i965/hsw: Enable L3 atomics.

Improves performance of the arb_shader_image_load_store-atomicity
piglit test by over 25x (which isn't a real benchmark it's just heavy
on atomics -- the improvement in a microbenchmark I wrote a while ago
seemed to be even greater).  The drawback is one needs to be
extra-careful not to hang the GPU (in fact the whole system).  A DC
partition must have been allocated on L3, the "convert L3 cycle for DC
to UC" bit may not be set, the MOCS L3 cacheability bit must be set
for all surfaces accessed using DC atomics, and the SCRATCH1 and
ROW_CHICKEN3 bits must be kept in sync.

A fairly recent kernel is required for the command parser to allow
writes to these registers.

Reviewed-by: Samuel Iglesias Gonsálvez <[email protected]>
Acked-by: Kenneth Graunke <[email protected]>
Reviewed-by: Kristian Høgsberg  <[email protected]>

1 files changed, 14 insertions, 0 deletions

diff --git a/src/mesa/drivers/dri/i965/gen7_l3_state.c b/src/mesa/drivers/dri/i965/gen7_l3_state.c
index 712c7c730a4..141d4812a21 100644
--- a/src/mesa/drivers/dri/i965/gen7_l3_state.c
+++ b/src/mesa/drivers/dri/i965/gen7_l3_state.c
@@ -258,5 +258,19 @@ setup_l3_config(struct brw_context *brw, const struct brw_l3_config *cfg)
                 SET_FIELD(cfg->n[L3P_T], GEN7_L3CNTLREG3_T_ALLOC));
 
       ADVANCE_BATCH();
+
+      if (brw->is_haswell && brw->intelScreen->cmd_parser_version >= 4) {
+         /* Enable L3 atomics on HSW if we have a DC partition, otherwise keep
+          * them disabled to avoid crashing the system hard.
+          */
+         BEGIN_BATCH(5);
+         OUT_BATCH(MI_LOAD_REGISTER_IMM | (5 - 2));
+         OUT_BATCH(HSW_SCRATCH1);
+         OUT_BATCH(has_dc ? 0 : HSW_SCRATCH1_L3_ATOMIC_DISABLE);
+         OUT_BATCH(HSW_ROW_CHICKEN3);
+         OUT_BATCH(HSW_ROW_CHICKEN3_L3_ATOMIC_DISABLE << 16 |
+                   (has_dc ? 0 : HSW_ROW_CHICKEN3_L3_ATOMIC_DISABLE));
+         ADVANCE_BATCH();
+      }
    }
 }