NVIDIA, Microsoft ally on high performance GPU computing

SANTA CLARA, USA: NVIDIA announced work with Microsoft to promote NVIDIA Tesla graphics processing units (GPUs) for high performance parallel computing using the Windows HPC Server 2008 operating system.

"The coupling of GPUs and CPUs illustrates the enormous power and opportunity of multicore co-processing," said Dan Reed, corporate vice president of Extreme Computing at Microsoft. "NVIDIA's work with Microsoft and the Windows HPC Server platform, is helping enable scientists and researchers in many fields achieve supercomputer performance on diverse applications."

NVIDIA Research developed several GPU-enabled applications on the Windows HPC Server 2008 platform, such as a ray tracing application that can be used for advanced photo-realistic modeling of automobiles. Related to this, NVIDIA worked with Microsoft Research to install a large Tesla GPU computing cluster and is studying applications that are optimized for the GPU.

In addition, a whole range of enterprise applications - such as data mining, machine learning and business intelligence, as well as scientific applications like molecular dynamics, financial computing and seismic processing - are taking advantage of the massively parallel CUDA(TM) architecture on which NVIDIA's GPUs are based to achieve higher levels of productivity.

The CUDA architecture enables developers to use the CPU and the GPU together in a co-processing model. Compute-intensive sections of an application use the parallel computing capabilities of the GPU, while the sequential part of an application's code runs on the CPU.

"The combination of GPUs and the Windows platform has been a great benefit to our VMD (Visual Molecular Dynamics) user community, bringing advanced molecular visualization and analysis capabilities to thousands of users," said John Stone, senior research programmer at the University of Illinois Urbana-Champaign. "As we move toward even larger biomolecular structures, GPUs will become increasingly important as they bring even more computational power to bear on what will be highly parallelizable computational problems."

"The scientific community was one of the first to realize the potential of the GPU to transform its work, observing speedups ranging from 20 to 200 times while using a range of compute-intensive applications," said Andy Keane, general manager of NVIDIA's Tesla business. "Researchers are increasingly using Windows on workstations and in data centers due to strong development tools like Microsoft Visual Studio, its ease of system management and its lower total cost of ownership."

NVIDIA Tesla high-performance GPU computing products support Windows XP and Windows Vista in the workstation and Windows Server 2003 and Windows Server 2008 in the data center. Tesla C1060 and S1070 GPU computing products are available from most major system vendors including Cray, Dell, HP and Lenovo.

NVIDIA delivers comprehensive OpenCL support under Snow Leopard

SANTA CLARA, USA: Apple's new Snow Leopard operating system (OS) is the first OS to integrate OpenCL, a cross-platform open standard that makes it possible for developers to tap into the vast gigaflops of computing power currently in the graphics processing unit (GPU) and use them for any application.

OpenCL on the NVIDIA CUDA architecture enables applications to use the CPU and the GPU together as co-processors. NVIDIA's integration of the CUDA architecture across its brands and segments enables it to offer Apple users a broad selection of 10 GPU models officially supported by Snow Leopard.

These are: NVIDIA GeForce 9400M, GeForce 9600M GT, GeForce 8600M GT, GeForce GT 120, GeForce GT 130, GeForce GTX 285, GeForce 8800 GT, GeForce 8800 GS, NVIDIA Quadro FX 4800, and Quadro FX 5600.

"NVIDIA chairs the OpenCL working group and is the only company to have OpenCL drivers for the GPU in the hands of thousands of Snow Leopard, Windows and Linux developers today," said Sanford Russell, general manager of CUDA at NVIDIA. "We're excited to see Snow Leopard ship, signaling the arrival GPU Computing for all Apple users."

NVIDIA has a range of documentation and tools available for OpenCL including a detailed programming guide, a Best Practices guide with tips and tricks for tuning performance, SDK code samples and a soon-to-be-released Visual Profiler for performance optimization.

In addition to working closely with Apple to integrate support for OpenCL into Snow Leopard, NVIDIA has also released OpenCL conformant drivers for Windows and Linux.

Magma's Quartz deployed by NVIDIA as primary design rule checker for 40nm and below

SAN JOSE, USA: Magma Design Automation Inc., a provider of chip design software, announced that its Quartz DRC has been deployed by NVIDIA Corp. as the primary physical verification checker for designs targeted at 40-nanometer (nm) and smaller process nodes.

NVIDIA, which invented the graphics processing unit and continues to lead its development, is using the Magma physical verification tools for applications ranging from custom cell development to full-chip verification. NVIDIA selected Quartz for 40 nm and below after use on multiple 65-nm designs and finding they delivered significantly faster turnaround time than existing physical verification tools.

"We have been using Magma's Quartz physical verification solution in production since we moved to the 65-nm process node, and it has proven to be both accurate and significantly faster than other solutions," said James Chen, VLSI technology manager at NVIDIA. "Through dozens of tapeouts, we've seen that Quartz provides the sign-off accuracy needed via certified runsets provided by our foundry partners. Though design sizes and rule complexity have increased significantly, we've been able to meet aggressive design schedules by leveraging Quartz's linear scalability on standard, low-memory Linux machines."

Quartz DRC and LVS are architected to process integrated circuit (IC) designs of any size, at any technology node, in the least amount of time. Magma's is the first truly scalable physical verification solution, able to provide turnaround time that is up to an order of magnitude faster than existing solutions while using existing compute resources. The Quartz tools are fully compatible with third-party IC implementation flows and can read file formats used by traditional physical verification tools.

"Quartz DRC and LVS have enabled silicon success for a wide range of customers, including those doing the most advanced designs in the world," said Anirudh Devgan, general manager of Magma's Custom Design Business Unit. "NVIDIA's decision to deploy Quartz as the primary physical verification design rule checker for 40-nm and smaller process nodes is an endorsement of the software's ability to provide the fastest turnaround-time while using very cost-effective hardware systems."

NVIDIA Tegra provides multimedia muscle in Zune HD

SANTA CLARA, USA: NVIDIA Corp. today announced that Microsoft’s new Zune HD portable media player is powered by the NVIDIA Tegra processor, which gives it exceptional multimedia capabilities.

The Zune HD player, which Microsoft recently announced is available for preorder, is the first portable media player to combine HD-compatible video1, HD Radio receiver, full-screen Internet browsing, an organic light emitting diode touch screen, and Wi-Fi.

These features will connect consumers to a whole new world of entertainment, while delivering excellent battery life. Working closely with Microsoft and optimizing the Tegra processor, NVIDIA has played an important role in helping to bring the next-generation Zune HD portable digital media player to market.

