Introducing llvm.invariant.group.barrier intrinsic

For more info for what reason it was invented, goto: http://lists.llvm.org/pipermail/cfe-dev/2015-July/044227.html invariant.group.barrier: http://reviews.llvm.org/D12310 docs: http://reviews.llvm.org/D11399 CodeGenPrepare: http://reviews.llvm.org/D12875 llvm-svn: 247711
llvm · Sep 15, 2015 · 6c15ec4 · 6c15ec4
1 parent dc29c97
commit 6c15ec4
Show file tree

Hide file tree

Showing 6 changed files with 230 additions and 5 deletions.
diff --git a/llvm/docs/LangRef.rst b/llvm/docs/LangRef.rst
@@ -4421,6 +4421,50 @@ the loop identifier metadata node directly:
 The ``llvm.bitsets`` global metadata is used to implement
 :doc:`bitsets <BitSets>`.
 
+'``invariant.group``' Metadata
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+The ``invariant.group`` metadata may be attached to ``load``/``store`` instructions.
+The existence of the ``invariant.group`` metadata on the instruction tells 
+the optimizer that every ``load`` and ``store`` to the same pointer operand 
+within the same invariant group can be assumed to load or store the same  
+value (but see the ``llvm.invariant.group.barrier`` intrinsic which affects 
+when two pointers are considered the same).
+
+Examples:
+
+.. code-block:: llvm
+
+   @unknownPtr = external global i8
+   ...
+   %ptr = alloca i8
+   store i8 42, i8* %ptr, !invariant.group !0
+   call void @foo(i8* %ptr)
+   
+   %a = load i8, i8* %ptr, !invariant.group !0 ; Can assume that value under %ptr didn't change
+   call void @foo(i8* %ptr)
+   %b = load i8, i8* %ptr, !invariant.group !1 ; Can't assume anything, because group changed
+  
+   %newPtr = call i8* @getPointer(i8* %ptr) 
+   %c = load i8, i8* %newPtr, !invariant.group !0 ; Can't assume anything, because we only have information about %ptr
+   
+   %unknownValue = load i8, i8* @unknownPtr
+   store i8 %unknownValue, i8* %ptr, !invariant.group !0 ; Can assume that %unknownValue == 42
+   
+   call void @foo(i8* %ptr)
+   %newPtr2 = call i8* @llvm.invariant.group.barrier(i8* %ptr)
+   %d = load i8, i8* %newPtr2, !invariant.group !0  ; Can't step through invariant.group.barrier to get value of %ptr
+   
+   ...
+   declare void @foo(i8*)
+   declare i8* @getPointer(i8*)
+   declare i8* @llvm.invariant.group.barrier(i8*)
+   
+   !0 = !{!"magic ptr"}
+   !1 = !{!"other ptr"}
+
+
+
 Module Flags Metadata
 =====================
 
@@ -6768,8 +6812,8 @@ Syntax:
 
 ::
 
-      <result> = load [volatile] <ty>, <ty>* <pointer>[, align <alignment>][, !nontemporal !<index>][, !invariant.load !<index>][, !nonnull !<index>][, !dereferenceable !<index>][, !dereferenceable_or_null !<index>]
-      <result> = load atomic [volatile] <ty>* <pointer> [singlethread] <ordering>, align <alignment>
+      <result> = load [volatile] <ty>, <ty>* <pointer>[, align <alignment>][, !nontemporal !<index>][, !invariant.load !<index>][, !invariant.group !<index>][, !nonnull !<index>][, !dereferenceable !<index>][, !dereferenceable_or_null !<index>]
+      <result> = load atomic [volatile] <ty>* <pointer> [singlethread] <ordering>, align <alignment> [, !invariant.group !<index>]
       !<index> = !{ i32 1 }
 
 Overview:
@@ -6825,6 +6869,9 @@ Being invariant does not imply that a location is dereferenceable,
 but it does imply that once the location is known dereferenceable
 its value is henceforth unchanging.
 
