Re: [Qemu-devel] [PATCH 10/14] i386: use inverted setcond when computing NS or NZ

2012-10-09 Thread Richard Henderson
On 10/06/2012 05:30 AM, Paolo Bonzini wrote: > Make gen_compute_eflags_z and gen_compute_eflags_s able to compute the > inverted condition, and use this in gen_setcc_slow_T0. We cannot do it > yet in gen_compute_eflags_c, but prepare the code for it anyway. It is > not worthwhile for PF, as usual

Re: [Qemu-devel] [PATCH 10/14] i386: use inverted setcond when computing NS or NZ

2012-10-07 Thread Blue Swirl
On Sat, Oct 6, 2012 at 12:30 PM, Paolo Bonzini wrote: > Make gen_compute_eflags_z and gen_compute_eflags_s able to compute the > inverted condition, and use this in gen_setcc_slow_T0. We cannot do it > yet in gen_compute_eflags_c, but prepare the code for it anyway. It is > not worthwhile for PF

[Qemu-devel] [PATCH 10/14] i386: use inverted setcond when computing NS or NZ

2012-10-06 Thread Paolo Bonzini
Make gen_compute_eflags_z and gen_compute_eflags_s able to compute the inverted condition, and use this in gen_setcc_slow_T0. We cannot do it yet in gen_compute_eflags_c, but prepare the code for it anyway. It is not worthwhile for PF, as usual. shr+and+xor could be replaced by and+setcond. I'm