EULER-ADAS: Energy-Efficient & SIMD-Unified Logarithmic-Posit Engine for Precision-Reconfigurable Approximate ADAS Acceleration

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Lokhande, Mukul, Pilipovic, Ratko, Kokane, Omkar, Teman, Adam, Vishvakarma, Santosh Kumar
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866911660791300096
author Lokhande, Mukul
Pilipovic, Ratko
Kokane, Omkar
Teman, Adam
Vishvakarma, Santosh Kumar
author_facet Lokhande, Mukul
Pilipovic, Ratko
Kokane, Omkar
Teman, Adam
Vishvakarma, Santosh Kumar
contents Advanced driver-assistance systems (ADAS) require neural compute engines that deliver low-latency inference under strict power and area constraints. Posit arithmetic is attractive for such accelerators because it provides high numerical fidelity at low precision, but its variable-length regime encoding increases encode/decode cost and exposes the datapath to large regime-field fault effects. This paper presents EULER-ADAS, a SIMD-enabled logarithmic bounded-Posit neural compute engine for energyefficient and reliability-aware ADAS acceleration. The proposed datapath combines bounded-regime Posit representation, stageadaptive logarithmic mantissa multiplication with bit truncation, and a SIMD-shared quire accumulation path supporting Posit- (8,0), Posit-(16,1), and Posit-(32,2) execution. The unified architecture enables 4xPosit-8, 2xPosit-16, or 1xPosit-32 operation without duplicating precision-specific hardware. FPGA implementation shows that the proposed configurations reduce LUT count by up to 41.4%, delay by up to 76.1%, and power by up to 71.9% relative to exact Posit neural compute engines, while achieving up to 10x lower energy-delay product than radix-4 Booth-based Posit multipliers. In 28-nm CMOS, the bounded variants occupy 0.013-0.016 mm2 , consume 19.8-22.1 mW, and operate at up to 1.84 GHz. Application-level evaluation across image-classification, ADAS, and edge-inference workloads shows that the evaluated Posit-16 and Posit-32 configurations remain within about 1.5 percentage points of FP32 accuracy. A TinyYOLOv3 prototype on Pynq-Z2 achieves 78 ms latency at 0.29 W and 22.6 mJ/frame, demonstrating the suitability of EULERADAS for low-power real-time ADAS inference.
format Preprint
id arxiv_https___arxiv_org_abs_2605_06875
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle EULER-ADAS: Energy-Efficient & SIMD-Unified Logarithmic-Posit Engine for Precision-Reconfigurable Approximate ADAS Acceleration
Lokhande, Mukul
Pilipovic, Ratko
Kokane, Omkar
Teman, Adam
Vishvakarma, Santosh Kumar
Hardware Architecture
Artificial Intelligence
Computer Vision and Pattern Recognition
Numerical Analysis
Image and Video Processing
Advanced driver-assistance systems (ADAS) require neural compute engines that deliver low-latency inference under strict power and area constraints. Posit arithmetic is attractive for such accelerators because it provides high numerical fidelity at low precision, but its variable-length regime encoding increases encode/decode cost and exposes the datapath to large regime-field fault effects. This paper presents EULER-ADAS, a SIMD-enabled logarithmic bounded-Posit neural compute engine for energyefficient and reliability-aware ADAS acceleration. The proposed datapath combines bounded-regime Posit representation, stageadaptive logarithmic mantissa multiplication with bit truncation, and a SIMD-shared quire accumulation path supporting Posit- (8,0), Posit-(16,1), and Posit-(32,2) execution. The unified architecture enables 4xPosit-8, 2xPosit-16, or 1xPosit-32 operation without duplicating precision-specific hardware. FPGA implementation shows that the proposed configurations reduce LUT count by up to 41.4%, delay by up to 76.1%, and power by up to 71.9% relative to exact Posit neural compute engines, while achieving up to 10x lower energy-delay product than radix-4 Booth-based Posit multipliers. In 28-nm CMOS, the bounded variants occupy 0.013-0.016 mm2 , consume 19.8-22.1 mW, and operate at up to 1.84 GHz. Application-level evaluation across image-classification, ADAS, and edge-inference workloads shows that the evaluated Posit-16 and Posit-32 configurations remain within about 1.5 percentage points of FP32 accuracy. A TinyYOLOv3 prototype on Pynq-Z2 achieves 78 ms latency at 0.29 W and 22.6 mJ/frame, demonstrating the suitability of EULERADAS for low-power real-time ADAS inference.
title EULER-ADAS: Energy-Efficient & SIMD-Unified Logarithmic-Posit Engine for Precision-Reconfigurable Approximate ADAS Acceleration
topic Hardware Architecture
Artificial Intelligence
Computer Vision and Pattern Recognition
Numerical Analysis
Image and Video Processing
url https://arxiv.org/abs/2605.06875