# Unlike the rest of the PyTorch this file must be python2 compliant.
# This script outputs relevant system environment info
# Run it with `python collect_env.py`.
import datetime
import locale
import re
import subprocess
import sys
import os
from collections import namedtuple


try:
    import torch
    TORCH_AVAILABLE = True
except (ImportError, NameError, AttributeError, OSError):
    TORCH_AVAILABLE = False

# System Environment Information
SystemEnv = namedtuple('SystemEnv', [
    'torch_version',
    'is_debug_build',
    'cuda_compiled_version',
    'gcc_version',
    'clang_version',
    'cmake_version',
    'os',
    'libc_version',
    'python_version',
    'python_platform',
    'is_cuda_available',
    'cuda_runtime_version',
    'cuda_module_loading',
    'nvidia_driver_version',
    'nvidia_gpu_models',
    'cudnn_version',
    'pip_version',  # 'pip' or 'pip3'
    'pip_packages',
    'conda_packages',
    'hip_compiled_version',
    'hip_runtime_version',
    'miopen_runtime_version',
    'caching_allocator_config',
    'is_xnnpack_available',
    'cpu_info',
])


def run(command):
    """Returns (return-code, stdout, stderr)"""
    p = subprocess.Popen(command, stdout=subprocess.PIPE,
                         stderr=subprocess.PIPE, shell=True)
    raw_output, raw_err = p.communicate()
    rc = p.returncode
    if get_platform() == 'win32':
        enc = 'oem'
    else:
        enc = locale.getpreferredencoding()
    output = raw_output.decode(enc)
    err = raw_err.decode(enc)
    return rc, output.strip(), err.strip()


def run_and_read_all(run_lambda, command):
    """Runs command using run_lambda; reads and returns entire output if rc is 0"""
    rc, out, _ = run_lambda(command)
    if rc != 0:
        return None
    return out


def run_and_parse_first_match(run_lambda, command, regex):
    """Runs command using run_lambda, returns the first regex match if it exists"""
    rc, out, _ = run_lambda(command)
    if rc != 0:
        return None
    match = re.search(regex, out)
    if match is None:
        return None
    return match.group(1)

def run_and_return_first_line(run_lambda, command):
    """Runs command using run_lambda and returns first line if output is not empty"""
    rc, out, _ = run_lambda(command)
    if rc != 0:
        return None
    return out.split('\n')[0]


def get_conda_packages(run_lambda):
    conda = os.environ.get('CONDA_EXE', 'conda')
    out = run_and_read_all(run_lambda, "{} list".format(conda))
    if out is None:
        return out

    return "\n".join(
        line
        for line in out.splitlines()
        if not line.startswith("#")
        and any(
            name in line
            for name in {
                "torch",
                "numpy",
                "cudatoolkit",
                "soumith",
                "mkl",
                "magma",
                "mkl",
            }
        )
    )

def get_gcc_version(run_lambda):
    return run_and_parse_first_match(run_lambda, 'gcc --version', r'gcc (.*)')

def get_clang_version(run_lambda):
    return run_and_parse_first_match(run_lambda, 'clang --version', r'clang version (.*)')


def get_cmake_version(run_lambda):
    return run_and_parse_first_match(run_lambda, 'cmake --version', r'cmake (.*)')


def get_nvidia_driver_version(run_lambda):
    if get_platform() == 'darwin':
        cmd = 'kextstat | grep -i cuda'
        return run_and_parse_first_match(run_lambda, cmd,
                                         r'com[.]nvidia[.]CUDA [(](.*?)[)]')
    smi = get_nvidia_smi()
    return run_and_parse_first_match(run_lambda, smi, r'Driver Version: (.*?) ')


def get_gpu_info(run_lambda):
    if get_platform() == 'darwin' or (TORCH_AVAILABLE and hasattr(torch.version, 'hip') and torch.version.hip is not None):
        if TORCH_AVAILABLE and torch.cuda.is_available():
            return torch.cuda.get_device_name(None)
        return None
    smi = get_nvidia_smi()
    uuid_regex = re.compile(r' \(UUID: .+?\)')
    rc, out, _ = run_lambda(smi + ' -L')
    if rc != 0:
        return None
    # Anonymize GPUs by removing their UUID
    return re.sub(uuid_regex, '', out)


def get_running_cuda_version(run_lambda):
    return run_and_parse_first_match(run_lambda, 'nvcc --version', r'release .+ V(.*)')


