Skip to content

GitLab

Commit ae3d6cb6 authored by Jing Zhang's avatar Jing Zhang
Browse files

fixed block_sync_lds

parents 760b0c75 b62926dc
Hide whitespace changes
Inline Side-by-side
Showing with 1361 additions and 248 deletions
library/include/ck/library/tensor_operation_instance/gpu/grouped_convolution_backward_data_bilinear.hpp 0 → 100644
View file @ ae3d6cb6
// SPDX-License-Identifier: MIT
// Copyright (c) 2024, Advanced Micro Devices, Inc. All rights reserved.
#pragma once
#include "ck/ck.hpp"
#include "ck/tensor_operation/gpu/device/tensor_layout.hpp"
#include "ck/tensor_operation/gpu/device/device_grouped_conv_bwd_data_multiple_d.hpp"
#include "ck/tensor_operation/gpu/element/element_wise_operation.hpp"
#include "ck/library/tensor_operation_instance/device_operation_instance_factory.hpp"
namespace ck {
namespace tensor_operation {
namespace device {
namespace instance {
#ifdef CK_ENABLE_FP16
void add_device_grouped_conv3d_bwd_data_xdl_bilinear_ndhwgk_gkzyxc_ndhwgc_f16_instances(
std::vector<std::unique_ptr<DeviceGroupedConvBwdDataMultipleD<3,
NDHWGK,
GKZYXC,
Tuple<NDHWGC>,
NDHWGC,
F16,
F16,
Tuple<F16>,
F16,
PassThrough,
PassThrough,
Bilinear>>>& instances);
#endif
#ifdef CK_ENABLE_FP32
void add_device_grouped_conv3d_bwd_data_xdl_bilinear_ndhwgk_gkzyxc_ndhwgc_f32_instances(
std::vector<std::unique_ptr<DeviceGroupedConvBwdDataMultipleD<3,
NDHWGK,
GKZYXC,
Tuple<NDHWGC>,
NDHWGC,
F32,
F32,
Tuple<F32>,
F32,
PassThrough,
PassThrough,
Bilinear>>>& instances);
#endif
#ifdef CK_ENABLE_BF16
void add_device_grouped_conv3d_bwd_data_xdl_bilinear_ndhwgk_gkzyxc_ndhwgc_bf16_instances(
std::vector<std::unique_ptr<DeviceGroupedConvBwdDataMultipleD<3,
NDHWGK,
GKZYXC,
Tuple<NDHWGC>,
NDHWGC,
BF16,
BF16,
Tuple<BF16>,
BF16,
PassThrough,
PassThrough,
Bilinear>>>& instances);
#endif
template <ck::index_t NumDimSpatial,
typename OutLayout,
typename WeiLayout,
typename InLayout,
typename OutDataType,
typename WeiDataType,
typename InDataType,
typename ComputeTypeA,
typename ComputeTypeB>
struct DeviceOperationInstanceFactory<
ck::tensor_operation::device::DeviceGroupedConvBwdDataMultipleD<
NumDimSpatial,
OutLayout,
WeiLayout,
Tuple<InLayout>,
InLayout,
OutDataType,
WeiDataType,
Tuple<InDataType>,
InDataType,
ck::tensor_operation::element_wise::PassThrough,
ck::tensor_operation::element_wise::PassThrough,
ck::tensor_operation::element_wise::Bilinear,
ComputeTypeA,
ComputeTypeB>>
{
using DeviceOp =
DeviceGroupedConvBwdDataMultipleD<NumDimSpatial,
OutLayout,
WeiLayout,
Tuple<InLayout>,
InLayout,
OutDataType,
WeiDataType,
Tuple<InDataType>,
InDataType,
ck::tensor_operation::element_wise::PassThrough,
ck::tensor_operation::element_wise::PassThrough,
ck::tensor_operation::element_wise::Bilinear,
ComputeTypeA,
ComputeTypeB>;
static auto GetInstances()
{
std::vector<std::unique_ptr<DeviceOp>> op_ptrs;
if constexpr(NumDimSpatial == 3)
{
if constexpr(is_same_v<InLayout, NDHWGC> && is_same_v<WeiLayout, GKZYXC> &&
is_same_v<OutLayout, NDHWGK>)
{
#ifdef CK_ENABLE_FP16
if constexpr(is_same_v<InDataType, F16> && is_same_v<WeiDataType, F16> &&
is_same_v<OutDataType, F16> && is_same_v<ComputeTypeA, F16> &&
is_same_v<ComputeTypeB, F16>)
{
add_device_grouped_conv3d_bwd_data_xdl_bilinear_ndhwgk_gkzyxc_ndhwgc_f16_instances(
op_ptrs);
}
#endif
#ifdef CK_ENABLE_FP32
else if constexpr(is_same_v<InDataType, F32> && is_same_v<WeiDataType, F32> &&
is_same_v<OutDataType, F32> && is_same_v<ComputeTypeA, F32> &&
is_same_v<ComputeTypeB, F32>)
{
add_device_grouped_conv3d_bwd_data_xdl_bilinear_ndhwgk_gkzyxc_ndhwgc_f32_instances(
op_ptrs);
}
#endif
#ifdef CK_ENABLE_BF16
else if constexpr(is_same_v<InDataType, BF16> && is_same_v<WeiDataType, BF16> &&
is_same_v<OutDataType, BF16> && is_same_v<ComputeTypeA, BF16> &&
is_same_v<ComputeTypeB, BF16>)
{
add_device_grouped_conv3d_bwd_data_xdl_bilinear_ndhwgk_gkzyxc_ndhwgc_bf16_instances(
op_ptrs);
}
#endif
}
}
return op_ptrs;
}
};
} // namespace instance
} // namespace device
} // namespace tensor_operation
} // namespace ck
library/include/ck/library/tensor_operation_instance/gpu/grouped_convolution_forward_bilinear.hpp 0 → 100644
View file @ ae3d6cb6
// SPDX-License-Identifier: MIT
// Copyright (c) 2024, Advanced Micro Devices, Inc. All rights reserved.
#pragma once
#include <vector>
#include <memory>
#include "ck/ck.hpp"
#include "ck/tensor_operation/gpu/device/device_grouped_conv_fwd_multiple_abd.hpp"
#include "ck/tensor_operation/gpu/device/tensor_layout.hpp"
#include "ck/tensor_operation/gpu/element/element_wise_operation.hpp"
#include "ck/library/tensor_operation_instance/device_operation_instance_factory.hpp"
namespace ck {
namespace tensor_operation {
namespace device {
namespace instance {
using PassThrough = ck::tensor_operation::element_wise::PassThrough;
using Bilinear = ck::tensor_operation::element_wise::Bilinear;
#ifdef CK_ENABLE_BF16
// grouped conv3d forward, NDHWGC/GKZYXC/NDHWGK
void add_device_grouped_conv3d_fwd_xdl_bilinear_ndhwgc_gkzyxc_ndhwgk_bf16_instances(
std::vector<std::unique_ptr<DeviceGroupedConvFwdMultipleABD<3,
NDHWGC,
GKZYXC,
ck::Tuple<NDHWGK>,
NDHWGK,
BF16,
BF16,
ck::Tuple<BF16>,
BF16,
PassThrough,
PassThrough,
Bilinear>>>& instances);
#endif
#ifdef CK_ENABLE_FP16
void add_device_grouped_conv3d_fwd_xdl_bilinear_ndhwgc_gkzyxc_ndhwgk_f16_instances(
std::vector<std::unique_ptr<DeviceGroupedConvFwdMultipleABD<3,
NDHWGC,
GKZYXC,
ck::Tuple<NDHWGK>,
NDHWGK,
F16,
F16,
ck::Tuple<F16>,
F16,
PassThrough,
PassThrough,
Bilinear>>>& instances);
#endif
#ifdef CK_ENABLE_FP32
void add_device_grouped_conv3d_fwd_xdl_bilinear_ndhwgc_gkzyxc_ndhwgk_f32_instances(
std::vector<std::unique_ptr<DeviceGroupedConvFwdMultipleABD<3,
NDHWGC,
GKZYXC,
ck::Tuple<NDHWGK>,
NDHWGK,
F32,
F32,
ck::Tuple<F32>,
F32,
PassThrough,
PassThrough,
Bilinear>>>& instances);
#endif
#ifdef CK_ENABLE_INT8
void add_device_grouped_conv3d_fwd_xdl_bilinear_ndhwgc_gkzyxc_ndhwgk_int8_instances(
std::vector<std::unique_ptr<DeviceGroupedConvFwdMultipleABD<3,
NDHWGC,
GKZYXC,
ck::Tuple<NDHWGK>,
NDHWGK,
int8_t,
int8_t,
ck::Tuple<int8_t>,
int8_t,
PassThrough,
PassThrough,
Bilinear>>>& instances);
#endif
template <ck::index_t NumDimSpatial,
typename InLayout,
typename WeiLayout,
typename DLayouts,
typename OutLayout,
