Scholar
Amit Sabne
Google Scholar ID: bG21Cg4AAAAJ
Google
Citations & Impact
Citations
1,509
H-index
15
i10-index
19
Publications
20
Co-authors
0
Contact
No contact links provided.
Publications
Resume (English only)
Academic Achievements
- Proposed and developed efficient programming models for accelerators, provided compiler and runtime support for these models, and formulated fast autotuning mechanisms for accelerator programs.
Research Experience
- Worked as a software engineer at Microsoft in the Visual C++ compiler team, researching and designing novel optimization techniques to improve program performance while lowering binary size and compilation time; conducted PhD research at Paramount Lab focusing on High Performance Computing, specifically on heterogeneous computing systems; interned with NEC Labs, Future Technologies Group at Oak Ridge National Labs, nVIDIA's CUDA Compiler team, and Qualcomm's Modems Systems Engineering team.
Education
- PhD in Computer Engineering from the School of Electrical and Computer Engineering, Purdue, under the guidance of Rudolf Eigenmann; B. Eng. (Hons.) in Electronics and Instrumentation from BITS-Pilani, India.
Background
- Senior staff software engineer and a technical lead manager at Google, working on a high performance compiler for Tensor Processing Units (TPUs), named XLA. Research interests include High Performance Computing with a focus on heterogeneous computing systems.
Miscellany
- Hobbies and other personal interests are not detailed.
Co-authors