The WorkShop

It’s tough work to make up for lost ground , especially so in the blistering fast semiconductor business . Remember the pre-core 2 duo days when AMD was the king , since then they have lost the lead on desktop processors in the most dramatic fashion . Huge losses in the last two quarters has put the chip major into quite a slump . The recent ATI acquisition is yet to bear fruit, and the recently launched R600 graphics platform has been more or less a disappointment, industry experts are now expecting AMD to go fabless .
The positive side of the story is the upcoming launch of their new architecture ‘Barcelona’ about which I had written a while ago, and a series of dual and quad core desktop processors branded ‘Phenom’ . Alongside this there will be the successor to the quad FX enthusiast platform called FASNB which will use a new AMD chipset . FASNB will have a socket for one or two Phenom processors , DDR3 support and will be able to employ the power of a pair of the new R600 based GPU’s in crossfire .
Production AMD Barcelona’s are expected by late August . AMD may not be done yet .

I happened to stumble upon this at tgdaily . Its called the Optimus Maximus keyboard , and it is developed by a Russian company called Art Lebedev studio. Now for the cool part of the story , every key of the Optimus Maximus keyboard is a stand-alone display showing the function it is currently associated with .

Other disturbing features of this obscenely expensive piece of hardware are as follows, a standalone LED in each of its 113 keys. Each LED has a size of 10.1 x 10.1 mm and offers a resolution of 48 x 48 pixels. apparently the keys can not only display images, but videos with frame rates of up to 10 fps as well. up to 65,536 colors are supported, which can be seen on viewing angles of up to 160 degrees. Image and video layouts are stored on SD cards, which can be inserted on the back of the keyboard.

Hmmm.. really impressive , if you think about it , its quite an achievement but again , how many computer users ever look down at their damn keyboards while typing . I don’t know many , and for $1500 i ll build a kick ass rig complete with disco lights . Instead of this why not spend all the effort in making keyboards more ergonomic or durable , or try to put in features which make it easier for people with disabilities . This goes up right up there with the Finger Nose Hair Trimmer in my list of utterly useless products . Anyone who can give me one good reason to buy the optimus maximus gets a candy. any takers ??

May 21 saw the annual PCI Special Interest Group’s developer’s conference in San Jose , California . It seems that the move to PCI-E 2.0 is going to happen very soon with a lot of major players showing off PCI-E 2.0 technology at the conference . For the uninitiated PCI-E 2.0 has been in development for some time now and aims to double the interconnect bit rate from 2.5 GT/s to 5 GT/s . It effectively increases the aggregate bandwidth of the 16-lane link to approximately 16 GB/s.
Intel who promised to launch a PCI-E 2.0 motherboard before 2008 rolls in demonstrated unreleased AMD and NVidia graphics chips on its Stoakley chip set for workstations which offers two PCI-E 2.0 ports supporting 16 parallel lanes each. Majors like ARM, LSI, NEC and Synopsys also showed off their PCI-E 2.0 technology at the conference .
Intel is expected to release its first chipsets supporting PCIe 2.0 in the second quarter of 2007 with its ‘Bearlake’ family. AMD will start supporting PCIe 2.0 with its RD700 chipset series and NVIDIA with their MCP72 chipset .The PCI SIG is already working to define a version 3.0 for Express that could appear in products in late 2009. it will probably target 8 or 10 G transfers/second.

So come 2008, get ready to embrace express 2.0 as the new standard , also gear up for faster , high performance graphics cards which eat will eat up 300W of power on the Express 2.0 specification . How fast will the transition happen ? , looking at the merciless move from PCI to AGP and then to PCI express , I would say soon … very soon

Recently the One Laptop Per Child (OLPC) group announced that its low-cost laptop would be raised from $100 up to $175 , Closer to home a Chennai based company has introduced a PC for INR 4500 ( Around $100) and is all set to market it to a potential 10 million customers across the Globe , Net PC as they call it is a network computer, designed on a completely new hardware platform without using any of the typical PC or thin client components. The hardware design instead uses components designed and developed for advanced electronic and digital devices. The devices come as a single or a dual processor solution and can be connected to a basic home TV which serves as the display. For as little as $10 a month the company provides access to all the basic computing functions and also provides a broadband connection . There is no local storage though and all storage is done on a remote server maintained by the company . I won’t get into the technical details of the product , visit the Novatium site for more information ,you can download the product specifications there . I believe this is a great initiative especially for developing countries where a PC is still a luxury and not a necessity . Maybe the OLPC guys can take a few hints from this

