[PATCH] Fix PR69274, 435.gromacs performance regression due to RA
Fri Feb 5 12:32:00 GMT 2016
On 02/05/2016 01:10 PM, Richard Biener wrote:
> It fails
> FAIL: gcc.target/i386/addr-sel-1.c scan-assembler b\\\\+1
> on i?86 (or x86_64 -m32) though, generating
> movl 4(%esp), %eax
> leal 1(%eax), %edx
> movsbl a+1(%eax), %eax
> movsbl b(%edx), %edx
> addl %edx, %eax
Well, it looks like the first movsbl load clobbers the potentially
better base register, so trivial propagation doesn't work.
It might be another case where allowing 2->2 in combine would help. Or
enabling -frename-registers and rerunning reload_combine afterwards.
More information about the Gcc-patches