abhinav Ashok kumar

Product Manager

India6 yrs 3 mos experience
Most Likely To SwitchAI Enabled

Key Highlights

  • Expert in LLVM and compiler optimization techniques.
  • Contributed to significant open-source projects like LLVM and MCSEMA.
  • Proficient in performance benchmarking and analysis.
Stackforce AI infers this person is a Compiler Optimization Specialist in the Open Source and High-Performance Computing industry.

Contact

Skills

Core Skills

Compiler OptimizationLlvm

Other Skills

MLIRperformance benchmarkingPythonBashMakeCMakeMIPS architectureopen-source contributionGDBClangGreen Hills compilerdecompilationIDA ProIDAPythonTensorFlow

About

As a GPU Compiler Performance Analyst at Qualcomm, I am an essential member of a dynamic team dedicated to delivering optimized, reliable, and high-performance compiler solutions tailored for diverse GPU architectures. Drawing upon my expertise in LLVM, MLIR, and machine learning (ML)/artificial intelligence (AI) techniques within compilers, I play a crucial role in designing and implementing compiler optimizations that exploit specific GPU features and requirements, such as code generation, memory access patterns, and parallel execution. I assume a pivotal role in crafting and implementing compiler optimizations specifically tailored to leverage the unique features and demands of various GPU architectures. My focus spans from code generation and memory access patterns to parallel execution, ensuring our solutions achieve unparalleled performance and reliability. Role and Responsibilities: Compiler Optimization: Leveraging the modular framework of LLVM, I design and implement compiler optimizations customized for specific GPU architectures. This involves refining code generation strategies, optimizing memory access patterns, and maximizing parallel execution to achieve peak performance. Performance Benchmarking: I am responsible for developing and executing comprehensive performance benchmarking tests to evaluate the effectiveness of compiler optimizations. By analyzing critical metrics such as execution time, memory usage, and power consumption across diverse workloads and scenarios, I ensure that our compiler solutions meet stringent performance targets. Hands-on Experience: I bring significant hands-on experience in various aspects of compiler development and validation. Additionally, I am proficient in Python and Bash scripting, as well as the Make and CMake build systems. My expertise extends to various standards of C++, enabling me to navigate complex compiler toolchains with ease. With a comprehensive skill set encompassing compiler optimization, performance benchmarking, and hands-on experience with Python, Bash, Make, CMake, and various C++ standards, I am well-equipped to contribute effectively to the development of high-performance compiler solutions

Experience

6 yrs 3 mos
Total Experience
2 yrs 3 mos
Average Tenure
3 yrs 6 mos
Current Experience

Qualcomm

Gpu compiler performance analysist

Nov 2022Present · 3 yrs 6 mos · Bengaluru, Karnataka, India

  • I am an indispensable member of a dynamic team committed to delivering cutting-edge compiler solutions tailored for diverse GPU architectures. Leveraging my extensive expertise in LLVM, MLIR, and machine learning (ML)/artificial intelligence (AI) techniques within compilers, I assume a pivotal role in crafting and implementing compiler optimizations specifically tailored to leverage the unique features and demands of various GPU architectures, including those compatible with DirectX, Vulkan, and SPIR-V. My focus spans from code generation and memory access patterns to parallel execution, ensuring our solutions achieve unparalleled performance and reliability.
  • Furthermore, my comprehensive understanding of GPU pipeline architecture in software empowers me to optimize compiler solutions effectively. This proficiency enables me to identify and implement optimizations that capitalize on GPU pipeline capabilities, enhancing performance and efficiency.
  • I have experience in compiler optimizations such as register allocation, instruction scheduling, loop optimization, and memory access optimization. .
  • In essence, my expertise in automation and scripting, coupled with my knowledge of GPU pipeline architecture, enables me to contribute effectively to the development of high-performance compiler solutions
LLVMMLIRcompiler optimizationperformance benchmarkingPythonBash+2

Blackfig techologies

Compiler Engineer

Oct 2021Nov 2022 · 1 yr 1 mo · Bangalore Urban, Karnataka, India

  • In my role, I conduct competitive performance analysis and resolve root bugs, including addressing customer-reported issues in VxWorks libc++ and LLVM. I possess hands-on experience in building tools like CMake and Make, as well as debugging with industry-standard tools such as GDB, LLDB, and Valgrind. My expertise extends to compiler optimization, where I strive to enhance performance and efficiency. Additionally, I am adept at utilizing software integration and release tools like Git and JIRA to ensure seamless project management and collaboration.
  • My proficiency spans the C/C++ toolchain, encompassing LLVM, Clang, GCC, and Binutils, as well as C/C++ standard libraries and compiler-rt and runtime libraries. I have extensive experience in benchmarking analysis, enabling me to evaluate and optimize system performance effectively. Moreover, my familiarity with ARM, MIPS, x86, and PowerPC architectures equips me to navigate diverse computing environments with ease.
  • . Carry out Competative performance analysis root and bug Resolving including customers bug in VxWorks libc++ and LLVM
  • . Hands on experience on building tools such as cmake, make and debugging issues with gdb, lldb, valgrind.
  • .Experience in compiler optimization
  • . Familiar with software integration and release tool such as Git and JIRA
  • . Have experience in C/C++ toolchain like LLVM. CLANG. GCC, BINUTILS,
  • . C/C++ standard libraries, compiler-rt and runtime libraries
  • experince in benchmarking analysis
  • familiar with arm, mips, x86 powerpc architecture
CMakeMakeGDBLLVMcompiler optimization