typename InDataType,
typename WeiDataType,
typename DDataTypes,
typename OutDataType,
typename ComputeType>
struct DeviceOperationInstanceFactory<ck::tensor_operation::device::DeviceGroupedConvFwdMultipleABD<
NumDimSpatial,
InLayout,
WeiLayout,
DLayouts,
OutLayout,
InDataType,
WeiDataType,
DDataTypes,
OutDataType,
ck::tensor_operation::element_wise::PassThrough,
ck::tensor_operation::element_wise::PassThrough,
ck::tensor_operation::element_wise::Bilinear,
ComputeType>>
{
using DeviceOp =
DeviceGroupedConvFwdMultipleABD<NumDimSpatial,
InLayout,
WeiLayout,
DLayouts,
OutLayout,
InDataType,
WeiDataType,
DDataTypes,
OutDataType,
ck::tensor_operation::element_wise::PassThrough,
ck::tensor_operation::element_wise::PassThrough,
ck::tensor_operation::element_wise::Bilinear,
ComputeType>;
static auto GetInstances()
{
std::vector<std::unique_ptr<DeviceOp>> op_ptrs;
if constexpr(NumDimSpatial == 3 && is_same_v<InLayout, NDHWGC> &&
is_same_v<WeiLayout, GKZYXC> && is_same_v<OutLayout, NDHWGK> &&
DLayouts::Size() == 1 && is_same_v<tuple_element_t<0, DLayouts>, NDHWGK>)
{
#ifdef CK_ENABLE_FP32
if constexpr(is_same_v<InDataType, float> && is_same_v<WeiDataType, float> &&
is_same_v<OutDataType, float>)
{
add_device_grouped_conv3d_fwd_xdl_bilinear_ndhwgc_gkzyxc_ndhwgk_f32_instances(
op_ptrs);
}
#endif
#ifdef CK_ENABLE_FP16
if constexpr(is_same_v<InDataType, half_t> && is_same_v<WeiDataType, half_t> &&
is_same_v<OutDataType, half_t> && is_same_v<ComputeType, half_t>)
{
add_device_grouped_conv3d_fwd_xdl_bilinear_ndhwgc_gkzyxc_ndhwgk_f16_instances(
op_ptrs);
}
#endif
#ifdef CK_ENABLE_BF16
if constexpr(is_same_v<InDataType, ck::bhalf_t> &&
is_same_v<WeiDataType, ck::bhalf_t> && is_same_v<OutDataType, ck::bhalf_t>)
{
add_device_grouped_conv3d_fwd_xdl_bilinear_ndhwgc_gkzyxc_ndhwgk_bf16_instances(
op_ptrs);
}
#endif
#ifdef CK_ENABLE_INT8
if constexpr(is_same_v<InDataType, int8_t> && is_same_v<WeiDataType, int8_t> &&
is_same_v<OutDataType, int8_t>)
{
add_device_grouped_conv3d_fwd_xdl_bilinear_ndhwgc_gkzyxc_ndhwgk_int8_instances(
op_ptrs);
}
#endif
}
return op_ptrs;
}
};
} // namespace instance
} // namespace device
} // namespace tensor_operation
} // namespace ck
library/include/ck/library/tensor_operation_instance/gpu/grouped_gemm_fixed_nk.hpp
View file @ ae3d6cb6
// SPDX-License-Identifier: MIT
// Copyright (c) 2018-2023, Advanced Micro Devices, Inc. All rights reserved.
// Copyright (c) 2018-2024, Advanced Micro Devices, Inc. All rights reserved.
#pragma once
......@@ -97,6 +97,35 @@ void add_device_grouped_gemm_xdl_fixed_nk_f16_i8_f16_mk_nk_mn_instances(
PassThrough,
PassThrough>>>& instances);
// bf16_inputA i8_inputB
#if defined(CK_ENABLE_BF16) && defined(CK_ENABLE_INT8)
void add_device_grouped_gemm_xdl_fixed_nk_bf16_i8_bf16_mk_kn_mn_instances(
std::vector<std::unique_ptr<DeviceGroupedGemmFixedNK<Row,
Row,
Empty_Tuple,
Row,
BF16,
I8,
Empty_Tuple,
BF16,
PassThrough,
PassThrough,
PassThrough>>>& instances);
void add_device_grouped_gemm_xdl_fixed_nk_bf16_i8_bf16_mk_nk_mn_instances(
std::vector<std::unique_ptr<DeviceGroupedGemmFixedNK<Row,
Col,
Empty_Tuple,
Row,
BF16,
I8,
Empty_Tuple,
BF16,
PassThrough,
PassThrough,
PassThrough>>>& instances);
#endif
template <typename ALayout,
typename BLayout,
typename ELayout,
......@@ -180,6 +209,24 @@ struct DeviceOperationInstanceFactory<
}
}
// bf16_i8_input
#if defined(CK_ENABLE_BF16) && defined(CK_ENABLE_INT8)
if constexpr(is_same_v<ADataType, bhalf_t> && is_same_v<BDataType, int8_t> &&
is_same_v<EDataType, bhalf_t>)
{
if constexpr(is_same_v<ALayout, Row> && is_same_v<BLayout, Row> &&
is_same_v<ELayout, Row>)
{
add_device_grouped_gemm_xdl_fixed_nk_bf16_i8_bf16_mk_kn_mn_instances(op_ptrs);
}
if constexpr(is_same_v<ALayout, Row> && is_same_v<BLayout, Col> &&
is_same_v<ELayout, Row>)
{
add_device_grouped_gemm_xdl_fixed_nk_bf16_i8_bf16_mk_nk_mn_instances(op_ptrs);
}
}
#endif
return op_ptrs;
}
};
......
library/include/ck/library/tensor_operation_instance/gpu/permute_scale.hpp
View file @ ae3d6cb6
// SPDX-License-Identifier: MIT
// Copyright (c) 2018-2023, Advanced Micro Devices, Inc. All rights reserved.
// Copyright (c) 2018-2024, Advanced Micro Devices, Inc. All rights reserved.
#pragma once
......@@ -17,7 +17,32 @@ namespace tensor_operation {
namespace device {
namespace instance {
void add_device_permute_scale_f16_instances(
#ifdef CK_ENABLE_FP16
void add_device_permute_scale_1d_f16_instances(
std::vector<std::unique_ptr<DeviceElementwise<ck::Tuple<F16>,
ck::Tuple<F16>,
PassThrough,
element_wise::UnarySquare,
Scale,
1>>>&);
void add_device_permute_scale_2d_f16_instances(
std::vector<std::unique_ptr<DeviceElementwise<ck::Tuple<F16>,
ck::Tuple<F16>,
PassThrough,
element_wise::UnarySquare,
Scale,
2>>>&);
void add_device_permute_scale_3d_f16_instances(
std::vector<std::unique_ptr<DeviceElementwise<ck::Tuple<F16>,
ck::Tuple<F16>,
PassThrough,
element_wise::UnarySquare,
Scale,
3>>>&);
void add_device_permute_scale_4d_f16_instances(
std::vector<std::unique_ptr<DeviceElementwise<ck::Tuple<F16>,
ck::Tuple<F16>,
PassThrough,
......@@ -25,7 +50,50 @@ void add_device_permute_scale_f16_instances(
Scale,
4>>>&);
void add_device_permute_scale_f32_instances(
void add_device_permute_scale_5d_f16_instances(
std::vector<std::unique_ptr<DeviceElementwise<ck::Tuple<F16>,
ck::Tuple<F16>,
PassThrough,
element_wise::UnarySquare,
Scale,
5>>>&);
void add_device_permute_scale_6d_f16_instances(
std::vector<std::unique_ptr<DeviceElementwise<ck::Tuple<F16>,
ck::Tuple<F16>,
PassThrough,
element_wise::UnarySquare,
Scale,
6>>>&);
#endif
#ifdef CK_ENABLE_FP32
void add_device_permute_scale_1d_f32_instances(
std::vector<std::unique_ptr<DeviceElementwise<ck::Tuple<F32>,
ck::Tuple<F32>,
PassThrough,
element_wise::UnarySquare,
Scale,
1>>>&);
void add_device_permute_scale_2d_f32_instances(
std::vector<std::unique_ptr<DeviceElementwise<ck::Tuple<F32>,
ck::Tuple<F32>,
PassThrough,
element_wise::UnarySquare,
Scale,
2>>>&);
void add_device_permute_scale_3d_f32_instances(
std::vector<std::unique_ptr<DeviceElementwise<ck::Tuple<F32>,
ck::Tuple<F32>,
PassThrough,
element_wise::UnarySquare,
Scale,
3>>>&);
void add_device_permute_scale_4d_f32_instances(
std::vector<std::unique_ptr<DeviceElementwise<ck::Tuple<F32>,
