2 papers
cs.MS2026
Lord of the Precision, the Two Floats: Double-Word Arithmetic for Complex Numbers
František Stloukal, Fabienne Jézéquel
Datacenter GPUs increasingly favour low-precision floating-point formats, offering higher throughput than FP64. Double-word (DW) arithmetic represents numbers as unevaluated sums o…
math.NA2026
Mixed-Precision Computing for Scientific Discovery: Formats, Co-Design, and Responsible Approximation
Emmanuel Agullo, Hartwig Anzt, Daniel Bauer +37
Reduced and mixed precision have moved from a niche optimization to a central design axis in scientific computing and engineering, driven by energy constraints, heterogeneous accel…