Introduce llvm.load.relative intrinsic.

This intrinsic takes two arguments, ``%ptr`` and ``%offset``. It loads
a 32-bit value from the address ``%ptr + %offset``, adds ``%ptr`` to that
value and returns it. The constant folder specifically recognizes the form of
this intrinsic and the constant initializers it may load from; if a loaded
constant initializer is known to have the form ``i32 trunc(x - %ptr)``,
the intrinsic call is folded to ``x``.

LLVM provides that the calculation of such a constant initializer will
not overflow at link time under the medium code model if ``x`` is an
``unnamed_addr`` function. However, it does not provide this guarantee for
a constant initializer folded into a function body. This intrinsic can be
used to avoid the possibility of overflows when loading from such a constant.

Differential Revision: http://reviews.llvm.org/D18367

llvm-svn: 267223

llvm/docs/LangRef.rst

@@ -12361,6 +12361,31 @@ if"); and this allows for "check widening" type optimizations.
 ``@llvm.experimental.guard`` cannot be invoked.
 
 
+'``llvm.load.relative``' Intrinsic
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+Syntax:
+"""""""
+
+::
+
+      declare i8* @llvm.load.relative.iN(i8* %ptr, iN %offset) argmemonly nounwind readonly
+
+Overview:
+"""""""""
+
+This intrinsic loads a 32-bit value from the address ``%ptr + %offset``,
+adds ``%ptr`` to that value and returns it. The constant folder specifically
+recognizes the form of this intrinsic and the constant initializers it may
+load from; if a loaded constant initializer is known to have the form
+``i32 trunc(x - %ptr)``, the intrinsic call is folded to ``x``.
+
+LLVM provides that the calculation of such a constant initializer will
+not overflow at link time under the medium code model if ``x`` is an
+``unnamed_addr`` function. However, it does not provide this guarantee for
+a constant initializer folded into a function body. This intrinsic can be
+used to avoid the possibility of overflows when loading from such a constant.
+
 Stack Map Intrinsics
 --------------------
 

llvm/include/llvm/CodeGen/Passes.h

@@ -680,6 +680,11 @@ namespace llvm {
   ///
   ModulePass *createLowerEmuTLSPass(const TargetMachine *TM);
 
+  /// This pass lowers the @llvm.load.relative intrinsic to instructions.
+  /// This is unsafe to do earlier because a pass may combine the constant
+  /// initializer into the load, which may result in an overflowing evaluation.
+  ModulePass *createPreISelIntrinsicLoweringPass();
+
   /// GlobalMerge - This pass merges internal (by default) globals into structs
   /// to enable reuse of a base pointer by indexed addressing modes.
   /// It can also be configured to focus on size optimizations only.

llvm/include/llvm/IR/Intrinsics.td

@@ -669,6 +669,9 @@ def int_masked_scatter: Intrinsic<[],
 def int_bitset_test : Intrinsic<[llvm_i1_ty], [llvm_ptr_ty, llvm_metadata_ty],
                                 [IntrNoMem]>;
 
+def int_load_relative: Intrinsic<[llvm_ptr_ty], [llvm_ptr_ty, llvm_anyint_ty],
+                                 [IntrReadMem, IntrArgMemOnly]>;
+
 //===----------------------------------------------------------------------===//
 // Target-specific intrinsics
 //===----------------------------------------------------------------------===//

llvm/include/llvm/InitializePasses.h

@@ -246,6 +246,7 @@ void initializePostOrderFunctionAttrsLegacyPassPass(PassRegistry&);
 void initializePostRAHazardRecognizerPass(PassRegistry&);
 void initializePostRASchedulerPass(PassRegistry&);
 void initializePostMachineSchedulerPass(PassRegistry&);
+void initializePreISelIntrinsicLoweringPass(PassRegistry&);
 void initializePrintFunctionPassWrapperPass(PassRegistry&);
 void initializePrintModulePassWrapperPass(PassRegistry&);
 void initializePrintBasicBlockPassPass(PassRegistry&);

llvm/lib/Analysis/InlineCost.cpp

@@ -900,6 +900,11 @@ bool CallAnalyzer::visitCallSite(CallSite CS) {
       default:
         return Base::visitCallSite(CS);
 
