GlobalISel: Set alignment on function argument stack load/store

diff --git a/llvm/include/llvm/CodeGen/GlobalISel/Utils.h b/llvm/include/llvm/CodeGen/GlobalISel/Utils.h
index 115b1ad01f5272236f3d26064dd54b97f43b6f43..b237c8347455fb1e7807e0c1f1880ac27dc98192 100644 (file)
--- a/llvm/include/llvm/CodeGen/GlobalISel/Utils.h
+++ b/llvm/include/llvm/CodeGen/GlobalISel/Utils.h
@@ -27,6 +27,7 @@ class MachineInstr;
 class MachineOperand;
 class MachineOptimizationRemarkEmitter;
 class MachineOptimizationRemarkMissed;
+struct MachinePointerInfo;
 class MachineRegisterInfo;
 class MCInstrDesc;
 class RegisterBankInfo;
@@ -180,5 +181,8 @@ inline bool isKnownNeverSNaN(Register Val, const MachineRegisterInfo &MRI) {
   return isKnownNeverNaN(Val, MRI, true);
 }
 
+unsigned inferAlignmentFromPtrInfo(MachineFunction &MF,
+                                   const MachinePointerInfo &MPO);
+
 } // End namespace llvm.
 #endif

diff --git a/llvm/lib/CodeGen/GlobalISel/Utils.cpp b/llvm/lib/CodeGen/GlobalISel/Utils.cpp
index 32f8666928355bd7ae3b1cce4dd6e53dde1e3064..b22d543d23813861e48b4ade3894393d0b7e607b 100644 (file)
--- a/llvm/lib/CodeGen/GlobalISel/Utils.cpp
+++ b/llvm/lib/CodeGen/GlobalISel/Utils.cpp
@@ -457,6 +457,17 @@ bool llvm::isKnownNeverNaN(Register Val, const MachineRegisterInfo &MRI,
   return false;
 }
 
+unsigned llvm::inferAlignmentFromPtrInfo(MachineFunction &MF,
+                                         const MachinePointerInfo &MPO) {
+  auto PSV = MPO.V.dyn_cast<const PseudoSourceValue *>();
+  if (auto FSPV = dyn_cast_or_null<FixedStackPseudoSourceValue>(PSV)) {
+    MachineFrameInfo &MFI = MF.getFrameInfo();
+    return MinAlign(MFI.getObjectAlignment(FSPV->getFrameIndex()), MPO.Offset);
+  }
+
+  return 1;
+}
+
 Optional<APInt> llvm::ConstantFoldExtOp(unsigned Opcode, const unsigned Op1,
                                         uint64_t Imm,
                                         const MachineRegisterInfo &MRI) {

diff --git a/llvm/lib/Target/AArch64/AArch64CallLowering.cpp b/llvm/lib/Target/AArch64/AArch64CallLowering.cpp
index cbbec8db088b3e230d26782b28f616445d1659ac..080c1f1364b7df26f7af8b281f74bbc6a7c5646b 100644 (file)
--- a/llvm/lib/Target/AArch64/AArch64CallLowering.cpp
+++ b/llvm/lib/Target/AArch64/AArch64CallLowering.cpp
@@ -86,10 +86,11 @@ struct IncomingArgHandler : public CallLowering::ValueHandler {
 
   void assignValueToAddress(Register ValVReg, Register Addr, uint64_t Size,
                             MachinePointerInfo &MPO, CCValAssign &VA) override {
-    // FIXME: Get alignment
-    auto MMO = MIRBuilder.getMF().getMachineMemOperand(
+    MachineFunction &MF = MIRBuilder.getMF();
+    unsigned Align = inferAlignmentFromPtrInfo(MF, MPO);
+    auto MMO = MF.getMachineMemOperand(
         MPO, MachineMemOperand::MOLoad | MachineMemOperand::MOInvariant, Size,
-        1);
+        Align);
     MIRBuilder.buildLoad(ValVReg, Addr, *MMO);
   }
 
@@ -175,8 +176,10 @@ struct OutgoingArgHandler : public CallLowering::ValueHandler {
       ValVReg = MIRBuilder.buildAnyExt(LLT::scalar(Size * 8), ValVReg)
                     .getReg(0);
     }
-    auto MMO = MIRBuilder.getMF().getMachineMemOperand(
-        MPO, MachineMemOperand::MOStore, Size, 1);
+    MachineFunction &MF = MIRBuilder.getMF();
+    unsigned Align = inferAlignmentFromPtrInfo(MF, MPO);
+    auto MMO = MF.getMachineMemOperand(
+        MPO, MachineMemOperand::MOStore, Size, Align);
     MIRBuilder.buildStore(ValVReg, Addr, *MMO);
   }
 

diff --git a/llvm/lib/Target/AMDGPU/AMDGPUCallLowering.cpp b/llvm/lib/Target/AMDGPU/AMDGPUCallLowering.cpp
index ae68e05ed752feea37566fb752c0eaaab45ec246..afbd89b2847bf1f8fc1c59413ad5e08a24e24fad 100644 (file)
--- a/llvm/lib/Target/AMDGPU/AMDGPUCallLowering.cpp
+++ b/llvm/lib/Target/AMDGPU/AMDGPUCallLowering.cpp
@@ -118,9 +118,13 @@ struct IncomingArgHandler : public CallLowering::ValueHandler {
 
   void assignValueToAddress(Register ValVReg, Register Addr, uint64_t Size,
                             MachinePointerInfo &MPO, CCValAssign &VA) override {
+    MachineFunction &MF = MIRBuilder.getMF();
+    unsigned Align = inferAlignmentFromPtrInfo(MF, MPO);
+
     // FIXME: Get alignment
-    auto MMO = MIRBuilder.getMF().getMachineMemOperand(
-      MPO, MachineMemOperand::MOLoad | MachineMemOperand::MOInvariant, Size, 1);
+    auto MMO = MF.getMachineMemOperand(
+        MPO, MachineMemOperand::MOLoad | MachineMemOperand::MOInvariant, Size,
+        Align);
     MIRBuilder.buildLoad(ValVReg, Addr, *MMO);
   }
 

diff --git a/llvm/lib/Target/ARM/ARMCallLowering.cpp b/llvm/lib/Target/ARM/ARMCallLowering.cpp
index 3783c256b6fc87b2776c0f5719700da2b852aea4..c2bd24d9cd0eaa25f31d4d16f1651ee701a5e688 100644 (file)
--- a/llvm/lib/Target/ARM/ARMCallLowering.cpp
+++ b/llvm/lib/Target/ARM/ARMCallLowering.cpp
@@ -312,18 +312,20 @@ struct IncomingValueHandler : public CallLowering::ValueHandler {
       Size = 4;
       assert(MRI.getType(ValVReg).isScalar() && "Only scalars supported atm");
 
-      auto LoadVReg =
-          buildLoad(LLT::scalar(32), Addr, Size, /* Alignment */ 1, MPO);
+      auto LoadVReg = buildLoad(LLT::scalar(32), Addr, Size, MPO);
       MIRBuilder.buildTrunc(ValVReg, LoadVReg);
     } else {
       // If the value is not extended, a simple load will suffice.
-      buildLoad(ValVReg, Addr, Size, /* Alignment */ 1, MPO);
+      buildLoad(ValVReg, Addr, Size, MPO);
     }
   }
 
   MachineInstrBuilder buildLoad(const DstOp &Res, Register Addr, uint64_t Size,
-                                unsigned Alignment, MachinePointerInfo &MPO) {
-    auto MMO = MIRBuilder.getMF().getMachineMemOperand(
+                                MachinePointerInfo &MPO) {
+    MachineFunction &MF = MIRBuilder.getMF();
+    unsigned Alignment = inferAlignmentFromPtrInfo(MF, MPO);
+
+    auto MMO = MF.getMachineMemOperand(
         MPO, MachineMemOperand::MOLoad, Size, Alignment);
     return MIRBuilder.buildLoad(Res, Addr, *MMO);
   }

diff --git a/llvm/lib/Target/X86/X86CallLowering.cpp b/llvm/lib/Target/X86/X86CallLowering.cpp
index 2749dc573cf802e52f1e37c1d661f7a97e4dd9e8..0e986a60d86bcd93b9796e4e63f287e266b988c9 100644 (file)
--- a/llvm/lib/Target/X86/X86CallLowering.cpp
+++ b/llvm/lib/Target/X86/X86CallLowering.cpp
@@ -146,10 +146,13 @@ struct OutgoingValueHandler : public CallLowering::ValueHandler {
 
   void assignValueToAddress(Register ValVReg, Register Addr, uint64_t Size,
                             MachinePointerInfo &MPO, CCValAssign &VA) override {
+    MachineFunction &MF = MIRBuilder.getMF();
     Register ExtReg = extendRegister(ValVReg, VA);
-    auto MMO = MIRBuilder.getMF().getMachineMemOperand(
+    unsigned Align = inferAlignmentFromPtrInfo(MF, MPO);
+
+    auto MMO = MF.getMachineMemOperand(
         MPO, MachineMemOperand::MOStore, VA.getLocVT().getStoreSize(),
-        /* Alignment */ 1);
+        Align);
     MIRBuilder.buildStore(ExtReg, Addr, *MMO);
   }
 
@@ -245,9 +248,11 @@ struct IncomingValueHandler : public CallLowering::ValueHandler {
 
   void assignValueToAddress(Register ValVReg, Register Addr, uint64_t Size,
                             MachinePointerInfo &MPO, CCValAssign &VA) override {
-    auto MMO = MIRBuilder.getMF().getMachineMemOperand(
+    MachineFunction &MF = MIRBuilder.getMF();
+    unsigned Align = inferAlignmentFromPtrInfo(MF, MPO);
+    auto MMO = MF.getMachineMemOperand(
         MPO, MachineMemOperand::MOLoad | MachineMemOperand::MOInvariant, Size,
-        1);
+        Align);
     MIRBuilder.buildLoad(ValVReg, Addr, *MMO);
   }
 

diff --git a/llvm/test/CodeGen/AArch64/GlobalISel/call-translator-ios.ll b/llvm/test/CodeGen/AArch64/GlobalISel/call-translator-ios.ll
index 5c715fb65c50c464c146c09232cea4b46ad6e6e5..cd7c4ae3d4842d73e845cb7c845761ada94df527 100644 (file)
--- a/llvm/test/CodeGen/AArch64/GlobalISel/call-translator-ios.ll
+++ b/llvm/test/CodeGen/AArch64/GlobalISel/call-translator-ios.ll
@@ -6,7 +6,7 @@
 ; CHECK-DAG:  - { id: [[STACK0:[0-9]+]], type: default, offset: 0, size: 1,
 ; CHECK-DAG:  - { id: [[STACK8:[0-9]+]], type: default, offset: 1, size: 1,
 ; CHECK: [[LHS_ADDR:%[0-9]+]]:_(p0) = G_FRAME_INDEX %fixed-stack.[[STACK0]]
-; CHECK: [[LHS:%[0-9]+]]:_(s8) = G_LOAD [[LHS_ADDR]](p0) :: (invariant load 1 from %fixed-stack.[[STACK0]])
+; CHECK: [[LHS:%[0-9]+]]:_(s8) = G_LOAD [[LHS_ADDR]](p0) :: (invariant load 1 from %fixed-stack.[[STACK0]], align 16)
 ; CHECK: [[RHS_ADDR:%[0-9]+]]:_(p0) = G_FRAME_INDEX %fixed-stack.[[STACK8]]
 ; CHECK: [[RHS:%[0-9]+]]:_(s8) = G_LOAD [[RHS_ADDR]](p0) :: (invariant load 1 from %fixed-stack.[[STACK8]])
 ; CHECK: [[SUM:%[0-9]+]]:_(s8) = G_ADD [[LHS]], [[RHS]]
@@ -82,10 +82,10 @@ define void @test_split_struct([2 x i64]* %ptr) {
 ; CHECK-DAG:   - { id: [[HI_FRAME:[0-9]+]], type: default, offset: 8, size: 8
 
 ; CHECK: [[LOPTR:%[0-9]+]]:_(p0) = G_FRAME_INDEX %fixed-stack.[[LO_FRAME]]
-; CHECK: [[LO:%[0-9]+]]:_(s64) = G_LOAD [[LOPTR]](p0) :: (invariant load 8 from %fixed-stack.[[LO_FRAME]], align 1)
+; CHECK: [[LO:%[0-9]+]]:_(s64) = G_LOAD [[LOPTR]](p0) :: (invariant load 8 from %fixed-stack.[[LO_FRAME]], align 16)
 
 ; CHECK: [[HIPTR:%[0-9]+]]:_(p0) = G_FRAME_INDEX %fixed-stack.[[HI_FRAME]]
-; CHECK: [[HI:%[0-9]+]]:_(s64) = G_LOAD [[HIPTR]](p0) :: (invariant load 8 from %fixed-stack.[[HI_FRAME]], align 1)
+; CHECK: [[HI:%[0-9]+]]:_(s64) = G_LOAD [[HIPTR]](p0) :: (invariant load 8 from %fixed-stack.[[HI_FRAME]])
 define void @take_split_struct([2 x i64]* %ptr, i64, i64, i64,
                                i64, i64, i64,
                                [2 x i64] %in) {

diff --git a/llvm/test/CodeGen/AArch64/GlobalISel/call-translator-tail-call.ll b/llvm/test/CodeGen/AArch64/GlobalISel/call-translator-tail-call.ll
index 174c6ecb89901800bcde517a37bf463d4858ace4..d028147d5987a44a5bdf435fe64a7e9b954ee770 100644 (file)
--- a/llvm/test/CodeGen/AArch64/GlobalISel/call-translator-tail-call.ll
+++ b/llvm/test/CodeGen/AArch64/GlobalISel/call-translator-tail-call.ll
@@ -42,7 +42,7 @@ declare void @outgoing_stack_args_fn(<4 x half>)
 define void @test_outgoing_stack_args([8 x <2 x double>], <4 x half> %arg) {
   ; COMMON-LABEL: name: test_outgoing_stack_args
   ; COMMON:   [[FRAME_INDEX:%[0-9]+]]:_(p0) = G_FRAME_INDEX %fixed-stack.0
-  ; COMMON:   [[LOAD:%[0-9]+]]:_(<4 x s16>) = G_LOAD [[FRAME_INDEX]](p0) :: (invariant load 8 from %fixed-stack.0, align 1)
+  ; COMMON:   [[LOAD:%[0-9]+]]:_(<4 x s16>) = G_LOAD [[FRAME_INDEX]](p0) :: (invariant load 8 from %fixed-stack.0, align 16)
   ; COMMON:   $d0 = COPY [[LOAD]](<4 x s16>)
   ; COMMON:   TCRETURNdi @outgoing_stack_args_fn, 0, csr_aarch64_aapcs, implicit $sp, implicit $d0
   tail call void @outgoing_stack_args_fn(<4 x half> %arg)
@@ -137,7 +137,7 @@ define void @test_varargs_3([8 x <2 x double>], <4 x half> %arg) {
   ; WINDOWS:   [[COPY6:%[0-9]+]]:_(<2 x s64>) = COPY $q6
   ; WINDOWS:   [[COPY7:%[0-9]+]]:_(<2 x s64>) = COPY $q7
   ; WINDOWS:   [[FRAME_INDEX:%[0-9]+]]:_(p0) = G_FRAME_INDEX %fixed-stack.0
-  ; WINDOWS:   [[LOAD:%[0-9]+]]:_(<4 x s16>) = G_LOAD [[FRAME_INDEX]](p0) :: (invariant load 8 from %fixed-stack.0, align 1)
+  ; WINDOWS:   [[LOAD:%[0-9]+]]:_(<4 x s16>) = G_LOAD [[FRAME_INDEX]](p0) :: (invariant load 8 from %fixed-stack.0, align 16)
   ; WINDOWS:   [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 42
   ; WINDOWS:   [[C1:%[0-9]+]]:_(s64) = G_FCONSTANT double 1.000000e+00
   ; WINDOWS:   [[C2:%[0-9]+]]:_(s64) = G_CONSTANT i64 12
@@ -170,7 +170,7 @@ define void @test_byval(i8* byval %ptr) {
   ; COMMON-LABEL: name: test_byval
   ; COMMON: bb.1 (%ir-block.0):
   ; COMMON:   [[FRAME_INDEX:%[0-9]+]]:_(p0) = G_FRAME_INDEX %fixed-stack.0
-  ; COMMON:   [[LOAD:%[0-9]+]]:_(p0) = G_LOAD [[FRAME_INDEX]](p0) :: (invariant load 8 from %fixed-stack.0, align 1)
+  ; COMMON:   [[LOAD:%[0-9]+]]:_(p0) = G_LOAD [[FRAME_INDEX]](p0) :: (invariant load 8 from %fixed-stack.0, align 16)
   ; COMMON:   ADJCALLSTACKDOWN 0, 0, implicit-def $sp, implicit $sp
   ; COMMON:   BL @simple_fn, csr_aarch64_aapcs, implicit-def $lr, implicit $sp
   ; COMMON:   ADJCALLSTACKUP 0, 0, implicit-def $sp, implicit $sp

