effb22e8a44763901ee2cf55c30290f0b1edb570 |
|
10-Oct-2017 |
Sanjoy Das <sanjoy@google.com> |
Use an external constant pool to reduce LLVM compile times LLVM does not deal well with huge arrays emitted inline into the IR. In JIT mode, this change teaches XLA to emit large constant tensors onto a side data structure, which are then symbolically linked to the generated executable. It is important to note that this works only in JIT mode, and my current understanding is that making this work reliably in AOT will be somewhat more difficult. PiperOrigin-RevId: 171626043
/external/tensorflow/tensorflow/compiler/xla/service/cpu/external_constant_pool.h
|