IBM Opens Up Power Architecture

IBM has surprised most of the players in this industry by opening up its prime processor architecture, Power, to extensions from third parties, with foundry and software support from IBM. Power has the technology and performance leadership in processors, and IBM has changed the competitive landscape with this move. IBM will continue to control the core architecture and instruction set to maintain compatibility, but everything else is open for change. This is a remarkable change from the giant of computer technology who files more than 3,000 patents per year.

From the press release:
NEW YORK -- March 31, 2004 -- IBM today outlined plans to openly collaborate and build a community of innovation around its Power microprocessor architecture used in a vast range of products from the world's most powerful enterprise systems and supercomputers to games and embedded devices. The move could have major implications for computers and the electronics industry at large.
For more information, follow these links to the full Press Release, and another link to the Power Web Site.

28Mar2004: Processor Design and History Resource

This is the most complete reference of processor types that I have seen anywhere. The home page has several links to other sources of information - see Great Microprocessors of the Past and Present (V 13.3.0) but it is the Table of Contents that is truly amazing. It constitutes seven sections, each with several entries, plus six appendicies. Here is an overview with links:
Even though I have lived through most of the computer revolution and read much of what was published, there are several processors I never heard of and dozens that I had forgotten. To top it all off, the sections cover the general architecture of like processors with links for even more details for the insatiable technologist. I've already spent too much time there. Strongly Recommended.

02Mar2004: Dual Desktop Processors in 2005

Dual processors on one chip will make purchase decisions harder in 2004. The dual processors will represent a very large performance jump and only the very latest motherboards will support them. Current motherboards are not ready for this, except possibly the AMD 939/940 pin socket systems (unconfirmed). Not until Intel's 775 pin LGA socket will there be one for Pentiums. From Xbit Labs:
Leading microprocessor makers, Intel and AMD, added multitude of technologies into their x86 microprocessors recently, including massive things like x86-64, Hyper-Threading and plethora of micro-architectural improvements. However, this is only the beginning of massive increase of CPU computing power! Next year Intel is rumored to start making dual-core chips, not only for servers, but for desktops and even mobile computers, according to reports from PC Watch web-site!
Read more at Xbit Labs.

18Feb2004: Intel Announces 64 Bit Xeon - Big Surprise Elsewhere

The worst kept secret in decades were the 64 bit extensions for Intel's Pentium and Xeon processors. You can read below (2Feb2004) why I knew Intel had no choice. But there really is a big surprise here, one which won't get much press. What is it?

The big surprise is that this is the first time since 1972 that anyone other than Intel has originated a new or extended architecture that was so good that Intel had to copy it to keep up. This issue will be downplayed by Intel at every chance, but the basic facts won't change. Intel has changed from a leader to a follower.

Intel's IA432 chip, a design so far ahead of technology in the 1980s that it took four chips to implement, was an earlier learning process. The Itanium, which was first conceived in 1991 and began building in 1994, is similar to the IA432 in some areas. Itanium was very aggressive as a new architecture and the design was well ahead of the technology in 1994. Despite this, Intel invested huge amounts of money to make it work, and eventually succeeded in building the technology.

What they overlooked along the way was their competitors, who advanced the ancient x86 ISA to new levels by borrowing concepts from RISC and pushing the CMOS technology. When the Itanium arrived, years late, it no longer had a big performance lead. Even so, Itanium could have dominated the top end systems because of 64 bit capabilities until AMD's 64 bit Opterons came along.

The design advance of AMD's 64 bit extensions was nothing short of brilliant. They recognized and cured the x86's single biggest weakness - too few registers. AMD also extended the instruction set in compatible ways and brought the ancient x86 architecture into the 21st century. It is the Opteron, not the Itanium, that will kill off most of the RISC processors, mainly on the basis of AMD's design changes. It is clear that only IBM's Power architecture and probably Sun and Fujitsu's SPARC architecture will continue as alternative high performance chips.

