Laurawly

import os

import numpy as np
import tvm
from tvm import te, auto_scheduler, topi
from tvm.topi.testing import conv2d_nchw_python
from tvm.contrib import cublas
target = tvm.target.Target('cuda')

M = 8192

Laurawly

#from dlib_alignment import dlib_detect_face, face_recover
import torch
from PIL import Image
import torchvision.transforms as transforms
from models.SRGAN_model import SRGANModel
import numpy as np
import argparse
#import utils
import cv2
import random

Laurawly

/*
 * Licensed to the Apache Software Foundation (ASF) under one
 * or more contributor license agreements.  See the NOTICE file
 * distributed with this work for additional information
 * regarding copyright ownership.  The ASF licenses this file
 * to you under the Apache License, Version 2.0 (the
 * "License"); you may not use this file except in compliance
 * with the License.  You may obtain a copy of the License at
 *
 *   http://www.apache.org/licenses/LICENSE-2.0

Laurawly

#include <mma.h>
extern "C" __global__ void default_function_kernel0( int* __restrict__ A,  int* __restrict__ B,  int* __restrict__ compute) {
  nvcuda::wmma::fragment<nvcuda::wmma::accumulator, 8, 8, 32, int> compute_wmma_accumulator[2];
  __shared__ int A_shared[512];
  __shared__ int B_shared[512];
  nvcuda::wmma::fragment<nvcuda::wmma::matrix_a, 8, 8, 32, nvcuda::wmma::experimental::precision::s4, nvcuda::wmma::row_major> A_shared_wmma_matrix_a[2];
  nvcuda::wmma::fragment<nvcuda::wmma::matrix_b, 8, 8, 32, nvcuda::wmma::experimental::precision::s4, nvcuda::wmma::col_major> B_shared_wmma_matrix_b[1];
  for (int i_c_init = 0; i_c_init < 1; ++i_c_init) {
    (void)nvcuda::wmma::fill_fragment(compute_wmma_accumulator[i_c_init], 0.000000e+00f);
  }

Laurawly

t # 0
69244 276143 1 1
v 0 1
v 1 1
v 2 1
v 3 1
v 4 1
v 5 1
v 6 1
v 7 1

Laurawly

t # 0
5 4 1 1
v 0 1
v 1 1
v 2 1
v 3 1
v 4 1
e 0 1 1
e 0 2 1
e 1 3 1

Laurawly

// attr [get_valid_counts_phase_one.v0] storage_scope = "global"
allocate get_valid_counts_phase_one.v0[int32 * 15360]
// attr [get_valid_counts_phase_one.v1] storage_scope = "global"
allocate get_valid_counts_phase_one.v1[int32 * 15360]
// attr [get_valid_counts_phase_two.v1] storage_scope = "global"
allocate get_valid_counts_phase_two.v1[int32 * 496]
// attr [get_valid_counts_phase_two.v0] storage_scope = "global"
allocate get_valid_counts_phase_two.v0[int32 * 15360]
// attr [get_valid_counts_phase_three] storage_scope = "global"
allocate get_valid_counts_phase_three[int32 * 496]

Laurawly

Traceback (most recent call last):
  File "demo.py", line 19, in <module>
    classifier = gcv.model_zoo.get_model('resnet50_v1d', pretrained=True, ctx=ctx)
  File "/home/laurawly/workspace/install/lib/python3.6/site-packages/gluoncv-0.5.0-py3.6.egg/gluoncv/model_zoo/model_zoo.py", line 241, in get_model
  File "/home/laurawly/workspace/install/lib/python3.6/site-packages/gluoncv-0.5.0-py3.6.egg/gluoncv/model_zoo/resnetv1b.py", line 629, in resnet50_v1d
  File "/home/laurawly/workspace/install/lib/python3.6/site-packages/mxnet/gluon/block.py", line 402, in load_parameters
    params[name]._load_init(loaded[name], ctx)
  File "/home/laurawly/workspace/install/lib/python3.6/site-packages/mxnet/gluon/parameter.py", line 271, in _load_init
    self._init_impl(data, ctx)
  File "/home/laurawly/workspace/install/lib/python3.6/site-packages/mxnet/gluon/parameter.py", line 311, in _init_impl

Laurawly

Traceback (most recent call last):
  File "topi/tests/python/test_topi_vision.py", line 437, in <module>
    test_get_valid_counts()
  File "topi/tests/python/test_topi_vision.py", line 84, in test_get_valid_counts
    verify_get_valid_counts((1, 15360, 5), 0)
  File "topi/tests/python/test_topi_vision.py", line 74, in verify_get_valid_counts
    check_device(device)
  File "topi/tests/python/test_topi_vision.py", line 70, in check_device
    tvm.testing.assert_allclose(tvm_out1.asnumpy(), np_out1, rtol=1e-3)
  File "/home/ubuntu/workplace/tvm/python/tvm/_ffi/ndarray.py", line 283, in asnumpy

Laurawly

def test_sort():
    dshape = (1, 500)
    data = tvm.placeholder(dshape, name="data")
    np_data = np.random.rand(dshape[0], dshape[1]).astype(data.dtype)
    print(np_data)
    np_result = np.argsort(-np_data)
    def check_device(device):
        ctx = tvm.context(device, 0)
        if not ctx.exist:
            print("Skip because %s is not enabled" % device)