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

disable atomicAdd for C Output Vector Length = 1 with 16bit data type #1737

Open
wants to merge 1 commit into
base: develop
Choose a base branch
from
Open

disable atomicAdd for C Output Vector Length = 1 with 16bit data type #1737

wants to merge 1 commit into from
+154 −128

Conversation

zjing14
Copy link
Contributor

@zjing14 zjing14 commented Dec 10, 2024

No description provided.

@zjing14
Copy link
Contributor Author

zjing14 commented Dec 10, 2024

@aska-0096 @carlushuang

@zjing14
Copy link
Contributor Author

zjing14 commented Dec 13, 2024

@bartekxk

bartekxk
bartekxk reviewed Dec 17, 2024
View reviewed changes
include/ck/tensor_operation/gpu/device/impl/device_gemm_multiple_d_xdl_cshuffle_v3.hpp
@@ -153,6 +158,11 @@ struct DeviceGemmMultiD_Xdl_CShuffle_V3 : public DeviceGemmMultipleDSplitK<ALayo
throw std::runtime_error("wrong! GridwiseGemm has invalid setting");
}

if((!IsHWSupportAtomicAdd) && (arg.KBatch > 1))
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

  1. Can we move it to IsSupported?
  2. (CDEShuffleBlockTransferScalarPerVectors{}[I0] > 1) || (sizeof(CDataType) > 2); Can we improve this condition? Types smaller than 2 are not supported even if ScalarPerVector is divisible by 2 and bf16 is supported only for gfx942

Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

@zjing14

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@bartekxk bartekxk bartekxk left review comments

@junliume junliume Awaiting requested review from junliume junliume is a code owner

@illsilin illsilin Awaiting requested review from illsilin illsilin is a code owner

@carlushuang carlushuang Awaiting requested review from carlushuang carlushuang is a code owner

@qianfengz qianfengz Awaiting requested review from qianfengz qianfengz is a code owner

@aosewski aosewski Awaiting requested review from aosewski aosewski is a code owner

@poyenc poyenc Awaiting requested review from poyenc poyenc is a code owner

@geyyer geyyer Awaiting requested review from geyyer geyyer is a code owner

@andriy-ca andriy-ca Awaiting requested review from andriy-ca andriy-ca is a code owner

At least 1 approving review is required to merge this pull request.

Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
2 participants
@zjing14 @bartekxk