forked from OSchip/llvm-project
3ceac2bbd5
Shifts with a uniform but non-constant count were considered very expensive to vectorize, because the splat of the uniform count and the shift would tend to appear in different blocks. That made the splat invisible to ISel, and we'd scalarize the shift at codegen time. Since r201655, CodeGenPrepare sinks those splats to be next to their use, and we are able to select the appropriate vector shifts. This updates the cost model to to take this into account by making shifts by a uniform cheap again. Differential Revision: https://reviews.llvm.org/D23049 llvm-svn: 277782 |
||
|---|---|---|
| .. | ||
| already-vectorized.ll | ||
| assume.ll | ||
| avx1.ll | ||
| avx512.ll | ||
| constant-vector-operand.ll | ||
| conversion-cost.ll | ||
| cost-model.ll | ||
| float-induction-x86.ll | ||
| force-ifcvt.ll | ||
| fp32_to_uint32-cost-model.ll | ||
| fp64_to_uint32-cost-model.ll | ||
| fp_to_sint8-cost-model.ll | ||
| funclet.ll | ||
| gather-cost.ll | ||
| gather_scatter.ll | ||
| gcc-examples.ll | ||
| illegal-parallel-loop-uniform-write.ll | ||
| imprecise-through-phis.ll | ||
| int128_no_gather.ll | ||
| lit.local.cfg | ||
| masked_load_store.ll | ||
| max-mstore.ll | ||
| metadata-enable.ll | ||
| min-trip-count-switch.ll | ||
| no-vector.ll | ||
| no_fpmath.ll | ||
| no_fpmath_with_hotness.ll | ||
| parallel-loops-after-reg2mem.ll | ||
| parallel-loops.ll | ||
| powof2div.ll | ||
| propagate-metadata.ll | ||
| ptr-indvar-crash.ll | ||
| rauw-bug.ll | ||
| reduction-crash.ll | ||
| reg-usage.ll | ||
| register-assumption.ll | ||
| scatter_crash.ll | ||
| small-size.ll | ||
| struct-store.ll | ||
| svml-calls.ll | ||
| tripcount.ll | ||
| uint64_to_fp64-cost-model.ll | ||
| uniform-phi.ll | ||
| uniform_load.ll | ||
| uniformshift.ll | ||
| unroll-pm.ll | ||
| unroll-small-loops.ll | ||
| unroll_selection.ll | ||
| veclib-calls.ll | ||
| vect.omp.force.ll | ||
| vect.omp.force.small-tc.ll | ||
| vector-scalar-select-cost.ll | ||
| vector_max_bandwidth.ll | ||
| vector_ptr_load_store.ll | ||
| vectorization-remarks-loopid-dbg.ll | ||
| vectorization-remarks-missed.ll | ||
| vectorization-remarks-profitable.ll | ||
| vectorization-remarks.ll | ||
| vectorize-only-for-real.ll | ||
| x86_fp80-vector-store.ll | ||