mirror of
https://github.com/n64dev/cen64.git
synced 2025-04-02 10:31:54 -04:00
335611d617
izy noticed that the branch LUT was generating memory moves and could be replaced with an inlined function that coerces gcc into generating a lea in its place: 4005ac: 8d 1c 00 lea (%rax,%rax,1),%ebx 4005af: c1 fb 1f sar $0x1f,%ebx 4005b2: f7 d3 not %ebx (no memory access) 4005b9: c1 e8 1e shr $0x1e,%eax 4005bc: 83 e0 01 and $0x1,%eax 4005bf: 44 8b 24 85 90 07 40 mov 0x400790(,%rax,4),%r12d (original has memory access) This ends up optimizing branch instructions quite nicely: "You see that when you use "mask" you execute "~mask". The compiler understands that ~(~(partial_mask)) = partial_mask and removes both "NOTs". So in this case my version uses 2 instructions and no memory access/cache pollution." |
||
|---|---|---|
| .. | ||
| docs | ||
| cp0.c | ||
| cp0.h | ||
| cp1.c | ||
| cp1.h | ||
| cpu.c | ||
| cpu.h | ||
| dcache.c | ||
| dcache.h | ||
| decoder.c | ||
| decoder.h | ||
| fault.c | ||
| fault.h | ||
| fault.md | ||
| functions.c | ||
| icache.c | ||
| icache.h | ||
| interface.c | ||
| interface.h | ||
| opcodes.c | ||
| opcodes.h | ||
| opcodes.md | ||
| opcodes_priv.h | ||
| pipeline.c | ||
| pipeline.h | ||
| registers.md | ||
| segment.c | ||
| segment.h | ||
| TODO.txt | ||