diff --git a/llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp b/llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
--- a/llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
+++ b/llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
@@ -17658,7 +17658,11 @@
 
       bool IsFastSt = false;
       bool IsFastLd = false;
-      if (TLI.isTypeLegal(StoreTy) &&
+      // Don't try vector types if we need a rotate. We may still fail the
+      // legality checks for the integer type, but we can't handle the rotate
+      // case with vectors.
+      // FIXME: We could use a shuffle in place of the rotate.
+      if (!NeedRotate && TLI.isTypeLegal(StoreTy) &&
           TLI.canMergeStoresTo(FirstStoreAS, StoreTy,
                                DAG.getMachineFunction()) &&
           TLI.allowsMemoryAccess(Context, DL, StoreTy,
diff --git a/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-store-merge-crash.ll b/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-store-merge-crash.ll
new file mode 100644
--- /dev/null
+++ b/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-store-merge-crash.ll
@@ -0,0 +1,31 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; RUN: llc < %s -mtriple=riscv64 -mattr=+experimental-zbb,+experimental-v \
+; RUN:     -riscv-v-vector-bits-min=128 | FileCheck %s
+
+; This test loads to values and stores them in reversed order. This previously
+; asserted because part of DAGCombiner::tryStoreMerge thinks we can use an i64
+; rotate, but the loads aren't sufficiently aligned. So then it tried to use
+; a vector type, but that can't handle the swapped case.
+
+@foo = global [2 x i32] zeroinitializer, align 4
+@bar = global [2 x i32] zeroinitializer, align 4
+
+define void @baz() nounwind {
+; CHECK-LABEL: baz:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    lui a0, %hi(foo)
+; CHECK-NEXT:    addi a1, a0, %lo(foo)
+; CHECK-NEXT:    lw a1, 4(a1)
+; CHECK-NEXT:    lw a0, %lo(foo)(a0)
+; CHECK-NEXT:    lui a2, %hi(bar)
+; CHECK-NEXT:    sw a1, %lo(bar)(a2)
+; CHECK-NEXT:    addi a1, a2, %lo(bar)
+; CHECK-NEXT:    sw a0, 4(a1)
+; CHECK-NEXT:    ret
+entry:
+  %0 = load i32, i32* getelementptr inbounds ([2 x i32], [2 x i32]* @foo, i64 0, i64 1), align 4
+  store i32 %0, i32* getelementptr inbounds ([2 x i32], [2 x i32]* @bar, i64 0, i64 0), align 4
+  %1 = load i32, i32* getelementptr inbounds ([2 x i32], [2 x i32]* @foo, i64 0, i64 0), align 4
+  store i32 %1, i32* getelementptr inbounds ([2 x i32], [2 x i32]* @bar, i64 0, i64 1), align 4
+  ret void
+}