“Tegra provides the multimedia muscle in Zune HD,” said Michael Rayfield, general manager of NVIDIA’s mobile business. “Users will love the device’s new design, amazing multimedia features and HD video out capability. Zune HD is a must-have for anyone looking for the best portable digital media player on the market.”

Key to Tegra’s rich multimedia features are eight independent processors, each designed for a specific class of tasks - among them are an HD video processor, an audio processor, a graphics processor, and two ARM cores.

The processors can work together or independently to minimize power consumption. The Microsoft Zune HD2 uses the following NVIDIA Tegra technology to deliver a unique visual experience:

* An HD video processor dedicated to HD video, providing unprecedented picture quality and ultra-smooth, vivid movie playback with low power consumption.
* An ultra-low power graphics processor for a compelling and intuitive user interface.
* NVIDIA nPower technology, which optimizes system power use and enables extended HD video and MP3 playback time.

Based on NVIDIA’s decade of graphics leadership, Tegra processor has been engineered over the past five years to bring high performance and low power capabilities to the next generation of mobile computing devices such as portable media players, smartphones, smartbooks, netbooks and tablets.

Tegra processor-based devices are delivering the experiences that today’s mobile consumers demand, with HD video playback, always-on HD Internet, and intuitive 3D user interfaces. There are 50 active Tegra processor-based design projects currently in the works today.

TI tops ABI Research's MID platforms vendor matrix ranking

NEW YORK, USA: Texas Instruments has been ranked at the top of the latest Vendor Matrix released by ABI Research.

NVIDIA and Freescale Semiconductor claimed the second and third spots in the company’s new evaluation of worldwide Mobile Internet Device (MID) platform vendors.

“Congratulations to TI for taking the MID Platforms vendor title for the second time,” said Jeff Orr, senior analyst.

“The company’s current MID platforms, incorporating ARM processor cores, excelled in several categories, including the implementation of every mobile operating system we examined –- from Windows Mobile to Palm’s webOS.”

Seven PC and mobile operating systems were factored into scoring. NVIDIA and Freescale represent the next generation of multimedia-rich MID platforms, which are expected to debut during the second half of 2009.

The Vendor Matrix is an analytical tool developed by ABI Research to provide a clear understanding of vendors’ positions in specific markets. Vendors are assessed on the important parameters of “innovation” and “implementation” across several criteria unique to each vendor matrix.

For this particular matrix, under "innovation," ABI Research examined these platforms’ connectivity options, their level of voice support, the capabilities of their processors, their displays, and the integration and support services available to licensees and manufacturers of the MID platform.

“TI received perfect scores for its range of voice support, display capabilities and integration support services,” notes Orr. “The company offers development tools, reference designs and consultative services necessary to accelerate MID design programs into manufacturing.”

Under "implementation," ABI Research scrutinized the following criteria: existing customer types (ie. what PC system, mobile handset and consumer electronics vendors are currently buying or licensing the MID platform or architecture); commercially available products, current PC operating system support, and existing mobile operating system support.

NVIDIA SLI now licensed for Intel Core i7 and i5 platforms

NEW DELHI, INDIA: NVIDIA Corp. announced that Intel Corp., and the world’s other leading motherboard manufacturers, including ASUS, EVGA, Gigabyte, and MSI, have all licensed NVIDIA SLI technology for inclusion on their Intel P55 Express chipset-based motherboards designed for the upcoming Intel Core i7 and i5 processor in the LGA1156 socket.

As a result, customers who purchase a validated P55-based motherboard and Core i7 or Core i5 processor when available can equip their PCs with any combination of NVIDIA GeForce GPUs, including Quad SLI, for the ultimate visual computing experience.

“NVIDIA SLI technology is a perfect complement to the processing prowess of our new Core i7 and Intel DP55KG desktop board,” said Clem Russo, VP and General Manager of Intel Client Board Division at Intel Corporation.

“NVIDIA and Intel share a combined passion for furthering the PC as the definitive platform for gaming, and this combination will surely be attractive to anyone building or purchasing a brand new PC this fall.”

NVIDIA SLI technology is now available for all consumer PC platforms, including the Intel Core i7, Core i5, Core 2 Quad and Core 2 Duo processors, as well as those based on the AMD Phenom II CPU.

In addition to raw graphics performance, NVIDIA GeForce GPUs also provide gamers with additional capabilities not found on any other discrete graphics solutions, including NVIDIA PhysX technology for deeper gaming immersion, and stereoscopic 3D gaming with NVIDIA 3D Vision technology.

“Only the best-designed motherboards are capable of tapping into—and reaping maximum benefits from—the powerful synergy between SLI technology and the P55 platform,” said Joe Hsieh, General Manager of ASUS’ Motherboard Business Unit.

“ASUS has honed the art and science of motherboard design with the ASUS P7P55 Deluxe and ROG Maximus III Series motherboards, which deliver unparalleled performance and stability.”

NVIDIA Tesla GPU for HP's flagship Z workstation

SANTA CLARA, USA: NVIDIA announced that HP's most powerful and expandable workstation--the HP Z800 Workstation--is now configurable with up to two NVIDIA Tesla graphics processing units (GPUs), another key indicator of the demand being seen for GPUs in the high performance computing (HPC) space.

Enterprises that rely on HP workstations to accelerate their work in fields ranging from scientific research and industrial design, to 3D animation and seismic exploration, can now reap the benefits of NVIDIA Tesla GPUs and tackle demanding computational workloads right at the desktop.

Based on the massively parallel NVIDIA CUDA architecture, Tesla GPUs are taking the high performance computing (HPC) industry by storm, delivering performance increases to critical codes across multiple fields.

In molecular dynamics, AMBER, a public research code with more than 60,000 users, has been written to leverage the massively parallel CUDA architecture to deliver a 50X speed up of simulations. The result is faster scientific insights for researchers.

In finance, Numerix and CompatibL have announced CUDA support for a new Counterparty Risk application of their Numerix 7 analytics solution used by over 375 financial institutions. This derivatives pricing application is today experiencing an 18X boost in performance in the calculation of complex pricing models with NVIDIA GPUs.

"The adoption of Tesla GPUs is the fastest of any new processor technology in the history of HPC," said Andy Keane, general manager of Tesla business at NVIDIA. "We are delighted to see a leader such as HP begin to ship Tesla GPU-enabled systems into the market and to help accelerate the work of their customers."

"HP's workstation customers are professionals at the top of their game, pushing the limits of technology, for more creativity and innovation than ever before," said Jeff Wood, director of worldwide marketing, Workstations, HP. "The NVIDIA Tesla GPU takes our flagship Z workstations to extreme heights for floating point intensive applications."

