[GlobalISel] Accept multiple vregs for lowerCall's args

Change the interface of CallLowering::lowerCall to accept several
virtual registers for each argument, instead of just one.  This is a
follow-up to D46018.

CallLowering::lowerReturn was similarly refactored in D49660 and
lowerFormalArguments in D63549.

With this change, we no longer pack the virtual registers generated for
aggregates into one big lump before delegating to the target. Therefore,
the target can decide itself whether it wants to handle them as separate
pieces or use one big register.

ARM and AArch64 have been updated to use the passed in virtual registers
directly, which means we no longer need to generate so many
merge/extract instructions.

NFCI for AMDGPU, Mips and X86.

Differential Revision: https://reviews.llvm.org/D63551

llvm-svn: 364512

10 files changed, 29 insertions, 100 deletions

diff --git a/llvm/include/llvm/CodeGen/GlobalISel/CallLowering.h b/llvm/include/llvm/CodeGen/GlobalISel/CallLowering.h
index 99c6b4c4fc1..d8d15bd0713 100644
--- a/llvm/include/llvm/CodeGen/GlobalISel/CallLowering.h
+++ b/llvm/include/llvm/CodeGen/GlobalISel/CallLowering.h
@@ -262,8 +262,10 @@ public:
   /// stored (or 0 if there is no return value). There will be one register for
   /// each non-aggregate type, as returned by \c computeValueLLTs.
   ///
-  /// \p ArgRegs is a list of virtual registers containing each argument that
-  /// needs to be passed.
+  /// \p ArgRegs is a list of lists of virtual registers containing each
+  /// argument that needs to be passed (argument \c i should be placed in \c
+  /// ArgRegs[i]). For each argument, there will be one register for each
+  /// non-aggregate type, as returned by \c computeValueLLTs.
   ///
   /// \p SwiftErrorVReg is non-zero if the call has a swifterror inout
   /// parameter, and contains the vreg that the swifterror should be copied into
@@ -276,8 +278,8 @@ public:
   ///
   /// \return true if the lowering succeeded, false otherwise.
   bool lowerCall(MachineIRBuilder &MIRBuilder, ImmutableCallSite CS,
-                 ArrayRef<Register> ResRegs, ArrayRef<Register> ArgRegs,
-                 Register SwiftErrorVReg,
+                 ArrayRef<Register> ResRegs,
+                 ArrayRef<ArrayRef<Register>> ArgRegs, Register SwiftErrorVReg,
                  std::function<unsigned()> GetCalleeReg) const;
 };
 
diff --git a/llvm/lib/CodeGen/GlobalISel/CallLowering.cpp b/llvm/lib/CodeGen/GlobalISel/CallLowering.cpp
index 0772021bc08..d257bbcf6f0 100644
--- a/llvm/lib/CodeGen/GlobalISel/CallLowering.cpp
+++ b/llvm/lib/CodeGen/GlobalISel/CallLowering.cpp
@@ -29,7 +29,7 @@ void CallLowering::anchor() {}
 
 bool CallLowering::lowerCall(MachineIRBuilder &MIRBuilder, ImmutableCallSite CS,
                              ArrayRef<Register> ResRegs,
-                             ArrayRef<Register> ArgRegs,
+                             ArrayRef<ArrayRef<Register>> ArgRegs,
                              Register SwiftErrorVReg,
                              std::function<unsigned()> GetCalleeReg) const {
   auto &DL = CS.getParent()->getParent()->getParent()->getDataLayout();
diff --git a/llvm/lib/CodeGen/GlobalISel/IRTranslator.cpp b/llvm/lib/CodeGen/GlobalISel/IRTranslator.cpp
index 2f076595065..48b3a52f084 100644
--- a/llvm/lib/CodeGen/GlobalISel/IRTranslator.cpp
+++ b/llvm/lib/CodeGen/GlobalISel/IRTranslator.cpp
@@ -1587,8 +1587,8 @@ bool IRTranslator::translateCall(const User &U, MachineIRBuilder &MIRBuilder) {
   if (!F || !F->isIntrinsic() || ID == Intrinsic::not_intrinsic) {
     ArrayRef<Register> Res = getOrCreateVRegs(CI);
 
