Index: lib/Transforms/Scalar/SROA.cpp
===================================================================
--- lib/Transforms/Scalar/SROA.cpp
+++ lib/Transforms/Scalar/SROA.cpp
@@ -1950,7 +1950,7 @@
                                             bool &WholeAllocaOp) {
   uint64_t Size = DL.getTypeStoreSize(AllocaTy);
 
-  uint64_t RelBegin = S.beginOffset() - AllocBeginOffset;
+  int64_t RelBegin = S.beginOffset() - AllocBeginOffset;
   uint64_t RelEnd = S.endOffset() - AllocBeginOffset;
 
   // We can't reasonably handle cases where the load or store extends past
@@ -1966,6 +1966,9 @@
     // We can't handle loads that extend past the allocated memory.
     if (DL.getTypeStoreSize(LI->getType()) > Size)
       return false;
+    // We can't handle split slice tails.
+    if (RelBegin < 0)
+      return false;
     // Note that we don't count vector loads or stores as whole-alloca
     // operations which enable integer widening because we would prefer to use
     // vector widening instead.
@@ -1987,6 +1990,9 @@
     // We can't handle stores that extend past the allocated memory.
     if (DL.getTypeStoreSize(ValueTy) > Size)
       return false;
+    // We can't handle split slice tails.
+    if (RelBegin < 0)
+      return false;
     // Note that we don't count vector loads or stores as whole-alloca
     // operations which enable integer widening because we would prefer to use
     // vector widening instead.
Index: test/Transforms/SROA/pr37267.ll
===================================================================
--- /dev/null
+++ test/Transforms/SROA/pr37267.ll
@@ -0,0 +1,23 @@
+; RUN: opt < %s -sroa -disable-output
+target datalayout = "E-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-n32:64-S128"
+target triple = "sparcv9-sun-solaris"
+
+; PR37267
+; Check that we don't crash on this test.
+
+define void @f2() {
+bb1:
+  %a.3 = alloca [6 x i16], align 1
+  %_tmp3 = getelementptr inbounds [6 x i16], [6 x i16]* %a.3, i16 0, i16 1
+  %_tmp5 = bitcast i16* %_tmp3 to i32*
+  store i32 131074, i32* %_tmp5, align 1
+  %_tmp8 = getelementptr inbounds [6 x i16], [6 x i16]* %a.3, i16 0, i16 4
+  %_tmp10 = bitcast i16* %_tmp8 to i32*
+  store i32 131074, i32* %_tmp10, align 1
+  %_tmp12 = getelementptr inbounds [6 x i16], [6 x i16]* %a.3, i16 0, i16 4
+  %_tmp13 = load i16, i16* %_tmp12, align 1
+  %_tmp15 = getelementptr inbounds [6 x i16], [6 x i16]* %a.3, i16 0, i16 1
+  %_tmp16 = load i16, i16* %_tmp15, align 1
+  ret void
+}
+