Weitek

Last updated
Weitek Corporation
Company typePrivate
IndustrySemiconductors
Founded1981
Defunct1996
Fate1996 acquired by Rockwell's Semiconductor Systems
Headquarters San Jose, California
Productsmicroprocessors, chipset
Weitek 4167 for i486-based computers KL Weitek 4167.jpg
Weitek 4167 for i486-based computers
Architecture of Weitek's WTL 1167 Weitek WTL1167 arch.svg
Architecture of Weitek's WTL 1167
Weitek SPARC Power mP KL Weitek SPARC Power uP.jpg
Weitek SPARC Power μP
Weitek Power9100 Weitek Power9100 PCI.jpg
Weitek Power9100

Weitek Corporation was an American chip-design company that originally focused on floating-point units for a number of commercial CPU designs. During the early to mid-1980s, Weitek designs could be found powering a number of high-end designs and parallel-processing supercomputers.

Contents

Weitek started in 1981, when several Intel engineers left to form their own company. Weitek developed math coprocessors for several systems, including those based on the Motorola 68000 family, the WTL 1064 and 1164, [1] and for Intel-based i286 systems, the WTL 1067[ citation needed ]. The 1067 was physically implemented as three chips, the WTL 1163, 1164 and 1165. [2] [3] When Intel's own FPU design for the i386 fell far behind in development, Weitek delivered the 1167 for them in the form of a daughtercard. Improvements in chip manufacturing allowed this to be reduced to a single-chip version, the WTL 2167[ citation needed ]. The WTL 3167 of 1988, also known as the Abacus, extended the system for use in Intel 80386 systems, [4] and finally the WTL 4167 in 1989 for the Intel 80486 which used the 486's larger socket format and ran at higher clock rates than the 3167 to provide higher performance arrount 4 MFLOPS in single precision. [5]

Weitek would later outfit FPUs to the early SPARC architecture such as the 3170 and 3172. [6] Weitek FPUs had several differences compared to x87 offerings, lacking extended double precision but having a register-file rather than a stack-based model, or using memory-mapped I/O as opposed to port-mapped I/O. [7] [8]

As orders increased for supercomputer applications, Weitek found themselves seriously disadvantaged by their fab, which was becoming rather outdated. HP approached them with a deal to use their newer fabs. This proved advantageous for both, and soon HP's fabs were open to anyone. Weitek also worked with HP on the design of their latest PA-RISC design and sold their version known as the XL-RISC 8200, which was sold as an embedded design and had some use in laser printers. In these roles, the company referred to the systems as "HyperScript Processor"s, referring to the PostScript rendering engine. [9]

In the late 1980s Weitek saw a new opportunity and started developing frame buffers for Sun Microsystems workstations. In the early 1990s they also introduced the SPARC POWER μP (as in "power-up"), a pin-compatible version of the SPARC processor. The μP could be dropped into existing SPARCstation 2 and SPARCstation IPX workstations and ran at 80 MHz, double the clock speed of the CPUs it replaced. [10] The chip ran twice as fast internally, providing a boost of about 50–60% in overall speed, due to the bus not getting any faster. However, they did not pursue this concept with later generations of SPARC processors.

Weitek turned their frame-buffer experience to the PC market in the early 90s and introduced a series of SVGA multimedia chipsets known as the "POWER" systems. Consisting of two chips, one drawing the graphics known as the P9000 and another handling the output, the VideoPower 5x86, the POWER series was used in a number of third-party designs based on the VESA Local Bus standard. [11] The P9001 moved to PCI and became fairly popular in 1994, known as the Viper in designs from Diamond and Orchid. The final generation, the P9100, combined the P9001 and 5286 into a single chip. Weitek adapters were fairly successful in the early days of the 486 market, but fell from use when less expensive systems were introduced by a host of new players in the mid-1990s. A couple of versions were also released for the Amiga and used its ReTargetable Graphics standard. [12]

During the early 1990s, most CPU designs started including FPUs built into the system, basically "for free", and Weitek made a series of attempts to re-enter the low-end CPU and graphics driver market with their W464 (486) and W564 (P5) systems, which used the host machine's RAM as the frame buffer to lower costs. By 1995, the company was almost dead, and in late 1996, Rockwell's Semiconductor Systems purchased the remains and quickly disappeared. [13]

See also

Related Research Articles

i386 32-bit microprocessor by Intel

The Intel 386, originally released as the 80386 and later renamed i386, was the first x86 32-bit microprocessor designed by Intel. Pre-production samples of the 386 were released to select developers in 1985, while mass production commenced in 1986. The processor was a significant evolution in the x86 architecture, extending a long line of processors that stretched back to the Intel 8008. The 386 was the central processing unit (CPU) of many workstations and high-end personal computers of the time. The 386 began to fall out of public use starting with the release of the i486 processor in 1989, while in embedded systems the 386 remained in widespread use until Intel finally discontinued it in 2007.

i486 Successor to the Intel 386

The Intel 486, officially named i486 and also known as 80486, is a microprocessor introduced in 1989. It is a higher-performance follow-up to the Intel 386. It represents the fourth generation of binary compatible CPUs following the 8086 of 1978, the Intel 80286 of 1982, and 1985's i386.

