基于__torch_dispatch__机制的dump方法

embedded/2024/12/22 21:27:10/

基于__torch_dispatch__机制的dump方法

  • 1.参考链接
  • 2.原理
  • 3.代码
  • 4.效果

之前拦截torch和torch.Tensor的办法,在处理backward时,不能看到aten算子的细节.以下基于__torch_dispatch__机制的方案更节约代码,且能看到调用栈

1.参考链接

[原理] (https://dev-discuss.pytorch.org/t/what-and-why-is-torch-dispatch/557)

2.原理

在这里插入图片描述

3.代码

python">import os
os.environ['CUDA_LAUNCH_BLOCKING'] = '1'
import torch
from torch import nn
import math
import torch.nn.functional as F
from torch.autograd import Variable
import time
import os
import threadingdevice="cuda"
from torch.utils._python_dispatch import TorchDispatchMode
import inspect
import traceback
from dataclasses import dataclass
from typing import Any@dataclass
class _ProfilerState:cls: Anyobject: Any = Nonelock=threading.Lock()
gindex=0
def save_tensor(name,args,index=0):if isinstance(args,torch.Tensor):print(name,index,args.shape)global gindexlock.acquire()torch.save(args,"{}_{}_{}_{}.pt".format(device,gindex,name,index))gindex+=1lock.release()if isinstance(args,tuple):for idx,x in enumerate(args):save_tensor(name,x,index+idx)class TorchDumpDispatchMode(TorchDispatchMode):def __init__(self,parent):super().__init__()self.parent=parentdef __torch_dispatch__(self, func, types, args=(), kwargs=None):func_packet = func._overloadpacket        if kwargs is None:kwargs = {}        enable_dump=Falseif func_packet.__name__ not in ["detach"]:enable_dump=Trueprint(f"Profiling {func_packet.__name__}") for idx,stack in enumerate(inspect.stack()):print(f'{"*"*idx}{stack.filename}{stack.lineno}')if enable_dump:     save_tensor(f"{func_packet.__name__}-input",args)ret= func(*args, **kwargs)if enable_dump:save_tensor(f"{func_packet.__name__}-output",ret)return retclass TorchDumper:_CURRENT_Dumper = Nonedef __init__(self,schedule: Any):self.p= _ProfilerState(schedule) def __enter__(self):assert TorchDumper._CURRENT_Dumper is NoneTorchDumper._CURRENT_Dumper = selfif self.p.object is None:o = self.p.cls(self)o.__enter__()self.p.object = oelse:self.p.object.step()return selfdef __exit__(self, exc_type, exc_val, exc_tb):TorchDumper._CURRENT_Dumper = Noneif self.p.object is not None:self.p.object.__exit__(exc_type, exc_val, exc_tb)class Attention(nn.Module):def __init__(self,max_seq_len,head_dim,flash):super().__init__()self.flash = flashself.dropout=0self.attn_dropout = nn.Dropout(self.dropout)self.head_dim=head_dimif not self.flash:print("WARNING: using slow attention. Flash Attention requires PyTorch >= 2.0")mask = torch.full((1, 1, max_seq_len, max_seq_len), float("-inf")).to(device)mask = torch.triu(mask, diagonal=1).half().to(device)self.register_buffer("mask", mask)		def forward(self,xq: torch.Tensor,xk: torch.Tensor,xv: torch.Tensor):if self.flash:output = torch.nn.functional.scaled_dot_product_attention(xq, xk, xv,attn_mask=None, dropout_p=self.dropout if self.training else 0.0, is_causal=True)else:_xk=xk.clone()t=_xk.transpose(2, 3)scores = torch.matmul(xq,t)scores = scores/math.sqrt(self.head_dim)a=self.mask[:, :, :seqlen, :seqlen]scores = scores+ascores = F.softmax(scores.float(), dim=-1)scores = scores.type_as(xq)scores = self.attn_dropout(scores)output = torch.matmul(scores, xv)  return outputdef main(flash,bs, n_local_heads, seqlen, head_dim):torch.random.manual_seed(1)q = torch.ones((bs, n_local_heads, seqlen, head_dim),dtype=torch.float32).half().to(device)k = torch.ones((bs, n_local_heads, seqlen, head_dim),dtype=torch.float32).half().to(device)v = torch.ones((bs, n_local_heads, seqlen, head_dim),dtype=torch.float32).half().to(device)q.data.normal_(0, 0.1)k.data.normal_(0, 0.1)v.data.normal_(0, 0.1)q=Variable(q, requires_grad=True).to(device)k=Variable(k, requires_grad=True).to(device)v=Variable(v, requires_grad=True).to(device)gt= torch.randint(0,head_dim,(bs*n_local_heads*seqlen,1)).reshape(-1).to(device)loss_func=nn.CrossEntropyLoss().to(device)model=Attention(seqlen,head_dim,flash).half().to(device)optim = torch.optim.SGD([q,k,v], lr=1.1)with TorchDumper(TorchDumpDispatchMode):for i in range(1):output = model(q,k,v)loss=loss_func(output.reshape(-1,head_dim),gt)loss.backward()  optim.step()print("{:.5f},{:.5f},{:.5f},{:.5f}".format(q.sum().item(),k.sum().item(),v.sum().item(),loss.item()))bs, n_local_heads, seqlen, head_dim = 8, 8, 512, 64
main(False,bs, n_local_heads, seqlen, head_dim)

