Registered user since Wed 14 Mar 2018
Kunal Banerjee has recently joined Walmart Global Tech (earlier known as Walmart Labs) as Staff Data Scientist. Earlier he was a Research Scientist at Parallel Computing Lab, Intel Labs, India, where his primary focus was on kernel optimization of deep learning workloads on Intel architectures (IA). For example, his code for convolution using Winograd, RNN, LSTM and GRU are available in open source libraries: LIBXSMM and Intel MKL-DNN. These libraries have been adopted in several software products including TensorFlow, Caffe, MS CNTK, Apache MXNet, Chainer, OpenVINO among others for enhanced performance on IA. He is also interested in low-precision deep neural networks. Specifically, together with his colleagues in Intel Labs, he has developed and implemented Ternary Residual Networks which uses 8-bits for activations and 2-bits for weights (with residual edges, if required) for neural networks. He also helped showcase the efficacy of BFLOAT16 datatype on IA. These works have been accepted in venues such as, SuperComputing, IPDPS, ICLR, CLUSTER, and have been recognized with awards such as, ISC Best Research Poster Award (AI & ML track), Intel’s Gordy Award (Intel Labs’ highest award) and Divisional Recognition Award. He has also contributed to Intel’s accelerator for deep learning training as part of Intel Artificial Intelligence Products Group.
Prior to joining Intel, he received my PhD from the Department of Computer Science and Engineering, IIT Kharagpur. His research areas encompassed program analysis, formal methods and verification. He was a recipient of Senior Research Fellowship from the Department of Science and Technology, India, and TCS Research Fellowship from Tata Consultancy Services for supporting his doctoral studies. His dissertation work won Best PhD Thesis Award at VLSI Design, Best PhD Forum Paper at ISVLSI and Techno Inventor Award (PhD) from India Electronics & Semiconductor Association (IESA).
|BotSE 2021||Author of Designing a Bot for Efficient Distribution of Service Requests within the BotSE 2021-track|
|* ICSE 2018 *||Author of Poster W29: Automatic Detection of Inverse Operations while Avoiding Loop Unrolling within the Posters -track|