张杰
主要研究方向
存储系统和专用处理器的研究和设计。
致力于从计算机体系结构层面出发,解决大数据和人工智能时代对于高性能存储系统的需求,突破冯诺依曼体系结构下数据迁移的瓶颈以及内存墙的限制。
负责和参与的项目得到了美国能源部、美国自然科学基金、韩国自然科学基金、三星电子、海力士、德州仪器和西部数据的资助。
在国际计算机会议上发表30余篇论文,包括:
计算机体系结构顶级会议ISCA(CCF-A,两篇),HPCA(CCF-A,三篇),MICRO(CCF-A,两篇);系统结构顶级会议OSDI (CCF-A), Eurosys (CCF-B);并行计算顶级会议 PACT (CCF-B);计算机存储顶级会议FAST(CCF-A);以及EDA顶级会议DAC(CCF-A)。
主要学术任职
在多个CCF-A类期刊和会议上担任审稿人,包括:
· IEEE Transactions on Computer (CCF-A)
· ACM Transactions on Storage (CCF-A)
· ACM Transactions on Computer Systems (CCF-A)
· IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems (CCF-A)
· IEEE Transactions on Parallel and Distributed Systems (CCF-A)
· ACM Transactions on Architecture and Code Optimization(CCF-B)
· IEEE Computer Architecture Letters
Selected Publications
Ohm-GPU: Integrating New Optical Network and Heterogeneous Memory into GPU Multi-Processors (MICRO) 2021
Revamping Storage Class Memory With Hardware Automated Memory-Over-Storage Solution (ISCA) 2021
ZnG: Architecting GPU Multi-Processors with New Flash for Scalable Data Analysis (ISCA) 2020
Scalable Parallel Flash Firmware for Many-core Architectures (FAST) 2020
DRAM-less: Hardware Acceleration of Data Processing with New Memory (HPCA) 2020
FlashGPU: Placing New Flash Next to GPU Cores (DAC) 2019
FUSE: Fusing STT-MRAM into GPUs to Alleviate Off-Chip Memory Access Overheads (HPCA) 2019
FlashShare: Punching Through Server Storage Stack from Kernel to Firmware for Ultra-Low Latency SSDs (OSDI) 2018
Amber: Enabling Precise Full-System Simulation with Detailed Modeling of All SSD Resources (MICRO) 2018
FlashAbacus: A Self-governing Flash-based Accelerator for Low-power Systems (Eurosys) 2018
DUANG: Fast and Lightweight Page Migration in Asymmetric Memory Systems (HPCA) 2016
NVMMU: A Non-Volatile Memory Management Unit for Heterogeneous GPU-SSD Architectures (PACT) 2015