mirror of
https://github.com/ROCm/composable_kernel.git
synced 2026-05-15 02:27:57 +00:00
817b2a47c6
* Add online-compiling facility
* Synchronize from fwd-v4r5 and implement host interfaces to call conv-fwd v4r4/v4r5 using on-line compiling method
* Tiny adjustment to time reporting
* Use object assignment to replace explicit bytes copying in the first kernel of v4r4/v4r5
* Use single thread to assign descriptor object to device memory
* Adjust to the workload assignment of the two kernels of v4r4 (experimental)
* Revert "Adjust to the workload assignment of the two kernels of v4r4 (experimental)"
This reverts commit eb38461456bb0c82b6c0d32cdd616e181907e20c.
* Update to make constexpr for generating descriptor types in kernel 2 of dynamic conv-fwd v4r4
* Update to dynamic conv-fwd v4r4 online-compiling
* Update to dynamic conv-fwd v4r5 online-compiling (result not accurate)
* Tiny update to driver/CMakeLists.txt
* clang-format
* Tiny comments change
* Add env OLC_DUMP_SAVE_TMP_DIR to support saving of temperary dir
* Fwd v4r5 olc perf (#39)
* added hip-clang flags that fix perf issue of online compilation
* fix bug for olc fwd-v4r5-nchw
* Move constexpr and type reference statements out of the function body in conv-fwd v4r4/v4r5 kernel wrapper
* Remove printing in hip_build_utils.cpp
* Update to root CMakeLists.txt
* Revert "Move constexpr and type reference statements out of the function body in conv-fwd v4r4/v4r5 kernel wrapper"
This reverts commit 3d2c5d8ecdd8298b72d127110500ed5b38d9835c.
Co-authored-by: Chao Liu <chao.liu2@amd.com>
Co-authored-by: Chao Liu <lc.roy86@gmail.com>
Co-authored-by: root <root@dc-smc-18.amd.com>
[ROCm/composable_kernel commit: 1685048a67]
115 lines
2.2 KiB
C++
115 lines
2.2 KiB
C++
#ifndef OLC_DRIVER_COMMON_HPP
|
|
#define OLC_DRIVER_COMMON_HPP
|
|
|
|
#include <half.hpp>
|
|
#include <vector>
|
|
#include <cassert>
|
|
|
|
// this enumerate should be synchronized with include/miopen.h
|
|
typedef enum {
|
|
appHalf = 0,
|
|
appFloat = 1,
|
|
appInt32 = 2,
|
|
appInt8 = 3,
|
|
appInt8x4 = 4,
|
|
appBFloat16 = 5,
|
|
appDouble = 6,
|
|
} appDataType_t;
|
|
|
|
namespace Driver {
|
|
|
|
template <appDataType_t typeNum>
|
|
struct get_type_from_type_enum
|
|
{
|
|
using type = float;
|
|
};
|
|
|
|
template <>
|
|
struct get_type_from_type_enum<appHalf>
|
|
{
|
|
using type = half_float::half;
|
|
};
|
|
|
|
template <>
|
|
struct get_type_from_type_enum<appFloat>
|
|
{
|
|
using type = float;
|
|
};
|
|
|
|
template <>
|
|
struct get_type_from_type_enum<appDouble>
|
|
{
|
|
using type = double;
|
|
};
|
|
|
|
template <>
|
|
struct get_type_from_type_enum<appInt32>
|
|
{
|
|
using type = int;
|
|
};
|
|
|
|
static inline int get_typeid_from_type_enum(appDataType_t t)
|
|
{
|
|
switch(t)
|
|
{
|
|
case appHalf: return (static_cast<int>('H'));
|
|
case appFloat: return (static_cast<int>('F'));
|
|
case appBFloat16: return (static_cast<int>('B'));
|
|
case appDouble: return (static_cast<int>('D'));
|
|
case appInt8:
|
|
case appInt8x4:
|
|
case appInt32: return (static_cast<int>('O'));
|
|
default: throw std::runtime_error("Only float, half, bfloat16 data type is supported."); break;
|
|
};
|
|
};
|
|
|
|
template <typename T>
|
|
static inline int get_typeid_from_type()
|
|
{
|
|
throw std::runtime_error("Unsupported typeid conversion for this type!");
|
|
};
|
|
|
|
template <>
|
|
inline int get_typeid_from_type<float>()
|
|
{
|
|
return (static_cast<int>('F'));
|
|
};
|
|
|
|
template <>
|
|
inline int get_typeid_from_type<half_float::half>()
|
|
{
|
|
return (static_cast<int>('H'));
|
|
};
|
|
|
|
template <>
|
|
inline int get_typeid_from_type<double>()
|
|
{
|
|
return (static_cast<int>('D'));
|
|
};
|
|
|
|
static inline float get_effective_average(std::vector<float>& values)
|
|
{
|
|
assert(!values.empty());
|
|
|
|
if(values.size() == 1)
|
|
return (values[0]);
|
|
else
|
|
{
|
|
float sum = 0.0f;
|
|
float maxVal = 0.0f;
|
|
|
|
for(const auto val : values)
|
|
{
|
|
if(maxVal < val)
|
|
maxVal = val;
|
|
sum += val;
|
|
};
|
|
|
|
return ((sum - maxVal) / (values.size() - 1));
|
|
};
|
|
};
|
|
|
|
} // namespace Driver
|
|
|
|
#endif
|