Mesa (master): radeonsi: add support for geometry shader invocations.

[Dave Airlie]

Module: Mesa
Branch: master
Commit: 556dd4af76ca0be9b0698139c06e6d12d52e8ff3
URL:    http://cgit.freedesktop.org/mesa/mesa/commit/?id=556dd4af76ca0be9b0698139c06e6d12d52e8ff3

Author: Dave Airlie <airlied at redhat.com>
Date:   Thu Jun 25 03:55:54 2015 +0100

radeonsi: add support for geometry shader invocations.

Reviewed-by: Marek Olšák <marek.olsak at amd.com>
Signed-off-by: Dave Airlie <airlied at redhat.com>

---

 docs/GL3.txt                                    |    2 +-
 src/gallium/drivers/radeonsi/si_shader.c        |    5 +++++
 src/gallium/drivers/radeonsi/si_shader.h        |    1 +
 src/gallium/drivers/radeonsi/si_state.c         |    1 -
 src/gallium/drivers/radeonsi/si_state_shaders.c |    7 +++++++
 5 files changed, 14 insertions(+), 2 deletions(-)

diff --git a/docs/GL3.txt b/docs/GL3.txt
index df913bd..81014a5 100644
--- a/docs/GL3.txt
+++ b/docs/GL3.txt
@@ -104,7 +104,7 @@ GL 4.0, GLSL 4.00:
   - Fused multiply-add                                 DONE ()
   - Packing/bitfield/conversion functions              DONE (r600, radeonsi, softpipe)
   - Enhanced textureGather                             DONE (r600, radeonsi, softpipe)
-  - Geometry shader instancing                         DONE (r600, llvmpipe, softpipe)
+  - Geometry shader instancing                         DONE (r600, radeonsi, llvmpipe, softpipe)
   - Geometry shader multiple streams                   DONE ()
   - Enhanced per-sample shading                        DONE (r600, radeonsi)
   - Interpolation functions                            DONE (r600)
diff --git a/src/gallium/drivers/radeonsi/si_shader.c b/src/gallium/drivers/radeonsi/si_shader.c
index 4ca3172..4d97b58 100644
--- a/src/gallium/drivers/radeonsi/si_shader.c
+++ b/src/gallium/drivers/radeonsi/si_shader.c
@@ -630,6 +630,11 @@ static void declare_system_value(
 				     SI_PARAM_BASE_VERTEX);
 		break;
 
+	case TGSI_SEMANTIC_INVOCATIONID:
+		value = LLVMGetParam(radeon_bld->main_fn,
+				     SI_PARAM_GS_INSTANCE_ID);
+		break;
+
 	case TGSI_SEMANTIC_SAMPLEID:
 		value = get_sample_id(radeon_bld);
 		break;
diff --git a/src/gallium/drivers/radeonsi/si_shader.h b/src/gallium/drivers/radeonsi/si_shader.h
index 51055af..b4339ae 100644
--- a/src/gallium/drivers/radeonsi/si_shader.h
+++ b/src/gallium/drivers/radeonsi/si_shader.h
@@ -115,6 +115,7 @@ struct si_shader_selector {
 
 	unsigned	gs_output_prim;
 	unsigned	gs_max_out_vertices;
+	unsigned	gs_num_invocations;
 	uint64_t	gs_used_inputs; /* mask of "get_unique_index" bits */
 };
 
diff --git a/src/gallium/drivers/radeonsi/si_state.c b/src/gallium/drivers/radeonsi/si_state.c
index 752467b..0dd08a2 100644
--- a/src/gallium/drivers/radeonsi/si_state.c
+++ b/src/gallium/drivers/radeonsi/si_state.c
@@ -3078,7 +3078,6 @@ void si_init_config(struct si_context *sctx)
 	si_pm4_set_reg(pm4, R_028B60_VGT_GS_VERT_ITEMSIZE_1, 0);
 	si_pm4_set_reg(pm4, R_028B64_VGT_GS_VERT_ITEMSIZE_2, 0);
 	si_pm4_set_reg(pm4, R_028B68_VGT_GS_VERT_ITEMSIZE_3, 0);
-	si_pm4_set_reg(pm4, R_028B90_VGT_GS_INSTANCE_CNT, 0);
 
 	si_pm4_set_reg(pm4, R_028B98_VGT_STRMOUT_BUFFER_CONFIG, 0x0);
 	si_pm4_set_reg(pm4, R_028AB4_VGT_REUSE_OFF, 0);
diff --git a/src/gallium/drivers/radeonsi/si_state_shaders.c b/src/gallium/drivers/radeonsi/si_state_shaders.c
index 48128fa..eef3baa 100644
--- a/src/gallium/drivers/radeonsi/si_state_shaders.c
+++ b/src/gallium/drivers/radeonsi/si_state_shaders.c
@@ -76,6 +76,7 @@ static void si_shader_gs(struct si_shader *shader)
 	unsigned gs_vert_itemsize = shader->selector->info.num_outputs * (16 >> 2);
 	unsigned gs_max_vert_out = shader->selector->gs_max_out_vertices;
 	unsigned gsvs_itemsize = gs_vert_itemsize * gs_max_vert_out;
+	unsigned gs_num_invocations = shader->selector->gs_num_invocations;
 	unsigned cut_mode;
 	struct si_pm4_state *pm4;
 	unsigned num_sgprs, num_user_sgprs;
@@ -118,6 +119,10 @@ static void si_shader_gs(struct si_shader *shader)
 
 	si_pm4_set_reg(pm4, R_028B5C_VGT_GS_VERT_ITEMSIZE, gs_vert_itemsize);
 
+	si_pm4_set_reg(pm4, R_028B90_VGT_GS_INSTANCE_CNT,
+		       S_028B90_CNT(MIN2(gs_num_invocations, 127)) |
+		       S_028B90_ENABLE(gs_num_invocations > 0));
+
 	va = shader->bo->gpu_address;
 	si_pm4_add_bo(pm4, shader->bo, RADEON_USAGE_READ, RADEON_PRIO_SHADER_DATA);
 	si_pm4_set_reg(pm4, R_00B220_SPI_SHADER_PGM_LO_GS, va >> 8);
@@ -490,6 +495,8 @@ static void *si_create_shader_state(struct pipe_context *ctx,
 			sel->info.properties[TGSI_PROPERTY_GS_OUTPUT_PRIM];
 		sel->gs_max_out_vertices =
 			sel->info.properties[TGSI_PROPERTY_GS_MAX_OUTPUT_VERTICES];
+		sel->gs_num_invocations =
+			sel->info.properties[TGSI_PROPERTY_GS_INVOCATIONS];
 
 		for (i = 0; i < sel->info.num_inputs; i++) {
 			unsigned name = sel->info.input_semantic_name[i];