Index: llvm/lib/CodeGen/SelectionDAG/SelectionDAGBuilder.cpp
===================================================================
--- llvm/lib/CodeGen/SelectionDAG/SelectionDAGBuilder.cpp
+++ llvm/lib/CodeGen/SelectionDAG/SelectionDAGBuilder.cpp
@@ -694,8 +694,12 @@
       // prevents it from being picked up by the earlier bitcast case.
       if (ValueVT.getVectorElementCount().isScalar() &&
           (!ValueVT.isFloatingPoint() || !PartVT.isInteger())) {
-        Val = DAG.getNode(ISD::EXTRACT_VECTOR_ELT, DL, PartVT, Val,
+        EVT ExtractVT = ValueVT.getVectorElementType();
+        Val = DAG.getNode(ISD::EXTRACT_VECTOR_ELT, DL, ExtractVT, Val,
                           DAG.getVectorIdxConstant(0, DL));
+
+        if (ExtractVT.getSizeInBits() != PartVT.getSizeInBits())
+          Val = DAG.getAnyExtOrTrunc(Val, DL, PartVT);
       } else {
         uint64_t ValueSize = ValueVT.getFixedSizeInBits();
         assert(PartVT.getFixedSizeInBits() > ValueSize &&
Index: llvm/test/CodeGen/AMDGPU/dagcombine-v1i8-extractvecelt-crash.ll
===================================================================
--- /dev/null
+++ llvm/test/CodeGen/AMDGPU/dagcombine-v1i8-extractvecelt-crash.ll
@@ -0,0 +1,47 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; RUN: llc -march=amdgcn -mcpu=gfx908 < %s | FileCheck %s
+
+; Regression test for a specific SelectionDAGBuilder Crash for
+; when <1 x i8> needs to be "split" to 1 i32 part.
+;
+; Before the fix, an illegal extract vector elt was generated which
+; later crashed the DAG Combiner.
+;
+;   t4: i32 = extract_vector_elt t10, Constant:i32<0>
+;
+; Now, the SelectionDAGBuilder should emit a i8 extract_vector_elt
+; and extend it to i32 after.
+
+define void @wombat(i1 %cond, <1 x i8> addrspace(5)* %addr) {
+; CHECK-LABEL: wombat:
+; CHECK:       ; %bb.0: ; %entry
+; CHECK-NEXT:    s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; CHECK-NEXT:    buffer_load_ubyte v2, v1, s[0:3], 0 offen
+; CHECK-NEXT:    v_and_b32_e32 v0, 1, v0
+; CHECK-NEXT:    v_cmp_eq_u32_e32 vcc, 1, v0
+; CHECK-NEXT:    s_xor_b64 s[6:7], vcc, -1
+; CHECK-NEXT:    s_mov_b64 s[4:5], 0
+; CHECK-NEXT:  .LBB0_1: ; %loop
+; CHECK-NEXT:    ; =>This Inner Loop Header: Depth=1
+; CHECK-NEXT:    s_and_b64 s[8:9], exec, s[6:7]
+; CHECK-NEXT:    s_or_b64 s[4:5], s[8:9], s[4:5]
+; CHECK-NEXT:    s_andn2_b64 exec, exec, s[4:5]
+; CHECK-NEXT:    s_cbranch_execnz .LBB0_1
+; CHECK-NEXT:  ; %bb.2: ; %end
+; CHECK-NEXT:    s_or_b64 exec, exec, s[4:5]
+; CHECK-NEXT:    s_waitcnt vmcnt(0)
+; CHECK-NEXT:    buffer_store_byte v2, v1, s[0:3], 0 offen
+; CHECK-NEXT:    s_waitcnt vmcnt(0)
+; CHECK-NEXT:    s_setpc_b64 s[30:31]
+entry:
+  br label %loop
+
+loop:
+  %load = load <1 x i8>, <1 x i8> addrspace(5)* %addr, align 1
+  store <1 x i8> poison, <1 x i8> addrspace(5)* %addr, align 1
+  store <1 x i8> %load, <1 x i8> addrspace(5)* %addr, align 1
+  br i1 %cond, label %loop, label %end
+
+end:
+  ret void
+}