Mesa (master): i965/cnl: Don't write to Cache Mode Register 1 on gen10+

Anuj Phogat aphogat at kemper.freedesktop.org
Fri Jun 23 18:20:34 UTC 2017


Module: Mesa
Branch: master
Commit: b98055330932a19997e68f2c935b0c7dfd90d9c1
URL:    http://cgit.freedesktop.org/mesa/mesa/commit/?id=b98055330932a19997e68f2c935b0c7dfd90d9c1

Author: Anuj Phogat <anuj.phogat at gmail.com>
Date:   Tue Jun 13 14:22:06 2017 -0700

i965/cnl: Don't write to Cache Mode Register 1 on gen10+

With below optimizations gone in gen10+ we have nothing left out to
write to CACHE_MODE_1:
Float Blend Optimization Enable: This bit have been removed in gen10+
Partial Resolve Disable in VC: Recommendation is to always set this
field to 0 in gen10+ and that's the default value of the bit.

Signed-off-by: Anuj Phogat <anuj.phogat at gmail.com>
Reviewed-by: Kenneth Graunke <kenneth at whitecape.org>

---

 src/mesa/drivers/dri/i965/brw_state_upload.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/src/mesa/drivers/dri/i965/brw_state_upload.c b/src/mesa/drivers/dri/i965/brw_state_upload.c
index 926597b625..5e82c1b4ce 100644
--- a/src/mesa/drivers/dri/i965/brw_state_upload.c
+++ b/src/mesa/drivers/dri/i965/brw_state_upload.c
@@ -60,8 +60,10 @@ brw_upload_initial_gpu_state(struct brw_context *brw)
 
    brw_upload_invariant_state(brw);
 
-   /* Recommended optimization for Victim Cache eviction in pixel backend. */
-   if (brw->gen >= 9) {
+   if (brw->gen == 9) {
+      /* Recommended optimizations for Victim Cache eviction and floating
+       * point blending.
+       */
       BEGIN_BATCH(3);
       OUT_BATCH(MI_LOAD_REGISTER_IMM | (3 - 2));
       OUT_BATCH(GEN7_CACHE_MODE_1);




More information about the mesa-commit mailing list