[Mesa-stable] [PATCH 1/5] i965: Hard code scratch_ids_per_subslice for Cherryview

[Jordan Justen]

Ken suggested that we might be underallocating scratch space on HD
400. Allocating scratch space as though there was actually 8 EUs
seems to help with a GPU hang seen on synmark CSDof.

Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=104636
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=105290
Cc: Kenneth Graunke <kenneth at whitecape.org>
Cc: Eero Tamminen <eero.t.tamminen at intel.com>
Cc: <mesa-stable at lists.freedesktop.org>
Signed-off-by: Jordan Justen <jordan.l.justen at intel.com>
---
 src/mesa/drivers/dri/i965/brw_program.c | 44 ++++++++++++++++++++-------------
 1 file changed, 27 insertions(+), 17 deletions(-)

diff --git a/src/mesa/drivers/dri/i965/brw_program.c b/src/mesa/drivers/dri/i965/brw_program.c
index 527f003977b..c121136c439 100644
--- a/src/mesa/drivers/dri/i965/brw_program.c
+++ b/src/mesa/drivers/dri/i965/brw_program.c
@@ -402,23 +402,33 @@ brw_alloc_stage_scratch(struct brw_context *brw,
       if (devinfo->gen >= 9)
          subslices = 4 * brw->screen->devinfo.num_slices;
 
-      /* WaCSScratchSize:hsw
-       *
-       * Haswell's scratch space address calculation appears to be sparse
-       * rather than tightly packed.  The Thread ID has bits indicating
-       * which subslice, EU within a subslice, and thread within an EU
-       * it is.  There's a maximum of two slices and two subslices, so these
-       * can be stored with a single bit.  Even though there are only 10 EUs
-       * per subslice, this is stored in 4 bits, so there's an effective
-       * maximum value of 16 EUs.  Similarly, although there are only 7
-       * threads per EU, this is stored in a 3 bit number, giving an effective
-       * maximum value of 8 threads per EU.
-       *
-       * This means that we need to use 16 * 8 instead of 10 * 7 for the
-       * number of threads per subslice.
-       */
-      const unsigned scratch_ids_per_subslice =
-         devinfo->is_haswell ? 16 * 8 : devinfo->max_cs_threads;
+      unsigned scratch_ids_per_subslice;
+      if (devinfo->is_haswell) {
+         /* WaCSScratchSize:hsw
+          *
+          * Haswell's scratch space address calculation appears to be sparse
+          * rather than tightly packed. The Thread ID has bits indicating
+          * which subslice, EU within a subslice, and thread within an EU it
+          * is. There's a maximum of two slices and two subslices, so these
+          * can be stored with a single bit. Even though there are only 10 EUs
+          * per subslice, this is stored in 4 bits, so there's an effective
+          * maximum value of 16 EUs. Similarly, although there are only 7
+          * threads per EU, this is stored in a 3 bit number, giving an
+          * effective maximum value of 8 threads per EU.
+          *
+          * This means that we need to use 16 * 8 instead of 10 * 7 for the
+          * number of threads per subslice.
+          */
+         scratch_ids_per_subslice = 16 * 8;
+      } else if (devinfo->is_cherryview) {
+         /* For Cherryview, it appears that the scratch addresses for the 6 EU
+          * devices may still generate compute scratch addresses covering the
+          * same range as 8 EU.
+          */
+         scratch_ids_per_subslice = 8 * 7;
+      } else {
+         scratch_ids_per_subslice = devinfo->max_cs_threads;
+      }
 
       thread_count = scratch_ids_per_subslice * subslices;
       break;
-- 
2.16.1