[ARM][LowOverheadLoops] Check scalar predicates

[samparker]

Summary

When trying to remove the loop iteration count, check that the instruction will always execute.

[SjoerdMeijer]

cheers, looks like a good fix to me.

llvm/lib/Target/ARM/ARMLowOverheadLoops.cpp

if (auto *Def = RDA->getReachingMIDef(LoLoop.Start,
                                       LoLoop.Start->getOperand(0).getReg())) {
       SmallPtrSet<MachineInstr*, 4> Remove;
       SmallPtrSet<MachineInstr*, 4> Ignore = { LoLoop.Start, LoLoop.Dec,
                                                LoLoop.End, LoLoop.InsertPt };
       SmallVector<MachineInstr*, 4> Chain = { Def };
       while (!Chain.empty()) {
         MachineInstr *MI = Chain.back();
         Chain.pop_back();
+        if (TII->getPredicate(*MI) != ARMCC::AL)
+          continue;
+
         if (RDA->isSafeToRemove(MI, Remove, Ignore)) {
           for (auto &MO : MI->operands()) {
             if (!MO.isReg() || !MO.isUse() || MO.getReg() == 0)
               continue;
             if (auto *Op = RDA->getReachingMIDef(MI, MO.getReg()))
               Chain.push_back(Op);
           }
           Ignore.insert(MI);

llvm/test/CodeGen/Thumb2/LowOverheadLoops/dont-ignore-vctp.mir

 # NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py
-# RUN: llc -mtriple=thumbv8.1m.main -mattr=+mve -run-pass=arm-low-overhead-loops %s -o - | FileCheck %s
+# RUN: llc -mtriple=thumbv8.1m.main -mattr=+mve -run-pass=arm-low-overhead-loops %s -o - --verify-machineinstrs | FileCheck %s
 
 --- |
   define hidden arm_aapcs_vfpcc void @dont_ignore_vctp(float* %pSrc, float* %pDst, i32 %blockSize) local_unnamed_addr #0 {
   entry:
     %mul = shl i32 %blockSize, 1
     %0 = add i32 %mul, 3
     %1 = icmp slt i32 %mul, 4
     %smin = select i1 %1, i32 %mul, i32 4
body:             |
   ; CHECK-LABEL: name: dont_ignore_vctp
   ; CHECK: bb.0.entry:
   ; CHECK:   successors: %bb.1(0x80000000)
   ; CHECK:   liveins: $lr, $r0, $r1, $r2, $r7
   ; CHECK:   frame-setup tPUSH 14, $noreg, killed $r7, killed $lr, implicit-def $sp, implicit $sp
   ; CHECK:   frame-setup CFI_INSTRUCTION def_cfa_offset 8
   ; CHECK:   frame-setup CFI_INSTRUCTION offset $lr, -4
   ; CHECK:   frame-setup CFI_INSTRUCTION offset $r7, -8
-  ; CHECK:   renamable $r3, dead $cpsr = tLSLri killed renamable $r2, 1, 14, $noreg
-  ; CHECK:   t2IT 11, 8, implicit-def dead $itstate
+  ; CHECK:   renamable $r3, dead $cpsr = tLSLri renamable $r2, 1, 14, $noreg
+  ; CHECK:   renamable $r12 = t2MOVi 4, 14, $noreg, $noreg
+  ; CHECK:   tCMPi8 renamable $r3, 4, 14, $noreg, implicit-def $cpsr
+  ; CHECK:   t2IT 11, 8, implicit-def $itstate
+  ; CHECK:   dead $r12 = t2LSLri killed renamable $r2, 1, 11, killed $cpsr, $noreg, implicit killed renamable $r12, implicit killed $itstate
   ; CHECK:   renamable $r2 = tLEApcrel %const.0, 14, $noreg
   ; CHECK:   renamable $q0 = MVE_VLDRWU32 killed renamable $r2, 0, 0, $noreg :: (load 16 from constant-pool)
   ; CHECK:   $lr = MVE_DLSTP_32 killed renamable $r3
   ; CHECK: bb.1.do.body (align 4):
   ; CHECK:   successors: %bb.1(0x7c000000), %bb.2(0x04000000)
   ; CHECK:   liveins: $lr, $q0, $r0, $r1
   ; CHECK:   renamable $q1 = nnan ninf nsz MVE_VLDRWU32 renamable $r0, 0, 0, $noreg
   ; CHECK:   renamable $q1 = nnan ninf nsz MVE_VMULf32 killed renamable $q1, renamable $q0, 0, $noreg, undef renamable $q1