Accelerating Confidential Recommendation Model Inference With Near-Memory Processing
- 24 January 2025
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Dependable and Secure Computing
- Vol. 22 (4) , 3580-3586
Abstract
Trusted Executing Environments (TEEs) in hardware designs protect program execution from other untrusted software programs in the processor as well as untrusted off-chip hardware components. Meanwhile, Near-Memory Processing (NMP) has shown performance and energy benefits on memory-intensive workloads. Recently, novel memory encryption schemes have been proposed to allow TEEs to leverage the benefit of NMP without trusting the NMP components. In this paper, we present a system design of confidential computing with NMP that can be directly used in Intel SGX, a TEE platform available in commercial processors today. We develop the full software stack and evaluate the results on commercial processors with the emulated AxDIMM, an FPGA-based NMP platform. In our case study on personalized Deep Learning Recommendation Model (DLRM) inference, the proposed confidential computing in NMP achieves up to 1.51× latency reduction and up to 2.57× throughout improvement.Keywords
Funding Information
- Air Force Office of Scientific Research (FA9550-22-1-0548)
- National Science Foundation (CCF-1942900)
This publication has 17 references indexed in Scilit:
- SecNDP: Secure Near-Data Processing with Untrusted Memory2022
- Near-Memory Processing in Action: Accelerating Personalized Recommendation With AxDIMMIEEE Micro, 2021
- Hardware Architecture and Software Stack for PIM Based on Commercial DRAM Technology : Industrial Product2021
- RecNMP: Accelerating Personalized Recommendation with Near-Memory Processing2020
- Regaining Lost Cycles with HotCalls2017
- Chameleon: Versatile and practical near-DRAM acceleration architecture for large memory systems2016
- PIM-enabled instructions2015
- AEGIS2014
- Multiparty Computation from Somewhat Homomorphic Encryption2012
- Efficient memory integrity verification and encryption for secure processors2003