The argument is invalid.Reason: Unsupport chip type, chipType=4

一、问题现象（附报错日志上下文）：
```
在容器环境中，执行下面程序报错：
import torch
import torch_npu
device = torch.device("npu:0")
torch.npu.set_device(device)
mask = torch.zeros((1, 1, 28, 28), device=device)
padded_mask = torch.ones((1, 1, 30, 30), device=device)
padded_mask[:, :, 1:-1, 1:-1] = mask
print(padded_mask)

详细错误信息参考下面日志详情

```

二、软件版本和环境信息:
```
-- CANN 版本 (e.g., CANN 3.0.x，5.x.x):  
package_name=Ascend-cann-toolkit
version=6.3.RC2
innerversion=V100R001C30SPC001B249
compatible_version=[V100R001C29],[V100R001C30]
arch=aarch64
os=linux
path=/usr/local/Ascend/ascend-toolkit/6.3.RC2/aarch64-linux

-- 镜像版本
ascendhub.huawei.com/public-ascendhub/pytorch-modelzoo:23.0.RC2-1.11.0

-- Pytorch 版本:
torch              1.11.0
torch-npu          1.11.0.post1

-- Python 版本:
Python 3.7.5

-- 操作系统版本:
NAME="Kylin Linux Advanced Server"
VERSION="V10 (Lance)"
ID="kylin"
VERSION_ID="V10"
PRETTY_NAME="Kylin Linux Advanced Server V10 (Lance)"
ANSI_COLOR="0;31"

-- 显卡型号
型号：310P3

-- 驱动版本
Version=23.0.1
ascendhal_version=7.35.19
aicpu_version=1.0
tdt_version=1.0
log_version=1.0
prof_version=2.0
dvppkernels_version=1.1
tsfw_version=1.0
Innerversion=V100R001C15SPC004B220
compatible_version=[V100R001C29],[V100R001C30],[V100R001C13],[V100R001C15]
compatible_version_fw=[6.4.0,6.4.99],[7.0.0,7.1.99]
package_version=23.0.1

```

三、测试步骤：
步骤1：启动docker镜像：
```
docker run -it --ipc=host --device=/dev/davinci2 --device=/dev/davinci_manager --device=/dev/devmm_svm --device=/dev/hisi_hdc -v /usr/local/Ascend/driver:/usr/local/Ascend/driver -v /usr/local/Ascend/add-ons/:/usr/local/Ascend/add-ons/ -v /usr/local/sbin/npu-smi:/usr/local/sbin/npu-smi -v /usr/local/sbin/:/usr/local/sbin/ -v /var/log/npu/conf/slog/slog.conf:/var/log/npu/conf/slog/slog.conf -v /var/log/npu/slog/:/var/log/npu/slog -v /var/log/npu/profiling/:/var/log/npu/profiling -v /var/log/npu/dump/:/var/log/npu/dump -v /var/log/npu/:/usr/slog ascendhub.huawei.com/public-ascendhub/pytorch-modelzoo:23.0.RC2-1.11.0 /bin/bash
```
步骤2：设置变量
```
source /usr/local/Ascend/ascend-toolkit/set_env.sh
```
步骤3：执行代码
```
import torch
import torch_npu
device = torch.device("npu:0")
torch.npu.set_device(device)
mask = torch.zeros((1, 1, 28, 28), device=device)
padded_mask = torch.ones((1, 1, 30, 30), device=device)
padded_mask[:, :, 1:-1, 1:-1] = mask
print(padded_mask)
```

