ir_to_mesa: Implement ir_binop_all_equal using DP4 w/SGE

The operation ir_binop_all_equal is !(a.x != b.x || a.y != b.y || a.z
!= b.z || a.w != b.w).  Logical-or is implemented using addition
(followed by clampling to [0,1]) on values of 0.0 and 1.0.  Replacing
the logical-or operators with addition gives !bool((int(a.x != b.x) +
int(a.y == b.y) + int(a.z == b.z) + int(a.w == b.w)).  This can be
implemented using a dot-product with a vector of all 1.0.  After the
dot-product, the value will be an integer on the range [0,4].

Previously a SEQ instruction was used to clamp the resulting logic
value to [0,1] and invert the result.  Using an SGE instruction on the
negation of the dot-product result has the same effect.  Many older
shader architectures do not support the SEQ instruction.  It must be
emulated using two SGE instructions and a MUL.  On these
architectures, the single SGE saves two instructions.

Reviewed-by: Eric Anholt <[email protected]>

1 files changed, 12 insertions, 1 deletions

diff --git a/src/mesa/program/ir_to_mesa.cpp b/src/mesa/program/ir_to_mesa.cpp
index 1c674ea8756..4c8b097de6b 100644
--- a/src/mesa/program/ir_to_mesa.cpp
+++ b/src/mesa/program/ir_to_mesa.cpp
@@ -1237,8 +1237,19 @@ 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]);
+
+	 /* After the dot-product, the value will be an integer on the
+	  * range [0,4].  Zero becomes 1.0, and positive values become zero.
+	  */
 	 emit_dp(ir, result_dst, temp, temp, vector_elements);
-	 emit(ir, OPCODE_SEQ, result_dst, result_src, src_reg_for_float(0.0));
+
+	 /* Negating the result of the dot-product gives values on the range
+	  * [-4, 0].  Zero becomes 1.0, and negative values become zero.  This
+	  * achieved using SGE.
+	  */
+	 src_reg sge_src = result_src;
+	 sge_src.negate = ~sge_src.negate;
+	 emit(ir, OPCODE_SGE, result_dst, sge_src, src_reg_for_float(0.0));
       } else {
 	 emit(ir, OPCODE_SEQ, result_dst, op[0], op[1]);
       }