OFHE: An Electro-Optical Accelerator for Discretized TFHE

• URL: http://arxiv.org/abs/2405.11607v1
• Date: Sun, 19 May 2024 16:27:21 GMT
• Title: OFHE: An Electro-Optical Accelerator for Discretized TFHE
• Authors: Mengxin Zheng, Cheng Chu, Qian Lou, Nathan Youngblood, Mo Li, Sajjad Moazeni, Lei Jiang,
• Abstract summary: textitOFHE is an electro-optical accelerator designed to process Discretized TFHE (DTFHE) operations. DTFHE is more efficient and versatile than other fully homomorphic encryption schemes. Existing TFHE accelerators are not easily upgradable to support DTFHE operations.
• Score: 14.192223933448174
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: This paper presents \textit{OFHE}, an electro-optical accelerator designed to process Discretized TFHE (DTFHE) operations, which encrypt multi-bit messages and support homomorphic multiplications, lookup table operations and full-domain functional bootstrappings. While DTFHE is more efficient and versatile than other fully homomorphic encryption schemes, it requires 32-, 64-, and 128-bit polynomial multiplications, which can be time-consuming. Existing TFHE accelerators are not easily upgradable to support DTFHE operations due to limited datapaths, a lack of datapath bit-width reconfigurability, and power inefficiencies when processing FFT and inverse FFT (IFFT) kernels. Compared to prior TFHE accelerators, OFHE addresses these challenges by improving the DTFHE operation latency by 8.7\%, the DTFHE operation throughput by $57\%$, and the DTFHE operation throughput per Watt by $94\%$.