def get_cudnn_version(run_lambda):
    """This will return a list of libcudnn.so; it's hard to tell which one is being used"""
    if get_platform() == 'win32':
        system_root = os.environ.get('SYSTEMROOT', 'C:\\Windows')
        cuda_path = os.environ.get('CUDA_PATH', "%CUDA_PATH%")
        where_cmd = os.path.join(system_root, 'System32', 'where')
        cudnn_cmd = '{} /R "{}\\bin" cudnn*.dll'.format(where_cmd, cuda_path)
    elif get_platform() == 'darwin':
        # CUDA libraries and drivers can be found in /usr/local/cuda/. See
        # https://docs.nvidia.com/cuda/cuda-installation-guide-mac-os-x/index.html#install
        # https://docs.nvidia.com/deeplearning/sdk/cudnn-install/index.html#installmac
        # Use CUDNN_LIBRARY when cudnn library is installed elsewhere.
        cudnn_cmd = 'ls /usr/local/cuda/lib/libcudnn*'
    else:
        cudnn_cmd = 'ldconfig -p | grep libcudnn | rev | cut -d" " -f1 | rev'
    rc, out, _ = run_lambda(cudnn_cmd)
    # find will return 1 if there are permission errors or if not found
    if len(out) == 0 or (rc != 1 and rc != 0):
        l = os.environ.get('CUDNN_LIBRARY')
        if l is not None and os.path.isfile(l):
            return os.path.realpath(l)
        return None
    files_set = set()
    for fn in out.split('\n'):
        fn = os.path.realpath(fn)  # eliminate symbolic links
        if os.path.isfile(fn):
            files_set.add(fn)
    if not files_set:
        return None
    # Alphabetize the result because the order is non-deterministic otherwise
    files = sorted(files_set)
    if len(files) == 1:
        return files[0]
    result = '\n'.join(files)
    return 'Probably one of the following:\n{}'.format(result)


def get_nvidia_smi():
    # Note: nvidia-smi is currently available only on Windows and Linux
    smi = 'nvidia-smi'
    if get_platform() == 'win32':
        system_root = os.environ.get('SYSTEMROOT', 'C:\\Windows')
        program_files_root = os.environ.get('PROGRAMFILES', 'C:\\Program Files')
        legacy_path = os.path.join(program_files_root, 'NVIDIA Corporation', 'NVSMI', smi)
        new_path = os.path.join(system_root, 'System32', smi)
        smis = [new_path, legacy_path]
        for candidate_smi in smis:
            if os.path.exists(candidate_smi):
                smi = '"{}"'.format(candidate_smi)
                break
    return smi


