[Mesa-dev] [PATCH 2/2] radv/gfx10: correctly determine the number of vertices per primitive

[Samuel Pitoiset]

For TES as NGG.

Signed-off-by: Samuel Pitoiset <samuel.pitoiset at gmail.com>
---
 src/amd/vulkan/radv_nir_to_llvm.c | 17 ++++++++++++++++-
 1 file changed, 16 insertions(+), 1 deletion(-)

diff --git a/src/amd/vulkan/radv_nir_to_llvm.c b/src/amd/vulkan/radv_nir_to_llvm.c
index 336bae28614..6e5a283f923 100644
--- a/src/amd/vulkan/radv_nir_to_llvm.c
+++ b/src/amd/vulkan/radv_nir_to_llvm.c
@@ -112,6 +112,7 @@ struct radv_shader_context {
 	unsigned gs_max_out_vertices;
 	unsigned gs_output_prim;
 
+	unsigned tes_point_mode;
 	unsigned tes_primitive_mode;
 
 	uint32_t tcs_patch_outputs_read;
@@ -3304,7 +3305,6 @@ handle_ngg_outputs_post(struct radv_shader_context *ctx)
 {
 	LLVMBuilderRef builder = ctx->ac.builder;
 	struct ac_build_if_state if_state;
-	unsigned num_vertices = 3;
 	LLVMValueRef tmp;
 
 	assert((ctx->stage == MESA_SHADER_VERTEX ||
@@ -3322,6 +3322,20 @@ handle_ngg_outputs_post(struct radv_shader_context *ctx)
 		ac_unpack_param(&ctx->ac, ctx->gs_vtx_offset[2], 0, 16),
 	};
 
+	/* Determine the number of vertices per primitive. */
+	unsigned num_vertices;
+
+	if (ctx->stage == MESA_SHADER_VERTEX) {
+		num_vertices = 3; /* TODO: optimize for points & lines */
+	} else {
+		if (ctx->tes_point_mode)
+			num_vertices = 1;
+		else if (ctx->tes_primitive_mode == GL_LINES)
+			num_vertices = 2;
+		else
+			num_vertices = 3;
+	}
+
 	/* TODO: streamout */
 
 	/* Copy Primitive IDs from GS threads to the LDS address corresponding
@@ -4435,6 +4449,7 @@ LLVMModuleRef ac_translate_nir_to_llvm(struct ac_llvm_compiler *ac_llvm,
 				ctx.tcs_num_inputs = util_last_bit64(shader_info->info.vs.ls_outputs_written);
 			ctx.tcs_num_patches = get_tcs_num_patches(&ctx);
 		} else if (shaders[i]->info.stage == MESA_SHADER_TESS_EVAL) {
+			ctx.tes_point_mode = shaders[i]->info.tess.point_mode;
 			ctx.tes_primitive_mode = shaders[i]->info.tess.primitive_mode;
 			ctx.abi.load_tess_varyings = load_tes_input;
 			ctx.abi.load_tess_coord = load_tess_coord;
-- 
2.22.0