[PowerPC] Assume 128bit multiply uses CTR

[TimNN]

Summary

This fixes https://bugs.llvm.org//show_bug.cgi?id=32485

[hfinkel]

A somewhat minified example IR which reproduces the assertion is attached to the linked bug report -- here I would also appreciate some guidance on in what form / where this can be integrated in the regression tests.

Just running llc on the resulting IR in the usual way should be fine.

lib/Target/PowerPC/PPCCTRLoops.cpp

250 ↗

(On Diff #94445)

It looks like we can have a more-targeted fix than this. The problem seems to be restricted to multiply. See below.

317 ↗

(On Diff #94445)

Here add:

case Intrinsic::umul_with_overflow: Opcode = ISD::UMULO; break;
case Intrinsic::smul_with_overflow: Opcode = ISD::SMULO; break;

and I think that should take care of it.

[TimNN]

Updated to a more targeted fix and added a test as suggested.

[TimNN]

@hfinkel: Thanks for the feedback!

I have made the changes recommended and uploaded a new revision. (I though this would trigger another mail but apparently it didn't, so I'm commenting again).

[hfinkel]

In D31790#722438, @TimNN wrote:

@hfinkel: Thanks for the feedback!

I have made the changes recommended and uploaded a new revision. (I though this would trigger another mail but apparently it didn't, so I'm commenting again).

Phabricator e-mails were broken for a while.

LGTM.

[TimNN]

I cannot commit this myself, could someone please do it for me?

llvm/trunk/lib/Target/PowerPC/PPCCTRLoops.cpp

#endif
           case Intrinsic::cos:
             return true;
           case Intrinsic::copysign:
             if (CI->getArgOperand(0)->getType()->getScalarType()->
                 isPPC_FP128Ty())
               return true;
             else
               continue; // ISD::FCOPYSIGN is never a library call.
-          case Intrinsic::sqrt:      Opcode = ISD::FSQRT;      break;
-          case Intrinsic::floor:     Opcode = ISD::FFLOOR;     break;
-          case Intrinsic::ceil:      Opcode = ISD::FCEIL;      break;
-          case Intrinsic::trunc:     Opcode = ISD::FTRUNC;     break;
-          case Intrinsic::rint:      Opcode = ISD::FRINT;      break;
-          case Intrinsic::nearbyint: Opcode = ISD::FNEARBYINT; break;
-          case Intrinsic::round:     Opcode = ISD::FROUND;     break;
-          case Intrinsic::minnum:    Opcode = ISD::FMINNUM;    break;
-          case Intrinsic::maxnum:    Opcode = ISD::FMAXNUM;    break;
+          case Intrinsic::sqrt:               Opcode = ISD::FSQRT;      break;
+          case Intrinsic::floor:              Opcode = ISD::FFLOOR;     break;
+          case Intrinsic::ceil:               Opcode = ISD::FCEIL;      break;
+          case Intrinsic::trunc:              Opcode = ISD::FTRUNC;     break;
+          case Intrinsic::rint:               Opcode = ISD::FRINT;      break;
+          case Intrinsic::nearbyint:          Opcode = ISD::FNEARBYINT; break;
+          case Intrinsic::round:              Opcode = ISD::FROUND;     break;
+          case Intrinsic::minnum:             Opcode = ISD::FMINNUM;    break;
+          case Intrinsic::maxnum:             Opcode = ISD::FMAXNUM;    break;
+          case Intrinsic::umul_with_overflow: Opcode = ISD::UMULO;      break;
+          case Intrinsic::smul_with_overflow: Opcode = ISD::SMULO;      break;
           }
         }
 
         // PowerPC does not use [US]DIVREM or other library calls for
         // operations on regular types which are not otherwise library calls
         // (i.e. soft float or atomics). If adapting for targets that do,
         // additional care is required here.
 

llvm/trunk/test/CodeGen/PowerPC/ctrloop-i128.ll

+; RUN: llc -O1 -verify-machineinstrs < %s
+target datalayout = "E-m:e-i64:64-n32:64"
+target triple = "powerpc64-unknown-linux-gnu"
+
+; Function Attrs: uwtable
+define fastcc void @_Crash_Fn() unnamed_addr #0 {
+entry-block:
+  br label %_Label_0
+
+_Label_0:                                         ; preds = %_Label_0, %entry-block
+  %result.0138 = phi i128 [ %5, %_Label_0 ], [ 0, %entry-block ]
+  %iter.sroa.0.0137 = phi i8* [ %0, %_Label_0 ], [ undef, %entry-block ]
+  %0 = getelementptr inbounds i8, i8* %iter.sroa.0.0137, i64 1
+  %1 = tail call { i128, i1 } @llvm.smul.with.overflow.i128(i128 %result.0138, i128 undef) #2
+  %2 = extractvalue { i128, i1 } %1, 0
+  %3 = tail call { i128, i1 } @llvm.sadd.with.overflow.i128(i128 %2, i128 0) #2
+  %4 = extractvalue { i128, i1 } %3, 1
+  %5 = extractvalue { i128, i1 } %3, 0
+  %6 = icmp eq i8* %0, null
+  br i1 %6, label %bb66.loopexit, label %_Label_0
+
+bb66.loopexit:                                    ; preds = %_Label_0
+  unreachable
+}
+
+; Function Attrs: nounwind readnone
+declare { i128, i1 } @llvm.sadd.with.overflow.i128(i128, i128) #1
+
+; Function Attrs: nounwind readnone
+declare { i128, i1 } @llvm.smul.with.overflow.i128(i128, i128) #1
+
+attributes #0 = { uwtable }
+attributes #1 = { nounwind readnone }
+attributes #2 = { nounwind }