+The optional ``!invariant.group`` metadata must reference a single metadata name
+ ``<index>`` corresponding to a metadata node. See ``invariant.group`` metadata.
+
 The optional ``!nonnull`` metadata must reference a single
 metadata name ``<index>`` corresponding to a metadata node with no
 entries. The existence of the ``!nonnull`` metadata on the
@@ -6882,8 +6929,8 @@ Syntax:
 
 ::
 
-      store [volatile] <ty> <value>, <ty>* <pointer>[, align <alignment>][, !nontemporal !<index>]        ; yields void
-      store atomic [volatile] <ty> <value>, <ty>* <pointer> [singlethread] <ordering>, align <alignment>  ; yields void
+      store [volatile] <ty> <value>, <ty>* <pointer>[, align <alignment>][, !nontemporal !<index>][, !invariant.group !<index>]        ; yields void
+      store atomic [volatile] <ty> <value>, <ty>* <pointer> [singlethread] <ordering>, align <alignment> [, !invariant.group !<index>] ; yields void
 
 Overview:
 """""""""
@@ -6930,6 +6977,9 @@ be reused in the cache. The code generator may select special
 instructions to save cache bandwidth, such as the MOVNT instruction on
 x86.
 
+The optional ``!invariant.group`` metadata must reference a 
+single metadata name ``<index>``. See ``invariant.group`` metadata.
+
 Semantics:
 """"""""""
 
@@ -11465,6 +11515,36 @@ Semantics:
 
 This intrinsic indicates that the memory is mutable again.
 
+'``llvm.invariant.group.barrier``' Intrinsic
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+Syntax:
+"""""""
+
+::
+
+      declare i8* @llvm.invariant.group.barrier(i8* <ptr>)
+
+Overview:
+"""""""""
+
+The '``llvm.invariant.group.barrier``' intrinsic can be used when an invariant 
+established by invariant.group metadata no longer holds, to obtain a new pointer
+value that does not carry the invariant information.
+
+
+Arguments:
+""""""""""
+
+The ``llvm.invariant.group.barrier`` takes only one argument, which is
+the pointer to the memory for which the ``invariant.group`` no longer holds.
+
+Semantics:
+""""""""""
+
+Returns another pointer that aliases its argument but which is considered different 
+for the purposes of ``load``/``store`` ``invariant.group`` metadata.
+
 General Intrinsics
 ------------------
 

diff --git a/llvm/include/llvm/IR/IRBuilder.h b/llvm/include/llvm/IR/IRBuilder.h
@@ -24,6 +24,7 @@
 #include "llvm/IR/Function.h"
 #include "llvm/IR/GlobalVariable.h"
 #include "llvm/IR/Instructions.h"
+#include "llvm/IR/Intrinsics.h"
 #include "llvm/IR/LLVMContext.h"
 #include "llvm/IR/Operator.h"
 #include "llvm/IR/ValueHandle.h"
@@ -1634,6 +1635,32 @@ class IRBuilder : public IRBuilderBase, public Inserter {
                            Name);
   }
 
+  /// \brief Create an invariant.group.barrier intrinsic call, that stops
+  /// optimizer to propagate equality using invariant.group metadata.
+  /// If Ptr type is different from i8*, it's casted to i8* before call
+  /// and casted back to Ptr type after call.
+  Value *CreateInvariantGroupBarrier(Value *Ptr) {
+    Module *M = BB->getParent()->getParent();
+    Function *FnInvariantGroupBarrier = Intrinsic::getDeclaration(M,
+            Intrinsic::invariant_group_barrier);
+
+    Type *ArgumentAndReturnType = FnInvariantGroupBarrier->getReturnType();
+    assert(ArgumentAndReturnType ==
+        FnInvariantGroupBarrier->getFunctionType()->getParamType(0) &&
+        "InvariantGroupBarrier should take and return the same type");
+    Type *PtrType = Ptr->getType();
+
+    bool PtrTypeConversionNeeded = PtrType != ArgumentAndReturnType;
+    if (PtrTypeConversionNeeded)
+      Ptr = CreateBitCast(Ptr, ArgumentAndReturnType);
+
+    CallInst *Fn = CreateCall(FnInvariantGroupBarrier, {Ptr});
+
+    if (PtrTypeConversionNeeded)
+      return CreateBitCast(Fn, PtrType);
+    return Fn;
+  }
+
   /// \brief Return a vector value that contains \arg V broadcasted to \p
   /// NumElts elements.
   Value *CreateVectorSplat(unsigned NumElts, Value *V, const Twine &Name = "") {

