RENO: a rename-based instruction optimizer
RENO: a rename-based instruction optimizer
复制标题
RENO：基于重命名的指令优化器
DOI：
10.1109/isca.2005.43
复制
发表时间：
2005
期刊：
影响因子：
--
通讯作者：
A. Roth
中科院分区：
文献类型：
--
作者：
Vlad Petric;Tingting Sha;A. Roth
Reno是一种修改的MIPS R10000寄存器Renamer，它使用MAP-table“短路”来实现几种众所周知的静态优化的动态版本：移动消除，常见的子表达消除，寄存器分配和恒定折叠。由于它会动态实现这些优化，因此Reno可以在静态编译器不能的某些情况下应用优化。周期级仿真表明，Reno在SpecInt2000和MediaBench中动态消除了22％的动态指令（即优化）。 Reno/ sub cf/分别负责消除的12％和17％。由于数据流依赖性围绕消除说明崩溃，因此性能分别提高了8％和13％。另外，由于消除的指令不消耗问题队列条目，物理寄存器或问题，旁路，注册文件和执行带宽，因此可以使用Reno来吸收显着缩放缩小的执行核心的性能影响。
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. Cycle-level simulation shows that RENO dynamically eliminates (i.e. optimizes away) 22% of the dynamic instructions in both SPECint2000 and MediaBench. RENO/sub 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.