ir_to_mesa: Implement ir_binop_any_nequal using DP4 w/saturate or DP4 w/SLT

The operation ir_binop_any_nequal is (a.x != b.x) || (a.y != b.y) ||
(a.z != b.z) || (a.w != b.w), and that is the same as any(bvec4(a.x !=
b.x, a.y != b.y, a.z != b.z, a.w != b.w)).  Implement the any() part
the same way the regular ir_unop_any is implemented.

Reviewed-by: Eric Anholt <eric@anholt.net>

diff --git a/src/mesa/program/ir_to_mesa.cpp b/src/mesa/program/ir_to_mesa.cpp
index 1bd9a2eee1b73a8a2a469a6e9f318e75b79dbf34..1c674ea8756f7fb4c24229fec4279a6092f9afb2 100644 (file)
--- a/src/mesa/program/ir_to_mesa.cpp
+++ b/src/mesa/program/ir_to_mesa.cpp
@@ -1249,8 +1249,26 @@ ir_to_mesa_visitor::visit(ir_expression *ir)
          ir->operands[1]->type->is_vector()) {
         src_reg temp = get_temp(glsl_type::vec4_type);
         emit(ir, OPCODE_SNE, dst_reg(temp), op[0], op[1]);
-        emit_dp(ir, result_dst, temp, temp, vector_elements);
-        emit(ir, OPCODE_SNE, result_dst, result_src, src_reg_for_float(0.0));
+
+        /* After the dot-product, the value will be an integer on the
+         * range [0,4].  Zero stays zero, and positive values become 1.0.
+         */
+        ir_to_mesa_instruction *const dp =
+           emit_dp(ir, result_dst, temp, temp, vector_elements);
+        if (this->prog->Target == GL_FRAGMENT_PROGRAM_ARB) {
+           /* The clamping to [0,1] can be done for free in the fragment
+            * shader with a saturate.
+            */
+           dp->saturate = true;
+        } else {
+           /* Negating the result of the dot-product gives values on the range
+            * [-4, 0].  Zero stays zero, and negative values become 1.0.  This
+            * achieved using SLT.
+            */
+           src_reg slt_src = result_src;
+           slt_src.negate = ~slt_src.negate;
+           emit(ir, OPCODE_SLT, result_dst, slt_src, src_reg_for_float(0.0));
+        }
       } else {
         emit(ir, OPCODE_SNE, result_dst, op[0], op[1]);
       }