Re: [PATCH] Adjust memory_move_cost for MASK_REGS when MODE_SIZE > 8.

2023-03-31 Thread Hongtao Liu via Gcc-patches
On Fri, Mar 31, 2023 at 1:57 PM Uros Bizjak wrote: > > On Fri, Mar 31, 2023 at 7:11 AM liuhongt wrote: > > > > RA sometimes will use lowest the cost of the mode with all different > > regclasses > > w/o check if it's hard_regno_mode_ok. > > It's impossible to put modes whose size > 8 into

Re: [PATCH] Adjust memory_move_cost for MASK_REGS when MODE_SIZE > 8.

2023-03-30 Thread Uros Bizjak via Gcc-patches
On Fri, Mar 31, 2023 at 7:11 AM liuhongt wrote: > > RA sometimes will use lowest the cost of the mode with all different > regclasses > w/o check if it's hard_regno_mode_ok. > It's impossible to put modes whose size > 8 into MASK_REGS, ajdust the cost to > avoid potential performance issue. I

[PATCH] Adjust memory_move_cost for MASK_REGS when MODE_SIZE > 8.

2023-03-30 Thread liuhongt via Gcc-patches
RA sometimes will use lowest the cost of the mode with all different regclasses w/o check if it's hard_regno_mode_ok. It's impossible to put modes whose size > 8 into MASK_REGS, ajdust the cost to avoid potential performance issue. Bootstrapped and regtested on x86_64-pc-linux-gnu{-m32,}. Ok for