Make RWPI use movw/movt when available

[christof]

Summary

When constructing global address literals while targeting the RWPI relocation model. LLVM currently only uses literal pools. If MOVW/MOVT instructions are available we can use these instead. Beside being more efficient it allows -arm-execute-only to work with -relocation-model=RWPI as well.

When we generate MOVW/MOVT for global addresses when targeting the RWPI relocation model, we need to use base relative relocations. This patch does the needed plumbing in MC to generate these for MOVW/MOVT.

[olista01]

The test change removes the tests of the constant-pool code path, but it looks like this path will still be used when optimising for size and not using execute-only. Could you extend the tests to check both code-paths?

lib/Target/ARM/ARMISelLowering.cpp

3195 ↗

(On Diff #86944)

The getCopyFromReg and ISD::ADD are duplicated, could they be pulled below the if?

[christof]

Added tests for ARM and Thumb2 without MOVT support and addressed the inline comments.

[olista01]

Thanks, LGTM.

llvm/trunk/lib/Target/ARM/ARMISelLowering.cpp

if (isPositionIndependent()) {
     return Result;
   } else if (Subtarget->isROPI() && IsRO) {
     // PC-relative.
     SDValue G = DAG.getTargetGlobalAddress(GV, dl, PtrVT);
     SDValue Result = DAG.getNode(ARMISD::WrapperPIC, dl, PtrVT, G);
     return Result;
   } else if (Subtarget->isRWPI() && !IsRO) {
     // SB-relative.
+    SDValue RelAddr;
+    if (Subtarget->useMovt(DAG.getMachineFunction())) {
+      ++NumMovwMovt;
+      SDValue G = DAG.getTargetGlobalAddress(GV, dl, PtrVT, 0, ARMII::MO_SBREL);
+      RelAddr = DAG.getNode(ARMISD::Wrapper, dl, PtrVT, G);
+    } else { // use literal pool for address constant
       ARMConstantPoolValue *CPV =
         ARMConstantPoolConstant::Create(GV, ARMCP::SBREL);
       SDValue CPAddr = DAG.getTargetConstantPool(CPV, PtrVT, 4);
       CPAddr = DAG.getNode(ARMISD::Wrapper, dl, MVT::i32, CPAddr);
-    SDValue G = DAG.getLoad(
+      RelAddr = DAG.getLoad(
           PtrVT, dl, DAG.getEntryNode(), CPAddr,
           MachinePointerInfo::getConstantPool(DAG.getMachineFunction()));
+    }
     SDValue SB = DAG.getCopyFromReg(DAG.getEntryNode(), dl, ARM::R9, PtrVT);
-    SDValue Result = DAG.getNode(ISD::ADD, dl, PtrVT, SB, G);
+    SDValue Result = DAG.getNode(ISD::ADD, dl, PtrVT, SB, RelAddr);
     return Result;
   }
 
   // If we have T2 ops, we can materialize the address directly via movt/movw
   // pair. This is always cheaper.
   if (Subtarget->useMovt(DAG.getMachineFunction())) {
     ++NumMovwMovt;
     // FIXME: Once remat is capable of dealing with instructions with register

llvm/trunk/lib/Target/ARM/ARMMCInstLower.cpp

 #include "llvm/Support/ErrorHandling.h"
 #include <cassert>
 #include <cstdint>
 
 using namespace llvm;
 
 MCOperand ARMAsmPrinter::GetSymbolRef(const MachineOperand &MO,
                                       const MCSymbol *Symbol) {
+  MCSymbolRefExpr::VariantKind SymbolVariant = MCSymbolRefExpr::VK_None;
+  if (MO.getTargetFlags() & ARMII::MO_SBREL)
+    SymbolVariant = MCSymbolRefExpr::VK_ARM_SBREL;
+
   const MCExpr *Expr =
-      MCSymbolRefExpr::create(Symbol, MCSymbolRefExpr::VK_None, OutContext);
+      MCSymbolRefExpr::create(Symbol, SymbolVariant, OutContext);
   switch (MO.getTargetFlags() & ARMII::MO_OPTION_MASK) {
   default:
     llvm_unreachable("Unknown target flag on symbol operand");
   case ARMII::MO_NO_FLAG:
     break;
   case ARMII::MO_LO16:
     Expr =
-        MCSymbolRefExpr::create(Symbol, MCSymbolRefExpr::VK_None, OutContext);
+        MCSymbolRefExpr::create(Symbol, SymbolVariant, OutContext);
     Expr = ARMMCExpr::createLower16(Expr, OutContext);
     break;
   case ARMII::MO_HI16:
     Expr =
-        MCSymbolRefExpr::create(Symbol, MCSymbolRefExpr::VK_None, OutContext);
+        MCSymbolRefExpr::create(Symbol, SymbolVariant, OutContext);
     Expr = ARMMCExpr::createUpper16(Expr, OutContext);
     break;
   }
 
