From: anton@mips.complang.tuwien.ac.at   
      
   anton@mips.complang.tuwien.ac.at (Anton Ertl) writes:   
   >Looking at the "18 RISC-V Compressed ISA V1.9" specification   
      
   Someone asked for more and dynamic numbers.  This work contains them   
   in Section 1.9:   
      
   |Table 1.7 lists the standard RVC instructions with the most frequent   
   |first, showing the individual contributions of those instructions to   
   |static code size and then the running total for three experiments: the   
   |SPEC benchmarks for both RV32C and RV64C for the Linux kernel. For   
   |RV32, RVC reduces static code size by 24.5% on Dhrystone and 30.9% on   
   |CoreMark. For RV64, it reduces static code size by 26.3% on SPECint,   
   |25.8% on SPECfp, and 31.1% on the Linux kernel.   
   |   
   |Table 1.8 ranks the RVC instructions by order of typical dynamic   
   |frequency. For RV32, RVC reduces dynamic bytes fetched by 29.2% on   
   |Dhrystone and 29.3% on CoreMark. For RV64, it reduces dynamic bytes   
   |fetched by 26.9% on SPECint, 22.4% on SPECfp, and 26.11% booting the   
   |Linux kernel.   
      
   If you want the tables, look at source:   
      
      
   - anton   
   --   
   'Anyone trying for "industrial quality" ISA should avoid undefined behavior.'   
     Mitch Alsup,    
      
   --- SoupGate-Win32 v1.05   
    * Origin: you cannot sedate... all the things you hate (1:229/2)