-    SmallVector<Register, 8> Args;
-    Register SwiftErrorVReg;
+    SmallVector<ArrayRef<Register>, 8> Args;
+    Register SwiftErrorVReg = 0;
     for (auto &Arg: CI.arg_operands()) {
       if (CLI->supportSwiftError() && isSwiftError(Arg)) {
         LLT Ty = getLLTForType(*Arg->getType(), *DL);
@@ -1600,7 +1600,7 @@ bool IRTranslator::translateCall(const User &U, MachineIRBuilder &MIRBuilder) {
             SwiftError.getOrCreateVRegDefAt(&CI, &MIRBuilder.getMBB(), Arg);
         continue;
       }
-      Args.push_back(packRegs(*Arg, MIRBuilder));
+      Args.push_back(getOrCreateVRegs(*Arg));
     }
 
     MF->getFrameInfo().setHasCalls(true);
@@ -1684,7 +1684,7 @@ bool IRTranslator::translateInvoke(const User &U,
   ArrayRef<Register> Res;
   if (!I.getType()->isVoidTy())
     Res = getOrCreateVRegs(I);
-  SmallVector<Register, 8> Args;
+  SmallVector<ArrayRef<Register>, 8> Args;
   Register SwiftErrorVReg = 0;
   for (auto &Arg : I.arg_operands()) {
     if (CLI->supportSwiftError() && isSwiftError(Arg)) {
@@ -1698,7 +1698,7 @@ bool IRTranslator::translateInvoke(const User &U,
       continue;
     }
 
-    Args.push_back(packRegs(*Arg, MIRBuilder));
+    Args.push_back(getOrCreateVRegs(*Arg));
   }
 
   if (!CLI->lowerCall(MIRBuilder, &I, Res, Args, SwiftErrorVReg,
diff --git a/llvm/lib/Target/AArch64/AArch64CallLowering.cpp b/llvm/lib/Target/AArch64/AArch64CallLowering.cpp
index 1fa12b0290b..76a858c3014 100644
--- a/llvm/lib/Target/AArch64/AArch64CallLowering.cpp
+++ b/llvm/lib/Target/AArch64/AArch64CallLowering.cpp
@@ -441,10 +441,9 @@ bool AArch64CallLowering::lowerCall(MachineIRBuilder &MIRBuilder,
 
   SmallVector<ArgInfo, 8> SplitArgs;
   for (auto &OrigArg : OrigArgs) {
-    assert(OrigArg.Regs.size() == 1 && "Can't handle multple regs yet");
     splitToValueTypes(OrigArg, SplitArgs, DL, MRI, CallConv,
                       [&](Register Reg, uint64_t Offset) {
-                        MIRBuilder.buildExtract(Reg, OrigArg.Regs[0], Offset);
+                        llvm_unreachable("Call params should already be split");
                       });
     // AAPCS requires that we zero-extend i1 to 8 bits by the caller.
     if (OrigArg.Ty->isIntegerTy(1))
diff --git a/llvm/lib/Target/ARM/ARMCallLowering.cpp b/llvm/lib/Target/ARM/ARMCallLowering.cpp
index 71b92517620..fdd94ab25ef 100644
--- a/llvm/lib/Target/ARM/ARMCallLowering.cpp
+++ b/llvm/lib/Target/ARM/ARMCallLowering.cpp
@@ -596,14 +596,9 @@ bool ARMCallLowering::lowerCall(MachineIRBuilder &MIRBuilder,
     if (Arg.Flags.isByVal())
       return false;
 
-    assert(Arg.Regs.size() == 1 && "Can't handle multple regs yet");
-
-    SmallVector<Register, 8> Regs;
-    splitToValueTypes(Arg, ArgInfos, MF,
-                      [&](unsigned Reg) { Regs.push_back(Reg); });
-
-    if (Regs.size() > 1)
-      MIRBuilder.buildUnmerge(Regs, Arg.Regs[0]);
+    splitToValueTypes(Arg, ArgInfos, MF, [&](Register Reg) {
+      llvm_unreachable("Function args should already be split");
+    });
   }
 
   auto ArgAssignFn = TLI.CCAssignFnForCall(CallConv, IsVarArg);
diff --git a/llvm/lib/Target/X86/X86CallLowering.cpp b/llvm/lib/Target/X86/X86CallLowering.cpp
index 3a980f40ab8..b16b3839c85 100644
--- a/llvm/lib/Target/X86/X86CallLowering.cpp
+++ b/llvm/lib/Target/X86/X86CallLowering.cpp
@@ -409,7 +409,9 @@ bool X86CallLowering::lowerCall(MachineIRBuilder &MIRBuilder,
     if (OrigArg.Flags.isByVal())
       return false;
 
