Startup Funding: March 2024

The challenge of moving data from place to place is increasingly a key concern for chip and system designers, and investors are taking note. Numerous startups developing interconnect technologies received significant backing in March, with approaches spanning chiplet-enabling PHYs, photonic fabrics for disaggregated compute and memory, and telecom transceiver modules.

Several new startups launched, including companies tackling dataflow processor architectures, custom deep learning chips, and optical networks for linking GPUs.

Plus, a massive round for ADAS/AD development tools, diamond semiconductors, more AI chips, and nanomaterial integration feature in this look at 39 startups that collectively raised over $1.1 billion in March.

• Summary table
• Chips
• AI hardware
• Manufacturing, equipment & materials
• Test, measurement & inspection
• Power devices
• Photonics & optics
• Quantum computing
• Sensors
• Displays & AR/VR
• Automotive
• Previous reports

Chips

Eliyan Corporation raised $60.0M in Series B funding, led by Samsung Catalyst Fund and Tiger Global Management, with participation from existing investors including Intel Capital, as well as SK Hynix, Cleveland Avenue, and Mesh Ventures. Eliyan develops chiplet interconnect technologies for multi-die architectures in either advanced packaging or standard organic substrates. Its NuLink technology, which is a superset of Bunch of Wires (BoW) and Universal Chiplet Interconnect Express (UCIe), is a die-to-die PHY to connect different functions in one package. It is capable of simultaneous bi-directional signaling, enabling designs to receive data while simultaneously transmitting data on the same wire at the same time. The PHY was recently taped out on TSMC’s 3nm process with a bandwidth of 64Gbps/bump using standard packaging. In addition to die-to-die, it offers die-to-memory interconnect with bidirectional transceivers for every data lane. Eliyan’s proposed Universal Memory Interface would enable a single ASIC SKU to be configured to connect to different memory chiplets and to non-memory dies such as co-packaged optics and SerDes chiplets. Based in Santa Clara, California, USA, it was founded in 2021.

Efficient Computer emerged from stealth with $16.0M in seed funding led by Eclipse VC. Efficient Computer has developed a reconfigurable dataflow processor architecture and software stack it claims is up to 100X more energy efficient than general-purpose CPUs currently on the market. The Fabric architecture expresses programs as a ‘circuit’ of instructions that shows which instructions talk to each other, enabling the circuit to be laid out spatially across an array of extremely simple processors to execute the program in parallel. The startup has implemented the architecture in a test SoC. The general-purpose processor is programmable via mainstream embedded programming languages and AI/ML frameworks and targets a range of edge applications including IoT, wearable and implantable health devices, space systems, and security and defense. Founded in 2022, it is based in Pittsburgh, Pennsylvania, USA.

AI hardware

Taalas emerged from stealth with $50.0M from two rounds of funding, led by Quiet Capital and individual investor Pierre Lamond. Taalas is developing an automated flow for rapidly implementing all types of deep learning models in silicon, including transformers, SSMs, diffusers, and MoEs. The startup says its technology enables one of its chips to hold an entire large AI model without requiring external memory, massively improving efficiency and enabling 10–100x growth in model size. The company is taping out its first large language model (LLM) chip in the third quarter of 2024. Founded in 2023, it is based in Toronto, Ontario, Canada.

NeuReality drew $20.0M in funding from the European Innovation Council Fund, Varana Capital, Cleveland Avenue, XT Hi-Tech, and OurCrowd, with participation from Cardumen Capital, Glory Ventures, and Alumni Venture Group. NeuReality makes purpose-built AI platforms optimized for deep learning inference in applications such as computer vision, natural language processing, recommendation engines, and generative AI in data centers and near-edge on-premises locations. The startup says its Network Addressable Processing Units (NAPU) move simple but critical data path functions from software to hardware, reducing the dependency on CPUs, NICs, and PCI switches. Its inference PCIe cards connect directly to Ethernet to manage AI queries from vast data pipelines originating from millions of users and billions of devices. The company also provides software and runtime libraries to accelerate AI deployment. Funds will support deployment of its inference solution. Founded in 2019, it is based in Caesarea, Israel, and has raised $70M to date.

Innatera Nanosystems raised €15.0M (~$16.3M) in Series A funding from Invest-NL Deep Tech Fund, European Innovation Council Fund, MIG Capital, Matterwave Ventures, and Delft Enterprises. Innatera develops neuromorphic processors based on an analog-mixed signal computing architecture that mimic the brain’s mechanisms for processing sensory data. Innatera’s processors use spiking neural networks with ultra-low power consumption and short response latency for always-on pattern recognition capabilities in applications at the sensor-edge. Funds will be used to accelerate mass production and broaden application offerings. Founded in 2018 as a spin off from the Delft University of Technology, it is based in Rijswijk, the Netherlands.