diff --git a/llvm/test/CodeGen/AArch64/GlobalISel/call-translator.ll b/llvm/test/CodeGen/AArch64/GlobalISel/call-translator.ll
index c3108a053ab830538be0daba514020c23a358472..c1fe9782580d565a997344769bdc91e1309dfa2f 100644 (file)
--- a/llvm/test/CodeGen/AArch64/GlobalISel/call-translator.ll
+++ b/llvm/test/CodeGen/AArch64/GlobalISel/call-translator.ll
@@ -177,11 +177,11 @@ define zeroext i8 @test_abi_zext_ret(i8* %addr) {
 ; CHECK-DAG:  - { id: [[STACK8:[0-9]+]], type: default, offset: 8, size: 8,
 ; CHECK-DAG:  - { id: [[STACK16:[0-9]+]], type: default, offset: 16, size: 8,
 ; CHECK: [[LHS_ADDR:%[0-9]+]]:_(p0) = G_FRAME_INDEX %fixed-stack.[[STACK0]]
-; CHECK: [[LHS:%[0-9]+]]:_(s64) = G_LOAD [[LHS_ADDR]](p0) :: (invariant load 8 from %fixed-stack.[[STACK0]], align 1)
+; CHECK: [[LHS:%[0-9]+]]:_(s64) = G_LOAD [[LHS_ADDR]](p0) :: (invariant load 8 from %fixed-stack.[[STACK0]], align 16)
 ; CHECK: [[RHS_ADDR:%[0-9]+]]:_(p0) = G_FRAME_INDEX %fixed-stack.[[STACK8]]
-; CHECK: [[RHS:%[0-9]+]]:_(s64) = G_LOAD [[RHS_ADDR]](p0) :: (invariant load 8 from %fixed-stack.[[STACK8]], align 1)
+; CHECK: [[RHS:%[0-9]+]]:_(s64) = G_LOAD [[RHS_ADDR]](p0) :: (invariant load 8 from %fixed-stack.[[STACK8]])
 ; CHECK: [[ADDR_ADDR:%[0-9]+]]:_(p0) = G_FRAME_INDEX %fixed-stack.[[STACK16]]
-; CHECK: [[ADDR:%[0-9]+]]:_(p0) = G_LOAD [[ADDR_ADDR]](p0) :: (invariant load 8 from %fixed-stack.[[STACK16]], align 1)
+; CHECK: [[ADDR:%[0-9]+]]:_(p0) = G_LOAD [[ADDR_ADDR]](p0) :: (invariant load 8 from %fixed-stack.[[STACK16]], align 16)
 ; CHECK: [[SUM:%[0-9]+]]:_(s64) = G_ADD [[LHS]], [[RHS]]
 ; CHECK: G_STORE [[SUM]](s64), [[ADDR]](p0)
 define void @test_stack_slots([8 x i64], i64 %lhs, i64 %rhs, i64* %addr) {
@@ -220,7 +220,7 @@ define void @test_call_stack() {
 ; CHECK-NEXT: - { id: [[SLOT:[0-9]+]], type: default, offset: 0, size: 1, alignment: 16, stack-id: default,
 ; CHECK-NEXT: isImmutable: true,
 ; CHECK: [[ADDR:%[0-9]+]]:_(p0) = G_FRAME_INDEX %fixed-stack.[[SLOT]]
-; CHECK: {{%[0-9]+}}:_(s1) = G_LOAD [[ADDR]](p0) :: (invariant load 1 from %fixed-stack.[[SLOT]])
+; CHECK: {{%[0-9]+}}:_(s1) = G_LOAD [[ADDR]](p0) :: (invariant load 1 from %fixed-stack.[[SLOT]], align 16)
 define void @test_mem_i1([8 x i64], i1 %in) {
   ret void
 }
@@ -273,10 +273,10 @@ define void @test_split_struct([2 x i64]* %ptr) {
 ; CHECK-DAG:   - { id: [[HI_FRAME:[0-9]+]], type: default, offset: 8, size: 8
 
 ; CHECK: [[LOPTR:%[0-9]+]]:_(p0) = G_FRAME_INDEX %fixed-stack.[[LO_FRAME]]
-; CHECK: [[LO:%[0-9]+]]:_(s64) = G_LOAD [[LOPTR]](p0) :: (invariant load 8 from %fixed-stack.[[LO_FRAME]], align 1)
+; CHECK: [[LO:%[0-9]+]]:_(s64) = G_LOAD [[LOPTR]](p0) :: (invariant load 8 from %fixed-stack.[[LO_FRAME]], align 16)
 
 ; CHECK: [[HIPTR:%[0-9]+]]:_(p0) = G_FRAME_INDEX %fixed-stack.[[HI_FRAME]]
-; CHECK: [[HI:%[0-9]+]]:_(s64) = G_LOAD [[HIPTR]](p0) :: (invariant load 8 from %fixed-stack.[[HI_FRAME]], align 1)
+; CHECK: [[HI:%[0-9]+]]:_(s64) = G_LOAD [[HIPTR]](p0) :: (invariant load 8 from %fixed-stack.[[HI_FRAME]])
 define void @take_split_struct([2 x i64]* %ptr, i64, i64, i64,
                                i64, i64, i64,
                                [2 x i64] %in) {

