| Commit message (Expand) | Author | Age | Files | Lines |
|---|
| * | InstCombiner::visitSelectInst - rename Pred to MinMaxPred to stop shadow vari... | Simon Pilgrim | 2019-08-28 | 1 | -5/+6 |
| * | [InstCombine] Fold select with ctlz to cttz | David Bolvansky | 2019-08-27 | 1 | -0/+38 |
| * | [Constant] Add 'isElementWiseEqual()' method | Roman Lebedev | 2019-08-24 | 1 | -16/+2 |
| * | [InstCombine] Try to reuse constant from select in leading comparison | Roman Lebedev | 2019-08-24 | 1 | -0/+93 |
| * | [InstCombine] simplify min/max of min/max with same operands (PR35607) | Sanjay Patel | 2019-08-20 | 1 | -0/+10 |
| * | [InstCombine] canonicalize a scalar-select-of-vectors to vector select | Sanjay Patel | 2019-08-16 | 1 | -0/+27 |
| * | [InstCombine] Non-canonical clamp-like pattern handling | Roman Lebedev | 2019-08-13 | 1 | -0/+146 |
| * | [InstCombine][NFC] Rename IsFreeToInvert() -> isFreeToInvert() for consistency | Roman Lebedev | 2019-08-13 | 1 | -3/+3 |
| * | [InstCombine] fold cmp+select using select operand equivalence | Sanjay Patel | 2019-08-02 | 1 | -2/+62 |
| * | [IR] SelectInst: add swapValues() utility | Roman Lebedev | 2019-08-01 | 1 | -4/+2 |
| * | [InstCombine] Disable fold from D64285 for non-integer types | David Bolvansky | 2019-07-12 | 1 | -0/+2 |
| * | [InstCombine] Fold select (icmp sgt x, -1), lshr (X, Y), ashr (X, Y) to ashr ... | David Bolvansky | 2019-07-12 | 1 | -0/+41 |
| * | [InstCombine] canonicalize fcmp+select to minnum/maxnum intrinsics | Sanjay Patel | 2019-06-30 | 1 | -0/+13 |
| * | [InstCombine] allow unordered preds when canonicalizing to fabs() | Sanjay Patel | 2019-06-10 | 1 | -2/+2 |
| * | [InstCombine] fix bug in canonicalization to fabs() | Sanjay Patel | 2019-06-10 | 1 | -2/+4 |
| * | [InstCombine] change canonicalization to fabs() to use FMF on fsub | Sanjay Patel | 2019-06-10 | 1 | -19/+21 |
| * | [InstCombine] allow unordered preds when canonicalizing to fabs() | Sanjay Patel | 2019-06-10 | 1 | -2/+4 |
| * | [InstCombine] change canonicalization to fabs() to use FMF on fneg | Sanjay Patel | 2019-06-09 | 1 | -13/+25 |
| * | [InstCombine] sink FP negation of operands through select | Sanjay Patel | 2019-05-06 | 1 | -0/+12 |
| * | [InstCombine] reduce code duplication; NFC | Sanjay Patel | 2019-05-06 | 1 | -7/+7 |
| * | [InstCombine] Use uadd.sat and usub.sat for canonicalization | Nikita Popov | 2019-03-27 | 1 | -28/+21 |
| * | [InstCombine] move add after smin/smax | Sanjay Patel | 2019-03-02 | 1 | -3/+16 |
| * | [InstCombine] move add after umin/umax | Sanjay Patel | 2019-03-01 | 1 | -0/+27 |
| * | [InstCombine] canonicalize more unsigned saturated add with 'not' | Sanjay Patel | 2019-02-26 | 1 | -0/+11 |
| * | [InstCombine] reduce even more unsigned saturated add with 'not' op | Sanjay Patel | 2019-02-19 | 1 | -5/+13 |
| * | [InstCombine] rearrange saturated add folds; NFC | Sanjay Patel | 2019-02-19 | 1 | -12/+14 |
| * | Revert "[InstCombine] reduce even more unsigned saturated add with 'not' op" | Sanjay Patel | 2019-02-18 | 1 | -28/+17 |
| * | [InstCombine] reduce even more unsigned saturated add with 'not' op | Sanjay Patel | 2019-02-18 | 1 | -17/+28 |
| * | [InstCombine] reduce more unsigned saturated add with 'not' op | Sanjay Patel | 2019-02-17 | 1 | -3/+13 |
| * | [InstCombine] reduce unsigned saturated add with 'not' op | Sanjay Patel | 2019-02-17 | 1 | -11/+28 |
| * | [InstCombine] canonicalize cmp/select form of uadd saturate with constant | Sanjay Patel | 2019-01-29 | 1 | -0/+20 |
| * | Update the file headers across all of the LLVM projects in the monorepo | Chandler Carruth | 2019-01-19 | 1 | -4/+3 |
| * | [InstCombine] canonicalize another raw IR rotate pattern to funnel shift | Sanjay Patel | 2019-01-08 | 1 | -3/+2 |
| * | [InstCombine] Relax cttz/ctlz with select on zero | Nikita Popov | 2019-01-05 | 1 | -8/+15 |
| * | [InstCombine] canonicalize raw IR rotate patterns to funnel shift | Sanjay Patel | 2019-01-01 | 1 | -13/+8 |
| * | [InstSimplify] fold select with implied condition | Sanjay Patel | 2018-11-29 | 1 | -18/+0 |
| * | [InstCombine] Remove a couple of asserts based on incorrect assumptions | Mandeep Singh Grang | 2018-11-14 | 1 | -11/+4 |
| * | [InstCombine] canonicalize rotate patterns with cmp/select | Sanjay Patel | 2018-11-13 | 1 | -0/+63 |
| * | [InstSimplify] fold select (fcmp X, Y), X, Y | Sanjay Patel | 2018-11-05 | 1 | -50/+0 |
| * | [InstCombine] loosen FP 0.0 constraint for fcmp+select substitution | Sanjay Patel | 2018-11-05 | 1 | -4/+13 |
| * | [InstCombine] use 'match' to handle vectors and simplify code | Sanjay Patel | 2018-10-23 | 1 | -2/+3 |
| * | [InstCombine] swap select profile metadata when swapping select ops | Sanjay Patel | 2018-10-23 | 1 | -0/+1 |
| * | [IRBuilder] Fixup CreateIntrinsic to allow specifying Types to Mangle. | Neil Henning | 2018-10-08 | 1 | -2/+2 |
| * | [InstCombine] Fold (min/max ~X, Y) -> ~(max/min X, ~Y) when Y is freely inver... | Craig Topper | 2018-09-22 | 1 | -10/+36 |
| * | [InstCombine] Fold (xor (min/max X, Y), -1) -> (max/min ~X, ~Y) when X and Y ... | Craig Topper | 2018-09-13 | 1 | -0/+2 |
| * | [InstCombine] remove checks for IsFreeToInvert() | Sanjay Patel | 2018-09-13 | 1 | -3/+1 |
| * | [InstCombine] reorder folds to reduce chance of infinite loops | Sanjay Patel | 2018-09-13 | 1 | -22/+20 |
| * | [InstCombine] Partially revert rL341674 due to PR38897. | Alina Sbirlea | 2018-09-10 | 1 | -35/+8 |
| * | [InstCombine] Fold (min/max ~X, Y) -> ~(max/min X, ~Y) when Y is freely inver... | Craig Topper | 2018-09-07 | 1 | -8/+35 |
| * | [InstCombine] Do not fold scalar ops over select with vector condition. | Florian Hahn | 2018-09-07 | 1 | -0/+8 |