+      case Intrinsic::load_relative:
+        // This is normally lowered to 4 LLVM instructions.
+        Cost += 3 * InlineConstants::InstrCost;
+        return false;
+
       case Intrinsic::memset:
       case Intrinsic::memcpy:
       case Intrinsic::memmove:

llvm/lib/Analysis/InstructionSimplify.cpp

@@ -3825,6 +3825,62 @@ static bool IsIdempotent(Intrinsic::ID ID) {
   }
 }
 
+static Value *SimplifyRelativeLoad(Constant *Ptr, Constant *Offset,
+                                   const DataLayout &DL) {
+  GlobalValue *PtrSym;
+  APInt PtrOffset;
+  if (!IsConstantOffsetFromGlobal(Ptr, PtrSym, PtrOffset, DL))
+    return nullptr;
+
+  Type *Int8PtrTy = Type::getInt8PtrTy(Ptr->getContext());
+  Type *Int32Ty = Type::getInt32Ty(Ptr->getContext());
+  Type *Int32PtrTy = Int32Ty->getPointerTo();
+  Type *Int64Ty = Type::getInt64Ty(Ptr->getContext());
+
+  auto *OffsetConstInt = dyn_cast<ConstantInt>(Offset);
+  if (!OffsetConstInt || OffsetConstInt->getType()->getBitWidth() > 64)
+    return nullptr;
+
+  uint64_t OffsetInt = OffsetConstInt->getSExtValue();
+  if (OffsetInt % 4 != 0)
+    return nullptr;
+
+  Constant *C = ConstantExpr::getGetElementPtr(
+      Int32Ty, ConstantExpr::getBitCast(Ptr, Int32PtrTy),
+      ConstantInt::get(Int64Ty, OffsetInt / 4));
+  Constant *Loaded = ConstantFoldLoadFromConstPtr(C, Int32Ty, DL);
+  if (!Loaded)
+    return nullptr;
+
+  auto *LoadedCE = dyn_cast<ConstantExpr>(Loaded);
+  if (!LoadedCE)
+    return nullptr;
+
+  if (LoadedCE->getOpcode() == Instruction::Trunc) {
+    LoadedCE = dyn_cast<ConstantExpr>(LoadedCE->getOperand(0));
+    if (!LoadedCE)
+      return nullptr;
+  }
+
+  if (LoadedCE->getOpcode() != Instruction::Sub)
+    return nullptr;
+
+  auto *LoadedLHS = dyn_cast<ConstantExpr>(LoadedCE->getOperand(0));
+  if (!LoadedLHS || LoadedLHS->getOpcode() != Instruction::PtrToInt)
+    return nullptr;
+  auto *LoadedLHSPtr = LoadedLHS->getOperand(0);
+
+  Constant *LoadedRHS = LoadedCE->getOperand(1);
+  GlobalValue *LoadedRHSSym;
+  APInt LoadedRHSOffset;
+  if (!IsConstantOffsetFromGlobal(LoadedRHS, LoadedRHSSym, LoadedRHSOffset,
+                                  DL) ||
+      PtrSym != LoadedRHSSym || PtrOffset != LoadedRHSOffset)
+    return nullptr;
+
+  return ConstantExpr::getBitCast(LoadedLHSPtr, Int8PtrTy);
+}
+
 template <typename IterTy>
 static Value *SimplifyIntrinsic(Function *F, IterTy ArgBegin, IterTy ArgEnd,
                                 const Query &Q, unsigned MaxRecurse) {
@@ -3865,6 +3921,11 @@ static Value *SimplifyIntrinsic(Function *F, IterTy ArgBegin, IterTy ArgEnd,
       if (match(RHS, m_Undef()))
         return Constant::getNullValue(ReturnType);
     }
+
+    if (IID == Intrinsic::load_relative && isa<Constant>(LHS) &&
+        isa<Constant>(RHS))
+      return SimplifyRelativeLoad(cast<Constant>(LHS), cast<Constant>(RHS),
+                                  Q.DL);
   }
 
