AI 中文总结
研究从帕斯卡到布莱克威尔架构的 warp 发散特性，通过多种测试方法区分稳定行为与架构变化，发现发散路径线性序列化，执行效率与路径数量有关，不同架构重新收敛机制有变化，新屏障类无明显运行时效果，发散性能成本稳定可预测。
AI 中文摘要
自伏特架构引入独立线程调度（ITS）以来，人们普遍认为英伟达 GPU 以固定方式处理 warp 发散。本文以 ITS 之前的帕斯卡架构为基线，对安培、霍珀以及数据中心和消费级的布莱克威尔 GPU 进行测试。通过循环精确微基准测试、硬件计数器和对编译器生成的 SASS 的静态分析，区分稳定行为和架构变化。结果表明，所有测试代中，发散路径随路径数量\(k\)线性序列化，执行效率随\(32/k\)下降，惩罚与占用率无关，预测可消除序列化成本。帕斯卡架构也有类似行为，但其编译器发出的重新收敛机制有很大变化，布莱克威尔架构引入了新特性，如两级收敛屏障分类等。控制位翻转实验表明新屏障类在测试中无明显运行时效果。所以，即使英伟达的控制流 ISA 和重新收敛机制不断发展，发散仍保持稳定且可预测的性能成本。
英文摘要
Since Volta introduced Independent Thread Scheduling (ITS), NVIDIA GPUs have been widely assumed to handle warp divergence in a fixed manner. We test this assumption across Ampere, Hopper, and datacenter and consumer Blackwell GPUs, using pre-ITS Pascal as a baseline. Combining cycle-accurate microbenchmarks, hardware counters, and static analysis of compiler-generated SASS, we separate stable behavior from architectural change. Across all tested generations, divergent paths serialize linearly with the number of paths $k$, following $T(k) \approx sk$ with no super-linear reconvergence penalty. Warp execution efficiency falls as $32/k$, the penalty is independent of occupancy, and predication removes the serialization cost. The same behavior appears on Pascal, showing that this programmer-visible cost model predates ITS. The compiler-emitted reconvergence machinery, however, has changed substantially. Pascal uses a per-warp SSY/SYNC instruction stack, whereas later generations use barrier-register instructions. Deferred reconvergence beyond the immediate post-dominator falls from 29 cases on Ampere to 2 on Blackwell. Blackwell also introduces a two-tier convergence-barrier classification, uniform-branch instructions, and explicit partial-mask warp synchronization, none of which appear on Ampere or Hopper. Controlled bit-flip experiments indicate that the new barrier class is a static compiler classification with no observable runtime effect in our tests. Thus, divergence retains a stable and predictable performance cost even as NVIDIA's control-flow ISA and reconvergence mechanisms continue to evolve.
Comments6 pages, 4 figures
