| Type | Public NASDAQ: XLNX S&P 500 Component |
|---|---|
| Industry | Integrated Circuits |
| Founded | 1984 |
| Founder(s) | Jim Barnett Ross Freeman Bernie Vonderschmitt |
| Headquarters | San Jose, CA, USA |
| Area served | Worldwide |
| Key people | Philip T. Gianos Chairman of the Board Moshe N. Gavrielov President CEO Director |
| Products | FPGAs, CPLDs |
| Revenue | $ 1.825 billion - 2008 |
| Operating income | $ 486 million - 2008 |
| Net income | $ 375.64 million - 2008 |
| Total assets | $ 2.825 billion - 2008 |
| Total equity | $ 1.737 billion - 2008 |
| Employees | 3,145 - September 2009 |
| Website | Xilinx.com |
Xilinx, Inc. (NASDAQ: XLNX) ( /ˈzaɪlɪŋks/ zy-lingks) is a supplier of programmable logic devices. It is known for inventing the field programmable gate array (FPGA) and as the first semiconductor company with a fabless manufacturing model.[1][2][3]
Founded in Silicon Valley in 1984, the company is headquartered in San Jose, California, U.S.A.; Dublin, Ireland; Singapore; and Tokyo, Japan. The company has corporate offices throughout North America, Asia and Europe.[4]
Contents |
Xilinx was founded in 1984 by two semiconductor engineers, Ross Freeman and Bernard Vonderschmitt, who were both working for integrated circuit and solid-state device manufacturer Zilog Corp.[4][5]
While working for Zilog, Freeman wanted to create chips that acted like a blank tape, allowing users to program the technology themselves. At the time, the concept was paradigm-changing.[5] "The concept required lots of transistors and, at that time, transistors were considered extremely precious – people thought that Ross's idea was pretty far out", said Xilinx Fellow Bill Carter, who when hired in 1984 as the first IC designer was the company's eighth employee.[5]
Big semiconductor manufacturers were enjoying strong profits by producing massive volumes of generic circuits.[4] Designing and manufacturing dozens of different circuits for specific markets offered lower profit margins and required greater manufacturing complexity.[4] What became known as the FPGA would allow circuits produced in quantity to be tailored by individual market segments.
Freeman failed to convince Zilog to invest in creating the FPGA to chase what was only a $100 million market at the time.[4] Freeman left Zilog and teamed up with his 60-year-old ex-colleague Bernard Vonderschmitt to raise millions in venture funding to design the first commercially viable FPGA.[4] The company was incorporated in 1984 and began selling its first product by 1985.[4]
By late 1987, the company had raised more than $18 million in venture capital (worth approximately $33 million in 2010 dollars adjusted for inflation) and generated revenues at an annualized rate of nearly $14 million.[4][6]
As demand for programmable logic continued to grow, so did Xilinx's revenues and profits.[4]
From 1988 to 1990, the company's revenue grew each year from $30 million to $50 million to $100 million.[4] During this time period, funding provider Monolithic Memories Inc. (MMI) was purchased by Xilinx competitor AMD.[4] As a result of the AMD acquisition, Xilinx dissolved the deal with MMI and went public on the NASDAQ in 1989.[4] The company also moved to a 144,000-square-foot (13,400 m2) plant in San Jose, California in order to keep pace with demand from companies like HP, Apple Inc., IBM and Sun Microsystems who were buying large quantities from Xilinx.[4]
Xilinx competitors emerged in the FPGA market in the mid-1990s.[4] Despite the competition, Xilinx’s sales grew to $135 million in 1991, $178 million in 1992 and $250 million in 1993.[4]
The company reached $550 million in revenue in 1995, one decade after having sold its first product.[4]
According to market research firm iSuppli, Xilinx has led the programmable logic device market share since the late 1990s. Over the years, Xilinx expanded operations to India, Asia and Europe.[7][8][9][10]
Xilinx's sales rose from $560 million in 1996 to nearly $2 billion by the end of its fiscal year 2010.[11] Moshe Gavrielov – an EDA and ASIC industry veteran who was appointed as president and CEO in early 2008 – introduced targeted design platforms to provide solutions that combine FPGAs with software, IP cores, boards and kits to address focused target applications.[12] These targeted design platforms are an alternative to costly application-specific integrated circuits (ASICs) and application-specific standard products (ASSPs).[13][14][15]
The company has expanded its product portfolio since its founding. Xilinx sells a broad range of FPGAs, complex programmable logic devices (CPLD), design tools, intellectual property and reference designs.[1] Xilinx also has a global services and training program.[1]
The company's products have been recognized by EE Times, EDN and others for innovation and market impact.[16][17][18]
Xilinx product lines (see Current Family Lines) include the Virtex, Kintex and Artix series, each including configurations and models optimized for different applications.[19] With the introduction of the Xilinx 7 Series in June, 2010, the company has moved to three major product families, the high-end Virtex, the mid-range Kintex family and the low-cost Artix family, retiring the Spartan brand, which ends with the Xilinx Series 6 FPGAs.[20][21]