   // Perform idempotent optimizations

llvm/lib/CodeGen/CMakeLists.txt

@@ -87,6 +87,7 @@ add_llvm_library(LLVMCodeGen
   PHIEliminationUtils.cpp
   PostRAHazardRecognizer.cpp
   PostRASchedulerList.cpp
+  PreISelIntrinsicLowering.cpp
   ProcessImplicitDefs.cpp
   PrologEpilogInserter.cpp
   PseudoSourceValue.cpp

llvm/lib/CodeGen/CodeGen.cpp

@@ -63,6 +63,7 @@ void llvm::initializeCodeGen(PassRegistry &Registry) {
   initializePostMachineSchedulerPass(Registry);
   initializePostRAHazardRecognizerPass(Registry);
   initializePostRASchedulerPass(Registry);
+  initializePreISelIntrinsicLoweringPass(Registry);
   initializeProcessImplicitDefsPass(Registry);
   initializeRegisterCoalescerPass(Registry);
   initializeShrinkWrapPass(Registry);

llvm/lib/CodeGen/LLVMTargetMachine.cpp

@@ -102,6 +102,8 @@ addPassesToGenerateCode(LLVMTargetMachine *TM, PassManagerBase &PM,
   if (TM->Options.EmulatedTLS)
     PM.add(createLowerEmuTLSPass(TM));
 
+  PM.add(createPreISelIntrinsicLoweringPass());
+
   // Add internal analysis passes from the target machine.
   PM.add(createTargetTransformInfoWrapperPass(TM->getTargetIRAnalysis()));
 

llvm/lib/CodeGen/PreISelIntrinsicLowering.cpp

@@ -0,0 +1,85 @@
+//===-- PreISelIntrinsicLowering.cpp - Pre-ISel intrinsic lowering pass ---===//
+//
+//                     The LLVM Compiler Infrastructure
+//
+// This file is distributed under the University of Illinois Open Source
+// License. See LICENSE.TXT for details.
+//
+//===----------------------------------------------------------------------===//
+//
+// This pass implements IR lowering for the llvm.load.relative intrinsic.
+//
+//===----------------------------------------------------------------------===//
+
+#include "llvm/CodeGen/Passes.h"
+#include "llvm/IR/Function.h"
+#include "llvm/IR/IRBuilder.h"
+#include "llvm/IR/Instructions.h"
+#include "llvm/IR/Intrinsics.h"
+#include "llvm/IR/Module.h"
+#include "llvm/Pass.h"
+
+using namespace llvm;
+
+namespace {
+
+bool lowerLoadRelative(Function &F) {
+  if (F.use_empty())
+    return false;
+
+  bool Changed = false;
+  Type *Int32Ty = Type::getInt32Ty(F.getContext());
+  Type *Int32PtrTy = Int32Ty->getPointerTo();
+  Type *Int8Ty = Type::getInt8Ty(F.getContext());
+
+  for (auto I = F.use_begin(), E = F.use_end(); I != E;) {
+    auto CI = dyn_cast<CallInst>(I->getUser());
+    ++I;
+    if (!CI || CI->getCalledValue() != &F)
+      continue;
+
+    IRBuilder<> B(CI);
+    Value *OffsetPtr =
+        B.CreateGEP(Int8Ty, CI->getArgOperand(0), CI->getArgOperand(1));
+    Value *OffsetPtrI32 = B.CreateBitCast(OffsetPtr, Int32PtrTy);
+    Value *OffsetI32 = B.CreateAlignedLoad(OffsetPtrI32, 4);
+
+    Value *ResultPtr = B.CreateGEP(Int8Ty, CI->getArgOperand(0), OffsetI32);
+
+    CI->replaceAllUsesWith(ResultPtr);
+    CI->eraseFromParent();
+    Changed = true;
+  }
+
+  return Changed;
+}
+
+bool lowerIntrinsics(Module &M) {
+  bool Changed = false;
+  for (Function &F : M) {
+    if (F.getName().startswith("llvm.load.relative."))
+      Changed |= lowerLoadRelative(F);
+  }
+  return Changed;
+}
+
+class PreISelIntrinsicLowering : public ModulePass {
+public:
+  static char ID;
+  PreISelIntrinsicLowering() : ModulePass(ID) {}
+
+  bool runOnModule(Module &M) {
+    return lowerIntrinsics(M);
+  }
+};
+
+char PreISelIntrinsicLowering::ID;
+
+}
+
+INITIALIZE_PASS(PreISelIntrinsicLowering, "pre-isel-intrinsic-lowering",
+                "Pre-ISel Intrinsic Lowering", false, false)
+
+ModulePass *llvm::createPreISelIntrinsicLoweringPass() {
+  return new PreISelIntrinsicLowering;
+}

llvm/test/CodeGen/Generic/stop-after.ll

@@ -6,6 +6,6 @@
 ; STOP-NEXT: Machine Function Analysis
 ; STOP-NEXT: MIR Printing Pass
 