ck::Tuple<F32>,
PassThrough,
......@@ -33,6 +101,23 @@ void add_device_permute_scale_f32_instances(
Scale,
4>>>&);
void add_device_permute_scale_5d_f32_instances(
std::vector<std::unique_ptr<DeviceElementwise<ck::Tuple<F32>,
ck::Tuple<F32>,
PassThrough,
element_wise::UnarySquare,
Scale,
5>>>&);
void add_device_permute_scale_6d_f32_instances(
std::vector<std::unique_ptr<DeviceElementwise<ck::Tuple<F32>,
ck::Tuple<F32>,
PassThrough,
element_wise::UnarySquare,
Scale,
6>>>&);
#endif
template <typename InDataTypeTuple,
typename OutDataTypeTuple,
typename ElementwiseOperation,
......@@ -57,15 +142,107 @@ struct DeviceOperationInstanceFactory<
static auto GetInstances()
{
std::vector<std::unique_ptr<DeviceOp>> op_ptrs;
if constexpr(is_same_v<InDataTypeTuple, ck::Tuple<F32>> &&
is_same_v<OutDataTypeTuple, ck::Tuple<F32>>)
if constexpr(NumDim == 1)
{
#ifdef CK_ENABLE_FP32
if constexpr(is_same_v<InDataTypeTuple, ck::Tuple<F32>> &&
is_same_v<OutDataTypeTuple, ck::Tuple<F32>>)
{
add_device_permute_scale_1d_f32_instances(op_ptrs);
}
#endif
#ifdef CK_ENABLE_FP16
if constexpr(is_same_v<InDataTypeTuple, ck::Tuple<F16>> &&
is_same_v<OutDataTypeTuple, ck::Tuple<F16>>)
{
add_device_permute_scale_1d_f16_instances(op_ptrs);
}
#endif
}
else if constexpr(NumDim == 2)
{
#ifdef CK_ENABLE_FP32
if constexpr(is_same_v<InDataTypeTuple, ck::Tuple<F32>> &&
is_same_v<OutDataTypeTuple, ck::Tuple<F32>>)
{
add_device_permute_scale_2d_f32_instances(op_ptrs);
}
#endif
#ifdef CK_ENABLE_FP16
if constexpr(is_same_v<InDataTypeTuple, ck::Tuple<F16>> &&
is_same_v<OutDataTypeTuple, ck::Tuple<F16>>)
{
add_device_permute_scale_2d_f16_instances(op_ptrs);
}
#endif
}
else if constexpr(NumDim == 3)
{
#ifdef CK_ENABLE_FP32
if constexpr(is_same_v<InDataTypeTuple, ck::Tuple<F32>> &&
is_same_v<OutDataTypeTuple, ck::Tuple<F32>>)
{
add_device_permute_scale_3d_f32_instances(op_ptrs);
}
#endif
#ifdef CK_ENABLE_FP16
if constexpr(is_same_v<InDataTypeTuple, ck::Tuple<F16>> &&
is_same_v<OutDataTypeTuple, ck::Tuple<F16>>)
{
add_device_permute_scale_3d_f16_instances(op_ptrs);
}
#endif
}
else if constexpr(NumDim == 4)
{
#ifdef CK_ENABLE_FP32
if constexpr(is_same_v<InDataTypeTuple, ck::Tuple<F32>> &&
is_same_v<OutDataTypeTuple, ck::Tuple<F32>>)
{
add_device_permute_scale_4d_f32_instances(op_ptrs);
}
#endif
#ifdef CK_ENABLE_FP16
if constexpr(is_same_v<InDataTypeTuple, ck::Tuple<F16>> &&
is_same_v<OutDataTypeTuple, ck::Tuple<F16>>)
{
add_device_permute_scale_4d_f16_instances(op_ptrs);
}
#endif
}
else if constexpr(NumDim == 5)
{
add_device_permute_scale_f32_instances(op_ptrs);
#ifdef CK_ENABLE_FP32
if constexpr(is_same_v<InDataTypeTuple, ck::Tuple<F32>> &&
is_same_v<OutDataTypeTuple, ck::Tuple<F32>>)
{
add_device_permute_scale_5d_f32_instances(op_ptrs);
}
#endif
#ifdef CK_ENABLE_FP16
if constexpr(is_same_v<InDataTypeTuple, ck::Tuple<F16>> &&
is_same_v<OutDataTypeTuple, ck::Tuple<F16>>)
{
add_device_permute_scale_5d_f16_instances(op_ptrs);
}
#endif
}
else if constexpr(is_same_v<InDataTypeTuple, ck::Tuple<F16>> &&
is_same_v<OutDataTypeTuple, ck::Tuple<F16>>)
else if constexpr(NumDim == 6)
{
add_device_permute_scale_f16_instances(op_ptrs);
#ifdef CK_ENABLE_FP32
if constexpr(is_same_v<InDataTypeTuple, ck::Tuple<F32>> &&
is_same_v<OutDataTypeTuple, ck::Tuple<F32>>)
{
add_device_permute_scale_6d_f32_instances(op_ptrs);
}
#endif
#ifdef CK_ENABLE_FP16
if constexpr(is_same_v<InDataTypeTuple, ck::Tuple<F16>> &&
is_same_v<OutDataTypeTuple, ck::Tuple<F16>>)
{
add_device_permute_scale_6d_f16_instances(op_ptrs);
}
#endif
}
return op_ptrs;
}
......
library/src/tensor_operation_instance/gpu/permute_scale/device_permute_scale_instances.cpp → library/include/ck/library/tensor_operation_instance/gpu/permute_scale/device_permute_scale_instances.hpp
View file @ ae3d6cb6
// SPDX-License-Identifier: MIT
// Copyright (c) 2018-2023, Advanced Micro Devices, Inc. All rights reserved.
#include "ck/ck.hpp"
#include "ck/tensor_operation/gpu/device/impl/device_elementwise_scale_impl.hpp"
#include "ck/utility/data_type.hpp"
#include "ck/library/tensor_operation_instance/add_device_operation_instance.hpp"
namespace ck {
namespace tensor_operation {
namespace device {
namespace instance {
using F16 = ck::half_t;
using F32 = float;
using Pass = ck::tensor_operation::element_wise::PassThrough;
using UnaryOp = ck::tensor_operation::element_wise::UnarySquare;
using Scale = ck::tensor_operation::element_wise::Scale;
// clang-format off
using device_permute_scale_f16_instances =
std::tuple <
DeviceElementwiseImpl<ck::Tuple<F16>, ck::Tuple<F16>, Pass, UnaryOp, Scale, 4, 1, ck::Sequence<1>, ck::Sequence<1>>,
DeviceElementwiseImpl<ck::Tuple<F16>, ck::Tuple<F16>, Pass, UnaryOp, Scale, 4, 8, ck::Sequence<1>, ck::Sequence<1>>,
DeviceElementwiseImpl<ck::Tuple<F16>, ck::Tuple<F16>, Pass, UnaryOp, Scale, 4, 4, ck::Sequence<1>, ck::Sequence<1>>,
DeviceElementwiseImpl<ck::Tuple<F16>, ck::Tuple<F16>, Pass, UnaryOp, Scale, 4, 2, ck::Sequence<1>, ck::Sequence<1>>
>;
using device_permute_scale_f32_instances = std::tuple<
DeviceElementwiseImpl<ck::Tuple<F32>, ck::Tuple<F32>, Pass, UnaryOp, Scale, 4, 1, ck::Sequence<1>, ck::Sequence<1>>,
DeviceElementwiseImpl<ck::Tuple<F32>, ck::Tuple<F32>, Pass, UnaryOp, Scale, 4, 8, ck::Sequence<1>, ck::Sequence<1>>,
DeviceElementwiseImpl<ck::Tuple<F32>, ck::Tuple<F32>, Pass, UnaryOp, Scale, 4, 4, ck::Sequence<1>, ck::Sequence<1>>,
DeviceElementwiseImpl<ck::Tuple<F32>, ck::Tuple<F32>, Pass, UnaryOp, Scale, 4, 2, ck::Sequence<1>, ck::Sequence<1>>
>;
// clang-format on
void add_device_permute_scale_f16_instances(
std::vector<std::unique_ptr<
DeviceElementwise<ck::Tuple<F16>, ck::Tuple<F16>, Pass, UnaryOp, Scale, 4>>>& instances)
{
add_device_operation_instances(instances, device_permute_scale_f16_instances{});
}
void add_device_permute_scale_f32_instances(
std::vector<std::unique_ptr<
DeviceElementwise<ck::Tuple<F32>, ck::Tuple<F32>, Pass, UnaryOp, Scale, 4>>>& instances)
{
add_device_operation_instances(instances, device_permute_scale_f32_instances{});
}
} // namespace instance
} // namespace device
} // namespace tensor_operation
} // namespace ck
// SPDX-License-Identifier: MIT
// Copyright (c) 2024, Advanced Micro Devices, Inc. All rights reserved.
