华为昇腾NPU

# NVIDIA PyTorch 代码
import torch

x = torch.randn(10000, 10000).cuda()
y = torch.randn(10000, 10000).cuda()
for _ in range(1000):
    z = x.mm(y)
print(z)


# 改造为华为910B上可运行的代码
# 第一步：import torch后，立即import torch_npu
# 第二步：cuda()函数换为npu()
import torch
import torch_npu

x = torch.randn(10000, 10000).npu()
y = torch.randn(10000, 10000).npu()
for _ in range(1000):
    z = x.mm(y)
print(z)

# 下载代码
wget https://webcal-public.ks3-cn-beijing.ksyuncs.com/npu_chips/huawei/dp_res18_ascend.py

# 执行代码训练，自动会下载MNIST数据集
python dp_res18.py

# 下载代码
wget https://webcal-public.ks3-cn-beijing.ksyuncs.com/debug/dp_res18_ascend.py

# 执行代码训练，自动会下载MNIST数据集
python dp_res18_ascend.py

# diff dp_res18.py dp_res18_ascend.py
8a9
> import torch_npu
29c30,31
< device = 'cuda' if torch.cuda.is_available() else 'cpu'
---
> device = 'npu' if torch.npu.is_available() else 'cpu'
> print("Detect device:", device)


# 从diff两个文件的结果可以看出，除多了import torch_npu和替换了cuda→npu，其他均相同

# npu-smi info
+------------------------------------------------------------------------------------------------+
| npu-smi 23.0.3                   Version: 23.0.3                                               |
+---------------------------+---------------+----------------------------------------------------+
| NPU   Name                | Health        | Power(W)    Temp(C)           Hugepages-Usage(page)|
| Chip                      | Bus-Id        | AICore(%)   Memory-Usage(MB)  HBM-Usage(MB)        |
+===========================+===============+====================================================+
| 6     910B2               | OK            | 98.7        46                0    / 0             |
| 0                         | 0000:82:00.0  | 0           0    / 0          3330 / 65536         |
+===========================+===============+====================================================+
+---------------------------+---------------+----------------------------------------------------+
| NPU     Chip              | Process id    | Process name             | Process memory(MB)      |
+===========================+===============+====================================================+
| No running processes found in NPU 6                                                            |
+===========================+===============+====================================================+

# npu-smi info watch
NpuID(Idx)  ChipId(Idx) Pwr(W)      Temp(C)     AI Core(%)  AI Cpu(%)   Ctrl Cpu(%) Memory(%)   Memory BW(%)
6           0           98.0        44          0           0           0           5           0
6           0           97.9        44          0           0           0           5           0