mirror of
https://github.com/ROCm/composable_kernel.git
synced 2026-05-27 08:25:46 +00:00
* enable gfx940 * switch between intrinsic mfma routines on mi100/200 and mi300 * fix mfma_int8 on MI300 * disable 2 int8 examples on MI300 * Update cmake-ck-dev.sh * restore gitignore file * modify Jenkinsfile to the internal repo * Bump rocm-docs-core from 0.24.0 to 0.29.0 in /docs/sphinx Bumps [rocm-docs-core](https://github.com/RadeonOpenCompute/rocm-docs-core) from 0.24.0 to 0.29.0. - [Release notes](https://github.com/RadeonOpenCompute/rocm-docs-core/releases) - [Changelog](https://github.com/RadeonOpenCompute/rocm-docs-core/blob/develop/CHANGELOG.md) - [Commits](https://github.com/RadeonOpenCompute/rocm-docs-core/compare/v0.24.0...v0.29.0) --- updated-dependencies: - dependency-name: rocm-docs-core dependency-type: direct:production update-type: version-update:semver-minor ... Signed-off-by: dependabot[bot] <support@github.com> * initial enablement of gfx950 * fix clang format * disable examples 31 and 41 int8 on gfx950 * add code * fix build wip * fix xx * now can build * naming * minor fix * wip fix * fix macro for exp2; fix warpgemm a/b in transposedC * unify as tuple_array * Update the required Python version to 3.9 * Update executable name in test scripts * re-structure tuple/array to avoid spill * Merge function templates * Fix format * Add constraint to array<> ctor * Re-use function * Some minor changes * remove wrong code in store_raw() * fix compile issue in transpose * Rename enum Rename 'cood_transform_enum' to 'coord_transform_enum' * let more integral_constant->constant, and formating * make sure thread_buffer can be tuple/array * temp fix buffer_store spill * not using custom data type by default, now we can have ISA-level same code as opt_padding * fix compile error, fp8 not ready now * fix fp8 duplicated move/shift/and/or problem * Default use CK_TILE_FLOAT_TO_FP8_STOCHASTIC rounding mode * fix scratch in fp8 kernel * update some readme * fix merge from upstream * sync with upstream * sync upstream again * sync 22 * remove unused * fix clang-format * update README of ck_tile example * fix several issue * let python version to be 3.8 as minimal * remove ck_tile example from default cmake target like all/install/check * remove mistake * 1).support receipe in generate.py 2).use simplified mask type 3).change left/right to pass into karg * fix some bug in group-mode masking and codegen. update README * F8 quantization for FMHA forward (#1224) * Add SAccElementFunction, PComputeElementFunction, OAccElementFunction in pipeline * Add element function to fmha api * Adjust P elementwise function * Fix bug of elementwise op, our elementwise op is not inout * Add some elementwise op, prepare to quantization * Let generate.py can generate different elementwise function * To prevent compiler issue, remove the elementwise function we have not used. * Remove f8 pipeline, we should share the same pipeline even in f8 * Remove remove_cvref_t * Avoid warning * Fix wrong fp8 QK/KV block gemm setting * Check fp8 rounding error in check_err() * Set fp8 rounding error for check_err() * Use CK_TILE_FLOAT_TO_FP8_STANDARD as default fp8 rounding mode * 1. codgen the f8 api and kernel 2. f8 host code * prevent