Mohammad Alian

Mohammad Alian

Auto-generated profile, based on publicly available information

Mohammad Alian

Cornell University, Ithaca, NY, USA

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

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

Representative Publications

View All Publications
30 March 2025
Verified
Conference Paper
Open access
DQDerrick Quinn
Derrick Quinn
MNMohammad Nouri
Mohammad Nouri
NPNeel Patel
Neel Patel
JSJohn Salihu
John Salihu
ASAlireza Salemi
Alireza Salemi
MAMohammad Alian
Mohammad Alian
An evolving solution to address hallucination and enhance accuracy in large language models (LLMs) is Retrieval-Augmented Generation (RAG), which involves augmenting LLMs with information retrieved from an external knowledge source, such as the web. This paper profiles several RAG execution pipelines and demystifies the complex interplay between their retrieval and generation phases. We demonstrate that while exact retrieval schemes are expensive, they can reduce inference time compared to approximate retrieval variants because an exact retrieval model can send a smaller but more accurate list of documents to the generative model while maintaining the same end-to-end accuracy. This observation motivates the acceleration of the exact nearest neighbor search for RAG. In this work, we design Intelligent Knowledge Store (IKS), a type-2 CXL device that implements a scale-out near-memory acceleration architecture with a novel cache-coherent interface between the host CPU and near-memory accelerators. IKS offers 13.4--27.9× faster exact nearest neighbor search over a 512GB vector database compared with executing the search on Intel Sapphire Rapids CPUs. This higher search performance translates to 1.7--26.3× lower end-to-end inference time for representative RAG applications. IKS is inherently a memory expander; its internal DRAM can be disaggregated and used for other applications running on the server to prevent DRAM -- which is the most expensive component in today's servers -- from being stranded.

20 June 2025
Verified
Conference Paper
Open access
DQDerrick Quinn
Derrick Quinn
EYE. Ezgi Yücel
E. Ezgi Yücel
MPMartin Prammer
Martin Prammer
ZFZhenxing Fan
Zhenxing Fan
KSKevin Skadron
Kevin Skadron
MAMohammad Alian
Mohammad Alian

27 April 2024
Verified
Conference Paper
Open access
RMRohan Mahapatra
Rohan Mahapatra
SGSoroush Ghodrati
Soroush Ghodrati
BAByung Hoon Ahn
Byung Hoon Ahn
SKSean Kinzer
Sean Kinzer
SWShu-Ting Wang
Shu-Ting Wang
HEHadi Esmaeilzadeh
Hadi Esmaeilzadeh

17 October 2025
Verified
Conference Paper
Open access
DQDerrick Quinn
Derrick Quinn
EYE. Ezgi Yücel
E. Ezgi Yücel
JKJinkwon Kim
Jinkwon Kim
JMJosé F. Martínez
José F. Martínez
MAMohammad Alian
Mohammad Alian

28 October 2023
Verified
Conference Paper
Open access
NPNeel Patel
Neel Patel
AMAmin Mamandipoor
Amin Mamandipoor
DQDerrick Quinn
Derrick Quinn
MAMohammad Alian
Mohammad Alian
DRAM constitutes over 50% of server cost and 75% of the embodied carbon footprint of a server. To mitigate DRAM cost, far memory architectures have emerged. They can be separated into two broad categories: software-defined far memory (SFM) and disaggregated far memory (DFM). In this work, we compare the cost of SFM and DFM in terms of their required capital investment, operational expense, and carbon footprint. We show that, for applications whose data sets are compressible and have predictable memory access patterns, it takes several years for a DFM to break even with an equivalent capacity SFM in terms of cost and sustainability. We then introduce XFM, a near-memory accelerated SFM architecture, which exploits the coldness of data during SFM-initiated swap ins and outs. XFM leverages refresh cycles to seamlessly switch the access control of DRAM between the CPU and near-memory accelerator. XFM parallelizes near-memory accelerator accesses with row refreshes and removes the memory interference caused by SFM swap ins and outs. We modify an open source far memory implementation to implement a full-stack, user-level XFM. Our experimental results use a combination of an FPGA implementation, simulation, and analytical modeling to show that XFM eliminates memory bandwidth utilization when performing compression and decompression operations with SFM s of capacities up to 1TB. The memory and cache utilization reductions translate to 5 ∼ 27% improvement in the combined performance of co-running applications.

15 December 2020 in IEEE Computer Architecture Letters
Verified
Journal Article
Closed access
MAMohammad Alian
Mohammad Alian
JSJongmin Shin
Jongmin Shin
KKKi-Dong Kang
Ki-Dong Kang
RWRen Wang
Ren Wang
ADAlexandros Daglis
Alexandros Daglis
NKNam Sung Kim
Nam Sung Kim
Network bandwidth demand in datacenters is doubling every 12 to 15 months. In response to this demand, high-bandwidth network interface cards, each capable of transferring 100s of Gigabits of data per second, are making inroads into the servers of next-generation datacenters. Such unprecedented data delivery rates on server endpoints raise new challenges, as inbound network traffic placement decisions within the memory hierarchy have a direct impact on end-to-end performance. Modern server-class Intel processors leverage DDIO technology to steer all inbound network data into the last-level cache (LLC), regardless of the network traffic’s nature. This static data placement policy is suboptimal, both from a performance and an energy efficiency standpoint. In this work, we design IDIO , a framework that—unlike DDIO—dynamically decides where to place inbound network traffic within a server’s multi-level memory hierarchy. IDIO dynamically monitors system behavior and distinguishes between different traffic classes to determine and periodically re-evaluate the best placement location for each flow: LLC, mid-level (L2) cache or DRAM. Our results show that IDIO increases a server’s maximum sustainable load by up to $\sim$ 33.3% across various network functions.