TileSpGEMM: A Tiled Algorithm for Parallel Sparse General Matrix-Matrix Multiplication on GPUs

preview_player
Показать описание
The 25-min presentation of our work TileSpGEMM: A Tiled Algorithm for Parallel Sparse General Matrix-Matrix Multiplication on GPUs at PPoPP '22.
  1. Yuyao Niu
Рекомендации по теме
TileSpGEMM: A Tiled 0:24:44

TileSpGEMM: A Tiled Algorithm for Parallel Sparse General Matrix-Matrix Multiplication on GPUs

TileSpGEMM (PPoPP '22) 0:11:28

TileSpGEMM (PPoPP '22)

TileSpMV: A Tiled 0:17:09

TileSpMV: A Tiled Algorithm for Sparse Matrix-Vector Multiplication on GPUs (IPDPS 2021)

HetSys Course: Lecture 0:24:03

HetSys Course: Lecture 9: Advanced Tiling for Matrix Multiplication (Spring 2023)

HetSys Course: Lecture 1:01:56

HetSys Course: Lecture 9: Advanced Tiling for Matrix Multiplication (Fall 2022)

Dr. Reza Hojabr 0:54:50

Dr. Reza Hojabr - 02/24/2023 - Streaming Accelerators for Highly Sparse GEMM on FPGAs

SPMM(Sparse Matrix Dense 0:01:58

SPMM(Sparse Matrix Dense Matrix Multiplication) for Needle

Communication-Avoiding and Memory-Constrained 0:17:45

Communication-Avoiding and Memory-Constrained Sparse Matrix-Matrix Multiplication at Extreme Scale

Parallel Algorithms for 0:14:48

Parallel Algorithms for Masked Sparse Matrix-Matrix Products

Learning Sparse Matrix 0:14:54

Learning Sparse Matrix Row Permutations for Efficient SpMM on GPU Architectures

LHAM:30 Performance Evaluation 0:16:58

LHAM:30 Performance Evaluation of Accurate Matrix–Matrix Multiplication on GPU Using Sparse Matrix

Accelerate GNN Training 0:03:39

Accelerate GNN Training with SpMM on GPUs

Portable performance on 0:26:29

Portable performance on multi threaded Sparse BLAS operations with PyRSB | SciPy 2021

PPoPP22_QGTC_Wang 0:09:09

PPoPP22_QGTC_Wang

ASPLOS'23 - Session 0:10:45

ASPLOS'23 - Session 4C - The Sparse Abstract Machine

Seamless Optimization of 0:30:42

Seamless Optimization of the GEMM Kernel for Task-based Programming Models

Matrix multiplications in 0:33:16

Matrix multiplications in CUDA

Open MLIR Meeting 0:59:21

Open MLIR Meeting 3-9-2023: Convolution Optimization to Improve Performance Beyond Im2Col+GEMM

[CGO '22] Session 0:21:10

[CGO '22] Session 8 - Unified Compilation for Lossless Compression and Sparse Computing

Comp Architecture - 0:31:41

Comp Architecture - Lecture 9c: SMASH: Accelerating Sparse Matrix Operations (ETH Zürich, Fall 2020)...

Lecture 08 - 1:06:06

Lecture 08 - Convolution

QGTC: Accelerating Quantized 0:18:18

QGTC: Accelerating Quantized Graph Neural Networks via GPU Tensor Core

Sparse Matrices Beyond 0:54:07

Sparse Matrices Beyond Solvers: Graphs, Biology, and Machine Learning

Centaur: A Chiplet-based, 0:19:49

Centaur: A Chiplet-based, Hybrid Sparse-Dense Accelerator for Personalized Recommendations

visit shbcf.ru