ARM and Taiwan Semiconductor Manufacturing Company, Ltd. (TWSE: 2330, NYSE: TSM) today jointly announced a long-term agreement that provides TSMC with access to a broad range of ARM processors and enables the development of ARM physical IP across TSMC technology nodes. This agreement supports the companies' mutual customers to achieve optimized Systems-On-Chip (SoC) based on ARM processors and covers a wide range of process nodes extending down to 20nm.

The agreement provides TSMC access to optimize the implementation of ARM processors on TSMC process technologies, including ARM Cortex processor family and CoreLink interconnect fabric for AMBA protocols. It also establishes a long-term relationship with ARM for the development of physical IP, including memory products and standard cell libraries targeting the most advanced TSMC 28nm and 20nm processes.

TSMC today held a groundbreaking ceremony in Taichung's Central Taiwan Science Park for Fab 15, TSMC's third 12-inch (300mm) Gigafab and an important milestone in the company's pledge to expand investment in Taiwan.

The groundbreaking ceremony was conducted by TSMC Chairman and CEO Dr. Morris Chang. "Science Parks have played a critical role in the development of Taiwan's high-tech industry. They have also provided important support to TSMC as we grew to become a leading global semiconductor company with its roots in Taiwan," Dr. Chang said. "Over the past two decades, TSMC has flourished in the Hsinchu and Tainan science parks, and our groundbreaking for Fab 15 today sets the foundation for TSMC to reach new heights."

SPARKLE Computer Co., Ltd., the professional VGA card manufacturer and supplier, today announced the SPARKLE GeForce GTX 460 series Graphics Cards, which includes the SPARKLE GeForce GTX 460 768MB Graphics Card, the SPARKLE GeForce GTX 460 1GB OC Graphics Card and the SPARKLE GeForce GTX 460 2GB Graphics Card.

As a deadly weapon of Fermi Family, SPARKLE GeForce GTX460 series graphics cards provide the best performance price ratio, being the the world's best $200 graphics card, it brings a new level of DirectX 11 performance to mainstream PC enthusiasts and gamers around the world.

One of the first pictures of NVIDIA's upcoming GF104 graphics processor has come to light, with a Chinese source picturing a GF104 qualification sample. The sample is based on the A1 silicon. The GPU package is similar to that of the GF100, it makes use of an integrated heat-spreader (IHS) to disperse heat from the die underneath it. The package is rectangular rather than square (probably a move to reduce board footprint, translating into more compact boards) The GPU is built on TSMC's 40 nm process, and is said to have significantly lower TDP compared to the GF100. One of the first SKUs built around it is the GeForce GTX 460.

Contrary to older reports, Expreview's report suggests that the GeForce GTX 460 will have 336 CUDA cores (instead of 256), and 768 MB of memory across a 192-bit GDDR5 memory interface. Its TDP is expected to be around the 150W mark, similar to that of a GeForce GTS 250. It will target price-point slightly above the $200 mark, while other SKUs carved out of this silicon will be lesser.

With AMD's next generation of graphics processors, the company plans to, at one point, switch its GPU manufacturing from its present Taiwan-based foundry partners such as TSMC and UMC, to GlobalFoundaries, its erstwhile own manufacturing division. From 40 nm, graphics processors are expected to jump to 28 nm as the next manufacturing process standard. GlobalFoundries will be ready with a 28 nm High-K metal gate (HKMG) node for making AMD products which are now bulk-manufactured in Taiwan.

During a quarterly conference call with financial analysts, chief executive officer of AMD, Dirk Meyer said "The first intersection of our AMD GPUs and GlobalFoundries are on the 28nm. We haven't been public with respect to any timing there." GlobalFoundries is said to have two principal kinds of 28 nm nodes, the 28nm-HP (High Performance) node makes complex chips such as GPUs, game console chips, storage controllers, networking and media encoding, while the 28nm-SLP (Super Low Power) is used for less complex devices, particularly intended to be low-power, for portable devices, such as baseband, application processors, and other handheld functions. In 2011, AMD is expected to release its next-generation of GPUs in a series codenamed "Northern Islands".

