summaryrefslogtreecommitdiffstats
path: root/llvm/lib/Transforms/InstCombine/InstCombineSelect.cpp
Commit message (Collapse)AuthorAgeFilesLines
* Surprisingly, we missed a trivial case here. Fix that!Nick Lewycky2012-09-281-0/+4
| | | | llvm-svn: 164814
* Prefer shuffles to selects. Backends love shuffles!Nick Lewycky2012-09-271-1/+19
| | | | llvm-svn: 164763
* fix infinite loop in instcombine in the presence of a (malformed) ↵Nuno Lopes2012-07-271-0/+4
| | | | | | | | self-referencing select inst. This can happen as long as the instruction is not reachable. Instcombine does generate these unreachable malformed selects when doing RAUW llvm-svn: 160874
* Simplify demanded bits of select sources where the condition is a constant ↵Pete Cooper2012-07-261-0/+11
| | | | | | vector llvm-svn: 160835
* Fix a bug in FoldSelectOpOp. Bitcast ops may change the number of vector ↵Nadav Rotem2012-06-071-0/+6
| | | | | | elements, which may disagree with the select condition type. llvm-svn: 158166
* InstCombine: Fix infinite loop when encountering switch on trivial icmp.Benjamin Kramer2012-05-281-1/+1
| | | | | | | | | | | | The test case feeds the following into InstCombine's visitSelect: %tobool8 = icmp ne i32 0, 0 %phitmp = select i1 %tobool8, i32 3, i32 0 Then instcombine replaces the right side of the switch with 0, doesn't notice that nothing changes and tries again indefinitely. This fixes PR12897. llvm-svn: 157587
* More dead code removal (using -Wunreachable-code)David Blaikie2012-01-201-1/+0
| | | | llvm-svn: 148578
* Added InstCombine for "select cond, ~cond, x" type patternsPete Cooper2011-12-151-0/+7
| | | | | | These can be reduced to "~cond & x" or "~cond | x" llvm-svn: 146624
* Fix a few more places where TargetData/TargetLibraryInfo is not being passed.Chad Rosier2011-12-021-14/+17
| | | | | | Add FIXMEs to places that are non-trivial to fix. llvm-svn: 145661
* Add a new icmp+select optz'n. Also shows off the load(cst) folding added inNick Lewycky2011-10-021-0/+6
| | | | | | r140966. llvm-svn: 140969
* Enhance a couple places where we were doing constant folding of instructions,Nick Lewycky2011-10-021-1/+6
| | | | | | but not load instructions. Noticed by inspection. llvm-svn: 140966
* Clean up includes of llvm/Analysis/ConstantFolding.h so it's included where ↵Eli Friedman2011-07-201-0/+1
| | | | | | it's used and not included where it isn't. llvm-svn: 135628
* Use ArrayRef in ConstantFoldInstOperands and ConstantFoldCall.Jay Foad2011-07-191-1/+1
| | | | llvm-svn: 135477
* land David Blaikie's patch to de-constify Type, with a few tweaks.Chris Lattner2011-07-181-2/+2
| | | | llvm-svn: 135375
* PR10180: Fix a instcombine crash with FP vectors.Eli Friedman2011-06-231-2/+2
| | | | llvm-svn: 133756
* ConstantFoldInstOperands doesn't like compares, hand it off to instsimplify ↵Benjamin Kramer2011-05-281-0/+10
| | | | | | | | instead. Fixes PR10040. llvm-svn: 132254
* InstCombine: Make switch folding with equality compares more aggressive by ↵Benjamin Kramer2011-05-271-15/+54
| | | | | | | | trying instsimplify on the arm where we know the compared value. Stuff like "x == y ? y : x&y" now folds into "x&y". llvm-svn: 132185
* Switch more inst insertion in instcombine to IRBuilder.Eli Friedman2011-05-181-10/+6
| | | | llvm-svn: 131547
* Switch more inst insertion in instcombine to IRBuilder.Eli Friedman2011-05-181-13/+6
| | | | llvm-svn: 131544
* Switch inst insertion in instcombine transform to IRBuilder.Eli Friedman2011-05-181-6/+2
| | | | llvm-svn: 131542
* Remove tabs I accidentally added.Nick Lewycky2011-03-281-15/+15
| | | | llvm-svn: 128413
* Teach the transformation that moves binary operators around selects to preserveNick Lewycky2011-03-271-8/+22
| | | | | | the subclass optional data. llvm-svn: 128388
* Add a small missed optimization: turn X == C ? X : Y into X == C ? C : Y. ThisNick Lewycky2011-03-271-0/+13
| | | | | | | | | | removes one use of X which helps it pass the many hasOneUse() checks. In my analysis, this turns up very often where X = A >>exact B and that can't be simplified unless X has one use (except by increasing the lifetime of A which is generally a performance loss). llvm-svn: 128373
* InstCombine: Fix a thinko where transform an icmp under the assumption that ↵Benjamin Kramer2011-03-111-3/+2
| | | | | | | | it's a zero comparison when it's not. Fixes PR9454. llvm-svn: 127464
* Fold select + select where both selects are on the same condition.Nick Lewycky2011-01-281-0/+13
| | | | llvm-svn: 124469
