+-----------------------------------------------------------------------------+
| NVIDIA-SMI 520.61.05 Driver Version: 520.61.05 CUDA Version: 11.8 |
|-------------------------------+----------------------+----------------------+
| GPU Name Persistence-M| Bus-Id Disp.A | Volatile Uncorr. ECC |
| Fan Temp Perf Pwr:Usage/Cap| Memory-Usage | GPU-Util Compute M. |
| | | MIG M. |
|===============================+======================+======================|
| 0 Tesla V100-SXM2... Off | 00000000:1A:00.0 Off | 0 |
| N/A 35C P0 56W / 300W | 1479MiB / 32768MiB | 0% Default |
| | | N/A |
+-------------------------------+----------------------+----------------------+
| 1 Tesla V100-SXM2... Off | 00000000:3D:00.0 Off | 0 |
| N/A 50C P0 71W / 300W | 4333MiB / 32768MiB | 69% Default |
| | | N/A |
+-------------------------------+----------------------+----------------------+
| 2 Tesla V100-SXM2... Off | 00000000:89:00.0 Off | 0 |
| N/A 29C P0 39W / 300W | 2MiB / 32768MiB | 0% Default |
| | | N/A |
+-------------------------------+----------------------+----------------------+
| 3 Tesla V100-SXM2... Off | 00000000:B2:00.0 Off | 0 |
| N/A 29C P0 38W / 300W | 3MiB / 32768MiB | 0% Default |
| | | N/A |
+-------------------------------+----------------------+----------------------+
(base) wurui@node10:~/wurui/experiment$ nvcc -V
nvcc: NVIDIA (R) Cuda compiler driver
Copyright (c) 2005-2021 NVIDIA Corporation
Built on Sun_Mar_21_19:15:46_PDT_2021
Cuda compilation tools, release 11.3, V11.3.58
Build cuda_11.3.r11.3/compiler.29745058_0
(base) wurui@node10:~/wurui/experiment$ gcc -v
Using built-in specs.
COLLECT_GCC=gcc
COLLECT_LTO_WRAPPER=/mnt/7T/lly/gcc-7.5.0/libexec/gcc/x86_64-pc-linux-gnu/7.5.0/lto-wrapper
Target: x86_64-pc-linux-gnu
Configured with: ../configure --disable-checking --enable-languages=c,c++ --disable-multilib --prefix=/mnt/7T/lly/gcc-7.5.0 --enable-threads=posix
Thread model: posix
gcc version 7.5.0 (GCC)
pytorch 1.11.0 py3.8_cuda11.3_cudnn8.2.0_0 pytorch
following is the code structure
|-- TCGNN_kernel.cu
|-- TCGNN.cpp
|-- setup.py
following is the code:
// TCGNN_kernel.cu
#include <torch/extension.h>
#include <stdio.h>
#include <vector>
#include <iostream>
#include <thrust/device_vector.h>
#include <thrust/sort.h>
#include <cuda_fp16.h>
#include <cuda.h>
#include <mma.h>
#include <cuda_runtime.h>
#include "config.h"
#define WPB 8
using namespace std;
using namespace nvcuda;
std::vector<torch::Tensor> spmm_forward_cuda(
torch::Tensor nodePointer,
torch::Tensor edgeList,
torch::Tensor blockPartition,
torch::Tensor edgeToColumn,
torch::Tensor edgeToRow,
int num_nodes,
int num_edges,
int embedding_dim,
torch::Tensor input
)
{
auto output = torch::zeros_like(input);
const int num_row_windows = blockPartition.size(0);
const int WARPperBlock = WPB;
dim3 grid(num_row_windows, 1, 1);
dim3 block(WARP_SIZE, WARPperBlock, 1);
const int dimTileNum = (embedding_dim + BLK_H - 1) / BLK_H;
const int dynamic_shared_size = dimTileNum * BLK_W * BLK_H * sizeof(float); // dynamic shared memory.
printf("break2\n");
spmm_forward_cuda_kernel<<<grid, block, dynamic_shared_size>>>(
nodePointer.data<int>(),
edgeList.data<int>(),
blockPartition.data<int>(),
edgeToColumn.data<int>(),
edgeToRow.data<int>(),
num_nodes,
num_edges,
embedding_dim,
input.data<float>(),
output.data<float>()
);
printf("break10\n");
// check for error
cudaError_t error = cudaGetLastError();
if(error != cudaSuccess)
{
// print the CUDA error message and exit
printf("CUDA error: %s\n", cudaGetErrorString(error));
exit(-1);
}
return {output};
}
__global__ void spmm_forward_cuda_kernel(
const int * __restrict__ nodePointer, // node pointer.
const int *__restrict__ edgeList, // edge list.
const int *__restrict__ blockPartition, // number of TC_blocks (16x8) in each row_window.
const int *__restrict__ edgeToColumn, // eid -> col within each row_window.
const int *__restrict__ edgeToRow, // eid -> col within each row_window.
const int numNodes,
const int numEdges,
const int embedding_dim, // embedding dimension.
const float *__restrict__ input, // input feature matrix.
float *output // aggreAGNNed output feature matrix.
) {
const unsigned bid = blockIdx.x; // block_index == row_window_index
const unsigned wid = threadIdx.y; // warp_index handling multi-dimension > 16.
const unsigned laneid = threadIdx.x; // lanid of each warp.
const unsigned tid = threadIdx.y * blockDim.x + laneid; // threadid of each block.
const unsigned warpSize = blockDim.x; // number of threads per warp.
const unsigned threadPerBlock = blockDim.x * blockDim.y; // number of threads per block.
if(bid == 0 && tid == 0) printf("break3\n");
const unsigned dimTileNum = embedding_dim / BLK_H; // number of tiles along the dimension
const unsigned nIdx_start = bid * BLK_H; // starting nodeIdx of current row_window.
const unsigned nIdx_end = min((bid + 1) * BLK_H, numNodes); // ending nodeIdx of current row_window.
const unsigned eIdx_start = nodePointer[nIdx_start]; // starting edgeIdx of current row_window.
const unsigned eIdx_end = nodePointer[nIdx_end]; // ending edgeIdx of the current row_window.
const unsigned num_TC_blocks = blockPartition[bid]; // number of TC_blocks of the current row_window.
const unsigned dense_bound = numNodes * embedding_dim;
printf("break4\n");
__shared__ float sparse_A[BLK_H * BLK_W]; // row-major sparse matrix shared memory store.
__shared__ int sparse_AToX_index[BLK_W]; // TC_block col to dense_tile row.
// __shared__ float dense_X[dimTileNum * BLK_W * BLK_H]; // column-major dense tile [dimTileNum, BLK_W, BLK_H]
extern __shared__ float dense_X[];
nvcuda::wmma::fragment<nvcuda::wmma::matrix_a, BLK_H, BLK_H, BLK_W, nvcuda::wmma::precision::tf32, nvcuda::wmma::row_major> a_frag;
wmma::fragment<wmma::matrix_b, BLK_H, BLK_H, BLK_W, wmma::precision::tf32, wmma::col_major> b_frag;
wmma::fragment<wmma::accumulator, BLK_H, BLK_H, BLK_W, float> acc_frag;
wmma::fill_fragment(acc_frag, 0.0f);
printf("break5\n");
// Processing TC_blocks along the column dimension of Sparse A.
for (unsigned i = 0; i < num_TC_blocks; i++){
// Init A_colToX_row with dummy values.
if (tid < BLK_W){
sparse_AToX_index[tid] = numNodes + 1;
}
__syncthreads();
// Init sparse_A with zero values.
