Listed Matthew Nicely as the CUTLASS product manager.. (#364)
This commit is contained in:
parent
808c25337a
commit
62e438f450
@ -18,7 +18,7 @@
|
|||||||
* Optimal performance using [**CUDA 11.5**](https://developer.nvidia.com/cuda-downloads)
|
* Optimal performance using [**CUDA 11.5**](https://developer.nvidia.com/cuda-downloads)
|
||||||
* Updates from the community (thanks!)
|
* Updates from the community (thanks!)
|
||||||
|
|
||||||
* **Deprecation announcement:** CUTLASS plans to deprecate the following platforms in the future. Let us know if this affects your use case.
|
* **Deprecation announcement:** CUTLASS plans to deprecate the following:
|
||||||
* Maxwell and Pascal GPU architectures
|
* Maxwell and Pascal GPU architectures
|
||||||
* Ubuntu 16.04
|
* Ubuntu 16.04
|
||||||
* CUDA 10.2
|
* CUDA 10.2
|
||||||
|
@ -25,6 +25,9 @@ Aditya Atluri
|
|||||||
David Tanner
|
David Tanner
|
||||||
Manikandan Ananth
|
Manikandan Ananth
|
||||||
|
|
||||||
|
## CUTLASS Product Manager
|
||||||
|
Matthew Nicely
|
||||||
|
|
||||||
## CONTRIBUTORS
|
## CONTRIBUTORS
|
||||||
Timothy Costa
|
Timothy Costa
|
||||||
Julien Demouth
|
Julien Demouth
|
||||||
@ -56,7 +59,6 @@ Olivier Giroux
|
|||||||
Stephen Jones
|
Stephen Jones
|
||||||
Rishkul Kulkarni
|
Rishkul Kulkarni
|
||||||
Bryce Lelbach
|
Bryce Lelbach
|
||||||
Matthew Nicely
|
|
||||||
Joel McCormack
|
Joel McCormack
|
||||||
Kyrylo Perelygin
|
Kyrylo Perelygin
|
||||||
|
|
||||||
|
@ -41,7 +41,7 @@ CUTLASS 2.8 is an update to CUTLASS adding:
|
|||||||
- [Grouped GEMM:](/examples/24_gemm_grouped) similar to batched GEMM with distinct problem size per group
|
- [Grouped GEMM:](/examples/24_gemm_grouped) similar to batched GEMM with distinct problem size per group
|
||||||
- [Implicit GEMM Convolution fusion](/examples/13_two_tensor_op_fusion/) supports staging 1st convolution's output accumulator in the shared memory on Turing.
|
- [Implicit GEMM Convolution fusion](/examples/13_two_tensor_op_fusion/) supports staging 1st convolution's output accumulator in the shared memory on Turing.
|
||||||
- Optimal performance using [CUDA 11.5](https://developer.nvidia.com/cuda-downloads)
|
- Optimal performance using [CUDA 11.5](https://developer.nvidia.com/cuda-downloads)
|
||||||
- CUTLASS plans to **deprecate** the following platforms in the future. Let us know if this affects your use case.
|
- **Deprecation announcement:** CUTLASS plans to deprecate the following:
|
||||||
- Maxwell and Pascal GPU architectures
|
- Maxwell and Pascal GPU architectures
|
||||||
- Ubuntu 16.04
|
- Ubuntu 16.04
|
||||||
- CUDA 10.2
|
- CUDA 10.2
|
||||||
|
Loading…
Reference in New Issue
Block a user