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

Add cutlass example #13

Merged

mehdi-goli merged 15 commits into codeplaysoftware:sycl-develop from aacostadiaz:aacosta/cute_demo_cutlass_example

Apr 4, 2024

Collaborator

aacostadiaz commented Apr 2, 2024

This PR adds an example using the Nvidia SM80 pipeline running on SYCL.

aacostadiaz and others added 4 commits

April 2, 2024 15:31


          Migrate cute sgemm_nt_1 to sycl

8ca1267


          Revert "Migrate cute sgemm_nt_1 to sycl"

8c71080


          Revert "Revert "Migrate cute sgemm_nt_1 to sycl""

864c67a


          Add cutlass example

1d942e8

aacostadiaz requested a review from mehdi-goli

April 2, 2024 17:49

mehdi-goli reviewed

View reviewed changes

examples/14_ampere_tf32_tensorop_gemm/CMakeLists.txt Outdated Show resolved Hide resolved

mehdi-goli reviewed

View reviewed changes

examples/14_ampere_tf32_tensorop_gemm/ampere_tf32_tensorop_gemm_cute.cpp Outdated Show resolved Hide resolved

aacostadiaz and others added 2 commits

April 3, 2024 12:01


          Update examples/14_ampere_tf32_tensorop_gemm/CMakeLists.txt

c51b3ca

Co-authored-by: Mehdi Goli <mehdi.goli@codeplay.com>


          Update examples/14_ampere_tf32_tensorop_gemm/ampere_tf32_tensorop_gem…

1e35302

…m_cute.cpp

Co-authored-by: Mehdi Goli <mehdi.goli@codeplay.com>

mehdi-goli reviewed

View reviewed changes

examples/14_ampere_tf32_tensorop_gemm/ampere_tf32_tensorop_gemm_cute.cu Outdated Show resolved Hide resolved