diff --git a/llvm/test/CodeGen/AMDGPU/GlobalISel/irtranslator-function-args.ll b/llvm/test/CodeGen/AMDGPU/GlobalISel/irtranslator-function-args.ll
index 425e8dc4fab6b7c88db3b01e5bd96cecd2a5b243..04b91c06a8cce7879eb709b1ffd272528afc3a3b 100644 (file)
--- a/llvm/test/CodeGen/AMDGPU/GlobalISel/irtranslator-function-args.ll
+++ b/llvm/test/CodeGen/AMDGPU/GlobalISel/irtranslator-function-args.ll
@@ -542,7 +542,7 @@ define void @void_func_v33i32(<33 x i32> %arg0) #0 {
   ; CHECK:   [[COPY30:%[0-9]+]]:_(s32) = COPY $vgpr30
   ; CHECK:   [[COPY31:%[0-9]+]]:_(s32) = COPY $vgpr31
   ; CHECK:   [[FRAME_INDEX:%[0-9]+]]:_(p5) = G_FRAME_INDEX %fixed-stack.0
-  ; CHECK:   [[LOAD:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX]](p5) :: (invariant load 4 from %fixed-stack.0, align 1, addrspace 5)
+  ; CHECK:   [[LOAD:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX]](p5) :: (invariant load 4 from %fixed-stack.0, align 16, addrspace 5)
   ; CHECK:   [[COPY32:%[0-9]+]]:sgpr_64 = COPY $sgpr30_sgpr31
   ; CHECK:   [[BUILD_VECTOR:%[0-9]+]]:_(<33 x s32>) = G_BUILD_VECTOR [[COPY]](s32), [[COPY1]](s32), [[COPY2]](s32), [[COPY3]](s32), [[COPY4]](s32), [[COPY5]](s32), [[COPY6]](s32), [[COPY7]](s32), [[COPY8]](s32), [[COPY9]](s32), [[COPY10]](s32), [[COPY11]](s32), [[COPY12]](s32), [[COPY13]](s32), [[COPY14]](s32), [[COPY15]](s32), [[COPY16]](s32), [[COPY17]](s32), [[COPY18]](s32), [[COPY19]](s32), [[COPY20]](s32), [[COPY21]](s32), [[COPY22]](s32), [[COPY23]](s32), [[COPY24]](s32), [[COPY25]](s32), [[COPY26]](s32), [[COPY27]](s32), [[COPY28]](s32), [[COPY29]](s32), [[COPY30]](s32), [[COPY31]](s32), [[LOAD]](s32)
   ; CHECK:   [[DEF:%[0-9]+]]:_(p1) = G_IMPLICIT_DEF
@@ -1361,7 +1361,7 @@ define void @void_func_byval_struct_i8_i32({ i8, i32 } addrspace(5)* byval %arg0
   ; CHECK: bb.1 (%ir-block.0):
   ; CHECK:   liveins: $sgpr30_sgpr31
   ; CHECK:   [[FRAME_INDEX:%[0-9]+]]:_(p5) = G_FRAME_INDEX %fixed-stack.0
-  ; CHECK:   [[LOAD:%[0-9]+]]:_(p5) = G_LOAD [[FRAME_INDEX]](p5) :: (invariant load 4 from %fixed-stack.0, align 1, addrspace 5)
+  ; CHECK:   [[LOAD:%[0-9]+]]:_(p5) = G_LOAD [[FRAME_INDEX]](p5) :: (invariant load 4 from %fixed-stack.0, align 16, addrspace 5)
   ; CHECK:   [[COPY:%[0-9]+]]:sgpr_64 = COPY $sgpr30_sgpr31
   ; CHECK:   [[DEF:%[0-9]+]]:_(p1) = G_IMPLICIT_DEF
   ; CHECK:   [[LOAD1:%[0-9]+]]:_(s8) = G_LOAD [[LOAD]](p5) :: (dereferenceable load 1 from %ir.arg0, align 4, addrspace 5)
@@ -1384,9 +1384,9 @@ define void @void_func_byval_struct_i8_i32_x2({ i8, i32 } addrspace(5)* byval %a
   ; CHECK: bb.1 (%ir-block.0):
   ; CHECK:   liveins: $vgpr0, $sgpr30_sgpr31
   ; CHECK:   [[FRAME_INDEX:%[0-9]+]]:_(p5) = G_FRAME_INDEX %fixed-stack.1
-  ; CHECK:   [[LOAD:%[0-9]+]]:_(p5) = G_LOAD [[FRAME_INDEX]](p5) :: (invariant load 4 from %fixed-stack.1, align 1, addrspace 5)
+  ; CHECK:   [[LOAD:%[0-9]+]]:_(p5) = G_LOAD [[FRAME_INDEX]](p5) :: (invariant load 4 from %fixed-stack.1, align 16, addrspace 5)
   ; CHECK:   [[FRAME_INDEX1:%[0-9]+]]:_(p5) = G_FRAME_INDEX %fixed-stack.0
-  ; CHECK:   [[LOAD1:%[0-9]+]]:_(p5) = G_LOAD [[FRAME_INDEX1]](p5) :: (invariant load 4 from %fixed-stack.0, align 1, addrspace 5)
+  ; CHECK:   [[LOAD1:%[0-9]+]]:_(p5) = G_LOAD [[FRAME_INDEX1]](p5) :: (invariant load 4 from %fixed-stack.0, align 8, addrspace 5)
   ; CHECK:   [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
   ; CHECK:   [[COPY1:%[0-9]+]]:sgpr_64 = COPY $sgpr30_sgpr31
   ; CHECK:   [[DEF:%[0-9]+]]:_(p1) = G_IMPLICIT_DEF
@@ -1421,9 +1421,9 @@ define void @void_func_byval_i32_byval_i64(i32 addrspace(5)* byval %arg0, i64 ad
   ; CHECK: bb.1 (%ir-block.0):
   ; CHECK:   liveins: $sgpr30_sgpr31
   ; CHECK:   [[FRAME_INDEX:%[0-9]+]]:_(p5) = G_FRAME_INDEX %fixed-stack.1
-  ; CHECK:   [[LOAD:%[0-9]+]]:_(p5) = G_LOAD [[FRAME_INDEX]](p5) :: (invariant load 4 from %fixed-stack.1, align 1, addrspace 5)
+  ; CHECK:   [[LOAD:%[0-9]+]]:_(p5) = G_LOAD [[FRAME_INDEX]](p5) :: (invariant load 4 from %fixed-stack.1, align 16, addrspace 5)
   ; CHECK:   [[FRAME_INDEX1:%[0-9]+]]:_(p5) = G_FRAME_INDEX %fixed-stack.0
-  ; CHECK:   [[LOAD1:%[0-9]+]]:_(p5) = G_LOAD [[FRAME_INDEX1]](p5) :: (invariant load 4 from %fixed-stack.0, align 1, addrspace 5)
+  ; CHECK:   [[LOAD1:%[0-9]+]]:_(p5) = G_LOAD [[FRAME_INDEX1]](p5) :: (invariant load 4 from %fixed-stack.0, align 8, addrspace 5)
   ; CHECK:   [[COPY:%[0-9]+]]:sgpr_64 = COPY $sgpr30_sgpr31
   ; CHECK:   [[DEF:%[0-9]+]]:_(p1) = G_IMPLICIT_DEF
   ; CHECK:   [[COPY1:%[0-9]+]]:_(p1) = COPY [[DEF]](p1)
@@ -1477,11 +1477,11 @@ define void @void_func_v32i32_i32_i64(<32 x i32> %arg0, i32 %arg1, i64 %arg2) #0
   ; CHECK:   [[COPY30:%[0-9]+]]:_(s32) = COPY $vgpr30
   ; CHECK:   [[COPY31:%[0-9]+]]:_(s32) = COPY $vgpr31
   ; CHECK:   [[FRAME_INDEX:%[0-9]+]]:_(p5) = G_FRAME_INDEX %fixed-stack.2
-  ; CHECK:   [[LOAD:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX]](p5) :: (invariant load 4 from %fixed-stack.2, align 1, addrspace 5)
+  ; CHECK:   [[LOAD:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX]](p5) :: (invariant load 4 from %fixed-stack.2, align 16, addrspace 5)
   ; CHECK:   [[FRAME_INDEX1:%[0-9]+]]:_(p5) = G_FRAME_INDEX %fixed-stack.1
-  ; CHECK:   [[LOAD1:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX1]](p5) :: (invariant load 4 from %fixed-stack.1, align 1, addrspace 5)
+  ; CHECK:   [[LOAD1:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX1]](p5) :: (invariant load 4 from %fixed-stack.1, addrspace 5)
   ; CHECK:   [[FRAME_INDEX2:%[0-9]+]]:_(p5) = G_FRAME_INDEX %fixed-stack.0
-  ; CHECK:   [[LOAD2:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX2]](p5) :: (invariant load 4 from %fixed-stack.0, align 1, addrspace 5)
+  ; CHECK:   [[LOAD2:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX2]](p5) :: (invariant load 4 from %fixed-stack.0, align 8, addrspace 5)
   ; CHECK:   [[COPY32:%[0-9]+]]:sgpr_64 = COPY $sgpr30_sgpr31
   ; CHECK:   [[BUILD_VECTOR:%[0-9]+]]:_(<32 x s32>) = G_BUILD_VECTOR [[COPY]](s32), [[COPY1]](s32), [[COPY2]](s32), [[COPY3]](s32), [[COPY4]](s32), [[COPY5]](s32), [[COPY6]](s32), [[COPY7]](s32), [[COPY8]](s32), [[COPY9]](s32), [[COPY10]](s32), [[COPY11]](s32), [[COPY12]](s32), [[COPY13]](s32), [[COPY14]](s32), [[COPY15]](s32), [[COPY16]](s32), [[COPY17]](s32), [[COPY18]](s32), [[COPY19]](s32), [[COPY20]](s32), [[COPY21]](s32), [[COPY22]](s32), [[COPY23]](s32), [[COPY24]](s32), [[COPY25]](s32), [[COPY26]](s32), [[COPY27]](s32), [[COPY28]](s32), [[COPY29]](s32), [[COPY30]](s32), [[COPY31]](s32)
   ; CHECK:   [[MV:%[0-9]+]]:_(s64) = G_MERGE_VALUES [[LOAD1]](s32), [[LOAD2]](s32)
@@ -1537,13 +1537,13 @@ define void @void_func_v32i32_i1_i8_i16(<32 x i32> %arg0, i1 %arg1, i8 %arg2, i1
   ; CHECK:   [[COPY30:%[0-9]+]]:_(s32) = COPY $vgpr30
   ; CHECK:   [[COPY31:%[0-9]+]]:_(s32) = COPY $vgpr31
   ; CHECK:   [[FRAME_INDEX:%[0-9]+]]:_(p5) = G_FRAME_INDEX %fixed-stack.3
-  ; CHECK:   [[LOAD:%[0-9]+]]:_(s1) = G_LOAD [[FRAME_INDEX]](p5) :: (invariant load 1 from %fixed-stack.3, addrspace 5)
+  ; CHECK:   [[LOAD:%[0-9]+]]:_(s1) = G_LOAD [[FRAME_INDEX]](p5) :: (invariant load 1 from %fixed-stack.3, align 16, addrspace 5)
   ; CHECK:   [[FRAME_INDEX1:%[0-9]+]]:_(p5) = G_FRAME_INDEX %fixed-stack.2
-  ; CHECK:   [[LOAD1:%[0-9]+]]:_(s8) = G_LOAD [[FRAME_INDEX1]](p5) :: (invariant load 1 from %fixed-stack.2, addrspace 5)
+  ; CHECK:   [[LOAD1:%[0-9]+]]:_(s8) = G_LOAD [[FRAME_INDEX1]](p5) :: (invariant load 1 from %fixed-stack.2, align 4, addrspace 5)
   ; CHECK:   [[FRAME_INDEX2:%[0-9]+]]:_(p5) = G_FRAME_INDEX %fixed-stack.1
-  ; CHECK:   [[LOAD2:%[0-9]+]]:_(s16) = G_LOAD [[FRAME_INDEX2]](p5) :: (invariant load 2 from %fixed-stack.1, align 1, addrspace 5)
+  ; CHECK:   [[LOAD2:%[0-9]+]]:_(s16) = G_LOAD [[FRAME_INDEX2]](p5) :: (invariant load 2 from %fixed-stack.1, align 8, addrspace 5)
   ; CHECK:   [[FRAME_INDEX3:%[0-9]+]]:_(p5) = G_FRAME_INDEX %fixed-stack.0
-  ; CHECK:   [[LOAD3:%[0-9]+]]:_(s16) = G_LOAD [[FRAME_INDEX3]](p5) :: (invariant load 2 from %fixed-stack.0, align 1, addrspace 5)
+  ; CHECK:   [[LOAD3:%[0-9]+]]:_(s16) = G_LOAD [[FRAME_INDEX3]](p5) :: (invariant load 2 from %fixed-stack.0, align 4, addrspace 5)
   ; CHECK:   [[COPY32:%[0-9]+]]:sgpr_64 = COPY $sgpr30_sgpr31
   ; CHECK:   [[BUILD_VECTOR:%[0-9]+]]:_(<32 x s32>) = G_BUILD_VECTOR [[COPY]](s32), [[COPY1]](s32), [[COPY2]](s32), [[COPY3]](s32), [[COPY4]](s32), [[COPY5]](s32), [[COPY6]](s32), [[COPY7]](s32), [[COPY8]](s32), [[COPY9]](s32), [[COPY10]](s32), [[COPY11]](s32), [[COPY12]](s32), [[COPY13]](s32), [[COPY14]](s32), [[COPY15]](s32), [[COPY16]](s32), [[COPY17]](s32), [[COPY18]](s32), [[COPY19]](s32), [[COPY20]](s32), [[COPY21]](s32), [[COPY22]](s32), [[COPY23]](s32), [[COPY24]](s32), [[COPY25]](s32), [[COPY26]](s32), [[COPY27]](s32), [[COPY28]](s32), [[COPY29]](s32), [[COPY30]](s32), [[COPY31]](s32)
   ; CHECK:   [[DEF:%[0-9]+]]:_(p1) = G_IMPLICIT_DEF
@@ -1603,13 +1603,13 @@ define void @void_func_v32i32_v2i32_v2f32(<32 x i32> %arg0, <2 x i32> %arg1, <2
   ; CHECK:   [[COPY30:%[0-9]+]]:_(s32) = COPY $vgpr30
   ; CHECK:   [[COPY31:%[0-9]+]]:_(s32) = COPY $vgpr31
   ; CHECK:   [[FRAME_INDEX:%[0-9]+]]:_(p5) = G_FRAME_INDEX %fixed-stack.3
-  ; CHECK:   [[LOAD:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX]](p5) :: (invariant load 4 from %fixed-stack.3, align 1, addrspace 5)
+  ; CHECK:   [[LOAD:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX]](p5) :: (invariant load 4 from %fixed-stack.3, align 16, addrspace 5)
   ; CHECK:   [[FRAME_INDEX1:%[0-9]+]]:_(p5) = G_FRAME_INDEX %fixed-stack.2
-  ; CHECK:   [[LOAD1:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX1]](p5) :: (invariant load 4 from %fixed-stack.2, align 1, addrspace 5)
+  ; CHECK:   [[LOAD1:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX1]](p5) :: (invariant load 4 from %fixed-stack.2, addrspace 5)
   ; CHECK:   [[FRAME_INDEX2:%[0-9]+]]:_(p5) = G_FRAME_INDEX %fixed-stack.1
-  ; CHECK:   [[LOAD2:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX2]](p5) :: (invariant load 4 from %fixed-stack.1, align 1, addrspace 5)
+  ; CHECK:   [[LOAD2:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX2]](p5) :: (invariant load 4 from %fixed-stack.1, align 8, addrspace 5)
   ; CHECK:   [[FRAME_INDEX3:%[0-9]+]]:_(p5) = G_FRAME_INDEX %fixed-stack.0
-  ; CHECK:   [[LOAD3:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX3]](p5) :: (invariant load 4 from %fixed-stack.0, align 1, addrspace 5)
+  ; CHECK:   [[LOAD3:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX3]](p5) :: (invariant load 4 from %fixed-stack.0, addrspace 5)
   ; CHECK:   [[COPY32:%[0-9]+]]:sgpr_64 = COPY $sgpr30_sgpr31
   ; CHECK:   [[BUILD_VECTOR:%[0-9]+]]:_(<32 x s32>) = G_BUILD_VECTOR [[COPY]](s32), [[COPY1]](s32), [[COPY2]](s32), [[COPY3]](s32), [[COPY4]](s32), [[COPY5]](s32), [[COPY6]](s32), [[COPY7]](s32), [[COPY8]](s32), [[COPY9]](s32), [[COPY10]](s32), [[COPY11]](s32), [[COPY12]](s32), [[COPY13]](s32), [[COPY14]](s32), [[COPY15]](s32), [[COPY16]](s32), [[COPY17]](s32), [[COPY18]](s32), [[COPY19]](s32), [[COPY20]](s32), [[COPY21]](s32), [[COPY22]](s32), [[COPY23]](s32), [[COPY24]](s32), [[COPY25]](s32), [[COPY26]](s32), [[COPY27]](s32), [[COPY28]](s32), [[COPY29]](s32), [[COPY30]](s32), [[COPY31]](s32)
   ; CHECK:   [[BUILD_VECTOR1:%[0-9]+]]:_(<2 x s32>) = G_BUILD_VECTOR [[LOAD]](s32), [[LOAD1]](s32)
@@ -1665,13 +1665,13 @@ define void @void_func_v32i32_v2i16_v2f16(<32 x i32> %arg0, <2 x i16> %arg1, <2
   ; CHECK:   [[COPY30:%[0-9]+]]:_(s32) = COPY $vgpr30
   ; CHECK:   [[COPY31:%[0-9]+]]:_(s32) = COPY $vgpr31
   ; CHECK:   [[FRAME_INDEX:%[0-9]+]]:_(p5) = G_FRAME_INDEX %fixed-stack.3
-  ; CHECK:   [[LOAD:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX]](p5) :: (invariant load 4 from %fixed-stack.3, align 1, addrspace 5)
+  ; CHECK:   [[LOAD:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX]](p5) :: (invariant load 4 from %fixed-stack.3, align 16, addrspace 5)
   ; CHECK:   [[FRAME_INDEX1:%[0-9]+]]:_(p5) = G_FRAME_INDEX %fixed-stack.2
-  ; CHECK:   [[LOAD1:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX1]](p5) :: (invariant load 4 from %fixed-stack.2, align 1, addrspace 5)
+  ; CHECK:   [[LOAD1:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX1]](p5) :: (invariant load 4 from %fixed-stack.2, addrspace 5)
   ; CHECK:   [[FRAME_INDEX2:%[0-9]+]]:_(p5) = G_FRAME_INDEX %fixed-stack.1
-  ; CHECK:   [[LOAD2:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX2]](p5) :: (invariant load 4 from %fixed-stack.1, align 1, addrspace 5)
+  ; CHECK:   [[LOAD2:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX2]](p5) :: (invariant load 4 from %fixed-stack.1, align 8, addrspace 5)
   ; CHECK:   [[FRAME_INDEX3:%[0-9]+]]:_(p5) = G_FRAME_INDEX %fixed-stack.0
-  ; CHECK:   [[LOAD3:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX3]](p5) :: (invariant load 4 from %fixed-stack.0, align 1, addrspace 5)
+  ; CHECK:   [[LOAD3:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX3]](p5) :: (invariant load 4 from %fixed-stack.0, addrspace 5)
   ; CHECK:   [[COPY32:%[0-9]+]]:sgpr_64 = COPY $sgpr30_sgpr31
   ; CHECK:   [[BUILD_VECTOR:%[0-9]+]]:_(<32 x s32>) = G_BUILD_VECTOR [[COPY]](s32), [[COPY1]](s32), [[COPY2]](s32), [[COPY3]](s32), [[COPY4]](s32), [[COPY5]](s32), [[COPY6]](s32), [[COPY7]](s32), [[COPY8]](s32), [[COPY9]](s32), [[COPY10]](s32), [[COPY11]](s32), [[COPY12]](s32), [[COPY13]](s32), [[COPY14]](s32), [[COPY15]](s32), [[COPY16]](s32), [[COPY17]](s32), [[COPY18]](s32), [[COPY19]](s32), [[COPY20]](s32), [[COPY21]](s32), [[COPY22]](s32), [[COPY23]](s32), [[COPY24]](s32), [[COPY25]](s32), [[COPY26]](s32), [[COPY27]](s32), [[COPY28]](s32), [[COPY29]](s32), [[COPY30]](s32), [[COPY31]](s32)
   ; CHECK:   [[BUILD_VECTOR1:%[0-9]+]]:_(<2 x s32>) = G_BUILD_VECTOR [[LOAD]](s32), [[LOAD1]](s32)
@@ -1729,21 +1729,21 @@ define void @void_func_v32i32_v2i64_v2f64(<32 x i32> %arg0, <2 x i64> %arg1, <2
   ; CHECK:   [[COPY30:%[0-9]+]]:_(s32) = COPY $vgpr30
   ; CHECK:   [[COPY31:%[0-9]+]]:_(s32) = COPY $vgpr31
   ; CHECK:   [[FRAME_INDEX:%[0-9]+]]:_(p5) = G_FRAME_INDEX %fixed-stack.7
-  ; CHECK:   [[LOAD:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX]](p5) :: (invariant load 4 from %fixed-stack.7, align 1, addrspace 5)
+  ; CHECK:   [[LOAD:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX]](p5) :: (invariant load 4 from %fixed-stack.7, align 16, addrspace 5)
   ; CHECK:   [[FRAME_INDEX1:%[0-9]+]]:_(p5) = G_FRAME_INDEX %fixed-stack.6
-  ; CHECK:   [[LOAD1:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX1]](p5) :: (invariant load 4 from %fixed-stack.6, align 1, addrspace 5)
+  ; CHECK:   [[LOAD1:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX1]](p5) :: (invariant load 4 from %fixed-stack.6, addrspace 5)
   ; CHECK:   [[FRAME_INDEX2:%[0-9]+]]:_(p5) = G_FRAME_INDEX %fixed-stack.5
-  ; CHECK:   [[LOAD2:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX2]](p5) :: (invariant load 4 from %fixed-stack.5, align 1, addrspace 5)
+  ; CHECK:   [[LOAD2:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX2]](p5) :: (invariant load 4 from %fixed-stack.5, align 8, addrspace 5)
   ; CHECK:   [[FRAME_INDEX3:%[0-9]+]]:_(p5) = G_FRAME_INDEX %fixed-stack.4
-  ; CHECK:   [[LOAD3:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX3]](p5) :: (invariant load 4 from %fixed-stack.4, align 1, addrspace 5)
+  ; CHECK:   [[LOAD3:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX3]](p5) :: (invariant load 4 from %fixed-stack.4, addrspace 5)
   ; CHECK:   [[FRAME_INDEX4:%[0-9]+]]:_(p5) = G_FRAME_INDEX %fixed-stack.3
-  ; CHECK:   [[LOAD4:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX4]](p5) :: (invariant load 4 from %fixed-stack.3, align 1, addrspace 5)
+  ; CHECK:   [[LOAD4:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX4]](p5) :: (invariant load 4 from %fixed-stack.3, align 16, addrspace 5)
   ; CHECK:   [[FRAME_INDEX5:%[0-9]+]]:_(p5) = G_FRAME_INDEX %fixed-stack.2
-  ; CHECK:   [[LOAD5:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX5]](p5) :: (invariant load 4 from %fixed-stack.2, align 1, addrspace 5)
+  ; CHECK:   [[LOAD5:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX5]](p5) :: (invariant load 4 from %fixed-stack.2, addrspace 5)
   ; CHECK:   [[FRAME_INDEX6:%[0-9]+]]:_(p5) = G_FRAME_INDEX %fixed-stack.1
