Reproducible BLAS Routines with Tunable Accuracy Using Ozaki Scheme for Many-Core Architectures
Daichi Mukunoki, Takeshi Ogita, Katsuhisa Ozaki
Topics & Concepts
Computer scienceMatrix multiplicationParallel computingMultiplication (music)Floating pointDot productRoundingDebuggingComputationDouble-precision floating-point formatImplementationComputational scienceAlgorithmOperating systemProgramming languageMathematicsPhysicsQuantum mechanicsQuantumGeometryCombinatoricsParallel Computing and Optimization TechniquesNumerical Methods and AlgorithmsLow-power high-performance VLSI design