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.

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

Fix build with disabled CK (after #2523) #2598

Merged
merged 2 commits into from
Dec 13, 2023
Merged

Fix build with disabled CK (after #2523) #2598

Show file tree
Hide file tree
Changes from 1 commit
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
cbfa84b
Properly guard CK usage by MIOPEN_USE_COMPOSABLEKERNEL defines
CAHEK7 Dec 12, 2023
abd49ce
Update src/solver/conv_hip_implicit_gemm_grouped_fwd_xdlops.cpp
junliume Dec 13, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
5 changes: 3 additions & 2 deletions src/solver/conv_hip_implicit_gemm_f16f8f16_fwd_xdlops.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -44,11 +44,12 @@ namespace miopen {
namespace solver {
namespace conv {

using d_type = ck::half_t;
using c_type = ck::f8_t;
using ProblemDescription = miopen::conv::ProblemDescription;

#if MIOPEN_USE_COMPOSABLEKERNEL
using d_type = ck::half_t;
using c_type = ck::f8_t;

template <typename DataType, typename ComputeType>
using DeviceOpF8Fwd = ck::tensor_operation::device::DeviceGroupedConvFwdMultipleABD<
3,
Expand Down
6 changes: 4 additions & 2 deletions src/solver/conv_hip_implicit_gemm_grouped_fwd_xdlops.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -191,7 +191,6 @@ bool ConvHipImplicitGemmGroupFwdXdlops::CheckCKApplicability(
{
return IsCKApplicable<DeviceOpGFwdPtrs<DataType>, CKArgs>(problem);
}
#endif

#if MIOPEN_ENABLE_AI_KERNEL_TUNING
static std::vector<std::string> GetKernelAsTokens(const std::string& kernel)
Expand Down Expand Up @@ -285,7 +284,8 @@ bool PerformanceConfigHipImplicitGemmGroupFwdXdlops::RunParameterPredictionModel
}
return false;
}
#endif
#endif // MIOPEN_ENABLE_AI_KERNEL_TUNING
#endif // MIOPEN_BACKEND_HIP && MIOPEN_USE_COMPOSABLEKERNEL
Copy link
Contributor

Choose a reason for hiding this comment

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

Is it really so that AI thing depends on CK???

Copy link
Contributor Author

Choose a reason for hiding this comment

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

This particular solver? Yes.

Copy link
Contributor

Choose a reason for hiding this comment

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

Oops, I see now. Obvious.


bool PerformanceConfigHipImplicitGemmGroupFwdXdlops::IsModelApplicable(
const ExecutionContext& ctx, const ProblemDescription& problem) const
Expand Down Expand Up @@ -339,6 +339,7 @@ void PerformanceConfigHipImplicitGemmGroupFwdXdlops::HeuristicInit(

bool PerformanceConfigHipImplicitGemmGroupFwdXdlops::SetNextValue(const ProblemDescription& problem)
{
#if MIOPEN_BACKEND_HIP && MIOPEN_USE_COMPOSABLEKERNEL
junliume marked this conversation as resolved.
Show resolved Hide resolved
if(valid_kernels.empty())
{
switch(problem.GetInDataType())
Expand All @@ -362,6 +363,7 @@ bool PerformanceConfigHipImplicitGemmGroupFwdXdlops::SetNextValue(const ProblemD
return true;
}
else
#endif
return false;
}

Expand Down
Loading