modify version and dcu_version

README_HIP.md

+# DeepSpeed
+
+## 安装
+DeepSpeed 支持
++ Python 3.7.
++ Python 3.8.
++ Python 3.9.
+
+### 使用pip安装
+DeepSpeed whl包下载目录：[https://cancon.hpccube.com:65024/4/main/deepspeed/dtk23.04](https://cancon.hpccube.com:65024/4/main/deepspeed/dtk23.04)
+根据对应的pytorch版本和python版本，下载对应deepspeed的whl包
+
+```shell
+pip install deepspeed* (下载的deepspeed的whl包)
+```
+
+### 使用源码安装
+编译之前，需要先安装对应版本python，安装相应的三方包依赖项，并配置DTK环境变量(以Centos7.x为例)。
+
+pytorch whl包下载目录：[https://cancon.hpccube.com:65024/4/main/pytorch/dtk23.04](https://cancon.hpccube.com:65024/4/main/pytorch/dtk23.04)
+
+根据python版本,下载对应pytorch的whl包。如果是基于pytorch1.13，需要注释掉op_builder/builder.py中大概L659： 
+```bash
+#sources[i] = str(src.relative_to(curr_file))
+```
+安装依赖项：
+```bash
+# 安装三方包的源
+yum install  epel-release  -y
+
+# 安装相关依赖项
+                        
+yum install libffi-devel -y
+yum -y install openssl openssl-devel
+                       
+yum install -y libaio-devel
+yum install -y libaio
+ls -l
+
+# 若python内未包含相关项，需基于上面安装的三方包重新源码编译python，再配置python环境
+python3 -m pip install --upgrade pip setuptools
+pip3 install wheel -i https://pypi.tuna.tsinghua.edu.cn/simple
+pip3 install ninja -i https://pypi.tuna.tsinghua.edu.cn/simple
+```
+
+下载DTK并配置环境变量:
+```bash
+# DTK tar包下载目录：光合社区/资源工具/DCU Toolkit/DTK23.04(https://cancon.hpccube.com:65024/1/main/DTK-23.04)，根据系统选择对应DTK的tar包，并解压至/opt目录。
+# 如果使用的是dtk23.04前的版本，可以参考以图片下方式修改torch中的hipify文件
+export ROCM_PATH=/opt/dtk-23.04
+source /opt/dtk-23.04/env.sh
+```
+![logo](hipify_20230511113250.png)
+
+
+编译deepspeed
+
+```bash
+# 下载源码 
+git clone -b ds-v0.9.2-rocm http://developer.hpccube.com/codes/aicomponent/deepspeed.git
+cd deepspeed
+sh requirements/run_pip.sh
+DS_BUILD_STRING=.dtk22.10.1.torch1.10 DS_BUILD_RANDOM_LTD=0 DS_BUILD_QUANTIZER=0 DS_BUILD_TRANSFORMER_INFERENCE=0 DS_BUILD_OPS=1 verbose=1 CXX=hipcc CC=hipcc python3 setup.py install bdist_wheel
+```
+
+安装deepspeed
+
+```bash
+# deepspeed的whl包会在dist文件夹生成
+pip3 install ./dist/deepspeed*
+```
+
+## Note
++ 若使用 pip install 下载安装过慢，可添加源：-i https://pypi.tuna.tsinghua.edu.cn/simple/
++ DS_BUILD_STRING为编译的版本号设置，例如版本号为.dtk22.10.1.torch1.10, dtkxxx为基于编译的dtk版本号，torchxxx为编译依赖的torch版本号等。
++ deepspeed共设置两种版本号查询方式，__version__和__dcu_version__，分别标识主版本号（与官网版本一致）和基于dcu适配的内部版本号。

deepspeed/__init__.py

@@ -36,7 +36,7 @@ from .runtime import DeepSpeedOptimizer, ZeROOptimizer
 
 from .pipe import PipelineModule
 
-from .git_version_info import version, git_hash, git_branch
+from .git_version_info import version, dcu_version, git_hash, git_branch
 
 
 def _parse_version(version_str):
@@ -47,6 +47,8 @@ def _parse_version(version_str):
 
 # Export version information
 __version__ = version
+#aiss
+__dcu_version__ = dcu_version
 __version_major__, __version_minor__, __version_patch__ = _parse_version(__version__)
 __git_hash__ = git_hash
 __git_branch__ = git_branch

deepspeed/git_version_info.py

@@ -15,6 +15,7 @@ except ModuleNotFoundError:
         version = "0.0.0"
     git_hash = '[none]'
     git_branch = '[none]'
+    dcu_version = '[none]'
 
     from .ops.op_builder.all_ops import ALL_OPS
     installed_ops = dict.fromkeys(ALL_OPS.keys(), False)

setup.py

@@ -179,7 +179,8 @@ print(f'Install Ops={install_ops}')
 # Write out version/git info.
 git_hash_cmd = "git rev-parse --short HEAD"
 git_branch_cmd = "git rev-parse --abbrev-ref HEAD"
-if command_exists('git') and 'DS_BUILD_STRING' not in os.environ:
+#if command_exists('git') and 'DS_BUILD_STRING' not in os.environ:
+if command_exists('git'):
     try:
         result = subprocess.check_output(git_hash_cmd, shell=True)
         git_hash = result.decode('utf-8').strip()
@@ -216,7 +217,7 @@ if sys.platform == "win32":
 
 # Parse the DeepSpeed version string from version.txt.
 version_str = open('version.txt', 'r').read().strip()
-
+dcu_version_str = version_str
 # Build specifiers like .devX can be added at install time. Otherwise, add the git hash.
 # Example: DS_BUILD_STRING=".dev20201022" python setup.py sdist bdist_wheel.
 
@@ -225,14 +226,16 @@ if 'DS_BUILD_STRING' in os.environ:
     # Build string env specified, probably building for distribution.
     with open('build.txt', 'w') as fd:
         fd.write(os.environ.get('DS_BUILD_STRING'))
-    version_str += os.environ.get('DS_BUILD_STRING')
+    dcu_version_str += f'+{git_hash}'+ os.environ.get('DS_BUILD_STRING')
 elif os.path.isfile('build.txt'):
     # build.txt exists, probably installing from distribution.
     with open('build.txt', 'r') as fd:
-        version_str += fd.read().strip()
+        dcu_version_str += fd.read().strip()
+    #aiss 
+        dcu_version_str += f'+{git_hash}'
 else:
     # None of the above, probably installing from source.
-    version_str += f'+{git_hash}'
+    dcu_version_str += f'+{git_hash}'
 
 torch_version = ".".join([TORCH_MAJOR, TORCH_MINOR])
 bf16_support = False
@@ -261,9 +264,10 @@ torch_info = {
     "hip_version": hip_version
 }
 
-print(f"version={version_str}, git_hash={git_hash}, git_branch={git_branch}")
+print(f"version={version_str}, dcu_version={dcu_version_str}, git_hash={git_hash}, git_branch={git_branch}")
 with open('deepspeed/git_version_info_installed.py', 'w') as fd:
     fd.write(f"version='{version_str}'\n")
+    fd.write(f"dcu_version='{dcu_version_str}'\n")
     fd.write(f"git_hash='{git_hash}'\n")
     fd.write(f"git_branch='{git_branch}'\n")
     fd.write(f"installed_ops={install_ops}\n")