[PATCH] D12742: [ARM] Scaling up values in ARMBaseInstrInfo::isProfitableToIfCvt() before they are scaled by a probability to avoid precision issue.

[Cong Hou via llvm-commits]

congh created this revision.
congh added reviewers: rengolin, t.p.northover, davidxl.
congh added a subscriber: llvm-commits.
Herald added subscribers: rengolin, aemerson.

In ARMBaseInstrInfo::isProfitableToIfCvt(), there is a simple cost model in which the number of cycles is scaled by a probability to estimate the cost. However, when the number of cycles is small (which is usually the case), there is a precision issue after the computation. For example, for the following code from ARMBaseInstrInfo::isProfitableToIfCvt():

```
unsigned TUnpredCost = Probability.scale(TCycles);
unsigned FUnpredCost = Probability.getCompl().scale(FCycles);
unsigned UnpredCost = TUnpredCost + FUnpredCost;
```

Assume Probability is 0.5 and both TCycles and FCycles are 1, the resulted UnpredCost is 0 while 1 should be a more reasonable result. To avoid this issue, this patch scales both TCycles and FCycles up by 1024 (chosen to make the multiplication a litter faster) before they are scaled by the probability. Other variables also need to be scaled up for the final comparison.

Several test cases are adjusted due to this change.

http://reviews.llvm.org/D12742

Files:
  lib/Target/ARM/ARMBaseInstrInfo.cpp
  test/CodeGen/ARM/2013-10-11-select-stalls.ll
  test/CodeGen/ARM/ifcvt4.ll
  test/CodeGen/ARM/sjlj-prepare-critical-edge.ll
  test/CodeGen/ARM/test-sharedidx.ll
  test/CodeGen/Thumb2/thumb2-ifcvt1.ll

-------------- next part --------------
A non-text attachment was scrubbed...
Name: D12742.34384.patch
Type: text/x-patch
Size: 5008 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20150909/6509518c/attachment.bin>