-    assert(OrigArg.Regs.size() == 1 && "Can't handle multple regs yet");
+    if (OrigArg.Regs.size() > 1)
+      return false;
+
     if (!splitToValueTypes(OrigArg, SplitArgs, DL, MRI,
                            [&](ArrayRef<Register> Regs) {
                              MIRBuilder.buildUnmerge(Regs, OrigArg.Regs[0]);
diff --git a/llvm/test/CodeGen/AArch64/GlobalISel/call-translator-cse.ll b/llvm/test/CodeGen/AArch64/GlobalISel/call-translator-cse.ll
index 9120c109f5b..74169cfa412 100644
--- a/llvm/test/CodeGen/AArch64/GlobalISel/call-translator-cse.ll
+++ b/llvm/test/CodeGen/AArch64/GlobalISel/call-translator-cse.ll
@@ -7,20 +7,14 @@
 ; CHECK: [[GEP:%[0-9]+]]:_(p0) = G_GEP [[ADDR]], [[CST]](s64)
 ; CHECK: [[HI:%[0-9]+]]:_(s64) = G_LOAD [[GEP]](p0) :: (load 8 from %ir.ptr + 8)
 
-; CHECK: [[IMPDEF:%[0-9]+]]:_(s128) = G_IMPLICIT_DEF
-; CHECK: [[INS1:%[0-9]+]]:_(s128) = G_INSERT [[IMPDEF]], [[LO]](s64), 0
-; CHECK: [[INS2:%[0-9]+]]:_(s128) = G_INSERT [[INS1]], [[HI]](s64), 64
-; CHECK: [[EXTLO:%[0-9]+]]:_(s64) = G_EXTRACT [[INS2]](s128), 0
-; CHECK: [[EXTHI:%[0-9]+]]:_(s64) = G_EXTRACT [[INS2]](s128), 64
-
 ; CHECK: [[SP:%[0-9]+]]:_(p0) = COPY $sp
 ; CHECK: [[CST2:%[0-9]+]]:_(s64) = G_CONSTANT i64 0
 ; CHECK: [[GEP2:%[0-9]+]]:_(p0) = G_GEP [[SP]], [[CST2]](s64)
-; CHECK: G_STORE [[EXTLO]](s64), [[GEP2]](p0) :: (store 8 into stack, align 1)
+; CHECK: G_STORE [[LO]](s64), [[GEP2]](p0) :: (store 8 into stack, align 1)
 ; CHECK: [[SP:%[0-9]+]]:_(p0) = COPY $sp
 ; CHECK: [[CST3:%[0-9]+]]:_(s64) = COPY [[CST]]
 ; CHECK: [[GEP3:%[0-9]+]]:_(p0) = G_GEP [[SP]], [[CST3]](s64)
-; CHECK: G_STORE [[EXTHI]](s64), [[GEP3]](p0) :: (store 8 into stack + 8, align 1)
+; CHECK: G_STORE [[HI]](s64), [[GEP3]](p0) :: (store 8 into stack + 8, align 1)
 define void @test_split_struct([2 x i64]* %ptr) {
   %struct = load [2 x i64], [2 x i64]* %ptr
   call void @take_split_struct([2 x i64]* null, i64 1, i64 2, i64 3,
diff --git a/llvm/test/CodeGen/AArch64/GlobalISel/call-translator-ios.ll b/llvm/test/CodeGen/AArch64/GlobalISel/call-translator-ios.ll
index 35cf986238c..754bfdb9520 100644
--- a/llvm/test/CodeGen/AArch64/GlobalISel/call-translator-ios.ll
+++ b/llvm/test/CodeGen/AArch64/GlobalISel/call-translator-ios.ll
@@ -59,21 +59,16 @@ define void @take_128bit_struct([2 x i64]* %ptr, [2 x i64] %in) {
 ; CHECK: [[CST:%[0-9]+]]:_(s64) = G_CONSTANT i64 8
 ; CHECK: [[GEP:%[0-9]+]]:_(p0) = G_GEP %0, [[CST]](s64)
 ; CHECK: [[LD2:%[0-9]+]]:_(s64) = G_LOAD %3(p0) :: (load 8 from %ir.ptr + 8)
-; CHECK: [[IMPDEF:%[0-9]+]]:_(s128) = G_IMPLICIT_DEF
-; CHECK: [[INS1:%[0-9]+]]:_(s128) = G_INSERT [[IMPDEF]], [[LD1]](s64), 0
-; CHECK: [[INS2:%[0-9]+]]:_(s128) = G_INSERT [[INS1]], [[LD2]](s64), 64
-; CHECK:  [[EXT1:%[0-9]+]]:_(s64) = G_EXTRACT [[INS2]](s128), 0
-; CHECK: [[EXT2:%[0-9]+]]:_(s64) = G_EXTRACT [[INS2]](s128), 64
 
