UNITED STATES

SECURITIES AND EXCHANGE COMMISSION

Washington, D.C. 20549

FORM 10-K

For the Fiscal Year December 31, 20192021 or

Commission file number: 000-32929

MOSYS,PERASO INC.

(Exact name of registrant as specified in its charter)

(408) 418-7500

(Registrant’s telephone number, including area code)

Securities registered pursuant to Section 12(b) of the Act:

Securities registered pursuant to Section 12(g) of the Act:

Indicate by check mark if the registrant is a well-known seasoned issuer, as defined in Rule 405 of the Securities Act. Yes ☐  No ☒

Indicate by check mark if the registrant is not required to file reports pursuant to Section 13 or Section 15(d) of the Act. Yes ☐  No ☒

Indicate by check mark whether the registrant (1) has filed all reports required to be filed by Section 13 or 15(d) of the Securities Exchange Act of 1934 during the preceding 12 months (or for such shorter period that the registrant was required to file such reports), and (2) has been subject to such filing requirements for the past 90 days. Yes ☒  No ☐

Indicate by check mark whether the registrant has submitted electronically every Interactive Data File required to be submitted pursuant to Rule 405 of Regulation S-T (§232.405 of this chapter) during the preceding 12 months (or for such shorter period that the registrant was required to submit such files). Yes ☒  No ☐

Indicate by check mark whether the registrant is a large accelerated filer, an accelerated filer, a non-accelerated filer, a smaller reporting company, or emerging growth company. See the definitions of “large accelerated filer,” “accelerated filer,” “smaller reporting company,” and "emerging growth company" in Rule 12b-2 of the Exchange Act:

If an emerging growth company, indicate by check mark if the registrant has elected not to use the extended transition period for complying with any new or revised financial accounting standards provided pursuant to Section 13(a) of the Exchange Act. ☐

Indicate by check mark whether the registrant has filed a report on and attestation to its management's assessment of the effectiveness of its internal control over financial reporting under Section 404(b) of the Sarbanes-Oxley Act (15 U.S.C. 7262(b)) by the registered public accounting firm that prepared or issued its audit report. ☐

Indicate by check mark whether the registrant is a shell company (as defined in Rule 12b-2 of the Act). Yes ☐  No ☒

The aggregate market value of the voting and non-voting common equity held by non-affiliates of the Registrant, based on the closing price of the shares of common stock on The NASDAQthe Nasdaq Stock Market on June 30, 20192021 was $7,534,001.  $54,027,405.

The number of shares of Registrant’s Common Stock outstanding, par value $0.001 per share, as of March 1, 2020,25, 2022, was 2,314,512

21,578,908 .

ANNUAL REPORT ON FORM 10-K

FOR THE YEAR ENDED DECEMBER 31, 20192021

TABLE OF CONTENTS

Special Note Regarding Forward-Looking Statements and Other Information Contained in this Report

2

Part ISPECIAL NOTE REGARDING FORWARD-LOOKING STATEMENTS AND OTHER INFORMATION CONTAINED IN THIS REPORT

This Annual Report on Form 10-K, or this Report, and the documents incorporated herein by reference contain forward-looking statements within the meaning of Section 27A of the Securities Act of 1933, as amended (the “Securities Act”), and Section 21E of the Securities Exchange Act of 1934, as amended (the “Exchange Act”), which include, without limitation, statements about the market for our products, technology, our strategy, competition, expected financial performance and other aspects of our business identified in this Annual Report, as well as other reports that we file from time to time with the Securities and Exchange Commission. Any statements about our business, financial results, financial condition and operations contained in this Annual Report that are not statements of historical fact may be deemed to be forward- looking statements. These forward-looking statements represent our intentions, plans, expectations, assumptions and beliefs about future events and are subject to risks, uncertainties and other factors including, without limitation, the direct and indirect effects of coronavirus disease 2019, or COVID-19, and related issues that may arise therefrom. Without limiting the foregoing, the words “believes,” “anticipates,” “expects,” “intends,” “plans,” “projects,” or similar expressions are intended to identify forward-looking statements. Our actual results could differ materially from those expressed or implied by these forward-looking statements as a result of various factors, including the risk factors described in Part I., Item 1A, “Risk Factors,” and elsewhere in this report.Report. We undertake no obligation to update publicly any forward-looking statements for any reason, except as required by law, even as new information becomes available or other events occur in the future.

MoSysPeraso^®, MoSys^®,1T-SRAM^® and Bandwidth Engine^® are registered trademarks of MoSys,Peraso Inc. QPR™, LineSpeed™ and GigaChip^TM are trademarks of MoSys,Peraso Inc.

Unless expressly indicated or the context requires otherwise, the terms “Peraso,” the “Company,” “we,” “us”or “our” in this Report refer to Peraso Inc., a Delaware corporation, and, where appropriate, its subsidiaries.

Part I

Item 1.  Business

Overview

MoSys,Peraso Inc., together with its subsidiaries (“MoSys,Peraso,” the “Company,“Company,” “we,“we,” “our”“our” or “us”), is a fabless semiconductor company focused on the development and sale of: i)semiconductordevices andmodulesbasedon our proprietary semiconductordevices and ii) performance of non-recurring engineering, or NRE, services and licensing of intellectual property, or IP. Our primary focus is the development of millimeter wavelength, or mmWave, wireless technology, for the 60 Gigahertz, or GHz, spectrum and for 5G cellular networks, or 5G. Our mmWave productsenablea rangeof applications,such as5G with low latencyand high reliability,as wellas multi-gigabit,mmWavelinksover25 kilometers. Our mmWave products addressconsumerapplications,such as wirelessvideostreamingand untethered augmented reality and virtual reality, or AR/VR. We also have a line of memory-denominated integrated circuits or ICs, for the high-speed cloud networking, communications, security appliance, video, monitor and test, data center and computing markets. markets that deliver time-to-market, performance, power, area and economic benefits for system original equipment manufacturers, or OEMs.

Business Combination

We were formerly known as MoSys, Inc., or MoSys. On September 14, 2021, we and our subsidiaries, 2864552 Ontario Inc. and 2864555 Ontario Inc., entered into an Arrangement Agreement, or the Arrangement Agreement, with Peraso Technologies Inc., or Peraso Tech, a privately-held corporation existing under the laws of the province of Ontario, to acquire all of the issued and outstanding common shares of Peraso Tech, or the Peraso Shares, including those Peraso Shares to be issued in connection with the conversion or exchange of secured convertible debentures and common share purchase warrants of Peraso Tech, as applicable, by way of a statutory plan of arrangement, or the Arrangement, under the Business Corporations Act (Ontario). On December 17, 2021, following the satisfaction of the closing conditions set forth in the Arrangement Agreement, the Arrangement was completed and we changed our name from MoSys to “Peraso Inc.” and began trading on the Nasdaq Stock Market, or the Nasdaq, under the symbol “PRSO.”

Industry Trends and Performance

MMWave and 5G

Thedemandforwirelessservicesisincreasingexponentially, therefore,wirelessusersand serviceproviderswillbe requiredto eventuallyutilizehigherfrequencyspectrumto meetthedemand.We believe the 5G wirelessindustryisthebestand latestexampleof how and why mmWaveisthefuture of wirelessnetworks.The 5G specificationincludeslow, midand mmWavefrequencies. There are significant expectations that 5G will significantly improve cellular network performance, as evidence by slogansas “10X thebandwidth”and “10X reductionin latency.”From our perspective, in reality,only partof the5G specificationtrulyofferssuch improvement,and we believe thisisrepresented bymmWave.

mmWaveisnot withoutchallenges,as mmWavesignalsdo not typicallytravelas faras traditionalwireless signalsand aremoreattenuatedby solidobjects.Mitigationstrategiesmustbe deployed,in particularwith regardsto themanagementof signalpropagation.Whereastraditionalwirelessdevicesutilizea broad,omni-antennapattern,mmWavesystemsrelyon phasedarraytechnology,which focussestheradiosignalintoa narrowbeamto improvepropagationcharacteristics.Perasois a globalleaderin implementingthesesophisticated radiosystemsand isone of thefew companiesin themarketthatissuccessfullyshippingphasedarraydevicesin massproduction.

In termsof specificmarketopportunity,mmWaveisa keydifferentiatingupdatefrom4G/LTE networks to 5G. Withinthe5G market,thereareseveralprimaryapplicationsformmWave.The initialtargetforPerasois referredto as the fixed wireless access, or FWA, segment.In thismarketsegment,carriersprovidetheircustomerswith a fixedwireless linkto a basestationor smallcell,thusprovidingthecustomerwith high-speedaccessto theInternet.mmWave can providedownload speedsof over1 Gbps and uploadspeedsof severalhundredmegabitspersecond. In addition, mmWaveisa muchcheaperalternativeto fiberand allowscarriersan additionaladvantageand competitive advantage againstotheraccesstechnologies,such as cable.Additionally,Peraso5G mmWaveRFmodulescan be utilizedin otherapplications,includinghotspots,laptopsand tablets.

5G mmWavehas supportfrommajorindustryplayers.Apple has incorporatedmmWavewirelessintoall versionsof theiPhone12 forsalein theUSmarket.The basicpremiseiscommon,which istheever-increasing demandforbandwidth.Verizonistheleadingcarrierin theUSatdeployingmmWaveforboth mobileand fixed wirelessaccess.The initial use caseforcellular service providersisto providetheircustomerbase(primarily smart phone customers)with continuityof networkaccessin highlycongestedenvironments, such as sporting events,publicbeaches,musicfestivalsor generallyany largegatheringwhere thousandsof usersareattemptingto accessthenetworksimultaneously.PerasobelievesthatmmWavewillgainuniversal acceptance,as userswilldemandfullcontinuityin termsof networkaccess.

Below aresomeearlyexamplesof carriersdeployingmmWavetechnology:

•June 8, 2021: UScellularsetsrecordwith 5G mmWavelinksof 10 kilometers;

•June 11, 2021: VerizonlaunchesOn Site, for theuse of mmWaveforon-premises,private5G networks; and

Longer term, we believe we are wellpositionedto addressthemobileopportunityformmWave, which is expected to presentan orderof magnitudeincreasein thetotalavailablemarket.

Memory

Our memory solutions deliver time-to-market, performance, power, area and economic benefits for system original equipment manufacturers, or OEMs. Our primary product line is marketed under the Accelerator Engine name and comprises our Bandwidth Engine and Programmable HyperSpeed Engine IC products, which integrate our proprietary, 1T-SRAM high-density embedded memory and a highly-efficient serial interface protocol resulting in a monolithic memory IC solution optimized for memory bandwidth and transaction access performance.   Further performance benefits can be achieved to offload statistical, search or other custom functions using our optional integrated logic and processor elements.

As data rates and the amount of high-speed processing increase, critical memory access bottlenecks occur. Our Accelerator Engine ICs dramatically increase memory accesses per second, removing these bottlenecks. In addition, the serial interface and high-memory capacity reduce the board footprint, number of pins and complexity, while using less power.  To complement our Accelerator Engine ICs

Our Products

Our primary focus is the development, marketing and utilize our technology we have recently introduced a new Software Accelerator product line that leverages our proprietary graphical memory engine technology to provide data classification capabilities.   These new software and IP products are hardware agnostic and operate with or without onesale of our Accelerator Engine IC mmWaveproducts. We expect mmWaveis generallydescribedas thefrequencyband from24 GHzto begin licensing300 GHz.Currently, therearetwo industrystandardsthat incorporatemmWavetechnologyforwirelesscommunications:(i)IEEE 802.11ad/ayand (ii)3GPPRelease15-17 (commonlyreferredto as 5G). Wehave developedand continueto developproductsthatconformto these products in the first half of 2020.standards.

mmWave ICs

Our LineSpeed firstproductlineoperatesin the60 GHzband and conformsto theIEEE802.11ad standard.This productlineincludesa basebandIC, product line comprises non-memory, high-speed serialization-deserialization interface,including multiplevariationsof mmWaveradiofrequency, or SerDes I/O, physical layer,RF, integrated circuits, or PHY, devices that ensure signal integrity between interfaces which is commonly referred toICs, as clock data recovery, or CDR, or retimer functionality, which perform multiplexing to transition from one speed to another, commonly referred to wellas Gearbox functionality. These PHY devices reside within optical modules associatedantennatechnology.The secondproductlineiscurrentlyin developmentand on networking equipment line cards designed for next-generation Ethernet and optical transport network applications.

Industry Background

The amount addressesthe5G mmWaveopportunity.Given ourexperiencein thedevelopmentof data and the number of data consumersmmWave technology and devices, we believe 5G mmWave,is growing exponentially, driven primarily by commercial a logicaladjacentmarket.

The firstmarkettargetedwas the60GHzIEEE 802.11ad market.Our60GHzIEEE802.11ad productshad two veryimportantadvantagesovertraditional2.4GHzand consumer cloud applications, video services, 5GHzWi-Fiproducts:veryhigh speed mobile networks, Internet of Things, or IoT, and many other cloud applications. In orderdatarates(up to meet these demands, the new cloud infrastructure, including the backbone, edge, access network and data centers, must scale in both speed and intelligence to handle real-time security, bandwidth allocation, and service-level expectations. In addition, workloads or applications delivered at a massive scale from the cloud require flexible and efficient data transmission to optimize resources to enable these applications and lower the overall cost, size and power of the data center. These increased demands strain

3

communication between onboard IC devices, limiting the data throughput in network switches and routers and the network backbone.

To meet these demands, carrier and enterprise networks are merging with the cloud and are undergoing significant changes and, most significantly, are migrating to packet-based Ethernet networks that enable higher throughput, lower cost and uniform technology across access, core and metro network infrastructure. These networks have been designed to deliver voice and video applications over high-speed Internet services on one converged, efficient and flexible network. These trends require networking systems, especially the high-speed switches, security appliances and routers that primarily comprise these networks, to comply with evolving market requirements and be capable of providing new services and better quality of service while supporting new protocols and standards. Traditional OEM network and telecommunications equipment manufacturers, such as Nokia Corporation, and its subsidiary, Alcatel-Lucent, Cisco Systems, Inc., Tel. LM Ericsson, Fujitsu Ltd., Hitachi Ltd., Huawei Technologies, and Juniper Networks, Inc., as well as new vendors and cloud-service providers, who are delivering a new set of white-box solutions, must offer higher levels of packet forwarding rates, bandwidth density and be optimized to enable higher-density, lower-power data path connectivity in the next generations of their networking systems.

