Re: [apache/tvm] [pre-RFC][BYOC] Marvell ML/AI Accelerator Integration (PR #9730)

2021-12-14 Thread Joe Chou
Hello @jroesch, After done more self-discovery from reviewing other BYOC code files and CMake setup files, I think now I am aware of that, in the Mrvl.cmake file, the source file lists for libtvm_runtime.so (e.g., RUNTIME_SRCS) and for libtvm.so (e.g., COMPILER_SRCS) need to be separated. I have

Re: [apache/tvm-rfcs] [RFC][TIR] Layout transformations on buffer access (#39)

2021-12-14 Thread Wuwei Lin
@wrongtest I'm working on the TensorIR side and have a draft version of `transform_layout`. The current implementation is ```void TransformLayout(ScheduleState self, const StmtSRef& block_sref, int buffer_index, bool is_write_index, const IndexMap& index_map);``` It applies the mapping function

Re: [apache/tvm-rfcs] [RFC][TIR] Layout transformations on buffer access (#39)

2021-12-14 Thread wrongtest
@Lunderberg Hi, I am much interested in `transform_layout` but my team depends totally on TensorIR schedule instead of TE. Could you kindly provide more design points on TensorIR side? It would be great if we can enjoy this preview feature in TensorIR. It is really useful for us. We have imp