#pragma unroll
for (unsigned idx = tid; idx < BLK_W * BLK_H; idx += threadPerBlock){
sparse_A[idx] = 0;
}
// Init dense_X with zero values.
#pragma unroll
for (unsigned idx = tid; idx < dimTileNum * BLK_W * BLK_H; idx += threadPerBlock){
dense_X[idx] = 0;
}
// Initialize sparse_A by using BLK_H (16) threads from the warp-0.
// currently fetch all neighbors of the current nodes.
// then to see whether it can fit into current TC_block frame of column.
#pragma unroll
for (unsigned eIdx = eIdx_start + tid; eIdx < eIdx_end; eIdx += threadPerBlock){
unsigned col = edgeToColumn[eIdx];
if (i * BLK_W <= col && col < (i + 1) * BLK_W){ // if the edge in the current TC_block frame of column.
unsigned row_local = edgeToRow[eIdx] % BLK_H;
unsigned col_local = col % BLK_W;
sparse_A[row_local * BLK_W + col_local] = 1; // set the edge of the sparse_A.
sparse_AToX_index[col_local] = edgeList[eIdx]; // record the mapping from sparse_A colId to rowId of dense_X.
}
}
__syncthreads();
// Initialize dense_X by column-major store,
// Threads of a warp for fetching a dense_X.
// each warp identify by wid.
if (wid < dimTileNum)
#pragma unroll
for (unsigned idx = laneid; idx < BLK_W * BLK_H; idx += warpSize){
unsigned dense_rowIdx = sparse_AToX_index[idx % BLK_W]; // TC_block_col to dense_tile_row.
unsigned dense_dimIdx = idx / BLK_W; // dimIndex of the dense tile.
unsigned source_idx = dense_rowIdx * embedding_dim + wid * BLK_H + dense_dimIdx;
unsigned target_idx = wid * BLK_W * BLK_H + idx;
// boundary test.
if (source_idx >= dense_bound)
dense_X[target_idx] = 0;
else
dense_X[target_idx] = input[source_idx];
}
__syncthreads();
if (wid < dimTileNum)
{
wmma::load_matrix_sync(a_frag, sparse_A, BLK_W);
wmma::load_matrix_sync(b_frag, dense_X + wid * BLK_W * BLK_H, BLK_W);
#pragma unroll
for (unsigned t = 0; t < a_frag.num_elements; t++) {
a_frag.x[t] = wmma::__float_to_tf32(a_frag.x[t]);
}
#pragma unroll
for (unsigned t = 0; t < b_frag.num_elements; t++) {
b_frag.x[t] = wmma::__float_to_tf32(b_frag.x[t]);
}
// Perform the matrix multiplication.
wmma::mma_sync(acc_frag, a_frag, b_frag, acc_frag);
}
}
if (wid < dimTileNum)
// Store the matrix to output matrix.
// * Note * embeeding dimension should be padded divisible by BLK_H for output correctness.
wmma::store_matrix_sync(output + bid * BLK_H * embedding_dim + wid * BLK_H, acc_frag, embedding_dim, wmma::mem_row_major);
}
setup.py like below:
import torch
from setuptools import setup
from torch.utils.cpp_extension import BuildExtension, CUDAExtension
setup(
name='TCGNN',
ext_modules=[
CUDAExtension('TCGNN', [
'TCGNN.cpp',
'TCGNN_kernel.cu',
], extra_compile_args={'cxx': cxx_args, 'nvcc': nvcc_args})
],
cmdclass={
'build_ext': BuildExtension
})
but when I run the command: python setup.py install, I get the error like error: name followed by "::" must be a class or namespace name no instance of function template "nvcuda::wmma::fill_fragment" matches the argument list argument types are: (<error-type>, float
(tcgnn) liyang@node10:~/ly/experiment$ python setup.py install
running install
/mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/setuptools/command/install.py:34: SetuptoolsDeprecationWarning: setup.py install is deprecated. Use build and pip and other standards-based tools.
warnings.warn(
/mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/setuptools/command/easy_install.py:156: EasyInstallDeprecationWarning: easy_install command is deprecated. Use build and pip and other standards-based tools.
warnings.warn(
running bdist_egg
running egg_info
creating TCGNN.egg-info
writing manifest file 'TCGNN.egg-info/SOURCES.txt'
writing manifest file 'TCGNN.egg-info/SOURCES.txt'
running install_lib
running build_ext
creating /home/liyang/ly/experiment/build
creating /home/liyang/ly/experiment/build/temp.linux-x86_64-3.8
Emitting ninja build file /home/liyang/ly/experiment/build/temp.linux-x86_64-3.8/build.ninja...
Compiling objects...