          Update examples/14_ampere_tf32_tensorop_gemm/ampere_tf32_tensorop_gem…

87b82f2

…m_cute.cu

Co-authored-by: Mehdi Goli <mehdi.goli@codeplay.com>

mehdi-goli reviewed

View reviewed changes

examples/cute/tutorial/CMakeLists.txt Outdated Show resolved Hide resolved

mehdi-goli reviewed

View reviewed changes

examples/cute/tutorial/sgemm_nt_1_sycl.cpp Outdated Show resolved Hide resolved


          Update examples/cute/tutorial/CMakeLists.txt

8b38c22

Co-authored-by: Mehdi Goli <mehdi.goli@codeplay.com>

mehdi-goli reviewed

View reviewed changes

include/cute/arch/copy_sm80.hpp Outdated Show resolved Hide resolved


          Update include/cute/arch/copy_sm80.hpp

Co-authored-by: Mehdi Goli <mehdi.goli@codeplay.com>

mehdi-goli reviewed

View reviewed changes

include/cute/config.hpp Show resolved Hide resolved


          Update include/cute/config.hpp

aa64581

Co-authored-by: Mehdi Goli <mehdi.goli@codeplay.com>

AD2605 reviewed

View reviewed changes

tools/util/include/cutlass/util/GPU_Clock.hpp Show resolved Hide resolved

mehdi-goli reviewed

View reviewed changes

include/cute/util/debug.hpp Outdated Show resolved Hide resolved

mehdi-goli reviewed

View reviewed changes

include/cute/util/debug.hpp Outdated Show resolved Hide resolved

mehdi-goli reviewed

View reviewed changes

include/cutlass/cutlass.h Show resolved Hide resolved

mehdi-goli reviewed

View reviewed changes

include/cutlass/cutlass.h Outdated Show resolved Hide resolved

mehdi-goli reviewed

View reviewed changes

include/cutlass/cutlass.h Show resolved Hide resolved

mehdi-goli reviewed

View reviewed changes

include/cutlass/cutlass.h Show resolved Hide resolved

mehdi-goli reviewed

View reviewed changes

include/cutlass/cutlass.h Show resolved Hide resolved

mehdi-goli reviewed

View reviewed changes

include/cutlass/cutlass.h Show resolved Hide resolved

mehdi-goli reviewed

View reviewed changes

include/cutlass/cutlass.h Show resolved Hide resolved

mehdi-goli reviewed

View reviewed changes

include/cutlass/cutlass.h Show resolved Hide resolved

mehdi-goli reviewed

View reviewed changes

include/cutlass/cutlass.h Show resolved Hide resolved

mehdi-goli reviewed

View reviewed changes

include/cutlass/cutlass.h Show resolved Hide resolved

mehdi-goli reviewed

View reviewed changes

include/cutlass/cutlass.h Show resolved Hide resolved

mehdi-goli reviewed

View reviewed changes

include/cutlass/detail/helper_macros.hpp Outdated Show resolved Hide resolved

mehdi-goli reviewed

View reviewed changes

include/cutlass/detail/helper_macros.hpp Show resolved Hide resolved

mehdi-goli approved these changes

View reviewed changes

Collaborator

mehdi-goli left a comment

LGTM! I have added comments on the files

aacostadiaz and others added 5 commits

April 3, 2024 17:34


          Update include/cute/util/debug.hpp

33f0557

Co-authored-by: Mehdi Goli <mehdi.goli@codeplay.com>


          Update include/cute/util/debug.hpp

67b7dd8

Co-authored-by: Mehdi Goli <mehdi.goli@codeplay.com>


          Update include/cutlass/detail/helper_macros.hpp

88128c2

Co-authored-by: Mehdi Goli <mehdi.goli@codeplay.com>


          Address comments

60cb33e


          Merge remote-tracking branch 'origin/aacosta/cute_demo_cutlass_exampl…

5e1eb1f

…e' into aacosta/cute_demo_cutlass_example

Collaborator

AD2605 commented Apr 4, 2024

I don;t seem to be able to neither resolve a conversation, nor approve the PR, hence in the form of this comment,
LGTM

AD2605 approved these changes

View reviewed changes

mehdi-goli merged commit 696397f into codeplaysoftware:sycl-develop

aacostadiaz deleted the aacosta/cute_demo_cutlass_example branch

April 4, 2024 08:34

aacostadiaz added a commit that referenced this pull request


          Add cutlass example (#13)

258115c

* Migrate cute sgemm_nt_1 to sycl

* Revert "Migrate cute sgemm_nt_1 to sycl"

* Revert "Revert "Migrate cute sgemm_nt_1 to sycl""

* Add cutlass example

* Update examples/14_ampere_tf32_tensorop_gemm/CMakeLists.txt

Co-authored-by: Mehdi Goli <mehdi.goli@codeplay.com>

* Update examples/14_ampere_tf32_tensorop_gemm/ampere_tf32_tensorop_gemm_cute.cpp

Co-authored-by: Mehdi Goli <mehdi.goli@codeplay.com>

* Update examples/14_ampere_tf32_tensorop_gemm/ampere_tf32_tensorop_gemm_cute.cu

Co-authored-by: Mehdi Goli <mehdi.goli@codeplay.com>

* Update examples/cute/tutorial/CMakeLists.txt

Co-authored-by: Mehdi Goli <mehdi.goli@codeplay.com>

* Update include/cute/arch/copy_sm80.hpp

Co-authored-by: Mehdi Goli <mehdi.goli@codeplay.com>

* Update include/cute/config.hpp

Co-authored-by: Mehdi Goli <mehdi.goli@codeplay.com>

* Update include/cute/util/debug.hpp

Co-authored-by: Mehdi Goli <mehdi.goli@codeplay.com>

* Update include/cute/util/debug.hpp

Co-authored-by: Mehdi Goli <mehdi.goli@codeplay.com>

* Update include/cutlass/detail/helper_macros.hpp

Co-authored-by: Mehdi Goli <mehdi.goli@codeplay.com>

* Address comments

---------

Co-authored-by: Mehdi Goli <mehdi.goli@codeplay.com>

aacostadiaz added a commit to aacostadiaz/cutlass-fork that referenced this pull request