Top 20 semicon rankings Q2-09 -- TSMC climbs up, AMD slips down!

Very interesting, isn't it? And I am not surprised! TSMC deserves to move up the top 20 semiconductor companies rankings!! It seems that AMD especially needs to really get its act together.

First, to the rankings. Recently, IC Insights released the list of the top 20 semiconductor sales leaders during Q2-09.Source: IC Insights

In this list, there are four fabless semiconductor companies -- Qualcomm, Broadcom, MediaTek and Nvidia in the top 20, and one foundry -- TSMC, perhaps, emphasizing the growing influence of TSMC as well as the fabless semiconductor companies.

AMD slips! Again?
I had written a couple of posts some time back on AMD and Intel, where the former had commented on the EC ruling on Intel, and also how both were at each other's throats, and had asked the question -- how will all of this help the market?

Well, one hopes that AMD will come back very much stronger in the next quarter, despite its uninspiring guidance for 3Q09, saying that it expects its sales to be "up slightly" from 2Q09.

TSMC, Hynix, MediaTek shine
Coming back to the table, the clear movers are TSMC, and no surprises there, as well as Hynix and MediaTek. In fact, with a little better Q3 performance, TSMC could well move up to the third position, overtaking both Texas Instruments and Toshiba.

Look at the last column -- the 2Q09/1Q09 percentage change -- TSMC has grown by a whopping 93 percent! One other thing! TSMC is reportedly eyeing business opportunities in solar photovoltaics and LEDs in a bid to diversify its revenue channels. Should these happen, expect TSMC to move up higher!

The closest to TSMC in terms of growth are Hynix at 40 percent and Qualcomm at 36 percent, respectively. MediaTek, another impressive mover, grew by 20 percent. Of course, there is Samsung as well, with 29 percent growth.

ST, Micron, Nvidia and NXP have done well too! According to IC Insights, Nvidia replaced Fujitsu in the Q2-09 top 20 rankings. And that brings us to the shakers or those who fared poorly.

Fujitsu, AMD, Freescale slide!
I've already touched upon AMD. Fujitsu cited flash memory and automotive device sales to have suffered immensely this quarter. However, it hopes Q3 will be better and said that customer demand was picking up. So, it could well be back in the Top 20 during Q3.

Yet another slip was in store for Freescale. It slipped from 16th position in 2008 to 18th position during Q1-09, and slid further to 20th position in Q2-09. Perhaps, overdependance on automotives has been its undoing.

An interesting statistic from IC Insights -- Fujitsu, with -9 percent and Freescale, with -2 percent growth, were the only two top-20 companies from Q1-09 to register a 2Q09/1Q09 sales decline!

Wonderful industry guidance
It is heartening to see 19 of the 20 companies registering positive growth this quarter. It won't be improper here to commend IC Insights on its wonderful industry guidance!

In an IC Insights study from late December 2008, it was very vocal in advising firms to adopt a quarterly outlook! It also forecast a significant rebound in the IC market beginning in the third quarter of the year!

IC Insights also stood out by pointing out in early July that H2-09 is likely to usher in strong seasonal strength for electronic system sales, a period of IC inventory replenishment, which began in 2Q09, and positive worldwide GDP growth.

IC Insights had marked 4Q08 as the beginning of the downturn/collapse and Q1-09 as the bottom of the cycle. This quarter (Q2) has largely been a replenishment phase for the inventories. Going by that count, Q3 could well see a true seasonal increase in demand. IC Insights also said that during Q4-09, market growth will mirror the health of the worldwide economy and electronic system sales.

There is light, after all, at the end of the tunnel! Wonder why are the industry folks continue to tell each other -- we still aren't having a good time! Maybe, it is time for them to shed their pessimism and from holding back on investments, and move on to show steely optimism, and indulge in really aggressive buying and selling! After all, work and progress will happen ONLY if you work!!

Top 20 semiconductor suppliers sales surge 21 percent in 2Q09!

USA: The 2Q09 results from the top 20 semiconductor producers illustrate why IC Insights has, since the beginning of this downturn, encouraged its clients to think quarterly about 2009! As shown below, the semiconductor industry continues to move through this silicon cycle very quickly on its way to recovery.

4Q08 — The beginning of the downturn/collapse
1Q09 — The bottom of the cycle
2Q09 — Inventory replenishment phase
3Q09 — Seasonal increase in demand
4Q09 and beyond — Market growth will mirror the health of the worldwide economy and electronic system sales

Over the past few years, much has been said regarding the "maturing" of the semiconductor industry and less volatile cycles. However, IC Insights' new Mid-Year Update to The McClean Report shows that the trend toward a less volatile semiconductor market does not apply when looking at the industry on a quarterly basis.

As shown in Fig. 1, the top 20 semiconductor companies, in total, registered a 2Q09/1Q09 sales increase of 21 percent. This was a 37-point swing compared to the 1Q09/4Q08 results when these same top 20 suppliers endured a sales drop of 16 percent!Source: IC Insights

As discussed in detail in IC Insights' Mid-Year Update to The McClean Report, much of the semiconductor sales surge in 2Q09 was due to inventory replenishment after the severe cutbacks of 4Q08 and 1Q09. However, seasonal demand for electronic systems is forecast to drive 3Q09 semiconductor sales up by at least another 8 percent.

IC Insights continues to forecast a 17 percent decline for the full-year 2009 semiconductor market (the same forecast it presented in December of 2008).

Spurred by the bottoming of the worldwide economy from global recession in 1Q09, the semiconductor market is forecast to continue along its recovery path in the second half of this year and gain further momentum in 2010.

Climbers:
TSMC — As forecast by IC Insights, the world's largest IC foundry almost doubled its sales in 2Q09. In fact, all of the four major pure-play foundries (TSMC, UMC, Chartered, and SMIC) registered very strong 2Q09 sales.

TSMC is expecting another 20 percent increase in sales in 3Q09. Moreover, the company raised its 2009 capital spending budget from $1.9 billion to $2.3 billion, which is good news for the struggling semiconductor equipment suppliers. Considering that the company only spent $390 million in the first half of 2009, a huge jump in spending (to $1.9 billion) is scheduled for the second half of this year!

Hynix — One of the world's largest memory suppliers, Hynix displayed a 40 percent sales surge in 2Q09/1Q09 and replaced AMD in the top 10. The company cited rebounding average selling prices (ASPs) for both flash memory and DRAM as a key boost to its sales figures.

IC Insights expects that memory ASPs will continue to rise in the second half of 2009 and beyond as the severe cutbacks in memory capital spending and facility closures further restrict available capacity.

