Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

[Auto Parallel]: Speed up intra-op plan generation by 44% #5446

Merged
merged 4 commits into from
Jul 15, 2024
Merged

[Auto Parallel]: Speed up intra-op plan generation by 44% #5446

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
272fc10
Remove unnecessary calls to deepcopy
stephankoe Mar 8, 2024
324269f
Build DimSpec's difference dict only once
stephankoe Mar 8, 2024
9829bb6
Merge branch 'main' of github.com:stephankoe/ColossalAI into optimize…
stephankoe Mar 9, 2024
462db34
Fix documentation of DimSpec's difference method
stephankoe Jul 13, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
87 changes: 51 additions & 36 deletions colossalai/tensor/d_tensor/sharding_spec.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,4 +1,3 @@
from copy import deepcopy
from typing import Dict, List

from ..utils import merge_same_dim_mesh_list
Expand All @@ -23,10 +22,11 @@ class DimSpec:
Otherwise, the element in shard_list means the data will be sharded in that dimension.
"""

_DIFFERENCE_DICT = None

def __init__(self, shard_list):
self.is_replica = len(shard_list) == 0
self.shard_list = shard_list
self.build_difference_2d_dict()

def __eq__(self, other):
return str(self) == str(other)
Expand All @@ -39,24 +39,43 @@ def __repr__(self):
target += str(dim)
return target

def _convert_str_to_shard_list(self, str_spec):
@property
def difference_dict(self):
"""
Convert str_spec into shard_list.
Returns the difference dict, and lazily initializes it when needed

Argument:
str_spec(str): dim spec in str type.
Return:
difference_dict(Dict[Tuple[int, int], Union[int, float, str]]):
difference dict
"""
if self._DIFFERENCE_DICT is None:
self._DIFFERENCE_DICT = self._build_difference_2d_dict()

if str_spec == "R":
return []
if str_spec == "S0":
return [0]
if str_spec == "S1":
return [1]
if str_spec == "S01":
return [0, 1]
return self._DIFFERENCE_DICT

def build_difference_2d_dict(self):
def dim_diff(self, other):
"""
The difference between two DimSpec.

Argument:
other(DimSpec): the dim spec to compare with.

Return:
difference(int): the difference between two DimSpec.

Example:
dim_spec = DimSpec([0])
other_dim_spec = DimSpec([0, 1])
print(dim_spec.dim_diff(other_dim_spec))

Output:
5
"""
Edenzzzz marked this conversation as resolved.
Show resolved Hide resolved
difference = self.difference_dict[(str(self), str(other))]
return difference

@classmethod
def _build_difference_2d_dict(cls):
"""
Build a difference mapping for 2D device mesh case. It will be used to
compute the difference between DimSpec pairs.
Expand All @@ -67,9 +86,8 @@ def build_difference_2d_dict(self):
difference_dict = {}
for source_spec in source_spec_list:
for target_spec in target_spec_list:
spec_pair = (deepcopy(source_spec), deepcopy(target_spec))
source_shard_list = self._convert_str_to_shard_list(source_spec)
target_shard_list = self._convert_str_to_shard_list(target_spec)
source_shard_list = cls._convert_str_to_shard_list(source_spec)
target_shard_list = cls._convert_str_to_shard_list(target_spec)

# source same as target
if source_shard_list == target_shard_list:
Expand Down Expand Up @@ -112,30 +130,27 @@ def build_difference_2d_dict(self):

else:
difference = NAN
difference_dict[spec_pair] = difference
difference_dict[(source_spec, target_spec)] = difference

self.difference_dict = difference_dict
return difference_dict

def dim_diff(self, other):
@staticmethod
def _convert_str_to_shard_list(str_spec):
"""
The difference between two _DimSpec.
Convert str_spec into shard_list.

Argument:
other(_DimSpec): the dim spec to compare with.

Return:
difference(int): the difference between two _DimSpec.

