ROCm/composable_kernel
1
0
Fork 0
mirror of https://github.com/ROCm/composable_kernel.git synced 2026-05-12 09:16:52 +00:00
Code Issues Packages Projects Releases Wiki Activity

sync 22

Browse Source
This commit is contained in:
carlushuang
2024-03-26 16:30:50 +00:00
parent f955af6ff7
commit 97902de98c
16 changed files with 1723 additions and 299 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
example/64_fpAintB_gemm/CMakeLists.txt Normal file
View File

@@ -0,0 +1,5 @@
if(GPU_TARGETS MATCHES "gfx11")
add_custom_target(example_fpAintB_gemm_wmma)
add_example_executable(example_fp16int8_gemm_wmma fp16int8_gemm_wmma.cpp)
add_dependencies(example_fpAintB_gemm_wmma example_fp16int8_gemm_wmma)
endif()

123
example/64_fpAintB_gemm/common.hpp Normal file
View File

@@ -0,0 +1,123 @@
// SPDX-License-Identifier: MIT
// Copyright (c) 2018-2023, Advanced Micro Devices, Inc. All rights reserved.
#pragma once
#include <cstdlib>
#include <iostream>
#include <initializer_list>
#include <numeric>
#include "ck/ck.hpp"
#include "ck/tensor_operation/gpu/device/gemm_specialization.hpp"
#include "ck/tensor_operation/gpu/device/tensor_layout.hpp"
#include "ck/tensor_operation/gpu/element/element_wise_operation.hpp"
#include "ck/utility/data_type.hpp"
#include "ck/library/utility/check_err.hpp"
#include "ck/library/utility/device_memory.hpp"
#include "ck/library/utility/fill.hpp"
#include "ck/library/utility/host_tensor.hpp"
#include "ck/library/utility/host_tensor_generator.hpp"
#include "ck/library/utility/literals.hpp"
#include "ck/library/reference_tensor_operation/cpu/reference_fpAintB_gemm.hpp"
struct ProblemSize final
{
ck::index_t M = 3840;
ck::index_t N = 4096;
ck::index_t K = 4096;
ck::index_t StrideA = 4096;
ck::index_t StrideB = 4096;
ck::index_t StrideC = 4096;
};
struct ExecutionConfig final
{
bool do_verification = true;
int init_method = 1;
bool time_kernel = false;
};
template <ck::index_t... Is>
using S = ck::Sequence<Is...>;
using Row = ck::tensor_layout::gemm::RowMajor;
using Col = ck::tensor_layout::gemm::ColumnMajor;
using PassThrough = ck::tensor_operation::element_wise::PassThrough;
template <typename IntType>
struct UnsignedWeightPreprocessor
{
};
template <>
struct UnsignedWeightPreprocessor<int8_t>
{
using UnsignedWeight = Tensor<uint8_t>;
using SignedWeight = Tensor<int8_t>;
static UnsignedWeight convert(SignedWeight const& Input)
{
UnsignedWeight Output = Input.template CopyAsType<uint8_t>();
auto f_kn = [&](auto k, auto n) {
const uint8_t adder = 128;
int8_t v_signed_weight;
uint8_t v_unsigned_weight;
ck::tensor_operation::element_wise::PassThrough{}(v_signed_weight, Input(k, n));
v_unsigned_weight = ck::type_convert<uint8_t>(v_signed_weight) + adder;
Output(k, n) = v_unsigned_weight;
};
make_ParallelTensorFunctor(f_kn, Input.mDesc.GetLengths()[0], Input.mDesc.GetLengths()[1])(
std::thread::hardware_concurrency());
return Output;
}
UnsignedWeight operator()(SignedWeight const& Input) { return convert(Input); }
};
inline bool
parse_cmd_args(int argc, char* argv[], ProblemSize& problem_size, ExecutionConfig& config)
{
if(argc == 1)
{
// use default case
}
else if(argc == 4)
{
config.do_verification = std::stoi(argv[1]);
config.init_method = std::stoi(argv[2]);
config.time_kernel = std::stoi(argv[3]);
}
else if(argc == 10)
{
config.do_verification = std::stoi(argv[1]);
config.init_method = std::stoi(argv[2]);
config.time_kernel = std::stoi(argv[3]);
problem_size.M = std::stoi(argv[4]);
problem_size.N = std::stoi(argv[5]);
problem_size.K = std::stoi(argv[6]);
problem_size.StrideA = std::stoi(argv[7]);
problem_size.StrideB = std::stoi(argv[8]);
problem_size.StrideC = std::stoi(argv[9]);
}
else
{
std::cerr << "arg1: verification (0=no, 1=yes)" << std::endl
<< "arg2: initialization (0=no init, 1=integer value, 2=decimal value)"
<< std::endl
<< "arg3: time kernel (0=no, 1=yes)" << std::endl
<< "arg4 to 9: M (256x), N(128x), K(32x), StrideA, StrideB, StrideC" << std::endl;
return false;
}
return true;
}