Xilinx designs, develops and markets programmable logic products including integrated circuits (ICs), software design tools, predefined system functions delivered as intellectual property (IP) cores, design services, customer training, field engineering and technical support.[1] Xilinx sells both FPGAs and CPLDs programmable logic devices for electronic equipment manufacturers in end markets such as communications, industrial, consumer, automotive and data processing.[22][23][24][25][26][27][28]
Xilinx's FPGAs have been used for the ALICE (A Large Ion Collider Experiment) at the CERN European laboratory on the French-Swiss border to map and disentangle the trajectories of thousands of subatomic particles.[29] Xilinx has also engaged in a partnership with the United States Air Force Research Laboratory’s Space Vehicles Directorate to develop FPGAs to withstand the damaging effects of radiation in space for deployment in new satellites, which are 1,000 times less sensitive to space radiation than the commercial equivalent.[30]
The Virtex-II Pro, Virtex-4, Virtex-5, and Virtex-6 FPGA families are focused on system-on-chip (SoC) designers because they include up to two embedded IBM PowerPC cores.[31][32][33] Some members of the Virtex-II Pro, Virtex-4 and Virtex-5 FPGA families contain PowerPC processor blocks.
Xilinx FPGAs can run a regular embedded OS (such as Linux or vxWorks) and can implement processor peripherals in programmable logic.[1]
Xilinx's IP cores include IP for simple functions (BCD encoders, counters, etc.), for domain specific cores (digital signal processing, FFT and FIR cores) to complex systems (multi-gigabit networking cores, MicroBlaze soft microprocessor, and the compact Picoblaze microcontroller).[1] Xilinx also creates custom cores for a fee.
The ISE Design Suite is the central electronic design automation (EDA) product family sold by Xilinx. The ISE Design Suite features include design entry and synthesis supporting Verilog or VHDL, place-and-route (PAR), completed verification and debug using ChipScope Pro tools, and creation of the bit files that are used to configure the chip.[1][34]
Xilinx's Embedded Developer's Kit (EDK) supports the embedded PowerPC 405 and 440 cores (in Virtex-II Pro and some Virtex-4 and -5 chips) and the Microblaze core. Xilinx's System Generator for DSP implements DSP designs on Xilinx FPGAs. A freeware version of its EDA software called ISE WebPACK is used with some of its non-high-performance chips. Xilinx is the only (as of 2007) FPGA vendor to distribute a native Linux freeware synthesis toolchain.[35]
Xilinx announced the architecture for an Extensible Processing Platform, which licenses the ARM Cortex-A9 MPCore processor for embedded systems designers familiar with the ARM platform.[36][37][38][39] The Extensible Processing Platform architecture abstracts much of the hardware burden away from the embedded software developers' point of view, giving them an unprecedented level of control in the development process.[36][37][38][39] With this platform, software developers can leverage their existing system code based on ARM technology and utilize vast off-the-shelf open-source and commercially available software component libraries.[36][37][38][39] Because the system boots an OS at reset, software development can get under way quickly within familiar development and debug environments using tools such as ARM’s RealView development suite and related third-party tools, Eclipse-based IDEs, GNU, the Xilinx Software Development Kit and others.[36][37][38][39] The platform targets embedded designers working on market applications that require multifunctionality and real-time responsiveness, such as automotive driver assistance, intelligent video surveillance, industrial automation, aerospace and defense, and next-generation wireless.[36][37][38][39] Xilinx announced, in early 2011, a new Zynq product family specifically based on its extensible processing platform.[40][41]
Following the introduction of its 28 nm 7-series FPGAs, Xilinx revealed that that several of the highest-density parts in those FPGA product lines will be constructed using multiple dice in one package, employing technology developed for 3D construction and stacked-die assemblies.[42][43] The technology stacks several (three or four) active FPGA dice side-by-side on a silicon interposer – a single piece of silicon that carries passive interconnect. The individual FPGA dice are conventional, and are flip-chip mounted by microbumps on to the interposer. The interposer provides direct interconnect between the FPGA dice, with no need for transceiver technologies such as high-speed SERDES.[42][43][44] In October 2011, Xilinx shipped the first FPGA to use the new technology, the Virtex-7 2000T FPGA, which includes 6.8 billion transistors and 20 million ASIC gates.[45][46][47][48]
In January 2011, Xilinx acquired design tool firm AutoESL Design Technologies to add System C high level design to its 6- and 7-series FPGA families.[49] The addition of AutoESL tools expands the design community for FPGAs with designers more accustomed to designing at a higher level of abstraction in C, C++ and System C.[50]
