Global ETD Search
Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.
Results
Showing 1 to 18 of 18 for “"SpMM"”.
-
QuadriSparse: RISC-V Sparse Matrix Accelerator and ISA Extension - A Tightly-Coupled Sparse-Dense Matrix Multiplication Accelerator for RISC-V
Sparse dense matrix multiplication (SpMM) is an important operation in many applications such as inference and training of pruned large language models, graph analytics and scientific computing. These applications often operate on data that is inherently sparse. Applying dense matrix multiplication …
-
Cache-Conscious Sparse Matrix Dense Matrix Multiplication on GPUs
… sparse matrix–dense matrix multiplication (SpMM) as a fundamental kernel—particularly in graph neural networks (GNNs). Modern GPUs, with their massive parallelism and high-bandwidth memory, offer immense potential for accelerating these workloads. While SpMM implementations using the …
-
New Parallel Algorithms for Large-Scale Matrix Computations
… parallel sparse-dense matrix multiplication (CRP-SpMM) algorithm. This algorithm can benefit from existing sparse matrix partitioning methods for sparse matrix-dense vector multiplication (SpMV), and further explores more effective 2D process grid sizes to reduce communication costs by …
-
The role of meridional modes in pacific climate variability and change
… relative importance of the NPMM and South PMM (SPMM) in ENSO and tropical Pacific decadal variability (TPDV) by performing experiments with the CESM model in which the NPMM and SPMM are selectively suppressed. We find that both meridional modes energize the tropical variance independently on …
-
Performance Primitives for Artificial Neural Networks
… as a sparse-matrix-dense-matrix multiplication (SpMM) and introduce neural network-optimized SpMM primitives. While SpMM primitives in Sparse BLAS libraries target problems with extremely high sparsity (commonly 99+% sparsity) and non-random sparsity patterns, the proposed SpMM primitive is …
-
ABSTRACTIONS AND OPTIMIZATIONS FOR SPARSE TENSOR COMPUTATION ON MODERN HARDWARE
… efficient sparse matrix-matrix multiplication (SpMM) kernel designs on modern GPU architectures featuring asynchronous execution models. The UniSparse compiler-generated kernels follow synchronous execution patterns and cannot match the performance of hand-tuned kernels on modern GPU platforms. …
-
Tuning Sparse Matrix Kernel Performance via Lightweight Signatures
… such as sparse-dense matrix multiplication (SpMM), sampled dense-dense matrix multiplication (SDDMM), etc. Sparse matrix kernels are typically bandwidth limited and can benefit from optimizations such as tiling to improve cache effectiveness. However, tiling sparse kernels is challenging. …
-
Design and Management Strategies for Hardware Accelerators
… the sparse matrix multi-vector multiplication (SpMM) performance on GPU architectures. We propose an intelligent mechanism for optimizing SpMM performance based on the sparsity pattern in the data. Our solution relies on developing a set of simple but effective data permutation policies that …
-
Development and Validation of a Tool for In-Plane Antilock Braking System (ABS) Simulations
… on a suspension parameter measuring machine (SPMM) in order to complement this design tool. The results of the objective tests performed have been discussed and the correlations and variations with respect to the simulation results have been analyzed.
-
Design of efficient block-sparse data structures and associated tensor multiplications for applications in Cluster in Molecule electronic structure calculations
… of Sparse-matrix dense-matrix multiplication (SpMM), while the Tile Master emphasizes solving the three-index integral problem using the block-sparse structure and compressed three-dimensional array format. Both the Tile structure and the Tile Master are made highly efficient and able to …
-
High-Performance Network- and GPU-Aware Communication for MPI Partitioned and MPI Neighbourhoods
… and a Sparse Matrix-Matrix multiplication (SpMM) kernel on multiple platforms.
-
Analytical Modeling and Efficient Implementation for Specialized Hardware Acceleration of Sparse Applications
… sparse-matrix dense-matrix multiplication (SpMM), sparse-matrix sparse vector multiplication (SpMSpV), and sparse-matrix sparse-matrix multiplication (SpGEMM). Guided by the analytical model, Vesper is designed to be configurable and resource-efficient, supporting diverse compute patterns …
-
Sparsity-Aware Hardware-Software Co-design of Spiking Neural Network Accelerators
… Sparse Matrix-Dense Matrix multiplication (SpMM) kernels, widely used in ANNs, are sub-optimal for SNNs due to their unique multiplication-free property, necessitating the development of specialized hardware acceleration techniques. This dissertation makes two major contributions. The first …
-
Direct numerical simulation and model evaluation for turbulent combustion at engine conditions
… MMC (SMMC) and shadow-position multiple mapping (SPMM) mixing models. The performances of the MMC-type mixing models are then assessed against three DNS datasets which feature increasing levels of extinction (decreasing reignition) within a statistically 1D nonpremixed mixing layer. The results …
-
FPGA-based high-performance neural network acceleration
… to handle Sparse Matrices Multiplications (SpMM) on extremely sparse and unbalanced input. With GNN inference as a case study, AWB-GCN achieves over 90% system efficiency, guarantees efficient off-chip memory access, and provides considerable speedups over CPUs (3255x), GPUs (80x), and a …
-
A hybrid communication pattern and algorithm for distributed sparse-times-dense matrix multiplication
Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2024-09-16 without embargo terms
-
A hybrid communication pattern and algorithm for distributed sparse-times-dense matrix multiplication
Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2024-09-16 without embargo terms
-
Hierarchical sparse computations and communications for solving inverse problems on supercomputers with multi-GPU nodes
Submission published under a 24 month embargo labeled 'Closed Access', the embargo will last until 2024-08-01