[Apache TVM Discuss] [Questions] Modifying weight parameters in OpStrategy

2020-09-21 Thread Tristan Konolige via Apache TVM Discuss
@haichen, I'm trying this, but the alter_op_layout is never called because the layouts appear to be invalid. Specifically, this line https://github.com/apache/incubator-tvm/blob/master/src/relay/transforms/transform_layout.h#L285-L286 always returns `success=false`. I tried adding the `Elemwis

[Apache TVM Discuss] [Questions] Modifying weight parameters in OpStrategy

2020-09-17 Thread Haichen Shen via Apache TVM Discuss
In this case, you can it in the op alter layout. You can check out the example from https://github.com/apache/incubator-tvm/blob/master/python/tvm/topi/x86/conv2d_alter_op.py#L40. --- [Visit Topic](https://discuss.tvm.apache.org/t/modifying-weight-parameters-in-opstrategy/7914/2) to resp

[Apache TVM Discuss] [Questions] Modifying weight parameters in OpStrategy

2020-09-15 Thread Tristan Konolige via Apache TVM Discuss
I'm working on improving the current `sparse_dense` kernels on the GPU. I have a performant implementation, but it requires modification of the input sparse matrix to make it more amenable to the GPU (I have been doing this modification at compile time as the input sparse matrix is always a st