Networking communications, security, video and computing systems throughout the cloud network must operate at higher speed and performance levels, and so require new generations of packet processors and improved memory subsystems to enable system performance. These systems and their component line cards generally need to support aggregate rates of 1004.5 gigabits per second, or Gbps, nGb/s)and above low latency(lessthan5 meters per second).The firstapplicationthathad tractionwas outdoorbroadband.This includedapplicationssuch aspoint-to-point, or PtP,backhaullinksor fixedwirelessaccess, FWA,usingpoint-to-multipointlinks, or PtMP. productsusingthe60GHzband areforthismarket.Asthespectrumisunlicensed(free),wirelesscarrierscan provideserviceswithouthavingto meetspend significantlyon wirelessspectrum. We are a leadingsupplierof semiconductorsin the continued growth PtP and PtMP markets.We arecurrentlyshippingto leadingequipmentsuppliersin network traffic. Data centersthisspace,as wellas directlyto serviceprovidersbuildingtheirown equipment.We believe our products and access equipment that were previously aggregating slower traffic at rates of up to 40Gbps now are being designed to aggregate traffic at 100Gbps, or more. The transition to high-bandwidth networks and the move to 100Gbps and higher rates at the edge (i.e., closer technology bringkey advantagesto the networks and users generating data and voice traffic) is underway, and market.First,ourproductssupportthe increase in data rates for these networks is expected spectrumfrom66GHzto continue to grow rapidly over the coming years.

The systems that our customers build come in various sizes and utilize cards that contain several types of semiconductors. Line cards71 GHz.These are found in chassis-based systems that have slots and can contain up to 20 line cards. Our networking and communication system and certain other system customers typically use chassis-based systems. The alternative is systems that contain a single card; these systems are generally oftenreferredto as appliances or “pizza boxes.”  Cardschannels5 and 6 in the802.11ad/ayspecifications.The key advantagein supportingthesechannelsis that typically plug into thesignalsareableto propagatemuchfurtherthanchannels1-4;this isa server or compute system are generally referred to as accelerator cards. We believe the wider use resultof these accelerator cards in systems throughout the network, especially significantlyloweroxygen absorptionat the edge, will expand the market opportunity for our products, as a number of these cards utilize field programmable gate array ICs, or FPGAs, as the packet processor. Our Accelerator Engines are ideally suited to support FPGAs performing these functions.  Each line card, or accelerator card, includes one or more processors and multiple memory chips. These processors are complex ICs or IC chipsets that perform high-speed data or packet processing for functions, such as traffic routing, shaping, metering, billing, statistics, detection, steering, security, video processing, monitoring and workload acceleration. The line cards use various types of memory ICs to facilitate temporary packet storage and assist frequenciesabove 66 GHz.Currently,customershave achievedlinksin the analysis and tracking rangeof information embedded within25 kilometers,which we believe issubstantiallylongerthanany 60 GHzlinksachieved to date.

In the data flowing through indoorarea,the processors. After a packet enters the line card, a packet or data processor helps separate the packet into smaller pieces 802.11ad technologyisidealfor rapid analysis. high speed,low latencyvideoapplications.In a typical packet-based network for example, the data is broken up into the packet header, which contains vital information on packet destination and type, such as the Internet protocol address, and the payload, which contains the data being sent. Generally, the line card operations must occur at full data rates and typically require frequent access to the memory ICs.

Simultaneously, the packet’s payload, which may be substantially larger than the packet header, is also stored in memory ICs until processing is complete and the packet indoorenvironments,ourproductscan be re-combined and sent to its next system destination. Within the line card, communication between the packet processor and memory ICs occurs through an interface consisting support3 Gb/s linkswith under5msof combinations of physical pins on each type of chip. These pins are grouped together in a parallel or a serial architecture to form a pathway, called a bus, through which information is transferred from one IC to the next.

Today, the majority of physical buses that connect networking equipment and components use a parallel architecture to communicate between processors and memory ICs, which means information can travel only in one direction and in one instance at a time. As processing speeds increase, the number of pins required and the speed of the bus in a parallel architecture become a limitation on system performance and capability. In contrast, the number of connections is reduced substantially across fewer, higher-rate pins in a serial architecture, and data is transferred

4latency.Exampleapplications include:

simultaneously in both directions. Data transfer rates are limited by •AR/VRlinksbetweenthe data access rates of the various ICs included on the line card, thus leading to bottlenecks when these ICs perform inadequately. In order to remove these bottlenecks headsetand meet next-generation bandwidth requirements, the line card ICs need to support higher access rates enabled by internal memory or high-speedvideoconsole;

•Universal serial bus, architectures or USB,videocamerasforcorporatevideoconferencing;

•Wirelesssecuritycameras;and

•Smartfactorysafetyand these more advanced interface protocols.surveillance.

Most networking and communication systems sold and in operation today include line cards that process data at speeds ranging from 10Gbps to 400Gbps, and support many aggregated slower ports. To accommodate the substantial and growing increase in demand for networking communications and applications, networking systems manufacturers are developing and bringing to market next-generation systems that run at aggregate speeds of 400 Gbps or more with newer products scaling to tens of thousands of Gbps, or tens of terabits, per second. Applications, such as security appliances, broadcast video and compute accelerators that were previously running at aggregate rates of 10Gbps or 40Gbps, are moving to higher aggregate rates in the 100s of Gbps.   Although processor performance in applications, such as computing and networking has traditionally doubled nearly every 18 months, or even sooner, the performance of external high-density memory technology has generally been able to double only once every 10 years. Existing memory IC solutions built for high capacity and based on parallel interface architecture struggle to meet the access rates required to meet speeds of 100Gbps and beyond due to system-level limitations for pin counts, power and performance. To compensate for slow external memory access, developers must either integrate larger amounts of on-chip memory and/or utilize complex system alternatives to try to work around the access-rate limitations of these memories. The additional memory and circuitry adds to IC power, size and cost and may not be feasible depending on the economics and technology used to implement the data processor. These networking and communications systems generally comprise a chassis populated by 4 to 16 line cards. Often, these systems are shipped to customers with only a portion of the line card slots populated, and the customer will add additional line cards to increase system performance, capacity and features.

Each line card requires a significant amount of memory to support its processing capabilities. Traditional external memory IC solutions currently used on line cards include both dynamic random access memory, or DRAM, and static random access memory, or SRAM. Line cards in networking systems use both specialized, high-performance DRAM ICs, such as reduced-latency DRAM, or RLDRAM, low-latency DRAM, or LLDRAM, and commodity DRAM, such as double data rate, or DDR ICs.  The latest DDR memory is high-bandwidth memory, or HBM, which provides high bandwidth, but has fundamentally slow access time.  For very high access, networking systems use higher-performance SRAM, which may be integrated into the data processing IC itself depending on size, power and economics or use traditional external SRAM IC, such as quad data rate, or QDR SRAM. These memories are very fast, but are much smaller, cost more and burn more power than traditional DRAM. Substantially all of these traditional memory IC solutions use parallel interfaces, which are slower than serial interfaces. For data processing solutions, which are unable to integrate large amounts of SRAM, such as field-programmable gate arrays (FPGA), we believe the traditional external SRAMs or RLDRAMs will be increasingly challenged to meet the performance, pin count, area and power requirements as networking systems and other new security, video, and compute systems expand beyond 100Gbps. The result is a gap between processor and memory performance. To meet the higher performance requirements being demanded by the industry, while using current components and architectural approaches, system designers must add more discrete memory ICs to the line cards and/or add more embedded memory on the packet processor. New processor and custom data processing engine ICs are being developed that integrate more SRAM to help offset the bottlenecks, but the cost to develop these custom ICs is high and there is a trade-off in cost, power and size.  FPGAs offer flexibility, lower development cost and time to market but are limited in the amount of internal circuitry and the amount of integrated SRAM memory. We believe our Accelerator Engine family of products is well suited to address memory access bottleneck challenges and provide significant performance, size, pin count and power advantages compared to traditional external memory solutions, primarily for FPGA-based systems.

In order to improve performance and resolve memory bottlenecks, in recent years, the trend has been to have algorithms on the memory device perform computations in order to reduce processing time and power consumption. This trend is sometimes called in-memory compute or processor-in-memory. In order to make a flexible solution, the in-memory compute can be accomplished with arrays of reduced instruction set computer, or RISC, cores on the memory device. Further performance gains can be accomplished with application-specific enhancements to the memory device’s instruction set architecture.

We have developed our ICs a high-volumemmWaveproductiontestmethodologyusingstandard,low-costproductiontestequipment.Ithas takenusseveralyearsto synergistically addressrefineperformanceof thisproductiontestmethodology,and we believe this places us in a leadershippositionin addressing the need for high-speed data accessoperationalchallengesof competitively producing and throughput currently confronting system designers. We expect our IC deliveringmmWaveproducts to meet the increasing demands placed on conventional memory technology used on the line cards in high-speed systems. We believeintohigh-volume markets.

mmWave modules

In 2021, webegan producing and sellingcompletemmWavemodules.The primary advantageprovidedby a moduleis that our products thesiliconand

5

theantennaareintegratedintoa singledevice.A differentiatingcharacteristicof mmWavetechnology are well positionedisthattheRFamplifiersmustbe as replacements for existing IC solutions in order to support the needs of a growing number of FPGA-based data processing applications with aggregate rates greater than 100Gbps that require high bandwidth and high access rate to memory.

Our Approach

We have leveraged our proprietary IP to design our IC products and related acceleration IP to help OEMs in our target markets to address the growing bottlenecks in system performance. We have incorporated critical features into our product families to accomplish this objective.

High-Performance Interface

High-speed, efficient interfaces are critical building blocks to meet high data transfer rate requirements for communication between ICs on network line cards. Semiconductor companies are increasingly turning to serial interface architectures to achieve needed system performance. Using serial interfaces, IC developers also are able to reduce the number of pins (the wired electrical pins that connect an IC closeas possibleto the network line card on which it is mounted) on the IC. With reducing geometries, the size of most high-performance ICs is dictated by the number of pins required, rather than the amount of logic and memory embedded in the chip. As antennato minimizeloss.By providinga result, using a serial interface facilitates cost reduction and reduced system power consumption, while improving the performance of both the IC itself and the overall system. While serial interfaces provide significantly enhanced performance over parallel interfaces, SerDes interfaces traditionally have had higher power consumption, which is a challenge for IC designers. Our SerDes interfaces, however, are optimized to meet our customers’ signal integrity, low-power consumption and latency requirements.

We make our interface technologies compliant with industry standards so that they module,wecan interoperate with interfaces on existing ICs. In addition, we make them programmable to support multiple data rates, which allows for greater flexibility for guaranteethe system designer, while lowering development and validation costs.

GigaChip Interface Protocol

In addition to the physical characteristics performanceof the serialamplifier to antenna interface,which simplifiesthe protocol used RFdesignengineering,facilitatingmoreopportunitiesforcompaniesthat have not providedRF-typesystems,as wellas shorteningthetimeto transmit data marketfornew products. Itis also an important element that impacts speed and performance. To address this and complementpossiblefor thirdpartiesto providemoduleproducts,but, given our Accelerator Engine devices, significantmmWaveantenna technology andintellectual property portfolio,we have developed the GigaChip Interface, or GCI, which is an open-interface transport protocol optimized for efficient chip-to-chip communications. The GCI electrical interface is compatible with the current industry standards, including 10G and 25G IEEE and OIF interface standards, to simplify electrical interoperability between devices. GCI can enable highly efficient serial chip-to-chip communications, and its transport efficiency averages 90% for the data transfersbelieve it handles. GCI is included in our ICs and is offered to customers and prospective partners on terms intended to encourage widespread adoption.

High-Performance and High-Density Memory Architecture

The high density of our proprietary 1T-SRAM technology stems from the use of a single-transistor, or 1T, which is similar to DRAM, with a storage cell for each bit of information. Embedded memory utilizing our 1T-SRAM technologies is typically two to three times denser than the six-transistor storage cells used by traditional SRAM, or 6T-SRAM. Embedded memory utilizing our 1T-SRAM technologies typically provides speeds essentially equal to or greater than the speeds of traditional SRAM and DRAM, particularly for larger memory sizes. Our 1T-SRAM memory designs can sustain random access cycle times of less than three nanoseconds, significantly faster than DRAM technology. Embedded memory utilizing our 1T-SRAM technologies can consume as little as one-half the active power and generate less heat than traditional SRAM when operating at the same speed. The 1T-SRAM allowsenables us to integrate more high-performance memory using less expensive processingprovidea highlycompetitivesolution,as weown the module technology reduce system level heat dissipation and enable reliable operation using lower-cost packaging.producethe significant modulecomponents.

6Memory

Embedded In-Memory Functions

We have combined our high-speed memory architecture with intelligence to define an embedded memory that can execute embedded functions and algorithms internally, or “in-memory,” to allow software and hardware designers acceleration options to improve the performance of their applications.

The in-memory functions executed within the memory architecture in our Accelerator Engine products result in application-performance increases by reducing the number of external memory and computational operations needed to accomplish the same functions using traditional memories.  Also, by executing in-memory, the resources of the packet processor and other ICs on the customer’s board are available to perform other functions.

Our Accelerator Engine ICs include an arithmetic logic unit, or ALU, which enables the performance of mathematical operations on data. Moving certain processing functions from the host data processor IC to the Accelerator Engine IC through the use of this embedded ALU, reduces the number of processing transactions and frees the host data processor IC to perform other important networking or micro-processing functions.

Our Programmable HyperSpeed Engine IC takes this concept one step further by incorporating integrated RISC processors optimized for processing data structures and graphs.  Our Programmable HyperSpeed Engine IC integrates RISC cores optimized for operating data stored in the memory block.  The integration of the cores with memory allows system algorithms or functions to be offloaded to the device and reduces overall system-task latency and increases throughput.  The processors can be programmed by the user to offload and accelerate standard and/or customized functions from the main processor thereby reducing memory transactions and data path complexity to provide improved performance and lower system latency.  New algorithms or functions can be added to or modified in the Programmable HyperSpeed Engine IC in software.

