[vectorizer] Completely disable the block frequency guidance of the loop

vectorizer, placing it behind an off-by-default flag.

It turns out that block frequency isn't what we want at all, here or
elsewhere. This has been I think a nagging feeling for several of us
working with it, but Arnold has given some really nice simple examples
where the results are so comprehensively wrong that they aren't useful.

I'm planning to email the dev list with a summary of why its not really
useful and a couple of ideas about how to better structure these types
of heuristics.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@200294 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/lib/Transforms/Vectorize/LoopVectorize.cpp b/lib/Transforms/Vectorize/LoopVectorize.cpp
index 78674952847bc33205aaa63aad51c50e21d56642..c72c2dc41fc07d3e3be02fab4dbe9f61921cbf9b 100644 (file)
--- a/lib/Transforms/Vectorize/LoopVectorize.cpp
+++ b/lib/Transforms/Vectorize/LoopVectorize.cpp
@@ -172,6 +172,12 @@ static cl::opt<unsigned> SmallLoopCost(
     "small-loop-cost", cl::init(20), cl::Hidden,
     cl::desc("The cost of a loop that is considered 'small' by the unroller."));
 
+static cl::opt<bool> LoopVectorizeWithBlockFrequency(
+    "loop-vectorize-with-block-frequency", cl::init(false), cl::Hidden,
+    cl::desc("Enable the use of the block frequency analysis to access PGO "
+             "heuristics minimizing code growth in cold regions and being more "
+             "aggressive in hot regions."));
+
 // Runtime unroll loops for load/store throughput.
 static cl::opt<bool> EnableLoadStoreRuntimeUnroll(
     "enable-loadstore-runtime-unroll", cl::init(false), cl::Hidden,
@@ -1099,9 +1105,13 @@ struct LoopVectorize : public FunctionPass {
     // Compute the weighted frequency of this loop being executed and see if it
     // is less than 20% of the function entry baseline frequency. Note that we
     // always have a canonical loop here because we think we *can* vectoriez.
-    BlockFrequency LoopEntryFreq = BFI->getBlockFreq(L->getLoopPreheader());
-    if (Hints.Force != 1 && LoopEntryFreq < ColdEntryFreq)
-      OptForSize = true;
+    // FIXME: This is hidden behind a flag due to pervasive problems with
+    // exactly what block frequency models.
+    if (LoopVectorizeWithBlockFrequency) {
+      BlockFrequency LoopEntryFreq = BFI->getBlockFreq(L->getLoopPreheader());
+      if (Hints.Force != 1 && LoopEntryFreq < ColdEntryFreq)
+        OptForSize = true;
+    }
 
     // Check the function attributes to see if implicit floats are allowed.a
     // FIXME: This check doesn't seem possibly correct -- what if the loop is

diff --git a/test/Transforms/LoopVectorize/X86/small-size.ll b/test/Transforms/LoopVectorize/X86/small-size.ll
index 1d46366369c83c94dd6e332f8c8a29c9898b84c9..dfa4faaf09eed32855517b5d8507db0bee34a302 100644 (file)
--- a/test/Transforms/LoopVectorize/X86/small-size.ll
+++ b/test/Transforms/LoopVectorize/X86/small-size.ll
@@ -1,4 +1,4 @@
-; RUN: opt < %s  -loop-vectorize -force-vector-unroll=1 -force-vector-width=4 -dce -instcombine -S | FileCheck %s
+; RUN: opt < %s  -loop-vectorize -force-vector-unroll=1 -force-vector-width=4 -loop-vectorize-with-block-frequency -dce -instcombine -S | FileCheck %s
 
 target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64-S128"
 target triple = "x86_64-apple-macosx10.8.0"