diff --git a/llvm/lib/Target/PowerPC/PPCISelLowering.cpp b/llvm/lib/Target/PowerPC/PPCISelLowering.cpp
--- a/llvm/lib/Target/PowerPC/PPCISelLowering.cpp
+++ b/llvm/lib/Target/PowerPC/PPCISelLowering.cpp
@@ -6861,9 +6861,14 @@
 
     const unsigned ByValSize = ArgFlags.getByValSize();
 
-    // An empty aggregate parameter takes up no storage and no registers.
-    if (ByValSize == 0)
+    // An empty aggregate parameter takes up no storage and no registers,
+    // but needs a MemLoc for a stack slot for the formal arguments side.
+    if (ByValSize == 0) {
+      State.addLoc(CCValAssign::getMem(ValNo, MVT::INVALID_SIMPLE_VALUE_TYPE,
+                                       State.getNextStackOffset(), RegVT,
+                                       LocInfo));
       return false;
+    }
 
     if (ByValSize <= PtrByteSize) {
       State.AllocateStack(PtrByteSize, PtrByteSize);
@@ -6978,6 +6983,24 @@
   return DAG.getNode(ISD::TRUNCATE, dl, ValVT, ArgValue);
 }
 
+static unsigned mapArgRegToOffsetAIX(unsigned Reg, const PPCFrameLowering *FL) {
+  const unsigned LASize = FL->getLinkageSize();
+
+  if (PPC::GPRCRegClass.contains(Reg)) {
+    assert(Reg >= PPC::R3 && Reg <= PPC::R10 &&
+           "Reg must be a valid argument register!");
+    return LASize + 4 * (Reg - PPC::R3);
+  }
+
+  if (PPC::G8RCRegClass.contains(Reg)) {
+    assert(Reg >= PPC::X3 && Reg <= PPC::X10 &&
+           "Reg must be a valid argument register!");
+    return LASize + 8 * (Reg - PPC::X3);
+  }
+
+  llvm_unreachable("Only general purpose registers expected.");
+}
+
 SDValue PPCTargetLowering::LowerFormalArguments_AIX(
     SDValue Chain, CallingConv::ID CallConv, bool isVarArg,
     const SmallVectorImpl<ISD::InputArg> &Ins, const SDLoc &dl,
@@ -7015,12 +7038,12 @@
   CCInfo.AllocateStack(LinkageSize, PtrByteSize);
   CCInfo.AnalyzeFormalArguments(Ins, CC_AIX);
 
+  SmallVector<SDValue, 8> MemOps;
+
   for (CCValAssign &VA : ArgLocs) {
     EVT ValVT = VA.getValVT();
     MVT LocVT = VA.getLocVT();
     ISD::ArgFlagsTy Flags = Ins[VA.getValNo()].Flags;
-    assert(!Flags.isByVal() &&
-           "Passing structure by value is unimplemented for formal arguments.");
     assert((VA.isRegLoc() || VA.isMemLoc()) &&
            "Unexpected location for function call argument.");
 
@@ -7033,6 +7056,59 @@
     if (VA.isMemLoc() && VA.needsCustom())
       continue;
 
