[memcpyopt] Teach memcpyopt to optimize across basic blocks

This teaches memcpyopt to make a non-local memdep query when a local query
indicates that the dependency is non-local. This notably allows it to
eliminate many more llvm.memcpy calls in common Rust code, often by 20-30%.

This is r319482 and r319483, along with fixes for PR35519: fix the 
optimization that merges stores into memsets to preserve cached memdep
info, and fix memdep's non-local caching strategy to not assume that larger
queries are always more conservative than smaller ones.

Fixes PR28958 and PR35519.

Differential Revision: https://reviews.llvm.org/D40802

llvm-svn: 321138

1 files changed, 11 insertions, 9 deletions

diff --git a/llvm/lib/Analysis/MemoryDependenceAnalysis.cpp b/llvm/lib/Analysis/MemoryDependenceAnalysis.cpp
index a6c5901..d5538f5 100644
--- a/llvm/lib/Analysis/MemoryDependenceAnalysis.cpp
+++ b/llvm/lib/Analysis/MemoryDependenceAnalysis.cpp
@@ -919,6 +919,14 @@ void MemoryDependenceResults::getNonLocalPointerDependency(
     Instruction *QueryInst, SmallVectorImpl<NonLocalDepResult> &Result) {
   const MemoryLocation Loc = MemoryLocation::get(QueryInst);
   bool isLoad = isa<LoadInst>(QueryInst);
+  return getNonLocalPointerDependencyFrom(QueryInst, Loc, isLoad, Result);
+}
+
+void MemoryDependenceResults::getNonLocalPointerDependencyFrom(
+    Instruction *QueryInst,
+    const MemoryLocation &Loc,
+    bool isLoad,
+    SmallVectorImpl<NonLocalDepResult> &Result) {
   BasicBlock *FromBB = QueryInst->getParent();
   assert(FromBB);
 
@@ -1118,21 +1126,15 @@ bool MemoryDependenceResults::getNonLocalPointerDepFromBB(
   // If we already have a cache entry for this CacheKey, we may need to do some
   // work to reconcile the cache entry and the current query.
   if (!Pair.second) {
-    if (CacheInfo->Size < Loc.Size) {
-      // The query's Size is greater than the cached one. Throw out the
-      // cached data and proceed with the query at the greater size.
+    if (CacheInfo->Size != Loc.Size) {
+      // The query's Size differs from the cached one. Throw out the
+      // cached data and proceed with the query at the new size.
       CacheInfo->Pair = BBSkipFirstBlockPair();
       CacheInfo->Size = Loc.Size;
       for (auto &Entry : CacheInfo->NonLocalDeps)
         if (Instruction *Inst = Entry.getResult().getInst())
           RemoveFromReverseMap(ReverseNonLocalPtrDeps, Inst, CacheKey);
       CacheInfo->NonLocalDeps.clear();
-    } else if (CacheInfo->Size > Loc.Size) {
-      // This query's Size is less than the cached one. Conservatively restart
-      // the query using the greater size.
-      return getNonLocalPointerDepFromBB(
-          QueryInst, Pointer, Loc.getWithNewSize(CacheInfo->Size), isLoad,
-          StartBB, Result, Visited, SkipFirstBlock);
     }
 
     // If the query's AATags are inconsistent with the cached one,