-; START: -machine-branch-prob -gc-lowering
+; START: -machine-branch-prob -pre-isel-intrinsic-lowering
 ; START: FunctionPass Manager
 ; START-NEXT: Lower Garbage Collection Instructions

llvm/test/Transforms/InstSimplify/load-relative-32.ll

@@ -0,0 +1,19 @@
+; RUN: opt < %s -instsimplify -S | FileCheck %s
+
+target datalayout = "e-p:32:32:32-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:32:64-f32:32:32-f64:32:64-v64:64:64-v128:128:128-a0:0:64-f80:32:32-n8:16:32"
+target triple = "i386-unknown-linux-gnu"
+
+@a = external global i8
+
+@c1 = constant [3 x i32] [i32 0, i32 0,
+i32 sub (i32 ptrtoint (i8* @a to i32), i32 ptrtoint (i32* getelementptr ([3 x i32], [3 x i32]* @c1, i32 0, i32 2) to i32))
+]
+
+; CHECK: @f1
+define i8* @f1() {
+  ; CHECK: ret i8* @a
+  %l = call i8* @llvm.load.relative.i32(i8* bitcast (i32* getelementptr ([3 x i32], [3 x i32]* @c1, i32 0, i32 2) to i8*), i32 0)
+  ret i8* %l
+}
+
+declare i8* @llvm.load.relative.i32(i8*, i32)

llvm/test/Transforms/InstSimplify/load-relative.ll

@@ -0,0 +1,75 @@
+; RUN: opt < %s -instsimplify -S | FileCheck %s
+
+target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
+target triple = "x86_64-unknown-linux-gnu"
+
+@a = external global i8
+@b = external global i8
+
+@c1 = constant i32 trunc (i64 sub (i64 ptrtoint (i8* @a to i64), i64 ptrtoint (i32* @c1 to i64)) to i32)
+@c2 = constant [7 x i32] [i32 0, i32 0,
+i32 trunc (i64 sub (i64 ptrtoint (i8* @a to i64), i64 ptrtoint (i32* getelementptr ([7 x i32], [7 x i32]* @c2, i32 0, i32 2) to i64)) to i32),
+i32 trunc (i64 sub (i64 ptrtoint (i8* @b to i64), i64 ptrtoint (i32* getelementptr ([7 x i32], [7 x i32]* @c2, i32 0, i32 2) to i64)) to i32),
+i32 trunc (i64 add (i64 ptrtoint (i8* @b to i64), i64 ptrtoint (i32* getelementptr ([7 x i32], [7 x i32]* @c2, i32 0, i32 2) to i64)) to i32),
+i32 trunc (i64 sub (i64 ptrtoint (i8* @b to i64), i64 1) to i32),
+i32 trunc (i64 sub (i64 0, i64 ptrtoint (i32* getelementptr ([7 x i32], [7 x i32]* @c2, i32 0, i32 2) to i64)) to i32)
+]
+
+; CHECK: @f1
+define i8* @f1() {
+  ; CHECK: ret i8* @a
+  %l = call i8* @llvm.load.relative.i32(i8* bitcast (i32* @c1 to i8*), i32 0)
+  ret i8* %l
+}
+
+; CHECK: @f2
+define i8* @f2() {
+  ; CHECK: ret i8* @a
+  %l = call i8* @llvm.load.relative.i32(i8* bitcast (i32* getelementptr ([7 x i32], [7 x i32]* @c2, i64 0, i64 2) to i8*), i32 0)
+  ret i8* %l
+}
+
+; CHECK: @f3
+define i8* @f3() {
+  ; CHECK: ret i8* @b
+  %l = call i8* @llvm.load.relative.i64(i8* bitcast (i32* getelementptr ([7 x i32], [7 x i32]* @c2, i64 0, i64 2) to i8*), i64 4)
+  ret i8* %l
+}
+
+; CHECK: @f4
+define i8* @f4() {
+  ; CHECK: ret i8* %
+  %l = call i8* @llvm.load.relative.i32(i8* bitcast (i32* getelementptr ([7 x i32], [7 x i32]* @c2, i64 0, i64 2) to i8*), i32 1)
+  ret i8* %l
+}
+
+; CHECK: @f5
+define i8* @f5() {
+  ; CHECK: ret i8* %
+  %l = call i8* @llvm.load.relative.i32(i8* zeroinitializer, i32 0)
+  ret i8* %l
+}
+
+; CHECK: @f6
+define i8* @f6() {
+  ; CHECK: ret i8* %
+  %l = call i8* @llvm.load.relative.i32(i8* bitcast (i32* getelementptr ([7 x i32], [7 x i32]* @c2, i64 0, i64 2) to i8*), i32 8)
+  ret i8* %l
+}
+
+; CHECK: @f7
+define i8* @f7() {
+  ; CHECK: ret i8* %
+  %l = call i8* @llvm.load.relative.i32(i8* bitcast (i32* getelementptr ([7 x i32], [7 x i32]* @c2, i64 0, i64 2) to i8*), i32 12)
+  ret i8* %l
+}
+
+; CHECK: @f8
+define i8* @f8() {
+  ; CHECK: ret i8* %
+  %l = call i8* @llvm.load.relative.i32(i8* bitcast (i32* getelementptr ([7 x i32], [7 x i32]* @c2, i64 0, i64 2) to i8*), i32 16)
+  ret i8* %l
+}
+
+declare i8* @llvm.load.relative.i32(i8*, i32)
+declare i8* @llvm.load.relative.i64(i8*, i64)

