My research explores opportunities in the intersection of computer architecture and networking to build efficient datacenters. My goal is to unlock the potentials of hardware and operating system co-design in architecting application-transparent, near-data processing hardware for improving datacenter's performance, energy efficiency, and scalability.
I have available funded research positions. Please contact me if you are interested in doing computer architecture and systems research.
Here are my research themes:
Near-Memory Processing (MICRO'18): Data movement is the main performance and power bottleneck in today’s large-scale computer systems. We are looking at novel architectures reduce the data movement in large-scale computers without compromising their programmability and cost.
In-Network Computing (MICRO'18): We are experimenting novel ways for utilizing the available computational resources in smart network devices (SmartNICs and programmable switches). More specifically, we are looking at designing a multi-node, disaggregated memory cluster in which remote memory accesses and synchronizations are accelerated by customized network protocols and in NIC computation.
Network Specialization: (MICRO'19) The future belongs to customization, not only for computation but also for communication. In our research group, we recognize the urgent need for inter-node communication network customization for large-scale computers. We study system-level solutions for customized networks that cut across processor, memory, and operating system architecture.
Mohammad Alian, "A cross-stack, network-centric architectural design for next-generation datacenters," Ph.D. Dissertation [dissertation][slides]
Soroush Ghodrati, Byung Hoon Ahn, Joon Kyung Kim, Sean Kinzer, Brahmendra Yatham, Navateja Alla, Hardik Sharma, Mohammad Alian, Eiman Ebrahimi, Nam Sung Kim, Cliff Young, Hadi Esmaeilzadeh, "Planaria: Dynamic architecture fission for spatial multi-tenant acceleration of deep neural networks," IEEE/ACM International Symposium on Microarchitecture (MICRO), to appear [paper][slides]
Jason Lowe-Power, Abdul Mutaal Ahmad, Ayaz Akram, Mohammad Alian, et al. "The gem5 simulator: Version 20.0+," arXiv preprint [paper]
Yifan Yuan, Mohammad Alian, Yipeng Wang, Ilia Kurakin, Ren Wang, Charlie Tai, Nam Sung Kim, "IOCA: High-speed I/O-aware LLC management for network-centric multi-tenant platforms," arXiv preprint [paper]
Mohammad Alian, Yifan Yuan, Jie Zhang, Ren Wang, Myoungsoo Jung, and Nam Sung Kim, "Data direct I/O characterization for future I/O system exploration," IEEE International Symposium on Performance Analysis of Systems and Software (ISPASS) [paper][slides]
Mohammad Alian, and Nam Sung Kim, "NetDIMM: Low-latency, near-memory network interface architecture," IEEE/ACM International Symposium on Microarchitecture (MICRO) [paper][slides]
Ki-dong Kang, Mohammad Alian, Deahoon Kim, Jaehyuk Huh, and Nam Sung Kim, "VIP: Virtual performance-state for efficient power management," ACM Symposium on Cloud Computing (SoCC) [paper][slides]
Mohammad Alian, Krishna Parasuram Srinivasan, and Nam Sung Kim, "Simulating PCI-express interconnect for future system exploration," IEEE International Symposium on Workload Characterization (IISWC) [paper][slides] [Nominated for the Best Paper Award]
Jie Zhang, Miryeong Kwon, Donghyun Gouk, Changlim Lee, Mohammad Alian, Myoungjun Chun, Mahmut Kandemir, Nam Sung Kim, Jihong Kim, and Myoungsoo Jung, "FlashShare: Punching through server storage stack from kernel to firmware for ultra-low latency SSDs," USENIX Symposium on Operating Systems Design and Implementation (OSDI) [paper][slides]
Seung Won Min, Mohammad Alian, Wen-mei Hwu, and Nam Sung Kim, "Semi-coherent DMA: An alternative I/O coherency management for embedded systems," IEEE Computer Architecture Letters (CAL)[paper]
Mohammad Alian, Seung Won Min, Hadi Asgharimoghaddam, Ashutosh Dhar, Dong Kai Wang, Thomas Roewer, Adam McPadden, Oliver OHalloran, Deming Chen, Jinjun Xiong, Daehoon Kim, Wen-mei Hwu, and Nam Sung Kim, "Application-transparent near-memory processing architecture with memory vhannel network," IEEE/ACM International Symposium on Microarchitecture (MICRO),[paper][slides] [Nominated for the Best Paper Award]
Youjie Li, Jongsea Park, Mohammad Alian, Yifan Yuan, Qu Zheng, Petian Pan, Ren Wang, Alexander Gerhard Schwing, Hadi Esmaeilzadeh, and Nam Sung Kim, "A network-centric hardware/argorithm co-design to accelerate distributed training of deep neural networks," IEEE/ACM International Symposium on Microarchitecture (MICRO) [paper][slides]
Seokhan Lee, Kiwon Lee, Minchul Sung, Mohammad Alian, Chankyung Kim, Wooyeong Cho, Reum Oh, Seongil O, Jung Ho Ahn, and Nam Sung Kim, "3D-XPath: High-density managed DRAM architecture with cost-effective alternative paths for memory transactions," Parallel Architecture and Compilation Techniques (PACT) [paper][slides]
Daehoon Kim, Mohammad Alian, Jaehyuk Huh, and Nam Sung Kim, "Janus: Supporting heterogeneous power management in virtualized environments," ACM Symposium on Cloud Computing (SoCC) [poster]
Mohammad Alian, Gabor Dozsa, Umur Darbaz, Stephan Diestelhorst, Daehoon Kim, and Nam Sung Kim, "dist-gem5: Distributed simulation of computer clusters," IEEE International Symposium on Performance Analysis of Systems (ISPASS) [paper][slides] [Nominated for the Best Paper Award]
Mohammad Alian, Ahmed Abulila, Lokesh Jindal, Daehoon Kim, and Nam Sung Kim, “NCAP: Network-driven, packet context-aware power management for client-server architecture,” IEEE Symposium on High Performance Computer Architecture (HPCA) [paper][slides] [Nominated for the Best Paper Award] [Honorable Mention in 2018 IEEE MICRO Top Picks]
Mohammad Alian, Daehoon Kim, and Nam Sung Kim, “pd-gem5: Simulation Infrastructure for Parallel/Distributed Computer Systems,” IEEE Computer Architecture Letters (CAL), Jan 2016, Paper
Mohammad Alian, "pd-gem5: Simulation infrastructure for parallel/distributed computer systems for network-driven optimization," Masters Thesis [thesis]