   if (!MO.isJTI() && MO.getOffset())
     Expr = MCBinaryExpr::createAdd(Expr,
                                    MCConstantExpr::create(MO.getOffset(),
                                                           OutContext),

llvm/trunk/lib/Target/ARM/MCTargetDesc/ARMBaseInfo.h

enum TOF {
     MO_LO16 = 0x1,
 
     /// MO_HI16 - On a symbol operand, this represents a relocation containing
     /// higher 16 bit of the address. Used only via movt instruction.
     MO_HI16 = 0x2,
 
     /// MO_OPTION_MASK - Most flags are mutually exclusive; this mask selects
     /// just that part of the flag set.
-    MO_OPTION_MASK = 0x1f,
+    MO_OPTION_MASK = 0x0f,
+
+    /// MO_SBREL - On a symbol operand, this represents a static base relative
+    /// relocation. Used in movw and movt instructions.
+    MO_SBREL = 0x10,
 
     /// MO_DLLIMPORT - On a symbol operand, this represents that the reference
     /// to the symbol is for an import stub.  This is used for DLL import
     /// storage class indication on Windows.
     MO_DLLIMPORT = 0x20,
 
     /// MO_SECREL - On a symbol operand this indicates that the immediate is
     /// the offset from beginning of section.

llvm/trunk/lib/Target/ARM/MCTargetDesc/ARMELFObjectWriter.cpp

case ARM::fixup_arm_movw_lo16:
         Type = ELF::R_ARM_MOVW_ABS_NC;
         break;
       case MCSymbolRefExpr::VK_ARM_SBREL:
         Type = ELF:: R_ARM_MOVW_BREL_NC;
         break;
       }
       break;
     case ARM::fixup_t2_movt_hi16:
+      switch (Modifier) {
+      default: llvm_unreachable("Unsupported Modifier");
+      case MCSymbolRefExpr::VK_None:
         Type = ELF::R_ARM_THM_MOVT_ABS;
         break;
+      case MCSymbolRefExpr::VK_ARM_SBREL:
+        Type = ELF:: R_ARM_THM_MOVT_BREL;
+        break;
+      }
+      break;
     case ARM::fixup_t2_movw_lo16:
+      switch (Modifier) {
+      default: llvm_unreachable("Unsupported Modifier");
+      case MCSymbolRefExpr::VK_None:
         Type = ELF::R_ARM_THM_MOVW_ABS_NC;
         break;
+      case MCSymbolRefExpr::VK_ARM_SBREL:
+        Type = ELF:: R_ARM_THM_MOVW_BREL_NC;
+        break;
+      }
+      break;
     }
   }
 
   return Type;
 }
 
 MCObjectWriter *llvm::createARMELFObjectWriter(raw_pwrite_stream &OS,
                                                uint8_t OSABI,
                                                bool IsLittleEndian) {
   MCELFObjectTargetWriter *MOTW = new ARMELFObjectWriter(OSABI);
   return createELFObjectWriter(MOTW, OS, IsLittleEndian);
 }

llvm/trunk/test/CodeGen/ARM/arm-position-independence.ll

 ; RUN: llc -relocation-model=static    -mtriple=armv7a--none-eabi < %s | FileCheck %s --check-prefix=CHECK --check-prefix=ARM_RO_ABS --check-prefix=ARM_RW_ABS
 ; RUN: llc -relocation-model=ropi      -mtriple=armv7a--none-eabi < %s | FileCheck %s --check-prefix=CHECK --check-prefix=ARM_RO_PC  --check-prefix=ARM_RW_ABS
 ; RUN: llc -relocation-model=rwpi      -mtriple=armv7a--none-eabi < %s | FileCheck %s --check-prefix=CHECK --check-prefix=ARM_RO_ABS --check-prefix=ARM_RW_SB
 ; RUN: llc -relocation-model=ropi-rwpi -mtriple=armv7a--none-eabi < %s | FileCheck %s --check-prefix=CHECK --check-prefix=ARM_RO_PC  --check-prefix=ARM_RW_SB
 
