RENO: A Rename-Based Instruction Optimizer

摘要

RENO is a modified MIPS R10000 register renamer that uses map-table "short-circuiting" to implement dynamic versions of several well-known static optimizations: move elimination, common subexpression elimination, register allocation, and constant folding. Because it implements these optimizations dynamically, RENO can apply optimizations in certain situations where static compilers cannot. Several of RENO's component optimizations have been previously proposed as independent mechanisms. Unified renaming implements dynamic move elimination and speculative memory bypassing (the dynamic counterpart of register allocation). Register integration implements common-subexpression elimination and speculative memory bypassing. RENO unifies these mechanisms and adds a dynamic version of constant folding, RENO_(CF). RENO_(CF) uses an extended map table format and a limited form of dynamic operation fusion. Cycle-level simulation shows that RENO dynamically eliminates (i.e., optimizes away) 22% of the dynamic instructions in both SPECint2000 and MediaBench. RENO_(CF) is responsible for 12% and 17% of the eliminations, respectively. Because dataflow dependences are collapsed around eliminated instructions, performance improves by 8% and 13%, respectively. Alternatively, because eliminated instructions do not consume issue queue entries, physical registers, or issue, bypass, register file, and execution bandwidth, RENO can be used to absorb the performance impact of a significantly scaled-down execution core.