BitFair: A 12nm Bit-Serial CNN Accelerator with Learnable Early Termination and Adaptive Bit Ordering for Ultra-Low-Power XR Vision

• URL: http://arxiv.org/abs/2607.05445v1
• Date: Sat, 04 Jul 2026 10:15:25 GMT
• Title: BitFair: A 12nm Bit-Serial CNN Accelerator with Learnable Early Termination and Adaptive Bit Ordering for Ultra-Low-Power XR Vision
• Abstract summary: BitFair is a bit-serial CNN accelerator with learnable bit-level early termination and adaptive bit ordering.<n>On IBM DVS128 Gesture and N-M, BitFair achieves 96.5% and 97.7% accuracy, respectively.
• Score: 9.413947161787124
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Extended Reality (XR) wearables require always-on perception within tight power envelopes of a few watts and motion-to-photon latency budgets below 20 ms, leaving only a few milliseconds for neural-network inference. Bit-serial computing is attractive for such energy-efficient neural network acceleration, but many existing architectures still process all bits even when ReLU sets the final output to zero. This paper presents BitFair, a software-hardware co-designed bit-serial CNN accelerator with learnable bit-level early termination and adaptive bit ordering, working under the ultra-low-power and strict latency requirements of XR applications. BitFair exploits dynamic bit-level sparsity by learning per-layer thresholds that trigger early termination when partial sums reliably predict that the final ReLU output will be zero. Furthermore, it searches for layer-wise bit orders that prioritize informative bits, maximizing early termination without sacrificing accuracy. A GlobalFoundries 12nm FinFET implementation with a core area of 0.34 mm^2, 104 KB on-chip memory, and voltage scaling from 0.55 to 0.70 V achieves sub-millisecond latency, up to 117.0 BTOPS/W, and 0.07 pJ/SOP. On IBM DVS128 Gesture and N-MNIST, BitFair achieves 96.5% and 97.7% accuracy, respectively, while improving effective energy efficiency by 4.0-22.1x and accuracy by up to 9.2% over prior fabricated XR vision accelerators.

