i965/vec4: Change vec4_visitor::emit_lrp to use MAC for gen<6

This allows us to emit ADD/MUL/MAC instead of MUL/ADD/MUL/ADD,
saving one instruction and two temporary registers.

Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Reviewed-by: Matt Turner <mattst88@gmail.com>
Signed-off-by: Juha-Pekka Heikkila <juhapekka.heikkila@gmail.com>

diff --git a/src/mesa/drivers/dri/i965/brw_vec4_visitor.cpp b/src/mesa/drivers/dri/i965/brw_vec4_visitor.cpp
index 059dc73..8fa0aee 100644 (file)
--- a/src/mesa/drivers/dri/i965/brw_vec4_visitor.cpp
+++ b/src/mesa/drivers/dri/i965/brw_vec4_visitor.cpp
@@ -1165,24 +1165,14 @@ vec4_visitor::emit_lrp(const dst_reg &dst,
    } else {
       /* Earlier generations don't support three source operations, so we
        * need to emit x*(1-a) + y*a.
-       *
-       * A better way to do this would be:
-       *    ADD one_minus_a, negate(a), 1.0f
-       *    MUL null, y, a
-       *    MAC dst, x, one_minus_a
-       * but we would need to support MAC and implicit accumulator.
        */
-      dst_reg y_times_a           = dst_reg(this, glsl_type::vec4_type);
-      dst_reg one_minus_a         = dst_reg(this, glsl_type::vec4_type);
-      dst_reg x_times_one_minus_a = dst_reg(this, glsl_type::vec4_type);
-      y_times_a.writemask           = dst.writemask;
-      one_minus_a.writemask         = dst.writemask;
-      x_times_one_minus_a.writemask = dst.writemask;
-
-      emit(MUL(y_times_a, y, a));
+      dst_reg one_minus_a   = dst_reg(this, glsl_type::vec4_type);
+      one_minus_a.writemask = dst.writemask;
+
       emit(ADD(one_minus_a, negate(a), src_reg(1.0f)));
-      emit(MUL(x_times_one_minus_a, x, src_reg(one_minus_a)));
-      emit(ADD(dst, src_reg(x_times_one_minus_a), src_reg(y_times_a)));
+      vec4_instruction *mul = emit(MUL(dst_null_f(), y, a));
+      mul->writes_accumulator = true;
+      emit(MAC(dst, x, src_reg(one_minus_a)));
    }
 }