# example outputs of CPU infos
#  * linux
#    Architecture:            x86_64
#      CPU op-mode(s):        32-bit, 64-bit
#      Address sizes:         46 bits physical, 48 bits virtual
#      Byte Order:            Little Endian
#    CPU(s):                  128
#      On-line CPU(s) list:   0-127
#    Vendor ID:               GenuineIntel
#      Model name:            Intel(R) Xeon(R) Platinum 8375C CPU @ 2.90GHz
#        CPU family:          6
#        Model:               106
#        Thread(s) per core:  2
#        Core(s) per socket:  32
#        Socket(s):           2
#        Stepping:            6
#        BogoMIPS:            5799.78
#        Flags:               fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr
#                             sse sse2 ss ht syscall nx pdpe1gb rdtscp lm constant_tsc arch_perfmon rep_good nopl
#                             xtopology nonstop_tsc cpuid aperfmperf tsc_known_freq pni pclmulqdq monitor ssse3 fma cx16
#                             pcid sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand
#                             hypervisor lahf_lm abm 3dnowprefetch invpcid_single ssbd ibrs ibpb stibp ibrs_enhanced
#                             fsgsbase tsc_adjust bmi1 avx2 smep bmi2 erms invpcid avx512f avx512dq rdseed adx smap
#                             avx512ifma clflushopt clwb avx512cd sha_ni avx512bw avx512vl xsaveopt xsavec xgetbv1
#                             xsaves wbnoinvd ida arat avx512vbmi pku ospke avx512_vbmi2 gfni vaes vpclmulqdq
#                             avx512_vnni avx512_bitalg tme avx512_vpopcntdq rdpid md_clear flush_l1d arch_capabilities
#    Virtualization features:
#      Hypervisor vendor:     KVM
#      Virtualization type:   full
#    Caches (sum of all):
#      L1d:                   3 MiB (64 instances)
#      L1i:                   2 MiB (64 instances)
#      L2:                    80 MiB (64 instances)
#      L3:                    108 MiB (2 instances)
#    NUMA:
#      NUMA node(s):          2
#      NUMA node0 CPU(s):     0-31,64-95
#      NUMA node1 CPU(s):     32-63,96-127
#    Vulnerabilities:
#      Itlb multihit:         Not affected
#      L1tf:                  Not affected
#      Mds:                   Not affected
#      Meltdown:              Not affected
#      Mmio stale data:       Vulnerable: Clear CPU buffers attempted, no microcode; SMT Host state unknown
#      Retbleed:              Not affected
#      Spec store bypass:     Mitigation; Speculative Store Bypass disabled via prctl and seccomp
#      Spectre v1:            Mitigation; usercopy/swapgs barriers and __user pointer sanitization
#      Spectre v2:            Mitigation; Enhanced IBRS, IBPB conditional, RSB filling, PBRSB-eIBRS SW sequence
#      Srbds:                 Not affected
#      Tsx async abort:       Not affected
#  * win32
#    Architecture=9
#    CurrentClockSpeed=2900
#    DeviceID=CPU0
#    Family=179
#    L2CacheSize=40960
#    L2CacheSpeed=
#    Manufacturer=GenuineIntel
#    MaxClockSpeed=2900
#    Name=Intel(R) Xeon(R) Platinum 8375C CPU @ 2.90GHz
#    ProcessorType=3
#    Revision=27142
#
#    Architecture=9
#    CurrentClockSpeed=2900
#    DeviceID=CPU1
#    Family=179
#    L2CacheSize=40960
#    L2CacheSpeed=
#    Manufacturer=GenuineIntel
#    MaxClockSpeed=2900
#    Name=Intel(R) Xeon(R) Platinum 8375C CPU @ 2.90GHz
#    ProcessorType=3
#    Revision=27142

def get_cpu_info(run_lambda):
    rc, out, err = 0, '', ''
    if get_platform() == 'linux':
        rc, out, err = run_lambda('lscpu')
    elif get_platform() == 'win32':
        rc, out, err = run_lambda('wmic cpu get Name,Manufacturer,Family,Architecture,ProcessorType,DeviceID,\
        CurrentClockSpeed,MaxClockSpeed,L2CacheSize,L2CacheSpeed,Revision /VALUE')
    elif get_platform() == 'darwin':
        rc, out, err = run_lambda("sysctl -n machdep.cpu.brand_string")
    cpu_info = 'None'
    if rc == 0:
        cpu_info = out
    else:
        cpu_info = err
    return cpu_info


def get_platform():
    if sys.platform.startswith('linux'):
        return 'linux'
    elif sys.platform.startswith('win32'):
        return 'win32'
    elif sys.platform.startswith('cygwin'):
        return 'cygwin'
    elif sys.platform.startswith('darwin'):
        return 'darwin'
    else:
        return sys.platform


def get_mac_version(run_lambda):
    return run_and_parse_first_match(run_lambda, 'sw_vers -productVersion', r'(.*)')


def get_windows_version(run_lambda):
    system_root = os.environ.get('SYSTEMROOT', 'C:\\Windows')
    wmic_cmd = os.path.join(system_root, 'System32', 'Wbem', 'wmic')
    findstr_cmd = os.path.join(system_root, 'System32', 'findstr')
    return run_and_read_all(run_lambda, '{} os get Caption | {} /v Caption'.format(wmic_cmd, findstr_cmd))


def get_lsb_version(run_lambda):
    return run_and_parse_first_match(run_lambda, 'lsb_release -a', r'Description:\t(.*)')


def check_release_file(run_lambda):
    return run_and_parse_first_match(run_lambda, 'cat /etc/*-release',
                                     r'PRETTY_NAME="(.*)"')


def get_os(run_lambda):
    from platform import machine
    platform = get_platform()

    if platform == 'win32' or platform == 'cygwin':
        return get_windows_version(run_lambda)

    if platform == 'darwin':
        version = get_mac_version(run_lambda)
        if version is None:
            return None
        return 'macOS {} ({})'.format(version, machine())

    if platform == 'linux':
        # Ubuntu/Debian based