Mesa (master): nir: Allow vec2/vec3/ vec4 instructions in the select peephole pass.

[Kenneth Graunke]

Module: Mesa
Branch: master
Commit: 1762568fd39b9be42d963d335e36daea25df7044
URL:    http://cgit.freedesktop.org/mesa/mesa/commit/?id=1762568fd39b9be42d963d335e36daea25df7044

Author: Kenneth Graunke <kenneth at whitecape.org>
Date:   Wed Jun 10 00:52:07 2015 -0700

nir: Allow vec2/vec3/vec4 instructions in the select peephole pass.

These are basically just moves, so they should be safe as well.

When disabling i965's GLSL IR level scalarizer (channel expressions)
pass, I started seeing NIR code like this:

        if ssa_21 {
                block block_1:
                /* preds: block_0 */
                vec4 ssa_120 = vec4 ssa_82, ssa_83, ssa_84, ssa_30
                /* succs: block_3 */
        } else {
                block block_2:
                /* preds: block_0 */
                /* succs: block_3 */
        }
        block block_3:
        /* preds: block_1 block_2 */
        vec4 ssa_33 = phi block_1: ssa_120, block_2: ssa_2

Previously, the GLSL IR scalarizer pass would break the vec4 into a
series of fmovs, which were allowed by the peephole pass.  But with
the vec4 operation, they were not.  We want to keep getting selects.

Normal i965 on Broadwell:
instructions in affected programs:     200 -> 176 (-12.00%)
helped:                                4

With brw_fs_channel_expressions() disabled:
instructions in affected programs:     1832 -> 1646 (-10.15%)
helped:                                30

Signed-off-by: Kenneth Graunke <kenneth at whitecape.org>
Reviewed-by: Jason Ekstrand <jason.ekstrand at intel.com>
Reviewed-by: Connor Abbott <cwabbott0 at gmail.com>

---

 src/glsl/nir/nir_opt_peephole_select.c |    4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/src/glsl/nir/nir_opt_peephole_select.c b/src/glsl/nir/nir_opt_peephole_select.c
index 82c65bb..ef7c977 100644
--- a/src/glsl/nir/nir_opt_peephole_select.c
+++ b/src/glsl/nir/nir_opt_peephole_select.c
@@ -86,7 +86,9 @@ block_check_for_allowed_instrs(nir_block *block)
          nir_alu_instr *mov = nir_instr_as_alu(instr);
          if (mov->op != nir_op_fmov && mov->op != nir_op_imov &&
              mov->op != nir_op_fneg && mov->op != nir_op_ineg &&
-             mov->op != nir_op_fabs && mov->op != nir_op_iabs)
+             mov->op != nir_op_fabs && mov->op != nir_op_iabs &&
+             mov->op != nir_op_vec2 && mov->op != nir_op_vec3 &&
+             mov->op != nir_op_vec4)
             return false;
 
          /* Can't handle saturate */