Our Strategy

Our primary business objective is to be a profitable IP-rich fabless semiconductor company offering ICs and related software and IP that deliver unparalleled memory bandwidth and access rate performance for high-performance data processing in cloud networking, security appliances, video, test and monitoring, and data center systems. The key components of our strategic plan include the following strategies:

Target Large and Growing Markets

Prior to 2019, our primary focus was the multi-billion dollar networking, telecommunications, security appliance and data center OEM equipment markets, as our products were developed to support the growth in 100Gbps and higher networking speeds. During 2019, we expanded our market focus to new markets, including video, test and measurement and computing markets. We are currently supporting numerous customers across these markets, with whom we have achieved design wins. We define a design win as a commitment from a customer to utilize one of our IC products in its system. We continue to actively pursue additional design wins for the use of our ICs in our target markets. We believe our design wins represent the potential for future revenue growth. However, there is no assurance that these customer designs will be shipped in large volume by our customers to their customers, how much revenue each design win is likely to generate, or how much revenue all of these (and future design wins) are likely to generate.

Build Long-Term Relationships with FPGA Vendors and Suppliers of Data Processing Solutions

We believe that having long-term relationships with FPGA providers is critical to our success, as such relationships enable us to reduce our time-to-market, provide us with a competitive advantage and expand our target markets. A key consideration of network system designers is to demonstrate interoperability between our IC products and the processor ICs  utilized in their systems. To obtain design wins, we must demonstrate this interoperability, and also show that our IC works optimally with the packet processor to achieve the performance requirements. In addition, our current strategy requires packet processor suppliers to adopt our GCI interface. To that end, we have been working closely with FPGA and application specific standard product providers to enable interoperability between our Accelerator Engine IC products and their high-performance products. To facilitate the acceptance of our Accelerator Engine ICs, we have made available development and characterization kits for system designers to evaluate and develop code for next-generation networking systems. Our characterization kits are fully-functional hardware platforms that allow FPGA and ASIC providers, and their customers, to demonstrate interoperability of the Accelerator Engine IC with the ASIC or FPGA the designers use within their systems.

7

Our IC Products

Accelerator Engines

Our Accelerator Engine IC products are targeted for FPGA-based systems and include the Bandwidth Engine, which is targeted for high-performance applications where throughput is critical, and the Programmable HyperSpeed Engine, which combines the features of the Bandwidth Engine with 32 RISC processors to allow user-defined functions or algorithms to be embedded in the Programmable HyperSpeed Engine.

Bandwidth Engine  The target applications for our memory ICs include a broad range of markets, including test and measurement, 5G networks, router, switching, security, computational storage, database acceleration, Big Data, aerospace and defense, advanced video, high-performance computing, machine learning and AI and other data-driven areas.

The Bandwidth Engine is a memory-dominated IC that has been designed to be a high-performance companion IC to packet processors. While the Bandwidth Engine primarily functions as a memory device with a high-performance and high-efficiency interface, it also can accelerate certain processing operations by serving as a co-processor element. Our Bandwidth Engine ICs combine: (1) our proprietary high-density, high-speed, low latency embedded memory, (2) our high-speed serial interface technology, or SerDes, (3) an open-standard interface protocol and (4) intelligent access technology. We believe an IC combining our 1T-SRAM memory and serial interface with logic and other intelligence functions provides a system-level solution and significantly improves overall system performance at lower cost, size and power consumption. Our Bandwidth Engine ICs can provide up to and over 6.5 billion memory accesses per second externally and 12 billion memory accesses per second internally, which we believe is more than three times the performance of current memory-based solutions. They also can enable system designers to significantly narrow the gap between processor and memory IC performance. Our customers that design Bandwidth Engine ICs onto the line cards in their systems will re-architect their systems at the line-card level and use our product to replace traditional memory solutions. When compared with existing commercially available solutions, our Bandwidth Engine ICs may:

Our Bandwidth Engine 2 IC products contain 576 megabits, or Mb, of memory and use a SerDes interface with up to 16 lanes operating at up to 12.5Gbps per lane. We have been shipping our Bandwidth Engine 2 IC products since 2013. We continue to win new designs for this device family, and expect these products to be our primary revenue source for the foreseeable future.

Our Bandwidth Engine 3 IC products contain 1152Mb of memory and use a SerDes interface with up to 16 lanes operating at up to 25Gbps per lane. Our Bandwidth Engine 3 ICs target support for packet-processing applications with up to five billion memory single word accesses per second, as well as burst mode to enable full duplex buffering up to 400 Gbps for ingress, egress and oversubscription applications. The devices provide benefits of size, power, pin count and cost savings to our customers.

Programmable HyperSpeed Engine

Our Programmable HyperSpeed Engine IC products further leverage our proven serial interface technology and high-density integrated memory with the processor engine architecture to enable high-speed customizable

search, security, and data analysis functions for networking, security, and data center applications, as well as new markets such as video and compute acceleration. The product architecture features 32 search-optimized processor engines, data flow schedulers, and over a terabit of internal access bandwidth. The device leverages our GCI interface technology and high-density integrated memory (1152Mb of 1T-SRAM embedded memory).

8

LineSpeed Flex PHYsQPR

Our LineSpeed Flexquad partition rate, or QPR, family of 100G PHYs, is designedlow cost, ultra-high speed SRAM memory devices features an architecture that allows for parallel accesses to multiple partitions of the memory simultaneously and allows access of up to 576 bits per read or write cycle. The QPR device includes four independent partitions per input/output and each partition functions as a stand-alone random-access SRAM. The high-performance interface, larger density and the multiple partitions work together to support industry standards and includes gearbox, Multi-Link Gearbox, or MLG, and high density CDR/retimer devices designed to enable Ethernet and OTN line card applications to support the latest electrical and optical interfaces. To date, we have announced four unique devices in this product family:

IP Licensing

Historically, we licensed our IT-SRAM memory and SerDes interface technologies on a worldwide basis to semiconductor companies, electronic product manufacturers, foundries, intellectual property companies and design companies.  Most of these licensees incorporated our technology into ICs that they sold to their customers, and, in the case of IT-SRAM licenses, pay a royalty to us for each IC shipped that incorporates our technology. Royalty and other revenue generated from our legacy IP agreements represented 7%, 9% and 11% of our total revenues for 2019, 2018 and 2017, respectively.  

Recently, we announced our new Software Accelerator product line consisting of software and IP available for license. This new product line will include multiple function accelerator platform products, which target specific application functions and will use a common software interface to allow performance scalability over multiple hardware environments. These function accelerator platform products are hardware agnostic and operate withits high capacity 567Mb or without one of our Accelerator Engine ICs. This software-defined, hardware-accelerated platform architecture utilizes1Gb devices. We also offer an internally developed graphicalRTL memory engine architecturecontroller that presents an SRAM-like interface to provide flexible data classification and analysis capability. We believesimplify the technology will generate new opportunities that require less up-front architectural changes by system designers and provide a scalable performance roadmap of options using our Accelerator Engine ICs. We expect our initial Software Accelerator products to be available for license in the first half of 2020.QPR design effort.

Research and Development

Our ability to compete in the future depends on successfully improving our technology to meet the market’s increasing demand for higher performance and lower cost solutions. Development of new IC products requires specialized chip design and product engineers, as well as significant fabrication and testing costs, including mask costs.

We currentlyhave over12 years’worth of technicalknow-how in thedesignand manufacturingof mmWavetechnology.The mostimportantaspectof thisknowledge isknowing how mmWave circuitswillperformin a real-worldenvironment.Traditionally,semiconductordesignutilizessophisticated computer-aided designtoolsto simulatetheperformanceof a devicethatismanufacturedata specificsemiconductor manufacturingplant.However, mmWaveisextremelydifficultto modelprecisely.Therefore,theonly pathto understandhow wella devicewillperformisto producethedeviceand testitin a real-world application.Over thelastdecade,manycompanieshave attemptedto developmmWavesemiconductordevices,however, given thatthedeviceshad inconsistentor weak performance,a numberof themwere unsuccessful and abandonedtheirdesign and product development efforts.

At a systemlevel,thereareadditionaltechnicalchallengespresentedby mmWave technologythatPerasohas overcomeand form a keypartof theinternalknow-how of Peraso.For example,a key technologyof mmWaveisthe conceptof beamformingand beam steeringusinga phasedarrayantenna.This technologyisutilizedto concentratetheRFenergyintoa narrowbeamto improvetherangeand coverageof mmWavedevices.We have developed effective of beamformingand beam steering technology for phasedarraycircuitsand antennas. Whiletherearemanyacademicexamplesof successful phasedarrayimplementations,thereisa vastbarrierbetweena “laboratory”versionof phasedarraytechnology and a versionthatisdeployedforcommercialuse. One such aspectistheimplementationof thebeamforming procedure,which seeksto maximizethroughputand do so whilenot impactinglatency.Whilethedetailsof achievingthisarecomplex,itisimportant-intellectualpropertythatwehave gainedthroughreal-world experience.

With regard to our memory products, we do not have internal resources forto develop new, memory IC products, and do not intend to expend any development efforts to develop new memory products. That said, we believe our Accelerator Engine IC product portfolioproducts will provide us with adequatemeaningful revenue growth opportunityand gross margin contributions for the foreseeable future.  We have focused our product development efforts on software-based capabilities and features that leverage our current technologies and core competencies, as well as our Accelerator Engine IC products. As discussed above, we recently announced our Software Accelerator product line, and the initial packet classification products will use our graph memory engine for performing embedded search and classification of packet headers.  We intend to continue to devote the majoritysubstantially all of our research and development efforts toward furthering the software accelerator product roadmap.

9further expanding our mmWave technology portfolio.

Sales and Marketing

We believe that systems OEMs typically prefer to extend the use of traditional memory solutions and their parallel interfaces, despite performance and costs challenges, and are reluctant to change their technology platforms and adopt new designs and technologies, such as serial interfaces, which are an integral part of our product solutions. Therefore, our principal selling and marketing activities to date have been focused on persuading these OEMs and key component specialists that our IC products provide critical performance advantages, as well as on securing design wins with them.

In addition to our direct sales personnel, we sell through sales representatives and distributors in the United States and Asia. During 2020, we entered into new distribution relationships with Arrow Electronics and DigiKey Electronics, which are two of the largest worldwide IC distributors. These distributors have a global presence with offices and technical selling and applications engineering capabilities, which we believe will enable us to reach new potential customers for our products.

We also have applications engineers who support our customer engagements and engage with the customers’ system architects and designers to propose and implement our IC and IP solutions to address system design challenges.challenges and improve performance.

In the markets we serve, the time from a design win to production volume shipments of our IC products can range from 1812 to 36 months. Networking, communicationswireless and wired communication and security appliance systems can have a product life from a few years to over 10 years once a product like ours has been designed into the system.

Our Historically, our revenue has been highly concentrated, with a few customers accounting for a significant percentage of our total revenue. For

During the year ended December 31, 2019, Flextronics, which primarily purchases on behalf2021, three customers accounted for 10% or more of Palo Alto Networks, Inc.our net revenues, including CEAC International Limited at 48%, WeLink Communications LLC at 19% and Nokia; Clavis Company our Japanese IC distributor; Sanmina and Palo Alto Networks, represented 30%, 17%, 14% and 13% of total revenue, respectively.  ForAlltek Technology Corp at 12%. During the year ended December 31, 2018, Flextronics, which primarily purchases on behalf2020, three customers accounted for 10% or more of Palo Alto Networks,our net revenues, including Ubiquiti Inc. at 55%, XCOM Labs, Inc. at 27% and Nokia; Clavis Company, our Japanese IC distributor; Palo Alto Networks; and Nokia, represented 32%, 18%, 18% and 15% of total revenue, respectively.Alltek Technology Corp at 12%.

Intellectual Property

We regard our patents, copyrights, trademarks, trade secrets and similar intellectual property as critical to our success and rely on a combination of patent, trademark, copyright, and trade secret laws to protect our proprietary rights.

As of December 31, 2019,2021, we held 62 U.S.105 United States and 3455 foreign patents on various aspects of our mmWave, antenna, memory and other technology, with expiration dates ranging from 20212022 to 2037.2040. We also held 625 pending patent applications in the U.S.United States and abroad. There can be no assurance that others will not independently develop or patent similar or competing technology or design around any patents that may be issued to us, or that we will be able to successfully enforce our patents against infringement by others.

We were alsoan activeparticipantin thedevelopmentof theIEEE 802.11ay wireless specificationand, to date, have been grantednine essentialclaimspatentswith respectto thisstandard.Essentialclaimspatentsareof particularvalueas a specificationcannotbe implementedwithoutviolatingthepatents.

The semiconductor industry is characterized by frequent litigation regarding patent and other intellectual property rights. Our IC customers, licensees or we might, from time to time, receive notice of claims that we have infringed patents or other intellectual property rights owned by others. Our successful protection of our patents and other intellectual property rights and our ability to make, use, import, offer to sell, and sell products free from the intellectual property rights of others are subject to a number of factors, particularly those described in Part I, Item 1A, “Risk Factors.”

Competition

mmWave

mmWavecircuitand systemdesignisa highlyspecializedengineeringskill,as wellas a challenging technologyto shipin massproduction.At frequenciesabove 24 GHz,circuitsareextremelyvulnerableto small variancesin thesemiconductormanufacturingprocess.Designingcircuitsthatminimizesusceptibilityto these variancestakesyearsof practice,and we believe we areone of thefew companiesin theworld thatisskilledin mmWave design.Further,we have shippedmmWavedevicesin volume,and ensuringalldevicessoldadhereto strictperformancestandardsisa corecompetencywe havedeveloped. In addition,we have developedourown mmWavephasedarrayantennatechnology,which allowsus to be highlycompetitivein termsof overallsystemcost.Our customers do not need to engage with third-party antennasuppliers,thuseliminatingtheadditionalcostfora third-partyantenna.