 ; RUN: llc -relocation-model=static    -mtriple=thumbv7m--none-eabi < %s | FileCheck %s --check-prefix=CHECK --check-prefix=THUMB2_RO_ABS --check-prefix=THUMB2_RW_ABS
 ; RUN: llc -relocation-model=ropi      -mtriple=thumbv7m--none-eabi < %s | FileCheck %s --check-prefix=CHECK --check-prefix=THUMB2_RO_PC  --check-prefix=THUMB2_RW_ABS
 ; RUN: llc -relocation-model=rwpi      -mtriple=thumbv7m--none-eabi < %s | FileCheck %s --check-prefix=CHECK --check-prefix=THUMB2_RO_ABS  --check-prefix=THUMB2_RW_SB
 ; RUN: llc -relocation-model=ropi-rwpi -mtriple=thumbv7m--none-eabi < %s | FileCheck %s --check-prefix=CHECK --check-prefix=THUMB2_RO_PC  --check-prefix=THUMB2_RW_SB
 
 ; RUN: llc -relocation-model=static    -mtriple=thumbv6m--none-eabi < %s | FileCheck %s --check-prefix=CHECK --check-prefix=THUMB1_RO_ABS --check-prefix=THUMB1_RW_ABS
 ; RUN: llc -relocation-model=ropi      -mtriple=thumbv6m--none-eabi < %s | FileCheck %s --check-prefix=CHECK --check-prefix=THUMB1_RO_PC  --check-prefix=THUMB1_RW_ABS
 ; RUN: llc -relocation-model=rwpi      -mtriple=thumbv6m--none-eabi < %s | FileCheck %s --check-prefix=CHECK --check-prefix=THUMB1_RO_ABS --check-prefix=THUMB1_RW_SB
 ; RUN: llc -relocation-model=ropi-rwpi -mtriple=thumbv6m--none-eabi < %s | FileCheck %s --check-prefix=CHECK --check-prefix=THUMB1_RO_PC  --check-prefix=THUMB1_RW_SB
 
+; RUN: llc -relocation-model=rwpi      -mtriple=armv7a--none-eabi   -mattr=no-movt < %s | FileCheck %s --check-prefix=CHECK --check-prefix=NO_MOVT_ARM_RO_ABS --check-prefix=NO_MOVT_ARM_RW_SB
+; RUN: llc -relocation-model=ropi-rwpi -mtriple=armv7a--none-eabi   -mattr=no-movt < %s | FileCheck %s --check-prefix=CHECK --check-prefix=NO_MOVT_ARM_RO_PC  --check-prefix=NO_MOVT_ARM_RW_SB
+
+; RUN: llc -relocation-model=rwpi      -mtriple=thumbv7m--none-eabi -mattr=no-movt < %s | FileCheck %s --check-prefix=CHECK --check-prefix=NO_MOVT_THUMB2_RO_ABS  --check-prefix=NO_MOVT_THUMB2_RW_SB
+; RUN: llc -relocation-model=ropi-rwpi -mtriple=thumbv7m--none-eabi -mattr=no-movt < %s | FileCheck %s --check-prefix=CHECK --check-prefix=NO_MOVT_THUMB2_RO_PC  --check-prefix=NO_MOVT_THUMB2_RW_SB
+
 target datalayout = "e-m:e-p:32:32-i64:64-v128:64:128-a:0:32-n32-S64"
 
 @a = external global i32, align 4
 @b = external constant i32, align 4
 
 define i32 @read() {
 entry:
   %0 = load i32, i32* @a, align 4
   ret i32 %0
 ; CHECK-LABEL: read:
 
 ; ARM_RW_ABS: movw    r[[REG:[0-9]]], :lower16:a
 ; ARM_RW_ABS: movt    r[[REG]], :upper16:a
 ; ARM_RW_ABS: ldr     r0, [r[[REG]]]
 
-; ARM_RW_SB: ldr     r[[REG:[0-9]]], [[LCPI:.LCPI[0-9]+_[0-9]+]]
+; ARM_RW_SB: movw    r[[REG:[0-9]]], :lower16:a(sbrel)
+; ARM_RW_SB: movt    r[[REG]], :upper16:a(sbrel)
 ; ARM_RW_SB: ldr     r0, [r9, r[[REG]]]
 
