mirror of
https://github.com/hpcaitech/ColossalAI.git
synced 2026-04-30 20:04:42 +00:00
32efe8e740
* [fx] modify the calculation of node_size in MetaInfoProp for activation checkpointing usages * [fx] modify the calculation of node_size in MetaInfoProp for activation checkpointing usages * [fx] modify the calculation of node_size in MetaInfoProp for activation checkpointing usages * [fx] merge development into main (#1) * [fx] activation checkpointing using Chen strategies. * [fx] add test for ckpt_solver_chen * [fx] add vanilla activation checkpoint search with test on resnet and densenet * [fx] add a namespace code for solver_chen. * [fx] fix the false interpretation of algorithm 3 in https://arxiv.org/abs/1604.06174. * [fx] fix lowercase naming conventions. * [fx] simplify test for ckpt. * [fx] add rules to linearize computation graphs for searching. (#2) * [fx] modify the calculation of node_size in MetaInfoProp for activation checkpointing usages * [fx] modify the calculation of node_size in MetaInfoProp for activation checkpointing usages * [fx] modify the calculation of node_size in MetaInfoProp for activation checkpointing usages * [fx] merge development into main (#1) * [fx] activation checkpointing using Chen strategies. * [fx] add test for ckpt_solver_chen * [fx] add vanilla activation checkpoint search with test on resnet and densenet * [fx] add a namespace code for solver_chen. * [fx] fix the false interpretation of algorithm 3 in https://arxiv.org/abs/1604.06174. * [fx] fix lowercase naming conventions. * [fx] simplify test for ckpt. * [fx] fix test and algorithm bugs in activation checkpointing. * [fx] polish ckpt_test. * [fx] add rules to linearize computation graphs for searching. * [fx] remove chen_sqrt for sake of simplicity * [fx] remove chen_sqrt for sake of simplicity * [fx] remove chen_sqrt for sake of simplicity * [fx] remove chen_sqrt for sake of simplicity * [fx] fix inconsistencies. * [fx] fix MetaInfoProp. * [fx] fix MetaInfoProp. * [fx] consider MetaInfoProp for inplace operands. * [fx] consider MetaInfoProp for inplace operands. * [fx] consider MetaInfoProp for inplace operands. * [fx] consider MetaInfoProp for inplace operands. * [fx] consider MetaInfoProp for inplace operands. * [fx] add profiler for fx nodes. * [fx] add profiler for fx nodes. * [fx] add profiler for fx nodes. * [fx] add profiler for fx nodes. * [fx] add profiler for fx nodes. * [fx] add profiler for fx nodes. * [fx] add profiler for fx nodes. * [fx] fix error in tests. * [fx] unfix bug. * [fx] unfix bug.
23 lines
1.2 KiB
Python
23 lines
1.2 KiB
Python
from typing import Tuple, Union
|
|
import torch
|
|
from ..registry import meta_profiler_function
|
|
|
|
|
|
@meta_profiler_function.register(torch.nn.functional.avg_pool1d)
|
|
@meta_profiler_function.register(torch.nn.functional.avg_pool2d)
|
|
@meta_profiler_function.register(torch.nn.functional.avg_pool3d)
|
|
@meta_profiler_function.register(torch.nn.functional.max_pool1d)
|
|
@meta_profiler_function.register(torch.nn.functional.max_pool2d)
|
|
@meta_profiler_function.register(torch.nn.functional.max_pool3d)
|
|
@meta_profiler_function.register(torch.nn.functional.adaptive_avg_pool1d)
|
|
@meta_profiler_function.register(torch.nn.functional.adaptive_avg_pool2d)
|
|
@meta_profiler_function.register(torch.nn.functional.adaptive_avg_pool3d)
|
|
@meta_profiler_function.register(torch.nn.functional.adaptive_max_pool1d)
|
|
@meta_profiler_function.register(torch.nn.functional.adaptive_max_pool2d)
|
|
@meta_profiler_function.register(torch.nn.functional.adaptive_max_pool3d)
|
|
def torch_nn_func_pooling(input: torch.Tensor, *args, **kwargs) -> Tuple[int, int]:
|
|
# all pooling could be considered as going over each input element only once (https://stackoverflow.com/a/67301217)
|
|
flops = input.numel()
|
|
macs = 0
|
|
return flops, macs
|