Allowing ninja to set a default number of workers... (overridable by setting the environment variable MAX_JOBS=N)
[1/2] /usr/local/cuda-11.3/bin/nvcc -I/mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/torch/include -I/mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/torch/include/torch/csrc/api/include -I/mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/torch/include/TH -I/mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/torch/include/THC -I/usr/local/cuda-11.3/include -I/mnt/7T/lly/anaconda3/envs/tcgnn/include/python3.8 -c -c /home/liyang/ly/experiment/TCGNN_kernel.cu -o /home/liyang/ly/experiment/build/temp.linux-x86_64-3.8/TCGNN_kernel.o -D__CUDA_NO_HALF_OPERATORS__ -D__CUDA_NO_HALF_CONVERSIONS__ -D__CUDA_NO_BFLOAT16_CONVERSIONS__ -D__CUDA_NO_HALF2_OPERATORS__ --expt-relaxed-constexpr --compiler-options ''"'"'-fPIC'"'"'' -DTORCH_API_INCLUDE_EXTENSION_H '-DPYBIND11_COMPILER_TYPE="_gcc"' '-DPYBIND11_STDLIB="_libstdcpp"' '-DPYBIND11_BUILD_ABI="_cxxabi1011"' -DTORCH_EXTENSION_NAME=TCGNN -D_GLIBCXX_USE_CXX11_ABI=0 -gencode=arch=compute_70,code=compute_70 -gencode=arch=compute_70,code=sm_70 -std=c++14
FAILED: /home/liyang/ly/experiment/build/temp.linux-x86_64-3.8/TCGNN_kernel.o
/usr/local/cuda-11.3/bin/nvcc -I/mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/torch/include -I/mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/torch/include/torch/csrc/api/include -I/mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/torch/include/TH -I/mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/torch/include/THC -I/usr/local/cuda-11.3/include -I/mnt/7T/lly/anaconda3/envs/tcgnn/include/python3.8 -c -c /home/liyang/ly/experiment/TCGNN_kernel.cu -o /home/liyang/ly/experiment/build/temp.linux-x86_64-3.8/TCGNN_kernel.o -D__CUDA_NO_HALF_OPERATORS__ -D__CUDA_NO_HALF_CONVERSIONS__ -D__CUDA_NO_BFLOAT16_CONVERSIONS__ -D__CUDA_NO_HALF2_OPERATORS__ --expt-relaxed-constexpr --compiler-options ''"'"'-fPIC'"'"'' -DTORCH_API_INCLUDE_EXTENSION_H '-DPYBIND11_COMPILER_TYPE="_gcc"' '-DPYBIND11_STDLIB="_libstdcpp"' '-DPYBIND11_BUILD_ABI="_cxxabi1011"' -DTORCH_EXTENSION_NAME=TCGNN -D_GLIBCXX_USE_CXX11_ABI=0 -gencode=arch=compute_70,code=compute_70 -gencode=arch=compute_70,code=sm_70 -std=c++14
/home/liyang/ly/experiment/TCGNN_kernel.cu(127): error: name followed by "::" must be a class or namespace name
/home/liyang/ly/experiment/TCGNN_kernel.cu(127): error: incomplete type is not allowed
/home/liyang/ly/experiment/TCGNN_kernel.cu(128): error: name followed by "::" must be a class or namespace name
/home/liyang/ly/experiment/TCGNN_kernel.cu(128): error: incomplete type is not allowed
/home/liyang/ly/experiment/TCGNN_kernel.cu(129): error: incomplete type is not allowed
/home/liyang/ly/experiment/TCGNN_kernel.cu(130): error: no instance of function template "nvcuda::wmma::fill_fragment" matches the argument list
argument types are: (<error-type>, float)
/home/liyang/ly/experiment/TCGNN_kernel.cu(191): error: no instance of overloaded function "nvcuda::wmma::load_matrix_sync" matches the argument list
argument types are: (<error-type>, float [128], int)
/home/liyang/ly/experiment/TCGNN_kernel.cu(192): error: no instance of overloaded function "nvcuda::wmma::load_matrix_sync" matches the argument list
argument types are: (<error-type>, float *, int)
/home/liyang/ly/experiment/TCGNN_kernel.cu(196): error: namespace "nvcuda::wmma" has no member "__float_to_tf32"
/home/liyang/ly/experiment/TCGNN_kernel.cu(201): error: namespace "nvcuda::wmma" has no member "__float_to_tf32"
10 errors detected in the compilation of "/home/liyang/ly/experiment/TCGNN_kernel.cu".
[2/2] c++ -MMD -MF /home/liyang/ly/experiment/build/temp.linux-x86_64-3.8/TCGNN.o.d -pthread -B /mnt/7T/lly/anaconda3/envs/tcgnn/compiler_compat -Wl,--sysroot=/ -Wsign-compare -DNDEBUG -g -fwrapv -O3 -Wall -Wstrict-prototypes -fPIC -I/mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/torch/include -I/mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/torch/include/torch/csrc/api/include -I/mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/torch/include/TH -I/mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/torch/include/THC -I/usr/local/cuda-11.3/include -I/mnt/7T/lly/anaconda3/envs/tcgnn/include/python3.8 -c -c /home/liyang/ly/experiment/TCGNN.cpp -o /home/liyang/ly/experiment/build/temp.linux-x86_64-3.8/TCGNN.o -DTORCH_API_INCLUDE_EXTENSION_H '-DPYBIND11_COMPILER_TYPE="_gcc"' '-DPYBIND11_STDLIB="_libstdcpp"' '-DPYBIND11_BUILD_ABI="_cxxabi1011"' -DTORCH_EXTENSION_NAME=TCGNN -D_GLIBCXX_USE_CXX11_ABI=0 -std=c++14
cc1plus: warning: command line option ‘-Wstrict-prototypes’ is valid for C/ObjC but not for C++
/home/liyang/ly/experiment/TCGNN.cpp:103:0: warning: ignoring #pragma omp parallel [-Wunknown-pragmas]
#pragma omp parallel for
/home/liyang/ly/experiment/TCGNN.cpp:109:0: warning: ignoring #pragma omp parallel [-Wunknown-pragmas]
#pragma omp parallel for reduction(+:block_counter)
In file included from /mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/torch/include/c10/core/DeviceType.h:8:0,
from /mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/torch/include/c10/core/Device.h:3,
from /mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/torch/include/c10/core/Allocator.h:6,
from /mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/torch/include/ATen/ATen.h:7,
from /mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/types.h:3,
from /mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader_options.h:4,
from /mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/base.h:3,
from /mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/stateful.h:3,
from /mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader.h:3,
from /mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data.h:3,
from /mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/all.h:8,
from /mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/torch/include/torch/extension.h:4,
from /home/liyang/ly/experiment/TCGNN.cpp:1:
/home/liyang/ly/experiment/TCGNN.cpp: In function ‘std::vector<at::Tensor> spmm_forward(at::Tensor, at::Tensor, at::Tensor, at::Tensor, at::Tensor, at::Tensor)’:
/home/liyang/ly/experiment/TCGNN.cpp:27:42: warning: ‘at::DeprecatedTypeProperties& at::Tensor::type() const’ is deprecated: Tensor.type() is deprecated. Instead use Tensor.options(), which in many cases (e.g. in a constructor) is a drop-in replacement. If you were using data from type(), that is now available from Tensor itself, so instead of tensor.type().scalar_type(), use tensor.scalar_type() instead and instead of tensor.type().backend() use tensor.device(). [-Wdeprecated-declarations]
#define CHECK_CUDA(x) TORCH_CHECK(x.type().is_cuda(), #x " must be a CUDA tensor")
^
/mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/torch/include/c10/macros/Macros.h:204:64: note: in definition of macro ‘C10_UNLIKELY’
#define C10_UNLIKELY(expr) (__builtin_expect(static_cast<bool>(expr), 0))
^~~~
/mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/torch/include/c10/util/Exception.h:460:7: note: in expansion of macro ‘C10_UNLIKELY_OR_CONST’
if (C10_UNLIKELY_OR_CONST(!(cond))) { \
^~~~~~~~~~~~~~~~~~~~~
