Lonely Emo
Software Engineer at Emonazi
Deolali, Maharashtra, India
Summary
🤩
RockstarLonely Emo is a software engineer with five years of experience specializing in compilers and computer architecture, currently working at Emonazi from Deolali, India. He is an active open-source contributor to LLVM/MLIR ecosystems, having improved NVGPU and Affine dialects and added shape-checking and optimization passes to enhance thread-to-data mapping and vector handling. At buddy-compiler he helped build MLIR-based compiler examples and integrated an ANTLR frontend for a Toy language, plus GPU and vector operation demos that bridge DSLs to domain-specific architectures. Practical and research-minded, he combines backend systems engineering with hands-on compiler engineering—unexpectedly blending student curiosity with production-grade contributions to widely used projects.
5 years of coding experience
Github Skills (14)
tensorrt10
gpu-programming10
compiler-design10
c-language10
tensor10
tensorflow10
cprogramming-language10
operation10
mlr10
antlr10
llvm10
vectorization9
vector9
testing7
Programming languages (9)
Github contributions (5)
buddy-compiler/buddy-mlir
May 2022 - Dec 2022
An MLIR-based compiler framework bridges DSLs (domain-specific languages) to DSAs (domain-specific architectures).
Role in this project:
Back-end Developer & Compiler Engineer
Back-end Developer & Compiler EngineerContributions:69 reviews, 7 commits, 43 PRs in 7 months
Contributions summary:Lonely primarily contributed to the development of examples demonstrating the use of MLIR dialects for compiler development. The commits showcase the implementation of examples using MLIR for affine, memref, and tensor operations, including reinterpret casts, insert/extract slices, and shape manipulations. They also worked on integrating an ANTLR frontend to the Toy language within the MLIR framework, creating a more complete compiler example. Furthermore, they added examples for GPU and vector operations within the MLIR framework.
mlir
llvm/llvm-project
Jun 2022 - Mar 2025
The LLVM Project is a collection of modular and reusable compiler and toolchain technologies.
Role in this project:Back-end Developer
Back-end DeveloperContributions:49 reviews, 33 PRs, 7 pushes in 2 years 10 months
Contributions summary:Lonely primarily contributed to the MLIR (Multi-Level Intermediate Representation) project within the LLVM project, focusing on the NVGPU and Affine dialects. Their work involved implementing and testing new features, including adding shape checks to the nvgpu.mma op and introducing AffineScope to the gpu.func op. These changes aimed to improve thread-to-data mapping and shape validation. Further contributions include folding constant indices in vector operations, and making affine-loop-unroll and affine-loop-unroll-jam passes interface passes.
compilerstechnologiesclangsubmittoolchain
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.