[Mesa-dev] [PATCH 4/8] radeonsi: apply a tessellation bug workaround for SI

[Marek Olšák]

From: Marek Olšák <marek.olsak at amd.com>

Cc: 13.0 <mesa-stable at lists.freedesktop.org>
---
 src/gallium/drivers/radeonsi/si_state_draw.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/src/gallium/drivers/radeonsi/si_state_draw.c b/src/gallium/drivers/radeonsi/si_state_draw.c
index 10073ef..cba5a03 100644
--- a/src/gallium/drivers/radeonsi/si_state_draw.c
+++ b/src/gallium/drivers/radeonsi/si_state_draw.c
@@ -159,20 +159,27 @@ static void si_emit_derived_tess_state(struct si_context *sctx,
 
 	/* Make sure the output data fits in the offchip buffer */
 	*num_patches = MIN2(*num_patches,
 			    (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.
 	 */
 	*num_patches = MIN2(*num_patches, 40);
+
+	/* SI bug workaround - limit LS-HS threadgroups to only one wave. */
+	if (sctx->b.chip_class == SI) {
+		unsigned one_wave = 64 / MAX2(num_tcs_input_cp, num_tcs_output_cp);
+		*num_patches = MIN2(*num_patches, one_wave);
+	}
+
 	sctx->last_num_patches = *num_patches;
 
 	output_patch0_offset = input_patch_size * *num_patches;
 	perpatch_output_offset = output_patch0_offset + pervertex_output_patch_size;
 
 	lds_size = output_patch0_offset + output_patch_size * *num_patches;
 	ls_rsrc2 = ls->current->config.rsrc2;
 
 	if (sctx->b.chip_class >= CIK) {
 		assert(lds_size <= 65536);
-- 
2.7.4