+    if (Flags.isByVal() && VA.isMemLoc()) {
+      if (Flags.getByValSize() != 0)
+        report_fatal_error(
+            "ByVal arguments passed on stack not implemented yet");
+
+      const int FI = MF.getFrameInfo().CreateFixedObject(
+          PtrByteSize, VA.getLocMemOffset(), /* IsImmutable */ false,
+          /* IsAliased */ true);
+      SDValue FIN = DAG.getFrameIndex(FI, PtrVT);
+      InVals.push_back(FIN);
+
+      continue;
+    }
+
+    if (Flags.isByVal()) {
+      assert(VA.isRegLoc() && "MemLocs should already be handled.");
+
+      const unsigned ByValSize = Flags.getByValSize();
+      if (ByValSize > PtrByteSize)
+        report_fatal_error("Formal arguments greater then register size not "
+                           "implemented yet.");
+
+      const MCPhysReg ArgReg = VA.getLocReg();
+      const PPCFrameLowering *FL = Subtarget.getFrameLowering();
+      const unsigned Offset = mapArgRegToOffsetAIX(ArgReg, FL);
+
+      const unsigned StackSize = alignTo(ByValSize, PtrByteSize);
+      const int FI = MF.getFrameInfo().CreateFixedObject(
+          StackSize, Offset, /* IsImmutable */ false, /* IsAliased */ true);
+      SDValue FIN = DAG.getFrameIndex(FI, PtrVT);
+
+      InVals.push_back(FIN);
+
+      const unsigned VReg = MF.addLiveIn(ArgReg, IsPPC64 ? &PPC::G8RCRegClass
+                                                         : &PPC::GPRCRegClass);
+
+      // Since the callers side has left justified the aggregate in the
+      // register, we can simply store the entire register into the stack
+      // slot.
+      // The store to the fixedstack object is needed becuase accessing a
+      // field of the ByVal will use a gep and load. Ideally we will optimize
+      // to extracting the value from the register directly, and elide the
+      // stores when the arguments address is not taken, but that will need to
+      // be future work.
+      SDValue CopyFrom = DAG.getCopyFromReg(Chain, dl, VReg, LocVT);
+      SDValue Store =
+          DAG.getStore(CopyFrom.getValue(1), dl, CopyFrom, FIN,
+                       MachinePointerInfo::getFixedStack(MF, FI, 0));
+
+      MemOps.push_back(Store);
+      continue;
+    }
+
     if (VA.isRegLoc()) {
       MVT::SimpleValueType SVT = ValVT.getSimpleVT().SimpleTy;
       unsigned VReg =
@@ -7080,6 +7156,9 @@
   PPCFunctionInfo *FuncInfo = MF.getInfo<PPCFunctionInfo>();
   FuncInfo->setMinReservedArea(CallerReservedArea);
 
+  if (!MemOps.empty())
+    Chain = DAG.getNode(ISD::TokenFactor, dl, MVT::Other, MemOps);
+
   return Chain;
 }
 
@@ -7156,8 +7235,13 @@
 
     if (Flags.isByVal()) {
       const unsigned ByValSize = Flags.getByValSize();
+
+      // Nothing to do for zero-sized ByVals on the caller side.
+      if (!ByValSize)
+        continue;
+
       assert(
-          VA.isRegLoc() && ByValSize > 0 && ByValSize <= PtrByteSize &&
+          VA.isRegLoc() && ByValSize <= PtrByteSize &&
           "Pass-by-value arguments are only supported in a single register.");
 
       // Loads must be a power-of-2 size and cannot be larger than the
diff --git a/llvm/test/CodeGen/PowerPC/aix-cc-byval.ll b/llvm/test/CodeGen/PowerPC/aix-cc-byval.ll
--- a/llvm/test/CodeGen/PowerPC/aix-cc-byval.ll
+++ b/llvm/test/CodeGen/PowerPC/aix-cc-byval.ll
@@ -22,11 +22,10 @@
 define void @call_test_byval_1Byte() {
 entry:
   %s0 = alloca %struct.S0, align 8
-  call void @test_byval_1Byte(%struct.S0* byval(%struct.S0) align 1 %s0, %struct.S1* byval(%struct.S1) align 1 @gS1)
+  %call = call zeroext i8 @test_byval_1Byte(%struct.S0* byval(%struct.S0) align 1 %s0, %struct.S1* byval(%struct.S1) align 1 @gS1)
   ret void
 }
 
-declare void @test_byval_1Byte(%struct.S0* byval(%struct.S0) align 1, %struct.S1* byval(%struct.S1) align 1)
 