Related papers

• E-ReCON: An Energy- and Resource-Efficient Precision-Configurable Sparse nvCIM Macro for Conventional and Spiking Neural Edge Inference [0.0]
  E-ReCON is a 16 Kb digital compute-in-memory (DCIM) macro based on a compact 3T1R ReRAM bitcell for edge-AI inference.<n>A novel interleaved 10T/28T adder tree is introduced, reducing transistor count and power consumption by 37% and 28%, respectively.<n>The proposed macro achieves a minimum latency of 0.48 ns, throughput of 2.31-3.1 TOPS, and energy efficiency of up to 419 TOPS/W.
  arXiv  Detail & Related papers  (2026-05-20T05:18:27Z)
• BWTA: Accurate and Efficient Binarized Transformer by Algorithm-Hardware Co-design [71.97035034203275]
  We analyze zero-point distortion in binarization and propose a Binary Weights & Ternary Activations (BWTA) quantization scheme.<n>For training, we propose Smooth Multi-Stage Quantization, combining a Levelwise Degradation Strategy and a MagnitudeAlignment Projection Factor.<n>Experiments show that BWTA approaches full-precision performance for Transformer-based models, with an average 3.5% drop on GLUE and less than 2% drop on five tasks.
  arXiv  Detail & Related papers  (2026-04-05T04:25:07Z)
• Enabling Vibration-Based Gesture Recognition on Everyday Furniture via Energy-Efficient FPGA Implementation of 1D Convolutional Networks [11.481972015296812]
  This study proposes an energy-efficient solution deploying compact NNs on low-power Field-Programmable Gate Arrays (FPGAs)<n>We replace complex spectral preprocessing with raw waveform input, eliminating complex on-board preprocessing while reducing input size by 21x without sacrificing accuracy.<n>We design two lightweight architectures (1D-CNN and 1D-SepCNN) tailored for embedded FPGAs, reducing parameters from 369 million to as few as 216 while maintaining comparable accuracy.
  arXiv  Detail & Related papers  (2025-10-27T09:30:36Z)
• Spark Transformer: Reactivating Sparsity in FFN and Attention [53.221448818147024]
  We introduce Spark Transformer, a novel architecture that achieves a high level of activation sparsity in both FFN and the attention mechanism.<n>This sparsity translates to a 2.5x reduction in FLOPs, leading to decoding wall-time speedups of up to 1.79x on CPU and 1.40x on GPU.
  arXiv  Detail & Related papers  (2025-06-07T03:51:13Z)
• TeLLMe: An Energy-Efficient Ternary LLM Accelerator for Prefilling and Decoding on Edge FPGAs [5.889337608109388]
  TeLLMe is the first ternary LLM accelerator for low-power FPGAs.<n>It supports both prefill and autoregressive decoding using 1.58-bit weights and 8-bit activations.<n>Under a 7W power budget, TeLLMe delivers up to 9 tokens/s throughput over 1,024-token contexts.
  arXiv  Detail & Related papers  (2025-04-22T21:00:58Z)
• Global Vision Transformer Pruning with Hessian-Aware Saliency [93.33895899995224]
  This work challenges the common design philosophy of the Vision Transformer (ViT) model with uniform dimension across all the stacked blocks in a model stage. We derive a novel Hessian-based structural pruning criteria comparable across all layers and structures, with latency-aware regularization for direct latency reduction. Performing iterative pruning on the DeiT-Base model leads to a new architecture family called NViT (Novel ViT), with a novel parameter that utilizes parameters more efficiently.
  arXiv  Detail & Related papers  (2021-10-10T18:04:59Z)
• BEANNA: A Binary-Enabled Architecture for Neural Network Acceleration [0.0]
  This paper proposes and evaluates a neural network hardware accelerator capable of processing both floating point and binary network layers. Running at a clock speed of 100MHz, BEANNA achieves a peak throughput of 52.8 GigaOps/second.
  arXiv  Detail & Related papers  (2021-08-04T23:17:34Z)
• Random and Adversarial Bit Error Robustness: Energy-Efficient and Secure DNN Accelerators [105.60654479548356]
  We show that a combination of robust fixed-point quantization, weight clipping, as well as random bit error training (RandBET) improves robustness against random or adversarial bit errors in quantized DNN weights significantly. This leads to high energy savings for low-voltage operation as well as low-precision quantization, but also improves security of DNN accelerators.
  arXiv  Detail & Related papers  (2021-04-16T19:11:14Z)
• FastFlowNet: A Lightweight Network for Fast Optical Flow Estimation [81.76975488010213]
  Dense optical flow estimation plays a key role in many robotic vision tasks. Current networks often occupy large number of parameters and require heavy computation costs. Our proposed FastFlowNet works in the well-known coarse-to-fine manner with following innovations.
  arXiv  Detail & Related papers  (2021-03-08T03:09:37Z)
• Sound Event Detection with Binary Neural Networks on Tightly Power-Constrained IoT Devices [20.349809458335532]
  Sound event detection (SED) is a hot topic in consumer and smart city applications. Existing approaches based on Deep Neural Networks are very effective, but highly demanding in terms of memory, power, and throughput. In this paper, we explore the combination of extreme quantization to a small-print binary neural network (BNN) with the highly energy-efficient, RISC-V-based (8+1)-core GAP8 microcontroller.
  arXiv  Detail & Related papers  (2021-01-12T12:38:23Z)
• EdgeBERT: Sentence-Level Energy Optimizations for Latency-Aware Multi-Task NLP Inference [82.1584439276834]
  Transformer-based language models such as BERT provide significant accuracy improvement for a multitude of natural language processing (NLP) tasks. We present EdgeBERT, an in-depth algorithm- hardware co-design for latency-aware energy optimization for multi-task NLP.
  arXiv  Detail & Related papers  (2020-11-28T19:21:47Z)
• BitPruning: Learning Bitlengths for Aggressive and Accurate Quantization [57.14179747713731]
  We introduce a training method for minimizing inference bitlength at any granularity while maintaining accuracy. With ImageNet, the method produces an average per layer bitlength of 4.13, 3.76 and 4.36 bits.
  arXiv  Detail & Related papers  (2020-02-08T04:58:33Z)

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.