DLAccel: Building high performance Deep Learning Accelerator for future generation FPGA computing platform

(5th Workshop, in conjunction with 22nd ICDCIT 2026)

16th – 19th January, 2026

Organized by:
Kalinga Institute of Industrial Technology,
Deemed to be University, Bhubaneswar, Odisha, India

About the Workshop

Deep Learning has become a state-of-the-art solution to all machine intelligence based problems due to its high accuracy and efficiency. It helps in making real time decisions in applications like Advanced Driver Assistance Systems (ADAS), Robots, Autonomous Vehicles, Industrial Automation, Aerospace and Defense specific tasks. For accurate decisions and real time behavior, a massive amount of data needs to be processed. To process these data, the Deep learning Hardware acceleration is needed in which an application offloads a high computational task into specialized hardware for achieving high efficiency when compared to software implementation in CPU alone. Deep learning acceleration in hardware utilizes specialized computing devices designed to significantly speed up the training and inference of deep learning models. These accelerators are optimized for the high computational demands and parallelism inherent in deep neural networks, surpassing general-purpose CPUs in efficiency, speed, and power consumption.

Resource Person

Dr. Khyamling Parane,FPGA domain expert, Intel Corporation Bangalore, India.
Email ID: [email protected]

Registration Details:

  • Half day event in Physical Mode.
  • Scheduled on 17th January,2026 (10 am onwards).
  • Theory with Hands-on industry related activities.
  • Participation certificate will be issued to all attendees.
  • Registration fees per participant is 200 INR only.
  • Registration deadline is 30th December, 2025.
  • Workshop Capacity is limited to 250 attendees.

Workshop Co-chairs

Dr.Sushruta Mishra
SCE, KIIT-DU
Email : [email protected]

Dr.Abhaya Kumar Sahoo
SCE, KIIT-DU
Email : [email protected]

Dr. Manas Lenka
SCE, KIIT-DU
Email : [email protected]