Scalable Multi-FPGA HPC Architecture for Associative Memory System.

Associative memory is a cornerstone of cognitive intelligence within the human brain. The Bayesian confidence propagation neural network (BCPNN), a cortex-inspired model with high biological plausibility, has proven effective in emulating high-level cognitive functions like associative memory. However, the current approach using GPUs to simulate BCPNN-based associative memory tasks encounters challenges in latency and power efficiency as the model size scales. This work proposes a scalable multi-FPGA high performance computing (HPC) architecture designed for the associative memory system. The architecture integrates a set of hypercolumn unit (HCU) computing cores for intra-board online learning and inference, along with a spike-based synchronization scheme for inter-board communication among multiple FPGAs. Several design strategies, including population-based model mapping, packet-based spike synchronization, and cluster-based timing optimization, are presented to facilitate the multi-FPGA implementation. The architecture is implemented and validated on two Xilinx Alveo U50 FPGA cards, achieving a maximum model size of 200×10 and a peak working frequency of 220 MHz for the associative memory system. Both the memory-bounded spatial scalability and compute-bounded temporal scalability of the architecture are evaluated and optimized, achieving a maximum scale-latency ratio (SLR) of 268.82 for the two-FPGA implementation. Compared to a two-GPU counterpart, the two-FPGA approach demonstrates a maximum latency reduction of 51.72× and a power reduction exceeding 5.28× under the same network configuration. Compared with the state-of-the-art works, the two-FPGA implementation exhibits a high pattern storage capacity for the associative memory task.

Sensitive subcellular scale and real-time detection of hydrogen peroxide by a W-doped Pt microelectrode.

A W-doped Pt modified graphene oxide (Pt-W-GO) electrochemical microelectrode was developed to detect hydrogen peroxide (H2O2) in real time at a subcellular scale. Interestingly, results showed that the concentration of H2O2 in the nucleus of HeLa cells was 2.68 times and 0.51 times that in the extracellular membrane and cytoplasm, respectively.

Co4+ in porous ZIF-67-derives intercalating-bridging adsorption of 2-reaction sites for simultaneous 2-electron transfer toward sensitive detection of uric acid.

Metal-organic frameworks (MOFs) have been used to detect uric acid (UA), but still very challenging to achieve a low detection limit due to the low inferior conductivity of MOFs. Herein, three different N-doped ZIF-67-derived carbons were synthesized for the first time by one-step co-pyrolysis of 2-methylimidazole with cobalt nitrate (CN), cobalt acetate (CA) or cobalt chloride (CC) toward UA sensing. Afterwards, the cobalt nitrate-derived Co particle (Co/CN) supported by N-doped ZIF-67-derived carbon displays extremely low detection limit and high sensitivity for UA, outperformed all reported MOFs-based UA sensors. More interestingly, it was discovered that the high valence Co4+ within the Co/CN sample produced in high-acidic environment can intercalate in the frame for a bridge adsorption between two reaction sites, which boosted simultaneous 2-electron transfer, while Co3+ only allows an end-adsorption structure for one-electron transfer being the rate determining step. Furthermore, the bridge adsorption mode of UA on Co4+ -based catalyst was also verified by theoretical DFT calculations and XPS experiment. This work holds great promise for a selective and sensitive UA sensor for practical bioscience and clinic diagnostic applications while shedding lights in fundamental research for innovative designs and developments of high-sensitive electrochemical sensors.

CircPKN2 promotes ferroptosis in bladder cancer by promoting the ubiquitination of Stearoyl-CoA Desaturase 1.

Bladder cancer (BC) is one of the most common malignancies in the male urinary system and currently lacks an optimal treatment strategy. To elucidate the pathogenic mechanisms of BC from the perspective of circular RNAs, we conducted this study. Building upon our previous research, a novel circRNA, circPKN2, captured our interest due to its significant downregulation in BC, and its close association with the prognosis of BC patients. Our research findings indicate that circPKN2 can inhibit the proliferation and migration of BC cells in vitro. Furthermore, we discovered that circPKN2 exerts its anti-cancer effects in BC by promoting ferroptosis. Mechanistic studies revealed that circPKN2 recruits STUB1 to facilitate the ubiquitination of SCD1, thereby suppressing the WNT pathway and promoting ferroptosis in BC. Additionally, our research unveiled the regulatory role of the splicing factor QKI in the biogenesis of circPKN2. Animal studies demonstrated that circPKN2 enhances ferroptosis in BC cells in vivo, inhibiting tumor growth and metastasis. The discovery of the anti-cancer factor circPKN2 holds promise for providing new therapeutic targets in the prevention and treatment of BC.

A Reconfigurable Near-Sensor Processor for Anomaly Detection in Limb Prostheses.

This paper presents a reconfigurable near-sensor anomaly detection processor to real-time monitor the potential anomalous behaviors of amputees with limb prostheses. The processor is low-power, low-latency, and suitable for equipment on the prostheses and comprises a reconfigurable Variational Autoencoder (VAE), a scalable Self-Organizing Map (SOM) Array, and a window-size-adjustable Markov Chain, which can implement an integrated miniaturized anomaly detection system. With the reconfigurable VAE, the proposed processor can support up to 64 sensor sampling channels programmable by global configuration, which can meet the anomaly detection requirements in different scenarios. A scalable SOM array allows for the selection of different sizes based on the complexity of the data. Unlike traditional time accumulation-based anomaly detection methods, the Markov Chain is utilized to detect time-series-based anomalous data. The processor is designed and fabricated in a UMC 40-nm LP technology with a core area of 1.49 mm2 and a power consumption of 1.81 mW. It achieves real-time detection performance with 0.933 average F1 Score for the FSP dataset within 24.22 µs, and 0.956 average F1 Score for the SFDLA-12 dataset within 30.48 µs, respectively. The energy dissipation of detection for each input feature is 43.84 nJ with the FSP dataset, and 55.17 nJ with the SFDLA-12 dataset. Compared with ARM Cortex-M4 and ARM Cortex-M33 microcontrollers, the processor achieves energy and area efficiency improvements ranging from 257×, 193× and 11×, 8×, respectively.