2019


Batched Sparse Matrix Multiplication for Accelerating Graph Convolutional Networks,
Yusuke Nagasaka, Akira Nukada, Ryosuke Kojima, Satoshi Matsuoka,
19th Annual IEEE/ACM International Symposium in Cluster, Cloud, and Grid Computing (CCGrid 2019),
Larnaca,
Proceedings of the 19th Annual IEEE/ACM International Symposium in Cluster, Cloud, and Grid Computing (CCGRID),
IEEE,
May. 2019.

Performance Optimization of Sparse Matrix Kernels for Many-core Architectures,
Yusuke Nagasaka,
26 Mar. 2019.

Performance Optimization of Sparse Matrix Kernels for Many-core Architectures,
Yusuke Nagasaka,
26 Mar. 2019.

Performance Optimization of Sparse Matrix Kernels for Many-core Architectures,
Yusuke Nagasaka,
26 Mar. 2019.

2018


MRG8 - Random Number Generation for the Exascale Era,
Yusuke Nagasaka, Akira Nukada, Satoshi Matsuoka, Kenichi Miura, John Shalf,
PASC 2018: Platform for Advanced Scientific Computing Conference,
Basel,
PASC '18 Proceedings of the Platform for Advanced Scientific Computing Conference,
ACM,
Jul. 2018.

2017


High-performance and Memory-saving Sparse General Matrix-Matrix Multiplication for NVIDIA Pascal GPU,
Yusuke Nagasaka, Akira Nukada, Satoshi Matsuoka,
International Conference on Parallel Processing,
Bristol,
7 Sep. 2017.

Fast and Memory-saving SpGEMM Algorithm for New Pascal Generation GPU,
Yusuke Nagasaka,
GPU Technology Conference (GTC2017),
San Jose,
May. 2017.

2016


Fast Sparse General Matrix-Matrix Multiplication on GPU with Low Memory Usage,
Yusuke Nagasaka, Akira Nukada, Satoshi Matsuoka,
The International Conference for High Performance Computing, Networking, Storage and Analysis (SC16),
Salt Lake City, Utah,
15 Nov. 2016.

メモリ使用量を抑えた疎行列疎行列積計算のGPU高速化,
長坂侑亮, 額田彰, 松岡聡,
第156回ハイパフォーマンスコンピューティング研究発表会,
情報処理学会研究報告,
情報処理学会,
Vol. 2016-HPC-156, No. 15, pp. 1-9,
8 Sep. 2016.

Adaptive Multi-level Blocking Optimization for Sparse Matrix Vector Multiplication on GPU,
Yusuke Nagasaka, Akira Nukada, Satoshi Matsuoka,
International Conference on Computational Science (ICCS 2016),
San Diego, CA,
Procedia Computer Science,
Volume 80, pp. 131-142,
1 Jun. 2016.

Fast Sparse Matrix Vector Multiplication with Highly-Compressed Sparse Format,
Yusuke Nagasaka,
GPU Technology Conference (GTC2016),
San Jose,
4 Apr. 2016.

2015


Multi-level Blocking Optimization for Fast Sparse Matrix Vector Multiplication on GPUs,
Yusuke Nagasaka, Akira Nukada, Satoshi Matsuoka,
The International Conference for High Performance Computing, Networking, Storage and Analysis (SC15),
Austin, Texas,
15 Nov. 2015.

多段階ブロッキングによるメモリアクセス量削 減を図った GPU 向け疎行列ベクトル積計算手法の性能評価,
長坂侑亮,
GPU テクノロジ・カンファレンス(GTC Japan 2015),
18 Sep. 2015.

疎行列ベクトル積計算を対象とした GPU 向けメ モリアクセス削減手法,
長坂侑亮, 額田彰, 松岡聡,
第151回ハイパフォーマンスコンピューティング研究発表会,
情報処理学会,
Vol. 2015-HPC-151, No. 8, pp. 1-7,
23 Sep. 2015.

2014


Cache-aware Sparse Matrix Formats for Kepler GPU,
Yusuke Nagasaka, Akira Nukada, Satoshi Matsuoka,
International Conference on Parallel and Distributed Systems (ICPADS2014),
Hsinchu,
2014 20th IEEE International Conference on Parallel and Distributed Systems ICPADS 2014,
pp. 281-288,
16 2014.

GPUでのキャッシュ再利用性を考慮した列分割型疎行列フォーマットの性能評価,
長坂侑亮,
GTC Japan 2014,
東京,
16 Jul. 2014.

Cache-aware Sparse Matrix Format for GPU,
Yusuke Nagasaka, Akira Nukada, Satoshi Matsuoka,
International Superconputing Conference (ISC'14) HPC in Asia Posters,
26 Jun. 2014.

GPU のキャッシュを考慮した疎行列ベクトル積計算手法の性能評価,
長坂侑亮, 額田彰, 松岡聡,
第144回ハイパフォーマンスコンピューティング研究発表会,
神奈川県横浜市,
情報処理学会研究報告,
情報処理学会,
Vol. 2014-HPC-144, No. 5, pp. 1-9,
26 May. 2014.