warning in filter mode * Remove not-in-use elementwise function kargs * Remove more not-in-use elementwise function kargs * Small refinements in C++ source files * Use conditional_t<> to simplify code * Support heterogeneous argument for binary function types * Re-use already-existing scales<> functor template * Fix wrong value produced by saturating * Generalize the composes<> template * Unify saturates<> implementation * Fix type errors in composes<> * Extend less_equal<> * Reuse the existing template less_equal<> in check_err() * Add equal<float> & equal<double> * Rename check_err() parameter * Rename check_err() parameter * Add FIXME comment for adding new macro in future * Remove unnecessary cast to void * Eliminate duplicated code * Avoid dividing api pool into more than 2 groups * Use more clear variable names * Use affirmative condition in if stmt * Remove blank lines * Donot perfect forwarding in composes<> * To fix compile error, revert generate.py back to4439cc107d* Fix bug of p element function * Add compute element op to host softmax * Remove element function in api interface * Extract user parameter * Rename pscale and oscale variable * rename f8 to fp8 * rename more f8 to fp8 * Add pipeline::operator() without element_functor * 1. Remove deprecated pipeline enum 2. Refine host code parameter * Use quantization range as input * 1. Rename max_dtype to dtype_max. 2. Rename scale to scale_s 3.Add init description * Refine description * prevent early return * unify _squant kernel name in cpp, update README * Adjust the default range. * Refine error message and bias range * Add fp8 benchmark and smoke test * fix fp8 swizzle_factor=4 case --------- Co-authored-by: Po Yen Chen <PoYen.Chen@amd.com> Co-authored-by: carlushuang <carlus.huang@amd.com> --------- Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: illsilin <Illia.Silin@amd.com> Co-authored-by: Illia Silin <98187287+illsilin@users.noreply.github.com> Co-authored-by: Jing Zhang <jizha@amd.com> Co-authored-by: zjing14 <zhangjing14@gmail.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> Co-authored-by: Po-Yen, Chen <PoYen.Chen@amd.com> Co-authored-by: rocking <ChunYu.Lai@amd.com> [ROCm/composable_kernel commit:db376dd8a4]
160 lines
5.4 KiB
C++
160 lines
5.4 KiB
C++
// SPDX-License-Identifier: MIT
|
|
// Copyright (c) 2018-2023, Advanced Micro Devices, Inc. All rights reserved.
|
|
|
|
#pragma once
|
|
|
|
#include <ostream>
|
|
#include <string>
|
|
|
|
#include "ck_tile/core.hpp"
|
|
#include "ck_tile/ops/fmha.hpp"
|
|
|
|
// keep this in sync with ck_tile::GenericAttentionMaskEnum
|
|
enum class mask_enum
|
|
{
|
|
no_mask = 0,
|
|
mask_top_left,
|
|
mask_bottom_right,
|
|
window_generic,
|
|
};
|
|
|
|
struct mask_info
|
|
{
|
|
mask_enum type;
|
|
ck_tile::index_t y, x;
|
|
ck_tile::index_t left, right; // FA style SWA left/right
|
|
|
|
void serialize(std::ostream& os) const
|
|
{
|
|
if(type == mask_enum::no_mask)
|
|
os << "n";
|
|
else if(type == mask_enum::mask_top_left)
|
|
os << "t(" << left << ":" << right << ")";
|
|
else if(type == mask_enum::mask_bottom_right)
|
|
os << "b(" << left << ":" << right << ")";
|
|
else
|
|
{
|
|
os << "g(" << y << ":" << x << ")";
|
|
}
|
|
}
|
|
