[Allocator] Introduce tensorpool_mkl_allocator#54
Open
yuanhu2435 wants to merge 1 commit intochangqi1:mainfrom
Open
[Allocator] Introduce tensorpool_mkl_allocator#54yuanhu2435 wants to merge 1 commit intochangqi1:mainfrom
yuanhu2435 wants to merge 1 commit intochangqi1:mainfrom
Conversation
It combines tensorpool_allocator and mkl_allocator to improve allocator performance for both small size and large size memory allocation. Add an env value "TENSORPOOL_MKL_LARGE_SIZE" to set large size threshold. It is by default 512K. Signed-off-by: Lin Xie <lin.xie@intel.com> Signed-off-by: Yuan Hu <yuan1.hu@intel.com>
Owner
|
@yuanhu2435 Thanks. I got your perf data from shoucai model, but I didn't catch the perf differences both small size and large size. Did you test shoucai model perf on small batch size and large batch size? I could see the MKLAllocator's latency is lowest then others, not TensorpoolMKLAllocator. So would you please give us two situations about TensorpoolMKLAllocator latency == MKLAllocator latency < TensorPoolAllocator latency and TensorpoolMKLAllocator latency == TensorPoolAllocator latency < MKLAllocator latency, right? |
|
I think we need to collect more perf data for more models since this is the fundamental change. |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Tensorpool mkl allocator combines tensorpool_allocator and mkl_allocator to improve allocator performance for both small size and large size memory allocation.
To confirm our allocator is effective, we test it on "shoucai" model.
Test env: CPU Intel(R) Xeon(R) Platinum 8358 CPU @ 2.60GHz, 1 socket, 32 cores, lock frequency to 2.6GHz
Command line:
$python3 graph_runner.py --input-graph=sub_graph_external.pbtxt --input-data=placeholder_dump.jsonResult