Insert IMPLICIT_DEFS for undef uses in tail merging

Tail merging can convert an undef use into a normal one when creating a
common tail. Doing so can make the register live out from a block which
previously contained the undef use. To keep the liveness up-to-date,
insert IMPLICIT_DEFs in such blocks when necessary.

To enable this patch the computeLiveIns() function which used to
compute live-ins for a block and set them immediately is split into new
functions:
- computeLiveIns() just computes the live-ins in a LivePhysRegs set.
- addLiveIns() applies the live-ins to a block live-in list.
- computeAndAddLiveIns() is a convenience function combining the other
  two functions and behaving like computeLiveIns() before this patch.

Based on a patch by Krzysztof Parzyszek <kparzysz@codeaurora.org>

Differential Revision: https://reviews.llvm.org/D37034

llvm-svn: 312668

2 files changed, 90 insertions, 3 deletions

diff --git a/llvm/test/CodeGen/Hexagon/branchfolder-insert-impdef.mir b/llvm/test/CodeGen/Hexagon/branchfolder-insert-impdef.mir
new file mode 100644
index 00000000000..bdb0614ede5
--- /dev/null
+++ b/llvm/test/CodeGen/Hexagon/branchfolder-insert-impdef.mir
@@ -0,0 +1,87 @@
+# RUN: llc -march=hexagon -run-pass branch-folder %s -o - -verify-machineinstrs | FileCheck %s
+
+# Branch folding will perform tail merging of bb.1 and bb.2, and bb.2 will
+# become the common tail. The use of R0 in bb.2 is <undef> while the
+# corresponding use in bb.1 is not. The common tail will have the <undef>
+# flag removed, which will cause R0 to become a live-in to bb.2. The problem
+# is that R0 is not live-out from all predecessors of bb.2, namely is not
+# live-out from bb.0. To remedy that, the branch folder should add an
+# IMPLICIT_DEF to that block.
+
+# CHECK-LABEL: name: func0
+# CHECK-LABEL: bb.0:
+# CHECK: %r0 = IMPLICIT_DEF
+# CHECK-LABEL: bb.1:
+# CHECK-LABEL: bb.2:
+# CHECK: liveins: %r0
+# CHECK: PS_storerhabs 0, %r0
+# CHECK: PS_jmpret
+
+---
+name: func0
+tracksRegLiveness: true
+
+body: |
+  bb.0:
+    liveins: %r31
+    successors: %bb.1, %bb.2
+      J2_jumpt undef %p0, %bb.2, implicit-def %pc
+      J2_jump %bb.1, implicit-def %pc
+
+  bb.1:
+    liveins: %r31
+    successors: %bb.3
+      %r0 = L2_loadruh_io undef %r1, 0
+      PS_storerhabs 0, killed %r0
+      J2_jump %bb.3, implicit-def %pc
+
+  bb.2:
+    liveins: %r31
+    successors: %bb.3
+      PS_storerhabs 0, undef %r0
+      J2_jump %bb.3, implicit-def %pc
+
+  bb.3:
+    liveins: %r31
+      PS_jmpret killed %r31, implicit-def %pc
+...
+---
+# CHECK-LABEL: name: func1
+# CHECK-LABEL: bb.1:
+# CHECK: %r0 = IMPLICIT_DEF
+# CHECK-LABEL: bb.2:
+# CHECK-LABEL: bb.3:
+# CHECK: liveins: %r0
+# CHECK: PS_storerhabs 0, killed %r0
+# CHECK: PS_jmpret
+
+name: func1
+tracksRegLiveness: true
+
+body: |
+  bb.0:
+    liveins: %r31
+    successors: %bb.1, %bb.2
+      J2_jumpt undef %p0, %bb.2, implicit-def %pc
+      J2_jump %bb.1, implicit-def %pc
+
+  bb.1:
+    liveins: %r31
+    successors: %bb.3
+      %r1 = A2_tfrsi 1
+      PS_storerhabs 0, undef %r0
+      %r0 = A2_tfrsi 1
+      J2_jump %bb.3, implicit-def %pc
+
+  bb.2:
+    liveins: %r31
+    successors: %bb.3
+      %r0 = L2_loadruh_io undef %r1, 0
+      PS_storerhabs 0, killed %r0
+      %r0 = A2_tfrsi 1
+      J2_jump %bb.3, implicit-def %pc
+
+  bb.3:
+    liveins: %r31
+      PS_jmpret killed %r31, implicit undef %r0, implicit-def %pc
+...
diff --git a/llvm/test/CodeGen/Hexagon/livephysregs-lane-masks2.mir b/llvm/test/CodeGen/Hexagon/livephysregs-lane-masks2.mir
index 58685701655..2b39a0cfc24 100644
--- a/llvm/test/CodeGen/Hexagon/livephysregs-lane-masks2.mir
+++ b/llvm/test/CodeGen/Hexagon/livephysregs-lane-masks2.mir
@@ -13,13 +13,13 @@ tracksRegLiveness: true
 
 body: |
   bb.0:
-    liveins: %p2, %r0
+    liveins: %p0:0x1, %p2, %r0
     successors: %bb.1, %bb.2
         J2_jumpt killed %p2, %bb.1, implicit-def %pc
         J2_jump %bb.2, implicit-def %pc
 
   bb.1:
-    liveins: %r0, %r19
+    liveins: %p0:0x1, %r0, %r19
     successors: %bb.3
         %r2 = A2_tfrsi 4
         %r1 = COPY %r19
@@ -28,7 +28,7 @@ body: |
         J2_jump %bb.3, implicit-def %pc
 
   bb.2:
-    liveins: %r0, %r18
+    liveins: %p0:0x1, %r0, %r18
     successors: %bb.3
         %r2 = A2_tfrsi 5
         %r1 = L2_loadrh_io %r18, 0