From 1a57717bbe8a2cedf2e1bb72cfd7ec85cd2350fc Mon Sep 17 00:00:00 2001 From: Eric Anholt Date: Mon, 21 Feb 2011 23:46:52 -0800 Subject: i965: Apply a workaround for the Ironlake "vertex flashing". This is an awful hack and will hurt performance on Ironlake, but we're at a loss as to what's going wrong otherwise. This is the only common variable we've found that avoids the problem on 4 applications (CelShading, gnome-shell, Pill Popper, and my GLSL demo), while other variables we've tried appear to only be confounding. Neither the specifications nor the hardware team have been able to provide any enlightenment, despite much searching. https://bugs.freedesktop.org/show_bug.cgi?id=29172 Tested by: Chris Lord (Pill Popper) Tested by: Ryan Lortie (gnome-shell) --- src/mesa/drivers/dri/i965/brw_vs_state.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) (limited to 'src/mesa/drivers') diff --git a/src/mesa/drivers/dri/i965/brw_vs_state.c b/src/mesa/drivers/dri/i965/brw_vs_state.c index be92313861..c3a7cc247c 100644 --- a/src/mesa/drivers/dri/i965/brw_vs_state.c +++ b/src/mesa/drivers/dri/i965/brw_vs_state.c @@ -96,7 +96,14 @@ vs_unit_create_from_key(struct brw_context *brw, struct brw_vs_unit_key *key) * and those dwords will be written to the second URB handle when we * brw_urb_WRITE() results. */ - vs.thread1.single_program_flow = 0; + /* Disable single program flow on Ironlake. We cannot reliably get + * all applications working without it. See: + * https://bugs.freedesktop.org/show_bug.cgi?id=29172 + * + * The most notable and reliably failing application is the Humus + * demo "CelShading" + */ + vs.thread1.single_program_flow = (intel->gen == 5); if (intel->gen == 5) vs.thread1.binding_table_entry_count = 0; /* hardware requirement */ -- cgit v1.2.3