DzAvril opened a new pull request #10801:
URL: https://github.com/apache/tvm/pull/10801
The input of op `concatenate` is a list of tensors. We tried to bring it to
ACL and found the JSON node of it is like below.
```JSON
{
"nodes": [
{
"op": "input",
"name": "arm_compute_lib_0_i0",
"attrs": {
"dtype": [
[
"int32",
"int32",
"int32"
]
],
"shape": [
[
[1, 234, 234, 256],
[1, 234, 234, 256],
[1, 234, 234, 256]
]
]
}
},
{
"op": "kernel",
"name": "concatenate",
"inputs": [[
0,
0,
0], [
0,
1,
0], [
0,
2,
0]],
"attrs": {
"num_outputs": "1",
"num_inputs": "3",
"dtype": [
[
"int32"
]
],
"axis": [
[
"0"
]
],
"shape": [
[
[3, 234, 234, 256]
]
]
}
}
],
"arg_nodes": [0],
"heads": [[
1,
0,
0]],
"node_row_ptr": [0, 3, 4]
}
```
The inputs of node `kernel` is:
```JSON
"inputs": [[
0,
0,
0], [
0,
1,
0], [
0,
2,
0]]
```
Element in `inputs` is the index of `input` node. Taking `[0, 1, 0]` as an
example, the first `0` is `nodeid`, the second `1` is `indexid`, and the last
`0` is `version`.
But in function `Run`, it only uses `0` as `indexid` in statement `uint32_t
eid = EntryID(nid, 0);` so the other two inputs are ignored.
```c++
void Run() override {
for (size_t i = 0; i < input_nodes_.size(); ++i) {
auto nid = input_nodes_[i];
uint32_t eid = EntryID(nid, 0);
if (nodes_[nid].GetOpType() == "input") {
void* data = data_entry_[eid]->data;
CheckACLError(layer_.inputs[i].allocator()->import_memory(data));
}
}
for (size_t i = 0; i < outputs_.size(); ++i) {
uint32_t eid = EntryID(outputs_[i]);
void* data = data_entry_[eid]->data;
CheckACLError(layer_.outputs[i].allocator()->import_memory(data));
}
this->layer_.function->run();
}
```
This PR introduces a variable `json_inputid_to_layer_inputid` which maps the
input index of JSON node to the index of the ACL layer's inputs.
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