 ; CHECK-LABEL: name: call_test_byval_1Byte{{.*}}
 
@@ -63,18 +62,59 @@
 ; ASM64-NEXT:  nop
 ; ASM64-NEXT:  addi 1, 1, 128
 
+
+define zeroext i8 @test_byval_1Byte(%struct.S0* byval(%struct.S0) align 1 %s0, %struct.S1* byval(%struct.S1) align 1 %s) {
+entry:
+  %arrayidx = getelementptr inbounds %struct.S1, %struct.S1* %s, i32 0, i32 0, i32 0
+  %0 = load i8, i8* %arrayidx, align 1
+  ret i8 %0
+}
+
+; CHECK-LABEL: name:            test_byval_1Byte
+
+; 32BIT:       fixedStack:
+; 32BIT-NEXT:    - { id: 0, type: default, offset: 24, size: 4, alignment: 8, stack-id: default,
+; 32BIT-NEXT:        isImmutable: false, isAliased: true, callee-saved-register: '', callee-saved-restored: true,
+; 32BIT:         - { id: 1, type: default, offset: 24, size: 4, alignment: 8, stack-id: default,
+; 32BIT-NEXT:        isImmutable: false, isAliased: true, callee-saved-register: '', callee-saved-restored: true,
+
+; 32BIT:       bb.0.entry:
+; 32BIT-NEXT:    liveins: $r3
+; 32BIT:         STW killed renamable $r3, 0, %fixed-stack.0 :: (store 4 into %fixed-stack.0, align 8)
+; 32BIT-NEXT:    renamable $r3 = LBZ 0,  %fixed-stack.0 :: (dereferenceable load 1
+; 32BIT-NEXT:    BLR
+
+; 64BIT:       fixedStack:
+; 64BIT-NEXT:    - { id: 0, type: default, offset: 48, size: 8, alignment: 16, stack-id: default,
+; 64BIT-NEXT:        isImmutable: false, isAliased: true, callee-saved-register: '', callee-saved-restored: true,
+; 64BIT:         - { id: 1, type: default, offset: 48, size: 8, alignment: 16, stack-id: default,
+; 64BIT-NEXT:        isImmutable: false, isAliased: true, callee-saved-register: '', callee-saved-restored: true,
+
+; 64BIT:      bb.0.entry:
+; 64BIT-NEXT:   liveins: $x3
+; 64BIT:        STD killed renamable $x3, 0, %fixed-stack.0 :: (store 8 into %fixed-stack.0, align 16)
+; 64BIT-NEXT:   renamable $x3 = LBZ8 0, %fixed-stack.0 :: (dereferenceable load 1
+
+; CHECKASM-LABEL: .test_byval_1Byte:
+
+; ASM32:        stw 3, 24(1)
+; ASM32-NEXT:   lbz 3, 24(1)
+; ASM32-NEXT:   blr
+
+; ASM64:        std 3, 48(1)
+; ASM64-NEXT:   lbz 3, 48(1)
+; ASM64-NEXT:   blr
+
 %struct.S2 = type { [2 x i8] }
 
 @gS2 = external global %struct.S2, align 1
 
 define void @call_test_byval_2Byte() {
 entry:
-  call void @test_byval_2Byte(%struct.S2* byval(%struct.S2) align 1 @gS2)
+  %call = call zeroext i8 @test_byval_2Byte(%struct.S2* byval(%struct.S2) align 1 @gS2)
   ret void
 }
 
-declare void @test_byval_2Byte(%struct.S2* byval(%struct.S2) align 1)
-
 ; CHECK-LABEL: name: call_test_byval_2Byte{{.*}}
 
 ; 32BIT:       ADJCALLSTACKDOWN 56, 0, implicit-def dead $r1, implicit $r1
@@ -110,18 +150,51 @@
 ; ASM64-NEXT:  nop
 ; ASM64-NEXT:  addi 1, 1, 112
 
