OP 実装を C++ で作成する - 2.5 日本語

// in my_add_op.cpp
class MyAddOp {
};

#include <vart/op_imp.h>

class MyAddOp {
    MyAddOp(const xir::Op* op1, xir::Attrs* attrs) : op{op1} {
      // op and attrs is not in use.
}
public:
    const xir::Op * const op;
};

class MyAddOp {
  ...
  int calculate(vart::simple_tensor_buffer_t output,
                std::vector<vart::simple_tensor_buffer_t<float>> inputs) {
    for (auto i = 0u; i < output.mem_size / sizeof(float); ++i) {
      output.data[i] = 0.0f;
      for (auto input : inputs) {
        output.data[i] = output.data[i] + input.data[i];
      }
    }
    return 0;
  }
...
}

% g++ -fPIC -std=c++17 -c -o  /tmp/my_add_op.o -Wall -Werror -I ~/.local/Ubuntu.18.04.x86_64.Debug/include/ my_add_op.cpp

% mkdir -p /tmp/lib;
% g++ -Wl,--no-undefined -shared -o /tmp/lib/libvart_op_imp_add.so /tmp/my_add_op.o -L ~/.local/Ubuntu.18.04.x86_64.Debug/lib -lglog -lvitis_ai_library-runner_helper -lvart-runner -lxir

Makefile を使用してライブラリのコンパイルとリンクを実行することもできます。次のコード スニペットに、makefile の例を示します。

OUTPUT_DIR = $(HOME)/build/customer_op

all: $(OUTPUT_DIR) $(OUTPUT_DIR)/libvart_op_imp_add.so

$(OUTPUT_DIR):
    mkdir -p $@

$(OUTPUT_DIR)/my_add_op.o: my_add_op.cpp
    $(CXX) -std=c++17 -fPIC -c -o $@ -I. -I=/install/Debug/include -Wall  -U_FORTIFY_SOURCE -D_FORTIFY_SOURCE=0 $<

$(OUTPUT_DIR)/libvart_op_imp_add.so:  $(OUTPUT_DIR)/my_add_op.o
    $(CXX) -Wl,--no-undefined -shared -o $@ $+ -L=/install/Debug/lib  -lglog -lvitis_ai_library-runner_helper -lvart-runner -lxir

% ipython;
import xir
g = xir.Graph("simple_graph")
a = g.create_op("a", "data", {"shape": [1,2,2,4], "data_type": "FLOAT32"});
b = g.create_op("b", "data", {"shape": [1,2,2,4], "data_type": "FLOAT32"});
add = g.create_op("add_op", "add",  {"shape": [1,2,2,4], "data_type": "FLOAT32"}, {"input": [a,b]})
root = g.get_root_subgraph()
root.create_child_subgraph()
user_subgraph = root.merge_children(set([g.get_leaf_subgraph(a), g.get_leaf_subgraph(b)]))
cpu_subgraph = root.merge_children(set([g.get_leaf_subgraph(add)]))
user_subgraph.set_attr("device", "USER")
cpu_subgraph.set_attr("device", "CPU")
g.serialize("/tmp/add.xmodel")

% cd /tmp
% mkdir -p ref
% ipython
import numpy as np
a = np.arange(1, 17, dtype=np.float32)
b = np.arange(1, 17, dtype=np.float32)
a.tofile("ref/a.bin")
b.tofile("ref/b.bin")
c = a + b
c.tofile("ref/c.bin")

% cd /tmp
% mkdir -p /tmp/dump
% env LD_LIBRARY_PATH=$HOME/.local/Ubuntu.18.04.x86_64.Debug/lib:/tmp/lib $HOME/.local/Ubuntu.18.04.x86_64.Debug/share/vitis_ai_library/test/cpu_task/test_op_imp --graph /tmp/add.xmodel --op "add_op"

xdputil run_op を使用して op を検証することもできます。

root@xilinx-zcu102-2021_2:~/add_op# xdputil run_op add.xmodel add_op -r ref -d dump
WARNING: Logging before InitGoogleLogging() is written to STDERR
I1202 09:32:41.497661  1208 test_op_run.cpp:79] try to test op: add_op
I1202 09:32:41.497745  1208 test_op_run.cpp:97]  input op: a tensor: a
I1202 09:32:41.497768  1208 test_op_run.cpp:97]  input op: b tensor: b
I1202 09:32:41.497865  1208 test_op_run.cpp:55] read ref/a.bin to 0xaaab17d605d0 size=64
I1202 09:32:41.497917  1208 test_op_run.cpp:55] read ref/b.bin to 0xaaab17c549b0 size=64
I1202 09:32:41.498561  1208 test_op_run.cpp:114] graph name:simple_graphtesting op: {
    {args: input= TensorBuffer{@0xaaab17ba9b90,tensor=xir::Tensor{name = a, type = FLOAT32, shape = {1, 2, 2, 4}},location=HOST_VIRT,data=[(Virt=0xaaab17d605d0, 64)]} TensorBuffer{@0xaaab17e2a860,tensor=xir::Tensor{name = b, type = FLOAT32, shape = {1, 2, 2, 4}},location=HOST_VIRT,data=[(Virt=0xaaab17c549b0, 64)]}}
{
I1202 09:32:41.499586  1208 test_op_run.cpp:68] write output to dump/add_op.bin from 0xaaab17de7090 size=64
test pass

% diff -u <(xxd ref/c.bin) <(xxd dump/add_op.bin)
% xxd ref/c.bin
% xxd dump/add_op.bin