static mask_info decode(std::string str, ck_tile::index_t seqlen_q, ck_tile::index_t seqlen_k)
|
|
{
|
|
ck_tile::index_t x_total = seqlen_k;
|
|
ck_tile::index_t y_total = seqlen_q;
|
|
mask_info tmp;
|
|
auto found_0 = str.find(':');
|
|
if(found_0 != std::string::npos)
|
|
{
|
|
std::string t = str.substr(0, found_0);
|
|
std::string v = str.substr(found_0 + 1);
|
|
if(t == "xt" || t == "xb")
|
|
{
|
|
// xformer style sliding window attn from top-left
|
|
ck_tile::index_t window_size = atoi(v.c_str());
|
|
ck_tile::index_t left_size = -1;
|
|
ck_tile::index_t right_size = 0;
|
|
if(window_size > 0)
|
|
{
|
|
left_size = window_size / 2;
|
|
right_size = window_size - 1 - left_size;
|
|
}
|
|
auto r = ck_tile::make_generic_attention_mask_coordinates_from_lr_window(
|
|
left_size, right_size, y_total, x_total, t == "xt");
|
|
|
|
tmp.type = t == "xt" ? mask_enum::mask_top_left : mask_enum::mask_bottom_right;
|
|
tmp.y = r.at(ck_tile::number<0>{});
|
|
tmp.x = r.at(ck_tile::number<1>{});
|
|
tmp.left = left_size;
|
|
tmp.right = right_size;
|
|
}
|
|
else
|
|
{
|
|
auto found_1 = v.find(",");
|
|
if(found_1 == std::string::npos)
|
|
{
|
|
printf("not supported value %s, %s\n", v.c_str(), str.c_str());
|
|
assert(0);
|
|
}
|
|
tmp.type = mask_enum::window_generic;
|
|
ck_tile::index_t v0 = atoi(v.substr(0, found_1).c_str());
|
|
ck_tile::index_t v1 = atoi(v.substr(found_1 + 1).c_str());
|
|
// TODO: some validation
|
|
if(t == "t")
|
|
{
|
|
tmp.type = mask_enum::mask_top_left;
|
|
auto r = ck_tile::make_generic_attention_mask_coordinates_from_lr_window(
|
|
v0, v1, y_total, x_total, true);
|
|
tmp.y = r.at(ck_tile::number<0>{});
|
|
tmp.x = r.at(ck_tile::number<1>{});
|
|
tmp.left = v0;
|
|
tmp.right = v1;
|
|
}
|
|
else if(t == "b")
|
|
{
|
|
tmp.type = mask_enum::mask_bottom_right;
|
|
auto r = ck_tile::make_generic_attention_mask_coordinates_from_lr_window(
|
|
v0, v1, y_total, x_total, false);
|
|
tmp.y = r.at(ck_tile::number<0>{});
|
|
tmp.x = r.at(ck_tile::number<1>{});
|
|
tmp.left = v0;
|
|
tmp.right = v1;
|
|
}
|
|
else if(t == "g")
|
|
{
|
|
tmp.y = v0;
|
|
tmp.x = v1;
|
|
tmp.left = v0; // TODO: don't use this?
|
|
tmp.right = v1;
|
|
}
|
|
else
|
|
{
|
|
printf("not supported type %s, %s\n", t.c_str(), str.c_str());
|
|
assert(0);
|
|
}
|
|
}
|
|
}
|
|
else
|
|
{
|
|
auto set_causal_top_left = [&]() {
|
|
tmp.type = mask_enum::mask_top_left;
|
|
tmp.y = seqlen_q;
|
|
tmp.x = 1;
|
|
tmp.left = -1;
|
|
tmp.right = 0;
|
|
};
|
|
auto set_causal_bottom_right = [&]() {
|
|
tmp.type = mask_enum::mask_bottom_right;
|
|
tmp.y = seqlen_q;
|
|
tmp.x = seqlen_k - seqlen_q + 1;
|
|
tmp.left = -1;
|
|
tmp.right = 0;
|
|
};
|
|
if(str == "t")
|
|
set_causal_top_left();
|
|
else if(str == "b")
|
|
set_causal_bottom_right();
|
|
else
|
|
{
|
|
tmp.type = static_cast<mask_enum>(atoi(str.c_str()));
|
|
if(tmp.type == mask_enum::mask_top_left)
|
|
{
|
|
set_causal_top_left();
|
|
}
|
|
else if(tmp.type == mask_enum::mask_bottom_right)
|
|
{
|
|
set_causal_bottom_right();
|
|
}
|
|
}
|
|
}
|
|
return tmp;
|
|
}
|
|
|
|
friend std::ostream& operator<<(std::ostream& os, const mask_info& mi);
|
|
};
|
|
|
|
inline std::ostream& operator<<(std::ostream& os, const mask_info& mi)
|
|
{
|
|
mi.serialize(os);
|
|
return os;
|
|
}
|