IEEE 802.11ad/ayMarket:

Our primarycompetitorin theIEEE802.11ad/aymarketisQualcomm.The primarybenefitthat weprovideto themarketisthesupportof thehigherfrequencybands from66 GHzto 71 GHz.The advantage at these frequencies is that oxygen attenuationissignificantlyreduced,and signalscan travelmuchfurther.

Wealsohave key pointsof differentiationcompared toQualcommforwirelessvideodevices.We are well positioned in thismarket, as we have USB3.0 builtintoour devices,so ourproductsgenerallysupportUSBarchitectures. A primeexampleisthereplacementof theUSBcablewith a wirelessversionusingourtechnology.Thereare manyapplicationswhere thiscan be of use, includingUSBweb cams,wirelessdisplays,and AR/VRheadsets. Wehave investedsignificantsoftwareresourcesintoprovidingthemarketwith wirelessUSBsolutions,and we believe thereisno othermmWavevendorin theworld thatcan offermulti-gigabitsolutionsas a replacementforwired USB.

5G Market:

With5G, oureffortsarefocusedon themmWaveRFfront-endphasedarraycomponentof thesystem. This focus isin contrastto theIEEE solution,in which Perasoprovidesa basebanddeviceas wellas an mmWaveRF front-endphasedarraydevice.The 5G productinstantiationisan RFmodulethatembracesa broadswath of intellectualpropertythatestablishesa substantialmoatto potentialcompetitors.Key elementsof our mmWave intellectual propertyinclude:

•RFcircuits;

•phasedarrayantenna;and

•in-systemcircuitcalibration,beamforming,real-timesystemmonitoring.

Froma competitiveperspective,we arecurrentlytheonly pure-play,5G vendorto offera dual-band (28/39GHz)RFsolutionfortheFWA market.Qualcommdoes offera 5G RFsolution fortheFWA market,however its solutionisbasedon aggregatingitsmobileRFsolution,which requires severalcompromisesin termsof cost,performance,and power consumption. Withan initialfocuson fixed wirelessaccess,wecan deriveadvantagesby optimizingoursiliconforthatspecificmarket.Furthermore, we have experiencedinitialsuccessin theunlicensed,60 GHz,FWA market,and we believewewill be able to transferallof ourknowledge gainedfromthe60 GHzmarketto the5G market. However, thismarketopportunityismore competitive,and potentialcompetitors,in addition toQualcomm, include Mediatekand SamsungElectronicsCo., Ltd., or Samsung.

Memory

The markets for our memory products are highly competitive. We believe that the principal competitive factors are:

10

level of technical support provided.

We believe that our products compete favorably with respect to each of these criteria. Our proprietary 1T-SRAM embedded memory and high-speed serial interface IP can provide our Accelerator Engine ICs with a competitive advantage over alternative devices. Alternative solutions are either DRAM or SRAM-based and can support either the memory size or speed requirements of high-performance networking systems, but generally not both. DRAM solutions provide a significant amount of memory at competitive cost, but DRAM solutions do not have the required fast access and cycle times to enable high-performance. The DRAM solutions currently used in networking systems include RLDRAM from Micron Technology, Inc., or Micron, LLDRAM from Renesas, DDR from Samsung, Electronics Co., Ltd., Micron and others, and HBM, which is stacked DRAM memory from Samsung Electronics Co. and SK Hynix. SRAM solutions can meet high-speed performance requirements, but often lack adequate memory size. The SRAM solutions currently used in networking systems primarily include QDR or similar SRAM products from Cypress Semiconductor Corporation and GSI Technology, Inc. Most of the currently available SRAM and DRAM solutions use a parallel, rather than a serial interface. To offset these drawbacks, system designers generally must use more discrete memory ICs, resulting in higher power consumption and greater utilization of space on the line card.

Our competitors include established semiconductor companies with significantly longer operating histories, greater name recognition and reputation, large customer bases, dedicated manufacturing facilities and greater financial, technical, sales and marketing resources. This may allow them to respond more quickly than us to new or emerging technologies or changes in customer requirements. Generally, customers prefer suppliers with greater financial resources than we have currently. Many of our competitors also have significant influence in the semiconductor industry. They may be able to introduce new technologies or devote greater resources to the development, marketing and sales of their products than we can. Furthermore, in the event of a manufacturing capacity shortage, these competitors may be able to manufacture products when we are unable to do so.

Our Accelerator Engine ICs compete with embedded memory solutions, stand-alone memory ICs, including both DRAM and SRAM ICs, ASICs designed by customers in-house to meet their system requirements, and NPUs that use significant internal memory and customer-designed software to implement tasks. Our prospective customers may be unwilling to adopt and design-in our ICs due to the uncertainties and risks surrounding designing a new IC into their systems and relying on a supplier that has limited history of manufacturing such ICs and limited financial resources. In addition, Accelerator Engine ICs require the customer and its other IC suppliers to implement our chip-to-chip communication protocol, the GCI interface. These parties may be unwilling to do this if they believe it could adversely impact their own future product developments or competitive advantages, or, if they believe it might complicate their development process or increase the cost of their products. To remain competitive, we believe we must provide unparalleled memory IC solutions with the highest bandwidth capability for our target markets, which solutions are engineered and built for high-reliability carrier and enterprise applications.

Our LineSpeed PHY ICs compete with solutions offered by Broadcom Ltd., Inphi Corporation, M/A-COM Technology Solutions Holdings, Inc. and Semtech Corp., as well as other smaller analog signal processing companies. We also may compete with ASICs designed by customers in-house to meet their system requirements, as well as by optical module OEMs. The market for our LineSpeed products is highly competitive, and customers have a number of suppliers they can choose from. We must provide differentiated features with a reasonable IC power budget, while offering competitive pricing.  To date, we have had limited success selling and marketing these products.

Manufacturing

We depend on third-party vendors to manufacture, package, assemble and test our IC products, as we do not own or operate a semiconductor fabrication, packaging or production testing facility. By outsourcing manufacturing, we can avoid the high cost associated with owning and operating our own facilities, allowing us to focus our efforts on the design and marketing of our products.

11

We perform an ongoing review of our product manufacturing and testing processes. Our IC products are subjected to extensive testing to assess whether their performance meets design specifications. Our test vendors provide us with immediate test data and the ability to generate characterization reports that are made available to our customers. We have achieved ISO 9001:2015 certification, and all of our significant manufacturing vendors have also achieved ISO 9001 certification.

Employees

As of December 31, 2019,2021, we had 2382 employees, all of whom areincluding 22 located in the United States consistingand 60 located in Canada. Our headcount consists of 1464 in research and development and manufacturing operations and 918 in sales, marketing and general and administrative functions.

Available Information

We were founded in 1991 and reincorporated in Delaware in September 2000. Our website address is www.mosys.com.www.peraso.com. The information in our website is not incorporated by reference into this report. Through a link on the Investor section of our website, we make available our annual reports on Form 10-K, quarterly reports on Form 10-Q, current reports on Form 8-K, and any amendments to those reports filed or furnished pursuant to Section 13(a) or 15(d) of the Securities Exchange Act, of 1934, as soon as reasonably practicable after they are filed with, or furnished to, the Securities and Exchange Commission, or SEC. You can also read any materials submitted electronically by us to the SEC on its website (www.sec.gov), which contains reports, proxy and information statements, and other information regarding issuers that file electronically with the SEC, including us.

Item 1A.  Risk Factors

The following risks could materially and adversely affect our business, financial condition, cash flows, and results of operations, and the trading price of our common stock could decline. These risk factors do not identify all risks that we face. Our operations could also be affected by factors that are not presently known to us or that we currently consider to be immaterial to our operations. Due to risks and uncertainties, known and unknown, our past financial results may not be a reliable indicator of futurefuture performance, and historical trends should not be used to anticipate results or trends in future periods. Refer also to the other information set forth in this Annual Report on Form 10-K, including in Part II, Item 7, “Management’s Discussion and Analysis of Financial Condition and Results of Operations” as well as our Consolidated Financial Statements and the related notes in Part II, Item 15.

We may not realizeallof the anticipatedbenefitsof the recent business combination.

In December 2021, we completed the Arrangement.The successof theArrangementwilldepend on, amongotherthings,our abilityto integratethebusinessesof Peraso Techand MoSys in a timelyfashion.Additionally,we maynot be ableto successfullyachievethelevelof costsavings,revenueenhancementsand synergies thatweexpect.Ifwe arenot ableto successfullyachievetheseobjectives,theanticipated benefitsof theArrangementmaynot be realizedfullyor atallor maytakelongerto realizethanexpected.In addition,failureto successfullyintegratethebusinessesin theexpectedtimeframemayadverselyaffectourbusiness,financialcondition,resultsof operationsor cashflows.In addition,the combinedoperationof two businessesmaybe a complex,costlyand time-consumingprocess.The difficultiesof combiningtheoperationsof thecompaniesinclude,interalia:

•theabilityof officersand directorsto, as required,effectivelytransferoperationalknowledge of

MoSys, especiallytheproductionof theMoSys products,to thenew managementteam;

•thediversionof managementattentionto integrationmatters;

•difficultiesin integratingfunctions,personnel,and systems;

•difficultiesin assimilatingemployeesand in attractingand retainingkey personnel;

•declinesin our resultsof operations,financialconditionor cashflows;

•a declinein themarketpriceof our common stock;

•contingentliabilitiesthatarelargerthanexpected;

•thedisruptionof, or thelossof momentumin, ongoing researchand development,.

Many of thesefactorsareoutsideourcontrol, and any one of themcouldresultin increasedcosts, decreasedexpectedrevenuesand diversionof managementtimeand energy,which couldmateriallyimpactour business,financialcondition,resultsof operationsand cashflows. These factors couldcause our operating results to suffer, decreaseor delaytheexpectedbenefits of theArrangementand negativelyimpactthepriceof our common stock. As a result,itcannotbe assuredthatwe willrealizethefullbenefitsanticipatedfromtheArrangementwithintheanticipatedtime frames,or atall.

Even ifthebusinesses areintegrated,therecan be no assurancethattheArrangementwillresultin therealizationof thefullbenefitof theanticipatedsynergiesand costsavingsor thatthesebenefitswillbe realizedwithintheexpectedtimeframesor atall.Difficultiesin integratingthebusinessescouldharm  our reputation. In addition,by engagingin the Arrangement,MoSys and Perasomayforegoor delaypursuitof otheropportunitiesthatmayhave provento have greatercommercialpotential.

We have a history of losses and we willmay need to raise additional capital in the future.

We recorded a net loss of approximately $2.6$10.9 million for the year ended December 31, 2019,2021, and ended the period with an accumulated deficit of approximately $238$117.1 million. We recorded a net loss of approximately $11.4$15.3 million for the year ended December 31, 2018,2020, and ended the period with an accumulated deficit of approximately $236$106.3 million. These and prior-year losses have resulted in significant negative cash flows and have required us to raise substantial amounts of additional capital during this period.flows. To remain competitive and expand our product offerings to customers, we will need to increase revenues substantially beyond levels that we have attained in the past in order to generate sustainable operating profit and sufficient cash flows to continue doing business without raising additional capital from time to time. Given our history of fluctuating revenues and operating losses, and the challenges we face in securing customers for our IC products, we cannot be certain that we will be able to achieve and maintain profitability on either a quarterly or annual basis in the future. As a result, we willmay need to raise additional capital in the future, which may or may not be available to us at all or only on unfavorable terms.

The full effects of COVID-19 and other potential future public health crises, epidemics, pandemics or similar events are uncertain and could have a material and adverse effect on our business, financial condition, operating results and cash flows.

The global outbreak of the coronavirus disease 2019, or COVID-19, was declared a pandemic by the World Health Organization and a national emergency by the U.S. government in March 2020. This has negatively affected the world economy, disrupted global supply chains, significantly restricted travel and transportation, resulted in mandated closures and orders to “shelter-in-place” and created significant disruption of the financial markets. The extent of the impact on our operational and financial performance will depend on future developments, including the duration and spread of the pandemic and related actions U.S. and foreign government agencies continue to take to prevent disease spread, all of which are uncertain, out of our control and cannot be predicted.

In accordance with applicable U.S. governmental ordinances generally exempting essential businesses and/or critical infrastructure workforces from mandated closures and orders to “shelter-in-place,” we are operating in support of essential products and services, subject to limitations and requirements in applicable state and county orders. We have been complying with county and state orders and have implemented a teleworking policy for our employees and contractors and significantly minimized the number of employees who visit our office. Since the outbreak of COVID-19, while we have experienced increased lead times for wafers, substrates and assembly services, we have experienced minimal impact on our production operations and have been able to satisfy all customer purchase orders timely. However, a facility closure, work slowdowns or temporary stoppage at one of our manufacturing suppliers could occur, which could have a longer-term impact and could delay our production and ability to conduct business and negatively impact our business, financial condition, operating results and cash flows.  

If our workforce is unable to work effectively, including because of illness, quarantines, absenteeism, government actions, facility closures, travel restrictions or other restrictions in connection with the COVID-19 pandemic, our operations will be negatively impacted. We may be unable to produce and sell our IC products, and our costs may increase as a result of the COVID-19 outbreak. The impacts could worsen if there is an extended duration of any COVID-19 outbreak or a resurgence of COVID-19 infection in affected regions after they have begun to experience improvement.

The continued spread of COVID-19 has also led to disruption and volatility in the global capital markets. We may be unable to access the capital markets, and additional capital may only be available to us on terms that could be significantly detrimental to our existing stockholders and to our business.

We are working with our stakeholders, including customers, suppliers and employees, to address the impact of this global pandemic. We continue to monitor the situation, to assess further possible implications to our business, supply chain and customers, and to take actions in an effort to mitigate adverse consequences. Should such disruption continue for an extended period of time, or if and when the pandemic ends, the resumption of normal business operations may be delayed or constrained by lingering effects of the pandemic (including limitations imposed by governmental authorities on our ability to return to normal operating practices). These effects, alone or taken together, could have a material adverse impact on our business, results of operations or financial condition.

Our failure to raise additional capital or generate the significant capital necessary or raise additional capital to expand our operations and invest in new products could reduce our ability to compete and could harm our business.