/home/liyang/ly/experiment/TCGNN.cpp:27:23: note: in expansion of macro ‘TORCH_CHECK’
#define CHECK_CUDA(x) TORCH_CHECK(x.type().is_cuda(), #x " must be a CUDA tensor")
^~~~~~~~~~~
/home/liyang/ly/experiment/TCGNN.cpp:29:24: note: in expansion of macro ‘CHECK_CUDA’
#define CHECK_INPUT(x) CHECK_CUDA(x); CHECK_CONTIGUOUS(x)
^~~~~~~~~~
/home/liyang/ly/experiment/TCGNN.cpp:44:3: note: in expansion of macro ‘CHECK_INPUT’
CHECK_INPUT(input);
^
In file included from /mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/torch/include/ATen/core/Tensor.h:3:0,
from /mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/torch/include/ATen/DeviceGuard.h:4,
from /mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/torch/include/ATen/ATen.h:11,
from /mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/types.h:3,
from /mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader_options.h:4,
from /mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/base.h:3,
from /mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/stateful.h:3,
from /mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader.h:3,
from /mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data.h:3,
from /mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/all.h:8,
from /mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/torch/include/torch/extension.h:4,
from /home/liyang/ly/experiment/TCGNN.cpp:1:
/mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/torch/include/ATen/core/TensorBody.h:210:30: note: declared here
DeprecatedTypeProperties & type() const {
^~~~
In file included from /mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/torch/include/c10/core/DeviceType.h:8:0,
from /mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/torch/include/c10/core/Device.h:3,
from /mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/torch/include/c10/core/Allocator.h:6,
from /mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/torch/include/ATen/ATen.h:7,
from /mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/types.h:3,
from /mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader_options.h:4,
from /mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/base.h:3,
from /mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/stateful.h:3,
from /mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader.h:3,
from /mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data.h:3,
from /mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/all.h:8,
from /mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/torch/include/torch/extension.h:4,
from /home/liyang/ly/experiment/TCGNN.cpp:1:
/home/liyang/ly/experiment/TCGNN.cpp:27:42: warning: ‘at::DeprecatedTypeProperties& at::Tensor::type() const’ is deprecated: Tensor.type() is deprecated. Instead use Tensor.options(), which in many cases (e.g. in a constructor) is a drop-in replacement. If you were using data from type(), that is now available from Tensor itself, so instead of tensor.type().scalar_type(), use tensor.scalar_type() instead and instead of tensor.type().backend() use tensor.device(). [-Wdeprecated-declarations]
#define CHECK_CUDA(x) TORCH_CHECK(x.type().is_cuda(), #x " must be a CUDA tensor")
^
/mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/torch/include/c10/macros/Macros.h:204:64: note: in definition of macro ‘C10_UNLIKELY’
#define C10_UNLIKELY(expr) (__builtin_expect(static_cast<bool>(expr), 0))
^~~~
/mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/torch/include/c10/util/Exception.h:460:7: note: in expansion of macro ‘C10_UNLIKELY_OR_CONST’
if (C10_UNLIKELY_OR_CONST(!(cond))) { \
^~~~~~~~~~~~~~~~~~~~~
/home/liyang/ly/experiment/TCGNN.cpp:27:23: note: in expansion of macro ‘TORCH_CHECK’
#define CHECK_CUDA(x) TORCH_CHECK(x.type().is_cuda(), #x " must be a CUDA tensor")
^~~~~~~~~~~
/home/liyang/ly/experiment/TCGNN.cpp:29:24: note: in expansion of macro ‘CHECK_CUDA’
#define CHECK_INPUT(x) CHECK_CUDA(x); CHECK_CONTIGUOUS(x)
^~~~~~~~~~
/home/liyang/ly/experiment/TCGNN.cpp:45:3: note: in expansion of macro ‘CHECK_INPUT’
CHECK_INPUT(nodePointer);
^
In file included from /mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/torch/include/ATen/core/Tensor.h:3:0,
from /mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/torch/include/ATen/DeviceGuard.h:4,
from /mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/torch/include/ATen/ATen.h:11,
from /mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/types.h:3,
from /mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader_options.h:4,
from /mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/base.h:3,
from /mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/stateful.h:3,
from /mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader.h:3,
from /mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data.h:3,
from /mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/all.h:8,
from /mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/torch/include/torch/extension.h:4,
from /home/liyang/ly/experiment/TCGNN.cpp:1:
/mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/torch/include/ATen/core/TensorBody.h:210:30: note: declared here
DeprecatedTypeProperties & type() const {
^~~~
In file included from /mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/torch/include/c10/core/DeviceType.h:8:0,
from /mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/torch/include/c10/core/Device.h:3,
from /mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/torch/include/c10/core/Allocator.h:6,
from /mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/torch/include/ATen/ATen.h:7,
from /mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/types.h:3,
from /mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader_options.h:4,
from /mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/base.h:3,
from /mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/stateful.h:3,
from /mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader.h:3,
from /mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data.h:3,
from /mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/all.h:8,
from /mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/torch/include/torch/extension.h:4,
from /home/liyang/ly/experiment/TCGNN.cpp:1:
/home/liyang/ly/experiment/TCGNN.cpp:27:42: warning: ‘at::DeprecatedTypeProperties& at::Tensor::type() const’ is deprecated: Tensor.type() is deprecated. Instead use Tensor.options(), which in many cases (e.g. in a constructor) is a drop-in replacement. If you were using data from type(), that is now available from Tensor itself, so instead of tensor.type().scalar_type(), use tensor.scalar_type() instead and instead of tensor.type().backend() use tensor.device(). [-Wdeprecated-declarations]
#define CHECK_CUDA(x) TORCH_CHECK(x.type().is_cuda(), #x " must be a CUDA tensor")
^
/mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/torch/include/c10/macros/Macros.h:204:64: note: in definition of macro ‘C10_UNLIKELY’
#define C10_UNLIKELY(expr) (__builtin_expect(static_cast<bool>(expr), 0))
^~~~
/mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/torch/include/c10/util/Exception.h:460:7: note: in expansion of macro ‘C10_UNLIKELY_OR_CONST’
