llvm-project/llvm/test/Transforms/VectorCombine
Sanjay Patel 48a23bccf3 [VectorCombine] limit load+insert transform to one-use
As discussed in:
https://llvm.org/PR47558
...there are several potential fixes/follow-ups visible
in the test case, but this is the quickest and safest
fix of the perf regression.
2020-09-17 14:29:15 -04:00
..
AArch64 [VectorCombine][SVE] Do not fold bitcast shuffle for scalable type. 2020-09-02 15:02:16 -07:00
Hexagon [VectorCombine] add test for Hexagon that would crash; NFC 2020-08-12 08:38:20 -04:00
X86 [VectorCombine] limit load+insert transform to one-use 2020-09-17 14:29:15 -04:00