Mesa (master): radv: set optimal OVERWRITE_COMBINER_WATERMARK on GFX9

[GitLab Mirror]

Module: Mesa
Branch: master
Commit: 90d68858ed491ec12628845369d242b8a1f20940
URL:    http://cgit.freedesktop.org/mesa/mesa/commit/?id=90d68858ed491ec12628845369d242b8a1f20940

Author: Samuel Pitoiset <samuel.pitoiset at gmail.com>
Date:   Mon Nov 12 09:46:14 2018 +0100

radv: set optimal OVERWRITE_COMBINER_WATERMARK on GFX9

Ported from RadeonSI.

Signed-off-by: Samuel Pitoiset <samuel.pitoiset at gmail.com>
Reviewed-by: Bas Nieuwenhuizen <bas at basnieuwenhuizen.nl>

---

 src/amd/vulkan/radv_cmd_buffer.c | 21 +++++++++++++++++++++
 src/amd/vulkan/si_cmd_buffer.c   |  3 ---
 2 files changed, 21 insertions(+), 3 deletions(-)

diff --git a/src/amd/vulkan/radv_cmd_buffer.c b/src/amd/vulkan/radv_cmd_buffer.c
index 1f22fda7c5..8e0ed284d6 100644
--- a/src/amd/vulkan/radv_cmd_buffer.c
+++ b/src/amd/vulkan/radv_cmd_buffer.c
@@ -1483,6 +1483,7 @@ radv_emit_framebuffer_state(struct radv_cmd_buffer *cmd_buffer)
 	int i;
 	struct radv_framebuffer *framebuffer = cmd_buffer->state.framebuffer;
 	const struct radv_subpass *subpass = cmd_buffer->state.subpass;
+	unsigned num_bpp64_colorbufs = 0;
 
 	/* this may happen for inherited secondary recording */
 	if (!framebuffer)
@@ -1506,6 +1507,9 @@ radv_emit_framebuffer_state(struct radv_cmd_buffer *cmd_buffer)
 		radv_emit_fb_color_state(cmd_buffer, i, att, image, layout);
 
 		radv_load_color_clear_metadata(cmd_buffer, image, i);
+
+		if (image->surface.bpe >= 8)
+			num_bpp64_colorbufs++;
 	}
 
 	if(subpass->depth_stencil_attachment.attachment != VK_ATTACHMENT_UNUSED) {
@@ -1541,6 +1545,23 @@ radv_emit_framebuffer_state(struct radv_cmd_buffer *cmd_buffer)
 			       S_028208_BR_X(framebuffer->width) |
 			       S_028208_BR_Y(framebuffer->height));
 
+	if (cmd_buffer->device->physical_device->rad_info.chip_class >= VI) {
+		uint8_t watermark = 4; /* Default value for VI. */
+
+		/* For optimal DCC performance. */
+		if (cmd_buffer->device->physical_device->rad_info.chip_class >= GFX9) {
+			if (num_bpp64_colorbufs >= 5) {
+				watermark = 8;
+			} else {
+				watermark = 6;
+			}
+		}
+
+		radeon_set_context_reg(cmd_buffer->cs, R_028424_CB_DCC_CONTROL,
+				       S_028424_OVERWRITE_COMBINER_MRT_SHARING_DISABLE(1) |
+				       S_028424_OVERWRITE_COMBINER_WATERMARK(watermark));
+	}
+
 	if (cmd_buffer->device->dfsm_allowed) {
 		radeon_emit(cmd_buffer->cs, PKT3(PKT3_EVENT_WRITE, 0, 0));
 		radeon_emit(cmd_buffer->cs, EVENT_TYPE(V_028A90_BREAK_BATCH) | EVENT_INDEX(0));
diff --git a/src/amd/vulkan/si_cmd_buffer.c b/src/amd/vulkan/si_cmd_buffer.c
index f4da2b38fd..a9f2572541 100644
--- a/src/amd/vulkan/si_cmd_buffer.c
+++ b/src/amd/vulkan/si_cmd_buffer.c
@@ -305,9 +305,6 @@ si_emit_graphics(struct radv_physical_device *physical_device,
 
 	if (physical_device->rad_info.chip_class >= VI) {
 		uint32_t vgt_tess_distribution;
-		radeon_set_context_reg(cs, R_028424_CB_DCC_CONTROL,
-				       S_028424_OVERWRITE_COMBINER_MRT_SHARING_DISABLE(1) |
-				       S_028424_OVERWRITE_COMBINER_WATERMARK(4));
 
 		vgt_tess_distribution = S_028B50_ACCUM_ISOLINE(32) |
 			S_028B50_ACCUM_TRI(11) |