Parallel change to "i965/gs: Fix up gl_PointSize input swizzling for
DUAL_INSTANCED gs.", except applied to the gl_PrimitiveID fixup
instead of the gl_PointSize fixup.
---
src/mesa/drivers/dri/i965/brw_vec4_generator.cpp | 18 +++++++++++++++++-
src/mesa/drivers/dri/i965/brw_vec4_gs_visitor.cpp | 10 +++++++++-
2 files changed, 26 insertions(+), 2 deletions(-)
diff --git a/src/mesa/drivers/dri/i965/brw_vec4_generator.cpp
b/src/mesa/drivers/dri/i965/brw_vec4_generator.cpp
index 700da54..07e9697 100644
--- a/src/mesa/drivers/dri/i965/brw_vec4_generator.cpp
+++ b/src/mesa/drivers/dri/i965/brw_vec4_generator.cpp
@@ -876,7 +876,23 @@ vec4_generator::generate_vec4_instruction(vec4_instruction
*instruction,
}
break;
case BRW_OPCODE_ADD:
- brw_ADD(p, dst, src[0], src[1]);
+ if (dst.width == BRW_WIDTH_4) {
+ /* This happens in the geometry shader primitive ID workaround for
+ * "dual instanced" geometry shaders, since they use attributes
+ * (including gl_PrimitiveID) that are vec4's. Since the exec width
+ * is only 4, it's essential that the caller set force_writemask_all
+ * in order to make sure the MOV happens regardless of which channels
+ * are enabled.
+ */
+ assert(inst->force_writemask_all);
+
+ /* To satisfy register region restrictions, the source registers need
+ * a stride of <4;4,1>.
+ */
+ brw_ADD(p, dst, stride(src[0], 4, 4, 1), stride(src[1], 4, 4, 1));
+ } else {
+ brw_ADD(p, dst, src[0], src[1]);
+ }
break;
case BRW_OPCODE_MUL:
brw_MUL(p, dst, src[0], src[1]);
diff --git a/src/mesa/drivers/dri/i965/brw_vec4_gs_visitor.cpp
b/src/mesa/drivers/dri/i965/brw_vec4_gs_visitor.cpp
index 5b823c4..76209b0 100644
--- a/src/mesa/drivers/dri/i965/brw_vec4_gs_visitor.cpp
+++ b/src/mesa/drivers/dri/i965/brw_vec4_gs_visitor.cpp
@@ -149,7 +149,15 @@ vec4_gs_visitor::primitive_id_workaround()
this->current_annotation = "primitive ID workaround";
dst_reg dst(ATTR, VARYING_SLOT_PRIMITIVE_ID);
dst.type = BRW_REGISTER_TYPE_UD;
- emit(ADD(dst, src_reg(dst), src_reg(primitive_id_offset)));
+ vec4_instruction *inst =
+ emit(ADD(dst, src_reg(dst), src_reg(primitive_id_offset)));
+
+ /* In dual instanced dispatch mode, the primitive ID has a width of 4, so
+ * we need to make sure the ADD happens regardless of which channels are
+ * enabled.
+ */
+ inst->force_writemask_all = true;
+
this->current_annotation = NULL;
}
--
1.8.4.1
_______________________________________________
mesa-dev mailing list
mesa-dev@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/mesa-dev