+; NO_MOVT_ARM_RW_SB: ldr     r[[REG:[0-9]]], [[LCPI:.LCPI[0-9]+_[0-9]+]]
+; NO_MOVT_ARM_RW_SB: ldr     r0, [r9, r[[REG]]]
+
 ; THUMB2_RW_ABS: movw    r[[REG:[0-9]]], :lower16:a
 ; THUMB2_RW_ABS: movt    r[[REG]], :upper16:a
 ; THUMB2_RW_ABS: ldr     r0, [r[[REG]]]
 
-; THUMB2_RW_SB: ldr     r[[REG:[0-9]]], [[LCPI:.LCPI[0-9]+_[0-9]+]]
+; THUMB2_RW_SB: movw    r[[REG:[0-9]]], :lower16:a(sbrel)
+; THUMB2_RW_SB: movt    r[[REG]], :upper16:a(sbrel)
 ; THUMB2_RW_SB: ldr.w   r0, [r9, r[[REG]]]
 
+; NO_MOVT_THUMB2_RW_SB: ldr     r[[REG:[0-9]]], [[LCPI:.LCPI[0-9]+_[0-9]+]]
+; NO_MOVT_THUMB2_RW_SB: ldr.w   r0, [r9, r[[REG]]]
+
 ; THUMB1_RW_ABS: ldr     r[[REG:[0-9]]], [[LCPI:.LCPI[0-9]+_[0-9]+]]
 ; THUMB1_RW_ABS: ldr     r0, [r[[REG]]]
 
 ; THUMB1_RW_SB: ldr     r[[REG:[0-9]]], [[LCPI:.LCPI[0-9]+_[0-9]+]]
 ; THUMB1_RW_SB: mov     r[[REG_SB:[0-9]+]], r9
 ; THUMB1_RW_SB: ldr     r0, [r[[REG_SB]], r[[REG]]]
 
 ; CHECK: {{(bx lr|pop)}}
 
-; ARM_RW_SB: [[LCPI]]
-; ARM_RW_SB: .long   a(sbrel)
+; NO_MOVT_ARM_RW_SB: [[LCPI]]
+; NO_MOVT_ARM_RW_SB: .long   a(sbrel)
 
-; THUMB2_RW_SB: [[LCPI]]
-; THUMB2_RW_SB: .long   a(sbrel)
+; NO_MOVT_THUMB2_RW_SB: [[LCPI]]
+; NO_MOVT_THUMB2_RW_SB: .long   a(sbrel)
 
 ; THUMB1_RW_ABS: [[LCPI]]
 ; THUMB1_RW_ABS-NEXT: .long a
 
 ; THUMB1_RW_SB: [[LCPI]]
 ; THUMB1_RW_SB: .long   a(sbrel)
 }
 
 define void @write(i32 %v)  {
 entry:
   store i32 %v, i32* @a, align 4
   ret void
 ; CHECK-LABEL: write:
 
 ; ARM_RW_ABS: movw    r[[REG:[0-9]]], :lower16:a
 ; ARM_RW_ABS: movt    r[[REG]], :upper16:a
 ; ARM_RW_ABS: str     r0, [r[[REG:[0-9]]]]
 
-; ARM_RW_SB: ldr     r[[REG:[0-9]]], [[LCPI:.LCPI[0-9]+_[0-9]+]]
-; ARM_RW_SB: str     r0, [r9, r[[REG]]]
+; ARM_RW_SB: movw    r[[REG:[0-9]]], :lower16:a
+; ARM_RW_SB: movt    r[[REG]], :upper16:a
+; ARM_RW_SB: str     r0, [r9, r[[REG:[0-9]]]]
+
+; NO_MOVT_ARM_RW_SB: ldr     r[[REG:[0-9]]], [[LCPI:.LCPI[0-9]+_[0-9]+]]
+; NO_MOVT_ARM_RW_SB: str     r0, [r9, r[[REG]]]
 
 ; THUMB2_RW_ABS: movw    r[[REG:[0-9]]], :lower16:a
 ; THUMB2_RW_ABS: movt    r[[REG]], :upper16:a
 ; THUMB2_RW_ABS: str     r0, [r[[REG]]]
 
-; THUMB2_RW_SB: ldr     r[[REG:[0-9]]], [[LCPI:.LCPI[0-9]+_[0-9]+]]
+; THUMB2_RW_SB: movw    r[[REG:[0-9]]], :lower16:a(sbrel)
+; THUMB2_RW_SB: movt    r[[REG]], :upper16:a(sbrel)
 ; THUMB2_RW_SB: str.w   r0, [r9, r[[REG]]]
 
