mirror of
https://github.com/ROCm/composable_kernel.git
synced 2026-05-11 08:50:17 +00:00
b4032629e5
* Overload output stream operator for LoopScheduler and PiplineVersion * Add Run overload accepting grid descriptors MK. * Add __device__ keyword for CalculateGridSize * Create device op GroupedGemmMultipleD * Add GroupedGemm MultipleD Tile Loop implementation. * Add an example for GroupedGemm MultipleD tile loop. * Device Op GroupedGEMMTileLoop. * Bunch of small changes in exmaple. * CkProfiler * Remove unused tparam. * Fix include statement. * Fix output stream overloads. * Do not make descriptors and check validity untill we find group. * Fix gemm desc initialization. * Revert device op * Fix compilation for DTYPES=FP16 * Validate tensor transfers paramters. * Validate on host only NK dims if M is not known. * Fix bug. * A convenient debug func for selecting threads. * Fix has main k block loop bug. * Make sure that b2c has up to date tile offset. * Output stream operator for Sequence type. * Cmake file formatting.
39 lines
856 B
C++
39 lines
856 B
C++
// SPDX-License-Identifier: MIT
|
|
// Copyright (c) 2018-2024, Advanced Micro Devices, Inc. All rights reserved.
|
|
#include <ostream>
|
|
|
|
#pragma once
|
|
|
|
#include "ck/utility/common_header.hpp"
|
|
#include "ck/tensor_description/tensor_adaptor.hpp"
|
|
|
|
namespace ck {
|
|
|
|
enum struct LoopScheduler
|
|
{
|
|
Default,
|
|
Interwave,
|
|
};
|
|
|
|
constexpr LoopScheduler make_default_loop_scheduler()
|
|
{
|
|
#if CK_EXPERIMENTAL_DEFAULT_TO_INTER_WAVE_SCHEDULING
|
|
return LoopScheduler::Interwave;
|
|
#else
|
|
return LoopScheduler::Default;
|
|
#endif // if CK_EXPERIMENTAL_DEFAULT_TO_INTER_WAVE_SCHEDULING
|
|
}
|
|
|
|
} // namespace ck
|
|
|
|
inline std::ostream& operator<<(std::ostream& os, const ck::LoopScheduler& s)
|
|
{
|
|
switch(s)
|
|
{
|
|
case ck::LoopScheduler::Default: os << "Default"; break;
|
|
case ck::LoopScheduler::Interwave: os << "Interwave"; break;
|
|
default: os << "";
|
|
}
|
|
return os;
|
|
}
|