[Mesa-dev] [PATCH] i965: Avoid dependency hints on math opcodes

[Ian Romanick]

On 02/12/2014 06:59 PM, Matt Turner wrote:
> On Wed, Feb 12, 2014 at 4:24 PM,  <mike at lunarg.com> wrote:
>> From: Mike Stroyan <mike at LunarG.com>
>>
>>   Putting NoDDClr and NoDDChk dependency control on instruction
>> sequences that include math opcodes can cause corruption of channels.
>> Treat math opcodes like send opcodes and suppress dependency hinting.
>>
>> Signed-off-by: Mike Stroyan <mike at LunarG.com>
>> Tested-by: Tony Bertapelli <anthony.p.bertapelli at intel.com>
>> ---
>>  src/mesa/drivers/dri/i965/brw_vec4.cpp | 8 ++++++++
>>  1 file changed, 8 insertions(+)
>>
>> diff --git a/src/mesa/drivers/dri/i965/brw_vec4.cpp b/src/mesa/drivers/dri/i965/brw_vec4.cpp
>> index dd23ed4..1c42ca8 100644
>> --- a/src/mesa/drivers/dri/i965/brw_vec4.cpp
>> +++ b/src/mesa/drivers/dri/i965/brw_vec4.cpp
>> @@ -717,6 +717,14 @@ vec4_visitor::opt_set_dependency_control()
>>              continue;
>>           }
>>
>> +         /* Dependency control does not work well over math instructions.
>> +          */
>> +         if (inst->is_math()) {
>> +            memset(last_grf_write, 0, sizeof(last_grf_write));
>> +            memset(last_mrf_write, 0, sizeof(last_mrf_write));
>> +            continue;
>> +         }
>> +
>>           /* Now, see if we can do dependency control for this instruction
>>            * against a previous one writing to its destination.
>>            */
>> --
>> 1.8.3.2
> 
> I can't find any mention of this in the PRMs. Do we have a bug report
> or something that this fixes?

We have some code involving a lot of inversesqrt calls that I haven't
quite turned into a shader_runner test yet... I also wonder if this
could be related to the Dota2 too-much-specular bug, but I haven't tried
that out yet either.

> _______________________________________________
> mesa-dev mailing list
> mesa-dev at lists.freedesktop.org
> http://lists.freedesktop.org/mailman/listinfo/mesa-dev