We intend to continue spending to grow our business. Despite the successful completion of our public offeringIf we do not achieve and repayment of a portion of and extension of the repayment date for  our Senior Secured Convertible Notes in October 2018,maintain profitability, we still mightwill need to obtain additional financing to pursue our business strategy, develop new products, respond to competition and market opportunities and acquire complementary businesses or technologies, in addition to repaying these notes.technologies. There can be no assurance that such additional capital, whether in the form of debt or equity financing, will be sufficient or available and, if available, that such capital will be offered on terms and conditions acceptable to us.

If we were to raise additional capital through sales of our equity securities, our stockholders would suffer dilution of their equity ownership, as exemplified by the substantial share dilution resulting from our October 2018 public offering.ownership. If we engage in a subsequent debt financing, we may be required to accept terms that restrict our ability to incur additional indebtedness, prohibit us from paying dividends, repurchasing our stock or making investments, and force us to maintain specified liquidity or other ratios, any of which could harm our business, operating results and financial condition. If we need additional capital and cannot raise it on acceptable terms, we may not be able to, among other things:

13

Our failure to successfully market our products could seriously harm our ability to execute our business strategy and may force us to curtail our research and development plans or existing operations.

Our success depends upon the acceptance by our target markets of our ICsproducts and technologies by original equipment suppliers to the cloud networking, security and other systems markets.manufacturers or OEMs. Our prospective customers may be unwilling to adopt and design-in our ICsproducts due to the uncertainties and risks surrounding designing a new IC or module and/or incorporating new IP into their systems and relying on a supplier that has a limited history of manufacturing such ICs. For example, our Accelerator Engine IC products require our customers and their other IC suppliers to implement our proprietary GigaChip chip-to-chip communication protocol, which they may be unwilling to do. In the past, we have experienced reluctance by potential customers to adopt our GigaChip interface.small, sole-sourced supplier. Thus, currently, we do not know whether we will be able to generate adequate profit from making and selling our products.products and licensing our technologies.

An important part of our strategy to gain market acceptance is to penetrate new markets by targeting market leaders to accept our ICtechnology solutions. This strategy is designed to encourage other participants in those markets to follow these leaders in adopting our solutions. If a high-profile industry participant adopts our ICsproducts for one or more of its products but fails to achieve success with those products, or is unable to successfully implement our ICs,products, other industry participants’ perception of our solutions could be harmed. Any such event could reduce the amount of future sales of our IC products.

Future revenue growth depends on our winning designs with existing and new customers, retaining current customers, and having those customers design our solutions into their product offerings and successfully selling and marketing such products. If we do not continue to win designs in the short term, our product revenue in the following years will not grow.

We sell our ICs to OEM customers that include our ICs and modules in their products. Our technology is generally incorporated into products at the design stage, which we refer to as a design win, and which we define as the point at which a customer has made a commitment to build a board against a fixed schematic for its system, and this board will utilize our ICs.products. As a result, our future revenue depends on our OEM customers designing our ICsproducts into their products, and on those products being produced in volume and successfully commercialized. If we fail to retain our current customers or convince our current or prospective customers to include our ICsproducts in their products and fail to achieve a consistent number of design wins, our results of operations and business will be harmed. In addition, if a current or prospective customer designs a competitor’s offering into its product, it becomes significantly more difficult for us to sell our IC solutionsproducts to that customer because changing suppliers involves significant cost, time, effort and risk for the OEM. Even if a customer designs one of our ICs or modules into its product, we cannot be assured that the OEM’s product will be commercially successful over time, or at all, or that we will receive or continue to receive any revenue from that customer. Furthermore, the customer product for which we obtain a design win may be canceled before the product enters production or before or after it is introduced into the market. Because of our extended sales cycle, our revenue in future years is highly dependent on design wins we are awarded today. Our lack of capital and uncertainty about our future technology roadmap also may limit our

success in achieving additional design wins, as discussed under “We may experience difficulties in transitioning to new wafer fabrication process technologies or in achieving higher levels of design integration, which may result in reduced manufacturing yields, delays in product deliveries and increased costs.”

The design win process for our products is generally a lengthy, expensive and competitive, process, with no guarantee of revenue, and, if we fail to generate sufficient revenue to offset our expenses, our business and operating results would suffer.

Achieving a design win for one of our products is typically a lengthy, expensive and competitive process because our customers generally take a considerable amount of time to evaluate our ICs.products. In the markets we serve, the time from initial customer engagement to design win to production volume shipments can range from twoone to three years, though it may take longer for new customers or markets we intend to address. In order to win designs, we are required to both incur design and development costs and dedicate substantial engineering resources in pursuit of a single customer opportunity. Even though we incur these costs we may not prevail in the competitive selection process, and, even if we do achieve a design win, we may never generate sufficient, or any, revenue to offset our development expenditures. Our customers have the option to decide whether or not to put our solutions into production after initially designing our products in the specification. The customer can make changes to its product after a design win

14

has been awarded to us, which can have the effect of canceling a previous design win. This occurred in 2018 when a large customer decided to phase out its use of our memory products. The delays inherent in our protracted sales cycle increase the risk that a customer will decide to cancel, curtail, reduce or delay its product plans, causing us to lose anticipated revenue. In addition, any change, delay or cancellation of a customer’s plans could harm our financial results, as we may have incurred significant expense while generating no revenue.

If our foundries do not achieve satisfactory yields or quality, our cost of net revenue will increase, our operating margins will decline and our reputation and customer relationships could be harmed.

We depend not only on sufficient foundry manufacturing capacity and wafer prices, but also on good production yields (the number of good die per wafer) and timely wafer delivery to meet customer demand and maintain profit margins. The fabrication of our products is a complex and technically demanding process. Minor deviations in the manufacturing process can cause substantial decreases in yields and, in some cases, cause production to be suspended. Our foundry, Taiwan Semiconductor Manufacturing Company, or TSMC, fromFrom time to time, experiencesour foundries experience manufacturing defects and reduced manufacturing yields. Changes in manufacturing processes or the inadvertent use of defective or contaminated materials by our foundries could result in lower than anticipated manufacturing yields, which would harm our revenue or increase our costs. For example, in the past, one of our foundryfoundries produced ICs and met its process specification range but did not meet our customer’s specifications causing us to write off a portion of our production lot. Many of these problems are difficult to detect at an early stage of the manufacturing process and may be time consuming and expensive to correct. Poor yields from our foundry, or defects, integration issues or other performance problems in our ICs, could cause us significant customer relations and business reputation problems, harm our operating results and give rise to financial or other damages to our customers. Our customers might consequently seek damages from us for their losses. A product liability claim brought against us, even if unsuccessful, would likely be time consuming and costly to defend.

We may experience difficulties in transitioning to new wafer fabrication process technologies or in achieving higher levels of design integration, which may result in reduced manufacturing yields, delays in product deliveries and increased costs.

We aim to use the most advanced manufacturing process technology appropriate for our solutions that is available from TSMC.our foundries. As a result, we periodically evaluate the benefits of migrating our solutions to other technologies in order to improve performance and reduce costs. These ongoing efforts require us from time to time to modify the manufacturing processes for our products and to redesign some products, which in turn may result in delays in product deliveries. We are dependent on TSMCour foundries to support the production of wafers for future versions of our ICs, as TSMC is our sole foundry.IC. Such production may require changes to TSMC’sthe foundry’s existing process technology. If TSMCthe foundry elects to not alter their process technology to support future versions of our ICs, we would need to identify a new foundry.

15

In addition,For example, our 1T-SRAM technology used in our Accelerator Engine products is not available at process nodes below 40 nanometers. To date, we have not developed any memory products below the 40-nanometer process node. Tonode and have no plans to continue the product roadmap for our Accelerator Engine products, we will need to identify a new foundry and/or no longer use our 1T-SRAM technology.products. We do not consider this to adversely affect our current product offerings, but we expect to face difficulties, delays and increased expense if we transition our products to new processes and potentially to new foundries for future products. For example, we believe any next generation of products will need to be designed using a more advanced process, which would require us to incur significantly high development costs for mask tooling and computer-aided design software. We currently lack the funds to pay for such development costs. Moreover, an inability to continue our product roadmap can adversely affect, and has in the past affected, our efforts to win new customers for these products, secure additional design wins and significantly grow our future revenues.

BecauseIf Taiwan Semiconductor Manufacturing, or TSMC, which is the manufacturingsole foundry for producing our memory ICs were to discontinue the foundry process used to produce our Accelerator Engine products, we would not be in a position to transition production of integrated circuits is extremely complex, the process of qualifyingthese products to a new foundry is a lengthy process and there can be no assurance that we will be ablecontinue to findmanufacture our products and qualify replacement suppliers without materially adversely affectingthis would require us to discontinue production of these products and would negatively impact our business, financial condition,future revenues results of operations and prospects for future growth. We cannot assure you thatcash flows.

To date, we will be able to maintain our relationship with our current foundry or develop relationships with new foundries. If we or TSMC experience significant delays in transitioning to smaller geometries or fail to efficiently implement transitions, we could experience reduced manufacturing yields, delays in product deliveries and increased costs, any of which could harm our relationships with our customers and our operating results.

We mayhave not achieveachieved the anticipated benefits of a fabless semiconductor company by developing and bringing to market our IC products.company.

Our goal ishas been to increase our total available market by creating high-performance ICs for mmWave, 5G, networking communications, and data center systems and other markets using our proprietary technology and design expertise. In recent years,Historically, this development effort has required that we add headcount and design resources, such as expensive software tools, which has increased our losses from, and cash used in, operations. Due to our limited financial resources, we have beenwere unable to sustain theseour memory IC development efforts and curtailed them in 2017. We may not be successful in our developmentOur efforts to bringincrease our ICs to market successfully nor be successful in selling ICs duerevenue and expand our markets have been subject to various risks and uncertainties, including, but not limited to:

16

If we experience significant delays in bringing our IC products to market, or if customer adoption of our products is delayed or if our customers’ products that include our IC products are not successful, this could have a material adverse effect on our anticipated revenues in upcoming years due to the potential loss of design wins and future revenues. We could experience significant delays in the future.

Our main objective is the development and sale of our productstechnologies to cloud networking, security, test and video system providers and their subsystem and component vendors and, if demand for these products does not grow, we may not achieve revenue growth and our strategic objectives.

We market and sell our ICs and IP to mmWave, 5G,cloud networking, communications, data center and other equipment providers and their subsystem and component vendors. We believe our future business and financial success depends on market acceptance and increasing sales of these products. In order toTo meet our growth and strategic objectives, networking infrastructure OEMs must incorporate our products into their systems and the demand for their systems must grow as well. We cannot provide assurance that sales of our products to these OEMs will increase substantially in the future or that the demand for our customers’ systems will increase. Our future revenues from these products may not increase in accordance with our growth and strategic objectives if, instead, our OEM customers modify their product designs, select products sold by our competitors or develop their own proprietary ICs.technologies. Moreover, demand for their products that incorporate our ICstechnologies may not grow or result in significant sales of such products due to factors affecting the customers and their business such as industry downturns, declines in capital spending in the enterprise and carrier markets or unfavorable macroeconomic conditions. Thus, the future success of our business depends in large part on factors outside our control, and sales of our products may not meet our revenue growth and strategic objectives.

Our failure to continue to develop new products and enhance our products on a timely basis could diminish our ability to attract and retain customers.

The existing and potential markets for our products are characterized by ever-increasing performance requirements, evolving industry standards, rapid technological change and product obsolescence. These characteristics lead to periodic changes in customer requirements, shorter product life cycles and changes in industry demands and mandate new product introductions and enhancements to maintain customer engagements and design wins. In order to attain and maintain a significant position in the market, we will need to continue to enhance and evolve our products and the underlying proprietary technologies in anticipation of these market trends although we do not have a large engineering staff.

Our future performance depends on a number of factors, including our ability to:

Our failure to enhance our existing IC products and develop future products that achieve broad market acceptance will harm our competitive position and impede our future growth.

17

Our ICs have a lengthy sales cycle, which makes it difficult to predict success in this market and the timing of future revenue.

Our ICs have a lengthy sales cycle, ranging from six to 24 months from the date of our initial proposal to a prospective customer until the date on which the customer confirms that it has designed our product into its system. An even lengthier period could ensue before we would know the volume of products that such customer will, or is likely to, order. A number of factors can contribute to the length of the sales cycle including technical evaluations of our products by the customers, the design process required to integrate our products into the customers’ products and the timing of the customers’ new product announcements. In anticipation of product orders, we may incur substantial costs before the sales cycle is complete and before we receive any customer payments. As a result, in the event that a sale is not completed or is cancelled or delayed, we may have incurred substantial expenses, making it more difficult for us to become profitable or otherwise negatively impacting our financial results. Furthermore, because of this lengthy sales cycle, the recording of revenues from our selling efforts may be substantially delayed, our ability to forecast our future revenue may be more limited and our revenue may fluctuate significantly from quarter to quarter. We cannot provide any assurances that our efforts to build a strong and profitable business based on the sale of ICs will succeed. If these efforts are not successful, in light of the substantial resources that we have invested, our future operating results and cash flows could be materially and adversely affected.

The semiconductor industry is cyclical in nature and subject to periodic downturns, which can negatively affect our revenue.

The semiconductor industry is cyclical and has experienced pronounced downturns for sustained periods of up to several years. To respond to any downturn, many semiconductor manufacturers and their customers will slow their research and development activities, cancel or delay new product developments, reduce their workforces and inventories and take a cautious approach to acquiring new equipment and technologies. As a result, our business has been in the past and could be adversely affected in the future by an industry downturn which could negatively impact our future revenue and profitability. Also, the cyclical nature of the semiconductor industry may cause our operating results to fluctuate significantly from year-to-year.

We expect our royalty revenues to decrease compared with our historical results, and there is no guarantee revenues from our IC products will replace these lost revenues in the near future.

We are no longer actively pursuing new license arrangements for our 1T-SRAM technologies, and, as a result, our royalty and other revenues in 2018 declined when compared with prior years. In addition, the production volumes of the current royalty-bearing products shipped by our licensees are expected to decrease; therefore we expect our royalty revenue to decrease in 2020 and future periods. Historically, royalties have generated a 100% gross margin, and any decrease in royalties adversely affects our gross margin, operating results and cash flows.

