Eli Friedman ef366a16a2 PR2621: Improvements to the SCEV AddRec binomial expansion. This ... version uses a new algorithm for evaluating the binomial coefficients which is significantly more efficient for AddRecs of more than 2 terms (see the comments in the code for details on how the algorithm works). It also fixes some bugs: it removes the arbitrary length restriction for AddRecs, it fixes the silent generation of incorrect code for AddRecs which require a wide calculation width, and it fixes an issue where we were incorrectly truncating the iteration count too far when evaluating an AddRec expression narrower than the induction variable. There are still a few related issues I know of: I think there's still an issue with the SCEVExpander expansion of AddRec in terms of the width of the induction variable used. The hack to avoid generating too-wide integers shouldn't be necessary; instead, the callers should be considering the cost of the expansion before expanding it (in addition to not expanding too-wide integers, we might not want to expand expressions that are really expensive, especially when optimizing for size; calculating an length-17 32-bit AddRec currently generates about 250 instructions of straight-line code on X86). Also, for long 32-bit AddRecs on X86, CodeGen really sucks at scheduling the code. I'm planning on filing follow-up PRs for these issues. llvm-svn: 54332		2008-08-04 23:49:06 +00:00
..
2007-07-15-NegativeStride.ll	While testing particular algorithms to compute loop iteration count the brute	2008-07-19 13:26:15 +00:00
2007-08-06-MisinterpretBranch.ll
2007-08-06-Unsigned.ll	Stop creating extraneous smax/umax in SCEV. This removes a regression where we	2008-07-12 07:41:32 +00:00
2007-09-27-LargeStepping.ll	While testing particular algorithms to compute loop iteration count the brute	2008-07-19 13:26:15 +00:00
2007-11-14-SignedAddRec.ll
2007-11-18-OrInstruction.ll
2008-02-11-ReversedCondition.ll
2008-02-12-SMAXTripCount.ll
2008-02-15-UMax.ll
2008-05-25-NegativeStepToZero.ll	Fix PR2088. Use modulo linear equation solver to compute loop iteration	2008-07-20 15:55:14 +00:00
2008-06-12-BinomialInt64.ll	Crash less. The i64 restriction in BinomialCoefficient caused some problems	2008-06-13 04:38:55 +00:00
2008-07-12-UnneededSelect1.ll	Stop creating extraneous smax/umax in SCEV. This removes a regression where we	2008-07-12 07:41:32 +00:00
2008-07-12-UnneededSelect2.ll	Stop creating extraneous smax/umax in SCEV. This removes a regression where we	2008-07-12 07:41:32 +00:00
2008-07-19-InfiniteLoop.ll	Fix PR2088. Use modulo linear equation solver to compute loop iteration	2008-07-20 15:55:14 +00:00
2008-07-19-WrappingIV.ll	Fix PR2088. Use modulo linear equation solver to compute loop iteration	2008-07-20 15:55:14 +00:00
2008-07-29-SGTTripCount.ll	Fix for PR2607: SCEV miscomputing the loop count for loops with an	2008-07-30 00:04:08 +00:00
2008-07-29-SMinExpr.ll	Another SCEV issue from PR2607; essentially the same issue, but this	2008-07-30 04:36:32 +00:00
2008-08-04-IVOverflow.ll	PR2621: Improvements to the SCEV AddRec binomial expansion. This	2008-08-04 23:49:06 +00:00
2008-08-04-LongAddRec.ll	PR2621: Improvements to the SCEV AddRec binomial expansion. This	2008-08-04 23:49:06 +00:00
dg.exp
do-loop.ll
smax.ll
SolveQuadraticEquation.ll	While testing particular algorithms to compute loop iteration count the brute	2008-07-19 13:26:15 +00:00
trip-count2.ll
trip-count.ll	While testing particular algorithms to compute loop iteration count the brute	2008-07-19 13:26:15 +00:00