Where will Itanium wind up? As a niche product for supercomputers and high end systems where maximum floating point performance is needed regardless of cost. The rest will go to Opteron and the extended (IA32e) Intel version. I expect this change of leadership in x86 design will cost Intel a lot, eventually dropping Intel's market share from above 70% to below 60%. AMD will wind up with almost all of the difference.

Of course Intel will fight back - but will they succeed? More about that soon.

02Feb2004: Prescott Released but Performance Neutral

I've read a number of articles on the Intel P4 'E' Prescott chip and have considered the possible reasons for the unimproved results. My conclusion is that Prescott has 64 bit extensions inside and operational at some level, but Intel has not yet enabled them for use.

I beleive that Intel is planning to enable the 64 bit extensions with the release of the 775 LGA socket in Q3 or Q4 in order to beat the powerful Opteron/AMD64 chips which currently outperform P4 despite running at a much slower clock rate.

My reasons for these conclusions are not precise, but together they are compelling. First, Intel cannot afford a long time before they can match and exceed Athlon64 performance because it would give AMD time to become established in Intel's most profitable arena - server chips. Second, given Intel's capabilities in design and manufacturing, the performance lag cannot be accidental - it has to be as a side effect of some other decision.

Third, Intel has stated outright that they will have 64 bit capable chips available when demand rises and software support is available. Reading between the lines, they recognized that AMD's 64 bit extension was a good design and would get accepted. They also realized that when Microsoft ships its 64 bit enabled OS this fall, demand will rise and they must be ready then.

Fourth, Intel routinely releases technology enhancements as disabled parts of chip versions just prior to the enabled version. Fifth, the 64 bit capability demands many more connections to the motherboard, thus the big jump in socket capability from current 478 pins to 775 connections in the upcoming LGA socket.

In summary, Intel has the capability to build a 64 x86 bit chip, the resources to design one, the need to remain competitive with AMD in order to keep AMD from growing into a bigger, more dangerous competitor. They will accept the hits to Xeon and Itanium in the short term in order to retain dominance in their major cash cow - 70+ percent of the end user processor market.

The potential damage to Xeon and Itanium will be limited by enhanced versions of these chips which are already in the pipeline. Intel is ready to respond to the attack of the AMD64. I believe both AMD and the public will be surprised at the strength of Intel's counter attack.

20Nov2003: 90nm PowerPC 970; A Look at POWER5, UltraSparc IV and Efficon

IBM is adding Intel SpeedStep-style clock frequency and core voltage scaling technology to the 90nm version of its PowerPC 970 processor, aka the G5. Read more at The Register.

ARS Technica has an overview of three new processors - the POWER5, UltraSparc IV and the Transmeta Efficon.

This article originally started life as an MPF CPU roundup, but it has evolved into more of an overview of three specific upcoming processors: IBM's POWER5, Sun's UltraSparc IV, and Transmeta's Efficon. Actually, the article focuses mostly on IBM's POWER5 and Transmeta's Efficon, but I also cover Sun's UltraSparc IV because it's relevant to the "big picture" that I want to paint with this report.

Read more at ARS Technica.

02Nov2003: Updates on Opteron; Sparc64 vs Sparc

01Nov2003: Optical Processor hits 8 TeraOps

Israeli startup Lenslet has developed an optical DSP that can perform eight trillion operations per second. According to a Reuters report, when Lenslet releases its Enlight processor in a matter of weeks, a unit using the technology will be 1.7 centimetres high and measure 15 by 15 centimetres. Check out this article at The Inquirer.

22Oct2003: Update on Server Processors

Ace's Hardware has a good overview on the server processors announced at MPF. Look for UltraSparc IV and Fujitsu Sparc64 VI here, and Power5 here.

20Oct2003: Clearspeed CS301;  Transmeta Efficon;  Via C5P;  IBM Power5;  Fujitsu Sparc64 VI

The annual Microprocessor Forum is the place for big announcements and this year was no exception. The Efficon and C5P are in the low power class.