Related papers

• BlockFFN: Towards End-Side Acceleration-Friendly Mixture-of-Experts with Chunk-Level Activation Sparsity [66.94629945519125]
  We introduce a novel MoE architecture, BlockFFN, as well as its efficient training and deployment techniques.<n>Specifically, we use a router integrating ReLU activation and RMSNorm for differentiable and flexible routing.<n>Next, to promote both token-level sparsity (TLS) and chunk-level sparsity ( CLS), CLS-aware training objectives are designed, making BlockFFN more acceleration-friendly.
  arXiv  Detail & Related papers  (2025-07-11T17:28:56Z)
• ABC-FHE : A Resource-Efficient Accelerator Enabling Bootstrappable Parameters for Client-Side Fully Homomorphic Encryption [0.8795040582681392]
  Homomorphic encryption (FHE) enables continuous computation on encrypted data.<n>Recent advancements in FHE accelerators have successfully improved server-side performance, but client-side computations remain a bottleneck.<n>We propose ABC-FHE, an area- and power-efficient FHE accelerator that supports bootstrappable parameters on the client side.
  arXiv  Detail & Related papers  (2025-06-10T05:37:31Z)
• PiT: Progressive Diffusion Transformer [50.46345527963736]
  We propose a series of Pseudo textbfProgressive Dtextbfiffusion textbfTransformer (textbfPiT)<n>Our proposed PiT-L achieves 54%$uparrow$ FID improvement over DiT-XL/2 while using less computation.
  arXiv  Detail & Related papers  (2025-05-19T15:02:33Z)
• GDNTT: an Area-Efficient Parallel NTT Accelerator Using Glitch-Driven Near-Memory Computing and Reconfigurable 10T SRAM [14.319119105134309]
  This paper proposes an area-efficient highly parallel NTT accelerator with glitch-driven near-memory computing (GDNTT)<n>The design integrates a 10T for data storage, enabling flexible row/column data access and streamlining circuit mapping strategies.<n> Evaluation results show that the proposed NTT accelerator achieves a 1.528* improvement in throughput-per-area compared to the state-of-the-art.
  arXiv  Detail & Related papers  (2025-05-13T01:53:07Z)
• VEXP: A Low-Cost RISC-V ISA Extension for Accelerated Softmax Computation in Transformers [13.984340807378457]
  Accelerating Softmax is challenging due to its non-pointwise, non-linear nature, with exponentiation as the most demanding step. We design a custom arithmetic block for Bfloat16 exponentiation leveraging a novel approximation algorithm based on Schraudolph's method. We execute Softmax with 162.7$times$ less latency and 74.3$times$ less energy compared to the baseline cluster.
  arXiv  Detail & Related papers  (2025-04-15T14:28:48Z)
• Task-Oriented Feature Compression for Multimodal Understanding via Device-Edge Co-Inference [49.77734021302196]
  We propose a task-oriented feature compression (TOFC) method for multimodal understanding in a device-edge co-inference framework. To enhance compression efficiency, multiple entropy models are adaptively selected based on the characteristics of the visual features. Results show that TOFC achieves up to 60% reduction in data transmission overhead and 50% reduction in system latency.
  arXiv  Detail & Related papers  (2025-03-17T08:37:22Z)
• TFHE-SBC: Software Designs for Fully Homomorphic Encryption over the Torus on Single Board Computers [0.0]
  homomorphic encryption (FHE) enables statistical processing and machine learning while protecting data. TFHE requires Torus Learning With Error (TLWE) encryption, which encrypts one bit at a time, leading to less efficient encryption and larger ciphertext size. We propose a novel SBC-specific design, textsfTFHE-SBC, to accelerate client-side TFHE operations and enhance communication and energy efficiency.
  arXiv  Detail & Related papers  (2025-03-04T12:36:58Z)
• Sliding Window Attention Training for Efficient Large Language Models [55.56483740523027]
  We introduce SWAT, which enables efficient long-context handling via Sliding Window Attention Training. This paper first attributes the inefficiency of Transformers to the attention sink phenomenon resulting from the high variance of softmax operation. Experiments demonstrate that SWAT achieves SOTA performance compared with state-of-the-art linear recurrent architectures on eight benchmarks.
  arXiv  Detail & Related papers  (2025-02-26T05:31:44Z)
• Accelerating Error Correction Code Transformers [56.75773430667148]
  We introduce a novel acceleration method for transformer-based decoders. We achieve a 90% compression ratio and reduce arithmetic operation energy consumption by at least 224 times on modern hardware.
  arXiv  Detail & Related papers  (2024-10-08T11:07:55Z)
• HF-NTT: Hazard-Free Dataflow Accelerator for Number Theoretic Transform [2.4578723416255754]
  Polynomial multiplication is one of the fundamental operations in many applications, such as fully homomorphic encryption (FHE) The Numberoretic Transform (NTT) has proven an effective tool in enhancing adaptable multiplication, but a fast method for generating NTT accelerators is lacking. In this paper, we introduce HF-NTT, a novel NTT accelerator, and introduce a data movement strategy that eliminates the need for bit-reversal operations.
  arXiv  Detail & Related papers  (2024-10-07T07:31:38Z)
• PEANO-ViT: Power-Efficient Approximations of Non-Linearities in Vision Transformers [4.523939613157408]
  Vision Transformers (ViTs) are designed for Field-Programmable Gate Arrays (FPGAs) ViTs' non-linear functions pose significant obstacles to efficient hardware implementation due to their complex mathematical operations. PEANO-ViT offers a novel approach to streamlining the implementation of the layer normalization layer.
  arXiv  Detail & Related papers  (2024-06-21T03:54:10Z)
• SWAT: Scalable and Efficient Window Attention-based Transformers Acceleration on FPGAs [3.302913401404089]
  Sliding window-based static sparse attention mitigates the problem by limiting the attention scope of the input tokens. We propose a dataflow-aware FPGA-based accelerator design, SWAT, that efficiently leverages the sparsity to achieve scalable performance for long input.
  arXiv  Detail & Related papers  (2024-05-27T10:25:08Z)
• Chain of Thought Empowers Transformers to Solve Inherently Serial Problems [57.58801785642868]
  Chain of thought (CoT) is a highly effective method to improve the accuracy of large language models (LLMs) on arithmetics and symbolic reasoning tasks. This work provides a theoretical understanding of the power of CoT for decoder-only transformers through the lens of expressiveness.
  arXiv  Detail & Related papers  (2024-02-20T10:11:03Z)
• From PEFT to DEFT: Parameter Efficient Finetuning for Reducing Activation Density in Transformers [52.199303258423306]
  We propose a novel density loss that encourages higher activation sparsity in pre-trained models. Our proposed method, textbfDEFT, can consistently reduce activation density by up to textbf44.94% on RoBERTa$_mathrmLarge$ and by textbf53.19% (encoder density) and textbf90.60% (decoder density) on Flan-T5$_mathrmXXL$.
  arXiv  Detail & Related papers  (2024-02-02T21:25:46Z)
• FHEmem: A Processing In-Memory Accelerator for Fully Homomorphic Encryption [9.884698447131374]
  Homomorphic Encryption (FHE) is a technique that allows arbitrary computations to be performed on encrypted data without the need for decryption. FHE is significantly slower than computation on plain data due to the increase in data size after encryption. We propose a PIM-based FHE accelerator, FHEmem, which exploits a novel processing in-memory architecture.
  arXiv  Detail & Related papers  (2023-11-27T20:11:38Z)
• AccelTran: A Sparsity-Aware Accelerator for Dynamic Inference with Transformers [6.0093441900032465]
  Self-attention-based transformer models have achieved tremendous success in the domain of natural language processing. Previous works directly operate on large matrices involved in the attention operation, which limits hardware utilization. We propose a novel dynamic inference scheme, DynaTran, which prunes activations at runtime with low overhead.
  arXiv  Detail & Related papers  (2023-02-28T16:17:23Z)
• HANT: Hardware-Aware Network Transformation [82.54824188745887]
  We propose hardware-aware network transformation (HANT) HANT replaces inefficient operations with more efficient alternatives using a neural architecture search like approach. Our results on accelerating the EfficientNet family show that HANT can accelerate them by up to 3.6x with 0.4% drop in the top-1 accuracy on the ImageNet dataset.
  arXiv  Detail & Related papers  (2021-07-12T18:46:34Z)
• Stable, Fast and Accurate: Kernelized Attention with Relative Positional Encoding [63.539333383965726]
  We propose a novel way to accelerate attention calculation for Transformers with relative positional encoding (RPE) Based upon the observation that relative positional encoding forms a Toeplitz matrix, we mathematically show that kernelized attention with RPE can be calculated efficiently using Fast Fourier Transform (FFT)
  arXiv  Detail & Related papers  (2021-06-23T17:51:26Z)
• DFTpy: An efficient and object-oriented platform for orbital-free DFT simulations [55.41644538483948]
  In this work, we present DFTpy, an open source software implementing OFDFT written entirely in Python 3. We showcase the electronic structure of a million-atom system of aluminum metal which was computed on a single CPU. DFTpy is released under the MIT license.
  arXiv  Detail & Related papers  (2020-02-07T19:07:41Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.