-%struct.S3 = type <{ i8, i16 }>
 
+define zeroext i8 @test_byval_2Byte(%struct.S2* byval(%struct.S2) align 1 %s) {
+entry:
+  %arrayidx = getelementptr inbounds %struct.S2, %struct.S2* %s, i32 0, i32 0, i32 1
+  %0 = load i8, i8* %arrayidx, align 1
+  ret i8 %0
+}
+
+; CHECK-LABEL: name:            test_byval_2Byte
+; 32BIT:      fixedStack:
+; 32BIT-NEXT:   - { id: 0, type: default, offset: 24, size: 4, alignment: 8, stack-id: default,
+
+; 32BIT:      bb.0.entry:
+; 32BIT-NEXT:   liveins: $r3
+; 32BIT:        STW killed renamable $r3, 0, %fixed-stack.0 :: (store 4 into %fixed-stack.0, align 8)
+; 32BIT-NEXT:   renamable $r3 = LBZ 1, %fixed-stack.0 :: (dereferenceable load 1
+
+; 64BIT:      fixedStack:
+; 64BIT-NEXT:   - { id: 0, type: default, offset: 48, size: 8, alignment: 16, stack-id: default,
+
+; 64BIT:      bb.0.entry:
+; 64BIT-NEXT:   liveins: $x3
+; 64BIT:        STD killed renamable $x3, 0, %fixed-stack.0 :: (store 8 into %fixed-stack.0, align 16)
+; 64BIT-NEXT:   renamable $x3 = LBZ8 1, %fixed-stack.0 :: (dereferenceable load 1
+
+; CHECKASM-LABEL: .test_byval_2Byte:
+
+; ASM32:        stw 3, 24(1)
+; ASM32-NEXT:   lbz 3, 25(1)
+; ASM32-NEXT:   blr
+
+; ASM64:        std 3, 48(1)
+; ASM64-NEXT:   lbz 3, 49(1)
+; ASM64-NEXT:   blr
+
+
+%struct.S3 = type <{ i8, i16 }>
 @gS3 = external global %struct.S3, align 1
 
 define void @call_test_byval_3Byte() {
 entry:
-  call void @test_byval_3Byte(%struct.S3* byval(%struct.S3) align 1 @gS3)
+  %call = call zeroext i16 @test_byval_3Byte(%struct.S3* byval(%struct.S3) align 1 @gS3)
   ret void
 }
 
-declare void @test_byval_3Byte(%struct.S3* byval(%struct.S3) align 1)
-
 ; CHECK-LABEL: name: call_test_byval_3Byte{{.*}}
 
 ; The DAG block permits some invalid inputs for the benefit of allowing more valid orderings.
@@ -166,6 +239,44 @@
 ; ASM64-NEXT:  bl .test_byval_3Byte
 ; ASM64-NEXT:  nop
 
+
+define zeroext i16 @test_byval_3Byte(%struct.S3* byval(%struct.S3) align 1 %s) {
+entry:
+  %gep = getelementptr inbounds %struct.S3, %struct.S3* %s, i32 0, i32 1
+  %0 = load i16, i16* %gep, align 1
+  ret i16 %0
+}
+
+; CHECK-LABEL: name:            test_byval_3Byte
+
+; 32BIT:      fixedStack:
+; 32BIT-NEXT:   - { id: 0, type: default, offset: 24, size: 4, alignment: 8, stack-id: default,
+
+; 32BIT:      bb.0.entry:
+; 32BIT-NEXT:   liveins: $r3
+; 32BIT:        STW killed renamable $r3, 0, %fixed-stack.0 :: (store 4 into %fixed-stack.0, align 8)
+; 32BIT-NEXT:   renamable $r3 = LHZ 1, %fixed-stack.0 :: (dereferenceable load 2
+
+; 64BIT:      fixedStack:
+; 64BIT-NEXT:   - { id: 0, type: default, offset: 48, size: 8, alignment: 16, stack-id: default,
+
+; 64BIT:      bb.0.entry:
+; 64BIT-NEXT:   liveins: $x3
+; 64BIT:        STD killed renamable $x3, 0, %fixed-stack.0 :: (store 8 into %fixed-stack.0, align 16)
+; 64BIT-NEXT:   renamable $x3 = LHZ8 1, %fixed-stack.0 :: (dereferenceable load 2
+
+
+; CHECKASM-LABEL: .test_byval_3Byte:
+
+; ASM32:        stw 3, 24(1)
+; ASM32-NEXT:   lhz 3, 25(1)
+; ASM32-NEXT:   blr
+
+; ASM64:        std 3, 48(1)
+; ASM64-NEXT:   lhz 3, 49(1)
+; ASM64-NEXT:   blr
+
+
 %struct.S4 = type { [4 x i8] }
 %struct.S4A = type { i32 }
 