+; NO_MOVT_THUMB2_RW_SB: ldr     r[[REG:[0-9]]], [[LCPI:.LCPI[0-9]+_[0-9]+]]
+; NO_MOVT_THUMB2_RW_SB: str.w   r0, [r9, r[[REG]]]
+
 ; THUMB1_RW_ABS: ldr     r[[REG:[0-9]]], [[LCPI:.LCPI[0-9]+_[0-9]+]]
 ; THUMB1_RW_ABS: str     r0, [r[[REG]]]
 
 ; THUMB1_RW_SB: ldr     r[[REG:[0-9]]], [[LCPI:.LCPI[0-9]+_[0-9]+]]
 ; THUMB1_RW_SB: mov     r[[REG_SB:[0-9]+]], r9
 ; THUMB1_RW_SB: str     r0, [r[[REG_SB]], r[[REG]]]
 
 ; CHECK: {{(bx lr|pop)}}
 
-; ARM_RW_SB: [[LCPI]]
-; ARM_RW_SB: .long   a(sbrel)
+; NO_MOVT_ARM_RW_SB: [[LCPI]]
+; NO_MOVT_ARM_RW_SB: .long   a(sbrel)
 
-; THUMB2_RW_SB: [[LCPI]]
-; THUMB2_RW_SB: .long   a(sbrel)
+; NO_MOVT_THUMB2_RW_SB: [[LCPI]]
+; NO_MOVT_THUMB2_RW_SB: .long   a(sbrel)
 
 ; THUMB1_RW_ABS: [[LCPI]]
 ; THUMB1_RW_ABS-NEXT: .long a
 
 ; THUMB1_RW_SB: [[LCPI]]
 ; THUMB1_RW_SB: .long   a(sbrel)
 }
 
 define i32 @read_const()  {
 entry:
   %0 = load i32, i32* @b, align 4
   ret i32 %0
 ; CHECK-LABEL: read_const:
 
 ; ARM_RO_ABS: movw    r[[reg:[0-9]]], :lower16:b
 ; ARM_RO_ABS: movt    r[[reg]], :upper16:b
 ; ARM_RO_ABS: ldr     r0, [r[[reg]]]
 
+; NO_MOVT_ARM_RO_ABS: ldr     r[[REG:[0-9]]], [[LCPI:.LCPI[0-9]+_[0-9]+]]
+; NO_MOVT_ARM_RO_ABS: ldr     r0, [r[[REG]]]
+
 ; ARM_RO_PC: movw    r[[REG:[0-9]]], :lower16:(b-([[LPC:.LPC[0-9]+_[0-9]+]]+8))
 ; ARM_RO_PC: movt    r[[REG]], :upper16:(b-([[LPC]]+8))
 ; ARM_RO_PC: [[LPC]]:
 ; ARM_RO_PC-NEXT: ldr     r0, [pc, r[[REG]]]
 
+; NO_MOVT_ARM_RO_PC: ldr     r[[REG:[0-9]]], [[LCPI:.LCPI[0-9]+_[0-9]+]]
+; NO_MOVT_ARM_RO_PC: [[LPC:.LPC[0-9]+_[0-9]+]]:
+; NO_MOVT_ARM_RO_PC: ldr     r0, [pc, r[[REG]]]
+
 ; THUMB2_RO_ABS: movw    r[[REG:[0-9]]], :lower16:b
 ; THUMB2_RO_ABS: movt    r[[REG]], :upper16:b
 ; THUMB2_RO_ABS: ldr     r0, [r[[REG]]]
 
+; NO_MOVT_THUMB2_RO_ABS: ldr     r[[REG:[0-9]]], [[LCPI:.LCPI[0-9]+_[0-9]+]]
+; NO_MOVT_THUMB2_RO_ABS: ldr     r0, [r[[REG]]]
+
 ; THUMB2_RO_PC: movw    r[[REG:[0-9]]], :lower16:(b-([[LPC:.LPC[0-9]+_[0-9]+]]+4))
 ; THUMB2_RO_PC: movt    r[[REG]], :upper16:(b-([[LPC]]+4))
 ; THUMB2_RO_PC: [[LPC]]:
 ; THUMB2_RO_PC-NEXT: add     r[[REG]], pc
 ; THUMB2_RO_PC: ldr     r0, [r[[REG]]]
 
