mirror of
https://github.com/deepspeedai/DeepSpeed.git
synced 2025-10-21 08:43:50 +08:00
a755a9e52c
Since currently `z1.h`, `z2.h` and `z3.h` are located under
`csrc/compile`, without this patch, torch hipify will fail to identify
these hipified headers on AMD platform:
```log
In file included from torch/include/ATen/cuda/CUDAEvent.h:3,
from deepspeed/ops/csrc/includes/deepcompile.h:16,
from deepspeed/ops/csrc/compile/z1.h:6,
from deepspeed/ops/csrc/compile/z1_hip.cpp:7:
torch/include/ATen/cuda/ATenCUDAGeneral.h:3:10: fatal error: cuda.h: No such file or directory
3 | #include <cuda.h>
| ^~~~~~~~
compilation terminated.
```
Signed-off-by: Hollow Man <hollowman@opensuse.org>
41 lines
1.1 KiB
Python
41 lines
1.1 KiB
Python
# Copyright (c) Microsoft Corporation.
|
|
# SPDX-License-Identifier: Apache-2.0
|
|
|
|
# DeepSpeed Team
|
|
|
|
from .builder import TorchCPUOpBuilder
|
|
|
|
|
|
class DeepCompileBuilder(TorchCPUOpBuilder):
|
|
BUILD_VAR = "DS_BUILD_DEEP_COMPILE"
|
|
NAME = "dc"
|
|
|
|
def __init__(self):
|
|
super().__init__(name=self.NAME)
|
|
|
|
def absolute_name(self):
|
|
return f'deepspeed.ops.{self.NAME}_op'
|
|
|
|
def sources(self):
|
|
return [
|
|
'csrc/compile/deepcompile.cpp', 'csrc/compile/init.cpp', 'csrc/compile/z1.cpp', 'csrc/compile/z2.cpp',
|
|
'csrc/compile/z3.cpp', 'csrc/compile/util.cpp'
|
|
]
|
|
|
|
def libraries_args(self):
|
|
args = super().libraries_args()
|
|
return args
|
|
|
|
def include_paths(self):
|
|
import os
|
|
import torch
|
|
if self.build_for_cpu:
|
|
CUDA_INCLUDE = []
|
|
elif not self.is_rocm_pytorch():
|
|
CUDA_INCLUDE = [os.path.join(torch.utils.cpp_extension.CUDA_HOME, "include")]
|
|
else:
|
|
CUDA_INCLUDE = [
|
|
os.path.join(torch.utils.cpp_extension.ROCM_HOME, "include"),
|
|
]
|
|
return ['csrc/includes', 'csrc/compile'] + CUDA_INCLUDE
|