Last updated

MoSys, Inc.
FormerlyMonolithic System Technology (1991–2006)
FoundedSeptember 16, 1991;31 years ago (1991-09-16) in San Jose, California
FounderFu-Chieh Hsu
DefunctDecember 20, 2021;11 months ago (2021-12-20)
FateMerger with Peraso Technologies

MoSys, Inc., originally Monolithic System Technology (MoST), was a fabless semiconductor design company founded in 1991. The company primarily designed memory chips and were especially known for their Multibank DRAM and 1T-SRAM technologies—the latter used on Nintendo's Wii and GameCube video game consoles.



MoSys was incorporated in San Jose, California, on September 16, 1991, as Monolithic System Technology. [1] The company was co-founded by Fu-Chieh Hsu, who also served as its chairman and president until December 2004. [2] Joined by Fu-Chieh were Wingyu Leung and Gary Banta, both vice presidents of design engineering. The initial design team staffed engineers poached from Integrated Device Technology, ISSI, Rambus, and Plus Logic. By 1994, the company had received $7.5 million in venture funding. [3]

The company's first major product was a specialized type of dynamic random-access memory that Monolithic termed Multibank DRAM (MDRAM). [3] The initial entry in this series of chips was a 4-Mb chip, composed of 16 cells of 16-bit-wide 16-kB memory; a simple interface on each of the cells connects them to a high-speed bus on the chip. On each leading edge and trailing edge of the chip-enable pulse, memory arrays output data onto the internal bus, achieving a 32-bit word on every pulse. [4] MDRAM secured design wins in July 1994 with Tseng Labs, Trident Microsystems, and S3 Inc. using the chips in their graphics accelerator cards. Access time was rated at 15  ns, compared to 60 ns of contemporary chips. [5] MDRAM required a proprietary interface and could not be adapted to the SIMM card standard for desktop computer memory of its day. [3] Volume production, handled by an outside fabricator, was achieved in late 1994. [6]

MoSys 1T-SRAM chip 1T-SRAM.JPG
MoSys 1T-SRAM chip

In July 1998, Monolithic introduced a series of pipelined-burst static RAM chips for the notebook computer market. [7] In September 1998 they introduced 1T-SRAM, a pseudo-static random-access memory technology. Unlike true static RAM, 1T-SRAM is essentially dynamic RAM, which requires each memory cell to be refreshed constantly. However, 1T-SRAM pairs each bank of cells with true SRAM cache of the same capacity; when more than one read/write operation occurs within a bank, the on-chip memory controller redirects access to the cache, allowing the cells within the bank to be refreshed. All banks not involved in a given transaction are meanwhile refreshed in the background. This effectively achieves SRAM-like performance, without the need for wait states for every recharge cycle. [8] The 1T in 1T-SRAM stands for 1 transistor; in dynamic RAM, typically only one transistor–capacitor pair is needed to build one memory cell, while static RAM commonly requires six transistors. [9] The academics Bruce Jacob, Spencer W. Ng, David T. Wang, writing in the book Memory Systems (2008), called the name a misnomer: "[1-transistor static RAM] is not really possible, but it makes for a catchy name". [10]

In 1999, Nintendo signed a contract with MoSys to use 1T-SRAM in its codenamed Dolphin video game console, [11] later unveiled as the GameCube in 2001. Over 25 million units of 1T-SRAM were produced up to October 2002. [12] A newer version of 1T-SRAM, dubbed 1T-SRAM Classic, was patented and introduced in 2006. [13] Nintendo re-entered a contract with Monolithic to use it in the Wii, in 2006. [14]

The company began narrowing its chip sales in 1998, in favor of licensing its patents to other semiconductor memory companies. [15] In September 2000, Monolithic's board members voted to reincorporate the company in Delaware. [16] The company still operated within California, relocating its research office to nearby Sunnyvale by June 2001. The same month, the company filed its initial public offering, mediated through A. G. Edwards. [17] The company's stock rose 12 percent within the first day of its launch, [15] leading to a net proceed of $51 million for Monolithic. [16] The Wall Street Journal saw this as a rekindling of interest in technology companies in the stock market, which had fallen in the twilight of the dot-com bubble. [15]

In February 2004, Synopsys announced that it would acquire Monolithic for US$432 million. [18] However, a month later, Synopsys terminated their agreement to buy out Monolithic and paid the company a $10 million termination fee as part of the merger contract. [19] This came after Synopsys had switched the terms of their acquisition, proposing to Monolithic a $13.50-per-share all-cash offer, incurring a very high premium. Monolithic followed with a lawsuit in Delaware courts seeking to force Synopsys to finish their acquisition. Monolithic dropped the suit in July 2004 without payment or liability. In late December 2004, following ill-health and a tough year for the company, chairman Fu-Chieh resigned from Monolithic, with chief financial officer Mark Voll taking the mantle. [2]