#include "ck/ck.hpp"
#include "ck/tensor_operation/gpu/device/impl/device_elementwise_scale_impl.hpp"
#include "ck/utility/data_type.hpp"
namespace ck {
namespace tensor_operation {
namespace device {
namespace instance {
using F16 = ck::half_t;
using F32 = float;
using Pass = ck::tensor_operation::element_wise::PassThrough;
using UnaryOp = ck::tensor_operation::element_wise::UnarySquare;
using Scale = ck::tensor_operation::element_wise::Scale;
// clang-format off
template <index_t NDims>
using device_permute_scale_f16_instances =
std::tuple <
DeviceElementwiseImpl<ck::Tuple<F16>, ck::Tuple<F16>, Pass, UnaryOp, Scale, NDims, 1, ck::Sequence<1>, ck::Sequence<1>>,
DeviceElementwiseImpl<ck::Tuple<F16>, ck::Tuple<F16>, Pass, UnaryOp, Scale, NDims, 8, ck::Sequence<8>, ck::Sequence<1>>,
DeviceElementwiseImpl<ck::Tuple<F16>, ck::Tuple<F16>, Pass, UnaryOp, Scale, NDims, 4, ck::Sequence<4>, ck::Sequence<1>>,
DeviceElementwiseImpl<ck::Tuple<F16>, ck::Tuple<F16>, Pass, UnaryOp, Scale, NDims, 2, ck::Sequence<2>, ck::Sequence<1>>
>;
template <index_t NDims>
using device_permute_scale_f32_instances = std::tuple<
DeviceElementwiseImpl<ck::Tuple<F32>, ck::Tuple<F32>, Pass, UnaryOp, Scale, NDims, 1, ck::Sequence<1>, ck::Sequence<1>>,
DeviceElementwiseImpl<ck::Tuple<F32>, ck::Tuple<F32>, Pass, UnaryOp, Scale, NDims, 8, ck::Sequence<8>, ck::Sequence<1>>,
DeviceElementwiseImpl<ck::Tuple<F32>, ck::Tuple<F32>, Pass, UnaryOp, Scale, NDims, 4, ck::Sequence<4>, ck::Sequence<1>>,
DeviceElementwiseImpl<ck::Tuple<F32>, ck::Tuple<F32>, Pass, UnaryOp, Scale, NDims, 2, ck::Sequence<2>, ck::Sequence<1>>
>;
// clang-format on
} // namespace instance
} // namespace device
} // namespace tensor_operation
} // namespace ck
library/src/tensor_operation_instance/gpu/gemm/CMakeLists.txt
View file @ ae3d6cb6
......@@ -111,6 +111,12 @@ list(APPEND GEMM_INSTANCES
device_gemm_xdl_c_shuffle_fp8_fp8_fp8_km_kn_mn_instance.cpp
device_gemm_xdl_c_shuffle_fp8_fp8_fp8_km_nk_mn_instance.cpp)
list(APPEND GEMM_INSTANCES
device_gemm_wmma_f16_f16_f16_mk_kn_mn_instance.cpp
device_gemm_wmma_f16_f16_f16_mk_nk_mn_instance.cpp
device_gemm_wmma_f16_f16_f16_km_kn_mn_instance.cpp
device_gemm_wmma_f16_f16_f16_km_nk_mn_instance.cpp)
add_instance_library(device_gemm_instance ${GEMM_INSTANCES})
set(ENABLE_PIPELINE_V2_OPT)
......
library/src/tensor_operation_instance/gpu/gemm/device_gemm_wmma_f16_f16_f16_km_kn_mn_instance.cpp 0 → 100644
View file @ ae3d6cb6
// SPDX-License-Identifier: MIT
// Copyright (c) 2018-2023, Advanced Micro Devices, Inc. All rights reserved.
#include <cstdlib>
#include "ck/ck.hpp"
#include "ck/tensor_operation/gpu/device/tensor_layout.hpp"
#include "ck/tensor_operation/gpu/device/gemm_specialization.hpp"
#include "ck/tensor_operation/gpu/device/impl/device_gemm_wmma.hpp"
#include "ck/library/tensor_operation_instance/add_device_operation_instance.hpp"
namespace ck {
namespace tensor_operation {
namespace device {
namespace instance {
using F16 = ck::half_t;
using F32 = float;
using Row = ck::tensor_layout::gemm::RowMajor;
using Col = ck::tensor_layout::gemm::ColumnMajor;
template <ck::index_t... Is>
using S = ck::Sequence<Is...>;
using PassThrough = ck::tensor_operation::element_wise::PassThrough;
// static constexpr auto GemmDefault = ck::tensor_operation::device::GemmSpecialization::Default;
static constexpr auto GemmMNKPadding = ck::tensor_operation::device::GemmSpecialization::MNKPadding;
// Compilation parameters for a[k, m] * b[k, n] = c[m, n]
using device_gemm_wmma_f16_f16_f16_km_kn_mn_instances = std::tuple<
// clang-format off
//######################| ALayout| BLayout| CLayout| AData| BData| CData| AccData| CShuffle| A| B| C| GEMM| NumPrefetch| Block| MPer| NPer| KPer| K1| MPer| NPer| M| N| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockLds| BBlockTransfer| BBlockTransfer| BBlockTransfer| BlockTransfer| BBlockTransfer| BBlockTransfer| BBlockLds| CShuffle| CShuffle| CShuffleBlockTransfer| CShuffleBlockTransfer|
//######################| | | | Type| Type| Type| Type| DataType| Elementwise| Elementwise| Elementwise|Specialization| | Size| Block| Block| Block| | WMMA| WMMA| Repeat| Repeat| ThreadCluster| ThreadCluster| SrcAccessOrder| SrcVectorDim| SrcScalar| DstScalar| AddExtraM| ThreadCluster| ThreadCluster| SrcAccessOrder| SrcVectorDim| SrcScalar| DstScalar| AddExtraN| MRepeat| MRepeat| ClusterLengths| ScalarPerVector|
//######################| | | | | | | | | Operation| Operation| Operation| | | | | | | | | | | | Lengths_K0_M_K1| ArrangeOrder| | | PerVector| PerVector_K1| | Lengths_K0_N_K1| ArrangeOrder| | | PerVector| PerVector_K1| | PerStore| PerStore| MBlock_MPerBlock| |
//######################| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | NBlock_NPerBlock| |
/* Prefetch 2, consume enormous vgpr resource*/
// 8 Waves
DeviceGemmWmma_CShuffle< Col, Row, Row, F16, F16, F16, F32, F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding, 2, 256, 128, 128, 32, 8, 16, 16, 4, 2, S<4, 64, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 1, 8, true, S<4, 64, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 1, 8, true, 1, 1, S<1, 32, 1, 8>, 8>,
// 4 Waves
DeviceGemmWmma_CShuffle< Col, Row, Row, F16, F16, F16, F32, F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding, 2, 128, 128, 64, 64, 8, 16, 16, 4, 2, S<4, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 1, 8, true, S<4, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 1, 8, true, 1, 1, S<1, 32, 1, 4>, 8>,
// 2 Waves
DeviceGemmWmma_CShuffle< Col, Row, Row, F16, F16, F16, F32, F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding, 2, 64, 64, 32, 32, 8, 16, 16, 4, 1, S<4, 16, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 1, 8, true, S<4, 16, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 1, 8, true, 1, 1, S<1, 16, 1, 4>, 8>,
// 1 Wave
DeviceGemmWmma_CShuffle< Col, Row, Row, F16, F16, F16, F32, F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding, 2, 32, 16, 16, 32, 8, 16, 16, 1, 1, S<2, 16, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 1, 8, true, S<2, 16, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 1, 8, true, 1, 1, S<1, 16, 1, 2>, 8>,
/* Prefetch 1, prefer larger KPerBlock value for better latency hiding*/
// 8 Waves
DeviceGemmWmma_CShuffle< Col, Row, Row, F16, F16, F16, F32, F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding, 1, 256, 128, 256, 64, 8, 16, 16, 4, 4, S<4, 64, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 1, 8, true, S<4, 64, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 1, 8, true, 1, 1, S<1, 32, 1, 8>, 8>,
DeviceGemmWmma_CShuffle< Col, Row, Row, F16, F16, F16, F32, F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding, 1, 256, 128, 128, 64, 8, 16, 16, 4, 2, S<4, 64, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 1, 8, true, S<4, 64, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 1, 8, true, 1, 1, S<1, 32, 1, 8>, 8>,
DeviceGemmWmma_CShuffle< Col, Row, Row, F16, F16, F16, F32, F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding, 1, 256, 128, 160, 64, 8, 16, 16, 2, 5, S<4, 64, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 1, 8, true, S<8, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 1, 8, true, 1, 1, S<1, 64, 1, 4>, 8>,
// 4 Waves
DeviceGemmWmma_CShuffle< Col, Row, Row, F16, F16, F16, F32, F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding, 1, 128, 128, 128, 32, 8, 16, 16, 4, 4, S<4, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 1, 8, true, S<4, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 1, 8, true, 1, 1, S<1, 32, 1, 4>, 8>,
DeviceGemmWmma_CShuffle< Col, Row, Row, F16, F16, F16, F32, F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding, 1, 128, 256, 64, 64, 8, 16, 16, 8, 2, S<4, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 1, 8, true, S<4, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 1, 8, true, 1, 1, S<1, 32, 1, 4>, 8>,
DeviceGemmWmma_CShuffle< Col, Row, Row, F16, F16, F16, F32, F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding, 1, 128, 64, 256, 64, 8, 16, 16, 2, 8, S<4, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 1, 8, true, S<4, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 1, 8, true, 1, 1, S<1, 32, 1, 4>, 8>,
DeviceGemmWmma_CShuffle< Col, Row, Row, F16, F16, F16, F32, F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding, 1, 128, 64, 80, 64, 8, 16, 16, 1, 5, S<4, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 1, 8, true, S<8, 16, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 1, 8, true, 1, 1, S<1, 64, 1, 2>, 8>,
// 2 Waves
