On Tue, Oct 1, 2013 at 12:16 PM, Kenneth Graunke <kenn...@whitecape.org> wrote:
> On 09/30/2013 07:16 PM, Ian Romanick wrote:
>> On 09/11/2013 10:00 PM, Chia-I Wu wrote:
>>> From: Chia-I Wu <o...@lunarg.com>
>>>
>>> Replicate the gradient of the top-left pixel to the other three pixels in
>>> the
>>> subspan, as how DDY is implemented. Before, different graidents were used
>>> for
>>> pixels in the top row and pixels in the bottom row.
>>>
>>> This change results in a less accurate approximation. However, it improves
>>> the performance of Xonotic with Ultra settings by 24.3879% +/- 0.832202% (at
>>> 95.0% confidence) on Haswell. No noticeable image quality difference
>>> observed.
>>>
>>> No piglit gpu.tests regressions.
>>>
>>> I failed to come up with an explanation for the performance difference. The
>>> change does not make a difference on Ivy Bridge either. If anyone has the
>>> insight, please kindly enlighten me. Performance differences may also be
>>> observed on other games that call textureGrad and dFdx.
>>
>> After all the experiments and discussions with the hardware guys, lets
>> go ahead and do this. We should do a couple things, however.
>>
>> 1. Disable the optimization if the application explicitly sets
>> GL_FRAGMENT_SHADER_DERIVATIVE_HINT to GL_NICEST.
>
> Urgh...I always hate adding more state-dependent recompiles...
>
> To accomplish this, you'll have to:
> - Add a new high_quality_derivatives flag to brw_wm_prog_key.
> - In brw_wm_populate_key, add:
> /* _NEW_HINT */
> key->high_quality_derivatives =
> ctx->Hint.FragmentShaderDerivative == GL_NICEST;
> - Add the _NEW_HINT dependency to brw_wm_prog's dirty flags.
>
>> 2. Add a driconf option, as suggested by Chris, to disable the optimization.
>
> ...which means changing the key setup to:
>
> if (brw->disable_derivative_optimization) {
> key->high_quality_derivatives =
> ctx->Hint.FragmentShaderDerivative != GL_FASTEST;
> } else {
> key->high_quality_derivatives =
> ctx->Hint.FragmentShaderDerivative == GL_NICEST;
> }
>
> and, in brw_fs_precompile, setting
>
> key->high_quality_derivatives = brw->disable_derivative_optimization;
Thanks for the instructions. I've sent an updated patch with all of
yours and Ian's comments incorporated.
>
> This all seems pretty awful to me...but I guess there's not really any
> getting around it. If the register had worked out, we could've just
> added a Hint() driver hook that programmed it appropriately. But alas.
>
>> 3. Use the same DDX / DDY calculation on all platforms.
>>
>> 4. Update the commit message and the comment in the code with the
>> explanation of the optimization (the HSW sample_d instruction does some
>> optimizations if the same LOD is used for all pixels, etc.).
>>
>>> Signed-off-by: Chia-I Wu <o...@lunarg.com>
>>> ---
>>> src/mesa/drivers/dri/i965/brw_fs_emit.cpp | 17 +++++++++++++----
>>> 1 file changed, 13 insertions(+), 4 deletions(-)
>>>
>>> diff --git a/src/mesa/drivers/dri/i965/brw_fs_emit.cpp
>>> b/src/mesa/drivers/dri/i965/brw_fs_emit.cpp
>>> index bfb3d33..c0d24a0 100644
>>> --- a/src/mesa/drivers/dri/i965/brw_fs_emit.cpp
>>> +++ b/src/mesa/drivers/dri/i965/brw_fs_emit.cpp
>>> @@ -564,16 +564,25 @@ fs_generator::generate_tex(fs_inst *inst, struct
>>> brw_reg dst, struct brw_reg src
>>> void
>>> fs_generator::generate_ddx(fs_inst *inst, struct brw_reg dst, struct
>>> brw_reg src)
>>> {
>>> + /* approximate with ((ss0.tr - ss0.tl)x4 (ss1.tr - ss1.tl)x4) on
>>> Haswell,
>>> + * which gives much better performance when the result is used with
>>> + * sample_d
>>> + */
>>> + unsigned vstride = (brw->is_haswell) ? BRW_VERTICAL_STRIDE_4 :
>>> + BRW_VERTICAL_STRIDE_2;
>>> + unsigned width = (brw->is_haswell) ? BRW_WIDTH_4 :
>>> + BRW_WIDTH_2;
>>> +
>>> struct brw_reg src0 = brw_reg(src.file, src.nr, 1,
>>> BRW_REGISTER_TYPE_F,
>>> - BRW_VERTICAL_STRIDE_2,
>>> - BRW_WIDTH_2,
>>> + vstride,
>>> + width,
>>> BRW_HORIZONTAL_STRIDE_0,
>>> BRW_SWIZZLE_XYZW, WRITEMASK_XYZW);
>>> struct brw_reg src1 = brw_reg(src.file, src.nr, 0,
>>> BRW_REGISTER_TYPE_F,
>>> - BRW_VERTICAL_STRIDE_2,
>>> - BRW_WIDTH_2,
>>> + vstride,
>>> + width,
>>> BRW_HORIZONTAL_STRIDE_0,
>>> BRW_SWIZZLE_XYZW, WRITEMASK_XYZW);
>>> brw_ADD(p, dst, src0, negate(src1));
>>>
>>
>> _______________________________________________
>> mesa-dev mailing list
>> mesa-dev@lists.freedesktop.org
>> http://lists.freedesktop.org/mailman/listinfo/mesa-dev
>>
>
--
o...@lunarg.com
_______________________________________________
mesa-dev mailing list
mesa-dev@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/mesa-dev