最后一步 print(padded_mask) 程序会报错

四、日志信息:
```
[WARN]operator(),NPUStream.cpp:188:Feature is not supported and the possible cause is that drivers and firmware packages do not match.
EE1001: The argument is invalid.Reason: Unsupport chip type, chipType=4.
        Solution: 1.Check the input parameter range of the function. 2.Check the function invocation relationship.
        TraceBack (most recent call last):
        Task execute failed, device_id=0, stream_id=0, task_id=1, flip_num=0, task_type=83.[FUNC:GetError][FILE:stream.cc][LINE:1418]
        The argument is invalid.Reason: Unsupport chip type, chipType=4.
        The argument is invalid.Reason: rtSetOpWaitTimeOut execute failed, reason=[feature not support]
        set wait timeout failed, runtime result = 207000[FUNC:ReportCallError][FILE:log_inner.cpp][LINE:161]
        rtStreamSynchronizeWithTimeout execute failed, reason=[tsfw param illegal][FUNC:FuncErrorReason][FILE:error_message_manage.cc][LINE:50]
        synchronize stream failed, runtime result = 507001[FUNC:ReportCallError][FILE:log_inner.cpp][LINE:161]
        Task execute failed, device_id=0, stream_id=4, task_id=1, flip_num=0, task_type=87.[FUNC:GetError][FILE:stream.cc][LINE:1418]
        Failed to synchronize stream, retCode=0x7150004.[FUNC:SyncGetDevMsg][FILE:api_impl.cc][LINE:4141]
        Sync get device msg failed, retCode=0x7150004.[FUNC:GetDevErrMsg][FILE:api_impl.cc][LINE:4160]
        rtGetDevMsg execute failed, reason=[tsfw param illegal][FUNC:FuncErrorReason][FILE:error_message_manage.cc][LINE:50]

Traceback (most recent call last):
  File "1.py", line 8, in <module>
    print(padded_mask)
  File "/usr/local/python3.7.5/lib/python3.7/site-packages/torch_npu/utils/_tensor_str.py", line 213, in __repr__
    return _str(self)
  File "/usr/local/python3.7.5/lib/python3.7/site-packages/torch_npu/utils/_tensor_str.py", line 163, in _str
    return _str_intern(self)
  File "/usr/local/python3.7.5/lib/python3.7/site-packages/torch_npu/utils/_tensor_str.py", line 140, in _str_intern
    tensor_str = _tensor_str(self, indent)
  File "/usr/local/python3.7.5/lib/python3.7/site-packages/torch_npu/utils/_tensor_str.py", line 57, in _tensor_str
    self = self.cpu()
RuntimeError: ACL stream synchronize failed, error code:507001
[W NPUStream.cpp:392] Warning: NPU warning, error code is 507001[Error]: 
[Error]: An internal error occurs in the task scheduler module on the device. 
        Rectify the fault based on the error information in the log, or you can ask us at follwing gitee link by issues: https://gitee.com/ascend/pytorch/issue
EL0005: The resources are busy.
        Possible Cause: 1. The resources have been occupied. 2. The device is being reset. 3. Software is not ready.
        Solution: 1. Close applications not in use. 2. Wait for a while and try again.
        TraceBack (most recent call last):
        Memory async copy failed, device_id=0, stream_id=3, task_id=4, flip_num=0, copy_type=0, memcpy_type=0, copy_data_type=0, length=32[FUNC:GetError][FILE:stream.cc][LINE:1418]
        rtDeviceSynchronize execute failed, reason=[tsfw param illegal][FUNC:FuncErrorReason][FILE:error_message_manage.cc][LINE:50]
        wait for compute device to finish failed, runtime result = 507001.[FUNC:ReportCallError][FILE:log_inner.cpp][LINE:161]
        Task execute failed, device_id=0, stream_id=4, task_id=1, flip_num=0, task_type=87.[FUNC:GetError][FILE:stream.cc][LINE:1418]
        Failed to synchronize stream, retCode=0x7150004.[FUNC:SyncGetDevMsg][FILE:api_impl.cc][LINE:4141]
        Sync get device msg failed, retCode=0x7150004.[FUNC:GetDevErrMsg][FILE:api_impl.cc][LINE:4160]
        rtGetDevMsg execute failed, reason=[tsfw param illegal][FUNC:FuncErrorReason][FILE:error_message_manage.cc][LINE:50]

EE1001: The argument is invalid.Reason: Unsupport chip type, chipType=4.
        Solution: 1.Check the input parameter range of the function. 2.Check the function invocation relationship.
        TraceBack (most recent call last):
        Task execute failed, device_id=0, stream_id=0, task_id=1, flip_num=0, task_type=83.[FUNC:GetError][FILE:stream.cc][LINE:1418]
        The argument is invalid.Reason: Unsupport chip type, chipType=4.
        The argument is invalid.Reason: rtSetOpWaitTimeOut execute failed, reason=[feature not support]
        set wait timeout failed, runtime result = 207000[FUNC:ReportCallError][FILE:log_inner.cpp][LINE:161]