* Instcombine: Fix pattern where the sext did not dominate the icmp using itTobias Grosser2011-01-091-2/+7
| | | | llvm-svn: 123121
* Fix a bug in r123034 (trying to sext/zext non-integers) and clean up a little.Frits van Bommel2011-01-081-5/+8
| | | | llvm-svn: 123061
* InstCombine: Match min/max hidden by sext/zextTobias Grosser2011-01-071-35/+70
| | | | | | | | | | | | | | | X = sext x; x >s c ? X : C+1 --> X = sext x; X <s C+1 ? C+1 : X X = sext x; x <s c ? X : C-1 --> X = sext x; X >s C-1 ? C-1 : X X = zext x; x >u c ? X : C+1 --> X = zext x; X <u C+1 ? C+1 : X X = zext x; x <u c ? X : C-1 --> X = zext x; X >u C-1 ? C-1 : X X = sext x; x >u c ? X : C+1 --> X = sext x; X <u C+1 ? C+1 : X X = sext x; x <u c ? X : C-1 --> X = sext x; X >u C-1 ? C-1 : X Instead of calculating this with mixed types promote all to the larger type. This enables scalar evolution to analyze this expression. PR8866 llvm-svn: 123034
* Some whitespace fixesTobias Grosser2011-01-071-24/+24
| | | | llvm-svn: 123033
* InstCombine: creating selects from -1 and 0 is fine, they combine into a ↵Benjamin Kramer2010-12-221-3/+6
| | | | | | sext from i1. llvm-svn: 122453
* Generalize the and-icmp-select instcombine further by allowing selects of ↵Benjamin Kramer2010-12-111-4/+22
| | | | | | | | | | | the form (x & 2^n) ? 2^m+C : C we can offset both arms by C to get the "(x & 2^n) ? 2^m : 0" form, optimize the select to a shift and apply the offset afterwards. llvm-svn: 121609
* Factor the (x & 2^n) ? 2^m : 0 instcombine into its own method and generalize itBenjamin Kramer2010-12-111-26/+54
| | | | | | to catch cases where n != m with a shift. llvm-svn: 121608
* Teach InstCombine not to use Add and Neg on FP. PR 8490.Dale Johannesen2010-10-271-1/+8
| | | | llvm-svn: 117510
* Remove the rest of my instcombine changes. Back to the drawing board on ↵Owen Anderson2010-07-161-28/+0
| | | | | | this one. llvm-svn: 108530
* Speculatively revert r108429 to fix the clang self-host.Owen Anderson2010-07-151-0/+28
| | | | llvm-svn: 108436
* Per Chris' suggestion, get rid of the select canonicalization and just addOwen Anderson2010-07-151-28/+0
| | | | | | | | the corresponding or-icmp-and pattern. This has the added benefit of doing the matching earlier, and thus being less susceptible to being confused by earlier transforms. llvm-svn: 108429
* Reapply r108378, with bugfixes, testcase, and improved comment formatting.Owen Anderson2010-07-151-0/+28
| | | | | | This now passes LIT, nighty test, and llvm-gcc bootstrap on my machine. llvm-svn: 108422
* Speculatively revert r108378; may be causing bootstrap failures.Eli Friedman2010-07-151-25/+0
| | | | llvm-svn: 108389
* Add instcombine transforms to optimize tests of multiple bits of the same ↵Owen Anderson2010-07-141-0/+25
| | | | | | value into a single larger comparison. llvm-svn: 108378
* Teach instcombine to transformBenjamin Kramer2010-07-081-0/+31
| | | | | | | | | | | | | | | | | | | | | | | | | | (X >s -1) ? C1 : C2 and (X <s 0) ? C2 : C1 into ((X >>s 31) & (C2 - C1)) + C1, avoiding the conditional. This optimization could be extended to take non-const C1 and C2 but we better stay conservative to avoid code size bloat for now. for int sel(int n) { return n >= 0 ? 60 : 100; } we now generate sarl $31, %edi andl $40, %edi leal 60(%rdi), %eax instead of testl %edi, %edi movl $60, %ecx movl $100, %eax cmovnsl %ecx, %eax llvm-svn: 107866
* move some select simplifications out out instcombine intoChris Lattner2010-04-201-31/+13
| | | | | | inst simplify. No functionality change. llvm-svn: 101873
* Don't do (X != Y) ? X : Y -> X for floating-point values; it doesn'tDan Gohman2010-02-231-5/+23
| | | | | | | | handle NaN properly. Do (X une Y) ? X : Y -> X if one of X and Y is not zero. llvm-svn: 96955
* Uniformize the names of type predicates: rather than having isFloatTy andDuncan Sands2010-02-151-2/+2
| | | | | | isInteger, we now have isFloatTy and isIntegerTy. Requested by Chris! llvm-svn: 96223
* change the canonical form of "cond ? -1 : 0" to be Chris Lattner2010-01-241-48/+18
| | | | | | | | "sext cond" instead of a select. This simplifies some instcombine code, matches the policy for zext (cond ? 1 : 0 -> zext), and allows us to generate better code for a testcase on ppc. llvm-svn: 94339
* Convert a ton of simple integer type equality tests to the new predicate.Benjamin Kramer2010-01-051-1/+1
| | | | llvm-svn: 92760
* clean up header.Chris Lattner2010-01-051-7/+2
| | | | llvm-svn: 92688
* split select out to its own file.Chris Lattner2010-01-051-0/+708
llvm-svn: 92687
OpenPOWER on IntegriCloud