Experiences and Progresses on Binary Translation system for Loongson Processor
- Chenggang Wu | Chinese Academy of Sciences
Chenggang Wu’s group started to research on Binary Translation (BT) technology since 2003. They try to provide a BT system for the China-made processor——Loongson. The performance of China-made processors is still much slower than state-of-the-art processors. They have to reduce the overhead of BT system as much as possible so as to provide users good experience. Now, their BT system can achieve 65% performance on average in comparison with native code generated by GNU CC4.4 –O3. In this talk, Chenggang will introduce their experiences and research progresses during their developing process.
Speaker Details
Chenggang Wu has been an associate professor at Institute of Computing Technology (ICT), Chinese Academy of Sciences (CAS) since 2005. He received his Ph.D. degree in Computer Science from ICT, CAS in 2001. His research interests include dynamic optimization, program analysis and computer architecture. Currently, He focus on research and development on dynamic binary translation and process-level virtual machines. His group is developing a dynamic binary translation system, DigitalBridge, which is expected to serve as an X86 virtual machine on Loongson processors. It can support several popular applications and provide user good experience now.
His work is founded by National Natural Science Foundation of China, the National Basic Research Program of China, the National High Technology Research and Development Program of China, and the National Science and Technology Major Project of China.
-
-
Jeff Running
-
-
Series: Microsoft Research Talks
-
Decoding the Human Brain – A Neurosurgeon’s Experience
- Dr. Pascal O. Zinn
-
-
-
-
-
-
Challenges in Evolving a Successful Database Product (SQL Server) to a Cloud Service (SQL Azure)
- Hanuma Kodavalla,
- Phil Bernstein
-
Improving text prediction accuracy using neurophysiology
- Sophia Mehdizadeh
-
Tongue-Gesture Recognition in Head-Mounted Displays
- Tan Gemicioglu
-
DIABLo: a Deep Individual-Agnostic Binaural Localizer
- Shoken Kaneko
-
-
-
-
Audio-based Toxic Language Detection
- Midia Yousefi
-
-
From SqueezeNet to SqueezeBERT: Developing Efficient Deep Neural Networks
- Forrest Iandola,
- Sujeeth Bharadwaj
-
Hope Speech and Help Speech: Surfacing Positivity Amidst Hate
- Ashique Khudabukhsh
-
-
-
Towards Mainstream Brain-Computer Interfaces (BCIs)
- Brendan Allison
-
-
-
-
Learning Structured Models for Safe Robot Control
- Subramanian Ramamoorthy
-