diff --git a/llvm/include/llvm/IR/DataLayout.h b/llvm/include/llvm/IR/DataLayout.h
--- a/llvm/include/llvm/IR/DataLayout.h
+++ b/llvm/include/llvm/IR/DataLayout.h
@@ -453,6 +453,14 @@
     return 8 * getTypeStoreSize(Ty);
   }
 
+  /// Returns true if no extra padding bits are needed when storing the
+  /// specified type.
+  ///
+  /// For example, returns false for i19 that has a 24-bit store size.
+  bool isTypeStoreSized(Type *Ty) const {
+    return getTypeSizeInBits(Ty) == getTypeStoreSizeInBits(Ty);
+  }
+
   /// Returns the offset in bytes between successive objects of the
   /// specified type, including alignment padding.
   ///
diff --git a/llvm/lib/Transforms/Scalar/DeadStoreElimination.cpp b/llvm/lib/Transforms/Scalar/DeadStoreElimination.cpp
--- a/llvm/lib/Transforms/Scalar/DeadStoreElimination.cpp
+++ b/llvm/lib/Transforms/Scalar/DeadStoreElimination.cpp
@@ -1211,12 +1211,15 @@
           auto *Earlier = dyn_cast<StoreInst>(DepWrite);
           auto *Later = dyn_cast<StoreInst>(Inst);
           if (Earlier && isa<ConstantInt>(Earlier->getValueOperand()) &&
+              DL.isTypeStoreSized(Earlier->getValueOperand()->getType()) &&
               Later && isa<ConstantInt>(Later->getValueOperand()) &&
+              DL.isTypeStoreSized(Later->getValueOperand()->getType()) &&
               memoryIsNotModifiedBetween(Earlier, Later, AA)) {
             // If the store we find is:
             //   a) partially overwritten by the store to 'Loc'
             //   b) the later store is fully contained in the earlier one and
             //   c) they both have a constant value
+            //   d) none of the two stores need padding
             // Merge the two stores, replacing the earlier store's value with a
             // merge of both values.
             // TODO: Deal with other constant types (vectors, etc), and probably
diff --git a/llvm/test/Transforms/DeadStoreElimination/PartialStore2.ll b/llvm/test/Transforms/DeadStoreElimination/PartialStore2.ll
new file mode 100644
--- /dev/null
+++ b/llvm/test/Transforms/DeadStoreElimination/PartialStore2.ll
@@ -0,0 +1,55 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
+; RUN: opt < %s --data-layout "e" -dse -enable-dse-partial-store-merging=true -S | FileCheck --check-prefix CHECK --check-prefix CHECK-LE %s
+; RUN: opt < %s --data-layout "E" -dse -enable-dse-partial-store-merging=true -S | FileCheck --check-prefix CHECK --check-prefix CHECK-BE %s
+
+; This test used to hit an assertion (see PR41949).
+;
+; Better safe than sorry, do not assume anything about the padding for the
+; i28 store that has 32 bits as store size.
+define void @test1(i32* %p) {
+; CHECK-LABEL: @test1(
+; CHECK-NEXT:    [[A:%.*]] = alloca i32
+; CHECK-NEXT:    [[B:%.*]] = bitcast i32* [[A]] to i28*
+; CHECK-NEXT:    [[C:%.*]] = bitcast i32* [[A]] to { i16, i16 }*
+; CHECK-NEXT:    [[C1:%.*]] = getelementptr inbounds { i16, i16 }, { i16, i16 }* [[C]], i32 0, i32 1
+; CHECK-NEXT:    store i28 10, i28* [[B]]
+; CHECK-NEXT:    store i16 20, i16* [[C1]]
+; CHECK-NEXT:    call void @test1(i32* [[A]])
+; CHECK-NEXT:    ret void
+;
+  %a = alloca i32
+  %b = bitcast i32* %a to i28*
+  %c = bitcast i32* %a to { i16, i16 }*
+  %c1 = getelementptr inbounds { i16, i16 }, { i16, i16 }* %c, i32 0, i32 1
+  store i28 10, i28* %b
+  store i16 20, i16* %c1
+
+  call void @test1(i32* %a)
+  ret void
+}
+
+
+; This test used to mis-compile (see PR41949).
+;
+; Better safe than sorry, do not assume anything about the padding for the
+; i12 store that has 16 bits as store size.
+define void @test2(i32* %p) {
+; CHECK-LABEL: @test2(
+; CHECK-NEXT:    [[U:%.*]] = alloca i32
+; CHECK-NEXT:    [[A:%.*]] = bitcast i32* [[U]] to i32*
+; CHECK-NEXT:    [[B:%.*]] = bitcast i32* [[U]] to i12*
+; CHECK-NEXT:    store i32 -1, i32* [[A]]
+; CHECK-NEXT:    store i12 20, i12* [[B]]
+; CHECK-NEXT:    call void @test2(i32* [[U]])
+; CHECK-NEXT:    ret void
+;
+  %u = alloca i32
+  %a = bitcast i32* %u to i32*
+  %b = bitcast i32* %u to i12*
+  store i32 -1, i32* %a
+  store i12 20, i12* %b
+
+  call void @test2(i32* %u)
+  ret void
+}
+