DeviceGemmWmma_CShuffle< Col, Row, Row, F16, F16, F16, F32, F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding, 1, 64, 16, 64, 64, 8, 16, 16, 1, 2, S<4, 16, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 1, 8, true, S<4, 16, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 1, 8, true, 1, 1, S<1, 16, 1, 4>, 8>,
DeviceGemmWmma_CShuffle< Col, Row, Row, F16, F16, F16, F32, F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding, 1, 64, 64, 32, 64, 8, 16, 16, 4, 1, S<4, 16, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 1, 8, true, S<4, 16, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 1, 8, true, 1, 1, S<1, 16, 1, 4>, 8>,
DeviceGemmWmma_CShuffle< Col, Row, Row, F16, F16, F16, F32, F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding, 1, 64, 32, 64, 64, 8, 16, 16, 2, 2, S<4, 16, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 1, 8, true, S<4, 16, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 1, 8, true, 1, 1, S<1, 16, 1, 4>, 8>,
// 1 Wave
DeviceGemmWmma_CShuffle< Col, Row, Row, F16, F16, F16, F32, F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding, 1, 32, 16, 32, 64, 8, 16, 16, 1, 2, S<2, 16, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 1, 8, true, S<2, 16, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 1, 8, true, 1, 1, S<1, 16, 1, 2>, 8>,
DeviceGemmWmma_CShuffle< Col, Row, Row, F16, F16, F16, F32, F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding, 1, 32, 16, 16, 64, 8, 16, 16, 1, 1, S<2, 16, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 1, 8, true, S<2, 16, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 1, 8, true, 1, 1, S<1, 16, 1, 2>, 8>
// clang-format on
>;
void add_device_gemm_wmma_f16_f16_f16_km_kn_mn_instances(
std::vector<std::unique_ptr<
DeviceGemm<Col, Row, Row, F16, F16, F16, PassThrough, PassThrough, PassThrough>>>&
instances)
{
add_device_operation_instances(instances, device_gemm_wmma_f16_f16_f16_km_kn_mn_instances{});
}
} // namespace instance
} // namespace device
} // namespace tensor_operation
} // namespace ck
library/src/tensor_operation_instance/gpu/gemm/device_gemm_wmma_f16_f16_f16_km_nk_mn_instance.cpp 0 → 100644
View file @ ae3d6cb6
// SPDX-License-Identifier: MIT
// Copyright (c) 2018-2023, Advanced Micro Devices, Inc. All rights reserved.
#include <cstdlib>
#include "ck/ck.hpp"
#include "ck/tensor_operation/gpu/device/tensor_layout.hpp"
#include "ck/tensor_operation/gpu/device/gemm_specialization.hpp"
#include "ck/tensor_operation/gpu/device/impl/device_gemm_wmma.hpp"
#include "ck/library/tensor_operation_instance/add_device_operation_instance.hpp"
namespace ck {
namespace tensor_operation {
namespace device {
namespace instance {
using F16 = ck::half_t;
using F32 = float;
using Row = ck::tensor_layout::gemm::RowMajor;
using Col = ck::tensor_layout::gemm::ColumnMajor;
template <ck::index_t... Is>
using S = ck::Sequence<Is...>;
using PassThrough = ck::tensor_operation::element_wise::PassThrough;
// static constexpr auto GemmDefault = ck::tensor_operation::device::GemmSpecialization::Default;
static constexpr auto GemmMNKPadding = ck::tensor_operation::device::GemmSpecialization::MNKPadding;
// Compilation parameters for a[k, m] * b[n, k] = c[m, n]
using device_gemm_wmma_f16_f16_f16_km_nk_mn_instances = std::tuple<
// clang-format off
//######################| ALayout| BLayout| CLayout| AData| BData| CData| AccData| CShuffle| A| B| C| GEMM| NumPrefetch| Block| MPer| NPer| KPer| K1| MPer| NPer| M| N| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockLds| BBlockTransfer| BBlockTransfer| BBlockTransfer| BlockTransfer| BBlockTransfer| BBlockTransfer| BBlockLds| CShuffle| CShuffle| CShuffleBlockTransfer| CShuffleBlockTransfer|
//######################| | | | Type| Type| Type| Type| DataType| Elementwise| Elementwise| Elementwise|Specialization| | Size| Block| Block| Block| | WMMA| WMMA| Repeat| Repeat| ThreadCluster| ThreadCluster| SrcAccessOrder| SrcVectorDim| SrcScalar| DstScalar| AddExtraM| ThreadCluster| ThreadCluster| SrcAccessOrder| SrcVectorDim| SrcScalar| DstScalar| AddExtraN| MRepeat| MRepeat| ClusterLengths| ScalarPerVector|
//######################| | | | | | | | | Operation| Operation| Operation| | | | | | | | | | | | Lengths_K0_M_K1| ArrangeOrder| | | PerVector| PerVector_K1| | Lengths_K0_N_K1| ArrangeOrder| | | PerVector| PerVector_K1| | PerStore| PerStore| MBlock_MPerBlock| |
//######################| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | NBlock_NPerBlock| |
/* Prefetch 2, consume enormous vgpr resource*/
// 8 Waves
DeviceGemmWmma_CShuffle< Col, Col, Row, F16, F16, F16, F32, F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding, 2, 256, 128, 128, 32, 8, 16, 16, 4, 2, S<4, 64, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 1, 8, true, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, true, 1, 1, S<1, 32, 1, 8>, 8>,
// 4 Waves
DeviceGemmWmma_CShuffle< Col, Col, Row, F16, F16, F16, F32, F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding, 2, 128, 128, 64, 64, 8, 16, 16, 4, 2, S<4, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 1, 8, true, S<4, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, true, 1, 1, S<1, 32, 1, 4>, 8>,
// 2 Waves
DeviceGemmWmma_CShuffle< Col, Col, Row, F16, F16, F16, F32, F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding, 2, 64, 64, 32, 32, 8, 16, 16, 4, 1, S<4, 16, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 1, 8, true, S<4, 16, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, true, 1, 1, S<1, 16, 1, 4>, 8>,
// 1 Wave
DeviceGemmWmma_CShuffle< Col, Col, Row, F16, F16, F16, F32, F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding, 2, 32, 16, 16, 32, 8, 16, 16, 1, 1, S<2, 16, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 1, 8, true, S<2, 16, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, true, 1, 1, S<1, 16, 1, 2>, 8>,
/* Prefetch 1, prefer larger KPerBlock value for better latency hiding*/
// 8 Waves
DeviceGemmWmma_CShuffle< Col, Col, Row, F16, F16, F16, F32, F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding, 1, 256, 128, 256, 64, 8, 16, 16, 4, 4, S<4, 64, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 1, 8, true, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, true, 1, 1, S<1, 32, 1, 8>, 8>,
DeviceGemmWmma_CShuffle< Col, Col, Row, F16, F16, F16, F32, F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding, 1, 256, 128, 128, 64, 8, 16, 16, 4, 2, S<4, 64, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 1, 8, true, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, true, 1, 1, S<1, 32, 1, 8>, 8>,
DeviceGemmWmma_CShuffle< Col, Col, Row, F16, F16, F16, F32, F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding, 1, 256, 128, 160, 64, 8, 16, 16, 2, 5, S<4, 64, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 1, 8, true, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, true, 1, 1, S<1, 64, 1, 4>, 8>,
// 4 Waves
DeviceGemmWmma_CShuffle< Col, Col, Row, F16, F16, F16, F32, F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding, 1, 128, 128, 128, 32, 8, 16, 16, 4, 4, S<4, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 1, 8, true, S<4, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, true, 1, 1, S<1, 32, 1, 4>, 8>,
DeviceGemmWmma_CShuffle< Col, Col, Row, F16, F16, F16, F32, F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding, 1, 128, 256, 64, 64, 8, 16, 16, 8, 2, S<4, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 1, 8, true, S<4, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, true, 1, 1, S<1, 32, 1, 4>, 8>,
DeviceGemmWmma_CShuffle< Col, Col, Row, F16, F16, F16, F32, F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding, 1, 128, 64, 256, 64, 8, 16, 16, 2, 8, S<4, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 1, 8, true, S<4, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, true, 1, 1, S<1, 32, 1, 4>, 8>,
DeviceGemmWmma_CShuffle< Col, Col, Row, F16, F16, F16, F32, F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding, 1, 128, 64, 80, 64, 8, 16, 16, 1, 5, S<4, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 1, 8, true, S<8, 16, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, true, 1, 1, S<1, 64, 1, 2>, 8>,
// 2 Waves
DeviceGemmWmma_CShuffle< Col, Col, Row, F16, F16, F16, F32, F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding, 1, 64, 16, 64, 64, 8, 16, 16, 1, 2, S<4, 16, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 1, 8, true, S<4, 16, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, true, 1, 1, S<1, 16, 1, 4>, 8>,
DeviceGemmWmma_CShuffle< Col, Col, Row, F16, F16, F16, F32, F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding, 1, 64, 64, 32, 64, 8, 16, 16, 4, 1, S<4, 16, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 1, 8, true, S<4, 16, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, true, 1, 1, S<1, 16, 1, 4>, 8>,