TSMC, one of the world's major semiconductor foundries, said that it has resolved all issues pertaining to proper yields of chips built on the 40 nanometre node. During a company event on the 19th, Mark Liu, Senior VP of Operations, said that the quality of production on the 40 nm node is almost on par with the 65 nm one. Liu stated that the chamber matching problems that had impacted yield rates for the company's 40nm node have been resolved.

TSMC caters to graphics processor giants NVIDIA and AMD, with both having designs of 40 nm performance graphics processors with multi-billion transistor counts. AMD has been selling 40 nm GPUs made by TSMC since its previous generation ATI Radeon HD 4770, it currently makes all its Radeon HD 5000 series GPUs on the node. NVIDIA is poised to release its first billion transistor 40 nm GPU, the GF100, in its consumer GeForce brand later this quarter.

In addition to this, TSMC has just finished building a new factory at the Hsinchu Science Park (HSP), Taiwan, part of its Fab 12. The new facility will be able to commence volume production of 28 nm products as early as by Q3 2010.

NVIDIA today launched its Next Generation Tegra, the world's first processor for the mobile web, specifically designed for the high-resolution needs of tablets. Consumers have been waiting for a truly portable, high-resolution, no-compromise Internet experience. NVIDIA's new Tegra processor delivers that by combining lightning-quick browsing, streaming 1080p video and Adobe Flash Player 10.1 acceleration with an immersive 3D user interface and days of battery life.

"Without question, 2010 is going to be year of the tablet," said Tim Bajarin, President, Creative Strategies, Inc. "The new NVIDIA Tegra processor has a unique feature set critical for tablets -- fast web browsing with fully rendered pages, uncompromised graphics, snappy user interface and HD video - all with the battery life we've only seen with cell phones."

NVIDIA's upcoming flagship graphics processor is going by a lot of codenames. While some call it the GF100, others GT300 (based on the present nomenclature), what is certain that the NVIDIA has given the architecture an internal name of "Fermi", after the Italian physicist Enrico Fermi, the inventor of the nuclear reactor. It doesn't come as a surprise, that the codename of the board itself is going to be called "reactor", according to some sources.

Based on information gathered so far about GT300/Fermi, here's what's packed into it:

• Transistor count of over 3 billion
• Built on the 40 nm TSMC process
• 512 shader processors (which NVIDIA may refer to as "CUDA cores")
• 32 cores per core cluster
• 384-bit GDDR5 memory interface
• 1 MB L1 cache memory, 768 KB L2 unified cache memory
• Up to 6 GB of total memory, 1.5 GB can be expected for the consumer graphics variant
• Half Speed IEEE 754 Double Precision floating point
• Native support for execution of C (CUDA), C++, Fortran, support for DirectCompute 11, DirectX 11, OpenGL 3.1, and OpenCL

GLOBALFOUNDRIES today announced the appointment of Jim Ballingall as vice president of marketing. In this role, Ballingall will be responsible for developing and implementing marketing solutions and strategies to support the growth of GLOBALFOUNDRIES as it aims to reshape the landscape of the foundry industry.

"The core of the GLOBALFOUNDRIES brand comprises the sum of the unique value propositions that we create, promise, and deliver to our customers," said Jim Kupec, senior vice president of sales and marketing at GLOBALFOUNDRIES. "As we strive to deliver on our vision and become the world's first truly global foundry, Jim's proven foundry industry leadership and experience will help us develop and convey our unique value propositions to customers and stakeholders and position the company for optimal success, as we unlock our customers' potential to innovate and win."

Taiwan Semiconductor Manufacturing Company, Ltd. has become the first foundry not only to achieve 28 nm functional 64 Mb SRAM yield, but also to achieve it across all three 28 nm nodes.

"Achieving 64 Mb SRAM yield across all three 28 nm process nodes is striking. It is particularly noteworthy because this achievement demonstrates the manufacturing benefits of the gate-last approach that we developed for the two TSMC 28 nm high-k metal gate processes," explained Dr. Jack Sun, vice president, Research and Development at TSMC.

"This accomplishment underscores TSMC's process technology capability and value in 28 nm. It shows TSMC is not only able to extend conventional SiON technology to 28 nm, but is also able to deliver the right 28 nm HKMG technology at the same time," explained Dr. Mark Liu, senior vice president, Advanced Technology Business at TSMC.