<span class="mw-page-title-main">Pentium (original)</span> Intel microprocessor

The Pentium is a microprocessor introduced by Intel on March 22, 1993. It is the first CPU using the Pentium brand. Considered the fifth generation in the x86 (8086) compatible line of processors, succeeding the i486, its implementation and microarchitecture was internally called P5.

<span class="mw-page-title-main">Reduced instruction set computer</span> Processor executing one instruction in minimal clock cycles

In electronics and computer science, a reduced instruction set computer (RISC) is a computer architecture designed to simplify the individual instructions given to the computer to accomplish tasks. Compared to the instructions given to a complex instruction set computer (CISC), a RISC computer might require more instructions in order to accomplish a task because the individual instructions are written in simpler code. The goal is to offset the need to process more instructions by increasing the speed of each instruction, in particular by implementing an instruction pipeline, which may be simpler to achieve given simpler instructions.

x86 Family of instruction set architectures

x86 is a family of complex instruction set computer (CISC) instruction set architectures initially developed by Intel, based on the 8086 microprocessor and its 8-bit-external-bus variant, the 8088. The 8086 was introduced in 1978 as a fully 16-bit extension of 8-bit Intel's 8080 microprocessor, with memory segmentation as a solution for addressing more memory than can be covered by a plain 16-bit address. The term "x86" came into being because the names of several successors to Intel's 8086 processor end in "86", including the 80186, 80286, 80386 and 80486. Colloquially, their names were "186", "286", "386" and "486".

The NS32000, sometimes known as the 32k, is a series of microprocessors produced by National Semiconductor. Design work began around 1980 and it was announced at the International Solid-State Circuits Conference in April 1981.

<span class="mw-page-title-main">Floating-point unit</span> Part of a computer system

A floating-point unit (FPU), numeric processing unit (NPU), colloquially math coprocessor, is a part of a computer system specially designed to carry out operations on floating-point numbers. Typical operations are addition, subtraction, multiplication, division, and square root. Some FPUs can also perform various transcendental functions such as exponential or trigonometric calculations, but the accuracy can be low, so some systems prefer to compute these functions in software.

The 88000 is a RISC instruction set architecture developed by Motorola during the 1980s. The MC88100 arrived on the market in 1988, some two years after the competing SPARC and MIPS. Due to the late start and extensive delays releasing the second-generation MC88110, the m88k achieved very limited success outside of the MVME platform and embedded controller environments. When Motorola joined the AIM alliance in 1991 to develop the PowerPC, further development of the 88000 ended.

<span class="mw-page-title-main">Workstation</span> High-end single-user computer

A workstation is a special computer designed for technical or scientific applications. Intended primarily to be used by a single user, they are commonly connected to a local area network and run multi-user operating systems. The term workstation has been used loosely to refer to everything from a mainframe computer terminal to a PC connected to a network, but the most common form refers to the class of hardware offered by several current and defunct companies such as Sun Microsystems, Silicon Graphics, Apollo Computer, DEC, HP, NeXT, and IBM which powered the 3D computer graphics revolution of the late 1990s.

The Intel i860 is a RISC microprocessor design introduced by Intel in 1989. It is one of Intel's first attempts at an entirely new, high-end instruction set architecture since the failed Intel iAPX 432 from the beginning of the 1980s. It was the world's first million-transistor chip. It was released with considerable fanfare, slightly obscuring the earlier Intel i960, which was successful in some niches of embedded systems. The i860 never achieved commercial success and the project was terminated in the mid-1990s.

<span class="mw-page-title-main">Cyrix</span> American microprocessor developer

Cyrix Corporation was a microprocessor developer that was founded in 1988 in Richardson, Texas, as a specialist supplier of floating point units for 286 and 386 microprocessors. The company was founded by Tom Brightman and Jerry Rogers.

<span class="mw-page-title-main">Pentium Pro</span> Sixth-generation x86 microprocessor by Intel

The Pentium Pro is a sixth-generation x86 microprocessor developed and manufactured by Intel and introduced on November 1, 1995. It introduced the P6 microarchitecture and was originally intended to replace the original Pentium in a full range of applications. Later, it was reduced to a more narrow role as a server and high-end desktop processor. The Pentium Pro was also used in supercomputers, most notably ASCI Red, which used two Pentium Pro CPUs on each computing node and was the first computer to reach over one teraFLOPS in 1996, holding the number one spot in the TOP500 list from 1997 to 2000.