        rtStreamSynchronizeWithTimeout execute failed, reason=[tsfw param illegal][FUNC:FuncErrorReason][FILE:error_message_manage.cc][LINE:50]
        synchronize stream failed, runtime result = 507001[FUNC:ReportCallError][FILE:log_inner.cpp][LINE:161]
        Task execute failed, device_id=0, stream_id=4, task_id=1, flip_num=0, task_type=87.[FUNC:GetError][FILE:stream.cc][LINE:1418]
        Failed to synchronize stream, retCode=0x7150004.[FUNC:SyncGetDevMsg][FILE:api_impl.cc][LINE:4141]
        Sync get device msg failed, retCode=0x7150004.[FUNC:GetDevErrMsg][FILE:api_impl.cc][LINE:4160]
        rtGetDevMsg execute failed, reason=[tsfw param illegal][FUNC:FuncErrorReason][FILE:error_message_manage.cc][LINE:50]
 (function npuSynchronizeDevice)
[W NPUStream.cpp:392] Warning: NPU warning, error code is 507001[Error]: 
[Error]: An internal error occurs in the task scheduler module on the device. 
        Rectify the fault based on the error information in the log, or you can ask us at follwing gitee link by issues: https://gitee.com/ascend/pytorch/issue
EH9999: Inner Error!
        rtDeviceSynchronize execute failed, reason=[tsfw param illegal][FUNC:FuncErrorReason][FILE:error_message_manage.cc][LINE:50]
EH9999  wait for compute device to finish failed, runtime result = 507001.[FUNC:ReportCallError][FILE:log_inner.cpp][LINE:161]
        TraceBack (most recent call last):
        Task execute failed, device_id=0, stream_id=4, task_id=1, flip_num=0, task_type=87.[FUNC:GetError][FILE:stream.cc][LINE:1418]
        Failed to synchronize stream, retCode=0x7150004.[FUNC:SyncGetDevMsg][FILE:api_impl.cc][LINE:4141]
        Sync get device msg failed, retCode=0x7150004.[FUNC:GetDevErrMsg][FILE:api_impl.cc][LINE:4160]
        rtGetDevMsg execute failed, reason=[tsfw param illegal][FUNC:FuncErrorReason][FILE:error_message_manage.cc][LINE:50]

EL0005: The resources are busy.
        Possible Cause: 1. The resources have been occupied. 2. The device is being reset. 3. Software is not ready.
        Solution: 1. Close applications not in use. 2. Wait for a while and try again.
        TraceBack (most recent call last):
        Memory async copy failed, device_id=0, stream_id=3, task_id=4, flip_num=0, copy_type=0, memcpy_type=0, copy_data_type=0, length=32[FUNC:GetError][FILE:stream.cc][LINE:1418]
        rtDeviceSynchronize execute failed, reason=[tsfw param illegal][FUNC:FuncErrorReason][FILE:error_message_manage.cc][LINE:50]
        wait for compute device to finish failed, runtime result = 507001.[FUNC:ReportCallError][FILE:log_inner.cpp][LINE:161]
        Task execute failed, device_id=0, stream_id=4, task_id=1, flip_num=0, task_type=87.[FUNC:GetError][FILE:stream.cc][LINE:1418]
        Failed to synchronize stream, retCode=0x7150004.[FUNC:SyncGetDevMsg][FILE:api_impl.cc][LINE:4141]
        Sync get device msg failed, retCode=0x7150004.[FUNC:GetDevErrMsg][FILE:api_impl.cc][LINE:4160]
        rtGetDevMsg execute failed, reason=[tsfw param illegal][FUNC:FuncErrorReason][FILE:error_message_manage.cc][LINE:50]

EE1001: The argument is invalid.Reason: Unsupport chip type, chipType=4.
        Solution: 1.Check the input parameter range of the function. 2.Check the function invocation relationship.
        TraceBack (most recent call last):
        Task execute failed, device_id=0, stream_id=0, task_id=1, flip_num=0, task_type=83.[FUNC:GetError][FILE:stream.cc][LINE:1418]
        The argument is invalid.Reason: Unsupport chip type, chipType=4.
        The argument is invalid.Reason: rtSetOpWaitTimeOut execute failed, reason=[feature not support]
        set wait timeout failed, runtime result = 207000[FUNC:ReportCallError][FILE:log_inner.cpp][LINE:161]
        rtStreamSynchronizeWithTimeout execute failed, reason=[tsfw param illegal][FUNC:FuncErrorReason][FILE:error_message_manage.cc][LINE:50]
        synchronize stream failed, runtime result = 507001[FUNC:ReportCallError][FILE:log_inner.cpp][LINE:161]
        Task execute failed, device_id=0, stream_id=4, task_id=1, flip_num=0, task_type=87.[FUNC:GetError][FILE:stream.cc][LINE:1418]
        Failed to synchronize stream, retCode=0x7150004.[FUNC:SyncGetDevMsg][FILE:api_impl.cc][LINE:4141]
        Sync get device msg failed, retCode=0x7150004.[FUNC:GetDevErrMsg][FILE:api_impl.cc][LINE:4160]
        rtGetDevMsg execute failed, reason=[tsfw param illegal][FUNC:FuncErrorReason][FILE:error_message_manage.cc][LINE:50]
 (function npuSynchronizeDevice)

```

Ascend/pytorch
暂停

内容风险标识

评论 (4)

Ascend/pytorch暂停 .gitee-modal { width: 500px !important; }

内容风险标识