[PATCH] D156850: [NFC][Coroutines] Use a reverse post-order to guide the computation about cross suspend infomation to reach a fixed point faster.

[witstorm via Phabricator via llvm-commits]

witstorm95 updated this revision to Diff 546328.
witstorm95 added a comment.

@ChuanqiXu The compilation time as follow,

  n: 20000
  6.25user 0.24system 0:06.50elapsed 99%CPU (0avgtext+0avgdata 1065512maxresident)k
  0inputs+16816outputs (0major+256090minor)pagefaults 0swaps
  
  n: 40000
  12.75user 0.93system 0:13.68elapsed 99%CPU (0avgtext+0avgdata 3784604maxresident)k
  8inputs+33536outputs (0major+931086minor)pagefaults 0swaps
  
  n: 60000
  19.73user 2.11system 0:21.86elapsed 99%CPU (0avgtext+0avgdata 8261644maxresident)k
  0inputs+50256outputs (0major+2045101minor)pagefaults 0swaps
  
  n: 80000
  28.88user 3.73system 0:32.63elapsed 99%CPU (0avgtext+0avgdata 14499536maxresident)k
  0inputs+66976outputs (0major+3597496minor)pagefaults 0swaps
  
  n: 100000
  37.95user 5.84system 0:43.79elapsed 99%CPU (0avgtext+0avgdata 22475716maxresident)k
  0inputs+83696outputs (0major+5583555minor)pagefaults 0swaps


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D156850/new/

https://reviews.llvm.org/D156850

Files:
  llvm/lib/Transforms/Coroutines/CoroFrame.cpp


Index: llvm/lib/Transforms/Coroutines/CoroFrame.cpp
===================================================================
--- llvm/lib/Transforms/Coroutines/CoroFrame.cpp
+++ llvm/lib/Transforms/Coroutines/CoroFrame.cpp
@@ -112,10 +112,11 @@
   }
 
   /// Compute the BlockData for the current function in one iteration.
-  /// Returns whether the BlockData changes in this iteration.
   /// Initialize - Whether this is the first iteration, we can optimize
   /// the initial case a little bit by manual loop switch.
-  template <bool Initialize = false> bool computeBlockData();
+  /// Returns whether the BlockData changes in this iteration.
+  template <bool Initialize = false, class BBRangeTy>
+  bool computeBlockData(const BBRangeTy &BBRange);
 
 public:
 #if !defined(NDEBUG) || defined(LLVM_ENABLE_DUMP)
@@ -223,12 +224,13 @@
 }
 #endif
 
-template <bool Initialize> bool SuspendCrossingInfo::computeBlockData() {
-  const size_t N = Mapping.size();
+template <bool Initialize, class BBRangeTy>
+bool SuspendCrossingInfo::computeBlockData(const BBRangeTy &BBRange) {
   bool Changed = false;
 
-  for (size_t I = 0; I < N; ++I) {
-    auto &B = Block[I];
+  for (auto BB : BBRange) {
+    auto BBNo = Mapping.blockToIndex(BB);
+    auto &B = Block[BBNo];
 
     // We don't need to count the predecessors when initialization.
     if constexpr (!Initialize)
@@ -261,7 +263,7 @@
     }
 
     if (B.Suspend) {
-      // If block S is a suspend block, it should kill all of the blocks it
+      // If block B is a suspend block, it should kill all of the blocks it
       // consumes.
       B.Kills |= B.Consumes;
     } else if (B.End) {
@@ -273,8 +275,8 @@
     } else {
       // This is reached when B block it not Suspend nor coro.end and it
       // need to make sure that it is not in the kill set.
-      B.KillLoop |= B.Kills[I];
-      B.Kills.reset(I);
+      B.KillLoop |= B.Kills[BBNo];
+      B.Kills.reset(BBNo);
     }
 
     if constexpr (!Initialize) {
@@ -283,9 +285,6 @@
     }
   }
 
-  if constexpr (Initialize)
-    return true;
-
   return Changed;
 }
 
@@ -325,9 +324,11 @@
       markSuspendBlock(Save);
   }
 
-  computeBlockData</*Initialize=*/true>();
-
-  while (computeBlockData())
+  // It is considered to be faster to use RPO traversal for forward-edges
+  // dataflow analysis.
+  ReversePostOrderTraversal<Function *> RPOT(&F);
+  computeBlockData</*Initialize=*/true>(RPOT);
+  while (computeBlockData</*Initialize*/ false>(RPOT))
     ;
 
   LLVM_DEBUG(dump());


-------------- next part --------------
A non-text attachment was scrubbed...
Name: D156850.546328.patch
Type: text/x-patch
Size: 2508 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20230802/714b6f1d/attachment.bin>