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.
Topics & Concepts
Homomorphic encryptionComputer scienceOverhead (engineering)EncryptionScheme (mathematics)Parallel computingArithmeticEmbedded systemComputer hardwareOperating systemMathematicsMathematical analysisCryptography and Data SecurityComplexity and Algorithms in GraphsAdvanced Data Storage Technologies