Boost the effective chain depth of loads and stores.

By default, boost the chain depth contribution of loads and stores. This will allow a load/store pair to vectorize even when it would not otherwise be long enough to satisfy the chain depth requirement.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@149761 91177308-0d34-0410-b5e6-96231b3b80d8

1 files changed, 10 insertions, 0 deletions

diff --git a/lib/Transforms/Vectorize/BBVectorize.cpp b/lib/Transforms/Vectorize/BBVectorize.cpp
index ce6e994c46..0780b4489f 100644
--- a/lib/Transforms/Vectorize/BBVectorize.cpp
+++ b/lib/Transforms/Vectorize/BBVectorize.cpp
@@ -104,6 +104,11 @@ AlignedOnly("bb-vectorize-aligned-only", cl::init(false), cl::Hidden,
   cl::desc("Only generate aligned loads and stores"));
 
 static cl::opt<bool>
+NoMemOpBoost("bb-vectorize-no-mem-op-boost",
+  cl::init(false), cl::Hidden,
+  cl::desc("Don't boost the chain-depth contribution of loads and stores"));
+
+static cl::opt<bool>
 FastDep("bb-vectorize-fast-dep", cl::init(false), cl::Hidden,
   cl::desc("Use a fast instruction dependency analysis"));
 
@@ -340,6 +345,11 @@ namespace {
       if (isa<InsertElementInst>(V) || isa<ExtractElementInst>(V))
         return 0;
 
+      // Give a load or store half of the required depth so that load/store
+      // pairs will vectorize.
+      if (!NoMemOpBoost && (isa<LoadInst>(V) || isa<StoreInst>(V)))
+        return ReqChainDepth/2;
+
       return 1;
     }