Skip to content
  • Matt Arsenault's avatar
    AMDGPU: Rework how private buffer passed for HSA · 26f8f3db
    Matt Arsenault authored
    If we know we have stack objects, we reserve the registers
    that the private buffer resource and wave offset are passed
    and use them directly.
    
    If not, reserve the last 5 SGPRs just in case we need to spill.
    After register allocation, try to pick the next available registers
    instead of the last SGPRs, and then insert copies from the inputs
    to the reserved registers in the progloue.
    
    This also only selectively enables all of the input registers
    which are really required instead of always enabling them.
    
    llvm-svn: 254331
    26f8f3db
Loading