On May 7, 2015 5:38 PM, "Ian Romanick" <<a href="mailto:idr@freedesktop.org">idr@freedesktop.org</a>> wrote: > > On 05/07/2015 04:50 PM, Jason Ekstrand wrote: > > GLSL IR vs. NIR shader-db results for SIMD8 vertex shaders on Broadwell: > > > > total instructions in shared programs: 2724483 -> 2711790 (-0.47%) > > instructions in affected programs: 1860859 -> 1848166 (-0.68%) > > helped: 4387 > > HURT: 4758 > > GAINED: 1499 > > > > The gained programs are ARB vertext programs that were previously going > > through the vec4 backend. Now that we have prog_to_nir, ARB vertex > > programs can go through the scalar backend so they show up as "gained" in > > the shader-db results. > > I thought we already did this... why didn't this happen when NIR became > the default for the FS backend? And has that reason (assuming there was > one) been resolved? We couldn't do copy propagation of values in the attribute register file. That, it turn was blocked on reworking the LOAD_PAYLOAD instruction. I pushed a series this morning that fixed both of those and cut 7.5% off of all SIMD8 VS instructions when using NIR. It also helps GLSL IR but by only 1% or so. --Jason > > --- > > src/mesa/drivers/dri/i965/brw_context.c | 2 +- > > 1 file changed, 1 insertion(+), 1 deletion(-) > > > > diff --git a/src/mesa/drivers/dri/i965/brw_context.c b/src/mesa/drivers/dri/i965/brw_context.c > > index fd7420a..8615e5e 100644 > > --- a/src/mesa/drivers/dri/i965/brw_context.c > > +++ b/src/mesa/drivers/dri/i965/brw_context.c > > @@ -588,7 +588,7 @@ brw_initialize_context_constants(struct brw_context *brw) > > ctx->Const.ShaderCompilerOptions[MESA_SHADER_VERTEX].EmitNoIndirectTemp = true; > > ctx->Const.ShaderCompilerOptions[MESA_SHADER_VERTEX].OptimizeForAOS = false; > > > > - if (brw_env_var_as_boolean("INTEL_USE_NIR", false)) > > + if (brw_env_var_as_boolean("INTEL_USE_NIR", true)) > > ctx->Const.ShaderCompilerOptions[MESA_SHADER_VERTEX].NirOptions = &nir_options; > > } > > >