LOgIQ: Log-Domain Optimization for Hardware-Efficient Inference and Quantization of Transformers
- 19 February 2026
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Very Large Scale Integration (VLSI) Systems
- Vol. 34 (4) , 1206-1216
Abstract
Quantization enables efficient large language model (LLM) inference by reducing memory and computation cost, but most existing methods sacrifice hardware simplicity through floating-point fallback, dequantization logic, or metadata routing. These overheads disrupt datapath regularity and limit gains in timing and area, especially in multiply-accumulate (MAC)-heavy transformer layers. We propose LogiMAC, a hardware-aligned quantization scheme that encodes weights in the log domain using shift-based arithmetic. LogiMAC embeds all decoding logic within the MAC unit, eliminates runtime scaling, and supports sublevel refinement without multipliers or look-up tables. The resulting datapath supports both shift directions with optional gating for unused paths. We evaluate LogiMAC across seven modern LLMs (ranging from 2B to 8B parameters) and compare it to strong baselines including SmoothQuant, GOBO, and SpinQuant. Our results show that while functional accuracy remains competitive, LogiMAC reduces area by $1.8\times $ and dynamic power by $5.9\times $ (in power-gated mode) compared to standard integer baselines. Timing analysis reveals over 50% of LogiMAC paths complete within just 12% of the normalized delay seen in other schemes. Validated over 34 million generated tokens, our findings demonstrate that accurate low-bit quantization can coexist with extreme hardware efficiency.Keywords
Funding Information
- National Science Foundation (CNS-2106237)
This publication has 11 references indexed in Scilit:
- HALO: Hardware-Aware Quantization with Low Critical-Path-Delay Weights for LLM AccelerationProceedings of the AAAI Conference on Artificial Intelligence, 2026
- AWQ: Activation-aware Weight Quantization for On-Device LLM Compression and AccelerationGetMobile: Mobile Computing and Communications, 2025
- FLQ: Design and implementation of hybrid multi-base full logarithmic quantization neural network acceleration architecture based on FPGASignal Processing: Image Communication, 2025
- Oltron: Algorithm-Hardware Co-design for Outlier-Aware Quantization of LLMs with Inter-/Intra-Layer Adaptation2024
- OliVe: Accelerating Large Language Models via Hardware-friendly Outlier-Victim Pair Quantization2023
- TruthfulQA: Measuring How Models Mimic Human Falsehoods2022
- GOBO: Quantizing Attention-Based NLP Models for Low Latency and Energy Efficient Inference2020
- Energy-Efficient Neural Network Accelerator Based on Outlier-Aware Low-Precision Computation2018
- In-Datacenter Performance Analysis of a Tensor Processing Unit2017
- The Sign/Logarithm Number SystemIEEE Transactions on Computers, 1975