From: anton@mips.complang.tuwien.ac.at   
      
   Robert Finch  writes:   
   >Skimming through the SPARC architecture manual I am wondering how they   
   >handle register renaming with a windowed register file. If the register   
   >window file is deep there must be a ginormous number of registers for   
   >renaming. Would it need to keep track of the renames for all the   
   >registers? How does it dump the rename state to memory?   
      
   There is no need to dump the rename state to memory, not for SPARC nor   
   for anything else.  It's only microarchitectural.   
      
   The large number of architected registers may have been a reason why   
   they needed so long to implement OoO execution.   
      
   I think that the cost is typically a register allocation table RAT per   
   branch (for maybe 50 branches or potential traps that you want to   
   predict, i.e., 50 RATs).  With 32 architected registers and 257-512   
   physical registers that's 32*9 bits = 288 bits per RAT; with the 136   
   architected registers of SPARC, and again <=512 physical registers,   
   that would be 1224 bits per RAT.   
      
   There are probably other options that using a RAT, but I have   
   forgotten them.   
      
   - 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)