@rygorous @TomF @zeux @wolf480pl @pervognsen Zcb is compressed forms of byte load/store, sign- and zero-extend, mul and not. Zcmp is compressed push/pop/return and a limited form of double-mov. They put together a nice spreadsheet showing the impact of each instruction: https://docs.google.com/spreadsheets/d/1bFMyGkuuulBXuIaMsjBINoCWoLwObr1l9h5TAWN8s7k/edit?gid=1837831327#gid=1837831327
W
wren6991@types.pl
@wren6991@types.pl
Posts
-
Someone on Lobsters wondered "how a modern compiler would fare against hand-optimized asm" in reference to Abrash's TransformVector (3x3 matrix-vector multiply) hand-written x87 routine in Quake. -
Someone on Lobsters wondered "how a modern compiler would fare against hand-optimized asm" in reference to Abrash's TransformVector (3x3 matrix-vector multiply) hand-written x87 routine in Quake.@rygorous @TomF @zeux @wolf480pl @pervognsen Would be interested to see how RISC-V fared with addition of B, Zcmp and Zcb. I find it's usually pretty close to Thumb. Zcb in particular is just "oops we forgot to put this in the C extension" and there's not much excuse not to implement it