Pei Mu is a compiler-focused researcher and engineer with a decade of experience building high-performance compilation pipelines for AI accelerators. He has shipped deep learning compiler features and backend codegens at SenseTime and Huawei (TBE for Ascend), and interned on compiler research at Microsoft, blending systems-level compiler engineering with applied research in auto-scheduling and polyhedral transformations. His work spans IR and pass design, control-flow and extern_call support, and generation of device-specific code (BangC, Cambricon MLU), with concrete wins in operator compile-time reduction and runtime performance optimization. Now based in Edinburgh pursuing an MSc by Research in compilers, he pairs industrial delivery with academic rigor and an unusual depth in low-level codegen for specialized ML hardware.
10 years of coding experience
4 years of employment as a software developer
Bachelor of Engineering - BE, 85.75(100), Bachelor of Engineering - BE, 85.75(100) at 山东大学
MSc by Research, compilers, MSc by Research, compilers at 英国爱丁堡大学
The Torch-MLIR project aims to provide first class support from the PyTorch ecosystem to the MLIR ecosystem.
Contributions:4 PRs, 49 pushes, 8 branches in 1 year 5 months
pytorchmlirdeep-learningtorchecosystem
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.