MediaTek — High-flying fabless IC supplier MediaTek joined the top 20 ranking by jumping six positions in 1Q09. As shown, the company moved up another two spots, to number 17, in 2Q09 with a 20 percent jump in sales.

The company continues to attribute much of its success to the "stay-at-home-economy" driving digital TV IC sales as well as continued strength in its core wireless communications business.

Descenders:
AMD — The second-largest MPU supplier in the world has continued to find that it is no fun to be in competition with the giant Intel! As shown, the company fell out of the top 10 in 2Q09 by barely growing (+0.6 percent), while Intel increased its sales by 12 percent. Moreover, AMD's guidance for 3Q09 was uninspiring, saying that it expects its sales to be "up slightly" from 2Q09.

Freescale — Freescale dropped from being ranked 16th in 2008 to 18th in 1Q09 to 20th in 2Q09 and was one of only two top-20 companies (along with Fujitsu) to register a 2Q09/1Q09 sales decline (-2 percent).

The company is in the midst of a major re-organization (eliminating its cellular phone business) and its fortunes are increasingly influenced by the health of the automotive industry.

Fujitsu — Fujitsu dropped from being ranked 17th in 1Q09 to 22nd in 2Q09 (Nvidia replaced Fujitsu in the 2Q09 top 20 ranking) as its 2Q09/1Q09 sales declined by 9 percent. The company stated that its flash memory and automotive device sales suffered the most in 2Q09.

However, Fujitsu believes that its customers' excess device inventories have now been depleted and that consumer demand is picking up.

AMD soars in Q2-09, Intel, Nvidia show great gains

TIBURON, USA: Jon Peddie Research (JPR), the industry's research and consulting firm for graphics and multimedia, has announced estimated graphics shipments and supplier market share for the second calendar quarter of 2009.

Graphics chips (GPUs and IGPs) are the leading indicator of the PC market. The GPUs go into a system before it becomes a PC and gets into the hands of the customer.

After the channel stopped ordering GPUs and depleted inventory in anticipation of a long drawn out worldwide recession in Q3 and Q4 of 2008, expectations were hopeful, if not high that Q1’09 would change for the better.

In fact, Q1 showed improvement but it was less than expected, or hoped. Instead, Q2 was a very good quarter for vendors -- counter to normal seasonality -- but then these are hardly normal times. It’s clear the channel is gearing up for what it thinks is going to be a robust back-to-school season.

Traditionally, Q1 to Q2 sales decline due to summer vacations and preparation for the fall. This year preparation seems to have gotten off to an early start.

Total market
Year to year things were great. Shipments jumped up to 98.3 million units, up 31.3 percent from last quarter -- and most everyone fared well.

Table: Total Graphics Chip Market for Q2'09Things probably aren't going to get back to the normal seasonality 'till Q3 or Q4 this year, and we won't hit the levels of 2008 until 2010.

However, people still need to buy things. Old computers will fail, new employees will be hired and need machines, and of course software upgrades like Windows 7 will be coming along.

We are still predicting an upturn in the PC market in Q3 and Q4 and in particular for the graphics market (which serves not just PCs but aerospace and automotive, industrial systems, medical systems, kiosks and POS). We are optimistic because these are seasonally the best quarters.

* In Q4 there will be two new operating systems: Apple's Snow Leopard, and Windows 7 which will help stimulate new purchases in the holiday season.
* ATI & Nvidia will be introducing new 40nm designs with higher performance, GPU-compute, and surprisingly aggressive prices.
* The worst is over for inventories run down and the channel is now restocking for back-to-school, and the holiday madness.
* And yes, there is pent up demand.
* We still believe there will be an impact from the stimulus programs worldwide.

Mac Mini carries $376.20 bill of materials

EL SEGUNDO, USA: Apple Inc.’s latest Mac Mini desktop computer demonstrates once again that Apple knows how to make computers better, smaller, and more attractive.

Such an achievement, however, comes at a premium and bears higher component costs due to the Mac Mini’s use of parts designed for mobile PCs, according to a dissection conducted by iSuppli Corp.’s Teardown Analysis Service.

The entry-level version of the new-generation Mac Mini carries a Bill of Materials (BOM) of $376.20, which increases to $387.14 when manufacturing costs are added. This low-end model of the Mac Mini is priced at $599, reflecting the relatively thin BOM/manufacturing margins generated by Apple’s PCs in relation to its lower-cost consumer items, specifically the iPod line.

The table summarizes the results of iSuppli’s teardown of the new Mac Mini.

iSuppli: Top Cost Drivers in the Second-Generation Mac Mini (Pricing in US Dollars)Source: iSuppli, June 2009

The total materials and manufacturing costs reported in iSuppli’s teardown analysis of the new Mac Mini mirror only the expenses for direct materials, manufacturing and basic tests.

Not included in this analysis are costs above and beyond the material manufacturing of the core device itself—i.e., the cost of intellectual property, royalties and licensing fees—as well as those expenses not already included into the per component price, software, software loading and test, shipping, logistics marketing and other channel costs.

Mini finds its inner mobile PC
“Unlike most desktop computers from other brands, the Mac Mini and, indeed, Apple’s entire Mac line make extensive use of components designed for notebook computers,” said Andrew Rassweiler, director and principal analyst for iSuppli. “This enables the Mini and other members of Apple’s computer line to achieve their very sleek and compact form factors, and to reduce energy consumption. However, the use of these components, along with other cost adders like software, yields a computer that is more expensive to make.”

The Mac Mini’s focus on mobile components starts at the top with the PC’s use of Intel Corp.’s Core 2 Duo P7350 microprocessor, which is designated as a mobile chip. The specific Mac Mini torn down by iSuppli incorporated a 2GHz clock speed version of Core 2 Duo P7350, which carries an iSuppli estimated price of $118.35. The next-level Mac Mini model features a 2.26GHz version of the microprocessor, available from Apple at a $150 premium in retail pricing.

Another mobile microchip embedded in the Mac Mini is the Nvidia GeForce 9400M graphics and I/O controller hub. Apple commonly uses this same part in its MacBook line of notebook PCs. The Nvidia GeForce 9400M comes in at an estimated price of $65.16.

Other mobile components in the Mac Mini that command a price premium include the 2.5-inch form factor Hard Disk Drive (HDD) and the slim Optical Disk Drive (ODD). The Hitachi 120GByte 2.5-inch-format HDD comes in at a price of $46, while the Mac Mini’s ODD—a DVD±R DL/DVD±RW/CD-RW 8 x speed drive—is priced at $32.

