mirror of
https://github.com/c64scene-ar/llvm-6502.git
synced 2025-01-10 18:34:09 +00:00
4053b1e30b
typically cost 1 cycle) instead of shld/shrd instruction (which are typically
6 or more cycles). This also saves code space.
For example, instead of emitting:
rotr:
mov %EAX, DWORD PTR [%ESP + 4]
mov %CL, BYTE PTR [%ESP + 8]
shrd %EAX, %EAX, %CL
ret
rotli:
mov %EAX, DWORD PTR [%ESP + 4]
shrd %EAX, %EAX, 27
ret
Emit:
rotr32:
mov %CL, BYTE PTR [%ESP + 8]
mov %EAX, DWORD PTR [%ESP + 4]
ror %EAX, %CL
ret
rotli32:
mov %EAX, DWORD PTR [%ESP + 4]
ror %EAX, 27
ret
We also emit byte rotate instructions which do not have a sh[lr]d counterpart
at all.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@19692 91177308-0d34-0410-b5e6-96231b3b80d8