# DECA: A Near-Core LLM Decompression Accelerator Grounded on a 3D Roofline Model

arXiv: https://arxiv.org/abs/2505.19349 · HTML: https://mlsanity.com/paper/2505.19349/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 32 of its 88 references that are in the map.
- First posted on arXiv 25 May 2025.

## Builds on (most cited first, 30 of 32)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [OPT: Open Pre-trained Transformer Language Models](https://mlsanity.com/paper/2205.01068/) (2022)
- [Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding](https://mlsanity.com/paper/1510.00149/) (2015)
- [SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot](https://mlsanity.com/paper/2301.00774/) (2023)
- [What is the State of Neural Network Pruning?](https://mlsanity.com/paper/2003.03033/) (2020)
- [Sparsity in Deep Learning: Pruning and growth for efficient inference and training in neural networks](https://mlsanity.com/paper/2102.00554/) (2021)
- [EIE: Efficient Inference Engine on Compressed Deep Neural Network](https://mlsanity.com/paper/1602.01528/) (2016)
- [Atom: Low-bit Quantization for Efficient and Accurate LLM Serving](https://mlsanity.com/paper/2310.19102/) (2023)
- [Pruning and Quantization for Deep Neural Network Acceleration: A Survey](https://mlsanity.com/paper/2101.09671/) (2021)
- [SpAtten: Efficient Sparse Attention Architecture with Cascade Token and Head Pruning](https://mlsanity.com/paper/2012.09852/) (2020)
- [TPU v4: An Optically Reconfigurable Supercomputer for Machine Learning with Hardware Support for Embeddings](https://mlsanity.com/paper/2304.01433/) (2023)
- [SCNN: An Accelerator for Compressed-sparse Convolutional Neural Networks](https://mlsanity.com/paper/1708.04485/) (2017)
- [Group Fisher Pruning for Practical Network Compression](https://mlsanity.com/paper/2108.00708/) (2021)
- [A3: Accelerating Attention Mechanisms in Neural Networks with Approximation](https://mlsanity.com/paper/2002.10941/) (2020)
- [Memory-Efficient Fine-Tuning of Compressed Large Language Models via sub-4-bit Integer Quantization](https://mlsanity.com/paper/2305.14152/) (2023)
- [NVIDIA Tensor Core Programmability, Performance & Precision](https://mlsanity.com/paper/1803.04014/) (2018)
- [Towards Greener LLMs: Bringing Energy-Efficiency to the Forefront of LLM Inference](https://mlsanity.com/paper/2403.20306/) (2024)
- [AC/DC: Alternating Compressed/DeCompressed Training of Deep Neural Networks](https://mlsanity.com/paper/2106.12379/) (2021)
- [SummIt: Iterative Text Summarization via ChatGPT](https://mlsanity.com/paper/2305.14835/) (2023)
- [Benchmarking and Dissecting the Nvidia Hopper GPU Architecture](https://mlsanity.com/paper/2402.13499/) (2024)
- [Effective Interplay between Sparsity and Quantization: From Theory to Practice](https://mlsanity.com/paper/2405.20935/) (2024)
- [Flash-LLM: Enabling Cost-Effective and Highly-Efficient Large Generative Model Inference with Unstructured Sparsity](https://mlsanity.com/paper/2309.10285/) (2023)
- [The ARM Scalable Vector Extension](https://mlsanity.com/paper/1803.06185/) (2018)
- [Tensor Processing Primitives: A Programming Abstraction for Efficiency and Portability in Deep Learning & HPC Workloads](https://mlsanity.com/paper/2104.05755/) (2021)
- [VEGETA: Vertically-Integrated Extensions for Sparse/Dense GEMM Tile Acceleration on CPUs](https://mlsanity.com/paper/2302.08687/) (2023)
- [HLAT: High-quality Large Language Model Pre-trained on AWS Trainium](https://mlsanity.com/paper/2404.10630/) (2024)
- [Harnessing Deep Learning and HPC Kernels via High-Level Loop and Tensor Abstractions on CPU Architectures](https://mlsanity.com/paper/2304.12576/) (2023)
- [MEGA: A Memory-Efficient GNN Accelerator Exploiting Degree-Aware Mixed-Precision Quantization](https://mlsanity.com/paper/2311.09775/) (2023)

## Built on by (most cited first, 2 of 2)

- [ZipServ: Fast and Memory-Efficient LLM Inference with Hardware-Aware Lossless Compression](https://mlsanity.com/paper/2603.17435/) (2026)
- [Cassandra: Enabling Reasoning LLMs at Edge via Self-Speculative Decoding](https://mlsanity.com/paper/2605.26558/) (2026)

## Abstract (arXiv)

To alleviate the memory bandwidth bottleneck in Large Language Model (LLM) inference workloads, weight matrices are stored in memory in quantized and sparsified formats. Hence, before tiles of these matrices can be processed by in-core generalized matrix multiplication (GeMM) hardware engines, they need to be dequantized and de-sparsified. This is currently performed in software with vector operations. Unfortunately, this approach delivers only modest performance. Moreover, it is hard to understand how to improve the system, as the overall GeMM performance depends on the interaction between memory resources, vector units, and hardware matrix engines. To improve the performance of LLM inference in advanced platforms equipped with in-core GeMM engines and HBM, this paper makes three main contributions. First, it develops an analytical performance model with a 3D visual representation that provides insights into how memory resources, vector units, and hardware matrix engines interact to deliver compressed GeMM performance. Second, it proposes DECA, a new near-core ML-model decompression accelerator. DECA offloads tile de-sparsification and dequantization from the CPU, producing ready-to-use tiles for in-core GeMM engines. Third, it introduces a new ISA extension that enables out-of-order invocation of the near-core accelerator. With this extension, accelerator and core computations can interleave and overlap with high-performance. Our evaluation shows that, in a simulated 56-core Xeon 4 server with HBM, DECA accelerates the execution of compressed GeMMs by up to 4x over the use of optimized Intel software kernels. Further, DECA reduces the next-token generation time of Llama2-70B and OPT-66B by 1.6x-2.6x.