diff --git a/llvm/include/llvm/IR/Intrinsics.td b/llvm/include/llvm/IR/Intrinsics.td
@@ -319,7 +319,7 @@ def int_instrprof_increment : Intrinsic<[],
                                         [llvm_ptr_ty, llvm_i64_ty,
                                          llvm_i32_ty, llvm_i32_ty],
                                         []>;
-
+                                        
 //===------------------- Standard C Library Intrinsics --------------------===//
 //
 
@@ -530,6 +530,10 @@ def int_invariant_end   : Intrinsic<[],
                                      llvm_ptr_ty],
                                     [IntrReadWriteArgMem, NoCapture<2>]>;
 
+def int_invariant_group_barrier : Intrinsic<[llvm_ptr_ty], 
+                                            [llvm_ptr_ty], 
+                                            [IntrNoMem]>;
+
 //===------------------------ Stackmap Intrinsics -------------------------===//
 //
 def int_experimental_stackmap : Intrinsic<[],

diff --git a/llvm/lib/CodeGen/CodeGenPrepare.cpp b/llvm/lib/CodeGen/CodeGenPrepare.cpp
@@ -187,6 +187,7 @@ class TypePromotionTransaction;
                         unsigned CreatedInstCost);
     bool splitBranchCondition(Function &F);
     bool simplifyOffsetableRelocate(Instruction &I);
+    void stripInvariantGroupMetadata(Instruction &I);
   };
 }
 
@@ -1411,6 +1412,10 @@ bool CodeGenPrepare::OptimizeCallInst(CallInst *CI, bool& ModifiedDT) {
       InsertedInsts.insert(ExtVal);
       return true;
     }
+    case Intrinsic::invariant_group_barrier:
+      II->replaceAllUsesWith(II->getArgOperand(0));
+      II->eraseFromParent();
+      return true;
     }
 
     if (TLI) {
@@ -4421,6 +4426,7 @@ bool CodeGenPrepare::OptimizeInst(Instruction *I, bool& ModifiedDT) {
       return OptimizeCmpExpression(CI);
 
   if (LoadInst *LI = dyn_cast<LoadInst>(I)) {
+    stripInvariantGroupMetadata(*LI);
     if (TLI) {
       unsigned AS = LI->getPointerAddressSpace();
       return OptimizeMemoryInst(I, I->getOperand(0), LI->getType(), AS);
@@ -4429,6 +4435,7 @@ bool CodeGenPrepare::OptimizeInst(Instruction *I, bool& ModifiedDT) {
   }
 