if (C10_UNLIKELY_OR_CONST(!(cond))) { \
^~~~~~~~~~~~~~~~~~~~~
/home/liyang/ly/experiment/TCGNN.cpp:27:23: note: in expansion of macro ‘TORCH_CHECK’
#define CHECK_CUDA(x) TORCH_CHECK(x.type().is_cuda(), #x " must be a CUDA tensor")
^~~~~~~~~~~
/home/liyang/ly/experiment/TCGNN.cpp:29:24: note: in expansion of macro ‘CHECK_CUDA’
#define CHECK_INPUT(x) CHECK_CUDA(x); CHECK_CONTIGUOUS(x)
^~~~~~~~~~
/home/liyang/ly/experiment/TCGNN.cpp:46:3: note: in expansion of macro ‘CHECK_INPUT’
CHECK_INPUT(edgeList);
^
In file included from /mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/torch/include/ATen/core/Tensor.h:3:0,
from /mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/torch/include/ATen/DeviceGuard.h:4,
from /mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/torch/include/ATen/ATen.h:11,
from /mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/types.h:3,
from /mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader_options.h:4,
from /mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/base.h:3,
from /mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/stateful.h:3,
from /mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader.h:3,
from /mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data.h:3,
from /mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/all.h:8,
from /mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/torch/include/torch/extension.h:4,
from /home/liyang/ly/experiment/TCGNN.cpp:1:
/mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/torch/include/ATen/core/TensorBody.h:210:30: note: declared here
DeprecatedTypeProperties & type() const {
^~~~
In file included from /mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/torch/include/c10/core/DeviceType.h:8:0,
from /mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/torch/include/c10/core/Device.h:3,
from /mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/torch/include/c10/core/Allocator.h:6,
from /mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/torch/include/ATen/ATen.h:7,
from /mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/types.h:3,
from /mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader_options.h:4,
from /mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/base.h:3,
from /mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/stateful.h:3,
from /mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader.h:3,
from /mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data.h:3,
from /mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/all.h:8,
from /mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/torch/include/torch/extension.h:4,
from /home/liyang/ly/experiment/TCGNN.cpp:1:
/home/liyang/ly/experiment/TCGNN.cpp:27:42: warning: ‘at::DeprecatedTypeProperties& at::Tensor::type() const’ is deprecated: Tensor.type() is deprecated. Instead use Tensor.options(), which in many cases (e.g. in a constructor) is a drop-in replacement. If you were using data from type(), that is now available from Tensor itself, so instead of tensor.type().scalar_type(), use tensor.scalar_type() instead and instead of tensor.type().backend() use tensor.device(). [-Wdeprecated-declarations]
#define CHECK_CUDA(x) TORCH_CHECK(x.type().is_cuda(), #x " must be a CUDA tensor")
^
/mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/torch/include/c10/macros/Macros.h:204:64: note: in definition of macro ‘C10_UNLIKELY’
#define C10_UNLIKELY(expr) (__builtin_expect(static_cast<bool>(expr), 0))
^~~~
/mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/torch/include/c10/util/Exception.h:460:7: note: in expansion of macro ‘C10_UNLIKELY_OR_CONST’
if (C10_UNLIKELY_OR_CONST(!(cond))) { \
^~~~~~~~~~~~~~~~~~~~~
/home/liyang/ly/experiment/TCGNN.cpp:27:23: note: in expansion of macro ‘TORCH_CHECK’
#define CHECK_CUDA(x) TORCH_CHECK(x.type().is_cuda(), #x " must be a CUDA tensor")
^~~~~~~~~~~
/home/liyang/ly/experiment/TCGNN.cpp:29:24: note: in expansion of macro ‘CHECK_CUDA’
#define CHECK_INPUT(x) CHECK_CUDA(x); CHECK_CONTIGUOUS(x)
^~~~~~~~~~
/home/liyang/ly/experiment/TCGNN.cpp:47:3: note: in expansion of macro ‘CHECK_INPUT’
CHECK_INPUT(blockPartition);
^
In file included from /mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/torch/include/ATen/core/Tensor.h:3:0,
from /mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/torch/include/ATen/DeviceGuard.h:4,
from /mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/torch/include/ATen/ATen.h:11,
from /mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/types.h:3,
from /mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader_options.h:4,
from /mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/base.h:3,
from /mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/stateful.h:3,
from /mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader.h:3,
from /mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data.h:3,
from /mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/all.h:8,
from /mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/torch/include/torch/extension.h:4,
from /home/liyang/ly/experiment/TCGNN.cpp:1:
/mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/torch/include/ATen/core/TensorBody.h:210:30: note: declared here
DeprecatedTypeProperties & type() const {
^~~~
In file included from /mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/torch/include/c10/core/DeviceType.h:8:0,
from /mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/torch/include/c10/core/Device.h:3,
from /mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/torch/include/c10/core/Allocator.h:6,
from /mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/torch/include/ATen/ATen.h:7,
from /mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/types.h:3,
from /mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader_options.h:4,
from /mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/base.h:3,
from /mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/stateful.h:3,
from /mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader.h:3,
from /mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data.h:3,
from /mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/all.h:8,
from /mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/torch/include/torch/extension.h:4,
from /home/liyang/ly/experiment/TCGNN.cpp:1:
/home/liyang/ly/experiment/TCGNN.cpp:27:42: warning: ‘at::DeprecatedTypeProperties& at::Tensor::type() const’ is deprecated: Tensor.type() is deprecated. Instead use Tensor.options(), which in many cases (e.g. in a constructor) is a drop-in replacement. If you were using data from type(), that is now available from Tensor itself, so instead of tensor.type().scalar_type(), use tensor.scalar_type() instead and instead of tensor.type().backend() use tensor.device(). [-Wdeprecated-declarations]
#define CHECK_CUDA(x) TORCH_CHECK(x.type().is_cuda(), #x " must be a CUDA tensor")
^
/mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/torch/include/c10/macros/Macros.h:204:64: note: in definition of macro ‘C10_UNLIKELY’
#define C10_UNLIKELY(expr) (__builtin_expect(static_cast<bool>(expr), 0))
^~~~
/mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/torch/include/c10/util/Exception.h:460:7: note: in expansion of macro ‘C10_UNLIKELY_OR_CONST’
if (C10_UNLIKELY_OR_CONST(!(cond))) { \
^~~~~~~~~~~~~~~~~~~~~
/home/liyang/ly/experiment/TCGNN.cpp:27:23: note: in expansion of macro ‘TORCH_CHECK’
#define CHECK_CUDA(x) TORCH_CHECK(x.type().is_cuda(), #x " must be a CUDA tensor")
^~~~~~~~~~~
/home/liyang/ly/experiment/TCGNN.cpp:29:24: note: in expansion of macro ‘CHECK_CUDA’
#define CHECK_INPUT(x) CHECK_CUDA(x); CHECK_CONTIGUOUS(x)
^~~~~~~~~~
/home/liyang/ly/experiment/TCGNN.cpp:48:3: note: in expansion of macro ‘CHECK_INPUT’
CHECK_INPUT(edgeToColumn);
^
In file included from /mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/torch/include/ATen/core/Tensor.h:3:0,
from /mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/torch/include/ATen/DeviceGuard.h:4,
from /mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/torch/include/ATen/ATen.h:11,
from /mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/types.h:3,
from /mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader_options.h:4,
from /mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/base.h:3,
from /mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/stateful.h:3,
from /mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader.h:3,
from /mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data.h:3,
from /mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/all.h:8,
from /mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/torch/include/torch/extension.h:4,
from /home/liyang/ly/experiment/TCGNN.cpp:1:
/mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/torch/include/ATen/core/TensorBody.h:210:30: note: declared here
DeprecatedTypeProperties & type() const {
^~~~
In file included from /mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/torch/include/c10/core/DeviceType.h:8:0,
from /mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/torch/include/c10/core/Device.h:3,
from /mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/torch/include/c10/core/Allocator.h:6,
from /mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/torch/include/ATen/ATen.h:7,
from /mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/types.h:3,
from /mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader_options.h:4,
from /mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/base.h:3,
from /mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/stateful.h:3,
from /mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader.h:3,
from /mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data.h:3,
from /mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/all.h:8,
from /mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/torch/include/torch/extension.h:4,
from /home/liyang/ly/experiment/TCGNN.cpp:1:
/home/liyang/ly/experiment/TCGNN.cpp:27:42: warning: ‘at::DeprecatedTypeProperties& at::Tensor::type() const’ is deprecated: Tensor.type() is deprecated. Instead use Tensor.options(), which in many cases (e.g. in a constructor) is a drop-in replacement. If you were using data from type(), that is now available from Tensor itself, so instead of tensor.type().scalar_type(), use tensor.scalar_type() instead and instead of tensor.type().backend() use tensor.device(). [-Wdeprecated-declarations]
#define CHECK_CUDA(x) TORCH_CHECK(x.type().is_cuda(), #x " must be a CUDA tensor")
^
/mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/torch/include/c10/macros/Macros.h:204:64: note: in definition of macro ‘C10_UNLIKELY’
#define C10_UNLIKELY(expr) (__builtin_expect(static_cast<bool>(expr), 0))
^~~~
/mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/torch/include/c10/util/Exception.h:460:7: note: in expansion of macro ‘C10_UNLIKELY_OR_CONST’
if (C10_UNLIKELY_OR_CONST(!(cond))) { \
^~~~~~~~~~~~~~~~~~~~~
/home/liyang/ly/experiment/TCGNN.cpp:27:23: note: in expansion of macro ‘TORCH_CHECK’
#define CHECK_CUDA(x) TORCH_CHECK(x.type().is_cuda(), #x " must be a CUDA tensor")
^~~~~~~~~~~
/home/liyang/ly/experiment/TCGNN.cpp:29:24: note: in expansion of macro ‘CHECK_CUDA’
#define CHECK_INPUT(x) CHECK_CUDA(x); CHECK_CONTIGUOUS(x)
^~~~~~~~~~
/home/liyang/ly/experiment/TCGNN.cpp:49:3: note: in expansion of macro ‘CHECK_INPUT’
CHECK_INPUT(edgeToRow);
^
In file included from /mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/torch/include/ATen/core/Tensor.h:3:0,
from /mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/torch/include/ATen/DeviceGuard.h:4,
from /mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/torch/include/ATen/ATen.h:11,
from /mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/types.h:3,
from /mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader_options.h:4,
from /mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/base.h:3,
from /mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/stateful.h:3,
from /mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader.h:3,
from /mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data.h:3,
from /mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/all.h:8,
from /mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/torch/include/torch/extension.h:4,
from /home/liyang/ly/experiment/TCGNN.cpp:1:
/mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/torch/include/ATen/core/TensorBody.h:210:30: note: declared here
DeprecatedTypeProperties & type() const {
^~~~
/home/liyang/ly/experiment/TCGNN.cpp: In function ‘std::map<unsigned int, unsigned int> inplace_deduplication(unsigned int*, unsigned int)’:
/home/liyang/ly/experiment/TCGNN.cpp:71:16: warning: comparison between signed and unsigned integer expressions [-Wsign-compare]
while (cur < length){
~~~~^~~~~~~~
/home/liyang/ly/experiment/TCGNN.cpp: In function ‘void preprocess(at::Tensor, at::Tensor, int, int, int, at::Tensor, at::Tensor, at::Tensor)’:
/home/liyang/ly/experiment/TCGNN.cpp:104:32: warning: comparison between signed and unsigned integer expressions [-Wsign-compare]
for (unsigned nid = 0; nid < num_nodes; nid++){
~~~~^~~~~~~~~~~
/home/liyang/ly/experiment/TCGNN.cpp:105:51: warning: comparison between signed and unsigned integer expressions [-Wsign-compare]
for (unsigned eid = nodePointer[nid]; eid < nodePointer[nid+1]; eid++)
/home/liyang/ly/experiment/TCGNN.cpp:110:34: warning: comparison between signed and unsigned integer expressions [-Wsign-compare]
for (unsigned iter = 0; iter < num_nodes + 1; iter += blockSize_h){
~~~~~^~~~~~~~~~~~~~~
/home/liyang/ly/experiment/TCGNN.cpp:11:25: warning: comparison between signed and unsigned integer expressions [-Wsign-compare]
#define min(x, y) (((x) < (y))? (x) : (y))
~~~~^~~~~
/home/liyang/ly/experiment/TCGNN.cpp:113:42: note: in expansion of macro ‘min’
unsigned block_end = nodePointer[min(iter + blockSize_h, num_nodes)];
^
ninja: build stopped: subcommand failed.
Traceback (most recent call last):
File "/mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/torch/utils/cpp_extension.py", line 1740, in _run_ninja_build
subprocess.run(
File "/mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/subprocess.py", line 516, in run
raise CalledProcessError(retcode, process.args,
subprocess.CalledProcessError: Command '['ninja', '-v']' returned non-zero exit status 1.
