FPnew：一种用于能量比例传输计算的开源多格式浮点单元结构
FPnew: An Open-Source Multi-Format Floating-Point Unit Architecture for Energy-Proportional Transprecision Computing
摘要：
摩尔定律和功率墙的放缓需要向精细可调精度（a.k.a.）转变。transprecision）计算以减少能量足迹。因此，我们需要能够以高能量比例在宽范围的精度上执行浮点运算的电路。我们介绍了FPnew，一个高度可配置的开源transprecision浮点单元（TP-FPU），能够支持各种标准和自定义FP格式。为了证明FPnew在通用处理器架构中的灵活性和效率，我们扩展了RISC-V ISA，包括半精度，bfloat 16和8位FP格式的操作，以及SIMD向量和多格式操作。集成到32位RISC-V内核中，我们的TP-FPU可以将混合精度应用的执行速度提高1.67倍w.r.t.。FP 32基准，同时保持端到端精度并将系统能耗降低37%。我们还将FPnew集成到64位RISC-V内核中，支持标量或2、4或8路SIMD向量上的五种FP格式。对于该内核，我们在0.45V至1.2V的宽电压范围内测量了采用Globalfoundries 22 FDX技术制造的硅。该单元实现了178 Gflop/sW（在FP 64上）和2.95 Tflop/sW（在8位微型浮点数上）之间的前沿测量能效，以及3.2 Gflop/s和25.3 Gflop/s之间的性能。
英文摘要：
The slowdown of Moore's law and the power wall necessitates a shift towards finely tunable precision (a.k.a. transprecision) computing to reduce energy footprint. Hence, we need circuits capable of performing floating-point operations on a wide range of precisions with high energy-proportionality. We present FPnew, a highly configurable open-source transprecision floating-point unit (TP-FPU) capable of supporting a wide range of standard and custom FP formats. To demonstrate the flexibility and efficiency of FPnew in general-purpose processor architectures, we extend the RISC-V ISA with operations on half-precision, bfloat16, and an 8bit FP format, as well as SIMD vectors and multi-format operations. Integrated into a 32-bit RISC-V core, our TP-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 system energy by 37%. We also integrate FPnew into a 64-bit RISC-V core, supporting five FP formats on scalars or 2, 4, or 8-way SIMD vectors. For this core, we measured the silicon manufactured in Globalfoundries 22FDX technology across a wide voltage range from 0.45V to 1.2V. The unit achieves leading-edge measured energy efficiencies between 178 Gflop/sW (on FP64) and 2.95 Tflop/sW (on 8-bit mini-floats), and a performance between 3.2 Gflop/s and 25.3 Gflop/s.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
