English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

The slowdown of Moore's law and the power wall necessitates a shift towardsfinely tunable precision (a.k.a. transprecision) computing to reduce energyfootprint. Hence, we need circuits capable of performing floating-pointoperations on a wide range of precisions with high energy-proportionality. Wepresent FPnew, a highly configurable open-source transprecision floating-pointunit (TP-FPU) capable of supporting a wide range of standard and custom FPformats. To demonstrate the flexibility and efficiency of FPnew ingeneral-purpose processor architectures, we extend the RISC-V ISA withoperations on half-precision, bfloat16, and an 8bit FP format, as well as SIMDvectors and multi-format operations. Integrated into a 32-bit RISC-V core, ourTP-FPU can speed up execution of mixed-precision applications by 1.67x w.r.t.an FP32 baseline, while maintaining end-to-end precision and reducing systemenergy by 37%. We also integrate FPnew into a 64-bit RISC-V core, supportingfive FP formats on scalars or 2, 4, or 8-way SIMD vectors. For this core, wemeasured the silicon manufactured in Globalfoundries 22FDX technology across awide voltage range from 0.45V to 1.2V. The unit achieves leading-edge measuredenergy efficiencies between 178 Gflop/sW (on FP64) and 2.95 Tflop/sW (on 8-bitmini-floats), and a performance between 3.2 Gflop/s and 25.3 Gflop/s.

FPnew: An Open-Source Multi-Format Floating-Point Unit Architecture for Energy-Proportional Transprecision Computing