Advanced Search
    Huang Lei, Feng Xiaobing, and Lü Fang. A Register Pressure Sensitive Instruction Speculative Scheduling Technology[J]. Journal of Computer Research and Development, 2009, 46(3): 485-491.
    Citation: Huang Lei, Feng Xiaobing, and Lü Fang. A Register Pressure Sensitive Instruction Speculative Scheduling Technology[J]. Journal of Computer Research and Development, 2009, 46(3): 485-491.

    A Register Pressure Sensitive Instruction Speculative Scheduling Technology

    • Speculation is an important method to overcome control flow constraints during instruction scheduling. On the one hand, speculation can exploit more instruction-level parallelism and improve performance. However, on the other hand, it may also lengthen the live range of variables and increase the register pressure, which in turn results in spilling some variables to memory and deteriorating the performance. Previous work on register pressure sensitive instruction scheduling generally scheduled instructions conservatively when there were too many live variables in the scheduling region. But actually different variables have different spilling costs and different impacts on performance. Here a register pressure sensitive speculative instruction scheduling technology is presented, which not only considers the count of live variables, but also analyzes the benefits and the spilling costs brought by instructions’ speculative motions. The decrement of cycles in critical path is calculated as benefit, while the spilled variables are predicted and their spilling cost is used as cost. Only the speculative motion with benefit greater than the cost is permitted in our method. This algorithm has been implemented in Godson Compiler for MIPS architecture. Experiment result shows that the method in this paper can obtain 1.44% speedup on average relative to its register pressure insensitive counterpart on SPEC CPU2000INT benchmarks.
    • loading

    Catalog

      Turn off MathJax
      Article Contents

      /

      DownLoad:  Full-Size Img  PowerPoint
      Return
      Return