机器学习内核的符号基本块分析
Symbolic Basic Block Profiling for Machine Learning Kernels
浏览论文内容
中文总结 AI 辅助
针对现有基本块分析技术的运行时开销与耗时问题，提出适用于机器学习内核的符号程序分析技术，在LLVM中实现后对78个ML算子评估，73个结果与动态插桩一致，中位数提速15093倍。
中文摘要 AI 辅助
当前的基本块分析技术通过动态插桩获取程序中每个基本块的执行次数，这些分析计数器会产生运行时开销，且需要执行程序，对于大输入规模而言，会耗费大量时间。我们提出符号程序分析技术，该技术以输入为自变量生成基本块执行次数的符号公式。我们的技术仅适用于特定类别的程序，即机器学习（ML）内核。我们在LLVM编译器中实现了该技术，并对来自50个不同ML模型的78个ML算子进行了评估，这些算子由机器学习编译器TVM生成。我们的符号分析结果与动态插桩的结果完全一致，在78个内核中有73个达到了这一效果，且速度提升的中位数为15093倍。
英文摘要
Current basic block profiling techniques obtain the count of executions of each basic block in a program using dynamic instrumentation. These profiling counters create runtime overheads and also require the execution of the program, which, for large input sizes, can take substantial time. We propose symbolic program profiling that generates symbolic formulae for a basic block's count with inputs as the independent variables. Our technique is limited in applicability to a certain class of programs, namely machine learning (ML) kernels. We implement our technique in the LLVM compiler and evaluate it on 78 ML operators from 50 different ML models. These operators are generated by TVM, a machine learning compiler. Our symbolic profiles deliver exactly the same results as dynamic instrumentation for 73 out of 78 kernels with a median speedup of 15093x.