Monolithic had, by the end of 2005, 76 full-time employees—25 executives in Delaware and 51 engineers in the company's research and development lab in Sunnyvale. In May 2006, the company formally renamed themselves to MoSys. [13]

By the late 2010s MoSys had pivoted to designing chips for security, telecommunications, and datacenters. In December 2021, they merged with Peraso Technologies, a designer of mmWave semiconductor, to emerge as Peraso Inc. [20]


  1. Bailey & Werner 2007, p. 40; Staff writer 1994, p. 95.
  2. 1 2 LaPedus 2004.
  3. 1 2 3 Staff writer 1994, p. 95.
  4. McLeod 1994, p. 5.
  5. Crothers 1994, p. 32.
  6. Schroeder 1994, p. 40.
  7. Ascierto 1999, p. 16.
  8. Glaskowsky 1999, p. 1.
  9. Jacob, Spencer & Wang 2008, p. 330; Shimpi 2001.
  10. Jacob, Spencer & Wang 2008, p. 330.
  11. Clarke & Hara 1999.
  12. Staff writer 2002.
  13. 1 2 Bailey & Werner 2007, p. 41.
  14. Block 2006.
  15. 1 2 3 Hennessey 2001, p. C14.
  16. 1 2 Bailey & Werner 2007, p. 40.
  17. Staff writer 2001, p. 6.
  18. Bloomberg L.P. 2004, p. 10.
  19. Bailey & Werner 2007, pp. 40–41.
  20. AccessWire 2021.

Related Research Articles

<span class="mw-page-title-main">Computer memory</span> Device used on a computer for storing data

In computing, memory is a device or system that is used to store information for immediate use in a computer or related computer hardware and digital electronic devices. The term memory is often synonymous with the term primary storage or main memory. An archaic synonym for memory is store.

<span class="mw-page-title-main">Static random-access memory</span> Type of computer memory

Static random-access memory is a type of random-access memory (RAM) that uses latching circuitry (flip-flop) to store each bit. SRAM is volatile memory; data is lost when power is removed.

<span class="mw-page-title-main">Dynamic random-access memory</span> Type of computer memory

Dynamic random-access memory is a type of random-access semiconductor memory that stores each bit of data in a memory cell, usually consisting of a tiny capacitor and a transistor, both typically based on metal-oxide-semiconductor (MOS) technology. While most DRAM memory cell designs use a capacitor and transistor, some only use two transistors. In the designs where a capacitor is used, the capacitor can either be charged or discharged; these two states are taken to represent the two values of a bit, conventionally called 0 and 1. The electric charge on the capacitors gradually leaks away; without intervention the data on the capacitor would soon be lost. To prevent this, DRAM requires an external memory refresh circuit which periodically rewrites the data in the capacitors, restoring them to their original charge. This refresh process is the defining characteristic of dynamic random-access memory, in contrast to static random-access memory (SRAM) which does not require data to be refreshed. Unlike flash memory, DRAM is volatile memory, since it loses its data quickly when power is removed. However, DRAM does exhibit limited data remanence.

Non-volatile random-access memory (NVRAM) is random-access memory that retains data without applied power. This is in contrast to dynamic random-access memory (DRAM) and static random-access memory (SRAM), which both maintain data only for as long as power is applied, or forms of sequential-access memory such as magnetic tape, which cannot be randomly accessed but which retains data indefinitely without electric power.

Magnetoresistive random-access memory (MRAM) is a type of non-volatile random-access memory which stores data in magnetic domains. Developed in the mid-1980s, proponents have argued that magnetoresistive RAM will eventually surpass competing technologies to become a dominant or even universal memory. Currently, memory technologies in use such as flash RAM and DRAM have practical advantages that have so far kept MRAM in a niche role in the market.

Nano-RAM is a proprietary computer memory technology from the company Nantero. It is a type of nonvolatile random-access memory based on the position of carbon nanotubes deposited on a chip-like substrate. In theory, the small size of the nanotubes allows for very high density memories. Nantero also refers to it as NRAM.

Volatile memory, in contrast to non-volatile memory, is computer memory that requires power to maintain the stored information; it retains its contents while powered on but when the power is interrupted, the stored data is quickly lost.

Semiconductor memory is a digital electronic semiconductor device used for digital data storage, such as computer memory. It typically refers to MOS memory, where data is stored within metal–oxide–semiconductor (MOS) memory cells on a silicon integrated circuit memory chip. There are numerous different types using different semiconductor technologies. The two main types of random-access memory (RAM) are static RAM (SRAM), which uses several MOS transistors per memory cell, and dynamic RAM (DRAM), which uses a MOS transistor and a MOS capacitor per cell. Non-volatile memory uses floating-gate memory cells, which consist of a single floating-gate MOS transistor per cell.

