[Mesa-dev] [PATCH 5/7] i965/fs: Don't dead code eliminate CMP(N).

[Matt Turner]

On Tue, Oct 22, 2013 at 1:56 PM, Eric Anholt <eric at anholt.net> wrote:
> Matt Turner <mattst88 at gmail.com> writes:
>
>> An future commit will enable CSE for CMP instructions. It operates on
>> the following code
>>
>>       cmp.ge.f0(8)  null     g45<8,8,1>F  0F
>> (+f0) sel(8)        g50<1>F  g40<8,8,1>F  g10<8,8,1>F
>>       cmp.ge.f0(8)  null     g45<8,8,1>F  0F
>> (+f0) sel(8)        g51<1>F  g41<8,8,1>F  g11<8,8,1>F
>>       cmp.ge.f0(8)  null     g45<8,8,1>F  0F
>> (+f0) sel(8)        g52<1>F  g42<8,8,1>F  g12<8,8,1>F
>>       cmp.ge.f0(8)  null     g45<8,8,1>F  0F
>> (+f0) sel(8)        g53<1>F  g43<8,8,1>F  g13<8,8,1>F
>>
>> by adding a new cmp.ge.f0(8) instruction writing into a GRF destination
>> and replacing the existing compares with MOVs from that destination,
>> leading to:
>>
>>       cmp.ge.f0(8)  g30<1>F  g45<8,8,1>F  0F
>>       mov(8)        null     g30<1>F
>> (+f0) sel(8)        g50<1>F  g40<8,8,1>F  g10<8,8,1>F
>>       mov(8)        null     g30<1>F
>> (+f0) sel(8)        g51<1>F  g41<8,8,1>F  g11<8,8,1>F
>>       mov(8)        null     g30<1>F
>> (+f0) sel(8)        g52<1>F  g42<8,8,1>F  g12<8,8,1>F
>>       mov(8)        null     g30<1>F
>> (+f0) sel(8)        g53<1>F  g43<8,8,1>F  g13<8,8,1>F
>>
>> The next patch will enable dead code elimination of MOVs with a null
>> destination, which in turn would cause the pass to recognize that the
>> new compare's g30 destination is never read and delete the instruction.
>> This would leave the flag register in an unknown state and break the
>> program.
>
> I think we should just not generate the dead MOVs, instead.  It would
> just be a matter of checking for dst.file == GRF when generating the
> temporary, right?

Yes, I think so. I like that plan better, because I've heard something
about null MOVs being necessary for workarounds on gen4 or similar.

I'll send a new patch to replace this one and a revised commit message for 4/7.