 ; CHECK: [[SP:%[0-9]+]]:_(p0) = COPY $sp
 ; CHECK: [[OFF:%[0-9]+]]:_(s64) = G_CONSTANT i64 0
 ; CHECK: [[ADDR:%[0-9]+]]:_(p0) = G_GEP [[SP]], [[OFF]](s64)
-; CHECK: G_STORE [[EXT1]](s64), [[ADDR]](p0) :: (store 8 into stack, align 1)
+; CHECK: G_STORE [[LD1]](s64), [[ADDR]](p0) :: (store 8 into stack, align 1)
 
 ; CHECK: [[SP:%[0-9]+]]:_(p0) = COPY $sp
 ; CHECK: [[OFF:%[0-9]+]]:_(s64) = COPY [[CST]]
 ; CHECK: [[ADDR:%[0-9]+]]:_(p0) = G_GEP [[SP]], [[OFF]]
-; CHECK: G_STORE [[EXT2]](s64), [[ADDR]](p0) :: (store 8 into stack + 8, align 1)
+; CHECK: G_STORE [[LD2]](s64), [[ADDR]](p0) :: (store 8 into stack + 8, align 1)
 define void @test_split_struct([2 x i64]* %ptr) {
   %struct = load [2 x i64], [2 x i64]* %ptr
   call void @take_split_struct([2 x i64]* null, i64 1, i64 2, i64 3,
diff --git a/llvm/test/CodeGen/AArch64/GlobalISel/call-translator.ll b/llvm/test/CodeGen/AArch64/GlobalISel/call-translator.ll
index cda1dc36677..b5e66d69ca0 100644
--- a/llvm/test/CodeGen/AArch64/GlobalISel/call-translator.ll
+++ b/llvm/test/CodeGen/AArch64/GlobalISel/call-translator.ll
@@ -112,20 +112,11 @@ define {double, i64, i32} @test_struct_return({double, i64, i32}* %addr) {
 ; CHECK: [[CST3:%[0-9]+]]:_(s64) = G_CONSTANT i64 24
 ; CHECK: [[GEP3:%[0-9]+]]:_(p0) = G_GEP %0, [[CST3]](s64)
 ; CHECK: [[LD4:%[0-9]+]]:_(s64) = G_LOAD [[GEP3]](p0) :: (load 8 from %ir.addr + 24)
-; CHECK: [[IMPDEF:%[0-9]+]]:_(s256) = G_IMPLICIT_DEF
-; CHECK: [[INS1:%[0-9]+]]:_(s256) = G_INSERT [[IMPDEF]], [[LD1]](s64), 0
-; CHECK: [[INS2:%[0-9]+]]:_(s256) = G_INSERT [[INS1]], [[LD2]](s64), 64
-; CHECK: [[INS3:%[0-9]+]]:_(s256) = G_INSERT [[INS2]], [[LD3]](s64), 128
-; CHECK: [[ARG:%[0-9]+]]:_(s256) = G_INSERT [[INS3]], [[LD4]](s64), 192
-; CHECK: [[E0:%[0-9]+]]:_(s64) = G_EXTRACT [[ARG]](s256), 0
-; CHECK: [[E1:%[0-9]+]]:_(s64) = G_EXTRACT [[ARG]](s256), 64
-; CHECK: [[E2:%[0-9]+]]:_(s64) = G_EXTRACT [[ARG]](s256), 128
-; CHECK: [[E3:%[0-9]+]]:_(s64) = G_EXTRACT [[ARG]](s256), 192
 