DeviceGemmWmma_CShuffle< Col, Col, Row, F16, F16, F16, F32, F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding, 1, 64, 32, 64, 64, 8, 16, 16, 2, 2, S<4, 16, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 1, 8, true, S<4, 16, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, true, 1, 1, S<1, 16, 1, 4>, 8>,
// 1 Wave
DeviceGemmWmma_CShuffle< Col, Col, Row, F16, F16, F16, F32, F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding, 1, 32, 16, 32, 64, 8, 16, 16, 1, 2, S<2, 16, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 1, 8, true, S<2, 16, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, true, 1, 1, S<1, 16, 1, 2>, 8>,
DeviceGemmWmma_CShuffle< Col, Col, Row, F16, F16, F16, F32, F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding, 1, 32, 16, 16, 64, 8, 16, 16, 1, 1, S<2, 16, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 1, 8, true, S<2, 16, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, true, 1, 1, S<1, 16, 1, 2>, 8>
// clang-format on
>;
void add_device_gemm_wmma_f16_f16_f16_km_nk_mn_instances(
std::vector<std::unique_ptr<
DeviceGemm<Col, Col, Row, F16, F16, F16, PassThrough, PassThrough, PassThrough>>>&
instances)
{
add_device_operation_instances(instances, device_gemm_wmma_f16_f16_f16_km_nk_mn_instances{});
}
} // namespace instance
} // namespace device
} // namespace tensor_operation
} // namespace ck
library/src/tensor_operation_instance/gpu/gemm/device_gemm_wmma_f16_f16_f16_mk_kn_mn_instance.cpp 0 → 100644
View file @ ae3d6cb6
// SPDX-License-Identifier: MIT
// Copyright (c) 2018-2023, Advanced Micro Devices, Inc. All rights reserved.
#include <cstdlib>
#include "ck/ck.hpp"
#include "ck/tensor_operation/gpu/device/tensor_layout.hpp"
#include "ck/tensor_operation/gpu/device/gemm_specialization.hpp"
#include "ck/tensor_operation/gpu/device/impl/device_gemm_wmma.hpp"
#include "ck/library/tensor_operation_instance/add_device_operation_instance.hpp"
namespace ck {
namespace tensor_operation {
namespace device {
namespace instance {
using F16 = ck::half_t;
using F32 = float;
using Row = ck::tensor_layout::gemm::RowMajor;
using Col = ck::tensor_layout::gemm::ColumnMajor;
template <ck::index_t... Is>
using S = ck::Sequence<Is...>;
using PassThrough = ck::tensor_operation::element_wise::PassThrough;
// static constexpr auto GemmDefault = ck::tensor_operation::device::GemmSpecialization::Default;
static constexpr auto GemmMNKPadding = ck::tensor_operation::device::GemmSpecialization::MNKPadding;
// Compilation parameters for a[m, k] * b[k, n] = c[m, n]
using device_gemm_wmma_f16_f16_f16_mk_kn_mn_instances = std::tuple<
// clang-format off
//######################| ALayout| BLayout| CLayout| AData| BData| CData| AccData| CShuffle| A| B| C| GEMM| NumPrefetch| Block| MPer| NPer| KPer| K1| MPer| NPer| M| N| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockLds| BBlockTransfer| BBlockTransfer| BBlockTransfer| BlockTransfer| BBlockTransfer| BBlockTransfer| BBlockLds| CShuffle| CShuffle| CShuffleBlockTransfer| CShuffleBlockTransfer|
//######################| | | | Type| Type| Type| Type| DataType| Elementwise| Elementwise| Elementwise|Specialization| | Size| Block| Block| Block| | WMMA| WMMA| Repeat| Repeat| ThreadCluster| ThreadCluster| SrcAccessOrder| SrcVectorDim| SrcScalar| DstScalar| AddExtraM| ThreadCluster| ThreadCluster| SrcAccessOrder| SrcVectorDim| SrcScalar| DstScalar| AddExtraN| MRepeat| MRepeat| ClusterLengths| ScalarPerVector|
//######################| | | | | | | | | Operation| Operation| Operation| | | | | | | | | | | | Lengths_K0_M_K1| ArrangeOrder| | | PerVector| PerVector_K1| | Lengths_K0_N_K1| ArrangeOrder| | | PerVector| PerVector_K1| | PerStore| PerStore| MBlock_MPerBlock| |
//######################| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | NBlock_NPerBlock| |
/* Prefetch 2, consume enormous vgpr resource*/
// 8 Waves
DeviceGemmWmma_CShuffle< Row, Row, Row, F16, F16, F16, F32, F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding, 2, 256, 128, 128, 32, 8, 16, 16, 4, 2, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, true, S<4, 64, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 1, 8, true, 1, 1, S<1, 32, 1, 8>, 8>,
// 4 Waves
DeviceGemmWmma_CShuffle< Row, Row, Row, F16, F16, F16, F32, F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding, 2, 128, 128, 64, 64, 8, 16, 16, 4, 2, S<4, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, true, S<4, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 1, 8, true, 1, 1, S<1, 32, 1, 4>, 8>,
// 2 Waves
DeviceGemmWmma_CShuffle< Row, Row, Row, F16, F16, F16, F32, F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding, 2, 64, 64, 32, 32, 8, 16, 16, 4, 1, S<4, 16, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, true, S<4, 16, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 1, 8, true, 1, 1, S<1, 16, 1, 4>, 8>,
// 1 Wave
DeviceGemmWmma_CShuffle< Row, Row, Row, F16, F16, F16, F32, F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding, 2, 32, 16, 16, 32, 8, 16, 16, 1, 1, S<2, 16, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, true, S<2, 16, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 1, 8, true, 1, 1, S<1, 16, 1, 2>, 8>,
/* Prefetch 1, prefer larger KPerBlock value for better latency hiding*/
// 8 Waves
DeviceGemmWmma_CShuffle< Row, Row, Row, F16, F16, F16, F32, F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding, 1, 256, 128, 256, 64, 8, 16, 16, 4, 4, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, true, S<4, 64, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 1, 8, true, 1, 1, S<1, 32, 1, 8>, 8>,
DeviceGemmWmma_CShuffle< Row, Row, Row, F16, F16, F16, F32, F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding, 1, 256, 128, 128, 64, 8, 16, 16, 4, 2, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, true, S<4, 64, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 1, 8, true, 1, 1, S<1, 32, 1, 8>, 8>,
DeviceGemmWmma_CShuffle< Row, Row, Row, F16, F16, F16, F32, F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding, 1, 256, 128, 160, 64, 8, 16, 16, 2, 5, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, true, S<8, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 1, 8, true, 1, 1, S<1, 64, 1, 4>, 8>,
// 4 Waves
DeviceGemmWmma_CShuffle< Row, Row, Row, F16, F16, F16, F32, F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding, 1, 128, 128, 128, 32, 8, 16, 16, 4, 4, S<4, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, true, S<4, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 1, 8, true, 1, 1, S<1, 32, 1, 4>, 8>,
DeviceGemmWmma_CShuffle< Row, Row, Row, F16, F16, F16, F32, F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding, 1, 128, 256, 64, 64, 8, 16, 16, 8, 2, S<4, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, true, S<4, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 1, 8, true, 1, 1, S<1, 32, 1, 4>, 8>,
DeviceGemmWmma_CShuffle< Row, Row, Row, F16, F16, F16, F32, F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding, 1, 128, 64, 256, 64, 8, 16, 16, 2, 8, S<4, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, true, S<4, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 1, 8, true, 1, 1, S<1, 32, 1, 4>, 8>,
DeviceGemmWmma_CShuffle< Row, Row, Row, F16, F16, F16, F32, F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding, 1, 128, 64, 80, 64, 8, 16, 16, 1, 5, S<4, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, true, S<8, 16, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 1, 8, true, 1, 1, S<1, 64, 1, 2>, 8>,
// 2 Waves
DeviceGemmWmma_CShuffle< Row, Row, Row, F16, F16, F16, F32, F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding, 1, 64, 16, 64, 64, 8, 16, 16, 1, 2, S<4, 16, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, true, S<4, 16, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 1, 8, true, 1, 1, S<1, 16, 1, 4>, 8>,
DeviceGemmWmma_CShuffle< Row, Row, Row, F16, F16, F16, F32, F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding, 1, 64, 64, 32, 64, 8, 16, 16, 4, 1, S<4, 16, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, true, S<4, 16, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 1, 8, true, 1, 1, S<1, 16, 1, 4>, 8>,
DeviceGemmWmma_CShuffle< Row, Row, Row, F16, F16, F16, F32, F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding, 1, 64, 32, 64, 64, 8, 16, 16, 2, 2, S<4, 16, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, true, S<4, 16, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 1, 8, true, 1, 1, S<1, 16, 1, 4>, 8>,