Cutting PCs down to size
At a size of 6.5 x 6.5 x 2 inches, the Mac Mini is tiny compared to a more full-size desktop PC tower enclosure, which can be 10-20 times larger, not including Apple’s external power supply, of course.

Power up
In spite of its use of some mobile components, and the latest energy-saving silicon process geometries, the Mac mini overall has a great deal of processing power. As a result, it employs a 110-watt external power supply, representing a higher power usage than the first-generation model, which employed an 85-watt power supply.

This is so despite the process geometry leap from the 0.13 micron technology employed in Freescale’s RISC microprocessor in the first-generation Mac Mini, to Intel’s 45nm process Core 2 Duo used in this most recent generation Mac Mini.

“The new Mac Mini is a more powerful computer than the first-generation model, causing its peak power requirements to rise,” Rassweiler said. On the other hand, the Mac Mini has earned its green designation as it consumes less than 13 watts when in idle mode.

Nvidia inside
Another major difference between the new Mac Mini and the first- and second-generation models is the use of the Nvidia graphics controller and I/O controller hub. The first-generation Mac Mini employed an equivalent ATI part. The second-generation Mac Mini also employed an Intel graphics processor.

This represents a departure from conventional Intel chipset designs in which Intel provides all of the core silicon and processing beyond the microprocessor.

“Nvidia, as a specialist in the domain of graphics processing and acceleration, clearly enhances the performance of the Mac Mini,” Rassweiler said.

PGI, NVIDIA to deliver CUDA Fortran compiler

SINGAPORE: The Portland Group, a wholly-owned subsidiary of STMicroelectronics and a leading supplier of compilers for high-performance computing (HPC), today announced an agreement with NVIDIA under which the two companies plan to develop new Fortran language support for CUDA GPUs.

The NVIDIA CUDA architecture allows developers to offload computationally intensive kernels to the massively parallel GPU. Through function calls and language extensions, CUDA gives developers explicit control over the mapping of general-purpose computational kernels to GPUs as well as placement and movement of data between the x64 processor and the GPU.

The NVIDIA CUDA C compiler already provides this capability to C programmers. The CUDA Fortran compiler will provide this same level of control and optimization in a native Fortran environment from PGI.

“Fortran support for CUDA GPUs is a perfect complement to our existing roadmap for the PGI Accelerator Fortran and C compilers,” said Douglas Miles, director, The Portland Group. “It enables interoperability of PGI Fortran and CUDA C and gives PGI users a full range of options in porting and optimizing Fortran applications to leverage the power of CUDA-enabled NVIDIA GPUs.”

“The GPU computing developer community has made it clear there is a need and demand for a production-quality Fortran solution on the GPU,” said Andy Keane, general manager, Tesla GPU Computing Solutions, NVIDIA. “With their large base of Fortran developers for x64 processor-based HPC systems, PGI provides a perfect bridge for migration of production science and engineering codes from existing platforms to NVIDIA Tesla GPUs.”

The Portland Group and NVIDIA will release the Fortran language specification for CUDA GPUs at the International Conference on Supercomputing in Hamburg, Germany this week. The CUDA Fortran compiler will be added to a production release of the PGI Fortran compilers scheduled for availability in November 2009.

COMPUTEX TAIPEI shows influences on global hi-tech industry

TAIPEI, TAIWAN: On the strength of Taiwan's exceptional manufacturing and innovation competence for ICT products, COMPUTEX TAIPEI has become the best occasion for international tier-one companies to showcase their latest technologies and their strategic partnerships with local manufacturers.

At this year's COMPUTEX, several heavyweights, including Sean Maloney, Executive Vice President of Intel and Chief Sales and Marketing Officers, Jen-Hsun Huang, NVIDIA CEO, Warren East, ARM CEO, Steven Guggenheimer, Microsoft's OEM Division Corporate Vice President, Daniel Alegre, Vice President of Asia Pacific Sales & Operations for Google, and Woody Hobbs, CEO of Phoenix Technologies, all actively participates to unveil the latest technology trends.

Taiwanese companies also make endeavors to launch innovative products with leading technologies. Those enthusiastic efforts not only bring rich and splendid contents for COMPUTEX, but also demonstrate its increasing influences on global ICT industries.

New technologies drive netbook to evolve
Netbook, which has been rising quickly in past one year, is still the brightest focus at the showfloor. Characterized with a perfect combination of computing and mobile Internet as well as affordable price, lightweight, and long battery life, Netbook concept products, for sure, will be the most important force to drive the next-wave growth for hi-tech industry.

With comprehensive ecosystem and innovation capabilities, Taiwanese companies are considered the pioneers of creating Netbook market. Consequently, COMPUTEX TAIPEI has become a crucial base for international tier-one companies to seek for partnerships with local companies, in a bid to grab the enormous opportunities.

Taiwanese players trigger the Netbook revolutionary battle. And now, the competition has escalated from form factors and features to core processors such as CPUs and GPUs. For example, GPU vendor NIVIDA teams up with COMPAL Communications, IVENTEC, PEGATRON, and WISTRON to unveil 12 new high-definition MIDs (mobile Internet devices) powered by its Tegra processor.

NTEL, which has the dominating position in Netbook processor market, particularly debuts its next-generation code named "Pine Trail" Atom processor at the COMPUTEX. Through integration processing core and graphic core into one single die, the new chip will be able to help companies develop new-generation Netbooks with lighter weight and longer battery life.

To rival in the market, the Snapdragon platform developed by QUALCOMM has also gained supports from local manufacturers including ASUS, COMPAL COMMUNICATIONS, FOXCONN, HTC, INVENTEC, and WISTRON. QUALCOMM tries to reshape the traditional x86-based market landscape with its ARM-based processor. In addition, QUALCOMM and ARM also unveil the brand new concept of mobile device, Smartbook, claiming that, with all-day battery life, the new class of devices can bridge the functional divide between smartphones and laptops.

New era of diversified software technologies
Eyeing on the huge business opportunities for Netbooks, software vendors also jump on the bandwagon to compete with each other. The software giant MICROSOFT is very active during the show. It officially announces the release date of its long-waiting Windows 7 operating system at COMPUTEX TAIPEI, in an effort to assert its leading position to other vendors.

Meanwhile, the Android platform, which is backed by Google, also causes a stir at COMPUTEX. After Android has successfully moved into smartphone market, the industry is eager to know when it will be designed into Netbooks. ACER answers the question. The company takes the lead to announce at COMPUTEX that it will launch Android-based Netbook in third quarter this year. ELITEGROUP (ECS) also demonstrates a mockup of MID enabled by Android and TI OMAP3 processor.

