论文标题
在软件定义的硬件中进行有效的内存分区
Efficient Memory Partitioning in Software Defined Hardware
论文作者
论文摘要
随着程序员转向软件定义的硬件（SDH）以保持高水平的生产率，同时编程硬件以运行复杂的算法，因此编译器必须进行重命中，以自动对片上阵列进行自动分区。在本文中，我们引入了一个自动内存分配系统，该系统可以快速计算比先前系统更有效的分区方案。我们的系统采用各种节省资源的优化和ML成本模型来从一系列候选人中选择最佳分区方案。我们将我们的系统与各种基准测试的各种最先进的SDH编译器和FPGA进行了比较，发现我们的系统平均生成了解决方案，这些解决方案平均消耗了40.3％的逻辑资源，FFS减少了78.3％，较少的FFS，较少的Block RAM（BRAMS）少54.9％，而100％的DSPS减少了。
As programmers turn to software-defined hardware (SDH) to maintain a high level of productivity while programming hardware to run complex algorithms, heavy-lifting must be done by the compiler to automatically partition on-chip arrays. In this paper, we introduce an automatic memory partitioning system that can quickly compute more efficient partitioning schemes than prior systems. Our system employs a variety of resource-saving optimizations and an ML cost model to select the best partitioning scheme from an array of candidates. We compared our system against various state-of-the-art SDH compilers and FPGAs on a variety of benchmarks and found that our system generates solutions that, on average, consume 40.3% fewer logic resources, 78.3% fewer FFs, 54.9% fewer Block RAMs (BRAMs), and 100% fewer DSPs.