4.效果

Profiling clone
/home/user/proj/attention/attention_torch_dispatch_dumper.py60
*/home/user/proj/attention/attention_torch_dispatch_dumper.py109
**/home/anaconda3/envs/nvidia_training/lib/python3.10/site-packages/torch/nn/modules/module.py1527
***/home/anaconda3/envs/nvidia_training/lib/python3.10/site-packages/torch/nn/modules/module.py1518
****/home/user/proj/attention/attention_torch_dispatch_dumper.py144
*****/home/user/proj/attention/attention_torch_dispatch_dumper.py151
clone-input 0 torch.Size([8, 8, 512, 64])
clone-output 0 torch.Size([8, 8, 512, 64])
Profiling transpose
/home/user/proj/attention/attention_torch_dispatch_dumper.py60
*/home/user/proj/attention/attention_torch_dispatch_dumper.py110
**/home/anaconda3/envs/nvidia_training/lib/python3.10/site-packages/torch/nn/modules/module.py1527
***/home/anaconda3/envs/nvidia_training/lib/python3.10/site-packages/torch/nn/modules/module.py1518
****/home/user/proj/attention/attention_torch_dispatch_dumper.py144
*****/home/user/proj/attention/attention_torch_dispatch_dumper.py151
transpose-input 0 torch.Size([8, 8, 512, 64])
transpose-output 0 torch.Size([8, 8, 512, 64])
Profiling expand
/home/user/proj/attention/attention_torch_dispatch_dumper.py60
*/home/user/proj/attention/attention_torch_dispatch_dumper.py111
**/home/anaconda3/envs/nvidia_training/lib/python3.10/site-packages/torch/nn/modules/module.py1527
***/home/anaconda3/envs/nvidia_training/lib/python3.10/site-packages/torch/nn/modules/module.py1518
****/home/user/proj/attention/attention_torch_dispatch_dumper.py144
*****/home/user/proj/attention/attention_torch_dispatch_dumper.py151
expand-input 0 torch.Size([8, 8, 512, 64])
expand-output 0 torch.Size([8, 8, 512, 64])
Profiling view
/home/user/proj/attention/attention_torch_dispatch_dumper.py60
*/home/user/proj/attention/attention_torch_dispatch_dumper.py111
**/home/anaconda3/envs/nvidia_training/lib/python3.10/site-packages/torch/nn/modules/module.py1527
***/home/anaconda3/envs/nvidia_training/lib/python3.10/site-packages/torch/nn/modules/module.py1518
****/home/user/proj/attention/attention_torch_dispatch_dumper.py144
*****/home/user/proj/attention/attention_torch_dispatch_dumper.py151
view-input 0 torch.Size([8, 8, 512, 64])
view-output 0 torch.Size([8, 8, 512, 64])
Profiling expand
/home/user/proj/attention/attention_torch_dispatch_dumper.py60
*/home/user/proj/attention/attention_torch_dispatch_dumper.py111
**/home/anaconda3/envs/nvidia_training/lib/python3.10/site-packages/torch/nn/modules/module.py1527
***/home/anaconda3/envs/nvidia_training/lib/python3.10/site-packages/torch/nn/modules/module.py1518
****/home/user/proj/attention/attention_torch_dispatch_dumper.py144
*****/home/user/proj/attention/attention_torch_dispatch_dumper.py151
expand-input 0 torch.Size([8, 8, 64, 512])
expand-output 0 torch.Size([8, 8, 64, 512])
Profiling view
/home/user/proj/attention/attention_torch_dispatch_dumper.py60
*/home/user/proj/attention/attention_torch_dispatch_dumper.py111
**/home/anaconda3/envs/nvidia_training/lib/python3.10/site-packages/torch/nn/modules/module.py1527
***/home/anaconda3/envs/nvidia_training/lib/python3.10/site-packages/torch/nn/modules/module.py1518
****/home/user/proj/attention/attention_torch_dispatch_dumper.py144
*****/home/user/proj/attention/attention_torch_dispatch_dumper.py151
view-input 0 torch.Size([8, 8, 64, 512])
view-output 0 torch.Size([8, 8, 64, 512])
Profiling bmm
/home/user/proj/attention/attention_torch_dispatch_dumper.py60
*/home/user/proj/attention/attention_torch_dispatch_dumper.py111
**/home/anaconda3/envs/nvidia_training/lib/python3.10/site-packages/torch/nn/modules/module.py1527
***/home/anaconda3/envs/nvidia_training/lib/python3.10/site-packages/torch/nn/modules/module.py1518
****/home/user/proj/attention/attention_torch_dispatch_dumper.py144
*****/home/user/proj/attention/attention_torch_dispatch_dumper.py151
bmm-input 0 torch.Size([64, 512, 64])
bmm-input 1 torch.Size([64, 64, 512])
bmm-output 0 torch.Size([64, 512, 64])
bmm-output 1 torch.Size([64, 64, 512])
Profiling _unsafe_view

