[Mesa-dev] [PATCH 02/13] radeonsi: use uint32_t to declare si_shader_key.opt.kill_outputs

[Marek Olšák]

From: Marek Olšák <marek.olsak at amd.com>

the next patch will benefit from this
---
 src/gallium/drivers/radeonsi/si_shader.c        | 8 +++++---
 src/gallium/drivers/radeonsi/si_shader.h        | 3 ++-
 src/gallium/drivers/radeonsi/si_state_shaders.c | 5 +++--
 3 files changed, 10 insertions(+), 6 deletions(-)

diff --git a/src/gallium/drivers/radeonsi/si_shader.c b/src/gallium/drivers/radeonsi/si_shader.c
index a6b7e5e..4ee4a64 100644
--- a/src/gallium/drivers/radeonsi/si_shader.c
+++ b/src/gallium/drivers/radeonsi/si_shader.c
@@ -2269,35 +2269,36 @@ static void si_llvm_export_vs(struct lp_build_tgsi_context *bld_base,
 	unsigned semantic_name, semantic_index;
 	unsigned target;
 	unsigned param_count = 0;
 	unsigned pos_idx;
 	int i;
 
 	for (i = 0; i < noutput; i++) {
 		semantic_name = outputs[i].semantic_name;
 		semantic_index = outputs[i].semantic_index;
 		bool export_param = true;
+		unsigned id;
 
 		switch (semantic_name) {
 		case TGSI_SEMANTIC_POSITION: /* ignore these */
 		case TGSI_SEMANTIC_PSIZE:
 		case TGSI_SEMANTIC_CLIPVERTEX:
 		case TGSI_SEMANTIC_EDGEFLAG:
 			break;
 		case TGSI_SEMANTIC_GENERIC:
 			/* don't process indices the function can't handle */
 			if (semantic_index >= SI_MAX_IO_GENERIC)
 				break;
 			/* fall through */
 		default:
-			if (shader->key.opt.kill_outputs &
-			    (1ull << si_shader_io_get_unique_index(semantic_name, semantic_index)))
+			id = si_shader_io_get_unique_index(semantic_name, semantic_index);
+			if (shader->key.opt.kill_outputs[id / 32] & (1u << (id % 32)))
 				export_param = false;
 		}
 
 		if (outputs[i].vertex_stream[0] != 0 &&
 		    outputs[i].vertex_stream[1] != 0 &&
 		    outputs[i].vertex_stream[2] != 0 &&
 		    outputs[i].vertex_stream[3] != 0)
 			export_param = false;
 
 handle_semantic:
@@ -5328,21 +5329,22 @@ static void si_dump_shader_key(unsigned processor, const struct si_shader *shade
 		break;
 
 	default:
 		assert(0);
 	}
 
 	if ((processor == PIPE_SHADER_GEOMETRY ||
 	     processor == PIPE_SHADER_TESS_EVAL ||
 	     processor == PIPE_SHADER_VERTEX) &&
 	    !key->as_es && !key->as_ls) {
-		fprintf(f, "  opt.kill_outputs = 0x%"PRIx64"\n", key->opt.kill_outputs);
+		fprintf(f, "  opt.kill_outputs[0] = 0x%x\n", key->opt.kill_outputs[0]);
+		fprintf(f, "  opt.kill_outputs[1] = 0x%x\n", key->opt.kill_outputs[1]);
 		fprintf(f, "  opt.clip_disable = %u\n", key->opt.clip_disable);
 	}
 }
 
 static void si_init_shader_ctx(struct si_shader_context *ctx,
 			       struct si_screen *sscreen,
 			       LLVMTargetMachineRef tm)
 {
 	struct lp_build_tgsi_context *bld_base;
 
diff --git a/src/gallium/drivers/radeonsi/si_shader.h b/src/gallium/drivers/radeonsi/si_shader.h
index de520a2..76e09b2 100644
--- a/src/gallium/drivers/radeonsi/si_shader.h
+++ b/src/gallium/drivers/radeonsi/si_shader.h
@@ -494,21 +494,22 @@ struct si_shader_key {
 		union {
 			uint64_t	ff_tcs_inputs_to_copy; /* for fixed-func TCS */
 			/* When PS needs PrimID and GS is disabled. */
 			unsigned	vs_export_prim_id:1;
 		} u;
 	} mono;
 
 	/* Optimization flags for asynchronous compilation only. */
 	struct {
 		/* For HW VS (it can be VS, TES, GS) */
-		uint64_t	kill_outputs; /* "get_unique_index" bits */
+		/* Don't use "uint64_t" in order to get 32-bit alignment. */
+		uint32_t	kill_outputs[2]; /* "get_unique_index" bits */
 		unsigned	clip_disable:1;
 
 		/* For shaders where monolithic variants have better code.
 		 *
 		 * This is a flag that has no effect on code generation,
 		 * but forces monolithic shaders to be used as soon as
 		 * possible, because it's in the "opt" group.
 		 */
 		unsigned	prefer_mono:1;
 	} opt;
diff --git a/src/gallium/drivers/radeonsi/si_state_shaders.c b/src/gallium/drivers/radeonsi/si_state_shaders.c
index 07e6a42..15e46b5 100644
--- a/src/gallium/drivers/radeonsi/si_state_shaders.c
+++ b/src/gallium/drivers/radeonsi/si_state_shaders.c
@@ -1234,23 +1234,24 @@ static void si_shader_selector_key_hw_vs(struct si_context *sctx,
 	uint64_t inputs_read = 0;
 
 	/* ignore POSITION, PSIZE */
 	outputs_written &= ~((1ull << si_shader_io_get_unique_index(TGSI_SEMANTIC_POSITION, 0) |
 			     (1ull << si_shader_io_get_unique_index(TGSI_SEMANTIC_PSIZE, 0))));
 
 	if (!ps_disabled) {
 		inputs_read = ps->inputs_read;
 	}
 
-	uint64_t linked = outputs_written & inputs_read;
+	uint64_t kill_outputs = ~(outputs_written & inputs_read) & outputs_written;
 
-	key->opt.kill_outputs = ~linked & outputs_written;
+	key->opt.kill_outputs[0] = kill_outputs;
+	key->opt.kill_outputs[1] = kill_outputs >> 32;
 }
 
 /* Compute the key for the hw shader variant */
 static inline void si_shader_selector_key(struct pipe_context *ctx,
 					  struct si_shader_selector *sel,
 					  struct si_shader_key *key)
 {
 	struct si_context *sctx = (struct si_context *)ctx;
 
 	memset(key, 0, sizeof(*key));
-- 
2.7.4