Prior to 2010, Xilinx has offered two main FPGA families: the high-performance Virtex series and the high-volume Spartan series, with a cheaper EasyPath option for ramping to volume production.[19] The company also provides two CPLD lines, the CoolRunner and the 9500 series. Each model series has been released in multiple generations since its launch.[51] With the introduction of its 28 nm FPGAs in June 2010, Xilinx replaced the high-volume Spartan family with a Kintex family and the low-cost Artix family.[20][21]
In newer FPGA products, Xilinx minimized total power consumption by adopting a high-K metal gate (HKMG) process which allows for low static power consumption. At the 28 nm node, static power is a significant portion of the total power dissipation of a device and in some cases is the dominant factor. Through the use of a HKMG process, Xilinx has reduced power use while increasing logic capacity.[52] Virtex-6 and Spartan-6 FPGA families are said to consume 50 percent less power, and have up to twice the logic capacity compared to the previous generation of Xilinx FPGAs.[32][53][54]
In June, 2010 Xilinx introduced the Xilinx 7 series, the Virtex-7, Kintex-7, and Artix-7 families, promising improvements in system power, performance, capacity, and price. These new FPGA families are manufactured using TSMC's 28 nm HKMG process.[55] The 28-nm series 7 devices feature a 50 percent power reduction compared to the company's 40-nm devices and offer capacity of up to 2 million logic cells.[20] In March 2011, Xilinx introduced the Zynq-7000 family, which integrates a complete ARM Cortex-A9 MPCore processor-based system on a 28 nm FPGA for system architects and embedded software developers.[40][41]
The Virtex series of FPGAs have integrated features that include FIFO and ECC logic, DSP blocks, PCI-Express controllers, Ethernet MAC blocks, and high-speed transceivers. In addition to FPGA logic, the Virtex series includes embedded fixed function hardware for commonly used functions such as multipliers, memories, serial transceivers and microprocessor cores.[56] These capabilities are used in applications such as wired and wireless infrastructure equipment, advanced medical equipment, test and measurement, and defense systems.[57] Some Virtex family members are available in radiation-hardened packages, specifically to operate in space where harmful streams of high-energy particles can play havoc with semiconductors. The Virtex-5QV FPGA was designed to be 100 times more resistant to radiation than previous radiation-resistant models and offers a ten-fold increase in performance. However, characterization and test data were not yet available for the Virtex-5QX on the Xilinx Radiation Test Consortium website as of November 2011. [58]
Xilinx's most recently announced Virtex, the Virtex 7 family, is based on a 28 nm design and is reported to deliver a two-fold system performance improvement at 50 percent lower power compared to previous generation Virtex-6 devices. In addition, Virtex-7 doubles the memory bandwidth compared to previous generation Virtex FPGAs with 1866 Mb/s memory interfacing performance and over two million logic cells.[20][21]
In 2011, Xilinx began shipping sample quantities the Virtex-7 2000T FPGA that packages four smaller FPGAs into a single chip by placing them on a special silicon communications pad called an interposer to deliver 6.8 billion transistors in a single large chip. The interposer provides 10,000 data pathways between the individual FPGAs – roughly 10 to 100 times more than usually would be available on a board – to create a single FPGA. This approach allows the FPGA to conserve power, drawing 20 watts of power or less.[45][46][47]
This approach allows the Virtex-7 2000T FPGA to exceed Moore’s Law – Intel co-founder Gordon Moore’s prediction that the number of those transistors will double roughly every two years – by providing twice the number of transistors in a single FPGA than would be expected under the prediction. In comparison, Intel’s largest chips have about 2.6 billion transistors.[45][46][47]
The Virtex-6 family is built on a 40 nm process for compute-intensive electronic systems, and the company claims it consumes 15 percent less power and has 15 percent improved performance over competing 40 nm FPGAs.[59]
The Virtex-5 LX and the LXT are intended for logic-intensive applications, and the Virtex-5 SXT is for DSP applications.[60] With the Virtex-5, Xilinx changed the logic fabric from four-input LUTs to six-input LUTs. With the increasing complexity of combinational logic functions performed by SoC, the percentage of combinational paths requiring multiple four-input LUTs became a performance and routing bottleneck. The new six-input LUT represented a tradeoff between better handling of increasingly complex combinational functions, at the expense of a reduction in the absolute number of LUTs per device. The Virtex-5 series is a 65 nm design fabricated in 1.0 V, triple-oxide process technology.[61]
Legacy Virtex devices (Virtex, Virtex-II, Virtex-II Pro, Virtex 4) are still available, but are not recommended for use in new designs.
