diff --git a/llvm/lib/Transforms/IPO/ArgumentPromotion.cpp b/llvm/lib/Transforms/IPO/ArgumentPromotion.cpp
--- a/llvm/lib/Transforms/IPO/ArgumentPromotion.cpp
+++ b/llvm/lib/Transforms/IPO/ArgumentPromotion.cpp
@@ -517,8 +517,10 @@
       return false;
 
     int64_t Off = Offset.getSExtValue();
+    Align ArgAlign = Arg->getParamAlign().valueOrOne();
+    Align PartAlign = std::max(LI->getAlign(), ArgAlign);
     auto Pair = ArgParts.try_emplace(
-        Off, ArgPart{Ty, LI->getAlign(), GuaranteedToExecute ? LI : nullptr});
+        Off, ArgPart{Ty, PartAlign, GuaranteedToExecute ? LI : nullptr});
     ArgPart &Part = Pair.first->second;
     bool OffsetNotSeenBefore = Pair.second;
 
@@ -545,20 +547,20 @@
     // because we only allow a single type for a given offset, which also means
     // that the number of accessed bytes will be the same.
     if (!GuaranteedToExecute &&
-        (OffsetNotSeenBefore || Part.Alignment < LI->getAlign())) {
+        (OffsetNotSeenBefore || Part.Alignment < PartAlign)) {
       // We won't be able to prove dereferenceability for negative offsets.
       if (Off < 0)
         return false;
 
       // If the offset is not aligned, an aligned base pointer won't help.
-      if (!isAligned(LI->getAlign(), Off))
+      if (!isAligned(PartAlign, Off))
         return false;
 
       NeededDerefBytes = std::max(NeededDerefBytes, Off + Size.getFixedValue());
-      NeededAlign = std::max(NeededAlign, LI->getAlign());
+      NeededAlign = std::max(NeededAlign, PartAlign);
     }
 
-    Part.Alignment = std::max(Part.Alignment, LI->getAlign());
+    Part.Alignment = std::max(Part.Alignment, PartAlign);
     return true;
   };
 
diff --git a/llvm/test/Transforms/ArgumentPromotion/align.ll b/llvm/test/Transforms/ArgumentPromotion/align.ll
--- a/llvm/test/Transforms/ArgumentPromotion/align.ll
+++ b/llvm/test/Transforms/ArgumentPromotion/align.ll
@@ -1,6 +1,8 @@
 ; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --function-signature --scrub-attributes
 ; RUN: opt -S -argpromotion < %s | FileCheck %s
 
