Set Tensor Core MathType in conv using cudnn #34409
Merged
Conversation
This file contains 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
Update forked PaddlePaddle
Update my fork
update from PaddlePaddle
Update forked paddle repo
Update USERNAME/paddle
update Paddle USERNAME repo
update username repo
update local paddlepaddle
update paddlepaddle
… backward_TensorCore
… backward_TensorCore
|
Thanks for your contribution! |
Xreki
reviewed
Jul 27, 2021
| #if CUDA_VERSION >= 11000 | ||
| #if CUDNN_VERSION_MIN(8, 1, 0) | ||
| } else if (dev_ctx.GetComputeCapability() >= 80 && |
There was a problem hiding this comment.
前向、反向input、反向filter，设置cudnn conv算法的代码逻辑都是一样的，可以封装成一个函数。
Xreki
approved these changes
Aug 3, 2021
| VLOG(5) << "NOT use cudnn_tensor_op_math"; | ||
| } | ||
| #endif | ||
| return; |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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Outdated suggestions cannot be applied.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.
PR types
New features
PR changes
OPs
Describe
功能
当数据类型为bfloat16时，使用Tesnor Core。包括以下3部分：
ConvolutionDescriptor时，需要指明cudnnSetConvolutionMathType。该PR添加当dtype 为CUDNN_DATA_BFLOAT16时，设置MathType为CUDNN_TENSOR_OP_MATH。PSEUDO_BFLOAT16_CONFIG时，上述设置MathType的条件应改为if (dtype == CUDNN_DATA_FLOAT && allow_tf32)。由于满足PSEUDO_BFLOAT16_CONFIG与否，对性能无影响，故该PR设置MathType的条件是if (dtype == CUDNN_DATA_BFLOAT16)。CUDNN_DATA_BFLOAT16时设置MathType为CUDNN_TENSOR_OP_MATH。CUDNN_DATA_BFLOAT16时设置MathType为CUDNN_TENSOR_OP_MATH。对于前向卷积算法的选择、后向data卷积算法选择、后向filter卷积算法选择中的设置convMathType。将三部分封装成了统一的函数。
效果
通过LOG日志发现，当数据类型为bfloat16时，代码执行期望分支。