# PacQ: A SIMT Microarchitecture for Efficient Dataflow in Hyper-asymmetric GEMMs

arXiv: https://arxiv.org/abs/2502.18627 · HTML: https://mlsanity.com/paper/2502.18627/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 14 of its 24 references that are in the map.
- First posted on arXiv 25 Feb 2025.

## Builds on (most cited first, 14 of 14)

- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [OPT: Open Pre-trained Transformer Language Models](https://mlsanity.com/paper/2205.01068/) (2022)
- [GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers](https://mlsanity.com/paper/2210.17323/) (2022)
- [Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference](https://mlsanity.com/paper/1712.05877/) (2017)
- [SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models](https://mlsanity.com/paper/2211.10438/) (2022)
- [AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration](https://mlsanity.com/paper/2306.00978/) (2023)
- [BRECQ: Pushing the Limit of Post-Training Quantization by Block Reconstruction](https://mlsanity.com/paper/2102.05426/) (2021)
- [Atom: Low-bit Quantization for Efficient and Accurate LLM Serving](https://mlsanity.com/paper/2310.19102/) (2023)
- [BitNet: Scaling 1-bit Transformers for Large Language Models](https://mlsanity.com/paper/2310.11453/) (2023)
- [LUT-GEMM: Quantized Matrix Multiplication based on LUTs for Efficient Inference in Large-Scale Generative Language Models](https://mlsanity.com/paper/2206.09557/) (2022)
- [Who Says Elephants Can't Run: Bringing Large Scale MoE Models into Cloud Scale Production](https://mlsanity.com/paper/2211.10017/) (2022)
- [Modeling Deep Learning Accelerator Enabled GPUs](https://mlsanity.com/paper/1811.08309/) (2018)
- [TesseraQ: Ultra Low-Bit LLM Post-Training Quantization with Block Reconstruction](https://mlsanity.com/paper/2410.19103/) (2024)
- [High Throughput Matrix-Matrix Multiplication between Asymmetric Bit-Width Operands](https://mlsanity.com/paper/2008.00638/) (2020)

## Abstract (arXiv)

Weight-only quantization has been widely explored in large language models (LLMs) to reduce memory storage and data loading overhead. During deployment on single-instruction-multiple-threads (SIMT) architectures, weights are stored in low-precision integer (INT) format, while activations remain in full-precision floating-point (FP) format to preserve inference accuracy. Although memory footprint and data loading requirements for weight matrices are reduced, computation performance gains remain limited due to the need to convert weights back to FP format through unpacking and dequantization before GEMM operations. In this work, we investigate methods to accelerate GEMM operations involving packed low-precision INT weights and high-precision FP activations, defining this as the hyper-asymmetric GEMM problem. Our approach co-optimizes tile-level packing and dataflow strategies for INT weight matrices. We further design a specialized FP-INT multiplier unit tailored to our packing and dataflow strategies, enabling parallel processing of multiple INT weights. Finally, we integrate the packing, dataflow, and multiplier unit into PacQ, a SIMT microarchitecture designed to efficiently accelerate hyper-asymmetric GEMMs. We show that PacQ can achieve up to 1.99x speedup and 81.4% reduction in EDP compared to weight-only quantized LLM workloads running on conventional SIMT baselines.