[llvm] r181178 - Update the comment to mention that we use TTI.
Nadav Rotem
nrotem at apple.com
Sun May 5 20:06:36 PDT 2013
Author: nadav
Date: Sun May 5 22:06:36 2013
New Revision: 181178
URL: http://llvm.org/viewvc/llvm-project?rev=181178&view=rev
Log:
Update the comment to mention that we use TTI.
Modified:
llvm/trunk/lib/Transforms/Vectorize/LoopVectorize.cpp
Modified: llvm/trunk/lib/Transforms/Vectorize/LoopVectorize.cpp
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/Transforms/Vectorize/LoopVectorize.cpp?rev=181178&r1=181177&r2=181178&view=diff
==============================================================================
--- llvm/trunk/lib/Transforms/Vectorize/LoopVectorize.cpp (original)
+++ llvm/trunk/lib/Transforms/Vectorize/LoopVectorize.cpp Sun May 5 22:06:36 2013
@@ -8,9 +8,9 @@
//===----------------------------------------------------------------------===//
//
// This is the LLVM loop vectorizer. This pass modifies 'vectorizable' loops
-// and generates target-independent LLVM-IR. Legalization of the IR is done
-// in the codegen. However, the vectorizer uses (will use) the codegen
-// interfaces to generate IR that is likely to result in an optimal binary.
+// and generates target-independent LLVM-IR.
+// The vectorizer uses the TargetTransformInfo analysis to estimate the costs
+// of instructions in order to estimate the profitability of vectorization.
//
// The loop vectorizer combines consecutive loop iterations into a single
// 'wide' iteration. After this transformation the index is incremented
More information about the llvm-commits
mailing list