@@ -175,12 +286,10 @@
 entry:
   %s0 = alloca %struct.S0, align 8
   %s4a = alloca %struct.S4A, align 4
-  call void @test_byval_4Byte(%struct.S4* byval(%struct.S4) align 1 @gS4, %struct.S0* byval(%struct.S0) align 1 %s0, %struct.S4A* byval(%struct.S4A) align 4 %s4a)
+  %call = call signext i32 @test_byval_4Byte(%struct.S4* byval(%struct.S4) align 1 @gS4, %struct.S0* byval(%struct.S0) align 1 %s0, %struct.S4A* byval(%struct.S4A) align 4 %s4a)
   ret void
 }
 
-declare void @test_byval_4Byte(%struct.S4* byval(%struct.S4) align 1, %struct.S0* byval(%struct.S0) align 1, %struct.S4A* byval(%struct.S4A) align 4)
-
 ; CHECK-LABEL: name: call_test_byval_4Byte{{.*}}
 
 ; 32BIT:       ADJCALLSTACKDOWN 56, 0, implicit-def dead $r1, implicit $r1
@@ -219,3 +328,66 @@
 ; ASM64-NEXT:  nop
 ; ASM64-NEXT:  addi 1, 1, 128
 
+
+define signext i32 @test_byval_4Byte(%struct.S4* byval(%struct.S4) align 1 %s, %struct.S0* byval(%struct.S0) align 1, %struct.S4A* byval(%struct.S4A) align 4 %s4a) {
+entry:
+  %arrayidx = getelementptr inbounds %struct.S4, %struct.S4* %s, i32 0, i32 0, i32 3
+  %gep = getelementptr inbounds %struct.S4A, %struct.S4A* %s4a, i32 0, i32 0
+  %1 = load i8, i8* %arrayidx, align 1
+  %2 = load i32, i32* %gep, align 4
+  %conv = zext i8 %1 to i32
+  %add = add nsw i32 %2, %conv
+  ret i32 %add
+}
+
+; CHECK-LABEL: name:            test_byval_4Byte
+
+; 32BIT:      fixedStack:
+; 32BIT-NEXT:   - { id: 0, type: default, offset: 28, size: 4, alignment: 4, stack-id: default,
+; 32BIT-NEXT:       isImmutable: false, isAliased: true, callee-saved-register: '', callee-saved-restored: true,
+; 32BIT:        - { id: 1, type: default, offset: 28, size: 4, alignment: 4, stack-id: default,
+; 32BIT-NEXT:       isImmutable: false, isAliased: true, callee-saved-register: '', callee-saved-restored: true,
+; 32BIT:        - { id: 2, type: default, offset: 24, size: 4, alignment: 8, stack-id: default,
+; 32BIT-NEXT:       isImmutable: false, isAliased: true, callee-saved-register: '', callee-saved-restored: true,
+
+; 32BIT:      bb.0.entry:
+; 32BIT-NEXT:   liveins: $r3
+; 32BIT:        STW renamable $r3, 0, %fixed-stack.2 :: (store 4 into %fixed-stack.2, align 8)
+; 32BIT-DAG:    STW killed renamable $r4, 0, %fixed-stack.0 :: (store 4 into %fixed-stack.0)
+; 32BIT-DAG:    renamable $r[[SCRATCH:[0-9]+]] = RLWINM killed renamable $r3, 0, 24, 31