// 1 Wave
DeviceGemmWmma_CShuffle< Row, Row, Row, F16, F16, F16, F32, F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding, 1, 32, 16, 32, 64, 8, 16, 16, 1, 2, S<2, 16, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, true, S<2, 16, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 1, 8, true, 1, 1, S<1, 16, 1, 2>, 8>,
DeviceGemmWmma_CShuffle< Row, Row, Row, F16, F16, F16, F32, F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding, 1, 32, 16, 16, 64, 8, 16, 16, 1, 1, S<2, 16, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, true, S<2, 16, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 1, 8, true, 1, 1, S<1, 16, 1, 2>, 8>
#if 0
/* Prefetch 2, consume enormous vgpr resource*/
// 8 Waves
DeviceGemmWmma_CShuffle< Row, Row, Row, F16, F16, F16, F32, F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding, 2, 256, 128, 128, 32, 8, 16, 16, 4, 2, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, true, S<4, 64, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 8, true, 1, 1, S<1, 32, 1, 8>, 8>,
// 4 Waves
DeviceGemmWmma_CShuffle< Row, Row, Row, F16, F16, F16, F32, F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding, 2, 128, 128, 64, 64, 8, 16, 16, 4, 2, S<4, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, true, S<4, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 8, true, 1, 1, S<1, 32, 1, 4>, 8>,
// 2 Waves
DeviceGemmWmma_CShuffle< Row, Row, Row, F16, F16, F16, F32, F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding, 2, 64, 64, 32, 32, 8, 16, 16, 4, 1, S<4, 16, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, true, S<4, 16, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 8, true, 1, 1, S<1, 16, 1, 4>, 8>,
// 1 Wave
DeviceGemmWmma_CShuffle< Row, Row, Row, F16, F16, F16, F32, F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding, 2, 32, 16, 16, 32, 8, 16, 16, 1, 1, S<2, 16, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, true, S<2, 16, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 8, true, 1, 1, S<1, 16, 1, 2>, 8>,
/* Prefetch 1, prefer larger KPerBlock value for better latency hiding*/
// 8 Waves
DeviceGemmWmma_CShuffle< Row, Row, Row, F16, F16, F16, F32, F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding, 1, 256, 128, 256, 64, 8, 16, 16, 4, 4, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, true, S<4, 64, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 8, true, 1, 1, S<1, 32, 1, 8>, 8>,
DeviceGemmWmma_CShuffle< Row, Row, Row, F16, F16, F16, F32, F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding, 1, 256, 128, 128, 64, 8, 16, 16, 4, 2, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, true, S<4, 64, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 8, true, 1, 1, S<1, 32, 1, 8>, 8>,
DeviceGemmWmma_CShuffle< Row, Row, Row, F16, F16, F16, F32, F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding, 1, 256, 128, 160, 64, 8, 16, 16, 2, 5, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, true, S<8, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 8, true, 1, 1, S<1, 64, 1, 4>, 8>,
// 4 Waves
DeviceGemmWmma_CShuffle< Row, Row, Row, F16, F16, F16, F32, F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding, 1, 128, 128, 128, 32, 8, 16, 16, 4, 4, S<4, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, true, S<4, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 8, true, 1, 1, S<1, 32, 1, 4>, 8>,
DeviceGemmWmma_CShuffle< Row, Row, Row, F16, F16, F16, F32, F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding, 1, 128, 256, 64, 64, 8, 16, 16, 8, 2, S<4, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, true, S<4, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 8, true, 1, 1, S<1, 32, 1, 4>, 8>,
DeviceGemmWmma_CShuffle< Row, Row, Row, F16, F16, F16, F32, F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding, 1, 128, 64, 256, 64, 8, 16, 16, 2, 8, S<4, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, true, S<4, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 8, true, 1, 1, S<1, 32, 1, 4>, 8>,
DeviceGemmWmma_CShuffle< Row, Row, Row, F16, F16, F16, F32, F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding, 1, 128, 64, 80, 64, 8, 16, 16, 1, 5, S<4, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, true, S<8, 16, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 8, true, 1, 1, S<1, 64, 1, 2>, 8>,
// 2 Waves
DeviceGemmWmma_CShuffle< Row, Row, Row, F16, F16, F16, F32, F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding, 1, 64, 16, 64, 64, 8, 16, 16, 1, 2, S<4, 16, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, true, S<4, 16, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 8, true, 1, 1, S<1, 16, 1, 4>, 8>,
DeviceGemmWmma_CShuffle< Row, Row, Row, F16, F16, F16, F32, F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding, 1, 64, 64, 32, 64, 8, 16, 16, 4, 1, S<4, 16, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, true, S<4, 16, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 8, true, 1, 1, S<1, 16, 1, 4>, 8>,
DeviceGemmWmma_CShuffle< Row, Row, Row, F16, F16, F16, F32, F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding, 1, 64, 32, 64, 64, 8, 16, 16, 2, 2, S<4, 16, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, true, S<4, 16, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 8, true, 1, 1, S<1, 16, 1, 4>, 8>,
// 1 Wave
DeviceGemmWmma_CShuffle< Row, Row, Row, F16, F16, F16, F32, F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding, 1, 32, 16, 32, 64, 8, 16, 16, 1, 2, S<2, 16, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, true, S<2, 16, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 8, true, 1, 1, S<1, 16, 1, 2>, 8>,
DeviceGemmWmma_CShuffle< Row, Row, Row, F16, F16, F16, F32, F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding, 1, 32, 16, 16, 64, 8, 16, 16, 1, 1, S<2, 16, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, true, S<2, 16, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 8, true, 1, 1, S<1, 16, 1, 2>, 8>,
/* Prefetch 2, consume enormous vgpr resource*/
// 8 Waves
DeviceGemmWmma_CShuffle< Row, Row, Row, F16, F16, F16, F32, F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding, 2, 256, 128, 128, 32, 8, 16, 16, 4, 2, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, true, S<4, 64, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 8, true, 1, 1, S<1, 32, 1, 8>, 8>,
// 4 Waves
DeviceGemmWmma_CShuffle< Row, Row, Row, F16, F16, F16, F32, F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding, 2, 128, 128, 64, 64, 8, 16, 16, 4, 2, S<4, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, true, S<4, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 8, true, 1, 1, S<1, 32, 1, 4>, 8>,
// 2 Waves
DeviceGemmWmma_CShuffle< Row, Row, Row, F16, F16, F16, F32, F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding, 2, 64, 64, 32, 32, 8, 16, 16, 4, 1, S<4, 16, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, true, S<4, 16, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 8, true, 1, 1, S<1, 16, 1, 4>, 8>,
// 1 Wave
DeviceGemmWmma_CShuffle< Row, Row, Row, F16, F16, F16, F32, F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding, 2, 32, 16, 16, 32, 8, 16, 16, 1, 1, S<2, 16, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, true, S<2, 16, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 8, true, 1, 1, S<1, 16, 1, 2>, 8>,
/* Prefetch 1, prefer larger KPerBlock value for better latency hiding*/
// 8 Waves
DeviceGemmWmma_CShuffle< Row, Row, Row, F16, F16, F16, F32, F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding, 1, 256, 128, 256, 64, 8, 16, 16, 4, 4, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, true, S<4, 64, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 8, true, 1, 1, S<1, 32, 1, 8>, 8>,
DeviceGemmWmma_CShuffle< Row, Row, Row, F16, F16, F16, F32, F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding, 1, 256, 128, 128, 64, 8, 16, 16, 4, 2, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, true, S<4, 64, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 8, true, 1, 1, S<1, 32, 1, 8>, 8>,
DeviceGemmWmma_CShuffle< Row, Row, Row, F16, F16, F16, F32, F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding, 1, 256, 128, 160, 64, 8, 16, 16, 2, 5, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, true, S<8, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 8, true, 1, 1, S<1, 64, 1, 4>, 8>,
// 4 Waves
DeviceGemmWmma_CShuffle< Row, Row, Row, F16, F16, F16, F32, F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding, 1, 128, 128, 128, 32, 8, 16, 16, 4, 4, S<4, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, true, S<4, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 8, true, 1, 1, S<1, 32, 1, 4>, 8>,
