# Algorithm-Hardware Co-Design of Distribution-Aware Logarithmic-Posit Encodings for Efficient DNN Inference

arXiv: https://arxiv.org/abs/2403.05465 · HTML: https://mlsanity.com/paper/2403.05465/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 20 references that are in the map.
- First posted on arXiv 8 Mar 2024.

## Builds on (most cited first, 8 of 8)

- [BRECQ: Pushing the Limit of Post-Training Quantization by Block Reconstruction](https://mlsanity.com/paper/2102.05426/) (2021)
- [FQ-ViT: Post-Training Quantization for Fully Quantized Vision Transformer](https://mlsanity.com/paper/2111.13824/) (2021)
- [Bit Fusion: Bit-Level Dynamically Composable Architecture for Accelerating Deep Neural Networks](https://mlsanity.com/paper/1712.01507/) (2017)
- [ANT: Exploiting Adaptive Numerical Data Type for Low-bit Deep Neural Network Quantization](https://mlsanity.com/paper/2208.14286/) (2022)
- [DeepScaleTool : A Tool for the Accurate Estimation of Technology Scaling in the Deep-Submicron Era](https://mlsanity.com/paper/2102.10195/) (2021)
- [Rethinking floating point for deep learning](https://mlsanity.com/paper/1811.01721/) (2018)
- [EMQ: Evolving Training-free Proxies for Automated Mixed Precision Quantization](https://mlsanity.com/paper/2307.10554/) (2023)
- [Cheetah: Mixed Low-Precision Hardware & Software Co-Design Framework for DNNs on the Edge](https://mlsanity.com/paper/1908.02386/) (2019)

## Built on by (most cited first, 7 of 7)

- [MicroScopiQ: Accelerating Foundational Models through Outlier-Aware Microscaling Quantization](https://mlsanity.com/paper/2411.05282/) (2024)
- [CLAMP-ViT: Contrastive Data-Free Learning for Adaptive Post-Training Quantization of ViTs](https://mlsanity.com/paper/2407.05266/) (2024)
- [M-ANT: Efficient Low-bit Group Quantization for LLMs via Mathematically Adaptive Numerical Type](https://mlsanity.com/paper/2502.18755/) (2025)
- [Towards Efficient Neuro-Symbolic AI: From Workload Characterization to Hardware Architecture](https://mlsanity.com/paper/2409.13153/) (2024)
- [OuroMamba: A Data-Free Quantization Framework for Vision Mamba](https://mlsanity.com/paper/2503.10959/) (2025)
- [Accelerating LLM Inference with Flexible N:M Sparsity via A Fully Digital Compute-in-Memory Accelerator](https://mlsanity.com/paper/2504.14365/) (2025)
- [AIRCHITECT v2: Learning the Hardware Accelerator Design Space through Unified Representations](https://mlsanity.com/paper/2501.09954/) (2025)

## Abstract (arXiv)

Traditional Deep Neural Network (DNN) quantization methods using integer, fixed-point, or floating-point data types struggle to capture diverse DNN parameter distributions at low precision, and often require large silicon overhead and intensive quantization-aware training. In this study, we introduce Logarithmic Posits (LP), an adaptive, hardware-friendly data type inspired by posits that dynamically adapts to DNN weight/activation distributions by parameterizing LP bit fields. We also develop a novel genetic-algorithm based framework, LP Quantization (LPQ), to find optimal layer-wise LP parameters while reducing representational divergence between quantized and full-precision models through a novel global-local contrastive objective. Additionally, we design a unified mixed-precision LP accelerator (LPA) architecture comprising of processing elements (PEs) incorporating LP in the computational datapath. Our algorithm-hardware co-design demonstrates on average <1% drop in top-1 accuracy across various CNN and ViT models. It also achieves ~ 2x improvements in performance per unit area and 2.2x gains in energy efficiency compared to state-of-the-art quantization accelerators using different data types.