+%struct.ss = type { i32, i64 }
+
 define internal i32 @callee_must_exec(i32* %p) {
 ; CHECK-LABEL: define {{[^@]+}}@callee_must_exec
 ; CHECK-SAME: (i32 [[P_0_VAL:%.*]]) {
@@ -112,3 +114,117 @@
   call i32 @callee_not_guaranteed_aligned(i1 %c, i32* %p)
   ret void
 }
+
+define internal void @callee_load_from_aligned_1(%struct.ss* align 16 %b) {
+; CHECK-LABEL: define {{[^@]+}}@callee_load_from_aligned_1
+; CHECK-SAME: (i32 [[B_0:%.*]]) {
+; CHECK-NEXT:    [[TEMP2:%.*]] = add i32 [[B_0]], 1
+; CHECK-NEXT:    ret void
+;
+  %temp = getelementptr %struct.ss, %struct.ss* %b, i32 0, i32 0
+  %temp1 = load i32, i32* %temp, align 4
+  %temp2 = add i32 %temp1, 1
+  %temp3 = load i32, i32* %temp, align 8
+  ret void
+}
+
+define internal void @callee_load_from_aligned_2(%struct.ss* align 16 %b) {
+; CHECK-LABEL: define {{[^@]+}}@callee_load_from_aligned_2
+; CHECK-SAME: (i32 [[B_0:%.*]]) {
+; CHECK-NEXT:    [[TEMP2:%.*]] = add i32 [[B_0]], 1
+; CHECK-NEXT:    ret void
+;
+  %temp = getelementptr %struct.ss, %struct.ss* %b, i32 0, i32 0
+  %temp1 = load i32, i32* %temp, align 4
+  %temp2 = add i32 %temp1, 1
+  %temp3 = load i32, i32* %temp, align 32
+  ret void
+}
+
+define internal void @callee_load_from_aligned_3(%struct.ss* %b) {
+; CHECK-LABEL: define {{[^@]+}}@callee_load_from_aligned_3
+; CHECK-SAME: (i32 [[B_0:%.*]]) {
+; CHECK-NEXT:    [[TEMP2:%.*]] = add i32 [[B_0]], 1
+; CHECK-NEXT:    ret void
+;
+  %temp = getelementptr %struct.ss, %struct.ss* %b, i32 0, i32 0
+  %temp1 = load i32, i32* %temp, align 4
+  %temp2 = add i32 %temp1, 1
+  %temp3 = load i32, i32* %temp, align 8
+  ret void
+}
+
+define i32 @caller_load_from_aligned() {
+; CHECK-LABEL: define {{[^@]+}}@caller_load_from_aligned
+; CHECK-SAME: () {
+; CHECK-NEXT:    [[S:%.*]] = alloca [[STRUCT_SS:%.*]], align 16
+; CHECK-NEXT:    [[TEMP1:%.*]] = getelementptr [[STRUCT_SS]], %struct.ss* [[S]], i32 0, i32 0
+; CHECK-NEXT:    store i32 1, i32* [[TEMP1]], align 16
+; CHECK-NEXT:    [[TEMP4:%.*]] = getelementptr [[STRUCT_SS]], %struct.ss* [[S]], i32 0, i32 1
+; CHECK-NEXT:    store i64 2, i64* [[TEMP4]], align 4
+; CHECK-NEXT:    [[S_1_0:%.*]] = getelementptr [[STRUCT_SS]], %struct.ss* [[S]], i64 0, i32 0
+; CHECK-NEXT:    [[S_1_0_VAL:%.*]] = load i32, i32* [[S_1_0]], align 16
+; CHECK-NEXT:    call void @callee_load_from_aligned_1(i32 [[S_1_0_VAL]])
+; CHECK-NEXT:    [[S_2_0:%.*]] = getelementptr [[STRUCT_SS]], %struct.ss* [[S]], i64 0, i32 0
+; CHECK-NEXT:    [[S_2_0_VAL:%.*]] = load i32, i32* [[S_2_0]], align 32
+; CHECK-NEXT:    call void @callee_load_from_aligned_2(i32 [[S_2_0_VAL]])
+; CHECK-NEXT:    [[S_3_0:%.*]] = getelementptr [[STRUCT_SS]], %struct.ss* [[S]], i64 0, i32 0
+; CHECK-NEXT:    [[S_3_0_VAL:%.*]] = load i32, i32* [[S_3_0]], align 8
+; CHECK-NEXT:    call void @callee_load_from_aligned_3(i32 [[S_3_0_VAL]])
+; CHECK-NEXT:    ret i32 0
+;
+  %S = alloca %struct.ss, align 16
+  %temp1 = getelementptr %struct.ss, %struct.ss* %S, i32 0, i32 0
+  store i32 1, i32* %temp1, align 16
+  %temp4 = getelementptr %struct.ss, %struct.ss* %S, i32 0, i32 1
+  store i64 2, i64* %temp4, align 4
+  call void @callee_load_from_aligned_1(%struct.ss* %S)
+  call void @callee_load_from_aligned_2(%struct.ss* %S)
+  call void @callee_load_from_aligned_3(%struct.ss* %S)
+  ret i32 0
+}
+
+define internal void @callee_load_first_element(%struct.ss* byval(%struct.ss) align 16 %b) {
+; CHECK-LABEL: define {{[^@]+}}@callee_load_first_element
+; CHECK-SAME: (i32 [[B_0:%.*]], i64 [[B_1:%.*]]) {
+; CHECK-NEXT:    [[B:%.*]] = alloca [[STRUCT_SS:%.*]], align 16
+; CHECK-NEXT:    [[DOT0:%.*]] = getelementptr [[STRUCT_SS]], %struct.ss* [[B]], i32 0, i32 0
+; CHECK-NEXT:    store i32 [[B_0]], i32* [[DOT0]], align 16
+; CHECK-NEXT:    [[DOT1:%.*]] = getelementptr [[STRUCT_SS]], %struct.ss* [[B]], i32 0, i32 1
+; CHECK-NEXT:    store i64 [[B_1]], i64* [[DOT1]], align 4
+; CHECK-NEXT:    [[TEMP:%.*]] = getelementptr [[STRUCT_SS]], %struct.ss* [[B]], i32 0, i32 0
+; CHECK-NEXT:    [[TEMP1:%.*]] = load i32, i32* [[TEMP]], align 8
+; CHECK-NEXT:    [[TEMP2:%.*]] = add i32 [[TEMP1]], 1
+; CHECK-NEXT:    [[TEMP3:%.*]] = load i32, i32* [[TEMP]], align 32
+; CHECK-NEXT:    ret void
+;
+  %temp = getelementptr %struct.ss, %struct.ss* %b, i32 0, i32 0
+  %temp1 = load i32, i32* %temp, align 8
+  %temp2 = add i32 %temp1, 1
+  %temp3 = load i32, i32* %temp, align 32
+  ret void
+}
+
+define i32 @caller_load_first_element() {
+; CHECK-LABEL: define {{[^@]+}}@caller_load_first_element
+; CHECK-SAME: () {
+; CHECK-NEXT:    [[S:%.*]] = alloca [[STRUCT_SS:%.*]], align 16
+; CHECK-NEXT:    [[TEMP1:%.*]] = getelementptr [[STRUCT_SS]], %struct.ss* [[S]], i32 0, i32 0
+; CHECK-NEXT:    store i32 1, i32* [[TEMP1]], align 16
+; CHECK-NEXT:    [[TEMP4:%.*]] = getelementptr [[STRUCT_SS]], %struct.ss* [[S]], i32 0, i32 1
+; CHECK-NEXT:    store i64 2, i64* [[TEMP4]], align 4
+; CHECK-NEXT:    [[S_0:%.*]] = getelementptr [[STRUCT_SS]], %struct.ss* [[S]], i32 0, i32 0
+; CHECK-NEXT:    [[S_0_VAL:%.*]] = load i32, i32* [[S_0]], align 16
+; CHECK-NEXT:    [[S_1:%.*]] = getelementptr [[STRUCT_SS]], %struct.ss* [[S]], i32 0, i32 1
+; CHECK-NEXT:    [[S_1_VAL:%.*]] = load i64, i64* [[S_1]], align 4
+; CHECK-NEXT:    call void @callee_load_first_element(i32 [[S_0_VAL]], i64 [[S_1_VAL]])
+; CHECK-NEXT:    ret i32 0
+;
+  %S = alloca %struct.ss, align 16
+  %temp1 = getelementptr %struct.ss, %struct.ss* %S, i32 0, i32 0
+  store i32 1, i32* %temp1, align 16
+  %temp4 = getelementptr %struct.ss, %struct.ss* %S, i32 0, i32 1
+  store i64 2, i64* %temp4, align 4
+  call void @callee_load_first_element(%struct.ss* byval(%struct.ss) align 16 %S)
+  ret i32 0
+}