<span class="mw-page-title-main">Coprocessor</span> Type of computer processor

A coprocessor is a computer processor used to supplement the functions of the primary processor. Operations performed by the coprocessor may be floating-point arithmetic, graphics, signal processing, string processing, cryptography or I/O interfacing with peripheral devices. By offloading processor-intensive tasks from the main processor, coprocessors can accelerate system performance. Coprocessors allow a line of computers to be customized, so that customers who do not need the extra performance do not need to pay for it.

<span class="mw-page-title-main">Am386</span> AMD microprocessor clone

The Am386 CPU is a 100%-compatible clone of the Intel 80386 design released by AMD in March 1991. It sold millions of units, positioning AMD as a legitimate competitor to Intel, rather than being merely a second source for x86 CPUs.

NexGen, Inc. was a private semiconductor company based in Milpitas, California, that designed x86 microprocessors until it was purchased by AMD in 1996. NexGen was a fabless design house that designed its chips but relied on other companies for production. NexGen's chips were produced by IBM's Microelectronics division in Burlington, Vermont alongside PowerPC and DRAM parts.

<span class="mw-page-title-main">RapidCAD</span>

RapidCAD is a specially packaged Intel 486DX and a dummy floating point unit (FPU) designed as pin-compatible replacements for an Intel 80386 processor and 80387 FPU. Because the i486DX has a working on-chip FPU, a dummy FPU package is supplied to go in the Intel 387 FPU socket. The dummy FPU is used to provide the FERR signal, necessary for compatibility purposes.

<span class="mw-page-title-main">AMD Am29000</span> Family of RISC microprocessors and microcontrollers

The AMD Am29000, commonly shortened to 29k, is a family of 32-bit RISC microprocessors and microcontrollers developed and fabricated by Advanced Micro Devices (AMD). Based on the seminal Berkeley RISC, the 29k added a number of significant improvements. They were, for a time, the most popular RISC chips on the market, widely used in laser printers from a variety of manufacturers.

x87 is a floating-point-related subset of the x86 architecture instruction set. It originated as an extension of the 8086 instruction set in the form of optional floating-point coprocessors that work in tandem with corresponding x86 CPUs. These microchips have names ending in "87". This is also known as the NPX. Like other extensions to the basic instruction set, x87 instructions are not strictly needed to construct working programs, but provide hardware and microcode implementations of common numerical tasks, allowing these tasks to be performed much faster than corresponding machine code routines can. The x87 instruction set includes instructions for basic floating-point operations such as addition, subtraction and comparison, but also for more complex numerical operations, such as the computation of the tangent function and its inverse, for example.

<span class="mw-page-title-main">R3000</span> RISC microprocessor

The R3000 is a 32-bit RISC microprocessor chipset developed by MIPS Computer Systems that implemented the MIPS I instruction set architecture (ISA). Introduced in June 1988, it was the second MIPS implementation, succeeding the R2000 as the flagship MIPS microprocessor. It operated at 20, 25 and 33.33 MHz.

Since 1985, many processors implementing some version of the MIPS architecture have been designed and used widely.

References

  1. "Sun Floating Point Accelerator" . Retrieved 2020-04-18.
  2. Intel Corporation, "NewsBit: Daisy And Weitek Provide 80386 Support", Solutions, January/February 1986, Page 1
  3. achtung049, "Guide to Weitek chips, need little help", CPU-World, 2015-08-09 07:38:27. Retrieved 2022-2-24.
  4. WTL 3167 FLOATING-POINT COPROCESSOR (PDF). Weitek. September 1988.
  5. WTL 3167 Floating-Point Coprocessor (PDF). Weitek. July 1989.
  6. "Weitek FPUs at cpu-collection.de" . Retrieved 2020-04-18.
  7. "WTL 3167 FLOATING POINT COPROCESSOR PRELIMINARY DATA" (PDF). September 1988. Retrieved 2017-02-14.
  8. "EVERYTHING YOU ALWAYS WANTED TO KNOW ABOUT MATH COPROCESSORS" (text). Retrieved 2020-04-18.
  9. "Weitek Offers Fast RISC Raster CPUs For Laser Printers". Electronic News. 24 May 1988.
  10. "Enterprise Services FE Handbook" (PDF). Retrieved 2012-02-26.
  11. Alvarado, Omar; Fellers, Thomas; Davidson, Michael. "Molecular Expressions: Science Optics & You - Olympus MIC-D: Integrated Circuit Image Gallery - Weitek P9000 Video Graphics Processor". micro.magnet.fsu.edu. Retrieved 2023-05-21.
  12. Alvarado, Omar; Fellers, Thomas; Davidson, Michael. "Molecular Expressions: Science Optics & You - Olympus MIC-D: Integrated Circuit Image Gallery - Weitek 91460 Graphics Processor". micro.magnet.fsu.edu. Retrieved 2023-05-21.
  13. House, David (25 February 2012). "Weitek Oral History Panel" (PDF) (Interview).