From d6a41b5f70b9071cca8959afab66a6504e7cb7ce Mon Sep 17 00:00:00 2001 From: Kenneth Graunke Date: Fri, 25 Sep 2015 08:21:57 -0700 Subject: [PATCH] i965/gs: Optimize away the EOT write on Gen8+ with static vertex count. With static vertex counts, the final EOT write doesn't actually write any data - it's just there to end the thread. Typically, the last thing before ending the thread will be an EmitVertex() call, resulting in a URB write. We can just set EOT on that. Note that this isn't always possible - there might be an intervening SSBO write/image store, or the URB write may have been in a loop. shader-db statistics for geometry shaders only: total instructions in shared programs: 3173 -> 3149 (-0.76%) instructions in affected programs: 176 -> 152 (-13.64%) helped: 8 Signed-off-by: Kenneth Graunke Reviewed-by: Matt Turner --- src/mesa/drivers/dri/i965/brw_vec4_gs_visitor.cpp | 15 +++++++++++++++ 1 file changed, 15 insertions(+) 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 acf0501399c..d2edc5782fd 100644 --- a/src/mesa/drivers/dri/i965/brw_vec4_gs_visitor.cpp +++ b/src/mesa/drivers/dri/i965/brw_vec4_gs_visitor.cpp @@ -236,6 +236,21 @@ vec4_gs_visitor::emit_thread_end() bool static_vertex_count = c->prog_data.static_vertex_count != -1; + /* If the previous instruction was a URB write, we don't need to issue + * a second one - we can just set the EOT bit on the previous write. + * + * Skip this on Gen8+ unless there's a static vertex count, as we also + * need to write the vertex count out, and combining the two may not be + * possible (or at least not straightforward). + */ + vec4_instruction *last = (vec4_instruction *) instructions.get_tail(); + if (last && last->opcode == GS_OPCODE_URB_WRITE && + !(INTEL_DEBUG & DEBUG_SHADER_TIME) && + devinfo->gen >= 8 && static_vertex_count) { + last->urb_write_flags = BRW_URB_WRITE_EOT | last->urb_write_flags; + return; + } + current_annotation = "thread end"; dst_reg mrf_reg(MRF, base_mrf); src_reg r0(retype(brw_vec8_grf(0, 0), BRW_REGISTER_TYPE_UD)); -- 2.30.2