Merge pull request #85 from parched/umlo

DAG: correctly legalize UMULO.

Author: alexcrichton

lib/CodeGen/SelectionDAG/LegalizeDAG.cpp

@@ -3490,17 +3490,24 @@ bool SelectionDAGLegalize::ExpandNode(SDNode *Node) {
         LC = RTLIB::MUL_I128;
       assert(LC != RTLIB::UNKNOWN_LIBCALL && "Cannot expand this operation!");
 
-      // The high part is obtained by SRA'ing all but one of the bits of low
-      // part.
-      unsigned LoSize = VT.getSizeInBits();
-      SDValue HiLHS =
-          DAG.getNode(ISD::SRA, dl, VT, LHS,
-                      DAG.getConstant(LoSize - 1, dl,
-                                      TLI.getPointerTy(DAG.getDataLayout())));
-      SDValue HiRHS =
-          DAG.getNode(ISD::SRA, dl, VT, RHS,
-                      DAG.getConstant(LoSize - 1, dl,
-                                      TLI.getPointerTy(DAG.getDataLayout())));
+      SDValue HiLHS;
+      SDValue HiRHS;
+      if (isSigned) {
+        // The high part is obtained by SRA'ing all but one of the bits of low
+        // part.
+        unsigned LoSize = VT.getSizeInBits();
+        HiLHS =
+            DAG.getNode(ISD::SRA, dl, VT, LHS,
+                        DAG.getConstant(LoSize - 1, dl,
+                                        TLI.getPointerTy(DAG.getDataLayout())));
+        HiRHS =
+            DAG.getNode(ISD::SRA, dl, VT, RHS,
+                        DAG.getConstant(LoSize - 1, dl,
+                                        TLI.getPointerTy(DAG.getDataLayout())));
+      } else {
+          HiLHS = DAG.getConstant(0, dl, VT);
+          HiRHS = DAG.getConstant(0, dl, VT);
+      }
 
       // Here we're passing the 2 arguments explicitly as 4 arguments that are
       // pre-lowered to the correct types. This all depends upon WideVT not

test/CodeGen/ARM/v6m-umul-with-overflow.ll

@@ -0,0 +1,16 @@
+; RUN: llc < %s -mtriple=thumbv6m-none-eabi | FileCheck %s
+
+define i1 @unsigned_multiplication_did_overflow(i32, i32) {
+; CHECK-LABEL: unsigned_multiplication_did_overflow:
+entry-block:
+  %2 = tail call { i32, i1 } @llvm.umul.with.overflow.i32(i32 %0, i32 %1)
+  %3 = extractvalue { i32, i1 } %2, 1
+  ret i1 %3
+
+; CHECK: mov{{s?}}    r2, r1
+; CHECK: mov{{s?}}    r1, #0
+; CHECK: mov{{s?}}    r3, {{#0|r1}}
+; CHECK: bl     __aeabi_lmul
+}
+
+declare { i32, i1 } @llvm.umul.with.overflow.i32(i32, i32)