Robert bosch india limited,bangalore

Software Engineer

May 2021Oct 2021 · 5 mos · India

  • During my tenure at Bosch, I had the privilege of delving into the realm of compiler optimization, where I honed my skills in enhancing code efficiency and performance. I navigated seamlessly between proprietary environments, including the Green Hills compiler, and open-source tools like MinGW and Clang. This versatility allowed me to adapt to different ecosystems and optimize code across various platforms.
  • In my journey with Clang compiler, I explored the utilization of diverse sanitizer flags and runtime libraries, leveraging them to ensure code robustness and stability. Additionally, my familiarity with LLVM passes empowered me to delve deeper into code transformation and optimization techniques, driving enhancements in code quality and performance.
  • Moreover, I delved into compiler verification and debugging methods, ensuring the reliability and integrity of compiler output. These experiences not only enriched my technical acumen but also equipped me with invaluable insights into ensuring the correctness and efficiency of compiler-generated code.
  • As I embark on new endeavors, I carry with me a wealth of experience and expertise in compiler optimization, propelling me to pursue excellence and innovation in every aspect of my professional journey.
compiler optimizationClangGreen Hills compiler

Open source

Open source

Feb 2020Mar 2025 · 5 yrs 1 mo

  • I've had the opportunity to contribute to a couple of notable open-source projects:
  • LLVM: During my free time, I've made modest contributions to LLVM, mainly focusing on improving test cases and documentation. These efforts aimed to enhance the reliability and usability of LLVM for developers.
  • MCSEMA: While working at CDAC, I was fortunate to be part of a team that added support for the MIPS architecture to MCSEMA-4.0. It was a collaborative effort, and I'm grateful to have played a role in expanding MCSEMA's capabilities.
  • These experiences have allowed me to contribute to the open-source community in small but meaningful ways, and I'm humbled to have had the opportunity to be a part of these projects.
  • I have a keen interest in contributing to open-source projects, particularly in the realm of AI/ML in compiler
LLVMMIPS architectureopen-source contribution

Cdac

Project Engineer

Feb 2020May 2021 · 1 yr 3 mos · Hyderabad Area, India

  • https://github.com/CDACesec
  • Open source contributed in the project mcsema for mips architecture
  • During my tenure at CDAC, I gained valuable experience in decompilation, particularly through my involvement in the MCSEMA project. As MCSEMA is based on LLVM, I had the opportunity to delve deep into LLVM's architecture and gain exposure to its intricacies. This hands-on experience with LLVM provided me with a comprehensive understanding of compiler internals and code transformation techniques.
  • My role in MCSEMA involved contributing to the development of the executable lifter, which is a crucial component for decompiling binary executables into LLVM IR. Through this work, I gained insights into the challenges and complexities of decompilation, including handling different architectures and optimizing code generation for accuracy and efficiency.
  • Additionally, my involvement in MCSEMA allowed me to explore various decompilation strategies and techniques, broadening my knowledge in the field. I also utilized tools like IDA Pro and IDAPython to analyze and reverse-engineer binary executables, further enhancing my expertise in decompilation and reverse engineering.
  • Overall, my experience in decompilation and involvement in the MCSEMA project provided me with invaluable exposure to LLVM and compiler technology, enriching my skill set and deepening my understanding of software analysis and transformation.
  • >worked on executable lifter mcsema, ida pro idapython.
  • >familiar with LLVM lR KLEE symbolic executions tool
  • >c++ various standard
  • >familiar with mips assembly language and it's ABI
  • >bash scripting and other BINUTILS tools for reverse engineering and debugging
LLVMdecompilationIDA ProIDAPython

Education

Centre for Development of Advanced Computing (C-DAC)

Diploma in Embedded System And Design — Embedded System

Jan 2019Jan 2020

SHAMBHUNATH INSTITUTE OF ENGG AND TECHNOLOGY , ALLAHABAD

Bachelor of Technology — Computer Science

Jan 2014Jan 2018

Stackforce found 100+ more professionals with Compiler Optimization & Llvm

Explore similar profiles based on matching skills and experience