Pith. sign in

Acceleration of multi-component multiple-precision arithmetic with branch-free algorithms and SIMD vectorization

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it
abstract

Multiple-precision floating-point branch-free algorithms can significantly accelerate multi-component arithmetic implemented by combining hardware-based binary64 and binary32, particularly for triple- and quadruple-precision computations. In this study, we achieved benchmark results on x86 and ARM CPU platforms to quantify the accelerations achieved in linear computations and polynomial evaluation by integrating these algorithms.

fields

cs.MS 1

years

2026 1

verdicts

CONDITIONAL 1

representative citing papers

Multiple Double Arithmetic on NVIDIA Tensor Cores

cs.MS · 2026-07-08 · conditional · novelty 6.0

Multiple double matrix multiplication on FP64 tensor cores is achieved by splitting doubles into 13-bit quarters with trailing zeros, enabling error-free inner products without branching renormalization.

citing papers explorer

Showing 1 of 1 citing paper.

  • Multiple Double Arithmetic on NVIDIA Tensor Cores cs.MS · 2026-07-08 · conditional · none · ref 8 · internal anchor

    Multiple double matrix multiplication on FP64 tensor cores is achieved by splitting doubles into 13-bit quarters with trailing zeros, enabling error-free inner products without branching renormalization.