radeonsi: set a better NUM_PATCHES hard limit

AMDVLK uses 64 (distributed) and 16 (non-distributed).
radeonsi will use 63 and 16.
* This might improve tessellation performance on Hawaii, Bonaire, Tahiti,
  Pitcairn. (they will use 16)
* I'm not sure if this matters for 1 SE configs.

Tested-by: Dieter Nützel <Dieter@nuetzel-hh.de>

diff --git a/src/gallium/drivers/radeonsi/si_state_draw.c b/src/gallium/drivers/radeonsi/si_state_draw.c
index d61374e95cad2f0f9716210787046bcd58044162..b29135a1e68d00166cdec53e5866ed68d2e2db82 100644 (file)
--- a/src/gallium/drivers/radeonsi/si_state_draw.c
+++ b/src/gallium/drivers/radeonsi/si_state_draw.c
@@ -165,10 +165,17 @@ static bool si_emit_derived_tess_state(struct si_context *sctx,
                            (sctx->screen->tess_offchip_block_dw_size * 4) /
                            output_patch_size);
 
-       /* Not necessary for correctness, but improves performance. The
-        * specific value is taken from the proprietary driver.
+       /* Not necessary for correctness, but improves performance.
+        * The hardware can do more, but the radeonsi shader constant is
+        * limited to 6 bits.
         */
-       *num_patches = MIN2(*num_patches, 40);
+       *num_patches = MIN2(*num_patches, 63); /* triangles: 3 full waves except 3 lanes */
+
+       /* When distributed tessellation is unsupported, switch between SEs
+        * at a higher frequency to compensate for it.
+        */
+       if (!sctx->screen->has_distributed_tess && sctx->screen->info.max_se > 1)
+               *num_patches = MIN2(*num_patches, 16); /* recommended */
 
        /* Make sure that vector lanes are reasonably occupied. It probably
         * doesn't matter much because this is LS-HS, and TES is likely to