Index: llvm/test/Transforms/Inline/byval-align.ll
===================================================================
--- /dev/null
+++ llvm/test/Transforms/Inline/byval-align.ll
@@ -0,0 +1,55 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --function-signature
+; RUN: opt -inline -preserve-alignment-assumptions-during-inlining -S < %s | FileCheck %s
+target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64-S128"
+target triple = "x86_64-unknown-linux-gnu"
+
+; Test behavior of inserted alignment assumptions with byval. No
+; assume should be inserted.
+define void @byval_callee(float* byval(float) align 128 nocapture %a, float* %b) #0 {
+; CHECK-LABEL: define {{[^@]+}}@byval_callee
+; CHECK-SAME: (float* nocapture byval(float) align 128 [[A:%.*]], float* [[B:%.*]]) #0
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    [[LOAD:%.*]] = load float, float* [[A]], align 4
+; CHECK-NEXT:    [[B_IDX:%.*]] = getelementptr inbounds float, float* [[B]], i64 8
+; CHECK-NEXT:    [[ADD:%.*]] = fadd float [[LOAD]], 2.000000e+00
+; CHECK-NEXT:    store float [[ADD]], float* [[B_IDX]], align 4
+; CHECK-NEXT:    ret void
+;
+entry:
+  %load = load float, float* %a, align 4
+  %b.idx = getelementptr inbounds float, float* %b, i64 8
+  %add = fadd float %load, 2.0
+  store float %add, float* %b.idx, align 4
+  ret void
+}
+
+define void @byval_caller(float* nocapture align 64 %a, float* %b) #0 {
+; CHECK-LABEL: define {{[^@]+}}@byval_caller
+; CHECK-SAME: (float* nocapture align 64 [[A:%.*]], float* [[B:%.*]]) #0
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    [[A1:%.*]] = alloca float, align 128
+; CHECK-NEXT:    [[TMP0:%.*]] = bitcast float* [[A1]] to i8*
+; CHECK-NEXT:    call void @llvm.lifetime.start.p0i8(i64 4, i8* [[TMP0]])
+; CHECK-NEXT:    [[TMP1:%.*]] = bitcast float* [[A1]] to i8*
+; CHECK-NEXT:    [[TMP2:%.*]] = bitcast float* [[A]] to i8*
+; CHECK-NEXT:    call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 1 [[TMP1]], i8* align 1 [[TMP2]], i64 4, i1 false)
+; CHECK-NEXT:    [[LOAD_I:%.*]] = load float, float* [[A1]], align 4
+; CHECK-NEXT:    [[B_IDX_I:%.*]] = getelementptr inbounds float, float* [[B]], i64 8
+; CHECK-NEXT:    [[ADD_I:%.*]] = fadd float [[LOAD_I]], 2.000000e+00
+; CHECK-NEXT:    store float [[ADD_I]], float* [[B_IDX_I]], align 4
+; CHECK-NEXT:    [[TMP3:%.*]] = bitcast float* [[A1]] to i8*
+; CHECK-NEXT:    call void @llvm.lifetime.end.p0i8(i64 4, i8* [[TMP3]])
+; CHECK-NEXT:    [[CALLER_LOAD:%.*]] = load float, float* [[B]], align 4
+; CHECK-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds float, float* [[A]], i64 7
+; CHECK-NEXT:    store float [[CALLER_LOAD]], float* [[ARRAYIDX]], align 4
+; CHECK-NEXT:    ret void
+;
+entry:
+  call void @byval_callee(float* byval(float) align 128 %a, float* %b)
+  %caller.load = load float, float* %b, align 4
+  %arrayidx = getelementptr inbounds float, float* %a, i64 7
+  store float %caller.load, float* %arrayidx, align 4
+  ret void
+}
+
+attributes #0 = { nounwind uwtable }