+; NO_MOVT_THUMB2_RO_PC: ldr     r[[REG:[0-9]]], [[LCPI:.LCPI[0-9]+_[0-9]+]]
+; NO_MOVT_THUMB2_RO_PC: [[LPC:.LPC[0-9]+_[0-9]+]]:
+; NO_MOVT_THUMB2_RO_PC-NEXT: add     r[[REG]], pc
+; NO_MOVT_THUMB2_RO_PC: ldr     r0, [r[[REG]]]
+
+
 ; THUMB1_RO_ABS: ldr     r[[REG:[0-9]]], [[LCPI:.LCPI[0-9]+_[0-9]+]]
 ; THUMB1_RO_ABS: ldr     r0, [r[[REG]]]
 
 ; THUMB1_RO_PC: ldr     r[[REG:[0-9]]], [[LCPI:.LCPI[0-9]+_[0-9]+]]
 ; THUMB1_RO_PC: [[LPC:.LPC[0-9]+_[0-9]+]]:
 ; THUMB1_RO_PC-NEXT: add     r[[REG]], pc
 ; THUMB1_RO_PC: ldr     r0, [r[[REG]]]
 
 ; CHECK: {{(bx lr|pop)}}
 
+; NO_MOVT_ARM_RO_ABS: [[LCPI]]
+; NO_MOVT_ARM_RO_ABS-NEXT: .long b
+
+; NO_MOVT_THUMB2_RO_ABS: [[LCPI]]
+; NO_MOVT_THUMB2_RO_ABS-NEXT: .long b
+
 ; THUMB1_RO_ABS: [[LCPI]]
 ; THUMB1_RO_ABS-NEXT: .long b
 
+; NO_MOVT_ARM_RO_PC: [[LCPI]]
+; NO_MOVT_ARM_RO_PC-NEXT: .long b-([[LPC]]+8)
+
+; NO_MOVT_THUMB2_RO_PC: [[LCPI]]
+; NO_MOVT_THUMB2_RO_PC-NEXT: .long b-([[LPC]]+4)
+
 ; THUMB1_RO_PC: [[LCPI]]
 ; THUMB1_RO_PC-NEXT: .long b-([[LPC]]+4)
 }
 
 define i32* @take_addr()  {
 entry:
   ret i32* @a
 ; CHECK-LABEL: take_addr:
 
 ; ARM_RW_ABS: movw    r[[REG:[0-9]]], :lower16:a
 ; ARM_RW_ABS: movt    r[[REG]], :upper16:a
 
-; ARM_RW_SB: ldr     r[[REG:[0-9]]], [[LCPI:.LCPI[0-9]+_[0-9]+]]
+; ARM_RW_SB: movw    r[[REG:[0-9]]], :lower16:a(sbrel)
+; ARM_RW_SB: movt    r[[REG]], :upper16:a(sbrel)
 ; ARM_RW_SB: add     r0, r9, r[[REG]]
 
+; NO_MOVT_ARM_RW_SB: ldr     r[[REG:[0-9]]], [[LCPI:.LCPI[0-9]+_[0-9]+]]
+; NO_MOVT_ARM_RW_SB: add     r0, r9, r[[REG]]
+
 ; THUMB2_RW_ABS: movw    r[[REG:[0-9]]], :lower16:a
 ; THUMB2_RW_ABS: movt    r[[REG]], :upper16:a
 
-; THUMB2_RW_SB: ldr     r0, [[LCPI:.LCPI[0-9]+_[0-9]+]]
+; THUMB2_RW_SB: movw    r[[REG:[0-9]]], :lower16:a(sbrel)
+; THUMB2_RW_SB: movt    r[[REG]], :upper16:a(sbrel)
 ; THUMB2_RW_SB: add     r0, r9
 
+; NO_MOVT_THUMB2_RW_SB: ldr     r0, [[LCPI:.LCPI[0-9]+_[0-9]+]]
+; NO_MOVT_THUMB2_RW_SB: add     r0, r9
+
 ; THUMB1_RW_ABS: ldr     r0, [[LCPI:.LCPI[0-9]+_[0-9]+]]
 
 ; THUMB1_RW_SB: ldr     r[[REG:[0-9]]], [[LCPI:.LCPI[0-9]+_[0-9]+]]
 ; THUMB1_RW_SB: mov     r[[REG_SB:[0-9]+]], r9
 ; THUMB1_RW_SB: adds    r[[REG]], r[[REG_SB]], r[[REG]]
 
