News

Company’s award-winning EFLX® eFPGA technology currently used by 20 customers for 40 unique chips

MOUNTAIN VIEW, Calif. – September 25, 2023 – Flex Logix® Technologies, Inc., the leading supplier of embedded FPGA (eFPGA) IP, announced today that it now has 20 worldwide customers that have licensed the company’s advanced EFLX eFPGA technology architecture for 40 chips.

EFLX is the Only eFPGA with Automatic Flexible Hardware Error Correction

MOUNTAIN VIEW, Calif. – September 18, 2023 – Flex Logix® Technologies, Inc., the leading supplier of eFPGA IP, announced today the availability of Reconfigurable Block RAM with ECC and Parity Options.

Transformers require reconfigurability and numeric range that few accelerator IP solutions offer

See the presentation presented on September 12, 2023, at the AI Hardware and Edge AI Summit.

EFLX is the Only eFPGA with Emulation Models to Ensure First Silicon Success

MOUNTAIN VIEW, Calif. – September 11, 2023 – Flex Logix® Technologies, Inc., the leading supplier of eFPGA IP, announced today the availability of upgraded emulation models for EFLX eFPGA for both Cadence Palladium and Siemens Veloce.

Flex Logix EFLX eFPGA is the first eFPGA that enables a customer to match the performance of FPGAs from AMD/Xilinx and Intel (in the same process node) with the same density (LUTs/mm2). EFLX eFPGA has been in use with customers now for more than 5 years, hardware and software.

The object detection required for machine vision applications such as autonomous driving, smart manufacturing, and surveillance applications depends on AI modeling. 

EFLX eFPGA has been in use in SoCs for more than 5 years, hardware and software. More than 40 chips have been licensed to use EFLX eFPGA and more than 20 chips are working in silicon. Big customers like Renesas are planning high volumes and families of chips using eFPGA.

Today if you want high-performance DSP you have three choices:

1. Hardwire your function – zero flexibility
2. Use DSP IP based on VLIW
3. Use FPGAs with DSP MACs or math engines

We hear from customers that there is a growing need for very fast and flexible DSP, which hardwired solutions can’t address.

Jeremy Roberson, technical director and software architect for AI/ML at Flex Logix, talks about how to achieve better AI accuracy with minimal power and reduced obsolescence.

InferX IP provides flexibility to future-proof your AI solution, including state-of-the-art CNN & transformers workloads.

Today, we’re going to talk about AI, DSP, FPGAs, IP, and SoCs. Normally, these things don’t all go together. Certainly, FPGAs have been used to implement AI and DSP algorithms, although AI and DSP algorithms generally involve different sorts of computations.

DSP and AI are generally considered separate disciplines with different application solutions. In their early stages (before programmable processors), DSP implementations were discrete, built around a digital multiplier-accumulator (MAC). AI inference implementations also build on a MAC as their primitive. If the interconnect were programmable, could the MAC-based hardware be the same for both and still be efficient? Flex Logix says yes with their next-generation InferX reconfigurable DSP and AI IP.

Flex Logix, an eFPGA company, has stopped selling its InferX X1 AI accelerator chip, and will instead bring the architecture to market as licensable IP, Flex Logix CEO Geoff Tate told EE Times.

Flex Logix is changing its business model, offering its InferX block as IP and ceasing chip-building operations. It’ll serve chipmakers requiring either AI inference or DSP capability.

Note: The link will work by setting up a free login for the Flex Logix InferX article.

If you want high performance AI inference, such as Super-Resolution Object Detection and Recognition, in your SoC the challenge is to find a solution that can meet your needs and constraints.

Using eFPGAs to extend the life of different blocks and reduce inventory.

Talking to many different kinds of chips is becoming more complicated. There are new types of transistors, new protocols, and all of this is limited by the number of pins. Geoff Tate, CEO of Flex Logix, talks about adding programmability into the general-purpose I/O to enable more flexibility, lower inventory, and reduced obsolescence.

MOUNTAIN VIEW, Calif. – April 24, 2023 –  Flex Logix® Technologies, Inc., a leading innovator in DSP & AI inference IP and the leading supplier of eFPGA IP, announced today the availability of InferX™ IP & software for DSP and AI inference. InferX joins EFLX® eFPGA as Flex Logix’s second IP offering. It can be used by device manufacturers and systems companies that want the performance of a DSP-FPGA or a AI-GPU in their SoC, but at a fraction of the cost and power. The company’s EFLX eFPGA product line has already been proven in dozens of chips with many more in design from 180nm to 7nm with 5nm in development.

Using embedded FPGA to support the dozens of variations and kinds of GPIO interface protocols.

Your MCU/SoC today may have several options for GPIO connections: UART, SPI, I2C. But there are dozens of variations and kinds of GPIO interface protocols: you don’t have enough pins to provide all of them as hardwired options.

Every foundry and every node is different, but for every foundry/node there are multiple supported metal stacks.

Some chips use a lot more metal layers than others. A common rule of thumb is each metal layer increases wafer cost 10%. So, a chip with 5 more metal layers than another will cost 50%+ more.

One of the most critical ramifications of the emergence of quantum computers is the impact on security because quantum computers have the potential to break even the most secure encryption methods used today. That is why the industry will be seeing a rapid shift from traditional cryptosystems to Post Quantum Cryptography (PQC) systems in the next few years. PQC systems respond to this growing quantum threat because they are based on mathematical problems that cannot be solved efficiently with Shor’s algorithm, or by any other known quantum computing algorithm.

