[MemDep] Optimize SortNonLocalDepInfoCache sorting strategy for large caches with few unsorted entries

Author: DingdWang

llvm/lib/Analysis/MemoryDependenceAnalysis.cpp

@@ -983,33 +983,41 @@ MemDepResult MemoryDependenceResults::getNonLocalInfoForBlock(
 static void
 SortNonLocalDepInfoCache(MemoryDependenceResults::NonLocalDepInfo &Cache,
                          unsigned NumSortedEntries) {
-  switch (Cache.size() - NumSortedEntries) {
-  case 0:
-    // done, no new entries.
-    break;
-  case 2: {
-    // Two new entries, insert the last one into place.
-    NonLocalDepEntry Val = Cache.back();
-    Cache.pop_back();
-    MemoryDependenceResults::NonLocalDepInfo::iterator Entry =
-        std::upper_bound(Cache.begin(), Cache.end() - 1, Val);
-    Cache.insert(Entry, Val);
-    [[fallthrough]];
+
+  // Output number of sorted entries and size of cache for each sort.
+  LLVM_DEBUG(dbgs() << "NumSortedEntries: " << NumSortedEntries
+                    << ", Cache.size: " << Cache.size() << "\n");
+
+  // If only one entry, don't sort.
+  if (Cache.size() < 2)
+    return;
+
+  unsigned s = Cache.size() - NumSortedEntries;
+
+  // If the cache is already sorted, don't sort it again.
+  if (s == 0)
+    return;
+
+  // If no entry is sorted, sort the whole cache.
+  if (NumSortedEntries == 0) {
+    llvm::sort(Cache);
+    return;
   }
-  case 1:
-    // One new entry, Just insert the new value at the appropriate position.
-    if (Cache.size() != 1) {
+
+  // If the number of unsorted entires is small and the cache size is big, use
+  // insertion sort is faster. Here use Log2_32 to quickly choose the sort
+  // method.
+  if (s < Log2_32(Cache.size())) {
+    while (s > 0) {
       NonLocalDepEntry Val = Cache.back();
       Cache.pop_back();
       MemoryDependenceResults::NonLocalDepInfo::iterator Entry =
-          llvm::upper_bound(Cache, Val);
+          std::upper_bound(Cache.begin(), Cache.end() - s + 1, Val);
       Cache.insert(Entry, Val);
+      s--;
     }
-    break;
-  default:
-    // Added many values, do a full scale sort.
+  } else {
     llvm::sort(Cache);
-    break;
   }
 }