93
example/64_fpAintB_gemm/fp16int8_gemm_wmma.cpp Normal file
View File

@@ -0,0 +1,93 @@
// SPDX-License-Identifier: MIT
// Copyright (c) 2018-2023, Advanced Micro Devices, Inc. All rights reserved.
#include "common.hpp"
#include "ck/tensor_operation/gpu/device/impl/device_fpAintB_gemm_wmma.hpp"
// Implementation follows the paper:
// Kim, Young Jin, Rawn Henry, Raffy Fahim, and Hany Hassan Awadalla. “Who Says Elephants Can’t Run:
// Bringing Large Scale MoE Models into Cloud Scale Production.” arXiv, November 17, 2022.
// https://doi.org/10.48550/arXiv.2211.10017. Assume weight (Matrix B) is add preprocess to
// unsigned.
// The DeviceOp is CDataType = ADataType * Dequant(BDataType) * ScaleDataType
// The HostRef is CDataType = ADataType * Dequant(QuantDataType) * ScaleDataType
// TODO: Current implementation consume more VGPR than expected.
using ADataType = ck::half_t;
using QuantDataType = int8_t;
using BDataType = uint8_t;
using ScaleDataType = ck::half_t;
using AccDataType = float;
using CShuffleDataType = float;
using CDataType = ck::half_t;
using ALayout = Row;
using BLayout = Col;
using CLayout = Row;
using AElementOp = PassThrough;
using BElementOp = PassThrough;
using CElementOp = PassThrough;
static constexpr auto GemmDefault = ck::tensor_operation::device::GemmSpecialization::MNKPadding;
// clang-format off
using DeviceGemmInstance = ck::tensor_operation::device::DeviceFpAintBGemm_Wmma_CShuffle
< ALayout,
BLayout,
CLayout,
ADataType,
BDataType,
ScaleDataType,
CDataType,
AccDataType,
CShuffleDataType,
AElementOp,
BElementOp,
CElementOp,
GemmDefault,
1, // Prefetch stage
128, // BlockSize
64, // MPerBlock
128, // NPerBlock
64, // KPerBlock
8, // K1
16, // MPerWmma
16, // NPerWmma
2, // M-Repeat // M-PerWmma / M-Repeat = M-Wave
4, // N-Repeat // N-PerWmma / N-Repeat = N-Wave
S<4, 32, 1>,
S<1, 0, 2>,
S<1, 0, 2>,
2,
8,
8,
true,
S<4, 32, 1>,
S<1, 0, 2>,
S<1, 0, 2>,
2,
8,
8,
true,
1, // C shuffle (M Repeat) Per store
1, // C shuffle (N Repeat) Per store
S<1, 32, 1, 4>,
8>;
// clang-format on
using ReferenceGemmInstance = ck::tensor_operation::host::ReferencefpAintBGemm<ADataType,
QuantDataType,
ScaleDataType,
CDataType,
AccDataType,
AElementOp,
BElementOp,
CElementOp>;
#include "run_gemm_example.inc"
int main(int argc, char* argv[]) { return !run_gemm_example(argc, argv); }

