Cover Image

XR-NPE: High-Throughput Mixed-precision SIMD Neural Processing Engine for Extended Reality Perception Workloads

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Chaudhari, Tejas, J., Akarsh, Dewangan, Tanushree, Lokhande, Mukul, Vishvakarma, Santosh Kumar
Format:	Preprint
Published:	2025
Subjects:	Hardware Architecture Artificial Intelligence Computer Vision and Pattern Recognition Image and Video Processing
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

QForce-RL: Quantized FPGA-Optimized Reinforcement Learning Compute Engine
by: Jha, Anushka, et al.
Published: (2025)

Flex-PE: Flexible and SIMD Multi-Precision Processing Element for AI Workloads
by: Lokhande, Mukul, et al.
Published: (2024)

L-SPINE: A Low-Precision SIMD Spiking Neural Compute Engine for Resource-efficient Edge Inference
by: Kumar, Sonu, et al.
Published: (2026)

Bhasha-Rupantarika: Algorithm-Hardware Co-design approach for Multilingual Neural Machine Translation
by: Lokhande, Mukul, et al.
Published: (2025)

Res-DPU: Resource-shared Digital Processing-in-memory Unit for Edge-AI Workloads
by: Lokhande, Mukul, et al.
Published: (2025)

CORVET: A CORDIC-Powered, Resource-Frugal Mixed-Precision Vector Processing Engine for High-Throughput AIoT applications
by: Kumar, Sonu, et al.
Published: (2026)

SPADE: A SIMD Posit-enabled compute engine for Accelerating DNN Efficiency
by: Kumar, Sonu, et al.
Published: (2026)

POLARON: Precision-aware On-device Learning and Adaptive Runtime-cONfigurable AI acceleration
by: Lokhande, Mukul, et al.
Published: (2025)

CARMEN: CORDIC-Accelerated Resource-Efficient Multi-Precision Inference Engine for Deep Learning
by: Kumar, Sonu, et al.
Published: (2026)

EULER-ADAS: Energy-Efficient & SIMD-Unified Logarithmic-Posit Engine for Precision-Reconfigurable Approximate ADAS Acceleration
by: Lokhande, Mukul, et al.
Published: (2026)

E-ReCON: An Energy- and Resource-Efficient Precision-Configurable Sparse nvCIM Macro for Conventional and Spiking Neural Edge Inference
by: Tenwar, Ankit Kumar, et al.
Published: (2026)

FERMI-ML: A Flexible and Resource-Efficient Memory-In-Situ SRAM Macro for TinyML acceleration
by: Lokhande, Mukul, et al.
Published: (2025)

TREA: Low-precision Time-Multiplexed, Resource-Efficient Edge Accelerator for Object Detection and Classification
by: Sharma, Vijay Pratap, et al.
Published: (2026)

CORDIC Is All You Need
by: Kokane, Omkar, et al.
Published: (2025)

HOAA: Hybrid Overestimating Approximate Adder for Enhanced Performance Processing Engine
by: Kokane, Omkar, et al.
Published: (2024)

ReLANCE: A Resource-Efficient Low-Latency Cortical Neural Acceleration Engine
by: Kumar, Sonu, et al.
Published: (2025)

RAMAN: Resource-efficient ApproxiMate Posit Processing for Algorithm-Hardware Co-desigN
by: Khan, Mohd Faisal, et al.
Published: (2025)

HYDRA: Hybrid Data Multiplexing and Run-time Layer Configurable DNN Accelerator
by: Kumar, Sonu, et al.
Published: (2024)

SRAM Based Digital Custom Compute Engine for Improved Area Efficiency of AI Hardware
by: Dhakad, Narendra Singh, et al.
Published: (2026)

Retrospective: A CORDIC Based Configurable Activation Function for NN Applications
by: Kokane, Omkar, et al.
Published: (2025)

Bio-RV: Low-Power Resource-Efficient RISC-V Processor for Biomedical Applications
by: Sharma, Vijay Pratap, et al.
Published: (2026)

DHFP-PE: Dual-Precision Hybrid Floating Point Processing Element for AI Acceleration
by: Kumar, Shubham, et al.
Published: (2026)

ADS-IMC: Accelerating Data Sorting with In-Memory Computation
by: Dhakad, Narendra Singh, et al.
Published: (2026)

Configurable Multi-Port Memory Architecture for High-Speed Data Communication
by: Dhakad, Narendra Singh, et al.
Published: (2024)

Mixed-precision Neural Networks on RISC-V Cores: ISA extensions for Multi-Pumped Soft SIMD Operations
by: Armeniakos, Giorgos, et al.
Published: (2024)

Architectural Classification of XR Workloads: Cross-Layer Archetypes and Implications
by: Shi, Xinyu, et al.
Published: (2026)

Siracusa: A 16 nm Heterogenous RISC-V SoC for Extended Reality with At-MRAM Neural Engine
by: Prasad, Arpan Suravi, et al.
Published: (2023)

An Efficient Architecture and High-Throughput Implementation of CCSDS-123.0-B-2 Hybrid Entropy Coder Targeting Space-Grade SRAM FPGA Technology
by: Chatziantoniou, Panagiotis, et al.
Published: (2022)

NVM-in-Cache: Repurposing Commodity 6T SRAM Cache into NVM Analog Processing-in-Memory Engine using a Novel Compute-on-Powerline Scheme
by: Chakraborty, Subhradip, et al.
Published: (2025)

Modeling the Energy Consumption of the HEVC Software Encoding Process using Processor events
by: Ramasubbu, Geetha, et al.
Published: (2024)

Technology-Circuit-Algorithm Tri-Design for Processing-in-Pixel-in-Memory (P2M)
by: Kaiser, Md Abdullah-Al, et al.
Published: (2023)

An Energy-Efficient RFET-Based Stochastic Computing Neural Network Accelerator
by: Lu, Sheng, et al.
Published: (2025)

Voltage-Controlled Magnetic Tunnel Junction based ADC-less Global Shutter Processing-in-Pixel for Extreme-Edge Intelligence
by: Kaiser, Md Abdullah-Al, et al.
Published: (2024)

Systolic Array Data Flows for Efficient Matrix Multiplication in Deep Neural Networks
by: Raja, Tejas
Published: (2024)

FireFly-T: High-Throughput Sparsity Exploitation for Spiking Transformer Acceleration with Dual-Engine Overlay Architecture
by: Li, Tenglong, et al.
Published: (2025)

Allspark: Workload Orchestration for Visual Transformers on Processing In-Memory Systems
by: Ge, Mengke, et al.
Published: (2024)

Sub-Millisecond Event-Based Eye Tracking on a Resource-Constrained Microcontroller
by: Giordano, Marco, et al.
Published: (2025)

Pack my weights and run! Minimizing overheads for in-memory computing accelerators
by: Houshmand, Pouya, et al.
Published: (2024)

FPCA: Field-Programmable Pixel Convolutional Array for Extreme-Edge Intelligence
by: Yin, Zihan, et al.
Published: (2024)

FSL-HDnn: A 40 nm Few-shot On-Device Learning Accelerator with Integrated Feature Extraction and Hyperdimensional Computing
by: Xu, Weihong, et al.
Published: (2025)