Manufacturing, equipment & materials

Elephantech received JPY 3,000.0M (~$19.8M) in Series E financing. Elephantech offers a metal inkjet printing-based printed circuit board manufacturing technology that it claims is environmentally friendly and can reduce CO₂ emissions by 77% and water consumption by 95% compared to conventional manufacturing methods. The startup says its technology, which allows metal to be printed on a substrate only where necessary, can be applied to almost all PCB types. It currently focuses on single-sided flexible substrates and plans in the future to produce multi-layered and rigid PCBs. It also aims to add the capability to print on biomass substrates and use recyclable materials. Funds will be used for commercialization. Founded in 2014, it is based in Tokyo, Japan, and has raised around 15B yen to date.

Diamfab drew €8.7M (~$9.4M) in its first funding round from Asterion Ventures, Bpifrance, Kreaxi, Better Angle, Hello Tomorrow, and Grenoble Alpes Métropole. Diamfab synthesizes value-added diamond wafers for semiconductors and power components using its technology for epitaxy and doping of synthetic diamond. It also designs diamond electronic components it says are lighter and more energy-efficient than silicon devices, with resistance to high temperatures, radiation, and high voltages. It targets the automotive, renewable energy, and quantum industries. Funds will be used to set up a pilot line and accelerate development. Founded in 2019 as a spin off from CNRS lab Institut Néel, it is based in Grenoble, France.

Chiral Nano received $3.8M in pre-seed funding led by Founderful and HCVC, alongside grants from ETH Zurich and Venture Kick. Chiral Nano is developing nanomaterial-based transistors with a bridging carbon nanotube. It has designed a scalable manufacturing process to grow, select, and automatically integrate nanomaterials such as carbon nanotubes or graphene into transistors at high speed, high quality, and with full process control. Chiral says its nanotransistor technology is suitable for quantum processors, low-power sensors, and high-performance transistors. Along with robotic assembly equipment for placement of micrometer- and nanometer-sized materials, the startup offers foundry services. Funds will support development of its next-generation robotic machine. Founded in 2023 as a spin out from ETH Zurich and Empa, it is based in Zurich, Switzerland.

Gaianixx added JPY 350.0M (~$2.4M) to its previous JPY 1,000M Series B round from JIC Venture Growth Investments, Alconix Corporation, and SMBC Venture Capital, bringing the round to JPY 1,350.0M. Gaianixx has developed an epitaxy technology for growing high quality single crystals in a multilayer structure using a dynamic lattice matching mechanism. Its multifunctional interlayer technology has applications in semiconductor wafers, including for MEMS, power devices, and LEDs, as well as piezoelectric and ceramic films. Funds will be used for R&D, mass production, and hiring. Founded as a spin out from the University of Tokyo in 2021, it is based in Tokyo, Japan.

Membrion will receive up to $0.1M for a pilot project from the 100+ Accelerator. Membrion makes electro-ceramic desalination membranes for semiconductor and industrial wastewater treatment. The company claims its membranes can recover up to 98% of water in harsh conditions, such as high temperatures, low pH ranges, and with challenging trace chemicals. Founded in 2016, it is based in Seattle, Washington, USA.

Test, measurement & inspection

Robovision drew $42.0M in Series A funding led by Target Global and Astanor Ventures, joined by Red River West. Robovision offers a deep learning computer vision platform for a range of industries. For semiconductors, it can interface with DUV, e-beam, and optical solutions to perform in-line automatic defect classification (ADC) of wafers at sub-10nm nodes. Founded in 2012, it is based in Ghent, Belgium.

Power devices

e-peas Semiconductors drew €17.5M (~$19.0M) in financing led by Otium Capital, joined by new investors Nomainvest and EIC Fund, as well as existing investors KBC Focus Fund, The Faktory, Wallonie Entreprendre, Noshaq-Leansquare, and InvestBW. e-peas provides ultra-low power management ICs for energy harvesting that gather and manage energy from ambient sources such as light, radio frequency, temperature gradient, or vibration. It also offers ultra-low power microcontrollers and imagers. Founded in 2014, it is based in Louvain-La-Neuve, Belgium.