Our revenue has been highly concentrated among a small number of customers, and our results of operations could be harmed if we lose a key revenue source and fail to replace it.

Our overall revenue has been highly concentrated, with a few customers accounting for a significant percentage of our total revenue.  For the year ended December 31, 2019,2021, our three largest customers represented 30%, 17% and 14%approximately 81% of total revenue, respectively. For the year ended December 31, 2018, our three largest customers represented 32%, 18% and 18% of total revenue, respectively.revenue. We expect that a relatively small number of customers will continue to account for a substantial portion of our revenue for the foreseeable future.

18

As a result of this revenue concentration, our results of operations could be adversely affected by the decision of a single key customer to cease using our technology or products or by a decline in the number of products that incorporate our technology that are sold by a single licensee or customer or by a small group of licensees or customers.

Our revenue concentration may also pose credit risks which could negatively affect our cash flow and financial condition.

We might also face credit risks associated with the concentration of our revenue among a small number of licensees and customers. As ofAt December 31, 2019,2021, four customers represented 85%approximately 92% of total trade receivables. Our failure to collect receivables from any customer that represents a large percentage of receivables on a timely basis, or at all, could adversely affect our cash flow or results of operations.

Our products must meet exact specifications and defects and failures may occur, which may cause customers to return or stop buying our products.

Our customers generally establish demanding specifications for quality, performance and reliability that our products must meet. However, our products are highly complex and may contain defects and failures when they are first introduced or as new versions are released. If defects and failures occur in our products during the design phase or after, we could experience lost revenues, increased costs, including warranty and customer support expenses and penalties for non-performance stipulated in customer purchase agreements, delays in or cancellations or rescheduling of orders or shipments, product returns or discounts, diversion of management resources or damage to

our reputation and brand equity, and in some cases consequential damages, any of which would harm our operating results. In addition, delays in our ability to fill product orders as a result of quality control issues may negatively impact our relationship with our customers. We cannot assure you that we will have sufficient resources to satisfy any asserted claims. Furthermore, any such defects, failures or delays may be particularly damaging to us as we attempt to establish our reputation as a reliable provider of IC and module products.

Because we sell our products on a purchase order basis and rely on estimated forecasts of our customers’ needs, inaccurate forecasts could adversely affect our business.

We sell our IC products pursuant to individual purchase orders rather than long-term purchase commitments. Therefore, we will rely on estimated demand forecasts, based upon input from our customers, to determine how much product to manufacture. Because our sales are based primarily on purchase orders, our customers may cancel, delay or otherwise modify their purchase commitments with little or no notice to us. For these reasons, we will generally have limited visibility regarding our customers’ product needs. In addition, the product design cycle for networking OEMs is lengthy and it may be difficult for us to accurately anticipate when they will commence commercial shipments of products that include our ICs.ICs or modules.

Furthermore, if we experience substantial warranty claims, our customers may cancel existing orders or cease to place future orders. Any cancellation, delay or other modification in our customers’ orders could significantly reduce our revenue, cause our operating results to fluctuate from period to period and make it more difficult for us to predict our revenue. In the event of a cancellation or reduction of an order, we may not have enough time to reduce operating expenses to mitigate the effect of the lost revenue on our business.

If we overestimate customer demand for our products, we may purchase products from our manufacturers that we cannot sell. Conversely, if we underestimate customer demand or if sufficient manufacturing and testing capacity are unavailable, we would forego revenue opportunities and could lose market share in the markets served by our products and could incur penalty payments under our customer purchase agreements. In addition, our inability to meet customer requirements for our products could lead to delays in product shipments, force customers to identify alternative sources and otherwise adversely affect our ongoing relationships with our customers.

19

We depend on contract manufacturers for a significant portion of our revenue from the sale of our IC products.

Many of our current and prospective OEM customers use third party contract manufacturers to manufacture their systems and these contract manufacturers purchase our products directly from us on behalf of the OEMs. Although we expect to work with our OEM customers in the design and development phases of their systems, these OEMs often give contract manufacturers some authority in product purchasing decisions. If we cannot compete effectively for the business of these contract manufacturers, or if any of the contract manufacturers that work with our OEM customers experience financial or other difficulties in their businesses, our revenue and our business could be adversely affected. For example, if a contract manufacturer becomes subject to bankruptcy proceedings, we may not be able to obtain our products held by the contract manufacturer or recover payments owed to us by the contract manufacturer for products already delivered to the contract manufacturer. If we are unable to persuade contract manufacturers to purchase our products, or if the contract manufacturers are unable to deliver systems with our products to OEMs on a timely basis, our business would be adversely affected.

We rely on independent foundries and contractors for the manufacture, assembly, testing and packaging of our integrated circuits and modules, and the failure of any of these third parties to deliver products or otherwise perform as requested could damage our relationships with our customers and harm our sales and financial results.

As a fabless semiconductor company, we rely on third parties for substantially all of our manufacturing operations. We depend on these parties to supply us with material in a timely manner that meets our standards for yield, cost and quality. We do not have long-term supply contracts with any of our suppliers or manufacturing service providers, and therefore they are not obligated to manufacture products for us for any specific period, in any specific quantity or at any specified price except as may be provided in a particular purchase order. Any problems with our manufacturing supply chain, including disruptions due to the COVID-19 global pandemic,could adversely impact our ability to ship our products to our customers on time and in the quantity required which in turn could damage our customer relationships and impede market acceptance of our IC solutions.

20

Our third-party wafer foundriesfoundry and testing and assembly vendors are located in regions at high risk for earthquakes and other natural disasters.disasters and adverse consequences related to the outbreak of contagious diseases such as COVID-19. Any disruption to the operations of these foundries and vendors resulting from earthquakes or other natural disasters could cause significant delays in the development, production, shipment and sales of our IC products.

TSMC, which manufacturesCertain vendors that we utilize to manufacture our products isare located in Asia, as are other foundries we may use in the future. Our vendors that provide substrates and wafer sorting and handle the testing of our products are headquartered in either Asia or the San Francisco Bay Area of California. Our primary manufacturing operations are located in San Jose, California. The risk of an earthquake in the Pacific Rim region is significant due to the proximity of major earthquake fault lines. The occurrence of earthquakes or other natural disasters could result in the disruption of the wafer foundry or assembly and test capacity of the third parties that supply these services to us and may impede our research and development efforts as well as our ability to market and sell our products. We may not be able to obtain alternate capacity on favorable terms, if at all.

We face risks related to health epidemics whichThe COVID-19 global pandemic, along with outbreaks of new contagious diseases or the resurgence of existing diseases that significantly affect the Asia-Pacific region could adversely affect our business and results of operations.

Our business could be materially adversely affected by a widespread outbreak of contagious disease, includingdisrupt the recent outbreak of respiratory illness caused by a novel coronavirus first identified in China, known as COVID-19. We rely on TSMC and other suppliers, manufacturers and subcontractors located in nearby Taiwan for the manufacturingoperations of our products. The effects of this outbreak could include disruptions or restrictions on our employees’ ability to travel in Asia and other affected regions, as well as temporary closures of the facilities of our suppliers, customers, or other vendors in our supply chain, which could impact our business, interactions and relationships with our customers, third-partykey suppliers and contractors, and results of operations. In addition, a significant outbreak of contagious diseases manufacturing partners.

Disruptionsin oursupplychain due to shortagesin the human population globalsemiconductorbusinesscould result cause delaysforcustomersand impactrevenue.

Wemayexperiencedisruptions in ourglobalsemiconductorsupplychain,with suppliersincreasing leadtimesor placingproductson allocation,includingprocuringnecessarycomponents, wafers,substratesandassemblyservicesin a widespread health crisis that could adversely affect the economies timelyfashion.As a resultof thesepotentialsupplychaindisruptions,wemaybe requiredto increasecustomerorderleadtimesand financial markets placedsomeproductson allocation.Wemaybe unableto satisfyallof many countries, resulting thedemandforourproducts,which mayadverselyaffectcustomerrelationshipsand impactrevenue.

Priceincreasesfrom our supplychain can adverselyimpactrevenueor reducemargins.

Oursupplierscan increasethepriceof productsand servicesprovidedto us.Findingand qualifying alternateor additionalsuppliersin an economic downturn that could reduce responseto increasedpricingfromsupplierscan be a lengthyprocessand can leadto productiondelaysor additionalcosts,and such alternativesaresometimesnot available.Ifwe are unableto increasethe demand for priceof our products and likely impact to our results of operations.customersin responseto increasedcosts,wewouldfacereduced margins.

Any claim that our products or technology infringe third party intellectual propertyIP rights could increase our costs of operation and distract management and could result in expensive settlement costs or the discontinuance of our technology licensing or product offerings. In addition, we may incur substantial litigation expense which would adversely affect our profitability.

The semiconductor industry is characterized by vigorous protection and pursuit of intellectual propertyIP rights or positions which has resulted in often protracted and expensive litigation. We are not aware of any third party intellectual propertyIP that our products or technology would infringe. However, like many companies of our size with limited resources, we have not searched for all potentially applicable intellectual propertyIP in the public databases. It is possible that a third party now has, or may in the future obtain, patents or other intellectual property rights that our products or technology may now, or in the future, infringe. Our licensees and IC customers, or we, might, from time to time, receive notice of claims that we have infringed patents or other intellectual propertyIP rights of others. Litigation against us can result in significant expense and divert the efforts of our technical and management personnel whether or not the litigation has merit or results in a determination adverse to us.

21

The discovery of defects in our technology and products could expose us to liability for damages.

The discovery of a defect in our technologies and products could lead our customers to seek damages from us. Many of our agreements with customers include provisions waiving implied warranties regarding our technology and products and limiting our liability to our customers. We cannot be certain, however, that the waivers or limitations of liability contained in our agreements with customers will be enforceable.

Royalty amounts owed to us might be difficult to verify, and we might find it difficult, expensive and time-consuming to enforce our license agreements.

The standard terms of our 1T-SRAM license agreements require our licensees to document the manufacture and sale of products that incorporate our technology and generally report this data to us after the end of each quarter. We have the right to audit these royalty reports periodically, although we have not conducted any such audits recently. These audits can be expensive, time-consuming and potentially detrimental to our business relationships. A failure to fully enforce the royalty provisions of our license agreements could cause our revenue to decrease and impede our ability to achieve and maintain profitability.

We might not be able to protect and enforce our intellectual propertyIP rights which could impair our ability to compete and reduce the value of our technology.

Our technology is complex and is intended for use in complex ICs and networking systems. Our licensees’ products utilize our embedded memory and/or interface technology and a large number of companies manufacture and market these products. Because of these factors, policing the unauthorized use of our intellectual propertyIP is difficult and expensive. We cannot be certain that we will be able to detect unauthorized use of our technology or prevent other parties from designing and marketing unauthorized products based on our technology. In the event we identify any past or present infringement of our patents, copyrights or trademarks, or any violation of our trade secrets, confidentiality procedures or licensing agreements, we cannot assure you that the steps taken by us to protect our proprietary information will be adequate to prevent misappropriation of our technology. Our inability to adequately protect our intellectual propertyIP would reduce significantly the barriers of entry for directly competing technologies and could reduce the value of our technology. Furthermore, we might initiate claims or litigation against third parties for infringement of our proprietary rights or to establish the validity of our proprietary rights. Litigation by us could result in significant expense and divert the efforts of our technical and management personnel whether or not such litigation results in a determination favorable to us.

Our existing patents might not provide us with sufficient protection of our intellectual property,IP, and our patent applications might not result in the issuance of patents, either of which could reduce the value of our core technology and harm our business.

We rely on a combination of patents, trademarks, trade secret laws and confidentiality procedures to protect our intellectual propertyIP rights. We cannot be sure that any patents will be issued from any of our pending applications or that any claims allowed from pending applications will be of sufficient scope or strength, or issued in all countries where our products can be sold, to provide meaningful protection or any commercial advantage to us. Failure of our patents or patent applications to provide meaningful protection might allow others to utilize our technology without any compensation to us.

If we fail to retain key personnel, our business and growth could be negatively affected.

Our business has been dependent to a significant degree upon the services of a small number of executive officers and technical employees. The loss of key personnel could negatively impact our technology development efforts, our ability to deliver products under our existing agreements, maintain strategic relationships with our partners and obtain new customers. We generally have not entered into employment or non-competition agreements with any of our employees and do not maintain key-man life insurance on the lives of any of our key personnel.

22Our ability to utilize our net operating loss carryforwards is limited as a result of an “ownership change,” as defined in Section 382 of the Internal Revenue Code of 1986, as amended.

WeAs of December 31, 2021, we had over $100.0 million of net operating loss, or NOL, carryforwards for U.S. federal tax purposes. Under U.S. federal income tax law, we generally can use our NOL carryforwards (and certain related tax credits) to offset ordinary taxable income, thereby reducing our U.S. federal income tax liability, for up to 20 years from the year in which the losses were generated, after which time they will expire. Our California NOL carryforwards (and certain related tax credits) generally may incurbe used to offset future state taxable income for 20 years from the year in which the losses are generated, depending on the state, after which time they will expire. The rate at which we can utilize our NOL carryforwards is limited (which could result in NOL carryforwards expiring prior to their use) each time we experience an “ownership change,” as determined under Section 382 of the Internal Revenue Code. A Section 382 ownership change generally occurs if a shareholder or a group of shareholders who are deemed to own at least 5% of our common stock increase their ownership by more than 50 percentage points over their lowest ownership percentage within a rolling three-year period. If an ownership change occurs, Section 382 generally would impose an annual limit on the amount of post-ownership change taxable income that may be offset with pre-ownership change NOL carryforwards equal to the product of the total value of our outstanding equity immediately prior to the ownership change (reduced by certain items specified in Section 382) and the U.S. federal long-term tax-exempt interest rate in effect at the time of the ownership change. A number of special and complex rules apply in calculating this Section 382 limitation. While the complexity of Section 382 makes it difficult to determine whether and when an ownership change has occurred, and a formal study has not been performed, we believe that a Section 382 ownership change occurred as a result of a financing effected in October 2018. The Company believes this Section 382 limitation will result in substantially all of our federal and state NOLs federal tax credit carryforwards incurred prior to October 2018 expiring before they can be utilized. An additional debtownership change may occur upon the consummation of this offering. In addition, our ability to use our NOL carryforwards will be limited to the extent we fail to generate enough taxable income in the future subjectbefore they expire. Existing and future Section 382 limitations and our inability to certain limitations containedgenerate enough taxable income in the future could result in a substantial portion of our Senior Secured Convertible Notes.NOL carryforwards expiring before they are used. We have recorded a full valuation allowance for our deferred tax assets.