-  ; CHECK:   [[LOAD6:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX6]](p5) :: (invariant load 4 from %fixed-stack.1, align 1, addrspace 5)
+  ; CHECK:   [[LOAD6:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX6]](p5) :: (invariant load 4 from %fixed-stack.1, align 8, addrspace 5)
   ; CHECK:   [[FRAME_INDEX7:%[0-9]+]]:_(p5) = G_FRAME_INDEX %fixed-stack.0
-  ; CHECK:   [[LOAD7:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX7]](p5) :: (invariant load 4 from %fixed-stack.0, align 1, addrspace 5)
+  ; CHECK:   [[LOAD7:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX7]](p5) :: (invariant load 4 from %fixed-stack.0, addrspace 5)
   ; CHECK:   [[COPY32:%[0-9]+]]:sgpr_64 = COPY $sgpr30_sgpr31
   ; CHECK:   [[BUILD_VECTOR:%[0-9]+]]:_(<32 x s32>) = G_BUILD_VECTOR [[COPY]](s32), [[COPY1]](s32), [[COPY2]](s32), [[COPY3]](s32), [[COPY4]](s32), [[COPY5]](s32), [[COPY6]](s32), [[COPY7]](s32), [[COPY8]](s32), [[COPY9]](s32), [[COPY10]](s32), [[COPY11]](s32), [[COPY12]](s32), [[COPY13]](s32), [[COPY14]](s32), [[COPY15]](s32), [[COPY16]](s32), [[COPY17]](s32), [[COPY18]](s32), [[COPY19]](s32), [[COPY20]](s32), [[COPY21]](s32), [[COPY22]](s32), [[COPY23]](s32), [[COPY24]](s32), [[COPY25]](s32), [[COPY26]](s32), [[COPY27]](s32), [[COPY28]](s32), [[COPY29]](s32), [[COPY30]](s32), [[COPY31]](s32)
   ; CHECK:   [[MV:%[0-9]+]]:_(s64) = G_MERGE_VALUES [[LOAD]](s32), [[LOAD1]](s32)
@@ -1803,21 +1803,21 @@ define void @void_func_v32i32_v4i32_v4f32(<32 x i32> %arg0, <4 x i32> %arg1, <4
   ; CHECK:   [[COPY30:%[0-9]+]]:_(s32) = COPY $vgpr30
   ; CHECK:   [[COPY31:%[0-9]+]]:_(s32) = COPY $vgpr31
   ; CHECK:   [[FRAME_INDEX:%[0-9]+]]:_(p5) = G_FRAME_INDEX %fixed-stack.7
-  ; CHECK:   [[LOAD:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX]](p5) :: (invariant load 4 from %fixed-stack.7, align 1, addrspace 5)
+  ; CHECK:   [[LOAD:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX]](p5) :: (invariant load 4 from %fixed-stack.7, align 16, addrspace 5)
   ; CHECK:   [[FRAME_INDEX1:%[0-9]+]]:_(p5) = G_FRAME_INDEX %fixed-stack.6
-  ; CHECK:   [[LOAD1:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX1]](p5) :: (invariant load 4 from %fixed-stack.6, align 1, addrspace 5)
+  ; CHECK:   [[LOAD1:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX1]](p5) :: (invariant load 4 from %fixed-stack.6, addrspace 5)
   ; CHECK:   [[FRAME_INDEX2:%[0-9]+]]:_(p5) = G_FRAME_INDEX %fixed-stack.5
-  ; CHECK:   [[LOAD2:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX2]](p5) :: (invariant load 4 from %fixed-stack.5, align 1, addrspace 5)
+  ; CHECK:   [[LOAD2:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX2]](p5) :: (invariant load 4 from %fixed-stack.5, align 8, addrspace 5)
   ; CHECK:   [[FRAME_INDEX3:%[0-9]+]]:_(p5) = G_FRAME_INDEX %fixed-stack.4
-  ; CHECK:   [[LOAD3:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX3]](p5) :: (invariant load 4 from %fixed-stack.4, align 1, addrspace 5)
+  ; CHECK:   [[LOAD3:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX3]](p5) :: (invariant load 4 from %fixed-stack.4, addrspace 5)
   ; CHECK:   [[FRAME_INDEX4:%[0-9]+]]:_(p5) = G_FRAME_INDEX %fixed-stack.3
-  ; CHECK:   [[LOAD4:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX4]](p5) :: (invariant load 4 from %fixed-stack.3, align 1, addrspace 5)
+  ; CHECK:   [[LOAD4:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX4]](p5) :: (invariant load 4 from %fixed-stack.3, align 16, addrspace 5)
   ; CHECK:   [[FRAME_INDEX5:%[0-9]+]]:_(p5) = G_FRAME_INDEX %fixed-stack.2
-  ; CHECK:   [[LOAD5:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX5]](p5) :: (invariant load 4 from %fixed-stack.2, align 1, addrspace 5)
+  ; CHECK:   [[LOAD5:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX5]](p5) :: (invariant load 4 from %fixed-stack.2, addrspace 5)
   ; CHECK:   [[FRAME_INDEX6:%[0-9]+]]:_(p5) = G_FRAME_INDEX %fixed-stack.1
-  ; CHECK:   [[LOAD6:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX6]](p5) :: (invariant load 4 from %fixed-stack.1, align 1, addrspace 5)
+  ; CHECK:   [[LOAD6:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX6]](p5) :: (invariant load 4 from %fixed-stack.1, align 8, addrspace 5)
   ; CHECK:   [[FRAME_INDEX7:%[0-9]+]]:_(p5) = G_FRAME_INDEX %fixed-stack.0
-  ; CHECK:   [[LOAD7:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX7]](p5) :: (invariant load 4 from %fixed-stack.0, align 1, addrspace 5)
+  ; CHECK:   [[LOAD7:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX7]](p5) :: (invariant load 4 from %fixed-stack.0, addrspace 5)
   ; CHECK:   [[COPY32:%[0-9]+]]:sgpr_64 = COPY $sgpr30_sgpr31
   ; CHECK:   [[BUILD_VECTOR:%[0-9]+]]:_(<32 x s32>) = G_BUILD_VECTOR [[COPY]](s32), [[COPY1]](s32), [[COPY2]](s32), [[COPY3]](s32), [[COPY4]](s32), [[COPY5]](s32), [[COPY6]](s32), [[COPY7]](s32), [[COPY8]](s32), [[COPY9]](s32), [[COPY10]](s32), [[COPY11]](s32), [[COPY12]](s32), [[COPY13]](s32), [[COPY14]](s32), [[COPY15]](s32), [[COPY16]](s32), [[COPY17]](s32), [[COPY18]](s32), [[COPY19]](s32), [[COPY20]](s32), [[COPY21]](s32), [[COPY22]](s32), [[COPY23]](s32), [[COPY24]](s32), [[COPY25]](s32), [[COPY26]](s32), [[COPY27]](s32), [[COPY28]](s32), [[COPY29]](s32), [[COPY30]](s32), [[COPY31]](s32)
   ; CHECK:   [[BUILD_VECTOR1:%[0-9]+]]:_(<4 x s32>) = G_BUILD_VECTOR [[LOAD]](s32), [[LOAD1]](s32), [[LOAD2]](s32), [[LOAD3]](s32)
@@ -1873,37 +1873,37 @@ define void @void_func_v32i32_v8i32_v8f32(<32 x i32> %arg0, <8 x i32> %arg1, <8
   ; CHECK:   [[COPY30:%[0-9]+]]:_(s32) = COPY $vgpr30
   ; CHECK:   [[COPY31:%[0-9]+]]:_(s32) = COPY $vgpr31
   ; CHECK:   [[FRAME_INDEX:%[0-9]+]]:_(p5) = G_FRAME_INDEX %fixed-stack.15
-  ; CHECK:   [[LOAD:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX]](p5) :: (invariant load 4 from %fixed-stack.15, align 1, addrspace 5)
+  ; CHECK:   [[LOAD:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX]](p5) :: (invariant load 4 from %fixed-stack.15, align 16, addrspace 5)
   ; CHECK:   [[FRAME_INDEX1:%[0-9]+]]:_(p5) = G_FRAME_INDEX %fixed-stack.14
-  ; CHECK:   [[LOAD1:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX1]](p5) :: (invariant load 4 from %fixed-stack.14, align 1, addrspace 5)
+  ; CHECK:   [[LOAD1:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX1]](p5) :: (invariant load 4 from %fixed-stack.14, addrspace 5)
   ; CHECK:   [[FRAME_INDEX2:%[0-9]+]]:_(p5) = G_FRAME_INDEX %fixed-stack.13
-  ; CHECK:   [[LOAD2:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX2]](p5) :: (invariant load 4 from %fixed-stack.13, align 1, addrspace 5)
+  ; CHECK:   [[LOAD2:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX2]](p5) :: (invariant load 4 from %fixed-stack.13, align 8, addrspace 5)
   ; CHECK:   [[FRAME_INDEX3:%[0-9]+]]:_(p5) = G_FRAME_INDEX %fixed-stack.12
-  ; CHECK:   [[LOAD3:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX3]](p5) :: (invariant load 4 from %fixed-stack.12, align 1, addrspace 5)
+  ; CHECK:   [[LOAD3:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX3]](p5) :: (invariant load 4 from %fixed-stack.12, addrspace 5)
   ; CHECK:   [[FRAME_INDEX4:%[0-9]+]]:_(p5) = G_FRAME_INDEX %fixed-stack.11
-  ; CHECK:   [[LOAD4:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX4]](p5) :: (invariant load 4 from %fixed-stack.11, align 1, addrspace 5)
+  ; CHECK:   [[LOAD4:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX4]](p5) :: (invariant load 4 from %fixed-stack.11, align 16, addrspace 5)
   ; CHECK:   [[FRAME_INDEX5:%[0-9]+]]:_(p5) = G_FRAME_INDEX %fixed-stack.10
-  ; CHECK:   [[LOAD5:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX5]](p5) :: (invariant load 4 from %fixed-stack.10, align 1, addrspace 5)
+  ; CHECK:   [[LOAD5:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX5]](p5) :: (invariant load 4 from %fixed-stack.10, addrspace 5)
   ; CHECK:   [[FRAME_INDEX6:%[0-9]+]]:_(p5) = G_FRAME_INDEX %fixed-stack.9
-  ; CHECK:   [[LOAD6:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX6]](p5) :: (invariant load 4 from %fixed-stack.9, align 1, addrspace 5)
+  ; CHECK:   [[LOAD6:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX6]](p5) :: (invariant load 4 from %fixed-stack.9, align 8, addrspace 5)
   ; CHECK:   [[FRAME_INDEX7:%[0-9]+]]:_(p5) = G_FRAME_INDEX %fixed-stack.8
-  ; CHECK:   [[LOAD7:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX7]](p5) :: (invariant load 4 from %fixed-stack.8, align 1, addrspace 5)
+  ; CHECK:   [[LOAD7:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX7]](p5) :: (invariant load 4 from %fixed-stack.8, addrspace 5)
   ; CHECK:   [[FRAME_INDEX8:%[0-9]+]]:_(p5) = G_FRAME_INDEX %fixed-stack.7
-  ; CHECK:   [[LOAD8:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX8]](p5) :: (invariant load 4 from %fixed-stack.7, align 1, addrspace 5)
+  ; CHECK:   [[LOAD8:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX8]](p5) :: (invariant load 4 from %fixed-stack.7, align 16, addrspace 5)
   ; CHECK:   [[FRAME_INDEX9:%[0-9]+]]:_(p5) = G_FRAME_INDEX %fixed-stack.6
-  ; CHECK:   [[LOAD9:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX9]](p5) :: (invariant load 4 from %fixed-stack.6, align 1, addrspace 5)
+  ; CHECK:   [[LOAD9:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX9]](p5) :: (invariant load 4 from %fixed-stack.6, addrspace 5)
   ; CHECK:   [[FRAME_INDEX10:%[0-9]+]]:_(p5) = G_FRAME_INDEX %fixed-stack.5
-  ; CHECK:   [[LOAD10:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX10]](p5) :: (invariant load 4 from %fixed-stack.5, align 1, addrspace 5)
+  ; CHECK:   [[LOAD10:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX10]](p5) :: (invariant load 4 from %fixed-stack.5, align 8, addrspace 5)
   ; CHECK:   [[FRAME_INDEX11:%[0-9]+]]:_(p5) = G_FRAME_INDEX %fixed-stack.4
-  ; CHECK:   [[LOAD11:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX11]](p5) :: (invariant load 4 from %fixed-stack.4, align 1, addrspace 5)
+  ; CHECK:   [[LOAD11:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX11]](p5) :: (invariant load 4 from %fixed-stack.4, addrspace 5)
   ; CHECK:   [[FRAME_INDEX12:%[0-9]+]]:_(p5) = G_FRAME_INDEX %fixed-stack.3
-  ; CHECK:   [[LOAD12:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX12]](p5) :: (invariant load 4 from %fixed-stack.3, align 1, addrspace 5)
+  ; CHECK:   [[LOAD12:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX12]](p5) :: (invariant load 4 from %fixed-stack.3, align 16, addrspace 5)
   ; CHECK:   [[FRAME_INDEX13:%[0-9]+]]:_(p5) = G_FRAME_INDEX %fixed-stack.2
-  ; CHECK:   [[LOAD13:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX13]](p5) :: (invariant load 4 from %fixed-stack.2, align 1, addrspace 5)
+  ; CHECK:   [[LOAD13:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX13]](p5) :: (invariant load 4 from %fixed-stack.2, addrspace 5)
   ; CHECK:   [[FRAME_INDEX14:%[0-9]+]]:_(p5) = G_FRAME_INDEX %fixed-stack.1
-  ; CHECK:   [[LOAD14:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX14]](p5) :: (invariant load 4 from %fixed-stack.1, align 1, addrspace 5)
+  ; CHECK:   [[LOAD14:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX14]](p5) :: (invariant load 4 from %fixed-stack.1, align 8, addrspace 5)
   ; CHECK:   [[FRAME_INDEX15:%[0-9]+]]:_(p5) = G_FRAME_INDEX %fixed-stack.0
-  ; CHECK:   [[LOAD15:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX15]](p5) :: (invariant load 4 from %fixed-stack.0, align 1, addrspace 5)
+  ; CHECK:   [[LOAD15:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX15]](p5) :: (invariant load 4 from %fixed-stack.0, addrspace 5)
   ; CHECK:   [[COPY32:%[0-9]+]]:sgpr_64 = COPY $sgpr30_sgpr31
   ; CHECK:   [[BUILD_VECTOR:%[0-9]+]]:_(<32 x s32>) = G_BUILD_VECTOR [[COPY]](s32), [[COPY1]](s32), [[COPY2]](s32), [[COPY3]](s32), [[COPY4]](s32), [[COPY5]](s32), [[COPY6]](s32), [[COPY7]](s32), [[COPY8]](s32), [[COPY9]](s32), [[COPY10]](s32), [[COPY11]](s32), [[COPY12]](s32), [[COPY13]](s32), [[COPY14]](s32), [[COPY15]](s32), [[COPY16]](s32), [[COPY17]](s32), [[COPY18]](s32), [[COPY19]](s32), [[COPY20]](s32), [[COPY21]](s32), [[COPY22]](s32), [[COPY23]](s32), [[COPY24]](s32), [[COPY25]](s32), [[COPY26]](s32), [[COPY27]](s32), [[COPY28]](s32), [[COPY29]](s32), [[COPY30]](s32), [[COPY31]](s32)
   ; CHECK:   [[BUILD_VECTOR1:%[0-9]+]]:_(<8 x s32>) = G_BUILD_VECTOR [[LOAD]](s32), [[LOAD1]](s32), [[LOAD2]](s32), [[LOAD3]](s32), [[LOAD4]](s32), [[LOAD5]](s32), [[LOAD6]](s32), [[LOAD7]](s32)
@@ -1959,69 +1959,69 @@ define void @void_func_v32i32_v16i32_v16f32(<32 x i32> %arg0, <16 x i32> %arg1,
   ; CHECK:   [[COPY30:%[0-9]+]]:_(s32) = COPY $vgpr30
   ; CHECK:   [[COPY31:%[0-9]+]]:_(s32) = COPY $vgpr31
   ; CHECK:   [[FRAME_INDEX:%[0-9]+]]:_(p5) = G_FRAME_INDEX %fixed-stack.31
-  ; CHECK:   [[LOAD:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX]](p5) :: (invariant load 4 from %fixed-stack.31, align 1, addrspace 5)
+  ; CHECK:   [[LOAD:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX]](p5) :: (invariant load 4 from %fixed-stack.31, align 16, addrspace 5)
   ; CHECK:   [[FRAME_INDEX1:%[0-9]+]]:_(p5) = G_FRAME_INDEX %fixed-stack.30
-  ; CHECK:   [[LOAD1:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX1]](p5) :: (invariant load 4 from %fixed-stack.30, align 1, addrspace 5)
+  ; CHECK:   [[LOAD1:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX1]](p5) :: (invariant load 4 from %fixed-stack.30, addrspace 5)
   ; CHECK:   [[FRAME_INDEX2:%[0-9]+]]:_(p5) = G_FRAME_INDEX %fixed-stack.29
-  ; CHECK:   [[LOAD2:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX2]](p5) :: (invariant load 4 from %fixed-stack.29, align 1, addrspace 5)
+  ; CHECK:   [[LOAD2:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX2]](p5) :: (invariant load 4 from %fixed-stack.29, align 8, addrspace 5)
   ; CHECK:   [[FRAME_INDEX3:%[0-9]+]]:_(p5) = G_FRAME_INDEX %fixed-stack.28
-  ; CHECK:   [[LOAD3:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX3]](p5) :: (invariant load 4 from %fixed-stack.28, align 1, addrspace 5)
+  ; CHECK:   [[LOAD3:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX3]](p5) :: (invariant load 4 from %fixed-stack.28, addrspace 5)
   ; CHECK:   [[FRAME_INDEX4:%[0-9]+]]:_(p5) = G_FRAME_INDEX %fixed-stack.27
-  ; CHECK:   [[LOAD4:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX4]](p5) :: (invariant load 4 from %fixed-stack.27, align 1, addrspace 5)
+  ; CHECK:   [[LOAD4:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX4]](p5) :: (invariant load 4 from %fixed-stack.27, align 16, addrspace 5)
   ; CHECK:   [[FRAME_INDEX5:%[0-9]+]]:_(p5) = G_FRAME_INDEX %fixed-stack.26
-  ; CHECK:   [[LOAD5:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX5]](p5) :: (invariant load 4 from %fixed-stack.26, align 1, addrspace 5)
+  ; CHECK:   [[LOAD5:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX5]](p5) :: (invariant load 4 from %fixed-stack.26, addrspace 5)
   ; CHECK:   [[FRAME_INDEX6:%[0-9]+]]:_(p5) = G_FRAME_INDEX %fixed-stack.25
-  ; CHECK:   [[LOAD6:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX6]](p5) :: (invariant load 4 from %fixed-stack.25, align 1, addrspace 5)
+  ; CHECK:   [[LOAD6:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX6]](p5) :: (invariant load 4 from %fixed-stack.25, align 8, addrspace 5)
   ; CHECK:   [[FRAME_INDEX7:%[0-9]+]]:_(p5) = G_FRAME_INDEX %fixed-stack.24
-  ; CHECK:   [[LOAD7:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX7]](p5) :: (invariant load 4 from %fixed-stack.24, align 1, addrspace 5)
+  ; CHECK:   [[LOAD7:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX7]](p5) :: (invariant load 4 from %fixed-stack.24, addrspace 5)
   ; CHECK:   [[FRAME_INDEX8:%[0-9]+]]:_(p5) = G_FRAME_INDEX %fixed-stack.23
-  ; CHECK:   [[LOAD8:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX8]](p5) :: (invariant load 4 from %fixed-stack.23, align 1, addrspace 5)
+  ; CHECK:   [[LOAD8:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX8]](p5) :: (invariant load 4 from %fixed-stack.23, align 16, addrspace 5)
   ; CHECK:   [[FRAME_INDEX9:%[0-9]+]]:_(p5) = G_FRAME_INDEX %fixed-stack.22
-  ; CHECK:   [[LOAD9:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX9]](p5) :: (invariant load 4 from %fixed-stack.22, align 1, addrspace 5)
+  ; CHECK:   [[LOAD9:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX9]](p5) :: (invariant load 4 from %fixed-stack.22, addrspace 5)
   ; CHECK:   [[FRAME_INDEX10:%[0-9]+]]:_(p5) = G_FRAME_INDEX %fixed-stack.21