172
example/64_fpAintB_gemm/run_gemm_example.inc Normal file
View File

@@ -0,0 +1,172 @@
// SPDX-License-Identifier: MIT
// Copyright (c) 2018-2023, Advanced Micro Devices, Inc. All rights reserved.
#pragma once
bool run_gemm(const ProblemSize& problem_size, const ExecutionConfig& config)
{
#if defined(BUILD_INT4_EXAMPLE) && defined(CK_EXPERIMENTAL_BIT_INT_EXTENSION_INT4)
static_assert(sizeof(ck::int4_t) == sizeof(int8_t));
#endif
using namespace ck::literals;
auto& [M, N, K, StrideA, StrideB, StrideC] = problem_size;
auto f_host_tensor_descriptor =
[](std::size_t row, std::size_t col, std::size_t stride, auto layout) {
if constexpr(std::is_same_v<decltype(layout), ck::tensor_layout::gemm::RowMajor>)
{
return HostTensorDescriptor({row, col}, {stride, 1_uz});
}
else
{
return HostTensorDescriptor({row, col}, {1_uz, stride});
}
};
Tensor<ADataType> a_m_k(f_host_tensor_descriptor(M, K, StrideA, ALayout{}));
Tensor<QuantDataType> quant_b_k_n(f_host_tensor_descriptor(K, N, StrideB, BLayout{}));
// assume scale tensor is [1, n]
Tensor<ScaleDataType> scale_k_n(f_host_tensor_descriptor(K, N, 0, Row{}));
switch(config.init_method)
{
case 0: break;
case 1:
ck::utils::FillUniformDistributionIntegerValue<ADataType>{-1.f, 1.f}(a_m_k);
ck::utils::FillUniformDistributionIntegerValue<QuantDataType>{-1.f, 1.f}(quant_b_k_n);
ck::utils::FillUniformDistributionIntegerValue<ScaleDataType>{-1.f, 1.f}(scale_k_n);
break;
case 2:
ck::utils::FillUniformDistribution<ADataType>{-1.f, 1.f}(a_m_k);
ck::utils::FillUniformDistribution<QuantDataType>{-1.f, 1.f}(quant_b_k_n);
ck::utils::FillUniformDistribution<ScaleDataType>{-1.f, 1.f}(scale_k_n);
break;
default:
ck::utils::FillUniformDistribution<ADataType>{-1.f, 1.f}(a_m_k);
ck::utils::FillUniformDistribution<QuantDataType>{-1.f, 1.f}(quant_b_k_n);
ck::utils::FillUniformDistribution<ScaleDataType>{-1.f, 1.f}(scale_k_n);
}
UnsignedWeightPreprocessor<QuantDataType> preprocessor;
Tensor<BDataType> b_k_n = preprocessor(quant_b_k_n);
Tensor<CDataType> c_m_n_host_result(f_host_tensor_descriptor(M, N, StrideC, CLayout{}));
Tensor<CDataType> c_m_n_device_result(f_host_tensor_descriptor(M, N, StrideC, CLayout{}));
std::cout << "a_m_k: " << a_m_k.mDesc << std::endl;
std::cout << "b_k_n: " << b_k_n.mDesc << std::endl;
std::cout << "scale_k_n: " << scale_k_n.mDesc << std::endl;
std::cout << "c_m_n: " << c_m_n_host_result.mDesc << std::endl;
#ifdef BUILD_INT4_EXAMPLE
DeviceMem a_m_k_device_buf(sizeof(KernelADataType) * a_m_k.mDesc.GetElementSpaceSize());
DeviceMem b_k_n_device_buf(sizeof(KernelBDataType) * b_k_n.mDesc.GetElementSpaceSize());
DeviceMem c_m_n_device_buf(sizeof(KernelCDataType) *
c_m_n_device_result.mDesc.GetElementSpaceSize());
const Tensor<KernelADataType> a_m_k_converted(a_m_k);
const Tensor<KernelBDataType> b_k_n_converted(b_k_n);
a_m_k_device_buf.ToDevice(a_m_k_converted.mData.data());
b_k_n_device_buf.ToDevice(b_k_n_converted.mData.data());
