Program processors

  • No Comments

A Nonvolatile AI-Edge Processor With Lossless-Compressed-Computing STT-MRAM Near-Memory-Compute Macro Using Dynamic Floating-/Fixed-Point Accumulation

A Nonvolatile AI-Edge Processor With Lossless-Compressed-Computing STT-MRAM Near-Memory-Compute Macro Using Dynamic Floating-/Fixed-Point Accumulation 150 150
Author(s): De-Qi You, Win-San Khwa, Bo Zhang, Jui-Jen Wu, Chuan-Jia Jhang, Guan-Yi Lin, Po-Jung Chen, Ting-Chien Chiu, Fang-Yi Chen, Andrew Lee, Yu-Cheng Hung, Chung-Chuan Lo, Ren-Shuo Liu, Chih-Cheng Hsieh, Kea-Tiong Tang, Yu-Der Chih, Tsung-Yung Jonathan Chang, Meng-Fan Chang

Abstract:

Nonvolatile AI-edge processors based on near-memory-compute (nvNMC) enable energy-efficient multiply-and-accumulate (MAC) operations with short wakeup latency for edge inference operations. Lossless compression is required for floating-point (FP) neural network (NN) models under on-chip memory capacity constraints; however, this imposes several challenges: 1) data decompression overhead due to lossless FP weight encoding; 2) …

Published in: IEEE Journal of Solid-State Circuits
Page(s): 1 – 13
Year of Publication: 2026
Electronic ISSN: 1558-173X
DOI: 10.1109/JSSC.2026.3705432
Publisher: IEEE

View on IEEE Xplore

  • No Comments

ASAP: A 28-nm Transformer Training Accelerator With Alternating Sparsity and Asymmetrical Microscaling Precision

ASAP: A 28-nm Transformer Training Accelerator With Alternating Sparsity and Asymmetrical Microscaling Precision 150 150
Author(s): HanGyeol Mun, Jian Meng, Xiaofeng Hu, Yuan Liao, Chun-Ting Chen, Jae-sun Seo

Abstract:

This work presents ASAP, a 28-nm transformer-training accelerator that combines N:M structured sparsity with asymmetric microscaling floating-point (MXFP) precision through a unified algorithm–hardware co-design. ASAP introduces a progressive sparsity schedule in which pruned compute resources are reassigned to increase numerical precision for important weights and activations, stabilizing optimization …

Published in: IEEE Journal of Solid-State Circuits
Page(s): 1 – 14
Year of Publication: 2026
Electronic ISSN: 1558-173X
DOI: 10.1109/JSSC.2026.3693653
Publisher: IEEE

View on IEEE Xplore

  • No Comments

A 54- $\\mu$ W Design-Agnostic Clock, Voltage, and EM-Pulse Fault-Injection Attack Detection Using Time-to-Voltage Conversion

A 54- $\\mu$ W Design-Agnostic Clock, Voltage, and EM-Pulse Fault-Injection Attack Detection Using Time-to-Voltage Conversion 150 150
Author(s): Yudhajit Ray, Archisman Ghosh, Sarthak Antal, Shreyas Sen

Abstract:

This article presents a state-of-the-art design-agnostic clock, voltage, and electromagnetic pulse (EMP)-based fault-injection attack (FIA) detector. The efficient conversion of time-to-voltage information by integrating amplifiers transforms the time anomaly into the voltage domain, enabling its detection at a lower power consumption. The clock-glitch detector design consumes only $53~\mu $ W …

Published in: IEEE Journal of Solid-State Circuits
Page(s): 1 – 13
Year of Publication: 2026
Electronic ISSN: 1558-173X
DOI: 10.1109/JSSC.2026.3655593
Publisher: IEEE

View on IEEE Xplore

  • No Comments

SparseCol: A 1320 BTOPS/W Precision-Scalable NPU Exploiting Training-Free Structured Bit-Level Sparsity and Dynamic Dataflow

SparseCol: A 1320 BTOPS/W Precision-Scalable NPU Exploiting Training-Free Structured Bit-Level Sparsity and Dynamic Dataflow 150 150
Author(s): Man Shi, Vikram Jain, Weijie Jiang, Chao Fang, Antony Joseph, Wim Dehaene, Marian Verhelst

Abstract:

Bit-serial computation enables sequential processing of data at the bit level, providing several advantages, such as scalable computational precision. This approach has gained significant attention, especially for exploiting bit-level sparsity (BLS) in AI workloads. While current bit-serial processors leverage BLS to eliminate the computation associated with zero bits, they face …

Published in: IEEE Journal of Solid-State Circuits
Page(s): 1 – 14
Year of Publication: 2025
Electronic ISSN: 1558-173X
DOI: 10.1109/JSSC.2025.3636451
Publisher: IEEE

View on IEEE Xplore

  • No Comments

AACIM: A 2785-TOPS/W, 161-TOP/mm2, <1.17%-RMSE, Analog-In Analog-Out Computing-In-Memory Macro in 28 nm

AACIM: A 2785-TOPS/W, 161-TOP/mm2, <1.17%-RMSE, Analog-In Analog-Out Computing-In-Memory Macro in 28 nm 150 150
Author(s): Rentao Wan, Chuan-Tung Lin, Bo Zhang, Yannis Tsividis, Mingoo Seok

Abstract:

This article presents an analog-in analog-out CIM macro (AACIM) for use in analog deep neural network (DNN) processors. Our macro receives analog inputs, performs a 64-by-32 vector–matrix multiplication (VMM) with a current-discharging computation mechanism, and produces analog outputs. It stores a 4-bit weight as an analog voltage in the …

Published in: IEEE Journal of Solid-State Circuits
Page(s): 1 – 11
Year of Publication: 2025
Electronic ISSN: 1558-173X
DOI: 10.1109/JSSC.2025.3622309
Publisher: IEEE

View on IEEE Xplore

Search this website