diff --git a/llvm/lib/Transforms/Vectorize/VectorCombine.cpp b/llvm/lib/Transforms/Vectorize/VectorCombine.cpp
--- a/llvm/lib/Transforms/Vectorize/VectorCombine.cpp
+++ b/llvm/lib/Transforms/Vectorize/VectorCombine.cpp
@@ -111,6 +111,13 @@
   // TODO: Extend this to match GEP with constant offsets.
   Value *PtrOp = Load->getPointerOperand()->stripPointerCasts();
   assert(isa<PointerType>(PtrOp->getType()) && "Expected a pointer type");
+  unsigned AS = Load->getPointerAddressSpace();
+
+  // If original AS != Load's AS, we can't bitcast the original pointer and have
+  // to use Load's operand instead. Ideally we would want to strip pointer casts
+  // without changing AS, but there's no API to do that ATM.
+  if (AS != PtrOp->getType()->getPointerAddressSpace())
+    PtrOp = Load->getPointerOperand();
 
   Type *ScalarTy = Scalar->getType();
   uint64_t ScalarSize = ScalarTy->getPrimitiveSizeInBits();
@@ -126,7 +133,6 @@
   if (!isSafeToLoadUnconditionally(PtrOp, MinVecTy, Alignment, DL, Load, &DT))
     return false;
 
-  unsigned AS = Load->getPointerAddressSpace();
 
   // Original pattern: insertelt undef, load [free casts of] ScalarPtr, 0
   int OldCost = TTI.getMemoryOpCost(Instruction::Load, ScalarTy, Alignment, AS);
diff --git a/llvm/test/Transforms/VectorCombine/AMDGPU/as-transition.ll b/llvm/test/Transforms/VectorCombine/AMDGPU/as-transition.ll
new file mode 100644
--- /dev/null
+++ b/llvm/test/Transforms/VectorCombine/AMDGPU/as-transition.ll
@@ -0,0 +1,36 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
+; RUN: opt < %s -vector-combine -S -mtriple=amdgcn-amd-amdhsa | FileCheck %s --check-prefixes=CHECK
+
+; ModuleID = 'load-as-transition.ll'
+target datalayout = "e-p:64:64-p1:64:64-p2:32:32-p3:32:32-p4:64:64-p5:32:32-p6:32:32-i64:64-v16:16-v24:32-v32:32-v48:64-v96:128-v192:256-v256:256-v512:512-v1024:1024-v2048:2048-n32:64-S32-A5-ni:7"
+target triple = "amdgcn-amd-amdhsa"
+
+%struct.hoge = type { float }
+
+define protected amdgpu_kernel void @load_from_other_as(<4 x float>* nocapture nonnull %resultptr) local_unnamed_addr #0 {
+; CHECK-LABEL: @load_from_other_as(
+; CHECK-NEXT:  bb:
+; CHECK-NEXT:    [[A:%.*]] = alloca [[STRUCT_HOGE:%.*]], align 4, addrspace(5)
+; CHECK-NEXT:    [[B:%.*]] = addrspacecast [[STRUCT_HOGE]] addrspace(5)* [[A]] to %struct.hoge*
+; CHECK-NEXT:    [[C:%.*]] = getelementptr inbounds [[STRUCT_HOGE]], %struct.hoge* [[B]], i64 0, i32 0
+; CHECK-NEXT:    [[TMP0:%.*]] = bitcast float* [[C]] to <1 x float>*
+; CHECK-NEXT:    [[TMP1:%.*]] = load <1 x float>, <1 x float>* [[TMP0]], align 4
+; CHECK-NEXT:    [[E:%.*]] = shufflevector <1 x float> [[TMP1]], <1 x float> undef, <4 x i32> <i32 0, i32 undef, i32 undef, i32 undef>
+; CHECK-NEXT:    store <4 x float> [[E]], <4 x float>* [[RESULTPTR:%.*]], align 16
+; CHECK-NEXT:    ret void
+;
+bb:
+  %a = alloca %struct.hoge, align 4, addrspace(5)
+  %b = addrspacecast %struct.hoge addrspace(5)* %a to %struct.hoge*
+  %c = getelementptr inbounds %struct.hoge, %struct.hoge* %b, i64 0, i32 0
+  %d = load float, float* %c, align 4
+  %e = insertelement <4 x float> undef, float %d, i32 0
+  store <4 x float> %e, <4 x float>* %resultptr, align 16
+  ret void
+}
+
+attributes #0 = { "use-soft-float"="false" }
+
+!llvm.ident = !{!0}
+
+!0 = !{!"clang version 12.0.0"}
diff --git a/llvm/test/Transforms/VectorCombine/AMDGPU/lit.local.cfg b/llvm/test/Transforms/VectorCombine/AMDGPU/lit.local.cfg
new file mode 100644
--- /dev/null
+++ b/llvm/test/Transforms/VectorCombine/AMDGPU/lit.local.cfg
@@ -0,0 +1,2 @@
+if not 'AMDGPU' in config.root.targets:
+    config.unsupported = True