Example:
dim_spec = _DimSpec([0])
other_dim_spec = _DimSpec([0, 1])
print(dim_spec.difference(other_dim_spec))

Output:
5
str_spec(str): dim spec in str type.
"""
difference = self.difference_dict[(str(self), str(other))]
return difference

if str_spec == "R":
return []
if str_spec == "S0":
return [0]
if str_spec == "S1":
return [1]
if str_spec == "S01":
return [0, 1]


class ShardingSpec:
Expand Down
89 changes: 52 additions & 37 deletions colossalai/tensor/sharding_spec.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,5 +1,4 @@
import operator
from copy import deepcopy
from functools import reduce

import torch
Expand Down Expand Up @@ -27,10 +26,11 @@ class _DimSpec:
Otherwise, the element in shard_list means the data will be sharded in that dimension.
"""

_DIFFERENCE_DICT = None

def __init__(self, shard_list):
self.is_replica = len(shard_list) == 0
self.shard_list = shard_list
self.build_difference_2d_dict()

def __eq__(self, other):
return str(self) == str(other)
Expand All @@ -43,37 +43,55 @@ def __repr__(self):
target += str(dim)
return target

def _convert_str_to_shard_list(self, str_spec):
@property
def difference_dict(self):
"""
Convert str_spec into shard_list.
Returns the difference dict, and lazily initializes it when needed

Argument:
str_spec(str): dim spec in str type.
Return:
difference_dict(Dict[Tuple[int, int], Union[int, float, str]]):
difference dict
"""
if self._DIFFERENCE_DICT is None:
self._DIFFERENCE_DICT = self._build_difference_2d_dict()

if str_spec == "R":
return []
if str_spec == "S0":
return [0]
if str_spec == "S1":
return [1]
if str_spec == "S01":
return [0, 1]
return self._DIFFERENCE_DICT

def build_difference_2d_dict(self):
def difference(self, other):
"""
The difference between two _DimSpec.

Argument:
other(_DimSpec): the dim spec to compare with.

Return:
difference(int): the difference between two _DimSpec.

Example:
dim_spec = _DimSpec([0])
other_dim_spec = _DimSpec([0, 1])
print(dim_spec.difference(other_dim_spec))

Output:
5
Edenzzzz marked this conversation as resolved.
Show resolved Hide resolved
"""
difference = self.difference_dict[(str(self), str(other))]
return difference

@classmethod
def _build_difference_2d_dict(cls):
"""
Build a difference mapping for 2D device mesh case. It will be used to
compute the difference between DimSpec pairs.
compute the difference between _DimSpec pairs.
"""

source_spec_list = ["R", "S0", "S1", "S01"]
target_spec_list = ["R", "S0", "S1", "S01"]
difference_dict = {}
for source_spec in source_spec_list:
for target_spec in target_spec_list:
spec_pair = (deepcopy(source_spec), deepcopy(target_spec))
source_shard_list = self._convert_str_to_shard_list(source_spec)
target_shard_list = self._convert_str_to_shard_list(target_spec)
source_shard_list = cls._convert_str_to_shard_list(source_spec)
target_shard_list = cls._convert_str_to_shard_list(target_spec)

# source same as target
if source_shard_list == target_shard_list:
Expand Down Expand Up @@ -116,30 +134,27 @@ def build_difference_2d_dict(self):

else:
difference = NAN
difference_dict[spec_pair] = difference
difference_dict[(source_spec, target_spec)] = difference

self.difference_dict = difference_dict
return difference_dict

def difference(self, other):
@staticmethod
def _convert_str_to_shard_list(str_spec):
"""
The difference between two _DimSpec.
Convert str_spec into shard_list.

Argument:
other(_DimSpec): the dim spec to compare with.

Return:
difference(int): the difference between two _DimSpec.

Example:
dim_spec = _DimSpec([0])
other_dim_spec = _DimSpec([0, 1])
print(dim_spec.difference(other_dim_spec))

Output:
5
str_spec(str): dim spec in str type.
"""
difference = self.difference_dict[(str(self), str(other))]
return difference

if str_spec == "R":
return []
if str_spec == "S0":
return [0]
if str_spec == "S1":
return [1]
if str_spec == "S01":
return [0, 1]


class ShardingSpecException(Exception):
Expand Down
Loading