add erfinv FP16 test and BF16 test #53101
Closed
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
|
你的PR提交成功，感谢你对开源项目的贡献! |
|
Sorry to inform you that baa619d's CIs have passed for more than 7 days. To prevent PR conflicts, you need to re-run all CIs manually. |
|
@Vvsmile 麻烦review~下， 谢谢 |
ZzSean
reviewed
May 23, 2023
| @@ -15,6 +15,7 @@ | |||
| #pragma once | |||
|
|
|||
| #include "paddle/phi/core/dense_tensor.h" | |||
| #include "paddle/phi/core/device_context.h" | |||
ZzSean
reviewed
May 23, 2023
| #include "paddle/phi/core/kernel_registry.h" | ||
| #include "paddle/phi/kernels/elementwise_add_kernel.h" |
ZzSean
reviewed
May 23, 2023
| template <> | ||
| struct ErfinvFunctor<float16> { | ||
| HOSTDEVICE inline float16 operator()(const float16 x) const { | ||
| auto x_ = static_cast<float>(x); |
ZzSean
reviewed
May 23, 2023
| @@ -29,7 +32,7 @@ void ErfinvGradKernel(const Context& ctx, | |||
| auto eigen_dout = EigenVector<T>::Flatten(out_grad); | |||
| auto eigen_dx = EigenVector<T>::Flatten(*x_grad); | |||
| auto& place = *ctx.eigen_device(); | |||
| constexpr T half_sqrt_pi = static_cast<T>(1 / M_2_SQRTPI); | |||
| const T half_sqrt_pi = static_cast<T>(1 / M_2_SQRTPI); | |||
There was a problem hiding this comment.
根据CI错误提示这里应该修改为const常量
ZzSean
reviewed
May 23, 2023
| @@ -110,5 +114,67 @@ def run(place): | |||
| run(place) | |||
|
|
|||
|
|
|||
| class TestErfinvFP16OP(OpTest): | |||
ZzSean
reviewed
May 23, 2023
| self.python_api = paddle.erfinv | ||
| self.dtype = np.uint16 | ||
| self.shape = [11, 17] | ||
| self.x = np.random.uniform(-1, 1, size=self.shape).astype(self.dtype) |
ZzSean
reviewed
May 23, 2023
| self.shape = [11, 17] | ||
| self.x = np.random.uniform(-1, 1, size=self.shape).astype(self.dtype) | ||
| self.x_s = convert_uint16_to_float(self.x) | ||
| self.res_ref = erfinv(self.x_s).astype(np.float32) |
|
Sorry to inform you that 26dc177's CIs have passed for more than 7 days. To prevent PR conflicts, you need to re-run all CIs manually. |
| check_variable_and_dtype(x, 'x', ['float32', 'float64'], 'erfinv') | ||
| check_variable_and_dtype( | ||
| x, 'x', ['float32', 'float64', 'float16', 'uint16'], 'erfinv' | ||
| ) |
There was a problem hiding this comment.
这个文件4358行文档可以同步更新下支持的数据类型，另外可以解决下代码冲突，应该就可以合入了
Closed
|
close due to the following PR is merged: |
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
Others
PR changes
Others
Description
add erfinv FP16 test and BF16 test