IEEE

Distributed-Memory Sparse Deep Neural Network Inference Using Global Arrays

Abstract: Partitioned Global Address Space (PGAS) models exhibit tremendous promise in developing efficient and productive distributed-memory parallel applications. They have been used extensively in ...
HotHardware

ASUS ROG Matrix GeForce RTX 5090 Rocks Quad Fans And A Funktastic Design

You have to hand it to ASUS and its Republic of Gamers (ROG) division, it's not afraid to experiment with bold GPU designs. Following the launch of gold-themed Dhahab Edition graphics cards paying ...
marktechpost

RXTX: A Machine Learning-Guided Algorithm for Efficient Structured Matrix Multiplication

Discovering faster algorithms for matrix multiplication remains a key pursuit in computer science and numerical linear algebra. Since the pioneering contributions of Strassen and Winograd in the late ...
Scientific Research Publishing

Gibbs, N.E., Poole, Jr., W.G. and Stockmeyer, P.K. (1976) An Algorithm for Reducing the Bandwidth and Profile of a Sparse Matrix. SIAM Journal on Numerical Analysis, 13, 236-250.

ABSTRACT: Node renumbering is an important step in the solution of sparse systems of equations. It aims to reduce the bandwidth and profile of the matrix. This allows for the speeding up of the ...
Scientific Research Publishing

Barnard, S.T., Pothen, A. and Simon, H.D. (1993) A Spectral Algorithm for Envelope Reduction of Sparse Matrices. Proceedings of the 1993 ACM/IEEE Conference on Supercomputing ...

ABSTRACT: Node renumbering is an important step in the solution of sparse systems of equations. It aims to reduce the bandwidth and profile of the matrix. This allows for the speeding up of the ...
GitHub

README.md

Summary: Implemented a 2D convolution algorithm with tiling optimization using CUDA. Divided the input matrix into tiles and leveraged shared memory to minimize global memory accesses, ensuring ...