[MachinePipeliner] Fix order for nodes with Anti dependence in same c…

…ycle

Summary:
Problem exposed in PowerPC functional testing.

We did not consider Anti dependence for nodes in same cycle,
so we may end up generating bad machine code.
eg: the reduced test won't verify.

*** Bad machine code: Using an undefined physical register ***
- function:    lame_encode_buffer_interleaved
- basic block: %bb.4  (0x4bde4e12928)
- instruction: %29:gprc = ADDZE %27:gprc, implicit-def dead $carry, implicit $carry
- operand 3:   implicit $carry

Reviewers: bcahoon, kparzysz, hfinkel

Subscribers: MaskRay, wuzish, nemanjai, hiraditya, llvm-commits

Tags: #llvm

Differential Revision: https://reviews.llvm.org/D64192

llvm-svn: 365859

llvm/lib/CodeGen/MachinePipeliner.cpp

@@ -3559,6 +3559,14 @@ void SMSchedule::orderDependence(SwingSchedulerDAG *SSD, SUnit *SU,
         if (Pos < MoveUse)
           MoveUse = Pos;
       }
+      // We did not handle HW dependences in previous for loop,
+      // and we normally set Latency = 0 for Anti deps,
+      // so may have nodes in same cycle with Anti denpendent on HW regs.
+      else if (S.getKind() == SDep::Anti && stageScheduled(*I) == StageInst1) {
+        OrderBeforeUse = true;
+        if ((MoveUse == 0) || (Pos < MoveUse))
+          MoveUse = Pos;
+      }
     }
     for (auto &P : SU->Preds) {
       if (P.getSUnit() != *I)

llvm/test/CodeGen/PowerPC/sms-grp-order.ll

@@ -0,0 +1,48 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; RUN: llc < %s -mtriple=powerpc64le-unknown-linux-gnu -verify-machineinstrs\
+; RUN:       -mcpu=pwr9 --ppc-enable-pipeliner | FileCheck %s
+
+define void @lame_encode_buffer_interleaved() local_unnamed_addr {
+; CHECK-LABEL: lame_encode_buffer_interleaved:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    lhz 3, 0(0)
+; CHECK-NEXT:    li 5, 1
+; CHECK-NEXT:    sldi 5, 5, 62
+; CHECK-NEXT:    lhz 4, 0(3)
+; CHECK-NEXT:    mtctr 5
+; CHECK-NEXT:    .p2align 5
+; CHECK-NEXT:  .LBB0_1: #
+; CHECK-NEXT:    extsh 3, 3
+; CHECK-NEXT:    extsh 4, 4
+; CHECK-NEXT:    srawi 3, 3, 1
+; CHECK-NEXT:    addze 3, 3
+; CHECK-NEXT:    srawi 4, 4, 1
+; CHECK-NEXT:    addze 4, 4
+; CHECK-NEXT:    bdnz .LBB0_1
+; CHECK-NEXT:  # %bb.2:
+; CHECK-NEXT:    sth 3, 0(0)
+; CHECK-NEXT:    sth 4, 0(3)
+; CHECK-NEXT:    blr
+  br label %1
+
+1:                                                ; preds = %1, %0
+  %2 = phi i64 [ 0, %0 ], [ %13, %1 ]
+  %3 = load i16, i16* null, align 2
+  %4 = load i16, i16* undef, align 2
+  %5 = sext i16 %3 to i32
+  %6 = sext i16 %4 to i32
+  %7 = add nsw i32 0, %5
+  %8 = add nsw i32 0, %6
+  %9 = sdiv i32 %7, 2
+  %10 = sdiv i32 %8, 2
+  %11 = trunc i32 %9 to i16
+  %12 = trunc i32 %10 to i16
+  store i16 %11, i16* null, align 2
+  store i16 %12, i16* undef, align 2
+  %13 = add i64 %2, 4
+  %14 = icmp eq i64 %13, 0
+  br i1 %14, label %15, label %1
+
+15:                                               ; preds = %1
+  ret void
+}