diff options
| author | Eric Anholt <[email protected]> | 2012-06-07 08:48:50 -0700 |
|---|---|---|
| committer | Eric Anholt <[email protected]> | 2012-07-03 12:57:10 -0700 |
| commit | dd4282e38fd92c081875da6bce0b2345bd472532 (patch) | |
| tree | 049a9dddc9c9e1e8dfa0ba5dcb653fa66fbaac4c /src/mesa/drivers/dri/i965/brw_fs_copy_propagation.cpp | |
| parent | 0c4630bae001139dea42b78cd08157de4d90542b (diff) | |
i965/fs: Allow copy propagation on uniforms.
This is a big win for savage2, hon and yofrankie. 62 new programs for
savage2/hon get 16-wide mode, along with one for humus demos and two
for tropics. Even a few shaders from tropics see reductions of 15% or
more.
total instructions in shared programs: 216536 -> 207353 (-4.24%)
instructions in affected programs: 123941 -> 114758 (-7.41%)
In benchmarking Tropics, only a .040% +/- 034% performance improvement
was observed (n=90). Rather disappointing, but I was primarily
motivated to do this patch by a regression in the number of 16-wide
shaders compiled after a GRF texturing on IVB patch I'm working on.
Hopefully this helps avoid that regression.
Reviewed-by: Kenneth Graunke <[email protected]>
Diffstat (limited to 'src/mesa/drivers/dri/i965/brw_fs_copy_propagation.cpp')
| -rw-r--r-- | src/mesa/drivers/dri/i965/brw_fs_copy_propagation.cpp | 11 |
1 files changed, 7 insertions, 4 deletions
diff --git a/src/mesa/drivers/dri/i965/brw_fs_copy_propagation.cpp b/src/mesa/drivers/dri/i965/brw_fs_copy_propagation.cpp index a019cb5814c..bf26d86bd7c 100644 --- a/src/mesa/drivers/dri/i965/brw_fs_copy_propagation.cpp +++ b/src/mesa/drivers/dri/i965/brw_fs_copy_propagation.cpp @@ -48,9 +48,11 @@ fs_visitor::try_copy_propagate(fs_inst *inst, int arg, acp_entry *entry) bool has_source_modifiers = entry->src.abs || entry->src.negate; - if (intel->gen == 6 && inst->is_math() && has_source_modifiers) + if (intel->gen == 6 && inst->is_math() && + (has_source_modifiers || entry->src.file == UNIFORM)) return false; + inst->src[arg].file = entry->src.file; inst->src[arg].reg = entry->src.reg; inst->src[arg].reg_offset = entry->src.reg_offset; @@ -121,9 +123,10 @@ fs_visitor::opt_copy_propagate_local(void *mem_ctx, /* If this instruction is a raw copy, add it to the ACP. */ if (inst->opcode == BRW_OPCODE_MOV && inst->dst.file == GRF && - inst->src[0].file == GRF && - (inst->src[0].reg != inst->dst.reg || - inst->src[0].reg_offset != inst->dst.reg_offset) && + ((inst->src[0].file == GRF && + (inst->src[0].reg != inst->dst.reg || + inst->src[0].reg_offset != inst->dst.reg_offset)) || + inst->src[0].file == UNIFORM) && inst->src[0].type == inst->dst.type && !inst->saturate && !inst->predicated && |