Add an @llvm.sideeffect intrinsic

This patch implements Chandler's idea [0] for supporting languages that
require support for infinite loops with side effects, such as Rust, providing
part of a solution to bug 965 [1].

Specifically, it adds an `llvm.sideeffect()` intrinsic, which has no actual
effect, but which appears to optimization passes to have obscure side effects,
such that they don't optimize away loops containing it. It also teaches
several optimization passes to ignore this intrinsic, so that it doesn't
significantly impact optimization in most cases.

As discussed on llvm-dev [2], this patch is the first of two major parts.
The second part, to change LLVM's semantics to have defined behavior
on infinite loops by default, with a function attribute for opting into
potential-undefined-behavior, will be implemented and posted for review in
a separate patch.

[0] http://lists.llvm.org/pipermail/llvm-dev/2015-July/088103.html
[1] https://bugs.llvm.org/show_bug.cgi?id=965
[2] http://lists.llvm.org/pipermail/llvm-dev/2017-October/118632.html

Differential Revision: https://reviews.llvm.org/D38336

llvm-svn: 317729

6 files changed, 21 insertions, 3 deletions

diff --git a/llvm/lib/Transforms/Scalar/EarlyCSE.cpp b/llvm/lib/Transforms/Scalar/EarlyCSE.cpp
index 6d1362a6a28..1066dc33007 100644
--- a/llvm/lib/Transforms/Scalar/EarlyCSE.cpp
+++ b/llvm/lib/Transforms/Scalar/EarlyCSE.cpp
@@ -709,6 +709,12 @@ bool EarlyCSE::processNode(DomTreeNode *Node) {
       continue;
     }
 
+    // Skip sideeffect intrinsics, for the same reason as assume intrinsics.
+    if (match(Inst, m_Intrinsic<Intrinsic::sideeffect>())) {
+      DEBUG(dbgs() << "EarlyCSE skipping sideeffect: " << *Inst << '\n');
+      continue;
+    }
+
     // Skip invariant.start intrinsics since they only read memory, and we can
     // forward values across it. Also, we dont need to consume the last store
     // since the semantics of invariant.start allow us to perform DSE of the
diff --git a/llvm/lib/Transforms/Scalar/GVNHoist.cpp b/llvm/lib/Transforms/Scalar/GVNHoist.cpp
index d77ebdcd975..e90c89c2e3a 100644
--- a/llvm/lib/Transforms/Scalar/GVNHoist.cpp
+++ b/llvm/lib/Transforms/Scalar/GVNHoist.cpp
@@ -1110,7 +1110,8 @@ private:
         else if (auto *Call = dyn_cast<CallInst>(&I1)) {
           if (auto *Intr = dyn_cast<IntrinsicInst>(Call)) {
             if (isa<DbgInfoIntrinsic>(Intr) ||
-                Intr->getIntrinsicID() == Intrinsic::assume)
+                Intr->getIntrinsicID() == Intrinsic::assume ||
+                Intr->getIntrinsicID() == Intrinsic::sideeffect)
               continue;
           }
           if (Call->mayHaveSideEffects())
diff --git a/llvm/lib/Transforms/Utils/Evaluator.cpp b/llvm/lib/Transforms/Utils/Evaluator.cpp
index a65c3bac5e5..3c5e299fae9 100644
--- a/llvm/lib/Transforms/Utils/Evaluator.cpp
+++ b/llvm/lib/Transforms/Utils/Evaluator.cpp
@@ -433,6 +433,10 @@ bool Evaluator::EvaluateBlock(BasicBlock::iterator CurInst,
           DEBUG(dbgs() << "Skipping assume intrinsic.\n");
           ++CurInst;
           continue;
+        } else if (II->getIntrinsicID() == Intrinsic::sideeffect) {
+          DEBUG(dbgs() << "Skipping sideeffect intrinsic.\n");
+          ++CurInst;
+          continue;
         }
 
         DEBUG(dbgs() << "Unknown intrinsic. Can not evaluate.\n");
diff --git a/llvm/lib/Transforms/Vectorize/LoadStoreVectorizer.cpp b/llvm/lib/Transforms/Vectorize/LoadStoreVectorizer.cpp
index 5d355c52021..dc83b6d4d29 100644
--- a/llvm/lib/Transforms/Vectorize/LoadStoreVectorizer.cpp
+++ b/llvm/lib/Transforms/Vectorize/LoadStoreVectorizer.cpp
@@ -34,6 +34,7 @@
 #include "llvm/IR/InstrTypes.h"
 #include "llvm/IR/Instruction.h"
 #include "llvm/IR/Instructions.h"
+#include "llvm/IR/IntrinsicInst.h"
 #include "llvm/IR/Module.h"
 #include "llvm/IR/Type.h"
 #include "llvm/IR/User.h"
@@ -500,6 +501,10 @@ Vectorizer::getVectorizablePrefix(ArrayRef<Instruction *> Chain) {
         MemoryInstrs.push_back(&I);
       else
         ChainInstrs.push_back(&I);
+    } else if (isa<IntrinsicInst>(&I) &&
+               cast<IntrinsicInst>(&I)->getIntrinsicID() ==
+                   Intrinsic::sideeffect) {
+      // Ignore llvm.sideeffect calls.
     } else if (IsLoadChain && (I.mayWriteToMemory() || I.mayThrow())) {
       DEBUG(dbgs() << "LSV: Found may-write/throw operation: " << I << '\n');
       break;
diff --git a/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp b/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
index ed29ca0b573..673c47f4730 100644
--- a/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
+++ b/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
@@ -8117,7 +8117,7 @@ bool LoopVectorizationPlanner::tryToWiden(Instruction *I, VPBasicBlock *VPBB,
   if (CallInst *CI = dyn_cast<CallInst>(I)) {
     Intrinsic::ID ID = getVectorIntrinsicIDForCall(CI, TLI);
     if (ID && (ID == Intrinsic::assume || ID == Intrinsic::lifetime_end ||
-               ID == Intrinsic::lifetime_start))
+               ID == Intrinsic::lifetime_start || ID == Intrinsic::sideeffect))
       return false;
   }
 
diff --git a/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp b/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp
index 4232252af36..6c607062f25 100644
--- a/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp
+++ b/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp
@@ -3612,7 +3612,9 @@ void BoUpSLP::BlockScheduling::initScheduleData(Instruction *FromI,
            "new ScheduleData already in scheduling region");
     SD->init(SchedulingRegionID, I);
 
-    if (I->mayReadOrWriteMemory()) {
+    if (I->mayReadOrWriteMemory() &&
+        (!isa<IntrinsicInst>(I) ||
+         cast<IntrinsicInst>(I)->getIntrinsicID() != Intrinsic::sideeffect)) {
       // Update the linked list of memory accessing instructions.
       if (CurrentLoadStore) {
         CurrentLoadStore->NextLoadStore = SD;