-  ; CHECK:   [[LOAD10:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX10]](p5) :: (invariant load 4 from %fixed-stack.21, align 1, addrspace 5)
+  ; CHECK:   [[LOAD10:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX10]](p5) :: (invariant load 4 from %fixed-stack.21, align 8, addrspace 5)
   ; CHECK:   [[FRAME_INDEX11:%[0-9]+]]:_(p5) = G_FRAME_INDEX %fixed-stack.20
-  ; CHECK:   [[LOAD11:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX11]](p5) :: (invariant load 4 from %fixed-stack.20, align 1, addrspace 5)
+  ; CHECK:   [[LOAD11:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX11]](p5) :: (invariant load 4 from %fixed-stack.20, addrspace 5)
   ; CHECK:   [[FRAME_INDEX12:%[0-9]+]]:_(p5) = G_FRAME_INDEX %fixed-stack.19
-  ; CHECK:   [[LOAD12:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX12]](p5) :: (invariant load 4 from %fixed-stack.19, align 1, addrspace 5)
+  ; CHECK:   [[LOAD12:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX12]](p5) :: (invariant load 4 from %fixed-stack.19, align 16, addrspace 5)
   ; CHECK:   [[FRAME_INDEX13:%[0-9]+]]:_(p5) = G_FRAME_INDEX %fixed-stack.18
-  ; CHECK:   [[LOAD13:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX13]](p5) :: (invariant load 4 from %fixed-stack.18, align 1, addrspace 5)
+  ; CHECK:   [[LOAD13:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX13]](p5) :: (invariant load 4 from %fixed-stack.18, addrspace 5)
   ; CHECK:   [[FRAME_INDEX14:%[0-9]+]]:_(p5) = G_FRAME_INDEX %fixed-stack.17
-  ; CHECK:   [[LOAD14:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX14]](p5) :: (invariant load 4 from %fixed-stack.17, align 1, addrspace 5)
+  ; CHECK:   [[LOAD14:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX14]](p5) :: (invariant load 4 from %fixed-stack.17, align 8, addrspace 5)
   ; CHECK:   [[FRAME_INDEX15:%[0-9]+]]:_(p5) = G_FRAME_INDEX %fixed-stack.16
-  ; CHECK:   [[LOAD15:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX15]](p5) :: (invariant load 4 from %fixed-stack.16, align 1, addrspace 5)
+  ; CHECK:   [[LOAD15:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX15]](p5) :: (invariant load 4 from %fixed-stack.16, addrspace 5)
   ; CHECK:   [[FRAME_INDEX16:%[0-9]+]]:_(p5) = G_FRAME_INDEX %fixed-stack.15
-  ; CHECK:   [[LOAD16:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX16]](p5) :: (invariant load 4 from %fixed-stack.15, align 1, addrspace 5)
+  ; CHECK:   [[LOAD16:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX16]](p5) :: (invariant load 4 from %fixed-stack.15, align 16, addrspace 5)
   ; CHECK:   [[FRAME_INDEX17:%[0-9]+]]:_(p5) = G_FRAME_INDEX %fixed-stack.14
-  ; CHECK:   [[LOAD17:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX17]](p5) :: (invariant load 4 from %fixed-stack.14, align 1, addrspace 5)
+  ; CHECK:   [[LOAD17:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX17]](p5) :: (invariant load 4 from %fixed-stack.14, addrspace 5)
   ; CHECK:   [[FRAME_INDEX18:%[0-9]+]]:_(p5) = G_FRAME_INDEX %fixed-stack.13
-  ; CHECK:   [[LOAD18:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX18]](p5) :: (invariant load 4 from %fixed-stack.13, align 1, addrspace 5)
+  ; CHECK:   [[LOAD18:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX18]](p5) :: (invariant load 4 from %fixed-stack.13, align 8, addrspace 5)
   ; CHECK:   [[FRAME_INDEX19:%[0-9]+]]:_(p5) = G_FRAME_INDEX %fixed-stack.12
-  ; CHECK:   [[LOAD19:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX19]](p5) :: (invariant load 4 from %fixed-stack.12, align 1, addrspace 5)
+  ; CHECK:   [[LOAD19:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX19]](p5) :: (invariant load 4 from %fixed-stack.12, addrspace 5)
   ; CHECK:   [[FRAME_INDEX20:%[0-9]+]]:_(p5) = G_FRAME_INDEX %fixed-stack.11
-  ; CHECK:   [[LOAD20:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX20]](p5) :: (invariant load 4 from %fixed-stack.11, align 1, addrspace 5)
+  ; CHECK:   [[LOAD20:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX20]](p5) :: (invariant load 4 from %fixed-stack.11, align 16, addrspace 5)
   ; CHECK:   [[FRAME_INDEX21:%[0-9]+]]:_(p5) = G_FRAME_INDEX %fixed-stack.10
-  ; CHECK:   [[LOAD21:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX21]](p5) :: (invariant load 4 from %fixed-stack.10, align 1, addrspace 5)
+  ; CHECK:   [[LOAD21:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX21]](p5) :: (invariant load 4 from %fixed-stack.10, addrspace 5)
   ; CHECK:   [[FRAME_INDEX22:%[0-9]+]]:_(p5) = G_FRAME_INDEX %fixed-stack.9
-  ; CHECK:   [[LOAD22:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX22]](p5) :: (invariant load 4 from %fixed-stack.9, align 1, addrspace 5)
+  ; CHECK:   [[LOAD22:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX22]](p5) :: (invariant load 4 from %fixed-stack.9, align 8, addrspace 5)
   ; CHECK:   [[FRAME_INDEX23:%[0-9]+]]:_(p5) = G_FRAME_INDEX %fixed-stack.8
-  ; CHECK:   [[LOAD23:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX23]](p5) :: (invariant load 4 from %fixed-stack.8, align 1, addrspace 5)
+  ; CHECK:   [[LOAD23:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX23]](p5) :: (invariant load 4 from %fixed-stack.8, addrspace 5)
   ; CHECK:   [[FRAME_INDEX24:%[0-9]+]]:_(p5) = G_FRAME_INDEX %fixed-stack.7
-  ; CHECK:   [[LOAD24:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX24]](p5) :: (invariant load 4 from %fixed-stack.7, align 1, addrspace 5)
+  ; CHECK:   [[LOAD24:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX24]](p5) :: (invariant load 4 from %fixed-stack.7, align 16, addrspace 5)
   ; CHECK:   [[FRAME_INDEX25:%[0-9]+]]:_(p5) = G_FRAME_INDEX %fixed-stack.6
-  ; CHECK:   [[LOAD25:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX25]](p5) :: (invariant load 4 from %fixed-stack.6, align 1, addrspace 5)
+  ; CHECK:   [[LOAD25:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX25]](p5) :: (invariant load 4 from %fixed-stack.6, addrspace 5)
   ; CHECK:   [[FRAME_INDEX26:%[0-9]+]]:_(p5) = G_FRAME_INDEX %fixed-stack.5
-  ; CHECK:   [[LOAD26:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX26]](p5) :: (invariant load 4 from %fixed-stack.5, align 1, addrspace 5)
+  ; CHECK:   [[LOAD26:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX26]](p5) :: (invariant load 4 from %fixed-stack.5, align 8, addrspace 5)
   ; CHECK:   [[FRAME_INDEX27:%[0-9]+]]:_(p5) = G_FRAME_INDEX %fixed-stack.4
-  ; CHECK:   [[LOAD27:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX27]](p5) :: (invariant load 4 from %fixed-stack.4, align 1, addrspace 5)
+  ; CHECK:   [[LOAD27:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX27]](p5) :: (invariant load 4 from %fixed-stack.4, addrspace 5)
   ; CHECK:   [[FRAME_INDEX28:%[0-9]+]]:_(p5) = G_FRAME_INDEX %fixed-stack.3
-  ; CHECK:   [[LOAD28:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX28]](p5) :: (invariant load 4 from %fixed-stack.3, align 1, addrspace 5)
+  ; CHECK:   [[LOAD28:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX28]](p5) :: (invariant load 4 from %fixed-stack.3, align 16, addrspace 5)
   ; CHECK:   [[FRAME_INDEX29:%[0-9]+]]:_(p5) = G_FRAME_INDEX %fixed-stack.2
-  ; CHECK:   [[LOAD29:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX29]](p5) :: (invariant load 4 from %fixed-stack.2, align 1, addrspace 5)
+  ; CHECK:   [[LOAD29:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX29]](p5) :: (invariant load 4 from %fixed-stack.2, addrspace 5)
   ; CHECK:   [[FRAME_INDEX30:%[0-9]+]]:_(p5) = G_FRAME_INDEX %fixed-stack.1
-  ; CHECK:   [[LOAD30:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX30]](p5) :: (invariant load 4 from %fixed-stack.1, align 1, addrspace 5)
+  ; CHECK:   [[LOAD30:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX30]](p5) :: (invariant load 4 from %fixed-stack.1, align 8, addrspace 5)
   ; CHECK:   [[FRAME_INDEX31:%[0-9]+]]:_(p5) = G_FRAME_INDEX %fixed-stack.0
-  ; CHECK:   [[LOAD31:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX31]](p5) :: (invariant load 4 from %fixed-stack.0, align 1, addrspace 5)
+  ; CHECK:   [[LOAD31:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX31]](p5) :: (invariant load 4 from %fixed-stack.0, addrspace 5)
   ; CHECK:   [[COPY32:%[0-9]+]]:sgpr_64 = COPY $sgpr30_sgpr31
   ; CHECK:   [[BUILD_VECTOR:%[0-9]+]]:_(<32 x s32>) = G_BUILD_VECTOR [[COPY]](s32), [[COPY1]](s32), [[COPY2]](s32), [[COPY3]](s32), [[COPY4]](s32), [[COPY5]](s32), [[COPY6]](s32), [[COPY7]](s32), [[COPY8]](s32), [[COPY9]](s32), [[COPY10]](s32), [[COPY11]](s32), [[COPY12]](s32), [[COPY13]](s32), [[COPY14]](s32), [[COPY15]](s32), [[COPY16]](s32), [[COPY17]](s32), [[COPY18]](s32), [[COPY19]](s32), [[COPY20]](s32), [[COPY21]](s32), [[COPY22]](s32), [[COPY23]](s32), [[COPY24]](s32), [[COPY25]](s32), [[COPY26]](s32), [[COPY27]](s32), [[COPY28]](s32), [[COPY29]](s32), [[COPY30]](s32), [[COPY31]](s32)
   ; CHECK:   [[BUILD_VECTOR1:%[0-9]+]]:_(<16 x s32>) = G_BUILD_VECTOR [[LOAD]](s32), [[LOAD1]](s32), [[LOAD2]](s32), [[LOAD3]](s32), [[LOAD4]](s32), [[LOAD5]](s32), [[LOAD6]](s32), [[LOAD7]](s32), [[LOAD8]](s32), [[LOAD9]](s32), [[LOAD10]](s32), [[LOAD11]](s32), [[LOAD12]](s32), [[LOAD13]](s32), [[LOAD14]](s32), [[LOAD15]](s32)
@@ -2178,37 +2178,37 @@ define void @void_func_v32i32_v16i8(<32 x i32> %arg0, <16 x i8> %arg1) #0 {
   ; CHECK:   [[COPY30:%[0-9]+]]:_(s32) = COPY $vgpr30
   ; CHECK:   [[COPY31:%[0-9]+]]:_(s32) = COPY $vgpr31
   ; CHECK:   [[FRAME_INDEX:%[0-9]+]]:_(p5) = G_FRAME_INDEX %fixed-stack.15
-  ; CHECK:   [[LOAD:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX]](p5) :: (invariant load 4 from %fixed-stack.15, align 1, addrspace 5)
+  ; CHECK:   [[LOAD:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX]](p5) :: (invariant load 4 from %fixed-stack.15, align 16, addrspace 5)
   ; CHECK:   [[FRAME_INDEX1:%[0-9]+]]:_(p5) = G_FRAME_INDEX %fixed-stack.14
-  ; CHECK:   [[LOAD1:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX1]](p5) :: (invariant load 4 from %fixed-stack.14, align 1, addrspace 5)
+  ; CHECK:   [[LOAD1:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX1]](p5) :: (invariant load 4 from %fixed-stack.14, addrspace 5)
   ; CHECK:   [[FRAME_INDEX2:%[0-9]+]]:_(p5) = G_FRAME_INDEX %fixed-stack.13
-  ; CHECK:   [[LOAD2:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX2]](p5) :: (invariant load 4 from %fixed-stack.13, align 1, addrspace 5)
+  ; CHECK:   [[LOAD2:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX2]](p5) :: (invariant load 4 from %fixed-stack.13, align 8, addrspace 5)
   ; CHECK:   [[FRAME_INDEX3:%[0-9]+]]:_(p5) = G_FRAME_INDEX %fixed-stack.12
-  ; CHECK:   [[LOAD3:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX3]](p5) :: (invariant load 4 from %fixed-stack.12, align 1, addrspace 5)
+  ; CHECK:   [[LOAD3:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX3]](p5) :: (invariant load 4 from %fixed-stack.12, addrspace 5)
   ; CHECK:   [[FRAME_INDEX4:%[0-9]+]]:_(p5) = G_FRAME_INDEX %fixed-stack.11
-  ; CHECK:   [[LOAD4:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX4]](p5) :: (invariant load 4 from %fixed-stack.11, align 1, addrspace 5)
+  ; CHECK:   [[LOAD4:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX4]](p5) :: (invariant load 4 from %fixed-stack.11, align 16, addrspace 5)
   ; CHECK:   [[FRAME_INDEX5:%[0-9]+]]:_(p5) = G_FRAME_INDEX %fixed-stack.10
-  ; CHECK:   [[LOAD5:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX5]](p5) :: (invariant load 4 from %fixed-stack.10, align 1, addrspace 5)
+  ; CHECK:   [[LOAD5:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX5]](p5) :: (invariant load 4 from %fixed-stack.10, addrspace 5)
   ; CHECK:   [[FRAME_INDEX6:%[0-9]+]]:_(p5) = G_FRAME_INDEX %fixed-stack.9
-  ; CHECK:   [[LOAD6:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX6]](p5) :: (invariant load 4 from %fixed-stack.9, align 1, addrspace 5)
+  ; CHECK:   [[LOAD6:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX6]](p5) :: (invariant load 4 from %fixed-stack.9, align 8, addrspace 5)
   ; CHECK:   [[FRAME_INDEX7:%[0-9]+]]:_(p5) = G_FRAME_INDEX %fixed-stack.8
-  ; CHECK:   [[LOAD7:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX7]](p5) :: (invariant load 4 from %fixed-stack.8, align 1, addrspace 5)
+  ; CHECK:   [[LOAD7:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX7]](p5) :: (invariant load 4 from %fixed-stack.8, addrspace 5)
   ; CHECK:   [[FRAME_INDEX8:%[0-9]+]]:_(p5) = G_FRAME_INDEX %fixed-stack.7
-  ; CHECK:   [[LOAD8:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX8]](p5) :: (invariant load 4 from %fixed-stack.7, align 1, addrspace 5)
+  ; CHECK:   [[LOAD8:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX8]](p5) :: (invariant load 4 from %fixed-stack.7, align 16, addrspace 5)
   ; CHECK:   [[FRAME_INDEX9:%[0-9]+]]:_(p5) = G_FRAME_INDEX %fixed-stack.6
-  ; CHECK:   [[LOAD9:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX9]](p5) :: (invariant load 4 from %fixed-stack.6, align 1, addrspace 5)
+  ; CHECK:   [[LOAD9:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX9]](p5) :: (invariant load 4 from %fixed-stack.6, addrspace 5)
   ; CHECK:   [[FRAME_INDEX10:%[0-9]+]]:_(p5) = G_FRAME_INDEX %fixed-stack.5
-  ; CHECK:   [[LOAD10:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX10]](p5) :: (invariant load 4 from %fixed-stack.5, align 1, addrspace 5)
+  ; CHECK:   [[LOAD10:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX10]](p5) :: (invariant load 4 from %fixed-stack.5, align 8, addrspace 5)
   ; CHECK:   [[FRAME_INDEX11:%[0-9]+]]:_(p5) = G_FRAME_INDEX %fixed-stack.4
-  ; CHECK:   [[LOAD11:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX11]](p5) :: (invariant load 4 from %fixed-stack.4, align 1, addrspace 5)
+  ; CHECK:   [[LOAD11:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX11]](p5) :: (invariant load 4 from %fixed-stack.4, addrspace 5)
   ; CHECK:   [[FRAME_INDEX12:%[0-9]+]]:_(p5) = G_FRAME_INDEX %fixed-stack.3
-  ; CHECK:   [[LOAD12:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX12]](p5) :: (invariant load 4 from %fixed-stack.3, align 1, addrspace 5)
+  ; CHECK:   [[LOAD12:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX12]](p5) :: (invariant load 4 from %fixed-stack.3, align 16, addrspace 5)
   ; CHECK:   [[FRAME_INDEX13:%[0-9]+]]:_(p5) = G_FRAME_INDEX %fixed-stack.2
-  ; CHECK:   [[LOAD13:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX13]](p5) :: (invariant load 4 from %fixed-stack.2, align 1, addrspace 5)
+  ; CHECK:   [[LOAD13:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX13]](p5) :: (invariant load 4 from %fixed-stack.2, addrspace 5)
   ; CHECK:   [[FRAME_INDEX14:%[0-9]+]]:_(p5) = G_FRAME_INDEX %fixed-stack.1
-  ; CHECK:   [[LOAD14:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX14]](p5) :: (invariant load 4 from %fixed-stack.1, align 1, addrspace 5)
+  ; CHECK:   [[LOAD14:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX14]](p5) :: (invariant load 4 from %fixed-stack.1, align 8, addrspace 5)
   ; CHECK:   [[FRAME_INDEX15:%[0-9]+]]:_(p5) = G_FRAME_INDEX %fixed-stack.0
-  ; CHECK:   [[LOAD15:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX15]](p5) :: (invariant load 4 from %fixed-stack.0, align 1, addrspace 5)
+  ; CHECK:   [[LOAD15:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX15]](p5) :: (invariant load 4 from %fixed-stack.0, addrspace 5)
   ; CHECK:   [[COPY32:%[0-9]+]]:sgpr_64 = COPY $sgpr30_sgpr31
   ; CHECK:   [[BUILD_VECTOR:%[0-9]+]]:_(<32 x s32>) = G_BUILD_VECTOR [[COPY]](s32), [[COPY1]](s32), [[COPY2]](s32), [[COPY3]](s32), [[COPY4]](s32), [[COPY5]](s32), [[COPY6]](s32), [[COPY7]](s32), [[COPY8]](s32), [[COPY9]](s32), [[COPY10]](s32), [[COPY11]](s32), [[COPY12]](s32), [[COPY13]](s32), [[COPY14]](s32), [[COPY15]](s32), [[COPY16]](s32), [[COPY17]](s32), [[COPY18]](s32), [[COPY19]](s32), [[COPY20]](s32), [[COPY21]](s32), [[COPY22]](s32), [[COPY23]](s32), [[COPY24]](s32), [[COPY25]](s32), [[COPY26]](s32), [[COPY27]](s32), [[COPY28]](s32), [[COPY29]](s32), [[COPY30]](s32), [[COPY31]](s32)
   ; CHECK:   [[BUILD_VECTOR1:%[0-9]+]]:_(<16 x s32>) = G_BUILD_VECTOR [[LOAD]](s32), [[LOAD1]](s32), [[LOAD2]](s32), [[LOAD3]](s32), [[LOAD4]](s32), [[LOAD5]](s32), [[LOAD6]](s32), [[LOAD7]](s32), [[LOAD8]](s32), [[LOAD9]](s32), [[LOAD10]](s32), [[LOAD11]](s32), [[LOAD12]](s32), [[LOAD13]](s32), [[LOAD14]](s32), [[LOAD15]](s32)

