i965/fs: Add support for shadow comparitors with gather4

Note that gather4_po_c's parameters are too long for SIMD16. It might be
worth emitting 2xSIMD8 messages in this case at some point.

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

diff --git a/src/mesa/drivers/dri/i965/brw_fs_generator.cpp b/src/mesa/drivers/dri/i965/brw_fs_generator.cpp
index 6b9f70b..853120d 100644 (file)
--- a/src/mesa/drivers/dri/i965/brw_fs_generator.cpp
+++ b/src/mesa/drivers/dri/i965/brw_fs_generator.cpp
@@ -435,12 +435,21 @@ fs_generator::generate_tex(fs_inst *inst, struct brw_reg dst, struct brw_reg src
          msg_type = GEN5_SAMPLER_MESSAGE_LOD;
          break;
       case SHADER_OPCODE_TG4:
-         assert(brw->gen >= 6);
-         msg_type = GEN7_SAMPLER_MESSAGE_SAMPLE_GATHER4;
+         if (inst->shadow_compare) {
+            assert(brw->gen >= 7);
+            msg_type = GEN7_SAMPLER_MESSAGE_SAMPLE_GATHER4_C;
+         } else {
+            assert(brw->gen >= 6);
+            msg_type = GEN7_SAMPLER_MESSAGE_SAMPLE_GATHER4;
+         }
          break;
       case SHADER_OPCODE_TG4_OFFSET:
          assert(brw->gen >= 7);
-         msg_type = GEN7_SAMPLER_MESSAGE_SAMPLE_GATHER4_PO;
+         if (inst->shadow_compare) {
+            msg_type = GEN7_SAMPLER_MESSAGE_SAMPLE_GATHER4_PO_C;
+         } else {
+            msg_type = GEN7_SAMPLER_MESSAGE_SAMPLE_GATHER4_PO;
+         }
          break;
       default:
         assert(!"not reached");

diff --git a/src/mesa/drivers/dri/i965/brw_fs_visitor.cpp b/src/mesa/drivers/dri/i965/brw_fs_visitor.cpp
index 314fe2a..1d2da8c 100644 (file)
--- a/src/mesa/drivers/dri/i965/brw_fs_visitor.cpp
+++ b/src/mesa/drivers/dri/i965/brw_fs_visitor.cpp
@@ -1359,6 +1359,9 @@ fs_visitor::emit_texture_gen7(ir_texture *ir, fs_reg dst, fs_reg coordinate,
       break;
    case ir_tg4:
       if (has_nonconstant_offset) {
+         if (ir->shadow_comparitor && dispatch_width == 16)
+            fail("Gen7 does not support gather4_po_c in SIMD16 mode.");
+
          /* More crazy intermixing */
          ir->offset->accept(this);
          fs_reg offset_value = this->result;