TSMC and CEA-Leti, the leading French semiconductor research institute, signed an agreement today in which TSMC will join the new industrial program IMAGINE, led by CEA-Leti, on maskless lithography for IC manufacturing. Intended to operate for three years, this program allows companies to assess a maskless lithography infrastructure for IC manufacturing and use MAPPER Technology as a solution towards high throughput. It covers a global approach, including tool assessment, patterning and process integration, data handling, prototyping and cost analysis.

Sapphire today announced its Radeon HD 4730 accelerator. The new GPU surfaced along with Radeon HD 4790. Together these GPUs fill the Radeon HD 4700 series, bringing relief to the demand Radeon HD 4770 created, but is apparently unable to meet due to technical problems with the 40 nm manufacturing node of foundry partner TSMC.

The Sapphire Radeon HD 4730 uses a PCB that is pin-compatible with Radeon HD 4870, as it is based on the same RV770 core with a different configuration. The company used a simple cooler with radially-projecting aluminum fins, which it has been using on inexpensive models of the Radeon HD 4850, and HD 4830. The memory is subjected to its air-flow, while the VRM area has a heatsink of its own. The GPU has 640 stream processors enabled, with a 128-bit wide GDDR5 memory interface, holding 512 MB of memory. Sapphire cut down on the number of memory chips used, thanks to the narrower memory bus, while maintaining the memory bandwidth of similarly clocked 256-bit GDDR3. The core is clocked at 750 MHz, while the memory is at 900 MHz (3.6 GT/s effective). The outputs provided on the card are DVI-D, D-Sub, and HDMI. The card takes its power input from two 6-pin power connectors. The card uses a 3+2 phase power circuit. The Sapphire HD 4730 is expected to be priced at 80€.

Yesterday, AMD unveiled its surprise for this year's Computex, with a demonstration of a DirectX 11 3D scene. Behind the scenes though, was what AMD claimed to be the "world's first true DirectX 11 graphics processor". The hardware itself however, wasn't publicly displayed, although a memento of AMD's partnership with TSMC, a wafer of 40 nm DirectX 11 GPUs, was made public. VR-Zone however, sneaked into the backdrops and pictured the machine that ran the demo (which ironically, was built into a case with a side-window).

The graphics card, a portion of which, is hidden behind the "wing" of the AMD Dragon logo graphic, is seen to be about 8.5 inches long, spans across two slots, and has a seemingly sporty cooler with the ATI-red shroud. It draws power from a single 6-pin PCI-E connector. The photographers note that this could be the RV840-based desktop accelerator, which forms the performance-mainstream product for the company's upcoming DirectX 11-compliant GPU lineup codenamed "Evergreen". The first product from this series is expected to be released in September, weeks ahead of the launch of Microsoft Windows 7.

It seems that in order to make up for the shortages of the now very popular HD 4770, due to TSMC's issues with 40 nm manufacturing, AMD is dropping the prices of the HD 4850 to around the MSRP of the HD 4770. That is around $99.99 US and about €90, this will be putting further pressure on NVIDIA as AMD brings down one of its top GPUs in to the sub-$100 market.

Nearly a month since AMD's introduction of the 40 nm RV740 GPU, there is still no concrete sign of a 40 nm GPU from NVIDIA slated for anytime soon, apart from timely scoops on the GT300. Sources at graphics card vendors however seem confident that by the end of 2009, 40 nm GPUs will constitute at least 30% of NVIDIA's GPU shipments, that too sourced from TSMC, a foundry-partner which has been in the news off late, for technical problems with their 40 nm node, that are affecting its output efficiency.

What's more, NVIDIA seems to have expressed interest in becoming one of the first clients for TSMC's upcoming 28 nm process that is expected to become a reality in Q1 2010. This should also tell you that for GPUs, the next step for silicon fabrication technology will be 28 nm, unlike 32 nm for CPUs.

