Yuanbo Wen

Yuanbo Wen

Auto-generated profile, based on publicly available information

Yuanbo Wen

State Key Lab of Processors, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China

Research Focus & Metrics

Academic Career Length

22Years (2005-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 December 2005 in IEEE Transactions on Nuclear Science
Verified
Journal Article
Closed access
CMC.J. Marshall
C.J. Marshall
PMPaul William Mark Marshall
Paul William Mark Marshall
AWA. Waczynski
A. Waczynski
EPE.J. Polidan
E.J. Polidan
SJS.D. Johnson
S.D. Johnson
RHR.J. Hill
R.J. Hill
A Hubble space telescope wide field camera 3 e2v CCD was irradiated while operating at -84/spl deg/C and the dark current studied as a function of temperature while the charge coupled device was warmed to a sequence of temperatures up to a maximum of +30/spl deg/C. The device was then cooled back down to -84/spl deg/ and remeasured. Hot pixel populations were tracked during the warm up and cool down. Hot pixel annealing began below -40/spl deg/C and the anneal process was largely completed by the time the detector reached +20/spl deg/C. There was no apparent sharp annealing temperature. Although a large fraction of the hot pixels fell below the threshold to be counted as a hot pixel, they nevertheless sustained a higher leakage rate than the remaining population. The mechanism for hot pixel annealing is not presently understood. Room temperature irradiations do not adequately characterize the hot pixel distributions for cooled applications.

1 January 2025 in Journal of Computer Science and Technology
Verified
Journal Article
Closed access
PDF file
ZZZhen-Xing Zhang
Zhen-Xing Zhang
YWYuan-Bo Wen
Yuan-Bo Wen
HLHan-Qi Lyu
Han-Qi Lyu
CLChang Liu
Chang Liu
RZRui Zhang
Rui Zhang
YCYun-Ji Chen
Yun-Ji Chen


28 October 2023
Verified
Conference Paper
Open access
XSXinkai Song
Xinkai Song
YWYuanbo Wen
Yuanbo Wen
XHXing Hu
Xing Hu
TLTianbo Liu
Tianbo Liu
HZHaoxuan Zhou
Haoxuan Zhou
TCTianshi Chen
Tianshi Chen
Neural scene representation (NSR) initiates a new methodology of encoding a 3D scene with neural networks by learning from dozens of photos taken from different camera positions. NSR not only achieves significant improvement in the quality of novel view synthesis and 3D reconstruction but also reduces the camera cost from the expensive laser cameras to the cheap color cameras on the shelf. However, performing 3D scene encoding using NSR is far from real-time due to the extremely low hardware utilization (only utilization of hardware peak performance), which greatly limits its applications in real-time AR/VR interactions In this paper, we propose Cambricon-R, a fully fused on-chip processing architecture for real-time NSR learning. Initially, by performing a thorough characterization of the computing model of NSR on a GPU, we find that the extremely low hardware utilization is mainly caused by the fragmentary stages and heavy irregular memory accesses. To address these issues, we propose Cambricon-R architecture with a novel fully-fused ray-based execution model to eliminate the computing and memory inefficiencies for real-time NSR learning. Concretely, Cambricon-R features a ray-level fused architecture that not only eliminates the intermediate memory traffics but also leverages the point sparsity in scenes to eliminate unnecessary computations. Additionally, a high throughput on-chip memory system based on Auto-Interpolation Bank Array (AIBA) is proposed to efficiently handle a large volume of irregular memory accesses. We evaluate Cambricon-R on 12 commonly-used datasets with the state-of-the-art representative algorithm, instant-ngp. The result shows that Cambricon-R achieves PE utilization of , on average. Compared to the state-of-the-art solution on A100 GPU, Cambricon-R achieves 373.8 × speedup and 256.6 × energy saving, on average. More importantly, it enables real-time NSR learning with 69.0 scenes per second, on average.

23 June 2024
Verified
Conference Paper
Open access
SCShuyao Cheng
Shuyao Cheng
CLChongxiao Li
Chongxiao Li
ZDZidong Du
Zidong Du
RZRui Zhang
Rui Zhang
XHXing Hu
Xing Hu
QGQi Guo
Qi Guo
Pipelining is a widely applied micro-architectural performance optimization and requires non-trivial designs for better execution throughput. The key to pipeline throughput optimization is to resolve data hazards caused by read-after-write (RAW) dependencies, which are traditionally tackled by forwarding and speculation to avoid pipeline stalls. However, existing approaches are conducted based on high-level dataflow analysis, with potential loss of optimization opportunities for lack of analysis of the netlist structures. We propose an efficient method to resolve RAW dependencies with low-level netlist analysis by gate-level forwarding and speculation. With a greedy search method to detect and resolve short-delay gate-level signal paths for forwarding and an approximate circuit synthesis method with formal verification for gate-level speculation, the method efficiently utilizes the gate-level information to further improve pipeline throughput. Even if the gate-level design space is vast, by assembling the logic gates in the short-delay signal paths in fewer adjacent pipeline stages, the forwarding paths and the speculator bypass invalid pipeline stages and thus conceal the latency of these paths. We conduct experiments on the widely-used ISCAS/EPFL benchmark circuits and a large-scale RISC-V CPU, and our approach can find better designs than human experts.