10 June 2025 in IEEE Access
This paper proposes a novel Fast Fourier Transform hardware architecture for natural-order multi-input multi-output processing, which is based on approximate computing and the block floating-point data format. The architecture innovatively combines the low-power characteristics of approximate multipliers with the high-precision advantages of block floating-point data formats, enabling efficient processing of 2048-point and 4096-point Fast Fourier Transform data. By employing conflict-free memory access techniques, the design optimizes data scheduling, reduces idle cycles during processing, and significantly enhances energy efficiency while maintaining computational accuracy. Experimental validation demonstrates that the processor, fabricated using a 40nm process, achieves a compact chip area of 0.42 mm². Operating at a frequency of 671.14 MHz, it delivers a throughput of 1073.82 MS/s for 4096-point FFT computations, with a power consumption of only 110.85 mW and a signal-quantization-to-noise ratio of 58.51 dB. Compared to state-of-the-art designs, this architecture achieves breakthrough improvements in throughput performance while maintaining competitive energy efficiency.
26 May 2026 in Neurocomputing
8 May 2026 in IEEE Transactions on Circuits and Systems I: Regular Papers
The energy efficiency of object detection processors based on traditional artificial neural networks (ANNs) is constrained by intensive multiply-accumulate operations and frequent memory accesses. Spiking neural networks (SNNs), characterized by biological plausibility, multiplier-free computation, and inherent sparsity, offer a promising alternative for energy-efficient inference. However, deploying SNNs for high-resolution object detection faces three key challenges: 1) long time-steps to maintain accuracy; 2) redundant weight access across time-steps; and 3) substantial external memory access (EMA) incurred by intermediate feature maps (FM). To address the above challenges, a dedicated SNN processor is presented with three contributions: 1) a customized short time-step quantized spiking YOLO (QS-YOLO) model, achieving 65.80-72.90% mAP on VOC2007 within only 1–4 time-steps through a progressive temporal compression (PTC) and quantization framework; 2) a novel weight-locally-distributed stationary spatio-temporal sequential interleaving (WLS-STS) dataflow, enabling single weight access across all time-steps while supporting flexible time-step configuration without loss of processing element (PE) utilization; and 3) a workload-aware dynamic global buffer allocation strategy to eliminate FM-EMA. The proposed processor incorporates a heterogeneous dual-core architecture, comprising a spike-driven accumulate unit (SAU) and a multiply–accumulate unit (MAU), to efficiently accelerate both spiking and non-spiking operators in QS-YOLO. Implemented on XCVU13P FPGA, the processor achieves a peak energy efficiency of 146.48 GOPS/W at 100MHz. Compared with existing object detection FPGA processors, the proposed processor achieves state-of-the-art energy efficiency.
12 January 2026 in IEEE Solid-State Circuits Letters
This paper presents an approximate digital compute-in-memory (CIM) macro for low-power edge AI inference. It introduces three hierarchical innovations: 1) novel fused approximate multiply-add units (FAMUs) that reduces power and area consumption; 2) a bit-critical weight allocation architecture that optimally balances accuracy and hardware cost; and 3) a dynamic sparsity-adaptive configuration method to minimize accuracy loss in real-time. The macro achieves an energy efficiency of 60.35 TOPS/W and an area efficiency of 1105 GOPS/mm for INT8 MACs, outperforming prior works. It attains negligible accuracy degradation on multiple mainstream datasets and suits well for edge AI inference.
1 January 2026 in IEEE Transactions on Computers