From 5e3edd4b2891d839d440f58053f7207fc71554f4 Mon Sep 17 00:00:00 2001 From: Kenneth Graunke Date: Thu, 7 Jan 2016 15:45:21 -0800 Subject: [PATCH] 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 Reviewed-by: Matt Turner Cc: mesa-stable@lists.freedesktop.org --- src/glsl/ir.h | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/src/glsl/ir.h b/src/glsl/ir.h index a728c03..93e0734 100644 --- 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; } /** -- 2.7.4