[Mesa-stable] [PATCH 2/4] i965/vec4: Handle ir_triop_lrp on Gen4-5 as well.

[Kenneth Graunke]

When the vec4 backend encountered an ir_triop_lrp, it always emitted an
actual LRP instruction, which only exists on Gen6+.  Gen4-5 used
lower_instructions() to decompose ir_triop_lrp at the IR level.

Since commit 8d37e9915a3b21 ("glsl: Optimize open-coded lrp into lrp."),
we've had an bug where lower_instructions translates ir_triop_lrp into
arithmetic, but opt_algebraic reassembles it back into a lrp.

To avoid this ordering concern, just handle ir_triop_lrp in the backend.
The FS backend already does this, so we may as well do likewise.

Cc: "10.1" <mesa-stable at lists.freedesktop.org>
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=75253
Signed-off-by: Kenneth Graunke <kenneth at whitecape.org>
---
 src/mesa/drivers/dri/i965/brw_vec4.h           |  3 +++
 src/mesa/drivers/dri/i965/brw_vec4_visitor.cpp | 36 +++++++++++++++++++++-----
 2 files changed, 32 insertions(+), 7 deletions(-)

This patch fixes a regression from 10.0 to 10.1, and really needs to be
cherry-picked before the final 10.1.0 release.

Technically, it's the only one that needs to be cherry-picked, but I figured
I may as well CC the whole series and leave it up to the stable maintainers.

diff --git a/src/mesa/drivers/dri/i965/brw_vec4.h b/src/mesa/drivers/dri/i965/brw_vec4.h
index 6bd8b80..fb5c0a6 100644
--- a/src/mesa/drivers/dri/i965/brw_vec4.h
+++ b/src/mesa/drivers/dri/i965/brw_vec4.h
@@ -506,6 +506,9 @@ public:
 
    void emit_minmax(uint32_t condmod, dst_reg dst, src_reg src0, src_reg src1);
 
+   void emit_lrp(const dst_reg &dst,
+                 const src_reg &x, const src_reg &y, const src_reg &a);
+
    void emit_block_move(dst_reg *dst, src_reg *src,
 			const struct glsl_type *type, uint32_t predicate);
 
diff --git a/src/mesa/drivers/dri/i965/brw_vec4_visitor.cpp b/src/mesa/drivers/dri/i965/brw_vec4_visitor.cpp
index 95e0064..d4f1899 100644
--- a/src/mesa/drivers/dri/i965/brw_vec4_visitor.cpp
+++ b/src/mesa/drivers/dri/i965/brw_vec4_visitor.cpp
@@ -1132,6 +1132,34 @@ vec4_visitor::emit_minmax(uint32_t conditionalmod, dst_reg dst,
    }
 }
 
+void
+vec4_visitor::emit_lrp(const dst_reg &dst,
+                       const src_reg &x, const src_reg &y, const src_reg &a)
+{
+   if (brw->gen >= 6) {
+      /* Note that the instruction's argument order is reversed from GLSL
+       * and the IR.
+       */
+      emit(LRP(dst,
+               fix_3src_operand(a), fix_3src_operand(y), fix_3src_operand(x)));
+   } else {
+      /* Earlier generations don't support three source operations, so we
+       * need to emit x*(1-a) + y*a.
+       */
+      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));
+      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)));
+   }
+}
+
 static bool
 is_16bit_constant(ir_rvalue *rvalue)
 {
@@ -1628,13 +1656,7 @@ vec4_visitor::visit(ir_expression *ir)
       break;
 
    case ir_triop_lrp:
-      op[0] = fix_3src_operand(op[0]);
-      op[1] = fix_3src_operand(op[1]);
-      op[2] = fix_3src_operand(op[2]);
-      /* Note that the instruction's argument order is reversed from GLSL
-       * and the IR.
-       */
-      emit(LRP(result_dst, op[2], op[1], op[0]));
+      emit_lrp(result_dst, op[0], op[1], op[2]);
       break;
 
    case ir_triop_csel:
-- 
1.9.0