diff --git a/llvm/test/CodeGen/X86/GlobalISel/callingconv.ll b/llvm/test/CodeGen/X86/GlobalISel/callingconv.ll
index b8deacdb19b393e4dd23c1fa4b3fc84eb87a5073..da48f598a3f69c3ae57f4261086a2bd232a1ec44 100644 (file)
--- a/llvm/test/CodeGen/X86/GlobalISel/callingconv.ll
+++ b/llvm/test/CodeGen/X86/GlobalISel/callingconv.ll
@@ -1,6 +1,6 @@
 ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
-; RUN: llc -enable-cse-in-irtranslator=0 -enable-cse-in-legalizer=0 -mtriple=i386-linux-gnu -mattr=+sse2  -global-isel -verify-machineinstrs < %s -o - | FileCheck %s --check-prefix=ALL --check-prefix=X32
-; RUN: llc -enable-cse-in-irtranslator=0 -enable-cse-in-legalizer=0 -mtriple=x86_64-linux-gnu             -global-isel -verify-machineinstrs < %s -o - | FileCheck %s --check-prefix=ALL --check-prefix=X64
+; RUN: llc -enable-cse-in-irtranslator=0 -enable-cse-in-legalizer=0 -mtriple=i386-linux-gnu -mattr=+sse2  -global-isel -verify-machineinstrs < %s -o - | FileCheck %s --check-prefix=X32
+; RUN: llc -enable-cse-in-irtranslator=0 -enable-cse-in-legalizer=0 -mtriple=x86_64-linux-gnu             -global-isel -verify-machineinstrs < %s -o - | FileCheck %s --check-prefix=X64
 