NVIDIA's upcoming next-generation graphics processor, codenamed GT300 is on course for launch later this year. Its development seems to have crossed an important milestone, with news emerging that the company has already taped out some of the first engineering samples of the GPU, under the A1 batch. The development of the GPU is significant since it is the first high-end GPU to be designed on the 40 nm silicon process. Both NVIDIA and AMD however, are facing issues with the 40 nm manufacturing node of TSMC, the principal foundry-partner for the two. Due to this reason, the chip might be built by another foundry partner (yet to be known) the two are reaching out to. UMC could be a possibility, as it has recently announced its 40 nm node that is ready for "real, high-performance" designs.

The GT300 comes in three basic forms, which perhaps are differentiated by batch quality processing: G300 (that make it to consumer graphics, GeForce series), GT300 (that make it to high-performance computing products, Tesla series), and G200GL (that make it to professional/enterprise graphics, Quadro series). From what we know so far, the core features 512 shader processors, a revamped data processing model in the form of MIMD, and will feature a 512-bit wide GDDR5 memory interface to churn out around 256 GB/s of memory bandwidth. The GPU is compliant with DirectX 11, which makes its entry with Microsoft Windows 7 later this year, and can be found in release candidate versions of the OS already.

With rival AMD having a production-grade 40 nm graphics processor, and UMC's recent announcement of being ready with a high-performance 40 nm manufacturing node, the conditions are increasingly favourable for NVIDIA to flag-off large-scale production of 40 nm GPUs. According to Chinese print-media Commercial Times, the company set its foundry outsourcing schedule for within Q2 2009, with TSMC and UMC being the regular foundry-partners.

Within this quarter, NVIDIA will start mass-production of the entry-level GT218, high-end mobile GT215 and mainstream desktop GT214 and GT216 GPUs. Additionally, the company may also expand its output for the 55 nm G200b high-end GPU.

Intel Corporation and TSMC today announced a memorandum of understanding (MOU) to collaborate on addressing technology platform, intellectual property (IP) infrastructure, and System-on-Chip (SoC) solutions. Under the MOU, Intel would port its Atom processor CPU cores to the TSMC technology platform including processes, IP, libraries, and design flows. The collaboration is intended to expand Intel's Atom SoCs availability for Intel customers for a wider range of applications through integration with TSMC's diverse IP infrastructure.

After spinning off its manufacturing division to The Foundry Co., AMD is left with all the engineering resources it needs to make processors. Contradicting older roadmap slides by the company predicting it would start selling 32 nm processors in 2011, Dirk Meyer, CEO of AMD in an interview with Information Week said that the company is on-track to ship smaller, more powerful processors built on the 32 nm manufacturing process by 2010.

The new manufacturing process would allow the chip maker to step up transistor counts to add more features and computational power. Tomorrow, on March 2, the AMD is expected to close the deal with Advanced Technology Investment Company (ATIC) of Abu Dhabi to form The Foundry Company (TFC). This would render AMD fabless. The company will then, like other fabless market heavyweights such as NVIDIA and VIA, will focus on designing processors, while TFC, its largest foundry partner will manufacture the processors. Currently AMD is tied up with foundry companies such as TSMC and UMC for manufacturing products of its Graphics Products Group, products such as GPUs and chipset.

AMD will be an year behind larger market rival Intel in selling processors built on the 32 nm technology. Intel plans to roll out 32 nm processors by Q4 2009. AMD's designs will be ready by mid-2010, following which volume production of its 32 nm chips will commence by Q4 2010.

Morris Chang, chairman of Taiwan Semiconductor Manufacturing Co. (TSMC), said on Friday what his predictions were for the global semiconductor industry and when it will recover from the global economic crysis that's upon everything at the moment.

I think it will be 2012 before the total revenue of the semiconductor industry gets back to the '08 level

he said. Knowing that he has more than 50 years experience in this circle, and he's the founder of the world's largest contract chip manufacturer TSMC, we can trust his words. Mr. Chang also added that the semiconductor industry was "pretty close" to the bottom. That's really how bad the chip makers are doing at present.

Following reports of AMD's next flagship GPU, the RV790 being pushed to April, a fresh report from Hardware-Infos suggests that its sibling, the RV740 will join the league of the company's product launches slated for April. Company sources tell Hardware-Infos that the company has no product-launches scheduled for the upcoming CeBIT event held in Germany. The report suggests constraints of TSMC, a major foundry partner for AMD's graphics product group (GPG), with regards to its 40 nm bulk manufacturing process, as a likely cause although this bit wasn't endorsed by the source.