VLSI Technology, Inc., was an American company that designed and manufactured custom and semi-custom integrated circuits (ICs). The company was based in Silicon Valley, with headquarters at 1109 McKay Drive in San Jose. Along with LSI Logic, VLSI Technology defined the leading edge of the application-specific integrated circuit (ASIC) business, which accelerated the push of powerful embedded systems into affordable products.

1T-SRAM is a pseudo-static random-access memory (PSRAM) technology introduced by MoSys, Inc. in September 1998, which offers a high-density alternative to traditional static random-access memory (SRAM) in embedded memory applications. Mosys uses a single-transistor storage cell like dynamic random-access memory (DRAM), but surrounds the bit cell with control circuitry that makes the memory functionally equivalent to SRAM. 1T-SRAM has a standard single-cycle SRAM interface and appears to the surrounding logic just as an SRAM would.

<span class="mw-page-title-main">Ferroelectric RAM</span> Novel type of computer memory

Ferroelectric RAM is a random-access memory similar in construction to DRAM but using a ferroelectric layer instead of a dielectric layer to achieve non-volatility. FeRAM is one of a growing number of alternative non-volatile random-access memory technologies that offer the same functionality as flash memory. An FeRAM chip contains a thin film of ferroelectric material, often lead zirconate titanate, commonly referred to as PZT. The atoms in the PZT layer change polarity in an electric field, thereby producing a power-efficient binary switch. However, the most important aspect of the PZT is that it is not affected by power disruption or magnetic interference, making FeRAM a reliable nonvolatile memory.

Embedded DRAM (eDRAM) is dynamic random-access memory (DRAM) integrated on the same die or multi-chip module (MCM) of an application-specific integrated circuit (ASIC) or microprocessor. eDRAM's cost-per-bit is higher when compared to equivalent standalone DRAM chips used as external memory, but the performance advantages of placing eDRAM onto the same chip as the processor outweigh the cost disadvantages in many applications. In performance and size, eDRAM is positioned between level 3 cache and conventional DRAM on the memory bus, and effectively functions as a level 4 cache, though architectural descriptions may not explicitly refer to it in those terms.

Memory refresh is the process of periodically reading information from an area of computer memory and immediately rewriting the read information to the same area without modification, for the purpose of preserving the information. Memory refresh is a background maintenance process required during the operation of semiconductor dynamic random-access memory (DRAM), the most widely used type of computer memory, and in fact is the defining characteristic of this class of memory.

Computational RAM (C-RAM) is random-access memory with processing elements integrated on the same chip. This enables C-RAM to be used as a SIMD computer. It also can be used to more efficiently use memory bandwidth within a memory chip.

<span class="mw-page-title-main">Random-access memory</span> Form of computer data storage

Random-access memory is a form of computer memory that can be read and changed in any order, typically used to store working data and machine code. A random-access memory device allows data items to be read or written in almost the same amount of time irrespective of the physical location of data inside the memory, in contrast with other direct-access data storage media, where the time required to read and write data items varies significantly depending on their physical locations on the recording medium, due to mechanical limitations such as media rotation speeds and arm movement.

Thyristor RAM (T-RAM) is a type of random-access memory dating from 2009 invented and developed by T-RAM Semiconductor, which departs from the usual designs of memory cells, combining the strengths of the DRAM and SRAM: high density and high speed. This technology, which exploits the electrical property known as negative differential resistance and is called thin capacitively-coupled thyristor, is used to create memory cells capable of very high packing densities. Due to this, the memory is highly scalable, and already has a storage density that is several times higher than found in conventional 6T SRAM. It was expected that the next generation of T-RAM memory will have the same density as DRAM.

Z-RAM is a tradename of a now-obsolete dynamic random-access memory technology that did not require a capacitor to maintain its state. Z-RAM was developed between 2002 and 2010 by a now-defunct company named Innovative Silicon.

In modern computer memory, a sense amplifier is one of the elements which make up the circuitry on a semiconductor memory chip ; the term itself dates back to the era of magnetic core memory. A sense amplifier is part of the read circuitry that is used when data is read from the memory; its role is to sense the low power signals from a bitline that represents a data bit stored in a memory cell, and amplify the small voltage swing to recognizable logic levels so the data can be interpreted properly by logic outside the memory.

<span class="mw-page-title-main">Memory cell (computing)</span> Part of computer memory

The memory cell is the fundamental building block of computer memory. The memory cell is an electronic circuit that stores one bit of binary information and it must be set to store a logic 1 and reset to store a logic 0. Its value is maintained/stored until it is changed by the set/reset process. The value in the memory cell can be accessed by reading it.

Mosel Vitelic Inc. manufactures power discrete, power management IC and analog IC technologies. Mosel Vitelic Inc. joined the Taiwan Stock Exchange in September 1995.