On the other hand, processor IP core vendor MIPS TECHNOLOGIES announces at COMPUTEX the availability of MIPS architecture for Android platform. Within 60 days, optimized MIPS source code will be available, and MIPS Technologies has built up an ecosystem with partners to realize the development supports for Android.

Furthermore, the Moblin platform, which was initiated by INTEL and had finalized 2.0 version specifications in May, has also gained momentum in the industry. At the Mobiln Executive Summit held during COMPUTEX, both ACER and ASUS endorse this technology and will adopt it in various product lines. It is expected that Moblin-based Netbooks will enter the market in the short term.

Regardless of hardware or software market, we can see that a new era of sprawling technologies has quietly started at COMPUTEX TAIPEI. Consumers will benefit from more diversified choices in the future.

Turning crisis into opportunities with innovations
Even though mobile market shows greater growing momentum recently, desktop manufacturers still try to open new opportunities by launching AIO (All-in-one) PC and Nettops. In particular, in line with the introducing of MICORSOFT's Windows 7, which supports touch screen function, many companies, such as ACER, BENQ, ASUS, ECS, MSI, and GIGABYTE, display various Windows 7-enabled new products, in a bid to grab the long-expecting replacement market opportunities.

And, in traditional NB market, many local companies showcase series of ULV (ultra-low voltage) models, echoing the requirements of ultra-portable, power-saving, and affordable price. Having over 80 percent of worldwide NB shipments, Taiwanese manufacturers will soon drive the ULV NBs to the mainstream.

Sean Maloney, Executive Vice President of INTEL, mentioned in the keynote speech of COMPUTEX TAIPEI that Taiwan has made an outstanding record of shipping more than 1 billion Intel-based desktop motherboards. He recognizes that Taiwan industry has unmatched sense of urgency, cost focus built into DNA, drive for innovation, and ambition for growth, the advantages that other countries can't never surpass.

Maloney emphasizes that DT is dead is just a fallacy. Driven by the new technologies including Windows 7, HDMI, AIO PC, and Nehalem processors, Taiwanese companies will be able to create next billion DT requirements.

Many tier-one international companies such as INTEL and MICROSOFT make use of COMPUTEX TAIPEI to unveil new technologies and to seek for partnership with local manufacturers, a fact that highlights Taiwan's great advantages and influences on global ICT industries.

Many foreign heavyweights admire the optimistic atmosphere and dynamics here, as well as Taiwanese companies' confidence in turning the crisis into opportunities. With various new products and technologies launching, the impact of global financial turmoil is hardly seen at the showfloor. For the ICT industries all over the world, COMPUTEX TAIPEI is not only the No. 1 procurement platform, but also an important stage to showcase future industrial trends and the outstanding capabilities of Taiwan's hi-tech industry.

Source: ACN Newswire

NVIDIA Tegra-based devices revolutionize ‘MID’ market

COMPUTEX 2009, TAIPEI, TAIWAN: NVIDIA Corp. and industry partners today unveiled 12 new high-definition mobile Internet devices (MIDs) all powered by the NVIDIA Tegra processor, the world’s smallest and lowest power computer-on-a-chip.

These new Tegra-based devices, which include netbooks and tablets, deliver desktop-class Internet browsing with Flash video and animation acceleration, and up to 1080p video playback. NVIDIA Tegra processors feature always-on operation for instant access to the Internet, which compares to that of cell phone-class power management, and up to 5x the battery life of current netbooks—making days of HD mobile Internet experiences a reality.

“The mobile computing revolution has arrived,” stated Michael Rayfield, general manager of mobile business at NVIDIA. “These new Tegra-based products combine excellent Internet and media capabilities, always-on operation, and wireless connectivity for the untethered Internet experience consumers have been craving.”

With more than 20 Tegra-based projects currently in the works today, those attending Computex can see the following devices:

* Compal Communications, Inc. CN88 (netbook)
* ICD Ultra (tablet)
* Inventec Applications Corp. Rainbow (netbook)
* Mobinnova Mabo (tablet)
* Mobinnova ViewBook N910 (netbook)
* Pegatron Vivid (netbook)
* Wistron M5 (netbook)

“We’ve seen a groundswell of demand from consumers and telcos around the globe for a highly capable, low power, low cost netbook,” stated Mike Holland, vice president of business development, Mobinnova. “Thanks to Tegra we’ve been able to deliver that and more. With three new Tegra-based devices, we’ll be one of the first to meet that demand.”

Wireless phone carriers around the world are looking to expand the reach of the broadband Internet and agree that the always-on mobile Internet experiences enabled by Tegra-based MIDs will help drive new revenue streams and demand for 3G networks. Government programs to deliver the Internet to more people will have a greater impact since the subsidy budgets will go farther because of the lower system cost that Tegra enables. NVIDIA Tegra-based MIDs will support 3G, WiFi, and WiMax solutions from Motorola, Sierra Wireless modules based on Qualcomm, Icera, Via telesystems, and ST Ericsson to meet the needs of every carrier in every geography.

“Devices based on NVIDIA Tegra will allow us to offer a mobile Internet device that delivers an amazing level of functionality at minimal cost or even free through subsidies,” stated Antonio Domit, Executive Technology Advisor to America Movil, Grupo Carso, and Inbursa. “The combination of a Tegra-based MID and our high-speed national coverage will allow millions of people to access the Internet and have an unprecedented experience. I can imagine the story is the same for every country around the world.”

The Internet experience cannot be complete without great support for Adobe Flash, which is included in over 80 percent of the top 100 Web sites. In a separate announcement, NVIDIA announced that it has joined forces with Adobe to optimize and enable Adobe Flash to leverage the GPU (graphics processing unit) for visual computing so consumers can experience fluid Flash video and animations using a small fraction of the power needed by other netbooks. In addition to browsing Web sites with Flash, Tegra-based MIDs deliver all-day media processing, including:

* Listening to music for 25 days straight on one charge.
* Watching 1080p HD video for up to 10 hours.
* Playing video games at 46 frames per second.

The NVIDIA Tegra processor is a heterogeneous multiprocessor architecture. Each processor unit is architected for a specific class of tasks—a CPU for running html and Java, an HD video processor that makes streaming HD video playback possible on a netbook for the first time*, and an ultra-low power NVIDIA GPU for a compelling user interface and for Flash acceleration. These processors are used together or independently to deliver a wonderful experience while utilizing minimal power. With its ultra-low-power processor design, NVIDIA Tegra processors achieve up to 5 times the power efficiency of existing products in battery-operated computer systems running compelling visual computing applications.

