nir/opt_peephole_select: Don't try to remove flow control around indirect loads

That flow control may be trying to avoid invalid loads.  On at least
some platforms, those loads can also be expensive.

No shader-db changes on any Intel platform (even with the later patch
"intel/compiler: More peephole select").

v2: Add a 'indirect_load_ok' flag to nir_opt_peephole_select.  Suggested
by Rob.  See also the big comment in src/intel/compiler/brw_nir.c.

v3: Use nir_deref_instr_has_indirect instead of deref_has_indirect (from
nir_lower_io_arrays_to_elements.c).

v4: Fix inverted condition in brw_nir.c.  Noticed by Lionel.

Signed-off-by: Ian Romanick <ian.d.romanick@intel.com>
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>

src/intel/compiler/brw_nir.c

@@ -568,7 +568,18 @@ brw_nir_optimize(nir_shader *nir, const struct brw_compiler *compiler,
       OPT(nir_copy_prop);
       OPT(nir_opt_dce);
       OPT(nir_opt_cse);
-      OPT(nir_opt_peephole_select, 0);
+
+      /* For indirect loads of uniforms (push constants), we assume that array
+       * indices will nearly always be in bounds and the cost of the load is
+       * low.  Therefore there shouldn't be a performance benefit to avoid it.
+       * However, in vec4 tessellation shaders, these loads operate by
+       * actually pulling from memory.
+       */
+      const bool is_vec4_tessellation = !is_scalar &&
+         (nir->info.stage == MESA_SHADER_TESS_CTRL ||
+          nir->info.stage == MESA_SHADER_TESS_EVAL);
+      OPT(nir_opt_peephole_select, 0, !is_vec4_tessellation);
+
       OPT(nir_opt_intrinsics);
       OPT(nir_opt_idiv_const, 32);
       OPT(nir_opt_algebraic);