Photonics & optics

Celestial AI raised $175.0M in Series C funding led by U.S. Innovative Technology Fund, with participation from AMD Ventures, Koch Disruptive Technologies, Temasek and its subsidiary Xora Innovation, IAG Capital Partners, Samsung Catalyst, Smart Global Holdings, Porsche Automobil Holding, Engine Ventures, M-Ventures, and Tyche Partners. Celestial AI offers a photonic technology that enables optically addressable memory and compute both on-chip and between chips. Its optical interconnect is not restricted by the package beachfront and can deliver data to any location on the compute die. The company claims its photonic fabric provides compute-to-compute and compute-to-memory connectivity at terabits per second bandwidth with nanosecond latencies and enables the disaggregation of compute and memory in hyperscale data centers. The technology is compatible with standards including CXL, PCIe, UCIe, HBM, and proprietary electrical communication links. Funds will be used to execute customer collaborations and for commercialization. Founded in 2020, it is based in Santa Clara, California, USA.

EFFECT Photonics received $38.0M in Series D financing led by Innovation Industries Strategic Partners Fund and Invest-NL Deep Tech Fund with participation from other existing investors. EFFECT Photonics designs photonic optical systems and pluggable transceiver modules for high-speed fiber optics in telecommunications and data communications networks. Its technology uses integrated optical SoCs with digital signal processing and forward error correction technologies, combined with ultra-pure, tunable light sources. Funds will be used to accelerate development, commercialization, and production. A spinout from the Technical University of Eindhoven founded in 2010, it is based in Eindhoven, the Netherlands.

Oriole Networks launched with £10.0M (~$12.6M) in seed funding led by UCL Technology Fund, Clean Growth Fund, XTX Ventures, and Dorilton Ventures. Oriole Networks uses optical networks to connect thousands of GPUs together to increase the speed of large language model (LLM) training with reduced latency and increased energy efficiency. A spin out from University College London founded in 2023, it is based in London, UK.

Quintessent raised $11.5M in seed funding led by Osage University Partners, joined by M Ventures, and existing investors Sierra Ventures, Foothill Ventures, and Entrada Ventures. Quintessent develops optical interconnects built on a multi-wavelength quantum dot comb laser as part of a heterogeneous silicon photonic technology stack. The startup claims its interconnect for compute and switch chips in the data center reduces power consumption and required component count while multiplying bandwidth density. Founded in 2019, it is based in Santa Barbara, California, USA.

Quantum computing

Maybell Quantum raised $25.0M in a Series A round led by Cerberus Ventures. Maybell makes cryogenic dilution refrigerators and wiring solutions for quantum computer infrastructure. Funds will be used to scale manufacturing and open a new production facility. Founded in 2021, it is based in Denver, Colorado, USA.

Sensors

SteerLight drew €3.2M (~$3.5M) in equity and loan financing led by Stellantis Ventures, along with Quantonation, LIFTT, and Bpifrance. SteerLight develops silicon photonic lidar chips with monolithic integration of laser and detection mechanisms. Its initial focus is industrial applications, including autonomous robots. It plans to expand to infrastructure solutions, smart cities, and mobility. Founded in 2022 as a spin-off from CEA-Leti, it is based in Grenoble, France.

Displays & AR/VR

MICLEDI Microdisplays received $25.0M in a Series A round from imec.xpand, PMV, imec, KBC, and SFPIM. MICLEDI makes microLED arrays and display modules for the AR market, including smart glasses and automotive HUDs. Its product lineup includes blue, green, and red GaN-based microLED arrays and red AlInGaP microLED arrays. Funds will be used to design and build an active backplane ASIC, create a fully-functional microLED display module, and for hiring. A spin out from imec founded in 2019, it is based in Leuven, Belgium.

Automotive

Applied Intuition raised $250.0M in Series E financing led by Porsche Investments Management and individual investors Bilal Zuberi and Elad Gil, joined by Andreessen Horowitz, General Catalyst, and other individual investors. Applied Intuition offers a development platform to develop and test ADAS and automated driving systems for automotive, trucking, construction, mining, and agriculture. Its toolchain includes synthetic data generation and data mining, simulation of scenarios and perception systems, development of motion planning and controls, sensor suite design, verification/validation, and drive data management. Funds will be used for compute infrastructure, hiring, and to expand its product portfolio. Founded in 2017, it is based in Mountain View, California, USA.

Table

Funds & investors

Arm and Silicon Catalyst teamed up on the 2024 Arm Flexible Access for Startups Contest, which will award Arm technology credits to early-stage startups developing SoCs using Arm IP. Submission deadline is May 17, 2024.