forked from OSchip/llvm-project
f24900b934
The transform performs a bitwise logic op in a wider type followed by truncate when both inputs are truncated from the same source type: logic_op (truncate x), (truncate y) --> truncate (logic_op x, y) There are a bunch of other checks that should prevent doing this when it might be harmful. We already do this transform for scalars in this spot. The vector limitation was shared with a check for the case when the operands are extended. I'm not sure if that limit is needed either, but that would be a separate patch. Differential Revision: https://reviews.llvm.org/D55448 llvm-svn: 349303 |
||
|---|---|---|
| .. | ||
| align-64b.ll | ||
| align-128b.ll | ||
| align2-64b.ll | ||
| align2-128b.ll | ||
| arith.ll | ||
| bitcount-64b.ll | ||
| bitcount-128b.ll | ||
| bitwise-pred-64b.ll | ||
| bitwise-pred-128b.ll | ||
| bswap.ll | ||
| build-vector-i32-type.ll | ||
| concat-vectors-64b.ll | ||
| concat-vectors-128b.ll | ||
| contract-64b.ll | ||
| contract-128b.ll | ||
| ctpop-split.ll | ||
| deal-64b.ll | ||
| deal-128b.ll | ||
| delta-64b.ll | ||
| delta-128b.ll | ||
| delta2-64b.ll | ||
| extract-element.ll | ||
| float-cost.ll | ||
| interleave.ll | ||
| isel-anyext-inreg.ll | ||
| isel-anyext-pair.ll | ||
| isel-bitcast-vsplat.ll | ||
| isel-bitcast-vsplat2.ll | ||
| isel-bool-vector.ll | ||
| isel-build-undef.ll | ||
| isel-concat-multiple.ll | ||
| isel-concat-vectors-bool.ll | ||
| isel-concat-vectors.ll | ||
| isel-const-splat-bitcast.ll | ||
| isel-const-splat.ll | ||
| isel-const-vector.ll | ||
| isel-expand-unaligned-loads-noindexed.ll | ||
| isel-expand-unaligned-loads.ll | ||
| isel-extractelt-illegal-type.ll | ||
| isel-qfalse.ll | ||
| isel-select-const.ll | ||
| isel-setcc-pair.ll | ||
| isel-sext-inreg.ll | ||
| isel-shift-byte.ll | ||
| isel-shuffle-gather.ll | ||
| isel-shuffle-pack.ll | ||
| isel-truncate.ll | ||
| isel-vec-ext.ll | ||
| isel-vsplat-pair.ll | ||
| lower-insert-elt.ll | ||
| maximize-bandwidth.ll | ||
| perfect-single.ll | ||
| reg-sequence.ll | ||
| shift-64b.ll | ||
| shift-128b.ll | ||
| shuff-64b.ll | ||
| shuff-128b.ll | ||
| shuff-combos-64b.ll | ||
| shuff-combos-128b.ll | ||
| shuff-single.ll | ||
| vdd0.ll | ||
| vector-compare-64b.ll | ||
| vector-compare-128b.ll | ||
| vext-64b.ll | ||
| vext-128b.ll | ||
| vmux-order.ll | ||