-; CHECK: $x0 = COPY [[E0]](s64)
-; CHECK: $x1 = COPY [[E1]](s64)
-; CHECK: $x2 = COPY [[E2]](s64)
-; CHECK: $x3 = COPY [[E3]](s64)
+; CHECK: $x0 = COPY [[LD1]](s64)
+; CHECK: $x1 = COPY [[LD2]](s64)
+; CHECK: $x2 = COPY [[LD3]](s64)
+; CHECK: $x3 = COPY [[LD4]](s64)
 ; CHECK: BL @arr_callee, csr_aarch64_aapcs, implicit-def $lr, implicit $sp, implicit $x0, implicit $x1, implicit $x2, implicit $x3, implicit-def $x0, implicit-def $x1, implicit-def $x2, implicit-def $x3
 ; CHECK: [[E0:%[0-9]+]]:_(s64) = COPY $x0
 ; CHECK: [[E1:%[0-9]+]]:_(s64) = COPY $x1
@@ -262,20 +253,14 @@ define void @take_128bit_struct([2 x i64]* %ptr, [2 x i64] %in) {
 ; CHECK: [[GEP:%[0-9]+]]:_(p0) = G_GEP [[ADDR]], [[CST]](s64)
 ; CHECK: [[HI:%[0-9]+]]:_(s64) = G_LOAD [[GEP]](p0) :: (load 8 from %ir.ptr + 8)
 