+; 32BIT-DAG:    renamable $r3 = nsw ADD4 renamable $r4, killed renamable $r[[SCRATCH]]
+; 32BIT:        BLR
+
+; 64BIT:      fixedStack:
+; 64BIT-NEXT: - { id: 0, type: default, offset: 56, size: 8, alignment: 8, stack-id: default,
+; 64BIT-NEXT:     isImmutable: false, isAliased: true, callee-saved-register: '', callee-saved-restored: true,
+; 64BIT:      - { id: 1, type: default, offset: 56, size: 8, alignment: 8, stack-id: default,
+; 64BIT-NEXT:     isImmutable: false, isAliased: true, callee-saved-register: '', callee-saved-restored: true,
+; 64BIT:      - { id: 2, type: default, offset: 48, size: 8, alignment: 16, stack-id: default,
+; 64BIT-NEXT:     isImmutable: false, isAliased: true, callee-saved-register: '', callee-saved-restored: true,
+
+; 64BIT:      bb.0.entry:
+; 64BIT-NEXT:   liveins: $x3
+; 64BIT:        STD killed renamable $x3, 0, %fixed-stack.2 :: (store 8 into %fixed-stack.2, align 16)
+; 64BIT-NEXT:   STD killed renamable $x4, 0, %fixed-stack.0 :: (store 8 into %fixed-stack.0)
+; 64BIT-DAG:    renamable $r[[SCRATCH1:[0-9]+]] = LBZ 3, %fixed-stack.2 :: (dereferenceable load 1
+; 64BIT-DAG:    renamable $r[[SCRATCH2:[0-9]+]] = LWZ 0, %fixed-stack.0 :: (dereferenceable load 4
+; 64BIT-NEXT:   renamable $r[[SCRATCH3:[0-9]+]] = nsw ADD4 killed renamable $r[[SCRATCH2]], killed renamable $r[[SCRATCH1]]
+; 64BIT-NEXT:   renamable $x3 = EXTSW_32_64 killed renamable $r[[SCRATCH3]]
+; 64BIT-NEXT:   BLR8
+
+; CHECKASM-LABEL: .test_byval_4Byte:
+
+; ASM32:        stw 3, 24(1)
+; ASM32-DAG:    stw 4, 28(1)
+; ASM32-DAG:    clrlwi  [[SCRATCH:[0-9]+]], 3, 24
+; ASM32-DAG:    add 3, 4, [[SCRATCH]]
+; ASM32-NEXT:   blr
+
+; ASM64:        std 3, 48(1)
+; ASM64-NEXT:   std 4, 56(1)
+; ASM64-DAG:    lbz [[SCRATCH1:[0-9]+]], 51(1)
+; ASM64-DAG:    lwz [[SCRATCH2:[0-9]+]], 56(1)
+; ASM64-NEXT:   add [[SCRATCH3:[0-9]+]], [[SCRATCH2]], [[SCRATCH1]]
+; ASM64-NEXT:   extsw 3, [[SCRATCH3]]
+; ASM64-NEXT:   blr
diff --git a/llvm/test/CodeGen/PowerPC/aix64-cc-byval.ll b/llvm/test/CodeGen/PowerPC/aix64-cc-byval.ll
--- a/llvm/test/CodeGen/PowerPC/aix64-cc-byval.ll
+++ b/llvm/test/CodeGen/PowerPC/aix64-cc-byval.ll
@@ -12,12 +12,10 @@
 
 define void @call_test_byval_5Byte() {
 entry:
-  call void @test_byval_5Byte(%struct.S5* byval(%struct.S5) align 1 @gS5)
+  %call = call zeroext i8 @test_byval_5Byte(%struct.S5* byval(%struct.S5) align 1 @gS5)
   ret void
 }
 
