Jul 7 2014
Jul 3 2014
Jun 5 2014
LGTM. Please commit.
May 27 2014
Please document the code that you are adding to the vectorization of binary operators.
Please commit the patch with the fix to the commuted argument order and a fix to the typo in the docs.
May 23 2014
May 22 2014
Please add a testcase for one of the functions where the last argument is different and the SLPvectorizer is unable to vectorize the function.
May 21 2014
May 20 2014
May 19 2014
+ bool isSafeToClobberEFLAGS(MachineBasicBlock &MBB,
+ MachineBasicBlock::iterator I) const;
May 16 2014
I am sorry but this is the wrong approach. You copy a ton of code that we will need to maintain if we want to add support to new instructions.
May 14 2014
Excellent. Please update the cost model as well.
Overall this change makes sense. I did not review the patch carefully but I noticed that Andrea did. When you commit please split this patch to the different optimizations: shuffle blends, BLENDI, etc.
May 9 2014
I did not review the code carefully but I think it looks fine. We are not generating new shuffle masks so there should not be any lowering problems.
May 6 2014
May 5 2014
Why is getDebugLocString defined in LoopVectorize.cpp? I am expecting other passes to also need this utility. Please refactor this function and put this function in a place where other passes would be able to use it.
May 2 2014
The patch LGTM. Did you run it on the LLVM test suite? Do you know of any workloads that improve?
Apr 29 2014
This part LGTM.
Apr 24 2014
Apr 23 2014
I did not review the patch carefully but from a quick look it looks fine. Andrea, what do you say?