forked from OSchip/llvm-project
eb731b09f3
The 'ord' and 'uno' predicates have a logic operation for NAN built into their definitions: FCMP_ORD = 7, ///< 0 1 1 1 True if ordered (no nans) FCMP_UNO = 8, ///< 1 0 0 0 True if unordered: isnan(X) | isnan(Y) So we can simplify patterns like this: (fcmp ord (known NNAN), X) && (fcmp ord X, Y) --> fcmp ord X, Y (fcmp uno (known NNAN), X) || (fcmp uno X, Y) --> fcmp uno X, Y It might be better to split this into (X uno 0) | (Y uno 0) as a canonicalization, but that would be another patch. Differential Revision: https://reviews.llvm.org/D40130 llvm-svn: 318627 |
||
|---|---|---|
| .. | ||
| 2010-12-20-Boolean.ll | ||
| 2011-01-14-Thread.ll | ||
| 2011-02-01-Vector.ll | ||
| 2011-09-05-InsertExtractValue.ll | ||
| 2011-10-27-BinOpCrash.ll | ||
| 2011-11-23-MaskedBitsCrash.ll | ||
| 2013-04-19-ConstantFoldingCrash.ll | ||
| AndOrXor.ll | ||
| add-mask.ll | ||
| addsub.ll | ||
| and-icmps-same-ops.ll | ||
| assume.ll | ||
| bitcast-vector-fold.ll | ||
| bitreverse.ll | ||
| bswap.ll | ||
| call-callconv.ll | ||
| call.ll | ||
| cast.ll | ||
| compare.ll | ||
| dead-code-removal.ll | ||
| div.ll | ||
| exact-nsw-nuw.ll | ||
| fast-math.ll | ||
| fdiv.ll | ||
| floating-point-arithmetic.ll | ||
| floating-point-compare.ll | ||
| fold-builtin-fma.ll | ||
| gep.ll | ||
| icmp-bool-constant.ll | ||
| icmp-constant.ll | ||
| icmp-ranges.ll | ||
| implies.ll | ||
| load-relative-32.ll | ||
| load-relative.ll | ||
| load.ll | ||
| logic-of-fcmps.ll | ||
| maxmin.ll | ||
| mul.ll | ||
| negate.ll | ||
| noalias-ptr.ll | ||
| or-icmps-same-ops.ll | ||
| or.ll | ||
| past-the-end.ll | ||
| phi.ll | ||
| pr28725.ll | ||
| pr33957.ll | ||
| ptr_diff.ll | ||
| reassociate.ll | ||
| rem.ll | ||
| require-dominator.ll | ||
| returned.ll | ||
| select.ll | ||
| shift-128-kb.ll | ||
| shift-knownbits.ll | ||
| shr-nop.ll | ||
| shufflevector.ll | ||
| signed-div-rem.ll | ||
| simplify-nested-bitcast.ll | ||
| undef.ll | ||
| vec-cmp.ll | ||
| vector_gep.ll | ||
| vector_ptr_bitcast.ll | ||