From 0a0b32319372027a872364f1fcc7b3a5c2e96510 Mon Sep 17 00:00:00 2001 From: Eric Anholt Date: Thu, 2 May 2013 17:44:28 -0700 Subject: i965/fs: Fix test for smearing enabled on an instruction. We were expanding the live range too far, breaking register_coalesce_2() and compute_to_mrf() on 16-wide shaders. Turning it back on improves GLB2.7 performance by 0.239355% +/- 0.0850649% (n=398). shader-db stats are: total instructions in shared programs: 1627211 -> 1609262 (-1.10%) instructions in affected programs: 450351 -> 432402 (-3.99%) While 33 new 16-wide shaders are gained, 70 are lost. Despite that, tropics (the app that lost the most 16-wide) shows a .41% +/- .16% (n=7/8, first-run outlier removed) performance improvement on my HSW. Reviewed-by: Kenneth Graunke --- src/mesa/drivers/dri/i965/brw_fs_live_variables.cpp | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'src/mesa/drivers/dri/i965/brw_fs_live_variables.cpp') diff --git a/src/mesa/drivers/dri/i965/brw_fs_live_variables.cpp b/src/mesa/drivers/dri/i965/brw_fs_live_variables.cpp index 3daf8fa..f5daab2 100644 --- a/src/mesa/drivers/dri/i965/brw_fs_live_variables.cpp +++ b/src/mesa/drivers/dri/i965/brw_fs_live_variables.cpp @@ -216,7 +216,7 @@ fs_visitor::calculate_live_intervals() * pixel_x/pixel_y, which are registers of 16-bit values and thus * would get stomped by the first decode as well. */ - if (dispatch_width == 16 && (inst->src[i].smear || + if (dispatch_width == 16 && (inst->src[i].smear >= 0 || (this->pixel_x.reg == reg || this->pixel_y.reg == reg))) { end_ip++; -- cgit v1.1