llvm/test/Transforms/PreISelIntrinsicLowering/load-relative.ll

@@ -0,0 +1,26 @@
+; RUN: opt -pre-isel-intrinsic-lowering -S -o - %s | FileCheck %s
+
+; CHECK: define i8* @foo32(i8* [[P:%.*]], i32 [[O:%.*]])
+define i8* @foo32(i8* %p, i32 %o) {
+  ; CHECK: [[OP:%.*]] = getelementptr i8, i8* [[P]], i32 [[O]]
+  ; CHECK: [[OPI32:%.*]] = bitcast i8* [[OP]] to i32*
+  ; CHECK: [[OI32:%.*]] = load i32, i32* [[OPI32]], align 4
+  ; CHECK: [[R:%.*]] = getelementptr i8, i8* [[P]], i32 [[OI32]]
+  ; CHECK: ret i8* [[R]]
+  %l = call i8* @llvm.load.relative.i32(i8* %p, i32 %o)
+  ret i8* %l
+}
+
+; CHECK: define i8* @foo64(i8* [[P:%.*]], i64 [[O:%.*]])
+define i8* @foo64(i8* %p, i64 %o) {
+  ; CHECK: [[OP:%.*]] = getelementptr i8, i8* [[P]], i64 [[O]]
+  ; CHECK: [[OPI32:%.*]] = bitcast i8* [[OP]] to i32*
+  ; CHECK: [[OI32:%.*]] = load i32, i32* [[OPI32]], align 4
+  ; CHECK: [[R:%.*]] = getelementptr i8, i8* [[P]], i32 [[OI32]]
+  ; CHECK: ret i8* [[R]]
+  %l = call i8* @llvm.load.relative.i64(i8* %p, i64 %o)
+  ret i8* %l
+}
+
+declare i8* @llvm.load.relative.i32(i8*, i32)
+declare i8* @llvm.load.relative.i64(i8*, i64)

llvm/tools/opt/opt.cpp

@@ -353,6 +353,7 @@ int main(int argc, char **argv) {
   initializeDwarfEHPreparePass(Registry);
   initializeSafeStackPass(Registry);
   initializeSjLjEHPreparePass(Registry);
+  initializePreISelIntrinsicLoweringPass(Registry);
 
 #ifdef LINK_POLLY_INTO_TOOLS
   polly::initializePollyPasses(Registry);