The Kintex-7 family is the first Xilinx mid-range FPGA family that the company claims delivers Virtex-6 family performance at less than half the price while consuming 50 percent less power. The Kintex family includes high-performance 10.3 Gbit/s or lower-cost optimized 6.5 Gbit/s serial connectivity, memory, and logic performance required for applications such as high volume 10G optical wired communication equipment, and provides a balance of signal processing performance, power consumption and cost to support the deployment of Long Term Evolution (LTE) wireless networks.[20][21]
The Artix-7 family delivers 50 percent lower power and 35 percent lower cost compared to the Spartan-6 family and is based on the unified Virtex-series architecture. Xilinx claims that Artix-7 FPGAs deliver the performance required to address cost-sensitive, high-volume markets previously served by ASSPs, ASICs, and low-cost FPGAs. The Artix family is designed to address the small form factor and low power performance requirements of battery-powered portable ultrasound equipment, commercial digital camera lens control, and military avionics and communications equipment.[20][21]
The Zynq 7000 family incorporates an extensible processing platform into devices to address high-end embedded-system applications, such as video surveillance, automotive-driver assistance, next-generation wireless, and factory automation.[40][41][62] Zync-7000 FPGAs integrate a complete ARM Cortex-A9 MPCore-processor-based 28-nm system. The Zynq architecture differs from previous marriages of programmable logic and embedded processors by moving from an FPGA-centric platform to a processor-centric model.[40][41][62] For software developers, Zynq FPGAs appear the same as a standard, fully featured ARM processor-based system-on-chip (SOC) that boots immediately at power-up and can run a variety of operating systems independently of the programmable logic.[40][41][62]
The Spartan series targets applications with a low-power footprint, extreme cost sensitivity and high-volume; e.g. displays, set-top boxes, wireless routers and other applications.[63]
The Spartan-6 family is built on a 45-nanometer [nm], 9-metal layer, dual-oxide process technology.[53][64] The Spartan-6 was marketed in 2009 as a low-cost solution for automotive, wireless communications, flat-panel display and video surveillance applications.[64]
Because EasyPath devices are identical to the FPGAs that customers are already using, the parts can be produced faster and more reliably from the time they are ordered compared to similar competing programs.[65]
A 12-week time is guaranteed from receiving the design to mass production, and no redesign or re-qualification are required by the customer. In addition, customers are free to return from the non-programmable EasyPath FPGA production to original programmable Virtex FPGA production if the need for design changes arises.
Xilinx CEO Gavrielov plans to grow the company by providing more complete solutions to Xilinx customers that combine FPGA technology with IP cores, EDA tools and boards and kits to take a share of the ASIC and ASSP markets.[66] As of 2009, the cost of entry for an ASIC design is growing out of the price range for many applications, which makes FPGAs – which require much less development – a more viable option.[66] Gavrielov refers to a market trend he calls the Programmable Imperative that places shrinking design cycles against the time and cost of ASIC design.[67]
Xilinx joined the Fortune ranks of the "100 Best Companies to Work For" in 2001 as No. 14, rose to No. 6 in 2002 and rose again to No. 4 in 2003.[68]
In December 2008, GSA named Xilinx the Most Respected Public Semiconductor Company with $500 million to $10 billion in annual sales. The award recognizes excellence through success, vision and strategy in the industry.[69]
Having tried to register a number of more conventional company-names and having them rejected as already taken, the founders decided to deliberately create an unusual name in order to ensure that the name was accepted. Several legends explain the origin of the name. Xilinx Fellow Bill Carter said that the name Xilinx was chosen because "The chemical symbol for silicon is Si. The 'X's at each end represent programmable logic blocks. The "linx" represents programmable links that connect the logic blocks together."[5] Another explanation has it that two of the founders, Ross Freeman and Jim Barnett both attended the University of Illinois at Urbana–Champaign, also called the Fighting Illini. The name allegedly originated because the company founders were two ex-Illini, hence Xilinx (two 'X' Illini).
Ross Freeman, credited with the invention of the FPGA, was inducted into the National Inventor's Hall of Fame in 2009, more than 20 years after the invention of the FPGA.[70] Starting in 1992, Xilinx has had an annual tradition of awarding a company employee with the Ross Freeman Award for Technical Innovation in Freeman's memory. Award honorees are based on nominations for innovations that resulted in significant tangible benefit to the company. Finalists are chosen by a committee and winners are selected based on a vote.[70]
During the "tech boom years," competitor Altera was the market leader.[3][71] Today, Xilinx customers represent just over half of the entire programmable logic market, at 51%.[1][2][71] Altera is Xilinx's strongest competitor with 34% of the market. Other key players in this market are Actel and Lattice Semiconductor.