BitPacker: Enabling High Arithmetic Efficiency in Fully Homomorphic Encryption Accelerators
Nikola Samardzic, Daniel Sánchez
Abstract
Fully Homomorphic Encryption (FHE) enables computing directly on encrypted data. Though FHE is slow on a CPU, recent hardware accelerators compensate most of FHE's overheads, enabling real-time performance in complex programs like deep neural networks. However, the state-of-the-art FHE scheme, CKKS, is inefficient on accelerators. CKKS represents encrypted data using integers of widely different sizes (typically 30 to 60 bits). This leaves many bits unused in registers and arithmetic datapaths. This overhead is minor in CPUs, but accelerators are dominated by multiplications, so poor utilization causes large area and energy overheads.
Ask about this paper
Ask your agent about it.
Lune has read the top-tier papers around this one, so every answer names the papers it rests on.
Your agent calls
Lunesearch_papers
Free to start. No credit card required.
Terminal
Install the CLIlune papers get 5a48f570-e5fb-4a11-b66d-6bec20d2d7f1Cited by top-tier papers6
- Cinnamon: A Framework for Scale-Out Encrypted AISiddharth Jayashankar, Edward Chen, Tom Tang, Wenting Zheng et al.ASPLOS 2025 · 10 citations
- Cheddar: A Swift Fully Homomorphic Encryption Library Designed for GPU ArchitecturesWonseok Choi, Jongmin Kim, Jung Ho AhnASPLOS 2026 · 6 citations
- CROPHE: Cross-Operator Dataflow Optimization for Fully Homomorphic Encryption AcceleratorsXinhua Chen, Jiangbin Dong, Hongren Zheng, Tian Tang et al.HPCA 2026 · 1 citation
- Leveraging Discrete CKKS to Bootstrap in High PrecisionHyeongmin Choe, Jaehyung Kim, Damien Stehlé, Elias SuvantoCCS 2025
- Fenc2: Unifying Data Packing for Efficient Private Inference via Convolution and Architecture-Aware Fragment EncodingRan Ran, Zhaoting Gong, Nuo Xu, Yuanchao Xu et al.ISCA 2026
Related papers
- SHARP: A Short-Word Hierarchical Accelerator for Robust and Practical Fully Homomorphic EncryptionJongmin Kim, Sangpyo Kim, Jaewan Choi, Jaiyoung Park et al.ISCA 2023 · 110 citations
- Coyote: A Compiler for Vectorizing Encrypted Arithmetic CircuitsRaghav Malik, Kabir Sheth, Milind KulkarniASPLOS 2023 · 22 citations
- Falcon: Algorithm-Hardware Co-Design for Efficient Fully Homomorphic Encryption AcceleratorLiang Kong, Xianglong Deng, Guang Fan, Shengyu Fan et al.ASPLOS 2026
- F1: A Fast and Programmable Accelerator for Fully Homomorphic EncryptionNikola Samardzic, Axel Feldmann, Aleksandar Krastev, Srinivas Devadas et al.MICRO 2021 · 294 citations
- A Tensor Compiler with Automatic Data Packing for Simple and Efficient Fully Homomorphic EncryptionAleksandar Krastev, Nikola Samardzic, Simon Langowski, Srinivas Devadas et al.PLDI 2024 · 23 citations
