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.

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

adding 3d bn gtest #3385

Open
wants to merge 8 commits into
base: develop
Choose a base branch
from
Open

adding 3d bn gtest #3385

wants to merge 8 commits into from

Conversation

bghimireamd
Copy link
Contributor

No description provided.

const
{
std::string dimension = std::is_same<TestCase, BN2DTestCase>::value ? "2D"
Copy link
Contributor

Choose a reason for hiding this comment

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

We should start enforcing invalid types with compile-time failures (not just here, but for all of our tests). You could use std::enable_if, but it's so ugly...here's a cleaner idea:

constexpr int dimension = std::is_same<TestCase, BN2DTestCase>::value ? 2
            : std::is_same<TestCase, BN3DTestCase>::value ? 3
            : -1;
static_assert(dimension > 0);
<snip>
std::ostringstream oss;
oss << tensor_name + "_" + api_name + dimension + "D_" + info.index;
return oss.str();

// bfp16
TEST_P(GPU_BN_CK_BWD_Large_BFP16, DISABLED_BnV2LargeBWDCKbfp16) {}
TEST_P(GPU_BN_OCL_BWD_Large_BFP16, BnV2LargeBWDOCLbfp16) {}
// // // bfp16
Copy link
Contributor

Choose a reason for hiding this comment

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

extra //'s


// fp16
// // fp16
Copy link
Contributor

Choose a reason for hiding this comment

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

extra //'s

testing::ValuesIn({testBNAPIV2})),
TestNameGenerator<BN3DTestCase>());

// // bfp16
Copy link
Contributor

Choose a reason for hiding this comment

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

extra //'s


// fp32
// // fp32
Copy link
Contributor

Choose a reason for hiding this comment

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

extra //'s

TEST_P(GPU_BN_FWD_Train_Large_FP32, BnV2LargeFWD_TrainCKfp32) {}
TEST_P(GPU_BNFWDTrainSmall2D_FP32, BnV1SmallFWD_TrainCKfp32) {}
TEST_P(GPU_BNFWDTrainLarge2D_FP32, BnV2LargeFWD_TrainCKfp32) {}
TEST_P(GPU_BNFWDTrainSmall3D_FP32, BnV1SmallFWD_TrainC_3DKfp32) {}

// // // fp64
Copy link
Contributor

Choose a reason for hiding this comment

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

extra //'s

testing::Combine(testing::ValuesIn(Network3DBN<BN3DTestCase>()),
testing::ValuesIn({miopenTensorNCDHW}),
testing::ValuesIn({testBNAPIV1, testBNAPIV2})),
TestNameGenerator<BN3DTestCase>());

// // bfp16
Copy link
Contributor

Choose a reason for hiding this comment

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

extra //'s

testing::Combine(testing::ValuesIn(Network3DBN<BN3DTestCase>()),
testing::ValuesIn({miopenTensorNCDHW}),
testing::ValuesIn({testBNAPIV1, testBNAPIV2})),
TestNameGenerator<BN3DTestCase>());
// // fp32
Copy link
Contributor

Choose a reason for hiding this comment

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

extra //'s

testing::ValuesIn({miopenTensorNCHW}),
testing::ValuesIn({testBNAPIV2})),
TestNameGenerator());
TestNameGenerator<BN2DTestCase>());
// // fp64
Copy link
Contributor

Choose a reason for hiding this comment

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

extra //'s

testing::ValuesIn({miopenTensorNCHW, miopenTensorNHWC}),
testing::ValuesIn({testBNAPIV2})),
TestNameGenerator());
TestNameGenerator<BN2DTestCase>());
Copy link
Contributor

Choose a reason for hiding this comment

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

clang-format should clean these up as well

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Projects
None yet
Development

Successfully merging this pull request may close these issues.

3 participants