-declare void @test_byval_5Byte(%struct.S5* byval(%struct.S5) align 1)
-
 ; CHECK-LABEL: name: call_test_byval_5Byte{{.*}}
 
 ; ASM-LABEL: .call_test_byval_5Byte:
@@ -42,18 +40,40 @@
 ; ASM-NEXT:  bl .test_byval_5Byte
 ; ASM-NEXT:  nop
 
+
+define zeroext i8 @test_byval_5Byte(%struct.S5* byval(%struct.S5) align 1 %s) {
+entry:
+  %arrayidx = getelementptr inbounds %struct.S5, %struct.S5* %s, i32 0, i32 0, i32 4
+  %0 = load i8, i8* %arrayidx, align 1
+  ret i8 %0
+}
+
+; CHECK-LABEL: name:            test_byval_5Byte
+
+; CHECK:      fixedStack:
+; CHECK-NEXT:   - { id: 0, type: default, offset: 48, size: 8, alignment: 16,
+; CHECK:        bb.0.entry:
+; CHECK-NEXT:     liveins: $x3
+; CHECK:          STD killed renamable $x3, 0, %fixed-stack.0 :: (store 8 into %fixed-stack.0, align 16)
+; CHECK-NEXT:     renamable $x3 = LBZ8 4, %fixed-stack.0 :: (dereferenceable load 1
+
+; CHECKASM-LABEL: .test_byval_5Byte:
+
+; ASM:       std 3, 48(1)
+; ASM-NEXT:  lbz 3, 52(1)
+; ASM-NEXT:  blr
+
+
 %struct.S6 = type { [6 x i8] }
 
 @gS6 = external global %struct.S6, align 1
 
 define void @call_test_byval_6Byte() {
 entry:
-  call void @test_byval_6Byte(%struct.S6* byval(%struct.S6) align 1 @gS6)
+  %call = call zeroext i8 @test_byval_6Byte(%struct.S6* byval(%struct.S6) align 1 @gS6)
   ret void
 }
 
-declare void @test_byval_6Byte(%struct.S6* byval(%struct.S6) align 1)
-
 ; CHECK-LABEL: name: call_test_byval_6Byte{{.*}}
 
 ; ASM-LABEL: .call_test_byval_6Byte:
@@ -78,18 +98,39 @@
 ; ASM-NEXT:  bl .test_byval_6Byte
 ; ASM-NEXT:  nop
 
+
+define zeroext i8 @test_byval_6Byte(%struct.S6* byval(%struct.S6) align 1 %s) {
+entry:
+  %arrayidx = getelementptr inbounds %struct.S6, %struct.S6* %s, i32 0, i32 0, i32 5
+  %0 = load i8, i8* %arrayidx, align 1
+  ret i8 %0
+}
+
+; CHECK-LABEL: name:            test_byval_6Byte
+
+; CHECK:      fixedStack:
+; CHECK-NEXT:   - { id: 0, type: default, offset: 48, size: 8, alignment: 16,
+; CHECK:        bb.0.entry:
+; CHECK-NEXT:     liveins: $x3
+; CHECK:          STD killed renamable $x3, 0, %fixed-stack.0 :: (store 8 into %fixed-stack.0, align 16)
+; CHECK-NEXT:     renamable $x3 = LBZ8 5, %fixed-stack.0 :: (dereferenceable load 1
+
+; CHECKASM-LABEL: .test_byval_6Byte:
+
+; ASM:       std 3, 48(1)
+; ASM-NEXT:  lbz 3, 53(1)
+; ASM-NEXT:  blr
+
 %struct.S7 = type { [7 x i8] }
 
 @gS7 = external global %struct.S7, align 1
 
 define void @call_test_byval_7Byte() {
 entry:
-  call void @test_byval_7Byte(%struct.S7* byval(%struct.S7) align 1 @gS7)
+  %call = call zeroext i8 @test_byval_7Byte(%struct.S7* byval(%struct.S7) align 1 @gS7)
   ret void
 }
 