The above exception was the direct cause of the following exception:
Traceback (most recent call last):
File "setup.py", line 15, in <module>
setup(
File "/mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/setuptools/__init__.py", line 153, in setup
return distutils.core.setup(**attrs)
File "/mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/setuptools/_distutils/core.py", line 148, in setup
return run_commands(dist)
File "/mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/setuptools/_distutils/core.py", line 163, in run_commands
dist.run_commands()
File "/mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/setuptools/_distutils/dist.py", line 967, in run_commands
self.run_command(cmd)
File "/mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/setuptools/_distutils/dist.py", line 986, in run_command
cmd_obj.run()
File "/mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/setuptools/command/install.py", line 74, in run
self.do_egg_install()
File "/mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/setuptools/command/install.py", line 116, in do_egg_install
self.run_command('bdist_egg')
File "/mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/setuptools/_distutils/cmd.py", line 313, in run_command
self.distribution.run_command(command)
File "/mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/setuptools/_distutils/dist.py", line 986, in run_command
cmd_obj.run()
File "/mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/setuptools/command/bdist_egg.py", line 164, in run
cmd = self.call_command('install_lib', warn_dir=0)
File "/mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/setuptools/command/bdist_egg.py", line 150, in call_command
self.run_command(cmdname)
File "/mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/setuptools/_distutils/cmd.py", line 313, in run_command
self.distribution.run_command(command)
File "/mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/setuptools/_distutils/dist.py", line 986, in run_command
cmd_obj.run()
File "/mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/setuptools/command/install_lib.py", line 11, in run
self.build()
File "/mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/setuptools/_distutils/command/install_lib.py", line 107, in build
self.run_command('build_ext')
File "/mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/setuptools/_distutils/cmd.py", line 313, in run_command
self.distribution.run_command(command)
File "/mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/setuptools/_distutils/dist.py", line 986, in run_command
cmd_obj.run()
File "/mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/setuptools/command/build_ext.py", line 79, in run
_build_ext.run(self)
File "/mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/setuptools/_distutils/command/build_ext.py", line 339, in run
self.build_extensions()
File "/mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/torch/utils/cpp_extension.py", line 741, in build_extensions
build_ext.build_extensions(self)
File "/mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/setuptools/_distutils/command/build_ext.py", line 448, in build_extensions
self._build_extensions_serial()
File "/mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/setuptools/_distutils/command/build_ext.py", line 473, in _build_extensions_serial
self.build_extension(ext)
File "/mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/setuptools/command/build_ext.py", line 202, in build_extension
_build_ext.build_extension(self, ext)
File "/mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/setuptools/_distutils/command/build_ext.py", line 528, in build_extension
objects = self.compiler.compile(sources,
File "/mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/torch/utils/cpp_extension.py", line 562, in unix_wrap_ninja_compile
_write_ninja_file_and_compile_objects(
File "/mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/torch/utils/cpp_extension.py", line 1419, in _write_ninja_file_and_compile_objects
_run_ninja_build(
File "/mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/torch/utils/cpp_extension.py", line 1756, in _run_ninja_build
raise RuntimeError(message) from e
RuntimeError: Error compiling objects for extension
but when I run the command: TORCH_CUDA_ARCH_LIST="8.6" python setup.py install
it seems can compile well, between is the output:
running install
/mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/setuptools/command/install.py:34: SetuptoolsDeprecationWarning: setup.py install is deprecated. Use build and pip and other standards-based tools.
warnings.warn(
/mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/setuptools/command/easy_install.py:156: EasyInstallDeprecationWarning: easy_install command is deprecated. Use build and pip and other standards-based tools.
warnings.warn(
running bdist_egg
running egg_info
writing manifest file 'TCGNN.egg-info/SOURCES.txt'
running install_lib
running build_ext
Emitting ninja build file /home/liyang/ly/experiment/build/temp.linux-x86_64-3.8/build.ninja...
Compiling objects...
Allowing ninja to set a default number of workers... (overridable by setting the environment variable MAX_JOBS=N)
[1/1] /usr/local/cuda-11.3/bin/nvcc -I/mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/torch/include -I/mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/torch/include/torch/csrc/api/include -I/mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/torch/include/TH -I/mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/torch/include/THC -I/usr/local/cuda-11.3/include -I/mnt/7T/lly/anaconda3/envs/tcgnn/include/python3.8 -c -c /home/liyang/ly/experiment/TCGNN_kernel.cu -o /home/liyang/ly/experiment/build/temp.linux-x86_64-3.8/TCGNN_kernel.o -D__CUDA_NO_HALF_OPERATORS__ -D__CUDA_NO_HALF_CONVERSIONS__ -D__CUDA_NO_BFLOAT16_CONVERSIONS__ -D__CUDA_NO_HALF2_OPERATORS__ --expt-relaxed-constexpr --compiler-options ''"'"'-fPIC'"'"'' -DTORCH_API_INCLUDE_EXTENSION_H '-DPYBIND11_COMPILER_TYPE="_gcc"' '-DPYBIND11_STDLIB="_libstdcpp"' '-DPYBIND11_BUILD_ABI="_cxxabi1011"' -DTORCH_EXTENSION_NAME=TCGNN -D_GLIBCXX_USE_CXX11_ABI=0 -gencode=arch=compute_86,code=sm_86 -std=c++14
/home/liyang/ly/experiment/TCGNN_kernel.cu: In function ‘std::vector<at::Tensor> spmm_forward_cuda(at::Tensor, at::Tensor, at::Tensor, at::Tensor, at::Tensor, int, int, int, at::Tensor)’:
/home/liyang/ly/experiment/TCGNN_kernel.cu:61:126: warning: ‘T* at::Tensor::data() const [with T = int]’ is deprecated: Tensor.data<T>() is deprecated. Please use Tensor.data_ptr<T>() instead. [-Wdeprecated-declarations]
spmm_forward_cuda_kernel<<<grid, block, dynamic_shared_size>>>(
^
/mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/torch/include/ATen/core/TensorBody.h:232:1: note: declared here