          Add cutlass example (codeplaysoftware#13)

4db3803

* Migrate cute sgemm_nt_1 to sycl

* Revert "Migrate cute sgemm_nt_1 to sycl"

* Revert "Revert "Migrate cute sgemm_nt_1 to sycl""

* Add cutlass example

* Update examples/14_ampere_tf32_tensorop_gemm/CMakeLists.txt

Co-authored-by: Mehdi Goli <mehdi.goli@codeplay.com>

* Update examples/14_ampere_tf32_tensorop_gemm/ampere_tf32_tensorop_gemm_cute.cpp

Co-authored-by: Mehdi Goli <mehdi.goli@codeplay.com>

* Update examples/14_ampere_tf32_tensorop_gemm/ampere_tf32_tensorop_gemm_cute.cu

Co-authored-by: Mehdi Goli <mehdi.goli@codeplay.com>

* Update examples/cute/tutorial/CMakeLists.txt

Co-authored-by: Mehdi Goli <mehdi.goli@codeplay.com>

* Update include/cute/arch/copy_sm80.hpp

Co-authored-by: Mehdi Goli <mehdi.goli@codeplay.com>

* Update include/cute/config.hpp

Co-authored-by: Mehdi Goli <mehdi.goli@codeplay.com>

* Update include/cute/util/debug.hpp

Co-authored-by: Mehdi Goli <mehdi.goli@codeplay.com>

* Update include/cute/util/debug.hpp

Co-authored-by: Mehdi Goli <mehdi.goli@codeplay.com>

* Update include/cutlass/detail/helper_macros.hpp

Co-authored-by: Mehdi Goli <mehdi.goli@codeplay.com>

* Address comments

---------

Co-authored-by: Mehdi Goli <mehdi.goli@codeplay.com>

aacostadiaz added a commit to aacostadiaz/cutlass-fork that referenced this pull request


          Add cutlass example (codeplaysoftware#13)

f596e71

* Migrate cute sgemm_nt_1 to sycl

* Revert "Migrate cute sgemm_nt_1 to sycl"

* Revert "Revert "Migrate cute sgemm_nt_1 to sycl""

* Add cutlass example

* Update examples/14_ampere_tf32_tensorop_gemm/CMakeLists.txt

Co-authored-by: Mehdi Goli <mehdi.goli@codeplay.com>

* Update examples/14_ampere_tf32_tensorop_gemm/ampere_tf32_tensorop_gemm_cute.cpp

Co-authored-by: Mehdi Goli <mehdi.goli@codeplay.com>

* Update examples/14_ampere_tf32_tensorop_gemm/ampere_tf32_tensorop_gemm_cute.cu

Co-authored-by: Mehdi Goli <mehdi.goli@codeplay.com>

* Update examples/cute/tutorial/CMakeLists.txt

Co-authored-by: Mehdi Goli <mehdi.goli@codeplay.com>

* Update include/cute/arch/copy_sm80.hpp

Co-authored-by: Mehdi Goli <mehdi.goli@codeplay.com>

* Update include/cute/config.hpp

Co-authored-by: Mehdi Goli <mehdi.goli@codeplay.com>

* Update include/cute/util/debug.hpp

Co-authored-by: Mehdi Goli <mehdi.goli@codeplay.com>

* Update include/cute/util/debug.hpp

Co-authored-by: Mehdi Goli <mehdi.goli@codeplay.com>

* Update include/cutlass/detail/helper_macros.hpp

Co-authored-by: Mehdi Goli <mehdi.goli@codeplay.com>

* Address comments

---------

Co-authored-by: Mehdi Goli <mehdi.goli@codeplay.com>

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

Labels

None yet