From: Hal Finkel <hfinkel@anl.gov>
Date: Fri, 8 Feb 2013 21:13:39 +0000 (+0000)
Subject: BBVectorize: Use TTI->getAddressComputationCost
X-Git-Url: http://demsky.eecs.uci.edu/git/?a=commitdiff_plain;h=0cf5d396c14c71dd4fa1d102c2b3d178b1191436;p=oota-llvm.git

BBVectorize: Use TTI->getAddressComputationCost

This is a follow-up to the cost-model change in r174713 which splits
the cost of a memory operation between the address computation and the
actual memory access. In r174713, this cost is always added to the
memory operation cost, and so BBVectorize will do the same.

Currently, this new cost function is used only by ARM, and I don't
have any ARM test cases for BBVectorize. Assistance in generating some
good ARM test cases for BBVectorize would be greatly appreciated!

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@174743 91177308-0d34-0410-b5e6-96231b3b80d8
---

diff --git a/lib/Transforms/Vectorize/BBVectorize.cpp b/lib/Transforms/Vectorize/BBVectorize.cpp
index 9bf09ff122e..ec10b4207b5 100644
--- a/lib/Transforms/Vectorize/BBVectorize.cpp
+++ b/lib/Transforms/Vectorize/BBVectorize.cpp
@@ -972,6 +972,11 @@ namespace {
           unsigned VCost = TTI->getMemoryOpCost(I->getOpcode(), VType,
                                                 BottomAlignment,
                                                 IAddressSpace);
+
+          ICost += TTI->getAddressComputationCost(aTypeI);
+          JCost += TTI->getAddressComputationCost(aTypeJ);
+          VCost += TTI->getAddressComputationCost(VType);
+
           if (VCost > ICost + JCost)
             return false;