forked from OSchip/llvm-project
86e9bc1a34
Controlled by a compiler option, if 32-bit indices can be handled with zero/sign-extention alike (viz. no worries on non-negative indices), scatter/gather operations can use the more efficient 32-bit SIMD version. Reviewed By: bixia Differential Revision: https://reviews.llvm.org/D103632 |
||
---|---|---|
.. | ||
mlir | ||
mlir-c |