 ; CHECK: {{(bx lr|pop)}}
 
-; ARM_RW_SB: [[LCPI]]
-; ARM_RW_SB: .long   a(sbrel)
+; NO_MOVT_ARM_RW_SB: [[LCPI]]
+; NO_MOVT_ARM_RW_SB: .long   a(sbrel)
 
-; THUMB2_RW_SB: [[LCPI]]
-; THUMB2_RW_SB: .long   a(sbrel)
+; NO_MOVT_THUMB2_RW_SB: [[LCPI]]
+; NO_MOVT_THUMB2_RW_SB: .long   a(sbrel)
 
 ; THUMB1_RW_ABS: [[LCPI]]
 ; THUMB1_RW_ABS-NEXT: .long a
 
 ; THUMB1_RW_SB: [[LCPI]]
 ; THUMB1_RW_SB: .long   a(sbrel)
 }
 
 define i32* @take_addr_const()  {
 entry:
   ret i32* @b
 ; CHECK-LABEL: take_addr_const:
 
 ; ARM_RO_ABS: movw    r[[REG:[0-9]]], :lower16:b
 ; ARM_RO_ABS: movt    r[[REG]], :upper16:b
 
+; NO_MOVT_ARM_RO_ABS: ldr     r0, [[LCPI:.LCPI[0-9]+_[0-9]+]]
+
 ; ARM_RO_PC: movw    r[[REG:[0-9]]], :lower16:(b-([[LPC:.LPC[0-9]+_[0-9]+]]+8))
 ; ARM_RO_PC: movt    r[[REG]], :upper16:(b-([[LPC]]+8))
 ; ARM_RO_PC: [[LPC]]:
 ; ARM_RO_PC-NEXT: add     r0, pc, r[[REG:[0-9]]]
 
+; NO_MOVT_ARM_RO_PC: ldr     r[[REG:[0-9]]], [[LCPI:.LCPI[0-9]+_[0-9]+]]
+; NO_MOVT_ARM_RO_PC: [[LPC:.LPC[0-9]+_[0-9]+]]:
+; NO_MOVT_ARM_RO_PC-NEXT: add     r0, pc, r[[REG]]
+
 ; THUMB2_RO_ABS: movw    r[[REG:[0-9]]], :lower16:b
 ; THUMB2_RO_ABS: movt    r[[REG]], :upper16:b
 
+; NO_MOVT_THUMB2_RO_ABS: ldr     r0, [[LCPI:.LCPI[0-9]+_[0-9]+]]
+
 ; THUMB2_RO_PC: movw    r0, :lower16:(b-([[LPC:.LPC[0-9]+_[0-9]+]]+4))
 ; THUMB2_RO_PC: movt    r0, :upper16:(b-([[LPC]]+4))
 ; THUMB2_RO_PC: [[LPC]]:
 ; THUMB2_RO_PC-NEXT: add     r0, pc
 
+; NO_MOVT_THUMB2_RO_PC: ldr     r[[REG:[0-9]]], [[LCPI:.LCPI[0-9]+_[0-9]+]]
+; NO_MOVT_THUMB2_RO_PC: [[LPC:.LPC[0-9]+_[0-9]+]]:
+; NO_MOVT_THUMB2_RO_PC-NEXT: add     r[[REG]], pc
+
 ; THUMB1_RO_ABS: ldr     r0, [[LCPI:.LCPI[0-9]+_[0-9]+]]
 
 ; THUMB1_RO_PC: ldr     r[[REG:[0-9]]], [[LCPI:.LCPI[0-9]+_[0-9]+]]
 ; THUMB1_RO_PC: [[LPC:.LPC[0-9]+_[0-9]+]]:
 ; THUMB1_RO_PC-NEXT: add     r[[REG]], pc
 
 ; CHECK: {{(bx lr|pop)}}
 
+; NO_MOVT_ARM_RO_ABS: [[LCPI]]
+; NO_MOVT_ARM_RO_ABS-NEXT: .long b
+
+; NO_MOVT_THUMB2_RO_ABS: [[LCPI]]
+; NO_MOVT_THUMB2_RO_ABS-NEXT: .long b
+
 ; THUMB1_RO_ABS: [[LCPI]]
 ; THUMB1_RO_ABS-NEXT: .long b
 
