As part of the Qualcomm Lecture Series, the participants would learn the basics of Apache TVM, of an image processing language, of static analysis, as well as of scientific writing. These talks are planned on Mondays from December through January, and are open to all.

The talks would be delivered by The LLVM Toolchain team at Qualcomm. The team works on compilers and development tools for the different hardware blocks in the Snapdragon chipsets. The tools are based on the LLVM framework and enable developers to write efficient and high quality C/C++ applications. The team also supports Halide, a DSL meant for image processing applications and TVM, a framework for AI/ML applications. Halide and TVM compilers make it easy for the developers to write applications and generate optimized code for the Hexagon DSP hardware. The toolchain also includes tools like simulators, debuggers, profilers and code hygiene tools which help developers write better code.

Registration
Registration is free but mandatory. Please register for the lecture series here (it takes less than a minute).

Program
The event is scheduled online. E-meeting details will be mailed to the registered participants. Each talk is for 1 hour duration.

Date Time Speaker and Topic

December 7 15:30 Apache TVM: A Framework for AI/ML Applications
by Ravi Kolachana
Ravi has been working on various development tools like compilers/linkers/loaders/simulators/debuggers/IDEs over the last 16 years at Qualcomm.

December 14 15:30 Halide: A DSL for Image Processing
by Suyog Sarda
Suyog’s primary interest lies in system programming, compilers, code optimization. For past 3 years, he has been working on Halide on Hexagon DSP.

December 21 15:30 Profiling Based Super Block Scheduling for Code Size Sensitive Applications
by Arun Rangasamy
Arun’s primary interest is in compilers. His doctoral thesis was on compilers for optimizing energy; in industry, he has worked on compilers/libraries or optimizing performance and code size, targeting CPUs and GPUs.

January 11 15:30 Compiler driven Acceleration of Inference in Deep Neural Networks
by Arun Rangasamy
Arun’s primary interest is in compilers. His doctoral thesis was on compilers for optimizing energy; in industry, he has worked on compilers/libraries or optimizing performance and code size, targeting CPUs and GPUs.

January 18 15:30 Program Analysis: The journey from helper to oracle
by Awanish Pandey
Awanish did his Ph.D. under the supervision of Prof Subhajit Roy in the area of program analysis from I.I.T. Kanpur. After his Ph.D., he is broadly working in compilers, debuggers, and the program's security aspects.

January 25 15:30 Scientific Writing / Literature Survey
by Sushim Shrivastava
Sushim’s work domain for last 16 years at Qualcomm has been in evolution on 3G/4G/5G. For last four years he has been working on Software Security, Compilers and Machine Learning at Qualcomm.

Register Now.

Organizer

Rupesh Nasre, Coordinator for NSM Nodal Centre for Training in HPC and AI