The degreeAcquisitions or other business combinations that we pursue in the future, whether or not consummated, could result in other operating and financial difficulties.

In the future we may seek to which we are leveraged and the restrictions governingacquire additional product lines, technologies or businesses in an effort to increase our indebtedness could have important consequences including, but not limited to:

If we are in violation of the terms of our Senior Secured Convertible Notes in the future and do not receive a waiver, the note holders could choose to accelerate payment on all outstanding loan balances. If we needed to obtain replacement financing,combinations, we may not be able to quickly obtain equivalentidentify suitable candidates at prices we consider appropriate. We cannot readily predict the timing or suitable replacement financing. Ifsize of our future acquisitions or combinations, or the success of any such transactions.

To the extent that we consummate acquisitions, combinations or investments, we may face financial risks as a result, including increased costs associated with merged or acquired operations, increased indebtedness, economic dilution to gross and operating profit and earnings per share, or unanticipated costs and liabilities. Acquisitions may involve additional risks, including:

From time to time, we may enter into negotiations for acquisitions or investments that are unable to secure alternative sourcesnot ultimately consummated. These negotiations could result in significant diversion of funding, such acceleration wouldmanagement time, as well as substantial out-of-pocket costs, any of which could have a material adverse impacteffect on our business, operating results and financial condition.

Provisions of our certificate of incorporation and bylaws or Delaware law might delay or prevent a change-of-control transaction and depress the market price of our stock.

Various provisions of our certificate of incorporation and bylaws might have the effect of making it more difficult for a third party to acquire, or discouraging a third party from attempting to acquire, control of our company. These provisions could limit the price that certain investors might be willing to pay in the future for shares of our common stock. Certain of these provisions eliminate cumulative voting in the election of directors, limit the right of stockholders to call special meetings and establish specific procedures for director nominations by stockholders and the submission of other proposals for consideration at stockholder meetings.

We are also subject to provisions of Delaware law that could delay or make more difficult a merger, tender offer or proxy contest involving our company. In particular, Section 203 of the Delaware General Corporation Law prohibits a Delaware corporation from engaging in any business combination with any interested stockholder for a period of three years unless specific conditions are met. Any of these provisions could have the effect of delaying, deferring or preventing a change in control, including without limitation, discouraging a proxy contest or making more difficult the acquisition of a substantial block of our common stock.

Under our certificate of incorporation, our board of directors may issue up to 20,000,000 shares of preferred stock, potentially without stockholder approval on such terms as the board might determine. The rights of the holders of common stock will be subject to, and might be adversely affected by, the rights of the holders of any preferred stock that might be issued in the future.

Our stockholder rights plan could prevent stockholders from receiving a premium over the market price for their shares from a potential acquirer.

We adopted a stockholder rights plan that generally entitles our stockholders to rights to acquire additional shares of our common stock when a third party acquires 15% of our common stock or commences or announces its intent to commence a tender offer for at least 15% of our common stock. The plan also includes an exception to permit the acquisition of shares representing more than 15% of our common stock by a brokerage firm that manages independent customer accounts and generally does not have any discretionary voting power with respect to such shares. This plan could delay, deter or prevent an investor from acquiring us in a transaction that could otherwise result in stockholders receiving a premium over the market price for their shares of common stock. Our intention is to maintain and enforce the terms of this plan, which could delay, deter or prevent an investor from acquiring us in a transaction that could otherwise result in stockholders receiving a premium over the market price for their shares of common stock.

23

Potential volatility of the price of our common stock could negatively affect your investment.

We cannot assure you that there will continue to be an active trading market for our common stock. Historically, the stock market, as well as our common stock, has experienced significant price and volume fluctuations. Market prices of securities of technology companies have been highly volatile and frequently reach levels that bear no relationship to the operating performance of such companies. These market prices generally are not sustainable and are subject to wide variations. If our common stock trades to unsustainably high levels, it is likely that the market price of our common stock will thereafter experience a material decline.

In the past, securities class action litigation has often been brought against a company following periods of volatility in the market price of its securities. We could be the target of similar litigation in the future. Securities litigation could cause us to incur substantial costs, divert management’s attention and resources, harm our reputation in the industry and the securities markets and negatively impact our operating results.

Holders of exchangeable shares are expected to experience a delay in receiving shares of our common stock from the date they request an exchange, which may affect the value of the shares the holder receives in an exchange.

Holders of exchangeable shares who request to receive shares of our common stock in exchange for their exchangeable shares will not receive shares of our common stock until several business days after the applicable request is received. During this period, the market price of our common stock may increase or decrease. Any such increase or decrease would affect the value of the consideration to be received by such holder of exchangeable shares upon a subsequent sale of the common stock received in the exchange

We are a “smaller reporting company” and, as a result of the reduced disclosure and governance requirements applicable to smaller reporting companies, our common stock may be less attractive to investors.

We are a “smaller reporting company,” and are subject to lesser disclosure obligations in our SEC filings compared to other issuers. Specifically, “smaller reporting companies” are able to provide simplified executive compensation disclosures in their filings, are exempt from the provisions of Section 404(b) of the Sarbanes-Oxley Act requiring that independent registered public accounting firms provide an attestation report on the effectiveness of internal control over financial reporting and have certain other decreased disclosure obligations in their SEC filings, including, among other things, only being required to provide two years of audited financial statements in annual reports. Decreased disclosures in our SEC filings due to our status as a “smaller reporting company” may make it harder for investors to analyze our operating results and financial prospects.

If we fail to maintain compliance with the continued listing requirements of the Nasdaq Stock Market, our common stock may be delisted and the price of our common stock and our ability to access the capital markets could be negatively impacted.

Our common stock currently trades on the Nasdaq Stock Market, or Nasdaq, under the symbol “MOSY.“PRSO.” This market has continued listing standards that we must comply with in order to maintain the listing of our common stock. The continued listing standards include, among others, a minimum bid price requirement of $1.00 per share and any of: (i) a minimum stockholders’ equity of $2.5 million; (ii) a market value of listed securities of at least $35.0 million; or (iii) net income from continuing operations of $500,000 in the most recently completed fiscal year or in the two of the last three fiscal years. Our results of operations and fluctuating stock price directly impact our ability to satisfy these continued listing standards. In the event we are unable to maintain these continued listing standards, our common stock may be subject to delisting from the Nasdaq Stock Market.Nasdaq.

If we were to be delisted, we would expect our common stock to be traded in the over-the-counter market which could adversely affect the liquidity of our common stock. Additionally, we could face significant material adverse consequences, including:

Item 1B.  Unresolved Staff Comments

None.

Item 2.  Properties

We currently maintain facilities in San Jose, California and Toronto and Waterloo, Ontario, Canada. Our principal administrative, sales, marketing, support and research and development functions are located in athe leased facilityfacilities in San Jose California.and Toronto. We currently occupy approximately 10,000 square feet of space in the San Jose facility, and the lease extends through October 2020.until July 2022. We occupy approximately 12,700 square feet of space in the Toronto, Ontario facility, and the lease extends until December 2023. We also occupy approximately 2,400 square feet of space in the Waterloo, Ontario facility for research and development functions, and the lease extends until September 2022. We are presently seeking additional space to replace our Waterloo facility. We believe that our existing facility isfacilities are adequate to meet our current needs.

Item 3.  Legal Proceedings

The information set forth under the “Legal Matters” subheading in Note 910 (Commitments and Contingencies) of the Notes to Consolidated Financial Statements in Part II, Item 15, of this Annual Report on Form 10-K is incorporated herein by reference.

Item 4.  Mine Safety Disclosures

Not applicable.

25

PartPart II

Item 5.  Market for Registrant’s Common Equity, Related Stockholder Matters and Issuer Purchases of Equity Securities

Market Information for Common Stock

Our common stock is currently listed on the NASDAQNasdaq Stock Market under the symbol MOSY.“PRSO.”

Holders of Record

As of December 31, 2019,2021, there were three66 holders of record of our common stock. The actual number of stockholders is significantly greater than this number of record stockholders and includes stockholders who are beneficial owners but whose shares are held in street name by brokers and other nominees. This number of stockholders of record also does not include stockholders whose shares may be held in trust by other entities.

Securities Authorized for Issuance under Equity Compensation Plan

For information regarding securities authorized for issuance under equity compensation plans, please refer to Item 12—Security Ownership of Certain Beneficial Owners and Management and Related Stockholder Matters.

Item 6.  Selected Financial Data

Not applicable.

26[Reserved]

Item 7.  Management’s Discussion and Analysis ofof Financial Condition and Results of Operations

This Management’s Discussion and Analysis of Financial Condition and Results of Operations should be read in conjunction with the accompanying consolidated financial statements and notes included in this report.Report.

Overview

We were formerly known as MoSys, Inc. (MoSys) and were incorporated in California in 1991 and reincorporated in 2000 in Delaware. On September 14, 2021, we and our subsidiaries, 2864552 Ontario Inc. and 2864555 Ontario Inc., entered into an Arrangement Agreement (the Arrangement Agreement) with Peraso Technologies Inc. (Peraso Tech), a corporation existing under the laws of the province of Ontario, to acquire all of the issued and outstanding common shares of Peraso Tech (the Peraso Shares), including those Peraso Shares to be issued in connection with the conversion or exchange of secured convertible debentures and common share purchase warrants of Peraso Tech, as applicable, by way of a statutory plan of arrangement (the Arrangement) under the Business Corporations Act (Ontario). On December 17, 2021, following the satisfaction of the closing conditions set forth in the Arrangement Agreement, the Arrangement was completed and the Company changed its name to “Peraso Inc.” and began trading on the Nasdaq Stock Market (the Nasdaq) under the symbol “PRSO.”

For accounting purposes, the legal subsidiary, Peraso Tech, has been treated as the accounting acquirer and we, the legal parent, have been treated as the accounting acquiree. The transaction has been accounted for as a reverse acquisition in accordance with Accounting Standards Codification (ASC) No. 805, Business Combinations (ASC 805). Accordingly, the financial condition and results of operations discussed herein are a continuation of Peraso Tech’s financial results prior to December 17, 2021 and exclude the financial results of us prior to December 17, 2021. See Note 2 to the consolidated financial statements for additional disclosure.

Our strategy and primary business objective is to be a profitable, IP-rich fabless semiconductor company offering integrated circuits, or ICs, modules and related softwarenon-recurring engineering services. We specialize in the development of mmWave semiconductors, primarily in the 60 GHz spectrum band for 802.11ad/ay compliant devices and IP in the 28/39 GHz spectrum bands for 5G-compliant devices. We derive our revenue from selling semiconductor devices, as well as modules based on using those mmWave semiconductor devices. We have pioneereda high-volumemmWaveproductiontestmethodologyusingstandardlow costproductiontestequipment.Ithas takenusseveralyearsto refineperformanceof thisproductiontestmethodology,and we believe this places us in a leadershippositionin addressingoperationalchallengesof deliveringmmWaveproductsintohigh-volume markets. During 2021, weaugmented ourbusinessmodelby sellingcompletemmWavemodules.The primary advantageprovidedby a moduleisthesiliconand theantennaareintegratedintoa singledevice.A differentiatingcharacteristicof mmWavetechnologyisthat deliver unparalleledtheRFamplifiersmustbe as closeas possibleto the antennato minimizeloss, and by providinga module,wecan guaranteetheperformanceof the amplifier/antenna interface.

We also acquired a memory bandwidth and access rate performance for high-performance data processing in cloud networking, communications, security appliances, video, test and monitoring, and data center systems. Our solutions deliver time-to-market, performance, power, area and economic benefits for system original equipment manufacturers, or OEMs. Our primary product line is marketed under the Accelerator Engine name and comprises our Bandwidth Engine and Programmable HyperSpeed Engine IC products, which integrate our proprietary, 1T-SRAM high-density embedded memory and a highly-efficient serial interface protocol resulting in a monolithic memory IC solution optimized for memory bandwidth and transaction access performance.  Our second-generation Bandwidth Engine, or Bandwidth Engine 2, products are expected to be our primary revenue source through at least 2021, and we expect these products to continue to generate significant revenue thereafter.  As we are not developing new ICmemory products, from a product development perspective, we continue to leverage our current technologies and core competencies to expand our product offerings without incurring significant additional R&D expenses. Recently, we announced our new Software Accelerator product line consisting of software and IP available for license. This new product line will include multiple function accelerator platform products, which target specific application functions and will use a common software interface to allow performance scalability over multiple hardware environments. These function accelerator platform products are hardware agnostic and operate with or without one of our Accelerator Engine ICs. This software-defined, hardware-accelerated platform architecture utilizes an internally developed graphical memory engine architecture to provide flexible data classification and analysis capability. We believe the technology will generate new opportunities that require less up-front architectural changes by system designers and provide a scalable performance roadmap of options using our Accelerator Engine ICs. We expect our initial software accelerator products to be available for license in the first half of 2020. Despite our limited new IC product development efforts, we believe our current hardware and software/firmware product portfolio positions us for future growth and profitability.  We will continue to seek third-party funding for new product development efforts.

We incurred net losses of approximately $2.6$10.9 million and $11.4$10.2 million for the years ended December 31, 20192021 and 2018,2020, respectively, and had an accumulated deficit of approximately $238$117.1 million as of December 31, 2019.  2021. These and prior year losses have resulted in significant negative cash flows for almost a decade and have necessitated that we raise substantial amounts of additional capital during this period.To date, we have primarily financed our operations through multiple offerings of common stock to investors and affiliates, as well as asset sale transactions and one offering of convertible notes.