-declare void @test_byval_7Byte(%struct.S7* byval(%struct.S7) align 1)
-
 ; CHECK-LABEL: name: call_test_byval_7Byte{{.*}}
 
 ; ASM-LABEL: .call_test_byval_7Byte:
@@ -118,18 +159,40 @@
 ; ASM-NEXT:  bl .test_byval_7Byte
 ; ASM-NEXT:  nop
 
+
+define zeroext i8 @test_byval_7Byte(%struct.S7* byval(%struct.S7) align 1 %s) {
+entry:
+  %arrayidx = getelementptr inbounds %struct.S7, %struct.S7* %s, i32 0, i32 0, i32 6
+  %0 = load i8, i8* %arrayidx, align 1
+  ret i8 %0
+}
+
+; CHECK-LABEL: name:            test_byval_7Byte
+
+; CHECK:      fixedStack:
+; CHECK-NEXT:   - { id: 0, type: default, offset: 48, size: 8, alignment: 16,
+; CHECK:        bb.0.entry:
+; CHECK-NEXT:     liveins: $x3
+; CHECK:          STD killed renamable $x3, 0, %fixed-stack.0 :: (store 8 into %fixed-stack.0, align 16)
+; CHECK-NEXT:     renamable $x3 = LBZ8 6, %fixed-stack.0 :: (dereferenceable load 1
+
+; CHECKASM-LABEL: .test_byval_7Byte:
+
+; ASM:       std 3, 48(1)
+; ASM-NEXT:  lbz 3, 54(1)
+; ASM-NEXT:  blr
+
+
 %struct.S8 = type { [8 x i8] }
 
 @gS8 = external global %struct.S8, align 1
 
 define void @call_test_byval_8Byte() {
 entry:
-  call void @test_byval_8Byte(%struct.S8* byval(%struct.S8) align 1 @gS8)
+  %call = call zeroext i8 @test_byval_8Byte(%struct.S8* byval(%struct.S8) align 1 @gS8)
   ret void
 }
 
-declare void @test_byval_8Byte(%struct.S8* byval(%struct.S8) align 1)
-
 ; CHECK-LABEL: name: call_test_byval_8Byte{{.*}}
 
 ; ASM-LABEL: .call_test_byval_8Byte:
@@ -145,3 +208,29 @@
 ; ASM-NEXT:  ld 3, 0([[REGADDR]])
 ; ASM-NEXT:  bl .test_byval_8Byte
 ; ASM-NEXT:  nop
+
+
+define zeroext i8 @test_byval_8Byte(%struct.S8* byval(%struct.S8) align 1 %s) {
+entry:
+  %arrayidx = getelementptr inbounds %struct.S8, %struct.S8* %s, i32 0, i32 0, i32 7
+  %0 = load i8, i8* %arrayidx, align 1
+  ret i8 %0
+}
+
+; CHECK-LABEL: name:            test_byval_8Byte
+
+; CHECK:      fixedStack:
+; CHECK-NEXT:   - { id: 0, type: default, offset: 48, size: 8, alignment: 16,
+; CHECK:        bb.0.entry:
+; CHECK-NEXT:     liveins: $x3
+; CHECK:          renamable $x[[SCRATCH:[0-9]+]] = COPY $x3
+; CHECK-DAG:      renamable $x3 = RLDICL $x3, 0, 56
+; CHECK-DAG:      STD killed renamable $x[[SCRATCH]], 0, %fixed-stack.0 :: (store 8 into %fixed-stack.0, align 16)
+
+
+; CHECKASM-LABEL: .test_byval_8Byte:
+
+; ASM:       mr [[SCRATCH:[0-9]+]], 3
+; ASM-DAG:   clrldi  3, 3, 56
+; ASM-DAG:   std [[SCRATCH]], 48(1)
+; ASM-NEXT:  blr