glsl: Make bitfield_insert/extract and bfi/bfm non-vectorizable.

Currently, opt_vectorize() tries to combine:

    result.x = bitfieldInsert(src0.x, src1.x, src2.x, src3.x);
    result.y = bitfieldInsert(src0.y, src1.y, src2.y, src3.y);
    result.z = bitfieldInsert(src0.z, src1.z, src2.z, src3.z);
    result.w = bitfieldInsert(src0.w, src1.w, src2.w, src3.w);

into a single ir_quadop_bitfield_insert opcode, which operates on
ivec4s.  However, GLSL IR's opcodes currently require the bits and
offset parameters to be scalar integers.  So, this breaks.

We want to be able to vectorize this eventually, but for now, just
chicken out and make opt_vectorize() bail by marking all the bitfield
insert/extract related opcodes as horizontal.  This is a relatively
uncommon case today, so we'll do the simple fix for stable branches,
and fix it properly on master.

Fixes assertion failures when compiling Shadow of Mordor vertex shaders
on i965 in vec4 mode (where OptimizeForAOS enables opt_vectorize()).

Signed-off-by: Kenneth Graunke <kenneth@whitecape.org>
Reviewed-by: Matt Turner <mattst88@gmail.com>
Cc: mesa-stable@lists.freedesktop.org

diff --git a/src/glsl/ir.h b/src/glsl/ir.h
index a728c036e6b7382145a32f2335b2c3e3243dfde0..93e07343559280e1b3719ed47a9650ee6f580ce1 100644 (file)
--- a/src/glsl/ir.h
+++ b/src/glsl/ir.h
@@ -1726,7 +1726,12 @@ public:
              operation == ir_binop_dot ||
              operation == ir_binop_vector_extract ||
              operation == ir_triop_vector_insert ||
-             operation == ir_quadop_vector;
+             operation == ir_quadop_vector ||
+             /* TODO: these can't currently be vectorized */
+             operation == ir_quadop_bitfield_insert ||
+             operation == ir_triop_bitfield_extract ||
+             operation == ir_triop_bfi ||
+             operation == ir_binop_bfm;
    }
 
    /**