Daichi Mukunoki

发表

Numerical Reproducibility based on Minimal-Precision Validation

Stef Graillat, Toshiyuki Imamura, Daichi Mukunoki, 2019 .

Performance and energy consumption of accurate and mixed-precision linear algebra kernels on GPUs

Daichi Mukunoki, Takeshi Ogita, T. Ogita, 2020, J. Comput. Appl. Math..

Matrix Engines for High Performance Computing: A Paragon of Performance or Grasping at Straws? pdf

Mohamed Wahib, Yosuke Oyama, Jens Domke, 2020, 2021 IEEE International Parallel and Distributed Processing Symposium (IPDPS).

Performance comparison of double, triple and quadruple precision real and complex BLAS subroutines on GPUs

Daisuke Takahashi, Daichi Mukunoki, 2012, HiPC 2012.

Can We Avoid Rounding-Error Estimation in HPC Codes and Still Get Trustworthy Results?

Stef Graillat, Daichi Mukunoki, Roman Iakymchuk, 2020, VSTTE.

Optimization of Sparse Matrix-Vector Multiplication for CRS Format on NVIDIA Kepler Architecture GPUs

Daisuke Takahashi, Daichi Mukunoki, 2013, ICCSA.

DGEMM Using Tensor Cores, and Its Accurate and Reproducible Versions

Daichi Mukunoki, Katsuhisa Ozaki, Takeshi Ogita, 2020, ISC.

Design of an FPGA-Based Matrix Multiplier with Task Parallelism

Toshiyuki Imamura, Daichi Mukunoki, Yiyu Tan, 2019, PARCO.

Conjugate Gradient Solvers with High Accuracy and Bit-wise Reproducibility between CPU and GPU using Ozaki scheme

Daichi Mukunoki, Roman Iakymchuk, Katsuhisa Ozaki, 2021, HPC Asia.

Minimal-Precision Computing for High-Performance, Energy-Efficient, and Reliable Computations

Kentaro Sano, Stef Graillat, Daichi Mukunoki, 2019 .

Implementation and Evaluation of Triple Precision BLAS Subroutines on GPUs

Daisuke Takahashi, Daichi Mukunoki, D. Takahashi, 2012, 2012 IEEE 26th International Parallel and Distributed Processing Symposium Workshops & PhD Forum.

Fast Implementation of General Matrix-Vector Multiplication (GEMV) on Kepler GPUs

Daisuke Takahashi, Toshiyuki Imamura, Daichi Mukunoki, 2015, 2015 23rd Euromicro International Conference on Parallel, Distributed, and Network-Based Processing.

Automatic Thread-Block Size Adjustment for Memory-Bound BLAS Kernels on GPUs

Daisuke Takahashi, Toshiyuki Imamura, Daichi Mukunoki, 2016, 2016 IEEE 10th International Symposium on Embedded Multicore/Many-core Systems-on-Chip (MCSOC).

Implementation and Evaluation of Quadruple Precision BLAS Functions on GPUs

Daisuke Takahashi, Daichi Mukunoki, 2010, PARA.

Optimizing Precision for High-Performance, Robust, and Energy-Efficient Computations

Kentaro Sano, Stef Graillat, Toshiyuki Imamura, 2020 .

Reduced-Precision Floating-Point Formats on GPUs for High Performance and Energy Efficient Computation

Toshiyuki Imamura, Daichi Mukunoki, 2016, 2016 IEEE International Conference on Cluster Computing (CLUSTER).

White Paper from Workshop on Large-scale Parallel Numerical Computing Technology (LSPANC 2020): HPC and Computer Arithmetic toward Minimal-Precision Computing pdf

Taisuke Boku, Takeshi Fukaya, Jens Domke, 2020, ArXiv.

Implementation and Performance Analysis of 2.5D-PDGEMM on the K Computer

Toshiyuki Imamura, Daichi Mukunoki, 2017, PPAM.

Using Quadruple Precision Arithmetic to Accelerate Krylov Subspace Methods on GPUs

Daisuke Takahashi, Daichi Mukunoki, D. Takahashi, 2013, PPAM.

Performance Analysis of 2D-compatible 2.5D-PDGEMM on Knights Landing Cluster

Toshiyuki Imamura, Daichi Mukunoki, 2018, ICCS.

Reproducible BLAS Routines with Tunable Accuracy Using Ozaki Scheme for Many-Core Architectures

Daichi Mukunoki, Katsuhisa Ozaki, Takeshi Ogita, 2019, PPAM.

Design Towards Modern High Performance Numerical LA Library Enabling Heterogeneity and Flexible Data Formats

Yusuke Hirota, Toshiyuki Imamura, Daichi Mukunoki, 2017, PARCO.

Accurate Matrix Multiplication on Binary128 Format Accelerated by Ozaki Scheme

Toshiyuki Imamura, Daichi Mukunoki, Takeshi Ogita, 2021, ICPP.

A Rapid Euclidean Norm Calculation Algorithm that Reduces Overflow and Underflow

Daisuke Takahashi, Toshiyuki Imamura, Daichi Mukunoki, 2021, ICCSA.

Matrix Engines for High Performance Computing: A Paragon of Performance or Grasping at Straws?

Satoshi Matsuoka, Mohamed Wahib, Yosuke Oyama, 2021, 2021 IEEE International Parallel and Distributed Processing Symposium (IPDPS).

Accurate and Reproducible BLAS Routines with Ozaki Scheme for Many-core Architectures

Daichi Mukunoki, Takeshi Ogita, Katsuhisa Ozaki, 2019 .