Three NVIDIA GeForce GPUs drive world’s most powerful 17-inch Alienware notebook

SANTA CLARA, USA: Alienware, Dell’s premier high-performance PC gaming brand, unveiled today the M17x, with three NVIDIA GeForce graphics processing units (GPUs) to provide an unrivaled visual computing experience.

As a launch vehicle for the global expansion of the Alienware brand, Alienware equipped the M17x with a pair of NVIDIA GeForce GTX 280M enthusiast-class GPUs with NVIDIA SLI Technology along with the GeForce 9400M GPU to create the world’s most powerful 17-inch notebook.

“NVIDIA GeForce GPUs delivered the no compromise performance we demanded from our flagship gaming notebook,” said Arthur Lewis, general manager for Dell’s gaming group. “With the M17x, we will offer gamers in 35 countries the most innovative notebook product Alienware has ever created.”

“Alienware built the M17x specifically for gamers, and gamers want GeForce graphics,” said Rene Haas, general manager of notebook GPUs at NVIDIA. “By pushing technology and design innovation, Alienware strives to deliver the best, most immersive gaming experience possible.”

Built with the gamer in mind, the M17x pushes technology and design innovation, establishing a precedent for combining best-in-class performance with striking design. Alienware M17x laptops deliver scorching gaming performance by combining the horsepower of two discrete GeForce GTX 280M GPUs with NVIDIA SLI technology, and have the option of switching to a quiet operation mode with NVIDIA HybridPower technology.

In HybridPower operation, the powerful GTX 280M GPUs are powered down and graphics operation is transferred to the GeForce 9400M GPU to save battery life while still delivering great graphics.

Adobe and NVIDIA announce GPU acceleration for Flash Player

COMPUTEX, TAIPEI, TAIWAN: NVIDIA, the inventor of the GPU, and Adobe Systems Inc., announced that they are collaborating as part of the Open Screen Project to optimize and enable Adobe Flash Player, a key component of the Adobe Flash Platform, to leverage GPU video and graphics acceleration on a wide range of mobile Internet devices, including netbooks, tablets, mobile phones and other on-the-go media devices.

Adobe Flash Player will be accelerated across the range of NVIDIA processors, including NVIDIA Tegra, enabling users to enjoy uncompromised Web browsing, full H.264 video playback, and rich, consistent Flash technology based content any time, any place, and on any platform.

NVIDIA is also participating in the Open Screen Project, a broad initiative of 25 industry leaders to deliver a consistent runtime environment across devices.

Led by Adobe, the Open Screen Project is dedicated to enable Web content and standalone applications across desktops, netbooks, mobile devices, televisions, and other consumer electronics that take advantage of Adobe Flash Platform capabilities. For more information, visit www.openscreenproject.org.

“NVIDIA and Adobe share precisely the same vision – visually compelling applications running on every device,” said Michael Rayfield, general manager, Handheld Business at NVIDIA. “Consumers don’t have to sacrifice streaming video performance on small inexpensive platforms such as netbooks. A Tegra-based platform enables the rich, smooth playback they expect from a desktop PC.”

“NVIDIA’s unique expertise makes it an ideal partner for Adobe to integrate cutting-edge graphics and video acceleration into the Adobe Flash Platform, benefiting all types of devices,” said David Wadhwani, general manager and vice president, Platform Business Unit at Adobe. “Flash Player will leverage the power of the GPU to provide a rich, desktop-compatible Web experience on a wide range of devices.”

NVIDIA deploys Magma Talus 1.1 into production

BANGALORE, INDIA: Magma Design Automation Inc. announced that NVIDIA Corp. deployed Magma’s Talus 1.1 IC implementation system into full production.

Talus 1.1 offers significant improvements in routing, optimization and runtime as well as enhanced usability features. NVIDIA had been participating in the beta testing of the latest Talus release and, based on the positive results of the testing and improved flow performance, made the decision to start using Talus 1.1 for NVIDIA’s production design projects.

“We have recently upgraded to Talus 1.1 in our production environment based on significant improvements in the core algorithms, flow convergence and the overall usability,” said Patrick Sproule, manager of VLSI Design for NVIDIA. “In particular, the improvements in runtime, timing convergence and ECO routing have improved our throughput and quality of results.”

Magma’s unified data model is a key factor in the performance of the Talus chip implementation system. All the implementation and analysis engines in the Talus flow are built around, and have access to, the same data, and as a result flow convergence and turnaround times are shortened and optimization steps can be applied across the flow.

“We made a significant R&D investment in Talus 1.1 with the focus on improving overall performance and convergence while also improving the ease-of-use and efficiency of the system,” said Premal Buch, general manager of Magma’s Design Implementation Business Unit.

“Our customers are implementing very complex chips and need the combination of a powerful, fast, high-quality chip design system that is also easy to drive. We made a specific effort in Talus 1.1 to develop simplified flows that reduce the number of commands required, but still deliver superior results in the finished design. We are very pleased with the fact that Talus 1.1 performed so well for NVIDIA that they have moved it onto their production chip design projects.”

Talus platform
Talus is a completely unified RTL-to-GDSII system for design implementation, with advanced capabilities for nanometer design. To address shorter time-to-market windows, Talus is the first implementation solution to multi-process the entire IC design flow. Its front-end design system provides logic designers with a fast, high-capacity, physically aware synthesis capability.

Its physical design system addresses variability and multimode/multicorner complexity with new optimization, place and route, and clock tree synthesis technology. To reduce leakage and dynamic power, Talus also provides a complete low-power design system. To improve manufacturability and reliability, Talus provides built-in design-for-manufacturing (DFM) features such as redundant via insertion, recommended end-of-line extension, and wire spreading & widening.

World's first NVIDIA ION laptop changes small PCs forever!

SANTA CLARA, USA: NVIDIA Corp. and Lenovo advanced mobile computing by introducing a low-cost, small laptop that delivers up to 10 times faster graphics performance than today's small laptops.

Featuring the NVIDIA ION graphics processor, the Lenovo IdeaPad S12 offers improved application support while still providing long battery life thanks to its energy efficient design.

Lenovo used NVIDIA ION's revolutionary design to create a thin, lightweight, low-power laptop with a 12-inch screen and improved application compatibility. The Lenovo IdeaPad S12 has the graphics horsepower to support high definition media and many PC games which will not run on most low-cost small PCs. NVIDIA ION enables these capabilities with the industry's best graphics performance for low-power CPUs.