5G, networking, cloud storage, defense, smart home, automotive, and others – are looking to embedded FPGAs (eFPGA) to save power and reduce cost. All these applications demand reconfigurability with lower power/cost, but they also require strong security. Listen to this webinar recording on SemiWiki anytime!

Now portable applications can leverage the heterogeneous computing done at the data centers!

Longer chip lifetimes mean they need to adapt to security threats.

System companies are taking a more proactive role in co-designing their hardware and software roadmaps, so it’s no surprise that they are also driving the adoption of embedded FPGAs (eFPGA.) But why and why has it taken so long?

Dan is joined by Geoff Tate, CEO and Co-founder of Flex Logix. Geoff explains the embedded FPGA market, including some history, applications and challenges to deliver a product that customers really want. He provides some very relevant background on why Flex Logix has been so successful in this market, and what lies ahead.

The EE Times Silicon 100 list is out and there is a detailed write-up on Flex Logix on both the eFPGA and AI technologies. We also made their “Editor’s Eleven” list which is a smaller selection of companies that are making the news in EE Times, will continue making the news and are also the companies they think are setting the trends for the future.

The main concern is keeping the smart city systems and their data and functions safe, especially if the system is touching critical infrastructure. This article explains several ways including the flexible low power way by adding eFPGA to the systems. eFPGAs are increasing security and lowering power and cost.

Flex Logix Technologies announced that it has partnered with Intrinsic ID to ensure that any device using its eFPGA remains secure and can’t be modified maliciously, whether through physical attacks or remote hacking.

Flex Logix(R) Technologies, Inc., the leading supplier of embedded FPGA (eFPGA) IP, architecture and software, announced today that it has been selected to be part of a team of microelectronic industry leaders, led by Microsoft, to build a chip development platform with the utmost regard for security as demonstrated by the DoD RAMP Project. Flex Logix was chosen for its leading embedded (eFPGA) technology that enables chips to be reconfigurable after tape-out, allowing companies to adapt to new requirements, changing standards and protocols as needed.

Many systems use FPGAs because they are more efficient than processors for parallel processing. The area, power, and cost of FPGAs are driving system architects to look for a better solution. The solution is integrating FPGAs into the main SoC. Why? Because it saves power and cost by as much as 10X.

Flex Logix® Technologies, Inc. and CEVA, Inc. have announced today the world’s first successful silicon implementation using Flex Logix’s EFLX® embedded FPGA (eFPGA) connected to a CEVA-X2 DSP instruction extension interface.

Silicon Catalyst, the world’s only incubator focused exclusively on accelerating semiconductor solutions, is pleased to announce that Flex Logix® has joined as the newest member of its In-Kind Partner program (IKP). Portfolio companies in the Silicon Catalyst Incubator will have access to Flex Logix’s innovative embedded FPGA (eFPGA) IP and software, enabling silicon reconfigurability for use in their chip designs.

Before Covid-induced supply chain issues affected semiconductor availability and lead times, concerns about counterfeit parts and trusted supply chains were becoming the subject of many articles and discussions…

Flex Logix® Technologies, Inc., the leading supplier of embedded FPGA (eFPGA) IP, architecture and software, announced today that it has reached a significant milestone of signing licenses to develop more than 32 ASICs/SoCs integrating EFLX, with nearly half already working in silicon.

TO INCLUDE ANY FLEX LOGIX TECHNOLOGY FOR RESEARCH AND CHIP PROTOTYPING IN ALL AVAILABLE PROCESSES INCLUDING RADHARD Enables any US Government-funded research programs and activities to use reconfigurable computing IP for no license fees

FPGA has become strategic technology. It is strategically important to two very big, high-growth applications: Cloud data centers and Communications systems including 5G, and acquisitions of FPGA companies confirm this. Why? Because of Parallel programming, but FPGAs have some concerns. This presentation will talk about how embedding FPGAs (eFPGA) can change the use case for FPGA and the way software is controlled.

Machine vision is rapidly becoming a key enabling technology for digitalization and automation in automotive, healthcare, manufacturing, retail, smart buildings, smart cities, transportation, and logistics. According to ABI Research, a global technology intelligence firm, the total revenue of machine vision technology in the seven major markets is expected to reach US$36 billion by 2027, up from US$21.4 billion in 2022. This growth translates to a CAGR of 11%.

The X1 was specified to be a lean, high-performance edge accelerator for AI inference processing incorporating Flex Logix’s proprietary tensor processor, PCIe, DDR, memory, and a NoC. And we ran into an issue…

eFPGA Market has come a long ways over the years. Find out where its going in 2022.

Embedded FPGA (eFPGA) is the next big market for semiconductor IP. It can be used on almost every kind of digital chip and has a significant software value add as well—much like the market for embedded processors. When it comes to chip design, eFPGA provides competitive advantages that can add up to millions of dollars in savings and flexibility that wasn’t possible until now.

Consider these 6 factors when selecting an AI accelerator for your medical device.

It’s an exciting time to be a part of the rapidly growing AI industry, particularly in the field of inference. Once relegated simply to high-end and outrageously expensive computing systems, AI inference has been marching towards the edge at super-fast speeds. Today, customers in a wide range of industries – from medical, industrial, robotics, security, retail and imaging – are either evaluating or actually designing AI inference capabilities into their products and applications.

Why it’s so important to match the AI task to the right type of chip. Machine learning (ML)-based approaches to system development employ a fundamentally different style of programming than historically used in computer science. This approach uses example data to train a model to enable the machine to learn how to perform a task. ML training is highly iterative with each new piece of training data generating trillions of operations.