http://www.ppmy.cn/embedded/19903.html

相关文章

代购系统建站丨独立站建站丨商品选品上架API接口

代购系统建站丨独立站建站丨商品选品上架API接口

建立一个代购系统或独立站，并集成商品选品上架API接口，是一个涉及多个环节和技术的复杂过程。以下是一个大致的步骤指南： 淘宝代购集运系统演示站地址：https://o0b.cn/anzexi获取测试账号，添加taobao2024api薇好友获取…
阅读更多...
【介绍下IDM的实用功能】

【介绍下IDM的实用功能】

🎥博主：程序员不想YY啊 💫CSDN优质创作者，CSDN实力新星，CSDN博客专家 🤗点赞🎈收藏⭐再看💫养成习惯 ✨希望本文对您有所裨益，如有不足之处，欢迎在评论区提出…
阅读更多...
接口测试|超详细面试题【附答案】

接口测试|超详细面试题【附答案】

今天给姐妹们整理了一套超详细的附答案的接口测试面试题，姐妹们快学起来吧~ 接口测试的重要性，相信不用我多说了。接口测试是现在软件测试工程师一个加分项。因为很多朋友一开始做了几年的软件测试都是在做功能测试，做界面UI的测试&#xff…
阅读更多...
探索Java设计模式：模板方法模式

探索Java设计模式：模板方法模式

探索Java设计模式：深入理解与实践模板方法模式 模板方法模式（Template Method Pattern）是一种行为型设计模式，它定义了一个算法的框架，并允许子类在不改变算法整体结构的情况下重定义某些步骤。在Java编程中&#xff…
阅读更多...
C语言学习/复习36

C语言学习/复习36

一、程序的环境与预处理 二、翻译环境与执行环境 三、运行环境 四、预编译(预处理)详解
阅读更多...
Python 中空间数据的 10 个基本操作

Python 中空间数据的 10 个基本操作

读取几何图形首先，让我们从阅读几何图形开始。 来自 csv geoms = pd.read_csv(geometries.csv) 想象一下文件在列几何体下包含多边形，我们现在必须将它们转换为几何类型（默认情况下它们将被读取为字符串）。通常，几何图形将以wkt格式，我们用shapely库进行转换 # if th…
阅读更多...
Cookie 和 Session

Cookie 和 Session

一，Cookie Cookie是客户端存储数据的一种机制，浏览器中的数据来自服务器，但是在程序运行过程中也是有一些数据需要在浏览器这边存储，并在下次访问时再发给服务器，比如说，上次访问时间，用户身份…
阅读更多...
k8s安装KubeVirt

k8s安装KubeVirt

要在Kubernetes上安装KubeVirt以实现虚拟机的自动化控制，并创建虚拟机，你需要遵循以下步骤。请注意，这里假设你已经成功安装了Kubernetes和Kube-OVN。Kube-OVN是为Kubernetes设计的一个CNI插件，提供了高级网络功能，但是…
阅读更多...
最新文章

Copyright @ 2022~2023