+; NO_MOVT_ARM_RO_PC: [[LCPI]]
+; NO_MOVT_ARM_RO_PC-NEXT: .long b-([[LPC]]+8)
+
+; NO_MOVT_THUMB2_RO_PC: [[LCPI]]
+; NO_MOVT_THUMB2_RO_PC-NEXT: .long b-([[LPC]]+4)
+
 ; THUMB1_RO_PC: [[LCPI]]
 ; THUMB1_RO_PC-NEXT: .long b-([[LPC]]+4)
 }
 
 define i8* @take_addr_func()  {
 entry:
   ret i8* bitcast (i8* ()* @take_addr_func to i8*)
 ; CHECK-LABEL: take_addr_func:
 
 ; ARM_RO_ABS: movw    r[[REG:[0-9]]], :lower16:take_addr_func
 ; ARM_RO_ABS: movt    r[[REG]], :upper16:take_addr_func
 
+; NO_MOVT_ARM_RO_ABS: ldr     r0, [[LCPI:.LCPI[0-9]+_[0-9]+]]
+
 ; ARM_RO_PC: movw    r[[REG:[0-9]]], :lower16:(take_addr_func-([[LPC:.LPC[0-9]+_[0-9]+]]+8))
 ; ARM_RO_PC: movt    r[[REG]], :upper16:(take_addr_func-([[LPC]]+8))
 ; ARM_RO_PC: [[LPC]]:
 ; ARM_RO_PC-NEXT: add     r0, pc, r[[REG:[0-9]]]
 
+; NO_MOVT_ARM_RO_PC: ldr     r[[REG:[0-9]]], [[LCPI:.LCPI[0-9]+_[0-9]+]]
+; NO_MOVT_ARM_RO_PC: [[LPC:.LPC[0-9]+_[0-9]+]]:
+; NO_MOVT_ARM_RO_PC-NEXT: add     r0, pc, r[[REG]]
+
 ; THUMB2_RO_ABS: movw    r[[REG:[0-9]]], :lower16:take_addr_func
 ; THUMB2_RO_ABS: movt    r[[REG]], :upper16:take_addr_func
 
+; NO_MOVT_THUMB2_RO_ABS: ldr     r0, [[LCPI:.LCPI[0-9]+_[0-9]+]]
+
 ; THUMB2_RO_PC: movw    r0, :lower16:(take_addr_func-([[LPC:.LPC[0-9]+_[0-9]+]]+4))
 ; THUMB2_RO_PC: movt    r0, :upper16:(take_addr_func-([[LPC]]+4))
 ; THUMB2_RO_PC: [[LPC]]:
 ; THUMB2_RO_PC-NEXT: add     r0, pc
 
+; NO_MOVT_THUMB2_RO_PC: ldr     r[[REG:[0-9]]], [[LCPI:.LCPI[0-9]+_[0-9]+]]
+; NO_MOVT_THUMB2_RO_PC: [[LPC:.LPC[0-9]+_[0-9]+]]:
+; NO_MOVT_THUMB2_RO_PC-NEXT: add     r[[REG]], pc
+
 ; THUMB1_RO_ABS: ldr     r0, [[LCPI:.LCPI[0-9]+_[0-9]+]]
 
 ; THUMB1_RO_PC: ldr     r[[REG:[0-9]]], [[LCPI:.LCPI[0-9]+_[0-9]+]]
 ; THUMB1_RO_PC: [[LPC:.LPC[0-9]+_[0-9]+]]:
 ; THUMB1_RO_PC-NEXT: add     r[[REG]], pc
 
 ; CHECK: {{(bx lr|pop)}}
 
+; NO_MOVT_ARM_RO_ABS: [[LCPI]]
+; NO_MOVT_ARM_RO_ABS-NEXT: .long take_addr_func
+
+; NO_MOVT_THUMB2_RO_ABS: [[LCPI]]
+; NO_MOVT_THUMB2_RO_ABS-NEXT: .long take_addr_func
+
 ; THUMB1_RO_ABS: [[LCPI]]
 ; THUMB1_RO_ABS-NEXT: .long take_addr_func
 
+; NO_MOVT_ARM_RO_PC: [[LCPI]]
+; NO_MOVT_ARM_RO_PC-NEXT: .long take_addr_func-([[LPC]]+8)
+
+; NO_MOVT_THUMB2_RO_PC: [[LCPI]]
+; NO_MOVT_THUMB2_RO_PC-NEXT: .long take_addr_func-([[LPC]]+4)
+
 ; THUMB1_RO_PC: [[LCPI]]
 ; THUMB1_RO_PC-NEXT: .long take_addr_func-([[LPC]]+4)
 }
 
 define i8* @block_addr() {
 entry:
   br label %lab1