mirror of
https://github.com/ROCm/composable_kernel.git
synced 2026-05-14 18:17:44 +00:00
09bc04e7a4
* Add basic fp8 definitions and prn-generator
* Format
* Add fp8<->fp32 type_convert
* Format
* Split type_convert and cast_to/from_f8
* Format
* Minor fix
* Minor fix
* Move fp8 utils to a separate header
* Add elementwise ops
* Add fp8_convert_sr
* Format
* Add element op
* Eliminate magic numbers
* Split f8_convert_sr in host and device
* Format
* Add some constexpr
* Add a datatype test
* Format
* Another format
* Add fp8<->fp16 tests
* Update type_converts
* Format
* Add fp16 casting functions
* Format
* Use seed as a runtime arg
* Use element location for PRNG
* Format
* Add fp8<->fp16 to PassThrough element op
* Clean up
* Merge host and device implementations
* Add comments on rounding modes
* Remove leftover code
* Put type_converts into a separate header
* Put random number gen to a separate header
* Rearrange f8_utils' namespaces
* Refactor type_convert.hpp
* Move f8_t definition
[ROCm/composable_kernel commit: f0c620c42e]
54 lines
1.8 KiB
C++
54 lines
1.8 KiB
C++
// SPDX-License-Identifier: MIT
|
|
// Copyright (c) 2018-2023, Advanced Micro Devices, Inc. All rights reserved.
|
|
|
|
#pragma once
|
|
|
|
#include "ck/ck.hpp"
|
|
#include "ck/utility/array.hpp"
|
|
#include "ck/utility/container_helper.hpp"
|
|
#include "ck/utility/statically_indexed_array.hpp"
|
|
#include "ck/utility/container_element_picker.hpp"
|
|
#include "ck/utility/multi_index.hpp"
|
|
#include "ck/utility/data_type.hpp"
|
|
#include "ck/utility/functional.hpp"
|
|
#include "ck/utility/functional2.hpp"
|
|
#include "ck/utility/functional3.hpp"
|
|
#include "ck/utility/functional4.hpp"
|
|
#include "ck/utility/enable_if.hpp"
|
|
#include "ck/utility/ignore.hpp"
|
|
#include "ck/utility/integral_constant.hpp"
|
|
#include "ck/utility/math.hpp"
|
|
#include "ck/utility/number.hpp"
|
|
#include "ck/utility/sequence.hpp"
|
|
#include "ck/utility/sequence_helper.hpp"
|
|
#include "ck/utility/tuple.hpp"
|
|
#include "ck/utility/tuple_helper.hpp"
|
|
#include "ck/utility/type.hpp"
|
|
#include "ck/utility/type_convert.hpp"
|
|
#include "ck/utility/magic_division.hpp"
|
|
#include "ck/utility/c_style_pointer_cast.hpp"
|
|
#include "ck/utility/is_known_at_compile_time.hpp"
|
|
#include "ck/utility/transpose_vectors.hpp"
|
|
#include "ck/utility/inner_product.hpp"
|
|
#include "ck/utility/thread_group.hpp"
|
|
#include "ck/utility/debug.hpp"
|
|
|
|
#include "ck/utility/amd_buffer_addressing.hpp"
|
|
#include "ck/utility/amd_wave_read_first_lane.hpp"
|
|
#include "ck/utility/generic_memory_space_atomic.hpp"
|
|
#include "ck/utility/get_id.hpp"
|
|
#include "ck/utility/thread_group.hpp"
|
|
#include "ck/utility/synchronization.hpp"
|
|
#include "ck/utility/amd_address_space.hpp"
|
|
#include "ck/utility/static_buffer.hpp"
|
|
#include "ck/utility/dynamic_buffer.hpp"
|
|
|
|
// TODO: remove this
|
|
#if CK_USE_AMD_INLINE_ASM
|
|
#include "ck/utility/amd_inline_asm.hpp"
|
|
#endif
|
|
|
|
#ifdef CK_USE_AMD_MFMA
|
|
#include "ck/utility/amd_xdlops.hpp"
|
|
#endif
|