Clearspeed is a new design approach of parallel processors and low power together. The performance is impressive, the low power doubly so. Multiple CS301 chips can be tied together, putting a large array into a small box. This may be the multiprocessor for the rest of us.

The IBM Power5 and Fujitsu Sparc64 VI are in a class by themselves - the behemoth class. It's clear that IBM will own the very high end (if you have to ask, you can't afford it) of the SMP and cluster systems for the forseable future.

ClearSpeed CS301

This is a substantial design breakthru in parallel processing combined with low power. I expect this design, in its delivered chip variations, to make as much difference in parallel processing as the cluster and blade concepts have in the past. According to President Mike Calise, first silicon is working and no surprise to me, interest is very high. I will have more on this design soon. Here is a brief overview from the announcement:

The Clearspeed CS301 is a multi-threaded array processor that enables dramatic improvements in performance and power consumption for intensive floating point applications. At over 25 GFLOPS peak performance, the new chip provides more than twice the processing speed of competitive products. At 10 GFLOPS per Watt, power consumption is also twenty times more efficient. As a result, the CS301 delivers up to a ninety percent reduction in purchase price and running costs, making high performance computing affordable and available to companies of all sizes.
Read the full announcement at Clearspeed.



Transmeta Efficon

Finally supporting the full Pentium4 instruction set including SSE2, Efficon has integrated single-channel DDR400 controller, integrated AGP 4X and integrated Hypertransport for a choice of south bridges (same ones as on AMD Athlon64-M platform - Nvidia Nforce 3 Go comes to mind). While the claimed 7 W Thermal Design Power limit on Efficon will accommodate a 1100MHz CPU, compared to 900 MHz on Pentium M, Transmeta also claims overall better performance per cycle for Efficon vs Pentium M (not to mention Pentium 4-M). Read the full announcement for the Transmeta 8000 Efficon.

VIA C5P Nehemiah

VIA is firmly on its 'low-cost, low-power' fanless desktop CPU path and it continues with the new C5P Nehemiah CPU. Smaller than a US 1-cent coin, the C5P package enables dual-CPU Mini-ITX integrated PC boards for the first time. The claimed power figures show this thingie consumes roughly 30% less power than Pentium-M at the same clock. Check out the review at ExtremeTech.


IBM POWER5

Check out the picture of an 8 processor Power5! The MCMs now are more integrated - a single POWER5 MCM has four chips (8 CPUs) plus four 36 MB L3 cache chips, and allows for easier back-to-back with another MCM to make a very fast and compact 16-way system at full bandwidths systemwide. In fact, so compact that you could fit 16 of those in a single rack, and connect them with something like, say, Quadrics, for a nice little 2 TFLOPs supercomputer with 2TB RAM in that same rack. Finally, one more MP link on chip allows now for 64-way single SMP system in the same footprint as current 32-way POWER4+. For more details on the Power5, check out this article on The Inquirer.

Fujitsu SPARC64 VI

It is a powerful Sparc Class CPU, with dual 2.4GHz cores, 6MB ultra high bandwidth on-chip cache, fast buses, proper out-of-order execution with fast FP as well, and and scalability that far exceeds the UltraSPARC IV. The Fujitsu chip with 690 million transistors done in 0.09um copper process, similar process geometry is claimed for the Sun UltraSPARC IV as well. In reality, the dual-core, multithreaded (each core is 2-way SMT too) SPARC64VI should be at least twice as fast as dual-core UltraSPARC IV. Check out the Fujitsu Sparc Roadmap at Computer Business Review.


10Oct2003: Alpha EV7x Updates

It's not at all clear what will happen to the upcoming Alpha processor upgrades. There is both positive news and some questions not answered yet. Here are some links to the various news items:

It's clear that HPC is less than happy about the slow uptake of their Itanium systems and obviously believe that they can increase those by downplaying OpenVMS and the Alpha processor. This is a terrible mistake by HPC as it creates FUD for their own products while not really strengthing their position in high end systems.

You can check out the updated OpenVMS information in Large System Notes.

