SparseDitto: Customizing GPU Kernels for Different Sparsity Patterns with LLM-Based Agentic System

• URL: http://arxiv.org/abs/2608.05033v2
• Date: Wed, 12 Aug 2026 18:52:15 GMT
• Title: SparseDitto: Customizing GPU Kernels for Different Sparsity Patterns with LLM-Based Agentic System
• Abstract summary: We present SparseDitto, an LLM-based system that constructs a GPU kernel for each matrix, operator, and target GPU.<n>SparseDitto supports SpMV, SpMM, and SpGEMM within a unified design framework.<n>Its generated SpMM kernels also accelerate full-batch GCN training by up to 3.39x.
• Score: 45.52961410486319
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Sparse matrix kernels are fundamental to scientific computing, graph analytics, and machine learning. Their GPU performance depends strongly on the input sparsity pattern and execution strategy. For the same SpMM on the same matrix, cuSPARSE exhibits a 350x performance gap between CSR and Blocked-ELL. Our study of multiple data formats, specialized systems, and sparse compilers shows that no single implementation consistently dominates across sparsity patterns and operators. This motivates a system that can adapt its representation, execution strategy, and hardware mapping to each workload and target GPU. We present SparseDitto, an LLM-based system that constructs a GPU kernel for each matrix, operator, and target GPU. SparseDitto supports SpMV, SpMM, and SpGEMM within a unified design framework. A lightweight additive model ranks established strategies using structural features of the input matrix. An architecture-aware planner then proposes several candidate designs. Coding and verification agents implement and refine them using measurements from the target GPU. Across three sparse operators and a diverse set of matrices, SparseDitto achieves a geometric-mean speedup of 2.68x over cuSPARSE on an NVIDIA RTX PRO 6000 GPU, with a maximum of 146.61x. On an NVIDIA H200 GPU, it achieves 2.79x, with a maximum of 78.5x. Its generated SpMM kernels also accelerate full-batch GCN training by up to 3.39x.

Related papers

• GPUSparse: GPU-Accelerated Learned Sparse Retrieval with Parallel Inverted Indices [3.3723515662362265]
  We present GPUSparse, a system for GPU-accelerated exact learned sparse retrieval.<n>A GPU-parallel inverted index with block-aligned, warp-coalesced posting lists is used.<n>Batched scatter-add scoring algorithm processes hundreds of queries simultaneously.
  arXiv  Detail & Related papers  (2026-06-24T23:07:57Z)
• Accelerating GPU Inference of Large Language Models with Moderately Unstructured Sparse Weight Matrices [18.428868416628017]
  This paper proposes an efficient inference method for large language models (LLMs) with moderate sparsity.<n>It achieves up to 1.64x-level speedup over SpInfer and up to 1.41x end-to-end speedups over FlashLLM.
  arXiv  Detail & Related papers  (2026-06-13T13:38:27Z)
• Libra: Synergizing CUDA and Tensor Cores for High-Performance Sparse Matrix Multiplication [6.557224606759151]
  Modern accelerators are commonly equipped with cores and cores to accelerate sparse operators.<n>We show that utilizing one resource alone leads to inferior performance for sparse matrix multiplication, due to their respective limitations.<n>We propose a 2D-aware workload computation strategy find out the sweet point of task mapping operators, leveraging both the high performance of 2.9 cores and the low redundancy on cores.
  arXiv  Detail & Related papers  (2025-06-28T01:50:13Z)
• NGPU-LM: GPU-Accelerated N-Gram Language Model for Context-Biasing in Greedy ASR Decoding [54.88765757043535]
  This work rethinks data structures for statistical n-gram language models to enable fast and parallel operations for GPU-optimized inference.<n>Our approach, named NGPU-LM, introduces customizable greedy decoding for all major ASR model types with less than 7% computational overhead.<n>The proposed approach can eliminate more than 50% of the accuracy gap between greedy and beam search for out-of-domain scenarios while avoiding significant slowdown caused by beam search.
  arXiv  Detail & Related papers  (2025-05-28T20:43:10Z)
• TorchSparse++: Efficient Training and Inference Framework for Sparse Convolution on GPUs [20.4238781638402]
  Sparse convolution plays a pivotal role in emerging workloads, including point cloud processing in AR/VR, autonomous driving, and graph understanding in recommendation systems. Existing GPU libraries offer two dataflow types for sparse convolution. We introduce TorchSparse++, a new GPU library that achieves the best of both worlds.
  arXiv  Detail & Related papers  (2023-10-25T21:02:38Z)
• INR-Arch: A Dataflow Architecture and Compiler for Arbitrary-Order Gradient Computations in Implicit Neural Representation Processing [66.00729477511219]
  Given a function represented as a computation graph, traditional architectures face challenges in efficiently computing its nth-order gradient. We introduce INR-Arch, a framework that transforms the computation graph of an nth-order gradient into a hardware-optimized dataflow architecture. We present results that demonstrate 1.8-4.8x and 1.5-3.6x speedup compared to CPU and GPU baselines respectively.
  arXiv  Detail & Related papers  (2023-08-11T04:24:39Z)
• Batch-efficient EigenDecomposition for Small and Medium Matrices [65.67315418971688]
  EigenDecomposition (ED) is at the heart of many computer vision algorithms and applications. We propose a QR-based ED method dedicated to the application scenarios of computer vision.
  arXiv  Detail & Related papers  (2022-07-09T09:14:12Z)
• Adaptive Elastic Training for Sparse Deep Learning on Heterogeneous Multi-GPU Servers [65.60007071024629]
  We show that Adaptive SGD outperforms four state-of-the-art solutions in time-to-accuracy. We show experimentally that Adaptive SGD outperforms four state-of-the-art solutions in time-to-accuracy.
  arXiv  Detail & Related papers  (2021-10-13T20:58:15Z)
• VersaGNN: a Versatile accelerator for Graph neural networks [81.1667080640009]
  We propose textitVersaGNN, an ultra-efficient, systolic-array-based versatile hardware accelerator. textitVersaGNN achieves on average 3712$times$ speedup with 1301.25$times$ energy reduction on CPU, and 35.4$times$ speedup with 17.66$times$ energy reduction on GPU.
  arXiv  Detail & Related papers  (2021-05-04T04:10:48Z)
• Efficient and Generic 1D Dilated Convolution Layer for Deep Learning [52.899995651639436]
  We introduce our efficient implementation of a generic 1D convolution layer covering a wide range of parameters. It is optimized for x86 CPU architectures, in particular, for architectures containing Intel AVX-512 and AVX-512 BFloat16 instructions. We demonstrate the performance of our optimized 1D convolution layer by utilizing it in the end-to-end neural network training with real genomics datasets.
  arXiv  Detail & Related papers  (2021-04-16T09:54:30Z)
• Systolic Computing on GPUs for Productive Performance [2.8064596842326575]
  We propose a language and compiler to productively build high-performance systolic arrays that run on GPUs. A programmer it' specifies a projection of a dataflow compute onto a linear systolic array, while leaving the detailed implementation of the projection to a compiler. The compiler implements the specified projection and maps the linear systolic array to the SIMD execution units and vector registers of GPUs.
  arXiv  Detail & Related papers  (2020-10-29T18:49:54Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.