-; CHECK: [[IMPDEF:%[0-9]+]]:_(s128) = G_IMPLICIT_DEF
-; CHECK: [[INS1:%[0-9]+]]:_(s128) = G_INSERT [[IMPDEF]], [[LO]](s64), 0
-; CHECK: [[INS2:%[0-9]+]]:_(s128) = G_INSERT [[INS1]], [[HI]](s64), 64
-; CHECK: [[EXTLO:%[0-9]+]]:_(s64) = G_EXTRACT [[INS2]](s128), 0
-; CHECK: [[EXTHI:%[0-9]+]]:_(s64) = G_EXTRACT [[INS2]](s128), 64
-
 ; CHECK: [[SP:%[0-9]+]]:_(p0) = COPY $sp
 ; CHECK: [[CST2:%[0-9]+]]:_(s64) = G_CONSTANT i64 0
 ; CHECK: [[GEP2:%[0-9]+]]:_(p0) = G_GEP [[SP]], [[CST2]](s64)
-; CHECK: G_STORE [[EXTLO]](s64), [[GEP2]](p0) :: (store 8 into stack, align 1)
+; CHECK: G_STORE [[LO]](s64), [[GEP2]](p0) :: (store 8 into stack, align 1)
 ; CHECK: [[SP:%[0-9]+]]:_(p0) = COPY $sp
 ; CHECK: [[CST3:%[0-9]+]]:_(s64) = COPY [[CST]]
 ; CHECK: [[GEP3:%[0-9]+]]:_(p0) = G_GEP [[SP]], [[CST3]](s64)
-; CHECK: G_STORE [[EXTHI]](s64), [[GEP3]](p0) :: (store 8 into stack + 8, align 1)
+; CHECK: G_STORE [[HI]](s64), [[GEP3]](p0) :: (store 8 into stack + 8, align 1)
 define void @test_split_struct([2 x i64]* %ptr) {
   %struct = load [2 x i64], [2 x i64]* %ptr
   call void @take_split_struct([2 x i64]* null, i64 1, i64 2, i64 3,
diff --git a/llvm/test/CodeGen/ARM/GlobalISel/arm-param-lowering.ll b/llvm/test/CodeGen/ARM/GlobalISel/arm-param-lowering.ll
index 422785ac860..e4f6c1ebe19 100644
--- a/llvm/test/CodeGen/ARM/GlobalISel/arm-param-lowering.ll
+++ b/llvm/test/CodeGen/ARM/GlobalISel/arm-param-lowering.ll
@@ -202,11 +202,7 @@ define arm_aapcscc [3 x i32] @test_tiny_int_arrays([2 x i32] %arr) {
 ; CHECK: liveins: $r0, $r1
 ; CHECK: [[R0:%[0-9]+]]:_(s32) = COPY $r0
 ; CHECK: [[R1:%[0-9]+]]:_(s32) = COPY $r1
-; CHECK: [[IMPDEF:%[0-9]+]]:_(s64) = G_IMPLICIT_DEF
-; CHECK: [[INS1:%[0-9]+]]:_(s64) = G_INSERT [[IMPDEF]], [[R0]](s32), 0
-; CHECK: [[INS2:%[0-9]+]]:_(s64) = G_INSERT [[INS1]], [[R1]](s32), 32
 ; CHECK: ADJCALLSTACKDOWN 0, 0, 14, $noreg, implicit-def $sp, implicit $sp
-; CHECK: [[R0:%[0-9]+]]:_(s32), [[R1:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[INS2]](s64)
 ; CHECK: $r0 = COPY [[R0]]
 ; CHECK: $r1 = COPY [[R1]]
 ; ARM: BL @tiny_int_arrays_target, csr_aapcs, implicit-def $lr, implicit $sp, implicit $r0, implicit $r1, implicit-def $r0, implicit-def $r1
@@ -237,15 +233,7 @@ define arm_aapcscc void @test_multiple_int_arrays([2 x i32] %arr0, [2 x i32] %ar
 ; CHECK: [[R1:%[0-9]+]]:_(s32) = COPY $r1
 ; CHECK: [[R2:%[0-9]+]]:_(s32) = COPY $r2
 ; CHECK: [[R3:%[0-9]+]]:_(s32) = COPY $r3
-; CHECK: [[IMPDEF:%[0-9]+]]:_(s64) = G_IMPLICIT_DEF
-; CHECK: [[INS1:%[0-9]+]]:_(s64) = G_INSERT [[IMPDEF]], [[R0]](s32), 0
-; CHECK: [[INS2:%[0-9]+]]:_(s64) = G_INSERT [[INS1]], [[R1]](s32), 32
-; CHECK: [[IMPDEF2:%[0-9]+]]:_(s64) = G_IMPLICIT_DEF
-; CHECK: [[INS3:%[0-9]+]]:_(s64) = G_INSERT [[IMPDEF2]], [[R2]](s32), 0
-; CHECK: [[INS4:%[0-9]+]]:_(s64) = G_INSERT [[INS3]], [[R3]](s32), 32
 ; CHECK: ADJCALLSTACKDOWN 0, 0, 14, $noreg, implicit-def $sp, implicit $sp
