r600g/sb: fix issue with DCE between GVN and GCM (v2)

We can't perform DCE using the liveness pass between GVN and GCM
because it relies on the correct schedule, but GVN doesn't care about
preserving correctness - it's rescheduled later by GCM.

This patch makes dce_cleanup pass perform simple DCE
between GVN and GCM instead of relying on liveness pass.

Fixes https://bugs.freedesktop.org/show_bug.cgi?id=70088

Signed-off-by: Vadim Girlin <[email protected]>

4 files changed, 39 insertions, 12 deletions

diff --git a/src/gallium/drivers/r600/sb/sb_core.cpp b/src/gallium/drivers/r600/sb/sb_core.cpp
index b5dd88ed96d..9fd9d9ad25a 100644
--- a/src/gallium/drivers/r600/sb/sb_core.cpp
+++ b/src/gallium/drivers/r600/sb/sb_core.cpp
@@ -184,6 +184,8 @@ int r600_sb_bytecode_process(struct r600_context *rctx,
 		SB_RUN_PASS(psi_ops,		1);
 
 	SB_RUN_PASS(liveness,			0);
+
+	sh->dce_flags = DF_REMOVE_DEAD | DF_EXPAND;
 	SB_RUN_PASS(dce_cleanup,		0);
 	SB_RUN_PASS(def_use,			0);
 
@@ -201,9 +203,10 @@ int r600_sb_bytecode_process(struct r600_context *rctx,
 
 	SB_RUN_PASS(gvn,				1);
 
-	SB_RUN_PASS(liveness,			0);
+	SB_RUN_PASS(def_use,			1);
+
+	sh->dce_flags = DF_REMOVE_DEAD | DF_REMOVE_UNUSED;
 	SB_RUN_PASS(dce_cleanup,		1);
-	SB_RUN_PASS(def_use,			0);
 
 	SB_RUN_PASS(ra_split,			0);
 	SB_RUN_PASS(def_use,			0);
@@ -217,6 +220,9 @@ int r600_sb_bytecode_process(struct r600_context *rctx,
 	sh->compute_interferences = true;
 	SB_RUN_PASS(liveness,			0);
 
+	sh->dce_flags = DF_REMOVE_DEAD;
+	SB_RUN_PASS(dce_cleanup,		1);
+
 	SB_RUN_PASS(ra_coalesce,		1);
 	SB_RUN_PASS(ra_init,			1);
 
diff --git a/src/gallium/drivers/r600/sb/sb_dce_cleanup.cpp b/src/gallium/drivers/r600/sb/sb_dce_cleanup.cpp
index f879395f67c..79aef9106a4 100644
--- a/src/gallium/drivers/r600/sb/sb_dce_cleanup.cpp
+++ b/src/gallium/drivers/r600/sb/sb_dce_cleanup.cpp
@@ -56,7 +56,8 @@ bool dce_cleanup::visit(cf_node& n, bool enter) {
 		else
 			cleanup_dst(n);
 	} else {
-		if (n.bc.op_ptr->flags & (CF_CLAUSE | CF_BRANCH | CF_LOOP))
+		if ((sh.dce_flags & DF_EXPAND) &&
+				(n.bc.op_ptr->flags & (CF_CLAUSE | CF_BRANCH | CF_LOOP)))
 			n.expand();
 	}
 	return true;
@@ -107,19 +108,20 @@ bool dce_cleanup::visit(region_node& n, bool enter) {
 }
 
 void dce_cleanup::cleanup_dst(node& n) {
-	cleanup_dst_vec(n.dst);
+	if (!cleanup_dst_vec(n.dst) && remove_unused &&
+			!n.dst.empty() && !(n.flags & NF_DONT_KILL) && n.parent)
+		n.remove();
 }
 
 bool dce_cleanup::visit(container_node& n, bool enter) {
-	if (enter) {
+	if (enter)
 		cleanup_dst(n);
-	} else {
-
-	}
 	return true;
 }
 
-void dce_cleanup::cleanup_dst_vec(vvec& vv) {
+bool dce_cleanup::cleanup_dst_vec(vvec& vv) {
+	bool alive = false;
+
 	for (vvec::iterator I = vv.begin(), E = vv.end(); I != E; ++I) {
 		value* &v = *I;
 		if (!v)
@@ -128,9 +130,13 @@ void dce_cleanup::cleanup_dst_vec(vvec& vv) {
 		if (v->gvn_source && v->gvn_source->is_dead())
 			v->gvn_source = NULL;
 
-		if (v->is_dead())
+		if (v->is_dead() || (remove_unused && !v->is_rel() && !v->uses))
 			v = NULL;
+		else
+			alive = true;
 	}
+
+	return alive;
 }
 
 } // namespace r600_sb
diff --git a/src/gallium/drivers/r600/sb/sb_pass.h b/src/gallium/drivers/r600/sb/sb_pass.h
index 95d2a203a60..a3f8515acde 100644
--- a/src/gallium/drivers/r600/sb/sb_pass.h
+++ b/src/gallium/drivers/r600/sb/sb_pass.h
@@ -119,9 +119,12 @@ public:
 class dce_cleanup : public vpass {
 	using vpass::visit;
 
+	bool remove_unused;
+
 public:
 
-	dce_cleanup(shader &s) : vpass(s) {}
+	dce_cleanup(shader &s) : vpass(s),
+		remove_unused(s.dce_flags & DF_REMOVE_UNUSED) {}
 
 	virtual bool visit(node &n, bool enter);
 	virtual bool visit(alu_group_node &n, bool enter);
@@ -135,7 +138,7 @@ public:
 private:
 
 	void cleanup_dst(node &n);
-	void cleanup_dst_vec(vvec &vv);
+	bool cleanup_dst_vec(vvec &vv);
 
 };
 
diff --git a/src/gallium/drivers/r600/sb/sb_shader.h b/src/gallium/drivers/r600/sb/sb_shader.h
index e515d312d80..7955bba9b67 100644
--- a/src/gallium/drivers/r600/sb/sb_shader.h
+++ b/src/gallium/drivers/r600/sb/sb_shader.h
@@ -71,6 +71,16 @@ enum chunk_flags {
 	RCF_PREALLOC = (1 << 4)
 };
 
+enum dce_flags {
+	DF_REMOVE_DEAD  = (1 << 0),
+	DF_REMOVE_UNUSED = (1 << 1),
+	DF_EXPAND = (1 << 2),
+};
+
+inline dce_flags operator |(dce_flags l, dce_flags r) {
+	return (dce_flags)((unsigned)l|(unsigned)r);
+}
+
 inline chunk_flags operator |(chunk_flags l, chunk_flags r) {
 	return (chunk_flags)((unsigned)l|(unsigned)r);
 }
@@ -297,6 +307,8 @@ public:
 
 	unsigned ngpr, nstack;
 
+	unsigned dce_flags;
+
 	shader(sb_context &sctx, shader_target t, unsigned id);
 
 	~shader();