[Mesa-dev] [PATCH v2 37/73] radeonsi/nir: emit FS outputs

[Nicolai Hähnle]

From: Nicolai Hähnle <nicolai.haehnle at amd.com>

---
 src/gallium/drivers/radeonsi/si_shader.c | 24 ++++++++++++++----------
 1 file changed, 14 insertions(+), 10 deletions(-)

diff --git a/src/gallium/drivers/radeonsi/si_shader.c b/src/gallium/drivers/radeonsi/si_shader.c
index e90d25c..2b030c0 100644
--- a/src/gallium/drivers/radeonsi/si_shader.c
+++ b/src/gallium/drivers/radeonsi/si_shader.c
@@ -3318,23 +3318,25 @@ static void si_export_null(struct lp_build_tgsi_context *bld_base)
  * v[0:3] = color0.xyzw
  * v[4:7] = color1.xyzw
  * ...
  * vN+0 = Depth
  * vN+1 = Stencil
  * vN+2 = SampleMask
  * vN+3 = SampleMaskIn (used for OpenGL smoothing)
  *
  * The alpha-ref SGPR is returned via its original location.
  */
-static void si_llvm_return_fs_outputs(struct lp_build_tgsi_context *bld_base)
+static void si_llvm_return_fs_outputs(struct ac_shader_abi *abi,
+				      unsigned max_outputs,
+				      LLVMValueRef *addrs)
 {
-	struct si_shader_context *ctx = si_shader_context(bld_base);
+	struct si_shader_context *ctx = si_shader_context_from_abi(abi);
 	struct si_shader *shader = ctx->shader;
 	struct tgsi_shader_info *info = &shader->selector->info;
 	LLVMBuilderRef builder = ctx->gallivm.builder;
 	unsigned i, j, first_vgpr, vgpr;
 
 	LLVMValueRef color[8][4] = {};
 	LLVMValueRef depth = NULL, stencil = NULL, samplemask = NULL;
 	LLVMValueRef ret;
 
 	if (ctx->postponed_kill)
@@ -3342,51 +3344,52 @@ static void si_llvm_return_fs_outputs(struct lp_build_tgsi_context *bld_base)
 
 	/* Read the output values. */
 	for (i = 0; i < info->num_outputs; i++) {
 		unsigned semantic_name = info->output_semantic_name[i];
 		unsigned semantic_index = info->output_semantic_index[i];
 
 		switch (semantic_name) {
 		case TGSI_SEMANTIC_COLOR:
 			assert(semantic_index < 8);
 			for (j = 0; j < 4; j++) {
-				LLVMValueRef ptr = ctx->outputs[i][j];
+				LLVMValueRef ptr = addrs[4 * i + j];
 				LLVMValueRef result = LLVMBuildLoad(builder, ptr, "");
 				color[semantic_index][j] = result;
 			}
 			break;
 		case TGSI_SEMANTIC_POSITION:
 			depth = LLVMBuildLoad(builder,
-					      ctx->outputs[i][2], "");
+					      addrs[4 * i + 2], "");
 			break;
 		case TGSI_SEMANTIC_STENCIL:
 			stencil = LLVMBuildLoad(builder,
-						ctx->outputs[i][1], "");
+						addrs[4 * i + 1], "");
 			break;
 		case TGSI_SEMANTIC_SAMPLEMASK:
 			samplemask = LLVMBuildLoad(builder,
-						   ctx->outputs[i][0], "");
+						   addrs[4 * i + 0], "");
 			break;
 		default:
 			fprintf(stderr, "Warning: SI unhandled fs output type:%d\n",
 				semantic_name);
 		}
 	}
 
 	/* Fill the return structure. */
 	ret = ctx->return_value;
 
 	/* Set SGPRs. */
 	ret = LLVMBuildInsertValue(builder, ret,
-				   bitcast(bld_base, TGSI_TYPE_SIGNED,
-					   LLVMGetParam(ctx->main_fn,
-							SI_PARAM_ALPHA_REF)),
+				   LLVMBuildBitCast(ctx->ac.builder,
+						LLVMGetParam(ctx->main_fn,
+							SI_PARAM_ALPHA_REF),
+						ctx->i32, ""),
 				   SI_SGPR_ALPHA_REF, "");
 
 	/* Set VGPRs */
 	first_vgpr = vgpr = SI_SGPR_ALPHA_REF + 1;
 	for (i = 0; i < ARRAY_SIZE(color); i++) {
 		if (!color[i][0])
 			continue;
 
 		for (j = 0; j < 4; j++)
 			ret = LLVMBuildInsertValue(builder, ret, color[i][j], vgpr++, "");
@@ -5593,21 +5596,22 @@ static bool si_compile_tgsi_main(struct si_shader_context *ctx,
 			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;
 		bld_base->emit_epilogue = si_llvm_emit_gs_epilogue;
 		break;
 	case PIPE_SHADER_FRAGMENT:
 		ctx->load_input = declare_input_fs;
-		bld_base->emit_epilogue = si_llvm_return_fs_outputs;
+		ctx->abi.emit_outputs = si_llvm_return_fs_outputs;
+		bld_base->emit_epilogue = si_tgsi_emit_epilogue;
 		break;
 	case PIPE_SHADER_COMPUTE:
 		ctx->declare_memory_region = declare_compute_memory;
 		break;
 	default:
 		assert(!"Unsupported shader type");
 		return false;
 	}
 
 	ctx->abi.load_ubo = load_ubo;
-- 
2.9.3