Hiroyuki Ootomo

14 papers A* 1B 1C 2Journal 9Unranked 1

Year	Rank	Type	Title / Venue / Authors
2024	A*	`conf`	CAGRA: Highly Parallel Graph Construction and Approximate Nearest Neighbor Search for GPUs. ICDE Hiroyuki Ootomo, Akira Naruse, Corey Nolet, Ray Wang, Tamas Feher, Yong Wang
2024	J	`jnl`	DGEMM on integer matrix multiplication unit. Int. J. High Perform. Comput. Appl. Hiroyuki Ootomo, Katsuhisa Ozaki, Rio Yokota
2023	J	`jnl`	CAGRA: Highly Parallel Graph Construction and Approximate Nearest Neighbor Search for GPUs. CoRR Hiroyuki Ootomo, Akira Naruse, Corey Nolet, Ray Wang, Tamas Feher, Yong Wang
2023	J	`jnl`	Custom 8-bit floating point value format for reducing shared memory bank conflict in approximate nearest neighbor search. CoRR Hiroyuki Ootomo, Akira Naruse
2023	J	`jnl`	DGEMM on Integer Matrix Multiplication Unit. CoRR Hiroyuki Ootomo, Katsuhisa Ozaki, Rio Yokota
2023	B	`conf`	Fast Symmetric Eigenvalue Decomposition via WY Representation on Tensor Core. PPoPP Shaoshuai Zhang, Ruchi Shah, Hiroyuki Ootomo, Rio Yokota, Panruo Wu
2023	—	`conf`	Mixed-Precision Random Projection for RandNLA on Tensor Cores. PASC Hiroyuki Ootomo, Rio Yokota
2023	J	`jnl`	Mixed-Precision Random Projection for RandNLA on Tensor Cores. CoRR Hiroyuki Ootomo, Rio Yokota
2023	C	`conf`	Quantum Circuit Simulation by SGEMM Emulation on Tensor Cores and Automatic Precision Selection. ISC Hiroyuki Ootomo, Hidetaka Manabe, Kenji Harada, Rio Yokota
2023	J	`jnl`	Quantum Circuit Simulation by SGEMM Emulation on Tensor Cores and Automatic Precision Selection. CoRR Hiroyuki Ootomo, Hidetaka Manabe, Kenji Harada, Rio Yokota
2023	C	`conf`	Reducing shared memory footprint to leverage high throughput on Tensor Cores and its flexible API extension library. HPC Asia Hiroyuki Ootomo, Rio Yokota
2023	J	`jnl`	Reducing shared memory footprint to leverage high throughput on Tensor Cores and its flexible API extension library. CoRR Hiroyuki Ootomo, Rio Yokota
2022	J	`jnl`	Recovering single precision accuracy from Tensor Cores while surpassing the FP32 theoretical peak performance. CoRR Hiroyuki Ootomo, Rio Yokota
2022	J	`jnl`	Recovering single precision accuracy from Tensor Cores while surpassing the FP32 theoretical peak performance. Int. J. High Perform. Comput. Appl. Hiroyuki Ootomo, Rio Yokota