T * data() const {
^ ~~
/home/liyang/ly/experiment/TCGNN_kernel.cu:61:150: warning: ‘T* at::Tensor::data() const [with T = int]’ is deprecated: Tensor.data<T>() is deprecated. Please use Tensor.data_ptr<T>() instead. [-Wdeprecated-declarations]
spmm_forward_cuda_kernel<<<grid, block, dynamic_shared_size>>>(
^
/mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/torch/include/ATen/core/TensorBody.h:232:1: note: declared here
T * data() const {
^ ~~
/home/liyang/ly/experiment/TCGNN_kernel.cu:61:180: warning: ‘T* at::Tensor::data() const [with T = int]’ is deprecated: Tensor.data<T>() is deprecated. Please use Tensor.data_ptr<T>() instead. [-Wdeprecated-declarations]
spmm_forward_cuda_kernel<<<grid, block, dynamic_shared_size>>>(
^
/mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/torch/include/ATen/core/TensorBody.h:232:1: note: declared here
T * data() const {
^ ~~
/home/liyang/ly/experiment/TCGNN_kernel.cu:61:208: warning: ‘T* at::Tensor::data() const [with T = int]’ is deprecated: Tensor.data<T>() is deprecated. Please use Tensor.data_ptr<T>() instead. [-Wdeprecated-declarations]
spmm_forward_cuda_kernel<<<grid, block, dynamic_shared_size>>>(
^
/mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/torch/include/ATen/core/TensorBody.h:232:1: note: declared here
T * data() const {
^ ~~
/home/liyang/ly/experiment/TCGNN_kernel.cu:61:233: warning: ‘T* at::Tensor::data() const [with T = int]’ is deprecated: Tensor.data<T>() is deprecated. Please use Tensor.data_ptr<T>() instead. [-Wdeprecated-declarations]
spmm_forward_cuda_kernel<<<grid, block, dynamic_shared_size>>>(
^
/mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/torch/include/ATen/core/TensorBody.h:232:1: note: declared here
T * data() const {
^ ~~
/home/liyang/ly/experiment/TCGNN_kernel.cu:61:293: warning: ‘T* at::Tensor::data() const [with T = float]’ is deprecated: Tensor.data<T>() is deprecated. Please use Tensor.data_ptr<T>() instead. [-Wdeprecated-declarations]
spmm_forward_cuda_kernel<<<grid, block, dynamic_shared_size>>>(
^
/mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/torch/include/ATen/core/TensorBody.h:232:1: note: declared here
T * data() const {
^ ~~
/home/liyang/ly/experiment/TCGNN_kernel.cu:61:317: warning: ‘T* at::Tensor::data() const [with T = float]’ is deprecated: Tensor.data<T>() is deprecated. Please use Tensor.data_ptr<T>() instead. [-Wdeprecated-declarations]
spmm_forward_cuda_kernel<<<grid, block, dynamic_shared_size>>>(
^
/mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/torch/include/ATen/core/TensorBody.h:232:1: note: declared here
T * data() const {
^ ~~
creating build/lib.linux-x86_64-3.8
g++ -pthread -shared -B /mnt/7T/lly/anaconda3/envs/tcgnn/compiler_compat -L/mnt/7T/lly/anaconda3/envs/tcgnn/lib -Wl,-rpath=/mnt/7T/lly/anaconda3/envs/tcgnn/lib -Wl,--no-as-needed -Wl,--sysroot=/ /home/liyang/ly/experiment/build/temp.linux-x86_64-3.8/TCGNN.o /home/liyang/ly/experiment/build/temp.linux-x86_64-3.8/TCGNN_kernel.o -L/mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/torch/lib -L/usr/local/cuda-11.3/lib64 -lc10 -ltorch -ltorch_cpu -ltorch_python -lcudart -lc10_cuda -ltorch_cuda_cu -ltorch_cuda_cpp -o build/lib.linux-x86_64-3.8/TCGNN.cpython-38-x86_64-linux-gnu.so
/usr/bin/x86_64-linux-gnu-ld: warning: /mnt/7T/lly/anaconda3/envs/tcgnn/lib/libstdc++.so: unsupported GNU_PROPERTY_TYPE (5) type: 0xc0010001
/usr/bin/x86_64-linux-gnu-ld: warning: /mnt/7T/lly/anaconda3/envs/tcgnn/lib/libstdc++.so: unsupported GNU_PROPERTY_TYPE (5) type: 0xc0010002
/usr/bin/x86_64-linux-gnu-ld: warning: /mnt/7T/lly/anaconda3/envs/tcgnn/lib/libgcc_s.so.1: unsupported GNU_PROPERTY_TYPE (5) type: 0xc0010001
/usr/bin/x86_64-linux-gnu-ld: warning: /mnt/7T/lly/anaconda3/envs/tcgnn/lib/libgcc_s.so.1: unsupported GNU_PROPERTY_TYPE (5) type: 0xc0010002
/usr/bin/x86_64-linux-gnu-ld: warning: /mnt/7T/lly/anaconda3/envs/tcgnn/lib/libgcc_s.so.1: unsupported GNU_PROPERTY_TYPE (5) type: 0xc0010001
/usr/bin/x86_64-linux-gnu-ld: warning: /mnt/7T/lly/anaconda3/envs/tcgnn/lib/libgcc_s.so.1: unsupported GNU_PROPERTY_TYPE (5) type: 0xc0010002
creating build/bdist.linux-x86_64
creating build/bdist.linux-x86_64/egg
byte-compiling build/bdist.linux-x86_64/egg/TCGNN.py to TCGNN.cpython-38.pyc
creating build/bdist.linux-x86_64/egg/EGG-INFO
copying TCGNN.egg-info/PKG-INFO -> build/bdist.linux-x86_64/egg/EGG-INFO
copying TCGNN.egg-info/SOURCES.txt -> build/bdist.linux-x86_64/egg/EGG-INFO
copying TCGNN.egg-info/dependency_links.txt -> build/bdist.linux-x86_64/egg/EGG-INFO
copying TCGNN.egg-info/top_level.txt -> build/bdist.linux-x86_64/egg/EGG-INFO
zip_safe flag not set; analyzing archive contents...
__pycache__.TCGNN.cpython-38: module references __file__
creating dist
removing 'build/bdist.linux-x86_64/egg' (and everything under it)
removing '/mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/TCGNN-0.0.0-py3.8-linux-x86_64.egg' (and everything under it)
creating /mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/TCGNN-0.0.0-py3.8-linux-x86_64.egg
Extracting TCGNN-0.0.0-py3.8-linux-x86_64.egg to /mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages
byte-compiling /mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/TCGNN-0.0.0-py3.8-linux-x86_64.egg/TCGNN.py to TCGNN.cpython-38.pyc
TCGNN 0.0.0 is already the active version in easy-install.pth
Installed /mnt/7T/lly/anaconda3/envs/tcgnn/lib/python3.8/site-packages/TCGNN-0.0.0-py3.8-linux-x86_64.egg
Processing dependencies for TCGNN==0.0.0
Finished processing dependencies for TCGNN==0.0.0
but when i run the program, error occured like this:
tcgnn) wurui@node10:~/wurui/experiment$ ./1_bench_gcn.py
=> citeseer, hiddn: 16
Namespace(classes=6, dataset='citeseer', dim=3703, epochs=200, hidden=16, model='gcn', num_layers=2, single_kernel=False)
TC_Blocks: 1197
Exp_Edges: 153216
Prep. (ms): 1.615
torch.Size([3327, 3703]) torch.Size([3703, 16])
cuda:0 cuda:0
tensor([[-8.7582e+01, 2.4211e+01, -8.3589e-01, ..., 2.6267e+01,
-1.1155e+02, 8.8293e+01],
[ 8.3507e+01, 3.4958e+00, 5.1139e+01, ..., -9.2721e+01,
-2.4189e+01, -8.7180e+01],
[ 3.0647e+01, 1.0059e+01, -2.5137e+01, ..., -1.7531e+01,
1.6680e+02, -1.7924e+01],
...,
[-9.7669e+01, 6.3489e-02, 3.4873e+01, ..., 3.0643e+01,
3.0913e+01, -7.3062e+01],
[-1.7428e+01, -5.8077e+01, -8.2955e+01, ..., -1.5578e+01,
5.6977e+01, 3.3946e+01],
[ 7.7431e+01, 4.6048e+01, 3.6308e+01, ..., -5.4706e+01,
2.2290e+01, -2.6366e+01]], device='cuda:0')
torch.Size([3327, 16]) cuda:0
break1
break2
break10
CUDA error: no kernel image is available for execution on the device
the print shows that the program didn’t go into the kernel, and when I delete the code related to nvcuda, it compiles well and run well, so there is some problem with the nvcuda namespace.
any response would be appreciated!