 define i32 @test_ret_i32() {
 ; X32-LABEL: test_ret_i32:
@@ -117,7 +117,7 @@ define <8 x i32> @test_v8i32_args(<8 x i32> %arg1, <8 x i32> %arg2) {
 ; X32-NEXT:    subl $12, %esp
 ; X32-NEXT:    .cfi_def_cfa_offset 16
 ; X32-NEXT:    movaps %xmm2, %xmm0
-; X32-NEXT:    movups {{[0-9]+}}(%esp), %xmm1
+; X32-NEXT:    movaps {{[0-9]+}}(%esp), %xmm1
 ; X32-NEXT:    addl $12, %esp
 ; X32-NEXT:    .cfi_def_cfa_offset 4
 ; X32-NEXT:    retl
@@ -258,12 +258,12 @@ define <8 x i32> @test_split_return_callee(<8 x i32> %arg1, <8 x i32> %arg2) {
 ; X32-NEXT:    subl $44, %esp
 ; X32-NEXT:    .cfi_def_cfa_offset 48
 ; X32-NEXT:    movaps %xmm0, (%esp) # 16-byte Spill
-; X32-NEXT:    movaps %xmm1, {{[0-9]+}}(%esp) # 16-byte Spill
+; X32-NEXT:    movaps %xmm1, {{[-0-9]+}}(%e{{[sb]}}p) # 16-byte Spill
 ; X32-NEXT:    movdqa %xmm2, %xmm0
-; X32-NEXT:    movdqu {{[0-9]+}}(%esp), %xmm1
+; X32-NEXT:    movdqa {{[0-9]+}}(%esp), %xmm1
 ; X32-NEXT:    calll split_return_callee
 ; X32-NEXT:    paddd (%esp), %xmm0 # 16-byte Folded Reload
-; X32-NEXT:    paddd {{[0-9]+}}(%esp), %xmm1 # 16-byte Folded Reload
+; X32-NEXT:    paddd {{[-0-9]+}}(%e{{[sb]}}p), %xmm1 # 16-byte Folded Reload
 ; X32-NEXT:    addl $44, %esp
 ; X32-NEXT:    .cfi_def_cfa_offset 4
 ; X32-NEXT:    retl
@@ -273,12 +273,12 @@ define <8 x i32> @test_split_return_callee(<8 x i32> %arg1, <8 x i32> %arg2) {
 ; X64-NEXT:    subq $40, %rsp
 ; X64-NEXT:    .cfi_def_cfa_offset 48
 ; X64-NEXT:    movaps %xmm0, (%rsp) # 16-byte Spill
-; X64-NEXT:    movaps %xmm1, {{[0-9]+}}(%rsp) # 16-byte Spill
+; X64-NEXT:    movaps %xmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
 ; X64-NEXT:    movdqa %xmm2, %xmm0
 ; X64-NEXT:    movdqa %xmm3, %xmm1
 ; X64-NEXT:    callq split_return_callee
 ; X64-NEXT:    paddd (%rsp), %xmm0 # 16-byte Folded Reload
-; X64-NEXT:    paddd {{[0-9]+}}(%rsp), %xmm1 # 16-byte Folded Reload
+; X64-NEXT:    paddd {{[-0-9]+}}(%r{{[sb]}}p), %xmm1 # 16-byte Folded Reload
 ; X64-NEXT:    addq $40, %rsp
 ; X64-NEXT:    .cfi_def_cfa_offset 8
 ; X64-NEXT:    retq

