Re: [Qemu-devel] [PATCH] target-ppc: optimize cmp translation

2017-12-18 Thread Richard Henderson
On 12/16/2017 09:49 PM, Paolo Bonzini wrote: > We know that only one bit (in addition to SO) is going to be set in > the condition register, so do two movconds instead of three setconds, > three shifts and two ORs. > > For ppc64-linux-user, the code size reduction is around 5% and the > performanc

Re: [Qemu-devel] [PATCH] target-ppc: optimize cmp translation

2017-12-17 Thread David Gibson
On Sun, Dec 17, 2017 at 06:49:53AM +0100, Paolo Bonzini wrote: > We know that only one bit (in addition to SO) is going to be set in > the condition register, so do two movconds instead of three setconds, > three shifts and two ORs. > > For ppc64-linux-user, the code size reduction is around 5% an

[Qemu-devel] [PATCH] target-ppc: optimize cmp translation

2017-12-16 Thread Paolo Bonzini
We know that only one bit (in addition to SO) is going to be set in the condition register, so do two movconds instead of three setconds, three shifts and two ORs. For ppc64-linux-user, the code size reduction is around 5% and the performance improvement slightly less than 10%. For softmmu, the i