#else
DeviceMem a_m_k_device_buf(sizeof(ADataType) * a_m_k.mDesc.GetElementSpaceSize());
DeviceMem b_k_n_device_buf(sizeof(BDataType) * b_k_n.mDesc.GetElementSpaceSize());
DeviceMem scale_k_n_device_buf(sizeof(ScaleDataType) * scale_k_n.mDesc.GetElementSpaceSize());
DeviceMem c_m_n_device_buf(sizeof(CDataType) * c_m_n_device_result.mDesc.GetElementSpaceSize());
a_m_k_device_buf.ToDevice(a_m_k.mData.data());
b_k_n_device_buf.ToDevice(b_k_n.mData.data());
scale_k_n_device_buf.ToDevice(scale_k_n.mData.data());
#endif
auto a_element_op = AElementOp{};
auto b_element_op = BElementOp{};
auto c_element_op = CElementOp{};
// do GEMM
auto gemm = DeviceGemmInstance{};
auto invoker = gemm.MakeInvoker();
auto argument = gemm.MakeArgument(
#ifdef BUILD_INT4_EXAMPLE
static_cast<KernelADataType*>(a_m_k_device_buf.GetDeviceBuffer()),
static_cast<KernelBDataType*>(b_k_n_device_buf.GetDeviceBuffer()),
static_cast<KernelCDataType*>(c_m_n_device_buf.GetDeviceBuffer()),
#else
static_cast<ADataType*>(a_m_k_device_buf.GetDeviceBuffer()),
static_cast<BDataType*>(b_k_n_device_buf.GetDeviceBuffer()),
static_cast<ScaleDataType*>(scale_k_n_device_buf.GetDeviceBuffer()),
static_cast<CDataType*>(c_m_n_device_buf.GetDeviceBuffer()),
#endif
M,
N,
K,
StrideA,
StrideB,
StrideC,
a_element_op,
b_element_op,
c_element_op);
if(!gemm.IsSupportedArgument(argument))
{
std::cerr << gemm.GetTypeString() << " does not support this problem" << std::endl;
return true;
}
float ave_time = invoker.Run(argument, StreamConfig{nullptr, config.time_kernel});
std::size_t flop = 2_uz * M * N * K;
std::size_t num_btype =
sizeof(ADataType) * M * K + sizeof(BDataType) * K * N + sizeof(CDataType) * M * N;
float tflops = static_cast<float>(flop) / 1.E9 / ave_time;
float gb_per_sec = num_btype / 1.E6 / ave_time;
std::cout << "Perf: " << ave_time << " ms, " << tflops << " TFlops, " << gb_per_sec << " GB/s, "
<< gemm.GetTypeString() << std::endl;
if(config.do_verification)
{
auto ref_gemm = ReferenceGemmInstance{};
auto ref_invoker = ref_gemm.MakeInvoker();
auto ref_argument = ref_gemm.MakeArgument(a_m_k,
quant_b_k_n,
scale_k_n,
c_m_n_host_result,
a_element_op,
b_element_op,
c_element_op);
ref_invoker.Run(ref_argument);
#ifdef BUILD_INT4_EXAMPLE
Tensor<CDataType> c_m_n_device_result_converted(c_m_n_host_result.mDesc);
c_m_n_device_buf.FromDevice(c_m_n_device_result_converted.mData.data());
c_m_n_device_result = c_m_n_device_result_converted.CopyAsType<CDataType>();
return ck::utils::check_err(c_m_n_device_result_converted, c_m_n_host_result);
#else
c_m_n_device_buf.FromDevice(c_m_n_device_result.mData.data());
return ck::utils::check_err(c_m_n_device_result, c_m_n_host_result);
#endif
}
return true;
}
bool run_gemm_example(int argc, char* argv[])
{
ProblemSize problem_size;
ExecutionConfig config;
return !parse_cmd_args(argc, argv, problem_size, config) || run_gemm(problem_size, config);
}