mirror of
https://github.com/c64scene-ar/llvm-6502.git
synced 2025-02-13 10:32:06 +00:00
98a8ba0393
emitted too early. In particular, this fixes
Regression/CodeGen/X86/regpressure.ll:regpressure3.
This also improves the 2nd basic block in 164.gzip:flush_block, which went from
.LBBflush_block_1: # loopentry.1.i
movzx %EAX, WORD PTR [dyn_ltree + 20]
movzx %ECX, WORD PTR [dyn_ltree + 16]
mov DWORD PTR [%ESP + 32], %ECX
movzx %ECX, WORD PTR [dyn_ltree + 12]
movzx %EDX, WORD PTR [dyn_ltree + 8]
movzx %EBX, WORD PTR [dyn_ltree + 4]
mov DWORD PTR [%ESP + 36], %EBX
movzx %EBX, WORD PTR [dyn_ltree]
add DWORD PTR [%ESP + 36], %EBX
add %EDX, DWORD PTR [%ESP + 36]
add %ECX, %EDX
add DWORD PTR [%ESP + 32], %ECX
add %EAX, DWORD PTR [%ESP + 32]
movzx %ECX, WORD PTR [dyn_ltree + 24]
add %EAX, %ECX
mov %ECX, 0
mov %EDX, %ECX
to
.LBBflush_block_1: # loopentry.1.i
movzx %EAX, WORD PTR [dyn_ltree]
movzx %ECX, WORD PTR [dyn_ltree + 4]
add %ECX, %EAX
movzx %EAX, WORD PTR [dyn_ltree + 8]
add %EAX, %ECX
movzx %ECX, WORD PTR [dyn_ltree + 12]
add %ECX, %EAX
movzx %EAX, WORD PTR [dyn_ltree + 16]
add %EAX, %ECX
movzx %ECX, WORD PTR [dyn_ltree + 20]
add %ECX, %EAX
movzx %EAX, WORD PTR [dyn_ltree + 24]
add %ECX, %EAX
mov %EAX, 0
mov %EDX, %EAX
... which results in less spilling in the function.
This change alone speeds up 164.gzip from 37.23s to 36.24s on apoc. The
default isel takes 37.31s.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@19650 91177308-0d34-0410-b5e6-96231b3b80d8