-; CHECK: [[R0:%[0-9]+]]:_(s32), [[R1:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[INS2]](s64)
-; CHECK: [[R2:%[0-9]+]]:_(s32), [[R3:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[INS4]](s64)
 ; CHECK: $r0 = COPY [[R0]]
 ; CHECK: $r1 = COPY [[R1]]
 ; CHECK: $r2 = COPY [[R2]]
@@ -278,11 +266,7 @@ define arm_aapcscc void @test_large_int_arrays([20 x i32] %arr) {
 ; CHECK: [[FIRST_STACK_ELEMENT:%[0-9]+]]:_(s32) = G_LOAD [[FIRST_STACK_ELEMENT_FI]]{{.*}}load 4 from %fixed-stack.[[FIRST_STACK_ID]]
 ; CHECK: [[LAST_STACK_ELEMENT_FI:%[0-9]+]]:_(p0) = G_FRAME_INDEX %fixed-stack.[[LAST_STACK_ID]]
 ; CHECK: [[LAST_STACK_ELEMENT:%[0-9]+]]:_(s32) = G_LOAD [[LAST_STACK_ELEMENT_FI]]{{.*}}load 4 from %fixed-stack.[[LAST_STACK_ID]]
-; CHECK: [[IMPDEF:%[0-9]+]]:_(s640) = G_IMPLICIT_DEF
-; CHECK: [[INS1:%[0-9]+]]:_(s640) = G_INSERT [[IMPDEF]], [[R0]](s32), 0
-; CHECK: [[INS:%[0-9]+]]:_(s640) = G_INSERT {{.*}}, [[LAST_STACK_ELEMENT]](s32), 608
 ; CHECK: ADJCALLSTACKDOWN 64, 0, 14, $noreg, implicit-def $sp, implicit $sp
-; CHECK: [[R0:%[0-9]+]]:_(s32), [[R1:%[0-9]+]]:_(s32), [[R2:%[0-9]+]]:_(s32), [[R3:%[0-9]+]]:_(s32), [[FIRST_STACK_ELEMENT:%[0-9]+]]:_(s32), {{.*}}, [[LAST_STACK_ELEMENT:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[INS]](s640)
 ; CHECK: $r0 = COPY [[R0]]
 ; CHECK: $r1 = COPY [[R1]]
 ; CHECK: $r2 = COPY [[R2]]
@@ -324,12 +308,7 @@ define arm_aapcscc [2 x float] @test_fp_arrays_aapcs([3 x double] %arr) {
 ; BIG: [[ARR1:%[0-9]+]]:_(s64) = G_MERGE_VALUES [[ARR1_1]](s32), [[ARR1_0]](s32)
 ; CHECK: [[ARR2_FI:%[0-9]+]]:_(p0) = G_FRAME_INDEX %fixed-stack.[[ARR2_ID]]
 ; CHECK: [[ARR2:%[0-9]+]]:_(s64) = G_LOAD [[ARR2_FI]]{{.*}}load 8 from %fixed-stack.[[ARR2_ID]]
-; CHECK: [[IMPDEF:%[0-9]+]]:_(s192) = G_IMPLICIT_DEF
-; CHECK: [[INS1:%[0-9]+]]:_(s192) = G_INSERT [[IMPDEF]], [[ARR0]](s64), 0
-; CHECK: [[INS2:%[0-9]+]]:_(s192) = G_INSERT [[INS1]], [[ARR1]](s64), 64
-; CHECK: [[INS3:%[0-9]+]]:_(s192) = G_INSERT [[INS2]], [[ARR2]](s64), 128
 ; CHECK: ADJCALLSTACKDOWN 8, 0, 14, $noreg, implicit-def $sp, implicit $sp
-; CHECK: [[ARR0:%[0-9]+]]:_(s64), [[ARR1:%[0-9]+]]:_(s64), [[ARR2:%[0-9]+]]:_(s64) = G_UNMERGE_VALUES [[INS3]](s192)
 ; CHECK: [[ARR0_0:%[0-9]+]]:_(s32), [[ARR0_1:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[ARR0]](s64)
 ; LITTLE: $r0 = COPY [[ARR0_0]](s32)
 ; LITTLE: $r1 = COPY [[ARR0_1]](s32)
@@ -382,23 +361,7 @@ define arm_aapcs_vfpcc [4 x float] @test_fp_arrays_aapcs_vfp([3 x double] %x, [3
 ; CHECK: [[Z2:%[0-9]+]]:_(s64) = G_LOAD [[Z2_FI]]{{.*}}load 8
 ; CHECK: [[Z3_FI:%[0-9]+]]:_(p0) = G_FRAME_INDEX %fixed-stack.[[Z3_ID]]
 ; CHECK: [[Z3:%[0-9]+]]:_(s64) = G_LOAD [[Z3_FI]]{{.*}}load 8
-; CHECK: [[IMPDEF:%[0-9]+]]:_(s192) = G_IMPLICIT_DEF
-; CHECK: [[INS1:%[0-9]+]]:_(s192) = G_INSERT [[IMPDEF]], [[X0]](s64), 0
-; CHECK: [[INS2:%[0-9]+]]:_(s192) = G_INSERT [[INS1]], [[X1]](s64), 64
-; CHECK: [[INS3:%[0-9]+]]:_(s192) = G_INSERT [[INS2]], [[X2]](s64), 128