1Oct2003: AMD Announces Dual Core Opterons for 2005

AMD has put a date on dual core Opterons, which have been rumored for some time. The original Opteron design includes an internal interface to the north bridge for two cpus. Optrons will be moved to 90 nm lithography in early 2004, so the dual core chips will start on that line size and probably move to 65 nm in 2006. Read more on this at The Register and Xbit Labs.

26Sep2003: Opteron Design Analysis

Hans de Vries, the host of Computer-Architect, writes in detail about current and upcoming new processors using the x86 instruction set. Normally I don't cover this class of processors because they are well covered in the general press, but Hans' analysis merits a closer look.

Specifically, Hans has discovered several innovations in the Opteron (also Athlon FX and Athlon 64) design that make the chip faster and more efficient. Here is a short selection from the extensive chapter indexes:

This list selects points of special interest from the detailed four chapter analysis of the Opteron design. To read the whole document in detail will take at least an hour, but you can get a good feel for the system by just selecting the items listed above from the detailed chapter indexes. Recommended for technical people.

Even just skimming the information will give you a new appreciation for why the Opteron is winning all those supercomputer contracts. These same reasons will make Opteron and its sibling Athlon 64 and Athlon FX killer desktop systems. Read it all at Chip-Architect's Opteron Analysis.

15Sep2003: IBM Aims for TeraOps Chip

IBM has named this TRIPS, the Tera-op Reliable Intelligently Adaptive Processing System. The prototypes will include four Trips processors, each containing 16 execution units laid out in a 4 x 4 grid. By the end of the decade, when 32-nanometer process technology is available, the goal is to have tens of processing units on a single die, delivering more than 1 trillion operations per second.

TRIPS addresses the increasingly difficult problem of accessing data quickly on a chip operating at picosecond cycle times. At those rates, signals take several cycles just to travel across the chip. In order to make full use of the chip's capabilities, processing logic and data must be physically close together, yet predicting where that needs to happen is difficult. That's where the Adaptive nature of the chip comes in.

I think this new concept represents a fundamental change in the way future high end processors will be designed and built. Once again, IBM's investment in Research and Development, more than $6 billion per year, will pay off in future generations of products. Read more at EE Times and at IBM.

25Aug2003: Ultrasparc IV and Gemini Details

Ace's Hardware has a nice article with some details of the upcoming multicore processors Sun has designed. There is also a short piece on Sun's research contract with the government to design a single system image with 100,000 thread capability. Checkout the story at Ace's Hardware.

22Aug2003: IBM Details Power5 Simultaneous Multithreading (SMT)

At the high end of the performance curve, IBM is adding SMT to its dual core Power5 design. The main reason IBM gives for this is that there is a 40% performance gain possible with very little more energy required, thus reducing the heat generated for a given performance level. They also plan future chips to have 4 cores with 8 threads each on a single (very large) high performance chip. More info at C|Net News.

The Power5 processor will be used in a nuclear weapons simulation supercomputer at Lawrence Livermore National Laboratory. That machine, called ASCI Purple, is slated to use 12,544 Power5 chips. ASCI Purple, due to be running by the end of 2004, is expected to have 196 interconnected 64-processor servers, making a total of 12,544 Power5 chips. It will come with 50 terabytes of memory and will also will have IBM disk storage arrays holding 2 petabytes, or a quadrillion bytes, of data.

As for physical size, ASCI Purple will weigh about 197 tons, be linked to 119 miles of optical cable and 28 miles of copper cable, and occupy 8,900 square feet of floor space--or about two basketball courts. It will consume 4.7 megawatts of power, enough current for 4,000 homes, according to IBM. More on ASCI Purple at C|Net.

20Aug2003: Sun Announces Gemini CMP

Gemini, a dual processor on a chip, will combine two UltraSPARC II cores. It wll arrive in 2004, run at 1.2 GHz yet consume only 32 watts at maximum. This should be an ideal chip for small but powerful blade servers. More on Gemini at The Register.







All content on this site is Copyright 2001 - 2003 by Bill Nicholls
All Rights Reserved