nVidia has strapped on 2 Quadro FX5600 GPU’s ( OpenGl version of the mighty 8800GTX) onto thier already impressive line of Quadro plex VCS ( Visual computing system) . Looks like they are getting ready to take on the emerging GPCPU market as the new workstations support GPU computing with nVidia’s CUDA programming.
GPCPU has become a lucrative market for the future and a lot of big names are pouring money into it , recently Rapidmind , a startup grabbed $10 million of VC money for their GPCPU platform, keeping in pace nVidia is pushing its graphics cards hard as a platform for massively multi-threaded processing applications.
With the new GPU’s, the total frame buffer goes up to 3Gb (1.5 Gb per GPU) FSAA (full screen anti-aliasing) goes up to 64X , and as with the 8800GTX , the GPU’s have a unified shader architecture and fully support shader model 4.0 . Now comes my favorite part - performance stats 64x SLI FSAA,16 synchronized output channels,8 HD SDI channels,60 billion pixels/sec fill rate,1 billion triangles/sec geometry performance and is able to handle up to 148 megapixels display walls. and you can have many of these Quadro Plex boxes in your visualization cluster for scalability. Oh ! I forgot to mention they cost $18000 a piece.

April 23rd marked the fourth anniversary for the chipmaker’s Opteron and the ground-breaking AMD64 architecture , and to mark the occasion AMD announced widespread availability and pricing for the latest range of AMD Opteron dual-core server processors .
AMD also revealed updated performance numbers for its upcoming Quad-Core AMD Opteron™ processors, code-named ‘Barcelona.’ The new Barcelona projections show that AMD expects to have up to a 50 percent advantage in floating point performance and 20 percent in integer performance over the Intel’s “clovertown” quad-core processor at any given common clock frequency.AMD did not specify the clock speed of Barcelona. Intel’s Clovertown currently tops the chart at 2.66 GHz.
As for the performance of the new AMD Opteron Model 2222 and 8222 SE x86 dual-core server processors . AMD claims and I quote their website
“Under the newest SPECcpu2006 benchmarks, AMD Opteron™ processors continue to set the standard in x86 dual-core processor performance—besting our competitor by up to 15%. We credit that to our superior native dual-core design, with its Direct Connect Architecture, DDR2 memory, and industry-leading performance-per-watt. All with a clear migration path to native Quad-Core. It’s all proof positive that customer-centric innovation wins over hype.”
The AMD site also says
“Saying you’re the “World’s Best Processor” is one thing.
Actually being the “World’s Best Processor” is another.”

Considering their Dismal Q1 results , I would consider it a bold statement

More performance numbers
AMD Native Quad Core Tchnology

See the video where Randy Allen, Corporate Vice-President of AMD’s Server and Workstation Business talks about Barcelona

[youtube=http://www.youtube.com/watch?v=G_n3wvsfq4Y]

A few days back I had written about Blu-Ray outselling HD-DVD in the first quarter of 2007 , but looks like the HD-DVD camp is gaining momentum now . The Toshiba Website lists a HD-DVD player(Toshiba HD-A2) for as low as $399 and it has all the Bells and whistles for a true HD home theater experience . Rumors have started rolling in that Toshiba has outsourced a chunk of their manufacturing to China and thus have gained a significant cost advantage , another rumor suggests that a $200-$300 HD-DVD player will soon be hitting the markets with the first consignment arriving at WalMart as soon as mid may 2007 .
On the other hand the only blu-ray option available for anything under $600 is the PS3 , Sony has plans for a $499 blu-ray player for late this year, but anyone who is not a hardcore gamer and knows a wee bit of math will and I reinforce WILL go for HD-DVD , this has very serious implications for the blu-ray camp and especially so for Sony as they need blu-ray to accepted as the next generation media format for the PS3 to succeed in the long run . If the prices of blu-ray players do not come down by Mid 2007 then HD-DVD may start gaining widespread acceptance and if that happens then Sony will be left with another dead format and a bricked game console.