"NVIDIA ION is one of the latest technologies available for the PC industry for small, low cost laptop PCs, and we're excited to be among the first to use it," said Stephen DiFranco, vice president and general manager of consumer and commercial channels, Americas Group, Lenovo. "With its 12-inch display, full-size keyboard and rich multimedia options powered by ION, the IdeaPad S12 balances an improved computing experience along with the size and affordability many consumers are looking for today."

"The Lenovo IdeaPad S12 with NVIDIA ION graphics is a game changer for the industry," said Jeff Fisher, senior vice president of the GPU business unit at NVIDIA. "It's a powerful testament to what a small PC can do if it's optimized with ION. The thin and affordable S12 does everything you expect a PC to do including watching movies, playing games, flipping through vacation pictures or editing family videos."

NVIDIA ION graphics support:

* All versions of Windows XP, Vista, and Windows 7.
* Outstanding HD video including 1080p and Blu-ray movies.
* Stunning HD video through an external monitor via HDMI.
* Popular games including Spore and Battlefield Heroes.
* DirectX 10 graphics with advanced digital display connectivity.
* Accelerated video enhancement and conversion using NVIDIA CUDA technology

The Lenovo IdeaPad S12 with the NVIDIA ION graphics processor is expected to be available later this summer.

Chaos reigns in Top 20 semiconductor company rankings

USA: The global recession and subsequent inventory corrections in the electronic system and semiconductor industries have caused a major shakeup in the 1Q09 top 20 semiconductor company ranking (Fig. 1). As discussed in detail in IC Insights' May Update to The McClean Report, the volatility in the ranking is forecast to continue in 2Q09. Many top semiconductor suppliers are expected to rebound from a weak 1Q09 to register strong double-digit 2Q09/1Q09 sequential sales growth!

Of the top 20 companies in 1Q09, only Intel (#1), Samsung (#2), and Fujitsu (#17) remained in the same positions as they ranked in 2008. Some notable changes to the top 20 ranking are shown below.Climbers:

Qualcomm — The world's largest fabless IC supplier, which focuses on leading-edge cellphone devices, moved from being ranked 8th in 2008 to 6th in 1Q09. IC Insights anticipates increasingly positive news for Qualcomm as high-end cellphone (e.g., smartphone) sales pick up speed throughout 2009.

AMD — Jumped into the top 10 group, moving up three spots from 12th in 2008 to 9th in 1Q09. However, AMD is one of the few top semiconductor companies that has stated it expects 2Q09 sales to be worse than in 1Q09. How long will it stay in the top 10?

MediaTek — High-flying fabless IC supplier MediaTek joined the top 20 ranking by jumping five positions. In fact, MediaTek was the only top 20 semiconductor supplier to register a 1Q09/4Q08 sequential sales increase, a whopping 16% surge! The company attributed part of its success to the "stay-at-home-economy" driving digital TV IC sales as well as continued strength in its core wireless communications business.

Decenders:

TSMC — The largest foundry in the world dropped six positions in the 1Q09 ranking but managed to stay in the top 10. It is well known that fabless IC suppliers are some of the worst offenders with regard to IC inventory builds and burns. With fabless companies representing the bulk of TSMC's sales, the company has been caught in a hellacious two-quarter inventory burn period (4Q08 and 1Q09), with 1Q09 sales 57% less than were registered in 3Q08!

However, the anticipated recovery in TSMC's sales will be one of the most significant rebounds witnessed in the IC industry this year. Using current exchange rates, it is expected that TSMC's 2Q09 sales will be about $2.2 billion, a sequential increase of 89%! Moreover, IC Insights believes that if this level of sales is achieved next quarter, it would serve to rank TSMC as the third largest semiconductor supplier in the world in 2Q09!

NXP and Nvidia — These two companies fell out of the top 20 ranking in 1Q09, with NXP falling from being ranked 15th in 2008 to 21st in 1Q09 and Nvidia dropping from 20th to 22nd. However, IC Insights expects a significant rebound in both of these companies' sales in 2Q09, maybe even enough to put them back into the top 20!

The May Update to The McClean Report examines the top 20 semiconductor company ranking changes in more detail and incorporates company guidance in addition to IC Insights' own estimates to forecast the major ranking changes expected for 2Q09. Moreover, further details on the top 20 semiconductor suppliers as well as an additional 200 suppliers can also be found in IC Insights' Strategic Reviews Online database.

Source: IC Insights

NVIDIA adopts Synopsys IC Validator for sign-off physical verification

MOUNTAIN VIEW, USA: Synopsys Inc. announced that NVIDIA has adopted Synopsys' recently announced IC Validator physical verification solution.

The IC Validator DRC/LVS solution has been specifically developed for advanced designs at 45nm and below to offer in-design physical verification as well as signoff. As the inventor of the Graphics Processing Unit (GPU) and the world leader in visual computing technologies, NVIDIA designs multi-billion transistor processors that require the highest level of tool performance and productivity. By achieving near-linear scalability, such as the 20x speedup observed by NVIDIA using 25 CPUs, IC Validator provides accelerated time to tapeout.

"We continue to push design complexity to meet our customers' visual computing needs. To validate such large designs in a timely fashion, we require a high-performance, high-capacity physical verification engine. IC Validator demonstrated that we can verify our largest designs overnight using our standard hardware configurations," said James Chen, manager of VLSI technology at NVIDIA. "In addition, the flexibility offered by IC Validator's highly programmable language will help us customize design flows to improve productivity. Working closely with our foundry partners, we are deploying IC Validator for our designs."

IC Validator has been architected to address the challenges physical designers of complex designs at advanced process nodes face today. IC Validator delivers the high accuracy necessary for leading-edge process nodes, excellent scalability for efficient utilization of available hardware, superior ease-of-use for the physical designer, and high programmability for easier runset development.

The solution deploys intelligent auto detection techniques to identify available hardware resources by taking advantage of existing compute job scheduler configurations. This includes configuring an intelligent mix of distributed processing and multithreading to provide the industry's best scalability without special hardware setup.

For the runset writers and CAD managers, IC Validator offers a flexible programming language that can cut runset size from 2-10x, lowering the cost of setting up, maintaining and modifying the physical verification environment.

Already in production at a world-leading IDM and qualified at leading foundries, IC Validator offers incremental capabilities, significant automation and innovative features such as DRC error classification, multi-user collaboration, customized reporting and on-the-fly error reporting.

"As a leading semiconductor company focused on cutting-edge designs, NVIDIA has repeatedly set the bar for physical verification tool performance, capacity and programmability," said Antun Domic, senior vice president and general manager, Implementation Group at Synopsys. "NVIDIA's adoption of IC Validator is a significant endorsement of its benefits and Synopsys' technology addressing the requirements for the industry's most advanced designs."