diff --git a/llvm/test/CodeGen/X86/GlobalISel/irtranslator-callingconv.ll b/llvm/test/CodeGen/X86/GlobalISel/irtranslator-callingconv.ll
index a6ec164e85f62a550a19482e6ad9234bdb26984a..6c267652e17bb0c8188603761253f4bb4a54b0a2 100644 (file)
--- a/llvm/test/CodeGen/X86/GlobalISel/irtranslator-callingconv.ll
+++ b/llvm/test/CodeGen/X86/GlobalISel/irtranslator-callingconv.ll
@@ -10,21 +10,21 @@ define i8 @test_i8_args_8(i8 %arg1, i8 %arg2, i8 %arg3, i8 %arg4,
   ; X32-LABEL: name: test_i8_args_8
   ; X32: bb.1.entry:
   ; X32:   [[FRAME_INDEX:%[0-9]+]]:_(p0) = G_FRAME_INDEX %fixed-stack.7
-  ; X32:   [[LOAD:%[0-9]+]]:_(s8) = G_LOAD [[FRAME_INDEX]](p0) :: (invariant load 1 from %fixed-stack.7)
+  ; X32:   [[LOAD:%[0-9]+]]:_(s8) = G_LOAD [[FRAME_INDEX]](p0) :: (invariant load 1 from %fixed-stack.7, align 16)
   ; X32:   [[FRAME_INDEX1:%[0-9]+]]:_(p0) = G_FRAME_INDEX %fixed-stack.6
-  ; X32:   [[LOAD1:%[0-9]+]]:_(s8) = G_LOAD [[FRAME_INDEX1]](p0) :: (invariant load 1 from %fixed-stack.6)
+  ; X32:   [[LOAD1:%[0-9]+]]:_(s8) = G_LOAD [[FRAME_INDEX1]](p0) :: (invariant load 1 from %fixed-stack.6, align 4)
   ; X32:   [[FRAME_INDEX2:%[0-9]+]]:_(p0) = G_FRAME_INDEX %fixed-stack.5
-  ; X32:   [[LOAD2:%[0-9]+]]:_(s8) = G_LOAD [[FRAME_INDEX2]](p0) :: (invariant load 1 from %fixed-stack.5)
+  ; X32:   [[LOAD2:%[0-9]+]]:_(s8) = G_LOAD [[FRAME_INDEX2]](p0) :: (invariant load 1 from %fixed-stack.5, align 8)
   ; X32:   [[FRAME_INDEX3:%[0-9]+]]:_(p0) = G_FRAME_INDEX %fixed-stack.4
-  ; X32:   [[LOAD3:%[0-9]+]]:_(s8) = G_LOAD [[FRAME_INDEX3]](p0) :: (invariant load 1 from %fixed-stack.4)
+  ; X32:   [[LOAD3:%[0-9]+]]:_(s8) = G_LOAD [[FRAME_INDEX3]](p0) :: (invariant load 1 from %fixed-stack.4, align 4)
   ; X32:   [[FRAME_INDEX4:%[0-9]+]]:_(p0) = G_FRAME_INDEX %fixed-stack.3
-  ; X32:   [[LOAD4:%[0-9]+]]:_(s8) = G_LOAD [[FRAME_INDEX4]](p0) :: (invariant load 1 from %fixed-stack.3)
+  ; X32:   [[LOAD4:%[0-9]+]]:_(s8) = G_LOAD [[FRAME_INDEX4]](p0) :: (invariant load 1 from %fixed-stack.3, align 16)
   ; X32:   [[FRAME_INDEX5:%[0-9]+]]:_(p0) = G_FRAME_INDEX %fixed-stack.2
-  ; X32:   [[LOAD5:%[0-9]+]]:_(s8) = G_LOAD [[FRAME_INDEX5]](p0) :: (invariant load 1 from %fixed-stack.2)
+  ; X32:   [[LOAD5:%[0-9]+]]:_(s8) = G_LOAD [[FRAME_INDEX5]](p0) :: (invariant load 1 from %fixed-stack.2, align 4)
   ; X32:   [[FRAME_INDEX6:%[0-9]+]]:_(p0) = G_FRAME_INDEX %fixed-stack.1
-  ; X32:   [[LOAD6:%[0-9]+]]:_(s8) = G_LOAD [[FRAME_INDEX6]](p0) :: (invariant load 1 from %fixed-stack.1)
+  ; X32:   [[LOAD6:%[0-9]+]]:_(s8) = G_LOAD [[FRAME_INDEX6]](p0) :: (invariant load 1 from %fixed-stack.1, align 8)
   ; X32:   [[FRAME_INDEX7:%[0-9]+]]:_(p0) = G_FRAME_INDEX %fixed-stack.0
-  ; X32:   [[LOAD7:%[0-9]+]]:_(s8) = G_LOAD [[FRAME_INDEX7]](p0) :: (invariant load 1 from %fixed-stack.0)
+  ; X32:   [[LOAD7:%[0-9]+]]:_(s8) = G_LOAD [[FRAME_INDEX7]](p0) :: (invariant load 1 from %fixed-stack.0, align 4)
   ; X32:   [[GV:%[0-9]+]]:_(p0) = G_GLOBAL_VALUE @a1_8bit
   ; X32:   [[GV1:%[0-9]+]]:_(p0) = G_GLOBAL_VALUE @a7_8bit
   ; X32:   [[GV2:%[0-9]+]]:_(p0) = G_GLOBAL_VALUE @a8_8bit
@@ -49,9 +49,9 @@ define i8 @test_i8_args_8(i8 %arg1, i8 %arg2, i8 %arg3, i8 %arg4,
   ; X64:   [[COPY5:%[0-9]+]]:_(s32) = COPY $r9d
   ; X64:   [[TRUNC5:%[0-9]+]]:_(s8) = G_TRUNC [[COPY5]](s32)
   ; X64:   [[FRAME_INDEX:%[0-9]+]]:_(p0) = G_FRAME_INDEX %fixed-stack.1
-  ; X64:   [[LOAD:%[0-9]+]]:_(s8) = G_LOAD [[FRAME_INDEX]](p0) :: (invariant load 1 from %fixed-stack.1)
+  ; X64:   [[LOAD:%[0-9]+]]:_(s8) = G_LOAD [[FRAME_INDEX]](p0) :: (invariant load 1 from %fixed-stack.1, align 16)
   ; X64:   [[FRAME_INDEX1:%[0-9]+]]:_(p0) = G_FRAME_INDEX %fixed-stack.0
-  ; X64:   [[LOAD1:%[0-9]+]]:_(s8) = G_LOAD [[FRAME_INDEX1]](p0) :: (invariant load 1 from %fixed-stack.0)
+  ; X64:   [[LOAD1:%[0-9]+]]:_(s8) = G_LOAD [[FRAME_INDEX1]](p0) :: (invariant load 1 from %fixed-stack.0, align 8)
   ; X64:   [[GV:%[0-9]+]]:_(p0) = G_GLOBAL_VALUE @a1_8bit
   ; X64:   [[GV1:%[0-9]+]]:_(p0) = G_GLOBAL_VALUE @a7_8bit
   ; X64:   [[GV2:%[0-9]+]]:_(p0) = G_GLOBAL_VALUE @a8_8bit
@@ -76,21 +76,21 @@ define i32 @test_i32_args_8(i32 %arg1, i32 %arg2, i32 %arg3, i32 %arg4,
   ; X32-LABEL: name: test_i32_args_8
   ; X32: bb.1.entry:
   ; X32:   [[FRAME_INDEX:%[0-9]+]]:_(p0) = G_FRAME_INDEX %fixed-stack.7
-  ; X32:   [[LOAD:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX]](p0) :: (invariant load 4 from %fixed-stack.7, align 1)
+  ; X32:   [[LOAD:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX]](p0) :: (invariant load 4 from %fixed-stack.7, align 16)
   ; X32:   [[FRAME_INDEX1:%[0-9]+]]:_(p0) = G_FRAME_INDEX %fixed-stack.6
-  ; X32:   [[LOAD1:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX1]](p0) :: (invariant load 4 from %fixed-stack.6, align 1)
+  ; X32:   [[LOAD1:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX1]](p0) :: (invariant load 4 from %fixed-stack.6)
   ; X32:   [[FRAME_INDEX2:%[0-9]+]]:_(p0) = G_FRAME_INDEX %fixed-stack.5
-  ; X32:   [[LOAD2:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX2]](p0) :: (invariant load 4 from %fixed-stack.5, align 1)
+  ; X32:   [[LOAD2:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX2]](p0) :: (invariant load 4 from %fixed-stack.5, align 8)
   ; X32:   [[FRAME_INDEX3:%[0-9]+]]:_(p0) = G_FRAME_INDEX %fixed-stack.4
-  ; X32:   [[LOAD3:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX3]](p0) :: (invariant load 4 from %fixed-stack.4, align 1)
+  ; X32:   [[LOAD3:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX3]](p0) :: (invariant load 4 from %fixed-stack.4)
   ; X32:   [[FRAME_INDEX4:%[0-9]+]]:_(p0) = G_FRAME_INDEX %fixed-stack.3
-  ; X32:   [[LOAD4:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX4]](p0) :: (invariant load 4 from %fixed-stack.3, align 1)
+  ; X32:   [[LOAD4:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX4]](p0) :: (invariant load 4 from %fixed-stack.3, align 16)
   ; X32:   [[FRAME_INDEX5:%[0-9]+]]:_(p0) = G_FRAME_INDEX %fixed-stack.2
-  ; X32:   [[LOAD5:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX5]](p0) :: (invariant load 4 from %fixed-stack.2, align 1)
+  ; X32:   [[LOAD5:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX5]](p0) :: (invariant load 4 from %fixed-stack.2)
   ; X32:   [[FRAME_INDEX6:%[0-9]+]]:_(p0) = G_FRAME_INDEX %fixed-stack.1
-  ; X32:   [[LOAD6:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX6]](p0) :: (invariant load 4 from %fixed-stack.1, align 1)
+  ; X32:   [[LOAD6:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX6]](p0) :: (invariant load 4 from %fixed-stack.1, align 8)
   ; X32:   [[FRAME_INDEX7:%[0-9]+]]:_(p0) = G_FRAME_INDEX %fixed-stack.0
-  ; X32:   [[LOAD7:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX7]](p0) :: (invariant load 4 from %fixed-stack.0, align 1)
+  ; X32:   [[LOAD7:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX7]](p0) :: (invariant load 4 from %fixed-stack.0)
   ; X32:   [[GV:%[0-9]+]]:_(p0) = G_GLOBAL_VALUE @a1_32bit
   ; X32:   [[GV1:%[0-9]+]]:_(p0) = G_GLOBAL_VALUE @a7_32bit
   ; X32:   [[GV2:%[0-9]+]]:_(p0) = G_GLOBAL_VALUE @a8_32bit
@@ -109,9 +109,9 @@ define i32 @test_i32_args_8(i32 %arg1, i32 %arg2, i32 %arg3, i32 %arg4,
   ; X64:   [[COPY4:%[0-9]+]]:_(s32) = COPY $r8d
   ; X64:   [[COPY5:%[0-9]+]]:_(s32) = COPY $r9d
   ; X64:   [[FRAME_INDEX:%[0-9]+]]:_(p0) = G_FRAME_INDEX %fixed-stack.1
-  ; X64:   [[LOAD:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX]](p0) :: (invariant load 4 from %fixed-stack.1, align 1)
+  ; X64:   [[LOAD:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX]](p0) :: (invariant load 4 from %fixed-stack.1, align 16)
   ; X64:   [[FRAME_INDEX1:%[0-9]+]]:_(p0) = G_FRAME_INDEX %fixed-stack.0
-  ; X64:   [[LOAD1:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX1]](p0) :: (invariant load 4 from %fixed-stack.0, align 1)
+  ; X64:   [[LOAD1:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX1]](p0) :: (invariant load 4 from %fixed-stack.0, align 8)
   ; X64:   [[GV:%[0-9]+]]:_(p0) = G_GLOBAL_VALUE @a1_32bit
   ; X64:   [[GV1:%[0-9]+]]:_(p0) = G_GLOBAL_VALUE @a7_32bit
   ; X64:   [[GV2:%[0-9]+]]:_(p0) = G_GLOBAL_VALUE @a8_32bit
@@ -136,37 +136,37 @@ define i64 @test_i64_args_8(i64 %arg1, i64 %arg2, i64 %arg3, i64 %arg4,
   ; X32-LABEL: name: test_i64_args_8
   ; X32: bb.1.entry:
   ; X32:   [[FRAME_INDEX:%[0-9]+]]:_(p0) = G_FRAME_INDEX %fixed-stack.15
-  ; X32:   [[LOAD:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX]](p0) :: (invariant load 4 from %fixed-stack.15, align 1)
+  ; X32:   [[LOAD:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX]](p0) :: (invariant load 4 from %fixed-stack.15, align 16)
   ; X32:   [[FRAME_INDEX1:%[0-9]+]]:_(p0) = G_FRAME_INDEX %fixed-stack.14
-  ; X32:   [[LOAD1:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX1]](p0) :: (invariant load 4 from %fixed-stack.14, align 1)
+  ; X32:   [[LOAD1:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX1]](p0) :: (invariant load 4 from %fixed-stack.14)
   ; X32:   [[FRAME_INDEX2:%[0-9]+]]:_(p0) = G_FRAME_INDEX %fixed-stack.13
-  ; X32:   [[LOAD2:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX2]](p0) :: (invariant load 4 from %fixed-stack.13, align 1)
+  ; X32:   [[LOAD2:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX2]](p0) :: (invariant load 4 from %fixed-stack.13, align 8)
   ; X32:   [[FRAME_INDEX3:%[0-9]+]]:_(p0) = G_FRAME_INDEX %fixed-stack.12
-  ; X32:   [[LOAD3:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX3]](p0) :: (invariant load 4 from %fixed-stack.12, align 1)
+  ; X32:   [[LOAD3:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX3]](p0) :: (invariant load 4 from %fixed-stack.12)
   ; X32:   [[FRAME_INDEX4:%[0-9]+]]:_(p0) = G_FRAME_INDEX %fixed-stack.11
-  ; X32:   [[LOAD4:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX4]](p0) :: (invariant load 4 from %fixed-stack.11, align 1)
+  ; X32:   [[LOAD4:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX4]](p0) :: (invariant load 4 from %fixed-stack.11, align 16)
   ; X32:   [[FRAME_INDEX5:%[0-9]+]]:_(p0) = G_FRAME_INDEX %fixed-stack.10
-  ; X32:   [[LOAD5:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX5]](p0) :: (invariant load 4 from %fixed-stack.10, align 1)
+  ; X32:   [[LOAD5:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX5]](p0) :: (invariant load 4 from %fixed-stack.10)
   ; X32:   [[FRAME_INDEX6:%[0-9]+]]:_(p0) = G_FRAME_INDEX %fixed-stack.9
-  ; X32:   [[LOAD6:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX6]](p0) :: (invariant load 4 from %fixed-stack.9, align 1)
+  ; X32:   [[LOAD6:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX6]](p0) :: (invariant load 4 from %fixed-stack.9, align 8)
   ; X32:   [[FRAME_INDEX7:%[0-9]+]]:_(p0) = G_FRAME_INDEX %fixed-stack.8
-  ; X32:   [[LOAD7:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX7]](p0) :: (invariant load 4 from %fixed-stack.8, align 1)
+  ; X32:   [[LOAD7:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX7]](p0) :: (invariant load 4 from %fixed-stack.8)
   ; X32:   [[FRAME_INDEX8:%[0-9]+]]:_(p0) = G_FRAME_INDEX %fixed-stack.7
-  ; X32:   [[LOAD8:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX8]](p0) :: (invariant load 4 from %fixed-stack.7, align 1)
+  ; X32:   [[LOAD8:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX8]](p0) :: (invariant load 4 from %fixed-stack.7, align 16)
   ; X32:   [[FRAME_INDEX9:%[0-9]+]]:_(p0) = G_FRAME_INDEX %fixed-stack.6
-  ; X32:   [[LOAD9:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX9]](p0) :: (invariant load 4 from %fixed-stack.6, align 1)
+  ; X32:   [[LOAD9:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX9]](p0) :: (invariant load 4 from %fixed-stack.6)
   ; X32:   [[FRAME_INDEX10:%[0-9]+]]:_(p0) = G_FRAME_INDEX %fixed-stack.5
-  ; X32:   [[LOAD10:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX10]](p0) :: (invariant load 4 from %fixed-stack.5, align 1)
+  ; X32:   [[LOAD10:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX10]](p0) :: (invariant load 4 from %fixed-stack.5, align 8)
   ; X32:   [[FRAME_INDEX11:%[0-9]+]]:_(p0) = G_FRAME_INDEX %fixed-stack.4
-  ; X32:   [[LOAD11:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX11]](p0) :: (invariant load 4 from %fixed-stack.4, align 1)
+  ; X32:   [[LOAD11:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX11]](p0) :: (invariant load 4 from %fixed-stack.4)
   ; X32:   [[FRAME_INDEX12:%[0-9]+]]:_(p0) = G_FRAME_INDEX %fixed-stack.3
-  ; X32:   [[LOAD12:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX12]](p0) :: (invariant load 4 from %fixed-stack.3, align 1)
+  ; X32:   [[LOAD12:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX12]](p0) :: (invariant load 4 from %fixed-stack.3, align 16)
   ; X32:   [[FRAME_INDEX13:%[0-9]+]]:_(p0) = G_FRAME_INDEX %fixed-stack.2
-  ; X32:   [[LOAD13:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX13]](p0) :: (invariant load 4 from %fixed-stack.2, align 1)
+  ; X32:   [[LOAD13:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX13]](p0) :: (invariant load 4 from %fixed-stack.2)
   ; X32:   [[FRAME_INDEX14:%[0-9]+]]:_(p0) = G_FRAME_INDEX %fixed-stack.1
-  ; X32:   [[LOAD14:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX14]](p0) :: (invariant load 4 from %fixed-stack.1, align 1)
+  ; X32:   [[LOAD14:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX14]](p0) :: (invariant load 4 from %fixed-stack.1, align 8)
   ; X32:   [[FRAME_INDEX15:%[0-9]+]]:_(p0) = G_FRAME_INDEX %fixed-stack.0
-  ; X32:   [[LOAD15:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX15]](p0) :: (invariant load 4 from %fixed-stack.0, align 1)
+  ; X32:   [[LOAD15:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX15]](p0) :: (invariant load 4 from %fixed-stack.0)
   ; X32:   [[MV:%[0-9]+]]:_(s64) = G_MERGE_VALUES [[LOAD]](s32), [[LOAD1]](s32)
   ; X32:   [[MV1:%[0-9]+]]:_(s64) = G_MERGE_VALUES [[LOAD2]](s32), [[LOAD3]](s32)
   ; X32:   [[MV2:%[0-9]+]]:_(s64) = G_MERGE_VALUES [[LOAD4]](s32), [[LOAD5]](s32)
@@ -195,9 +195,9 @@ define i64 @test_i64_args_8(i64 %arg1, i64 %arg2, i64 %arg3, i64 %arg4,
   ; X64:   [[COPY4:%[0-9]+]]:_(s64) = COPY $r8
   ; X64:   [[COPY5:%[0-9]+]]:_(s64) = COPY $r9
   ; X64:   [[FRAME_INDEX:%[0-9]+]]:_(p0) = G_FRAME_INDEX %fixed-stack.1
-  ; X64:   [[LOAD:%[0-9]+]]:_(s64) = G_LOAD [[FRAME_INDEX]](p0) :: (invariant load 8 from %fixed-stack.1, align 1)
+  ; X64:   [[LOAD:%[0-9]+]]:_(s64) = G_LOAD [[FRAME_INDEX]](p0) :: (invariant load 8 from %fixed-stack.1, align 16)
   ; X64:   [[FRAME_INDEX1:%[0-9]+]]:_(p0) = G_FRAME_INDEX %fixed-stack.0
-  ; X64:   [[LOAD1:%[0-9]+]]:_(s64) = G_LOAD [[FRAME_INDEX1]](p0) :: (invariant load 8 from %fixed-stack.0, align 1)
+  ; X64:   [[LOAD1:%[0-9]+]]:_(s64) = G_LOAD [[FRAME_INDEX1]](p0) :: (invariant load 8 from %fixed-stack.0)
   ; X64:   [[GV:%[0-9]+]]:_(p0) = G_GLOBAL_VALUE @a1_64bit
   ; X64:   [[GV1:%[0-9]+]]:_(p0) = G_GLOBAL_VALUE @a7_64bit
   ; X64:   [[GV2:%[0-9]+]]:_(p0) = G_GLOBAL_VALUE @a8_64bit
@@ -219,9 +219,9 @@ define float @test_float_args(float %arg1, float %arg2) {
   ; X32-LABEL: name: test_float_args
   ; X32: bb.1 (%ir-block.0):
   ; X32:   [[FRAME_INDEX:%[0-9]+]]:_(p0) = G_FRAME_INDEX %fixed-stack.1
-  ; X32:   [[LOAD:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX]](p0) :: (invariant load 4 from %fixed-stack.1, align 1)
+  ; X32:   [[LOAD:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX]](p0) :: (invariant load 4 from %fixed-stack.1, align 16)
   ; X32:   [[FRAME_INDEX1:%[0-9]+]]:_(p0) = G_FRAME_INDEX %fixed-stack.0
-  ; X32:   [[LOAD1:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX1]](p0) :: (invariant load 4 from %fixed-stack.0, align 1)
+  ; X32:   [[LOAD1:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX1]](p0) :: (invariant load 4 from %fixed-stack.0)
   ; X32:   [[ANYEXT:%[0-9]+]]:_(s80) = G_ANYEXT [[LOAD1]](s32)
   ; X32:   $fp0 = COPY [[ANYEXT]](s80)
   ; X32:   RET 0, implicit $fp0
@@ -242,9 +242,9 @@ define double @test_double_args(double %arg1, double %arg2) {
   ; X32-LABEL: name: test_double_args
   ; X32: bb.1 (%ir-block.0):
   ; X32:   [[FRAME_INDEX:%[0-9]+]]:_(p0) = G_FRAME_INDEX %fixed-stack.1
-  ; X32:   [[LOAD:%[0-9]+]]:_(s64) = G_LOAD [[FRAME_INDEX]](p0) :: (invariant load 8 from %fixed-stack.1, align 1)
+  ; X32:   [[LOAD:%[0-9]+]]:_(s64) = G_LOAD [[FRAME_INDEX]](p0) :: (invariant load 8 from %fixed-stack.1, align 16)
   ; X32:   [[FRAME_INDEX1:%[0-9]+]]:_(p0) = G_FRAME_INDEX %fixed-stack.0
-  ; X32:   [[LOAD1:%[0-9]+]]:_(s64) = G_LOAD [[FRAME_INDEX1]](p0) :: (invariant load 8 from %fixed-stack.0, align 1)
+  ; X32:   [[LOAD1:%[0-9]+]]:_(s64) = G_LOAD [[FRAME_INDEX1]](p0) :: (invariant load 8 from %fixed-stack.0)
   ; X32:   [[ANYEXT:%[0-9]+]]:_(s80) = G_ANYEXT [[LOAD1]](s64)
   ; X32:   $fp0 = COPY [[ANYEXT]](s80)
   ; X32:   RET 0, implicit $fp0
@@ -319,7 +319,7 @@ define i32 * @test_memop_i32(i32 * %p1) {
   ; X32-LABEL: name: test_memop_i32
   ; X32: bb.1 (%ir-block.0):
   ; X32:   [[FRAME_INDEX:%[0-9]+]]:_(p0) = G_FRAME_INDEX %fixed-stack.0
-  ; X32:   [[LOAD:%[0-9]+]]:_(p0) = G_LOAD [[FRAME_INDEX]](p0) :: (invariant load 4 from %fixed-stack.0, align 1)
+  ; X32:   [[LOAD:%[0-9]+]]:_(p0) = G_LOAD [[FRAME_INDEX]](p0) :: (invariant load 4 from %fixed-stack.0, align 16)
   ; X32:   $eax = COPY [[LOAD]](p0)
   ; X32:   RET 0, implicit $eax
   ; X64-LABEL: name: test_memop_i32
@@ -354,9 +354,9 @@ define void @test_simple_arg(i32 %in0, i32 %in1) {
   ; X32-LABEL: name: test_simple_arg
   ; X32: bb.1 (%ir-block.0):
   ; X32:   [[FRAME_INDEX:%[0-9]+]]:_(p0) = G_FRAME_INDEX %fixed-stack.1
-  ; X32:   [[LOAD:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX]](p0) :: (invariant load 4 from %fixed-stack.1, align 1)
+  ; X32:   [[LOAD:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX]](p0) :: (invariant load 4 from %fixed-stack.1, align 16)
   ; X32:   [[FRAME_INDEX1:%[0-9]+]]:_(p0) = G_FRAME_INDEX %fixed-stack.0
-  ; X32:   [[LOAD1:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX1]](p0) :: (invariant load 4 from %fixed-stack.0, align 1)
+  ; X32:   [[LOAD1:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX1]](p0) :: (invariant load 4 from %fixed-stack.0)
   ; X32:   ADJCALLSTACKDOWN32 8, 0, 0, implicit-def $esp, implicit-def $eflags, implicit-def $ssp, implicit $esp, implicit $ssp
   ; X32:   [[COPY:%[0-9]+]]:_(p0) = COPY $esp
   ; X32:   [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 0
@@ -389,7 +389,7 @@ define void @test_simple_arg8_call(i32 %in0) {
   ; X32-LABEL: name: test_simple_arg8_call
   ; X32: bb.1 (%ir-block.0):
   ; X32:   [[FRAME_INDEX:%[0-9]+]]:_(p0) = G_FRAME_INDEX %fixed-stack.0
-  ; X32:   [[LOAD:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX]](p0) :: (invariant load 4 from %fixed-stack.0, align 1)
+  ; X32:   [[LOAD:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX]](p0) :: (invariant load 4 from %fixed-stack.0, align 16)
   ; X32:   ADJCALLSTACKDOWN32 32, 0, 0, implicit-def $esp, implicit-def $eflags, implicit-def $ssp, implicit $esp, implicit $ssp
   ; X32:   [[COPY:%[0-9]+]]:_(p0) = COPY $esp
   ; X32:   [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 0
@@ -493,7 +493,7 @@ define <8 x i32> @test_split_return_callee(<8 x i32> %arg1, <8 x i32> %arg2) {
   ; X32:   [[COPY1:%[0-9]+]]:_(<4 x s32>) = COPY $xmm1
   ; X32:   [[COPY2:%[0-9]+]]:_(<4 x s32>) = COPY $xmm2
   ; X32:   [[FRAME_INDEX:%[0-9]+]]:_(p0) = G_FRAME_INDEX %fixed-stack.0
-  ; X32:   [[LOAD:%[0-9]+]]:_(<4 x s32>) = G_LOAD [[FRAME_INDEX]](p0) :: (invariant load 16 from %fixed-stack.0, align 1)
+  ; X32:   [[LOAD:%[0-9]+]]:_(<4 x s32>) = G_LOAD [[FRAME_INDEX]](p0) :: (invariant load 16 from %fixed-stack.0)
   ; X32:   [[CONCAT_VECTORS:%[0-9]+]]:_(<8 x s32>) = G_CONCAT_VECTORS [[COPY]](<4 x s32>), [[COPY1]](<4 x s32>)
   ; X32:   [[CONCAT_VECTORS1:%[0-9]+]]:_(<8 x s32>) = G_CONCAT_VECTORS [[COPY2]](<4 x s32>), [[LOAD]](<4 x s32>)
   ; X32:   ADJCALLSTACKDOWN32 0, 0, 0, implicit-def $esp, implicit-def $eflags, implicit-def $ssp, implicit $esp, implicit $ssp
@@ -542,7 +542,7 @@ define void @test_indirect_call(void()* %func) {
   ; X32-LABEL: name: test_indirect_call
   ; X32: bb.1 (%ir-block.0):
   ; X32:   [[FRAME_INDEX:%[0-9]+]]:_(p0) = G_FRAME_INDEX %fixed-stack.0
-  ; X32:   [[LOAD:%[0-9]+]]:gr32(p0) = G_LOAD [[FRAME_INDEX]](p0) :: (invariant load 4 from %fixed-stack.0, align 1)
+  ; X32:   [[LOAD:%[0-9]+]]:gr32(p0) = G_LOAD [[FRAME_INDEX]](p0) :: (invariant load 4 from %fixed-stack.0, align 16)
   ; X32:   ADJCALLSTACKDOWN32 0, 0, 0, implicit-def $esp, implicit-def $eflags, implicit-def $ssp, implicit $esp, implicit $ssp
   ; X32:   CALL32r [[LOAD]](p0), csr_32, implicit $esp, implicit $ssp
   ; X32:   ADJCALLSTACKUP32 0, 0, implicit-def $esp, implicit-def $eflags, implicit-def $ssp, implicit $esp, implicit $ssp
@@ -565,7 +565,7 @@ define void @test_abi_exts_call(i8* %addr) {
   ; X32-LABEL: name: test_abi_exts_call
   ; X32: bb.1 (%ir-block.0):
   ; X32:   [[FRAME_INDEX:%[0-9]+]]:_(p0) = G_FRAME_INDEX %fixed-stack.0
-  ; X32:   [[LOAD:%[0-9]+]]:_(p0) = G_LOAD [[FRAME_INDEX]](p0) :: (invariant load 4 from %fixed-stack.0, align 1)
+  ; X32:   [[LOAD:%[0-9]+]]:_(p0) = G_LOAD [[FRAME_INDEX]](p0) :: (invariant load 4 from %fixed-stack.0, align 16)
   ; X32:   [[LOAD1:%[0-9]+]]:_(s8) = G_LOAD [[LOAD]](p0) :: (load 1 from %ir.addr)
   ; X32:   ADJCALLSTACKDOWN32 4, 0, 0, implicit-def $esp, implicit-def $eflags, implicit-def $ssp, implicit $esp, implicit $ssp
   ; X32:   [[COPY:%[0-9]+]]:_(p0) = COPY $esp
@@ -623,9 +623,9 @@ define void @test_variadic_call_1(i8** %addr_ptr, i32* %val_ptr) {
   ; X32-LABEL: name: test_variadic_call_1
   ; X32: bb.1 (%ir-block.0):
   ; X32:   [[FRAME_INDEX:%[0-9]+]]:_(p0) = G_FRAME_INDEX %fixed-stack.1
-  ; X32:   [[LOAD:%[0-9]+]]:_(p0) = G_LOAD [[FRAME_INDEX]](p0) :: (invariant load 4 from %fixed-stack.1, align 1)
+  ; X32:   [[LOAD:%[0-9]+]]:_(p0) = G_LOAD [[FRAME_INDEX]](p0) :: (invariant load 4 from %fixed-stack.1, align 16)
   ; X32:   [[FRAME_INDEX1:%[0-9]+]]:_(p0) = G_FRAME_INDEX %fixed-stack.0
-  ; X32:   [[LOAD1:%[0-9]+]]:_(p0) = G_LOAD [[FRAME_INDEX1]](p0) :: (invariant load 4 from %fixed-stack.0, align 1)
+  ; X32:   [[LOAD1:%[0-9]+]]:_(p0) = G_LOAD [[FRAME_INDEX1]](p0) :: (invariant load 4 from %fixed-stack.0)
   ; X32:   [[LOAD2:%[0-9]+]]:_(p0) = G_LOAD [[LOAD]](p0) :: (load 4 from %ir.addr_ptr)
   ; X32:   [[LOAD3:%[0-9]+]]:_(s32) = G_LOAD [[LOAD1]](p0) :: (load 4 from %ir.val_ptr)
   ; X32:   ADJCALLSTACKDOWN32 8, 0, 0, implicit-def $esp, implicit-def $eflags, implicit-def $ssp, implicit $esp, implicit $ssp
@@ -664,9 +664,9 @@ define void @test_variadic_call_2(i8** %addr_ptr, double* %val_ptr) {
   ; X32-LABEL: name: test_variadic_call_2
   ; X32: bb.1 (%ir-block.0):
   ; X32:   [[FRAME_INDEX:%[0-9]+]]:_(p0) = G_FRAME_INDEX %fixed-stack.1
-  ; X32:   [[LOAD:%[0-9]+]]:_(p0) = G_LOAD [[FRAME_INDEX]](p0) :: (invariant load 4 from %fixed-stack.1, align 1)
+  ; X32:   [[LOAD:%[0-9]+]]:_(p0) = G_LOAD [[FRAME_INDEX]](p0) :: (invariant load 4 from %fixed-stack.1, align 16)
   ; X32:   [[FRAME_INDEX1:%[0-9]+]]:_(p0) = G_FRAME_INDEX %fixed-stack.0
-  ; X32:   [[LOAD1:%[0-9]+]]:_(p0) = G_LOAD [[FRAME_INDEX1]](p0) :: (invariant load 4 from %fixed-stack.0, align 1)
+  ; X32:   [[LOAD1:%[0-9]+]]:_(p0) = G_LOAD [[FRAME_INDEX1]](p0) :: (invariant load 4 from %fixed-stack.0)
   ; X32:   [[LOAD2:%[0-9]+]]:_(p0) = G_LOAD [[LOAD]](p0) :: (load 4 from %ir.addr_ptr)
   ; X32:   [[LOAD3:%[0-9]+]]:_(s64) = G_LOAD [[LOAD1]](p0) :: (load 8 from %ir.val_ptr, align 4)
   ; X32:   ADJCALLSTACKDOWN32 12, 0, 0, implicit-def $esp, implicit-def $eflags, implicit-def $ssp, implicit $esp, implicit $ssp