The demand for smaller-sized, high-speed, high-density multi-chip packages (MCP) is growing by the day . Stacking Silicon to increase packing density in IC’s is not a new concept, but recently stacking has gained a new level of importance as the process is being introduced to make microprocessors and is slated to come into the mainstream by 2008,Currently chip components are connected by wire bonding, requiring vertical spacing between dies that is tens of microns deep and horizontal spacing on the package board hundreds of microns wide for the die-connecting wires.Stacked silicon, rather than placed side-by-side shortens on chip data travel distances, ultimately saving a whole lot of space on chip and offering an opportunity to drive Moore’s law forward .

“Through-silicon vias” (TSV) is the technology employed for stacking ,which uses vertical connections etched through the silicon wafer and filled with metal. This concept has been described by other chip manufacturers before . Intel revealed thier plans for TSV at the spring IDF 2005 and most recently Samsung announced that it has developed the first all-DRAM stacked memory package using TSV technology, which will soon result in memory packages that are faster, smaller and consume less power, Samsung’s technology forms laser-cut micron-sized holes that penetrate the silicon vertically to connect the memory circuits directly with a copper filling, eliminating the need for gaps of extra space and wires protruding beyond the sides of the dies.
While TSV is still in its early stages, the technology represents the next step in innovative packaging solutions which have become increasingly important to enable high-speed, high-density and high- performance Semiconductor solutions .

Via Technologies , the Taiwanese manufacturer of Integrated circuits who also happen to be the world’s largest independent manufacturer of motherboard chipsets , have announced the IT industry’s smallest mainboard form factor specification and they call it Pico-ITX , at 10cm x 7.2cm it measures in slightly bigger than a regular playing card , Pico-ITX is currently the smallest complete x86 mainboard in the industry, smaller than all existing ATX, BTX and ITX form factors.

Designed for the Via range of processors such as the C7 processor , Pico-ITX mainboard form factor will provide system developers and with a standardized, ultra compact and highly integrated platform that can be utilized across multiple embedded PC, system and appliance designs. Some examples where these can be used may be PCs embedded within dashboards or in-flight entertainment systems and industrial automation systems , Integrated multimedia devices and even ultra portable entertainment devices, Pico-ITX can enable the design of full x86 computing devices in form factors which were previously not practical due to size limitations. Though I don’t see the design being utilized to its full potential in the very near future but come 2008 one can expect a lot of movement in the UMPC sector . The reference design specification has the following key components

Processor :VIA C7/VIA Eden V4 bus processor
•NanoBGA2 package up to 1.5GHz
• 128K L1 and 128K L2 cache

Core Logic: VIA VX700 all-in-one system media processor

Main Memory : • 1 DDR2 400/533 So-DIMM socket
• Up to 1GB memory size

Graphics: • Integrated VIA UniChrome™ Pro II 3D/2D AGP graphics with MPEG-2/4 and WMV9 video decoder
• Integrated LVDS and DVI interface • VIP port for video overlay function

Storage (ATA) • UltraDMA 133/100/66/33
• One 44-pin right-angle IDE connector
• One SATA connector

Audio System: VIA VT1708A
• 7.1 channels high definition audio codec
• 7.1 channels audio out and SPDIF in header
• Sound Blaster, Sound Blaster Pro compatible

Ethernet: (LAN) VIA VT6106S
• 10/100Mbps Ethernet Controller

Intel has revealed the first performance numbers for their upcoming 45nm Penryn Series of processors at their spring IDF in Beijing . Penryn will make its debut in late 2007 or early 2008 and is the successor to the current line up of Core 2 Duo processors made on the 65nm process.
Intel gave out performance numbers of the new processor with a comparison to its current top of the line 2.93 GHz Kentsfield QX6800 CPU . In comparison the new 3.33 GHz Yorkfield processor (Penryn quad-core for desktops) with 12 MB L2 cache and FSB1333 will gain about 15% in imaging applications, 25% for 3-D Rendering, 40% or more for gaming and more than 40% faster video encoding with SSE4 optimized video encoders, This performance gain comes from the fact that Intel has a set of 47 new SSE instructions to enhance the performance of such CPU intensive Applications .

On the server and workstation side, Intel expects its 45 nm FSB1600 processors to deliver up to 45% more speed for Bandwidth Hungry applications and a 25% acceleration for servers which use Java, when compared to the current X5355 quad-core processor.
Intel also intends to announce Skulltrail : a Consumer dual socket solution for Penryn which would allow up-to 8 cores on two chips and 4 graphics card on board , It should be noted that AMD has such a platform out for some time now which I had written about ( Quad Fx) . For more information on Penryn visit the IDF site ,The session Files can be downloaded in the PDF format.