-; CHECK: [[IMPDEF2:%[0-9]+]]:_(s96) = G_IMPLICIT_DEF
-; CHECK: [[INS4:%[0-9]+]]:_(s96) = G_INSERT [[IMPDEF2]], [[Y0]](s32), 0
-; CHECK: [[INS5:%[0-9]+]]:_(s96) = G_INSERT [[INS4]], [[Y1]](s32), 32
-; CHECK: [[INS6:%[0-9]+]]:_(s96) = G_INSERT [[INS5]], [[Y2]](s32), 64
-; CHECK: [[IMPDEF3:%[0-9]+]]:_(s256) = G_IMPLICIT_DEF
-; CHECK: [[INS7:%[0-9]+]]:_(s256) = G_INSERT [[IMPDEF3]], [[Z0]](s64), 0
-; CHECK: [[INS8:%[0-9]+]]:_(s256) = G_INSERT [[INS7]], [[Z1]](s64), 64
-; CHECK: [[INS9:%[0-9]+]]:_(s256) = G_INSERT [[INS8]], [[Z2]](s64), 128
-; CHECK: [[INS10:%[0-9]+]]:_(s256) = G_INSERT [[INS9]], [[Z3]](s64), 192
 ; CHECK: ADJCALLSTACKDOWN 32, 0, 14, $noreg, implicit-def $sp, implicit $sp
-; CHECK: [[X0:%[0-9]+]]:_(s64), [[X1:%[0-9]+]]:_(s64), [[X2:%[0-9]+]]:_(s64) = G_UNMERGE_VALUES [[INS3]](s192)
-; CHECK: [[Y0:%[0-9]+]]:_(s32), [[Y1:%[0-9]+]]:_(s32), [[Y2:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[INS6]](s96)
-; CHECK: [[Z0:%[0-9]+]]:_(s64), [[Z1:%[0-9]+]]:_(s64), [[Z2:%[0-9]+]]:_(s64), [[Z3:%[0-9]+]]:_(s64) = G_UNMERGE_VALUES [[INS10]](s256)
 ; CHECK: $d0 = COPY [[X0]](s64)
 ; CHECK: $d1 = COPY [[X1]](s64)
 ; CHECK: $d2 = COPY [[X2]](s64)
@@ -457,9 +420,7 @@ define arm_aapcscc [2 x i32*] @test_tough_arrays([6 x [4 x i32]] %arr) {
 ; CHECK: [[FIRST_STACK_ELEMENT:%[0-9]+]]:_(s32) = G_LOAD [[FIRST_STACK_ELEMENT_FI]]{{.*}}load 4 from %fixed-stack.[[FIRST_STACK_ID]]
 ; CHECK: [[LAST_STACK_ELEMENT_FI:%[0-9]+]]:_(p0) = G_FRAME_INDEX %fixed-stack.[[LAST_STACK_ID]]
 ; CHECK: [[LAST_STACK_ELEMENT:%[0-9]+]]:_(s32) = G_LOAD [[LAST_STACK_ELEMENT_FI]]{{.*}}load 4 from %fixed-stack.[[LAST_STACK_ID]]
-; CHECK: [[INS:%[0-9]+]]:_(s768) = G_INSERT {{.*}}, [[LAST_STACK_ELEMENT]](s32), 736
 ; CHECK: ADJCALLSTACKDOWN 80, 0, 14, $noreg, implicit-def $sp, implicit $sp
-; CHECK: [[R0:%[0-9]+]]:_(s32), [[R1:%[0-9]+]]:_(s32), [[R2:%[0-9]+]]:_(s32), [[R3:%[0-9]+]]:_(s32), [[FIRST_STACK_ELEMENT:%[0-9]+]]:_(s32), {{.*}}, [[LAST_STACK_ELEMENT:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[INS]](s768)
 ; CHECK: $r0 = COPY [[R0]]
 ; CHECK: $r1 = COPY [[R1]]
 ; CHECK: $r2 = COPY [[R2]]
@@ -495,11 +456,7 @@ define arm_aapcscc {i32, i32} @test_structs({i32, i32} %x) {
 ; CHECK: liveins: $r0, $r1
 ; CHECK-DAG: [[X0:%[0-9]+]]:_(s32) = COPY $r0
 ; CHECK-DAG: [[X1:%[0-9]+]]:_(s32) = COPY $r1
-; CHECK: [[IMPDEF:%[0-9]+]]:_(s64) = G_IMPLICIT_DEF
-; CHECK: [[INS1:%[0-9]+]]:_(s64) = G_INSERT [[IMPDEF]], [[X0]](s32), 0
-; CHECK: [[INS2:%[0-9]+]]:_(s64) = G_INSERT [[INS1]], [[X1]](s32), 32
 ; CHECK: ADJCALLSTACKDOWN 0, 0, 14, $noreg, implicit-def $sp, implicit $sp
-; CHECK: [[X0:%[0-9]+]]:_(s32), [[X1:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[INS2]](s64)
 ; CHECK-DAG: $r0 = COPY [[X0]](s32)
 ; CHECK-DAG: $r1 = COPY [[X1]](s32)
 ; ARM: BL @structs_target, csr_aapcs, implicit-def $lr, implicit $sp, implicit $r0, implicit $r1, implicit-def $r0, implicit-def $r1