We may continueexpect to incur operating losses and will need to increase revenues substantially beyond levels that we have attained in the past in order to generate sustainable operating profit and sufficient cash flows to continue doing business without raising additional capital from time to time. 

COVID-19

The global outbreak of the coronavirus disease 2019 (COVID-19) was declared a pandemic by the World Health Organization and a national emergency by the U.S. government in March 2020.  This has negatively affected the U.S. and global economy, disrupted global supply chains, significantly restricted travel and transportation, resulted in mandated closures and orders to “shelter-in-place” and created significant disruption of the financial markets. The full extent of the COVID-19 impact on our operational and financial performance will depend on future developments, including the duration and spread of the pandemic and related actions taken by the U.S. and foreign government agencies to prevent disease spread, all of which are uncertain, out of our control, and cannot be predicted.

Since March 2020, certain jurisdictions in which we operate have issued ”shelter-in-place” orders. We have complied with these orders and, when such orders were in place, minimized business activities at our facilities. We have implemented a teleworking policy for our employees and contractors to reduce on-site activity at our facilities.

We remain diligent in continuing to identify and manage risks to our business given the changing uncertainties related to COVID-19. The ultimate impact of the COVID-19 pandemic on our business and results of operations is uncertain and difficult to predict, and we are closely monitoring impacts, especially to customer programs and our supply chain. We have and continue to experience longer lead times for certain components used to manufacture our products. While we believe that our operations personnel are currently in a position to meet expected customer demand levels in the coming quarters, we recognize that unpredictable events could create difficulties in the months ahead. We may not be able to address these difficulties in a timely manner, which could negatively impact our business, results of operations, financial condition and cash flows.

The continued spread of COVID-19 has also led to disruption and volatility in the global capital markets. Our ability to raise additional capital to support operations in the future may be impacted, and we may be unable to access the capital markets and additional capital may only be available to us on terms that could be significantly detrimental to our existing stockholders and to our business.  

Critical Accounting Policies and Use of Estimates

Our consolidated financial statements are prepared in conformity with accounting principles generally accepted in the United States of America. Note 1 to the consolidated financial statements included in Item 15 of this reportReport describes the significant accounting policies and methods used in the preparation of our consolidated financial statements.

27

We have identified the accounting policies below as some of the more critical to our business and the understanding of our results of operations. These policies may involve estimates and judgments that affect the reported amounts of assets, liabilities, revenues and expenses. Although we believe our judgments and estimates are appropriate, actual future results may differ from our estimates, and if different assumptions or conditions were to prevail, the results could be materially different from our reported results.

Business Combination

We allocate the fair value of purchase consideration to the tangible assets acquired, liabilities assumed and intangible assets acquired based on their estimated fair values. The excess of the fair value of purchase consideration over the fair values of these identifiable assets and liabilities is recorded as goodwill to reporting units based on the expected benefit from the business combination. Allocation of purchase consideration to identifiable assets and liabilities affects the amortization expense, as acquired finite-lived intangible assets are amortized over the useful life, whereas any indefinite-lived intangible assets, including goodwill, are not amortized. During the measurement period, which is not to exceed one year from the acquisition date, our records adjustments to the assets acquired and liabilities assumed, with the corresponding offset to goodwill. Upon the conclusion of the measurement period, any subsequent adjustments are recorded to earnings. Acquisition-related expenses are recognized separately from business combinations and are expensed as incurred.

Acquired Intangibles

Acquired intangible assets consist of developed technology and customer relationships that are measured at fair value at date of acquisition. In valuing acquired intangible assets, we make assumptions and estimates based in part on projected financial information, which makes assumptions and estimates inherently uncertain, particularly for early-stage technology companies. The significant estimates and assumptions used by us in the determination of the fair value of acquired intangible technology assets include the revenue growth rate, the royalty rate and the discount rate. The significant estimates and assumptions used by us in the determination of the fair value of acquired customer contract intangible assets include the revenue growth rate and the discount rate.

 As a result of the judgments that need to be made, we obtain the assistance of independent valuation firms. We complete these assessments as soon as practical after the closing dates. Any excess of the purchase price over the estimated fair values of the identifiable net assets acquired is recorded as goodwill.

Revenue Recognition

We adopted recognize revenue in accordance with Financial Accounting Standards Board (“FASB”) Accounting Standards Codification(FASB) ASC Topic 606, Revenue from Contracts with Customers, and all its related amendments (“(ASC 606). As described below, the analysis of contracts under ASC 606”), on January 1, 2018 using606 supports the modified retrospective method. We recognized the cumulative effectrecognition of initially applying the new revenue standard as an adjustmentat a point in time, resulting in revenue recognition timing that is materially consistent with our historical practice of recognizing product revenue when title and risk of loss pass to the opening balance of accumulated deficit as of January 1, 2018. The comparative information for 2017 has not been recast and continues to be reported under the accounting standards in effect for that period. See Note 1 to the consolidated financial statements in Item 15 of this report for an additional description of our recognition of the cumulative effect upon the adoption of ASC 606.customer.

We generate revenue primarily from sales of ICintegrated circuits and module products, performance of engineering services and licensing of ourits intellectual property. Revenues are recognized when control is transferred to customers in amounts that reflect the consideration we expect to be entitled to receive in exchange for those goods. Revenue recognition is evaluated through the following five steps: (i) identification of the contract, or contracts, with a customer; (ii) identification of the performance obligations in the contract; (iii) determination of the transaction price; (iv) allocation of the transaction price to the performance obligations in the contract; and (v) recognition of revenue when or as a performance obligation is satisfied.

IC productsProduct revenue

Revenue is recognized when performance obligations under the terms of a contract with a customer are satisfied.

The majority of our contracts have a single performance obligation to transfer products. Accordingly, we recognize revenue when title and risk of loss have been transferred to the customer, generally at the time of shipment of products. Revenue is measured as the amount of consideration we expect to receive in exchange for transferring products and is generally based upon a negotiated, formula, list or fixed price. We sell our products both directly to customers and through distributors generally under agreements with payment terms typically 60 days or less.

We may record an estimated allowance, at the time of shipment, for future returns and other charges against revenue consistent with the terms of sale.

RoyaltyLicense and other

Our licensing contracts typically provide for royalties based on the licensee’s use of our memory technology in its currently shipping commercial products. With the adoption of ASC 606 in January 2018, weWe estimate ourits royalty revenue in the calendar quarter in which the licensee uses the licensed technology.  Payments are received in the subsequent quarterquarter. We also generate revenue from licensing its technology. We recognize License fee as revenue at the point of time when the control of the license has been transferred and we have no continuing performance obligations to the customer.

Engineering services revenue

Engineering and development contracts with customers generally contain a single performance obligation that is delivered over time. Revenue is recognized using an output method that is consistent with the satisfaction of the performance obligation as a measure of progress.

Contract liabilities – deferred revenue

Our contract liabilities consist of advance customer payments and deferred revenue. We classify advance customer payments and deferred revenue as current or non-current based on the timing of when we expect to recognize revenue. As of December 31, 2021, contract liabilities were in a current position and included in deferred revenue.

Fair Value Measurements of Financial Instruments

We measure the fair value of financial instruments using a fair value hierarchy that prioritizes the inputs to valuation techniques used to measure fair value into three broad levels, as follows:

Level 1—Inputs used to measure fair value are unadjusted quoted prices that are available in active markets for the identical assets or liabilities as of the reporting date.

Level 2—Pricing is provided by third party sources of market information obtained from investment advisors rather than models. We do not adjust for or apply any additional assumptions or estimates to the pricing information we receive from advisors. Our Level 2 securities include cash equivalents and available-for-sale securities, which consisted primarily of corporate debt, and government agency and municipal debt securities from issuers with high quality credit ratings. Our investment advisors obtain pricing data from independent sources, such as Standard & Poor’s, Bloomberg and Interactive Data Corporation, and rely on comparable pricing of other securities because the Level 2 securities we hold are not actively traded and have fewer

28

observable transactions. We consider this the most reliable information available for the valuation of the securities.

Level 3—Unobservable inputs that are supported by little or no market activity and reflect the use of significant management judgment are used to measure fair value. These values are generally determined using pricing models for which the assumptions utilize management’s estimates of market participant assumptions. The determination of fair value for Level 3 investments and other financial instruments involves the most management judgment and subjectivity.

The carrying amounts of financial assets and liabilities, such as cash and cash equivalents, accounts receivable, accounts payable, notes payable and other payables, approximate their fair values because of the short maturity of these instruments. The carrying values of lease obligations and long-term financing obligations approximate their fair values because interest rates on these obligations are based on prevailing market interest rates

Valuation of long-lived Assets

We evaluate our long-lived assets for impairment at least annually, or more frequently when a triggering event is deemed to have occurred. This assessment is subjective in nature and requires significant management judgment to forecast future operating results, projected cash flows and current period market capitalization levels. If our estimates and assumptions change in the future, it could result in a material write-down of long-lived assets. We amortize our finite-lived intangible assets, such as developed technology and patent license, on a straight-line basis over their estimated useful lives of three to seven years. We recognize an impairment charge as the difference between the net book value of such assets and the fair value of the assets on the measurement date.

Goodwill

We determine the amount of potential goodwill impairment by comparing the fair value of the reporting unit with its carrying amount. To the extent the carrying value of a reporting unit exceeds its fair value, a goodwill impairment charge is recognized. We have determined that we have a single reporting unit for purposes of performing our goodwill impairment test. As we use the market approach to determine the step one fair value, the price of our common stock is an important component of the fair value calculation. We review goodwill for impairment on an annual basis or whenever events or changes in circumstances indicate the carrying value of an asset may not be recoverable. We first assess qualitative factors to determine whether it is more-likely-than-not that the fair value of the reporting unit is less than the carrying amount as a basis for determining whether it is necessary to perform an impairment test.

We performed our annual test for goodwill impairment as of September 1, 2019, and, due to a decrease in the price per share of our common stock, the test results indicated the goodwill carrying value was greater than its implied fair value. Further, the Company concluded a triggering event had occurred due to the sustained decrease in the price per share of its common stock and related reduced market capitalization as of September 30, 2019 and performed an additional test for impairment of its goodwill asset resulting in further indication that the goodwill carrying value was still greater than its implied fair value. As a result of both of these tests, the Company recorded non-cash impairment charges of $0.4 million during the third quarter of 2019.  As a result of these charges, the Company’s goodwill balance was reduced to zero as of September 30, 2019.

Deferred tax valuation allowance

When we prepare our consolidated financial statements, we estimate our income tax liability for each of the various jurisdictions where we conduct business. This requires us to estimate our actual current tax exposure and to assess temporary differences that result from differing treatment of certain items for tax and accounting purposes. These differences result in deferred tax assets, which we show on our consolidated balance sheet under the category of other assets. The net deferred tax assets are reduced by a valuation allowance if, based upon weighted available evidence, it is more likely than not that some or all of the deferred tax assets will not be realized. We must make significant judgments to determine our provision for income taxes, our deferred tax assets and liabilities and any valuation allowance to be recorded against our net deferred tax asset. We believe that utilization of our net operating loss and tax credit carryforwards, which comprise the majority of our deferred tax assets, may be subject to a substantial annual limitation due to the ownership change limitations provided by the Internal Revenue Code and

similar state provisions. See Note 4 to the consolidated financial statements in Item 15 of this report for an additional description of these limitations.

Stock-based compensation

We recognize stock-based compensation for equity awards on a straight-line basis over the requisite service period, usually the vesting period, based on the grant-date fair value. We estimate the value of employee stock

29

options on the date of grant using the Black-Scholes model. The determination of fair value of share-based payment awards on the date of grant using an option-pricing model is affected by our stock price, as well as assumptions regarding a number of highly complex and subjective variables. These variables include, but are not limited to, the expected stock price volatility over the term of the awards, and actual and projected employee stock option exercise behaviors. The expected term of options granted is derived from historical data on employee exercises and post-vesting employment termination behavior. The expected volatility is based on the historical volatility of our stock price.

Results of Operations

Net Revenue

Product revenue decreasedincreased in 20192021 compared with 20182020 due to reducedincreased shipments of our Bandwidth enginemmWave IC and module products. Specifically,We commenced selling our module products in 2021. We expect revenues to increase in 2022, as we completed final shipmentsexpect increased sales of our Bandwidth Engine 1 product in the first halfmmWave products and full-year contribution of 2019 and experienced reduced shipments to some ofrevenues from our large Bandwidth Engine 2 IC customers.  The increase from 2017 to 2018 was due to increased volume of shipments for our ICs, mainly Bandwidth Engine products, as additional customer design wins commenced production.memory products.  

RoyaltyLicense and other revenue primarily comprises revenue generated from licensing agreements.includes license, non-recurring engineering, or NRE, services and royalty revenues.  The decrease from 20182021 to 2019 was primarily due to a reduction in revenue from a one-time license and service agreement entered into in 2017 for our analog technology. The increase from 2017 to 20182020 was primarily due to a one-time license and service agreement entered intoof $5.0 million from a lead customer recognized in 2017 for our analog technology, partially offset by a decline in royalty revenue.the fourth quarter of 2020, decrease of $5.0 million one license revenue combined with reduced NRE revenues.

Cost of Net Revenue and Gross Profit

In each of 2019, 20182021 and 2017,2020 cost of net revenue primarily consisted of direct and indirect costs related to the sale of IC products.and module sales.

Cost of net revenue decreasedincreased in 20192021 from 20182020 due to decreasedincreased product shipments.  The increase in 2018

Gross profit decreased from 2017 was2021 to 2020 primarily due to the increase in materiallower license and production costs related to our increased IC shipments, partially offset by inventory write-downs recorded in 2017.  

30

Gross profit decreased from 2018 to 2019 primarily due to the decrease in IC shipments and the decrease in our royalty and otherNRE revenue, which generally has no associated costs.  Gross profit increased from 2017 to 2018 primarily due to the increase in IC shipments and improved manufacturing efficiencies and reduced material purchase prices as well as the increase in royalty and other revenues, which generally have little to no associated cost.higher margins than product revenues.  

Research and Development