[Mesa-dev] [PATCH v2 3/3] radeonsi: add nir support for gs epilogue

[Timothy Arceri]

v2: add emit_gs_epilogue() helper function to reduce duplication.
---
 src/gallium/drivers/radeonsi/si_shader.c | 25 +++++++++++++++++++++----
 1 file changed, 21 insertions(+), 4 deletions(-)

diff --git a/src/gallium/drivers/radeonsi/si_shader.c b/src/gallium/drivers/radeonsi/si_shader.c
index 0c77739f20..a4a2041b93 100644
--- a/src/gallium/drivers/radeonsi/si_shader.c
+++ b/src/gallium/drivers/radeonsi/si_shader.c
@@ -3241,31 +3241,47 @@ static void si_llvm_emit_es_epilogue(struct ac_shader_abi *abi,
 }
 
 static LLVMValueRef si_get_gs_wave_id(struct si_shader_context *ctx)
 {
 	if (ctx->screen->b.chip_class >= GFX9)
 		return unpack_param(ctx, ctx->param_merged_wave_info, 16, 8);
 	else
 		return LLVMGetParam(ctx->main_fn, ctx->param_gs_wave_id);
 }
 
-static void si_llvm_emit_gs_epilogue(struct lp_build_tgsi_context *bld_base)
+static void emit_gs_epilogue(struct si_shader_context *ctx)
 {
-	struct si_shader_context *ctx = si_shader_context(bld_base);
-
 	ac_build_sendmsg(&ctx->ac, AC_SENDMSG_GS_OP_NOP | AC_SENDMSG_GS_DONE,
 			 si_get_gs_wave_id(ctx));
 
 	if (ctx->screen->b.chip_class >= GFX9)
 		lp_build_endif(&ctx->merged_wrap_if_state);
 }
 
+static void si_llvm_emit_gs_epilogue(struct ac_shader_abi *abi,
+				     unsigned max_outputs,
+				     LLVMValueRef *addrs)
+{
+	struct si_shader_context *ctx = si_shader_context_from_abi(abi);
+	struct tgsi_shader_info UNUSED *info = &ctx->shader->selector->info;
+
+	assert(info->num_outputs <= max_outputs);
+
+	emit_gs_epilogue(ctx);
+}
+
+static void si_tgsi_emit_gs_epilogue(struct lp_build_tgsi_context *bld_base)
+{
+	struct si_shader_context *ctx = si_shader_context(bld_base);
+	emit_gs_epilogue(ctx);
+}
+
 static void si_llvm_emit_vs_epilogue(struct ac_shader_abi *abi,
 				     unsigned max_outputs,
 				     LLVMValueRef *addrs)
 {
 	struct si_shader_context *ctx = si_shader_context_from_abi(abi);
 	struct tgsi_shader_info *info = &ctx->shader->selector->info;
 	struct si_shader_output_values *outputs = NULL;
 	int i,j;
 
 	assert(!ctx->shader->is_gs_copy_shader);
@@ -5754,21 +5770,22 @@ static bool si_compile_tgsi_main(struct si_shader_context *ctx,
 		bld_base->emit_fetch_funcs[TGSI_FILE_INPUT] = fetch_input_tes;
 		if (shader->key.as_es)
 			ctx->abi.emit_outputs = si_llvm_emit_es_epilogue;
 		else
 			ctx->abi.emit_outputs = si_llvm_emit_vs_epilogue;
 		bld_base->emit_epilogue = si_tgsi_emit_epilogue;
 		break;
 	case PIPE_SHADER_GEOMETRY:
 		bld_base->emit_fetch_funcs[TGSI_FILE_INPUT] = fetch_input_gs;
 		ctx->abi.emit_vertex = si_llvm_emit_vertex;
-		bld_base->emit_epilogue = si_llvm_emit_gs_epilogue;
+		ctx->abi.emit_outputs = si_llvm_emit_gs_epilogue;
+		bld_base->emit_epilogue = si_tgsi_emit_gs_epilogue;
 		break;
 	case PIPE_SHADER_FRAGMENT:
 		ctx->load_input = declare_input_fs;
 		ctx->abi.emit_outputs = si_llvm_return_fs_outputs;
 		bld_base->emit_epilogue = si_tgsi_emit_epilogue;
 		break;
 	case PIPE_SHADER_COMPUTE:
 		break;
 	default:
 		assert(!"Unsupported shader type");
-- 
2.14.3