i965/vp: Use the sampler for pull constant loads on Gen7/7.5.

This improves performance in Trine 2 at 1280x720 (windowed) on "Very
High" settings by 30% (in the interactive menu) to 45% (in the forest
by the giant frog) on Haswell GT3e.

It also now generates the same assembly on Gen7 as it does on Gen8,
which always used the sampler for both types.

Signed-off-by: Kenneth Graunke <kenneth@whitecape.org>
Reviewed-by: Chris Forbes <chrisf@ijw.co.nz>
Reviewed-by: Matt Turner <mattst88@gmail.com>

diff --git a/src/mesa/drivers/dri/i965/brw_vec4_vp.cpp b/src/mesa/drivers/dri/i965/brw_vec4_vp.cpp
index f9c23cae2bf0cbda590f645dd74b36cde8186b24..f88a3718301036a3cdac5827e3899da4e3d881f3 100644 (file)
--- a/src/mesa/drivers/dri/i965/brw_vec4_vp.cpp
+++ b/src/mesa/drivers/dri/i965/brw_vec4_vp.cpp
@@ -545,11 +545,18 @@ vec4_vs_visitor::get_vp_src_reg(const prog_src_register &src)
 
          result = src_reg(this, glsl_type::vec4_type);
          src_reg surf_index = src_reg(unsigned(prog_data->base.binding_table.pull_constants_start));
-         vec4_instruction *load =
-            new(mem_ctx) vec4_instruction(this, VS_OPCODE_PULL_CONSTANT_LOAD,
-                                          dst_reg(result), surf_index, reladdr);
-         load->base_mrf = 14;
-         load->mlen = 1;
+         vec4_instruction *load;
+         if (brw->gen >= 7) {
+            load = new(mem_ctx)
+               vec4_instruction(this, VS_OPCODE_PULL_CONSTANT_LOAD_GEN7,
+                                dst_reg(result), surf_index, reladdr);
+         } else {
+            load = new(mem_ctx)
+               vec4_instruction(this, VS_OPCODE_PULL_CONSTANT_LOAD,
+                                dst_reg(result), surf_index, reladdr);
+            load->base_mrf = 14;
+            load->mlen = 1;
+         }
          emit(load);
          break;
       }