   if (StoreInst *SI = dyn_cast<StoreInst>(I)) {
+    stripInvariantGroupMetadata(*SI);
     if (TLI) {
       unsigned AS = SI->getPointerAddressSpace();
       return OptimizeMemoryInst(I, SI->getOperand(1),
@@ -4827,3 +4834,8 @@ bool CodeGenPrepare::splitBranchCondition(Function &F) {
   }
   return MadeChange;
 }
+
+void CodeGenPrepare::stripInvariantGroupMetadata(Instruction &I) {
+  if (auto *InvariantMD = I.getMetadata("invariant.group"))
+    I.dropUnknownNonDebugMetadata(InvariantMD->getMetadataID());
+}
diff --git a/llvm/test/Transforms/CodeGenPrepare/invariant.group.ll b/llvm/test/Transforms/CodeGenPrepare/invariant.group.ll
@@ -0,0 +1,23 @@
+; RUN: opt -codegenprepare -S < %s | FileCheck %s
+
+@tmp = global i8 0
+
+; CHECK-LABEL: define void @foo() {
+define void @foo() {
+enter:
+  ; CHECK-NOT: !invariant.group
+  ; CHECK-NOT: @llvm.invariant.group.barrier(
+  ; CHECK: %val = load i8, i8* @tmp
+  %val = load i8, i8* @tmp, !invariant.group !0
+  %ptr = call i8* @llvm.invariant.group.barrier(i8* @tmp)
+
+  ; CHECK: store i8 42, i8* @tmp
+  store i8 42, i8* %ptr, !invariant.group !0
+
+  ret void
+}
+; CHECK-LABEL: }
+
+declare i8* @llvm.invariant.group.barrier(i8*)
+
+!0 = !{!"something"}
diff --git a/llvm/test/Transforms/GlobalOpt/invariant.group.barrier.ll b/llvm/test/Transforms/GlobalOpt/invariant.group.barrier.ll
@@ -0,0 +1,79 @@
+; RUN: opt -S -globalopt < %s | FileCheck %s
+
+; This test is hint, what could globalOpt optimize and what it can't
+; FIXME: @tmp and @tmp2 can be safely set to 42
+; CHECK: @tmp = global i32 0
+; CHECK: @tmp2 = global i32 0
+; CHECK: @tmp3 = global i32 0
+
+@tmp = global i32 0
+@tmp2 = global i32 0
+@tmp3 = global i32 0
+@ptrToTmp3 = global i32* null
+
+@llvm.global_ctors = appending global [1 x { i32, void ()* }] [{ i32, void ()* } { i32 65535, void ()* @_GLOBAL__I_a }]
+
+define i32 @TheAnswerToLifeTheUniverseAndEverything() {
+  ret i32 42
+}
+
+define void @_GLOBAL__I_a() {
+enter:
+  call void @_optimizable()
+  call void @_not_optimizable()
+  ret void
+}
+
+define void @_optimizable() {
+enter:
+  %valptr = alloca i32
+
+  %val = call i32 @TheAnswerToLifeTheUniverseAndEverything()
+  store i32 %val, i32* @tmp
+  store i32 %val, i32* %valptr
+
+  %0 = bitcast i32* %valptr to i8*
+  %barr = call i8* @llvm.invariant.group.barrier(i8* %0)
+  %1 = bitcast i8* %barr to i32*
+
+  %val2 = load i32, i32* %1
+  store i32 %val2, i32* @tmp2
+  ret void
+}
+
+; We can't step through invariant.group.barrier here, because that would change
+; this load in @usage_of_globals()
+; val = load i32, i32* %ptrVal, !invariant.group !0 
+; into 
+; %val = load i32, i32* @tmp3, !invariant.group !0
+; and then we could assume that %val and %val2 to be the same, which coud be 
+; false, because @changeTmp3ValAndCallBarrierInside() may change the value
+; of @tmp3.
+define void @_not_optimizable() {
+enter:
+  store i32 13, i32* @tmp3, !invariant.group !0
+
+  %0 = bitcast i32* @tmp3 to i8*
+  %barr = call i8* @llvm.invariant.group.barrier(i8* %0)
+  %1 = bitcast i8* %barr to i32*
+
+  store i32* %1, i32** @ptrToTmp3
+  store i32 42, i32* %1, !invariant.group !0
+
+  ret void
+}
+define void @usage_of_globals() {
+entry:
+  %ptrVal = load i32*, i32** @ptrToTmp3
+  %val = load i32, i32* %ptrVal, !invariant.group !0
+
+  call void @changeTmp3ValAndCallBarrierInside()
+  %val2 = load i32, i32* @tmp3, !invariant.group !0
+  ret void;
+}
+
+declare void @changeTmp3ValAndCallBarrierInside()
+
+declare i8* @llvm.invariant.group.barrier(i8*)
+
+!0 = !{!"something"}