summaryrefslogtreecommitdiffstats
path: root/src
diff options
context:
space:
mode:
authorMarek Olšák <[email protected]>2016-06-03 16:20:17 +0200
committerMarek Olšák <[email protected]>2016-06-06 22:50:55 +0200
commit991cbfcb1459f3adce13d70c383f9c4c6fd4ee96 (patch)
treee599581baf980c8911339f902552600b33e77541 /src
parent2802310c256d599d80397a590fd32386bad03fe6 (diff)
radeonsi: add a performance tweak for 4 SE parts
Ported from Vulkan. Reviewed-by: Nicolai Hähnle <[email protected]>
Diffstat (limited to 'src')
-rw-r--r--src/gallium/drivers/radeonsi/si_state_draw.c11
1 files changed, 11 insertions, 0 deletions
diff --git a/src/gallium/drivers/radeonsi/si_state_draw.c b/src/gallium/drivers/radeonsi/si_state_draw.c
index aed509de9bb..0a85d5a0ca3 100644
--- a/src/gallium/drivers/radeonsi/si_state_draw.c
+++ b/src/gallium/drivers/radeonsi/si_state_draw.c
@@ -308,6 +308,17 @@ static unsigned si_get_ia_multi_vgt_param(struct si_context *sctx,
(info->indirect || info->instance_count > 1))
wd_switch_on_eop = true;
+ /* Performance recommendation for 4 SE Gfx7-8 parts if
+ * instances are smaller than a primgroup. Ignore the fact
+ * primgroup_size is a primitive count, not vertex count.
+ * Don't do anything for indirect draws.
+ */
+ if (sctx->b.chip_class <= VI &&
+ sctx->b.screen->info.max_se >= 4 &&
+ !info->indirect &&
+ info->instance_count > 1 && info->count < primgroup_size)
+ wd_switch_on_eop = true;
+
/* Required on CIK and later. */
if (sctx->b.screen->info.max_se > 2 && !wd_switch_on_eop)
ia_switch_on_eoi = true;