FPGA Frontiers: Unleashing Tomorrow’s Tech with Thamilmani Balakrishnan

Niranjana R

Updated on:


FPGA Insights has engaged in an exclusive interview with Thamilmani Balakrishnan, FPGA design engineer at Celerix technologies

iY ncCgSS2mGVZBW2Q5UkwY R8SLiilAYeO2lafzvJHu3E1Qx0DIjNq2nwewU7zbDTl 0Jp024Tk9Y2qkTBD4InOg5uYi DZG2axuAd nJj g Rz1EbS xqddTzot

Q1) Can you provide an overview of your experience with FPGA design projects mentioning a few that you’ve worked on, starting with a brief introduction?

I am currently working as a senior design engineer in Celerix technologies doing projects using ultra-scale plus FPGA for HFT, and my previous experience was at Pugos Technologies where worked upon fpga based machine vision projects to sort products based on color and size, I have done masters in VLSI design and bachelors degree in ECE. 
Coming to the projects majorly worked on algorithm developments for HFT with low latency-based applications and for image processing-based sortex applications, also worked on off-chip communication protocols like UART, spi, and chip communication protocols like axi3, axi-lite, and memory interfaces like ddr3, SRAM.

Q2) Can you explain the benefits of using FPGAs over other types of processors?

Since FPGAs will support parallel processing real-world time-critical applications can be easily executed through FPGA with comparatively less cost against the processors

Q3) What are the most significant trends observed in the FPGA industry over the past year? How will these trends shape the industry’s future?

Since recently hard processors with multiple cores have been integrated with FPGAs, we can easily implement machine learning algorithms along with the benefits of PL parallel processing with huge IO interfaces, so that many automation-based projects can be easily done through FPGAs.

Q4) How do you see FPGA development evolving to meet the demands of modern applications and complex workloads?

FPGAs keep evolving as per the time and demand, even to make programming more versatile we can use system c to develop logic for FPGA, with the latest ultra-scale plus FPGAs with less than 10nm transistors which will reduce power consumption and with millions of LUT’s and supporting different clock domains we can implement soc applications easily as well, also with available of thousands of DSP blocks complex decision-making algorithms can be implemented with nanoseconds of precision

Q5) Key drivers behind the increasing adoption of FPGAs in various applications and industries?

Much research and development have been going on new technologies in recent times, for FPGAs are preferred due to their reconfigurable abilities and short development cycles so that product development and testing can be done easily and effectively, also low volume specialized applications can be done with cost-effective using the FPGA

Q6) Sectors that stand to benefit the most from FPGA integration, and why?

Since ASIC is preferred for tried and tested large volume applications, new technology developments like 5G developments, data centers to handle the bulk of data, and in automotive where circuit-based technologies are implemented largely like adas, autonomous driving, and defense industries where new age electronics warfare systems are coming in large numbers, etc.

Q7) The role of FPGAs in accelerating AI applications and advancements expected in the near future.

AI applications will need more processing power in terms of clock speed and data width since FPGA has the advantage of parallel processing as well as low latency custom data width logic we can implement AI with minimal effort, unlike previous generations where we used to develop logic only through Verilog or VHDL now we can able to use system c, C++ or python in HLS environment, which make it easy for logics development. 

Especially for future real-time projects like AI robotics applications and defense projects like AI-guided electronics warfare and spy drones which need to handle multiple drivers and sensors simultaneously, FPGA will be an ideal choice over processors because of its parallel processing ability

Q8) Ensuring the security and integrity of FPGA designs, especially in sensitive applications like finance and defense.

Even Though security vulnerability is lesser compared to traditional processors, still FPGA is subjected to threats like cloning bit files, spoofing, reverse engineering from binary to RTL code, etc, so a better way to avoid this is encrypting the bitstream data, also use anti-tampering techniques like LVS(Layout Vs Schematic), especially need to secure development environment and keep it separate from a manufacturing environment to reduce the risk of exposing the product IP

Q9) Advice for students and professionals interested in pursuing a career in FPGA development to stay updated with the latest trends and technologies.

The FPGA domain keeps booming, and by 2030 the worth of FPGA projects will be in the tens of billions, students who are interested in the FPGA design field should start with digital design and cover all the basics, that we can start learning programming languages, to begin with, Verilog will be a great option since it is C based with simple operator constructs, then it is better to cover VHDL which is strongly typed language which is preferred in aerospace and defense projects because of its improved safety, for students who are willing to master any particular domain like RTL design or design verification, they can reach FPGA specialized training centers by offline so that we can get hands-on experience on FPGA boards. 

To keep updated about the latest changes happening in the FPGA fields we can visit websites like Xilinx or Intel frequently to get the latest technologies updates as well as about seminars notifications where they will organize for students to experienced persons with basic to latest topics.


Leave a Comment

This site uses Akismet to reduce spam. Learn how your comment data is processed.

Beyond Circuit Podcast by Logic Fruit: High-speed video interfaces in Indian Aerospace & Defence.