Another source shed some light on the specifications of the two graphics processors. It is suggested that the RV790 has expanded machinery at its disposal, with 960 stream processors and 48 texture memory units. Engineering samples based on the said GPU are known to carry faster memory chips. The specifications coupled with the suggested higher clock speeds of 850/975 MHz (core/memory) help explain how the RV790 could manage to pose competition to the NVIDIA GeForce GTX 285 accelerator. The RV740 on the other hand, is said to carry 640 stream processors, 32 texture memory units, and a 128-bit wide GDDR5 memory interface.

Taiwan Semiconductor Manufacturing Company (TSMC), the world's largest independent semiconductor foundry and chip maker for ATI, Altera, Broadcom, Conexant, Marvell, NVIDIA, and VIA products, recently posted its fourth-quarter financial results. TSMC reported revenue of NT$64.56 billion, net income of NT$12.45 billion, and earnings per share of NT$0.48 (US$0.07 per ADS unit) for the fourth-quarter that ended December 31, 2008. Year-over-year, the company's fourth-quarter revenue decreased 31.2% while net income and EPS decreased 63.9% and 62.3%, respectively. Compared to third-quarter of 2008, fourth-quarter results of TSMC represent a 30.6% decrease in revenue, a decrease of 59.3% in net income, and a decrease of 59% in EPS. That sharp decline in TSMC's finances is triggered by the contageous economic recession worldwide. Unfortunately it is taking money from literally everything and everyone.
"The global economic recession continues to worsen. Fourth quarter end-market sell-through was much below the already conservative expectations, and consumer demand remains very weak. This has led to a rising DOI for our customers, who continue to pare their inventories aggressively, resulting in a further significant cut back of wafer demand," said Lora Ho, VP and Chief Financial Officer of TSMC.

NVIDIA's G200b, its current flagship GPU will be suceeded later this year with the GT212, and as Hardware Infos discovers, NVIDIA seems to have given some interesting specifications to the GT212. To begin with, the GPU holds more than 1.8 billion transistors. It is built on TSMC's 40nm manufacturing node. The shader domain gets a boost with 384 shader units (a 60% increase over G200(b)). The GPU holds 96 texture memory units and a 256-bit wide GDDR5 memory bus with a clock speed of 1250 MHz (5000 MT/s).

The transition to GDDR5 seemed inevitable, with there being a genuine incentive of cutting down the number of memory chips (due to the efficient memory bus), with NVIDIA having completely avoided GDDR4. With the die-size being expected to be around 300 sq. mm, these GPUs will be cheaper to manufacture. The GT212 is slated for Q2 2009.

At the AMD Analyst Day event, AMD indicated in its presentations that The Foundry Company, a manufacturing company formed from the assets of AMD with the intestments of ATIC under the AssetSmart program, would in the future become an independent foundry company accepting foundry partnerships from companies apart from its one largest customer, AMD. The move would keep the newly formed company profitable and competitive with other Asian foundry companies.

In the same presentation, AMD also indicated that eventually it would assign manufacturing of its ATI Radeon GPUs and chipsets, to The Foundry Company (TFC). Currently GPUs and chipsets are being manufacuted by foundry companies such as TSMC and UMC in Taiwan. This move would send a significant chunk of manufacturing to TFC. Sources tell ATI Forum.de that at FAB38 Dresden, a major manufacturing facility, installations of the 40nm bulk manufacturing node is in full-swing (not to be confused with 45nm SOI, on which K10.5 processors are built). Also there are indications of the facility accepting orders for manufacturing chips on the new node from other fab-less companies, an attempt to bring in profitability right from the start.

The RV740 graphics processor by AMD could well be the first GPU in production, to be built on the newer 40nm manufacturing process, giving its makers something to brag about. The RV740 design and specifications are largely derived from the RV770LE (covered here), while bringing the GDDR5 memory standard to the mainstream.

Chinese industrial journals tell DigiTimes that the company has completed taping-out the RV740, and that the GPU is awaiting mass-production by AMD's foundry partner, Taiwan Semiconductor Manufacturing Company (TSMC). Mass production of products based on this GPU could commence by the end of Q1 2009.