Branch instructions dependent on hard-to-predict load data are the leading branch misprediction contributors. Current state-of-the-art history-based branch predictors have poor prediction accuracy for these branches. Prior research backs this observation by showing that increasing the size of a 256-KBit history-based branch predictor to its 1-MBit variant has just a 10% reduction in branch mispredictions. We present the novel Load Driven Branch Predictor(LDBP) specifically targeting hard-to-predict branches dependent on a load instruction. Though random load data determines the outcome for these branches, the load address for most of these data has a predictable pattern. This is an observable template in data structures like arrays and maps. Our predictor model exploits this behavior to trigger future loads associated with branches ahead of time and use its data to predict the branch's outcome. The predictable loads are tracked, and the precomputed outcomes of the branch instruction are buffered for making predictions. Our experimental results show that compared to a standalone 256-Kbit IMLI predictor, when LDBP is augmented with a 150-Kbit IMLI, it reduces the average branch mispredictions by 20% and improves average IPC by 13.1% for benchmarks from SPEC CINT2006 and GAP benchmark suite.

中文翻译：

---

负载驱动分支预测器 (LDBP)

依赖于难以预测的负载数据的分支指令是导致分支预测错误的主要因素。当前最先进的基于历史的分支预测器对这些分支的预测精度很差。先前的研究通过表明将 256-KBit 基于历史的分支预测器的大小增加到其 1-MBit 变体来支持这一观察结果，分支错误预测仅减少了 10%。我们提出了新颖的负载驱动分支预测器（LDBP），专门针对依赖于负载指令的难以预测的分支。尽管随机加载数据决定了这些分支的结果，但大多数这些数据的加载地址具有可预测的模式。这是数组和映射等数据结构中的可观察模板。我们的预测模型利用这种行为提前触发与分支相关的未来负载，并使用其数据来预测分支的结果。跟踪可预测的负载，并缓存分支指令的预计算结果以进行预测。我们的实验结果表明，与独立的 256-Kbit IMLI 预测器相比，当 LDBP 增加一个 150-Kbit IMLI 时，它可以将平均分支错误预测降低 20%，并将平均 IPC 提高 13.1%，用于来自 SPEC CINT2006 和 GAP 基准的基准测试套房。