DeviceGemmWmma_CShuffle< Row, Row, Row, F16, F16, F16, F32, F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding, 1, 128, 256, 64, 64, 8, 16, 16, 8, 2, S<4, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, true, S<4, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 8, true, 1, 1, S<1, 32, 1, 4>, 8>,
DeviceGemmWmma_CShuffle< Row, Row, Row, F16, F16, F16, F32, F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding, 1, 128, 64, 256, 64, 8, 16, 16, 2, 8, S<4, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, true, S<4, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 8, true, 1, 1, S<1, 32, 1, 4>, 8>,
DeviceGemmWmma_CShuffle< Row, Row, Row, F16, F16, F16, F32, F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding, 1, 128, 64, 80, 64, 8, 16, 16, 1, 5, S<4, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, true, S<8, 16, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 8, true, 1, 1, S<1, 64, 1, 2>, 8>,
// 2 Waves
DeviceGemmWmma_CShuffle< Row, Row, Row, F16, F16, F16, F32, F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding, 1, 64, 16, 64, 64, 8, 16, 16, 1, 2, S<4, 16, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, true, S<4, 16, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 8, true, 1, 1, S<1, 16, 1, 4>, 8>,
DeviceGemmWmma_CShuffle< Row, Row, Row, F16, F16, F16, F32, F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding, 1, 64, 64, 32, 64, 8, 16, 16, 4, 1, S<4, 16, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, true, S<4, 16, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 8, true, 1, 1, S<1, 16, 1, 4>, 8>,
DeviceGemmWmma_CShuffle< Row, Row, Row, F16, F16, F16, F32, F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding, 1, 64, 32, 64, 64, 8, 16, 16, 2, 2, S<4, 16, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, true, S<4, 16, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 8, true, 1, 1, S<1, 16, 1, 4>, 8>,
// 1 Wave
DeviceGemmWmma_CShuffle< Row, Row, Row, F16, F16, F16, F32, F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding, 1, 32, 16, 32, 64, 8, 16, 16, 1, 2, S<2, 16, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, true, S<2, 16, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 8, true, 1, 1, S<1, 16, 1, 2>, 8>,
DeviceGemmWmma_CShuffle< Row, Row, Row, F16, F16, F16, F32, F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding, 1, 32, 16, 16, 64, 8, 16, 16, 1, 1, S<2, 16, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, true, S<2, 16, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 8, true, 1, 1, S<1, 16, 1, 2>, 8>,
/* Prefetch 2, consume enormous vgpr resource*/
// 8 Waves
DeviceGemmWmma_CShuffle< Row, Row, Row, F16, F16, F16, F32, F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding, 2, 256, 128, 128, 32, 8, 16, 16, 4, 2, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, true, S<4, 64, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 8, 8, true, 1, 1, S<1, 32, 1, 8>, 8>,
// 4 Waves
DeviceGemmWmma_CShuffle< Row, Row, Row, F16, F16, F16, F32, F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding, 2, 128, 128, 64, 64, 8, 16, 16, 4, 2, S<4, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, true, S<4, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 8, 8, true, 1, 1, S<1, 32, 1, 4>, 8>,
// 2 Waves
DeviceGemmWmma_CShuffle< Row, Row, Row, F16, F16, F16, F32, F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding, 2, 64, 64, 32, 32, 8, 16, 16, 4, 1, S<4, 16, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, true, S<4, 16, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 8, 8, true, 1, 1, S<1, 16, 1, 4>, 8>,
// 1 Wave
DeviceGemmWmma_CShuffle< Row, Row, Row, F16, F16, F16, F32, F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding, 2, 32, 16, 16, 32, 8, 16, 16, 1, 1, S<2, 16, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, true, S<2, 16, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 8, 8, true, 1, 1, S<1, 16, 1, 2>, 8>,
/* Prefetch 1, prefer larger KPerBlock value for better latency hiding*/
// 8 Waves
DeviceGemmWmma_CShuffle< Row, Row, Row, F16, F16, F16, F32, F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding, 1, 256, 128, 256, 64, 8, 16, 16, 4, 4, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, true, S<4, 64, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 8, 8, true, 1, 1, S<1, 32, 1, 8>, 8>,
DeviceGemmWmma_CShuffle< Row, Row, Row, F16, F16, F16, F32, F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding, 1, 256, 128, 128, 64, 8, 16, 16, 4, 2, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, true, S<4, 64, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 8, 8, true, 1, 1, S<1, 32, 1, 8>, 8>,
DeviceGemmWmma_CShuffle< Row, Row, Row, F16, F16, F16, F32, F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding, 1, 256, 128, 160, 64, 8, 16, 16, 2, 5, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, true, S<8, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 8, 8, true, 1, 1, S<1, 64, 1, 4>, 8>,
// 4 Waves
DeviceGemmWmma_CShuffle< Row, Row, Row, F16, F16, F16, F32, F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding, 1, 128, 128, 128, 32, 8, 16, 16, 4, 4, S<4, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, true, S<4, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 8, 8, true, 1, 1, S<1, 32, 1, 4>, 8>,
DeviceGemmWmma_CShuffle< Row, Row, Row, F16, F16, F16, F32, F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding, 1, 128, 256, 64, 64, 8, 16, 16, 8, 2, S<4, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, true, S<4, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 8, 8, true, 1, 1, S<1, 32, 1, 4>, 8>,
DeviceGemmWmma_CShuffle< Row, Row, Row, F16, F16, F16, F32, F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding, 1, 128, 64, 256, 64, 8, 16, 16, 2, 8, S<4, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, true, S<4, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 8, 8, true, 1, 1, S<1, 32, 1, 4>, 8>,
DeviceGemmWmma_CShuffle< Row, Row, Row, F16, F16, F16, F32, F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding, 1, 128, 64, 80, 64, 8, 16, 16, 1, 5, S<4, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, true, S<8, 16, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 8, 8, true, 1, 1, S<1, 64, 1, 2>, 8>,
// 2 Waves
DeviceGemmWmma_CShuffle< Row, Row, Row, F16, F16, F16, F32, F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding, 1, 64, 16, 64, 64, 8, 16, 16, 1, 2, S<4, 16, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, true, S<4, 16, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 8, 8, true, 1, 1, S<1, 16, 1, 4>, 8>,
DeviceGemmWmma_CShuffle< Row, Row, Row, F16, F16, F16, F32, F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding, 1, 64, 64, 32, 64, 8, 16, 16, 4, 1, S<4, 16, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, true, S<4, 16, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 8, 8, true, 1, 1, S<1, 16, 1, 4>, 8>,
DeviceGemmWmma_CShuffle< Row, Row, Row, F16, F16, F16, F32, F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding, 1, 64, 32, 64, 64, 8, 16, 16, 2, 2, S<4, 16, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, true, S<4, 16, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 8, 8, true, 1, 1, S<1, 16, 1, 4>, 8>,
// 1 Wave
DeviceGemmWmma_CShuffle< Row, Row, Row, F16, F16, F16, F32, F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding, 1, 32, 16, 32, 64, 8, 16, 16, 1, 2, S<2, 16, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, true, S<2, 16, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 8, 8, true, 1, 1, S<1, 16, 1, 2>, 8>,
DeviceGemmWmma_CShuffle< Row, Row, Row, F16, F16, F16, F32, F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding, 1, 32, 16, 16, 64, 8, 16, 16, 1, 1, S<2, 16, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, true, S<2, 16, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 8, 8, true, 1, 1, S<1, 16, 1, 2>, 8>
#endif
// clang-format on
>;
void add_device_gemm_wmma_f16_f16_f16_mk_kn_mn_instances(
std::vector<std::unique_ptr<
DeviceGemm<Row, Row, Row, F16, F16, F16, PassThrough, PassThrough, PassThrough>>>&
instances)
{
add_device_operation_instances(instances, device_gemm_wmma_f16_f16_f16_mk_kn_mn_instances{});
}
} // namespace instance
} // namespace device
} // namespace tensor_operation
} // namespace ck
library/src/tensor_operation_instance/gpu/gemm/device_gemm_wmma_f16_f16_f16_mk_nk_mn_instance.cpp 0 → 100644
View file @ ae3d6cb6
// SPDX-License-Identifier: MIT
// Copyright (c) 2018-2023, Advanced Micro Devices, Inc. All rights reserved.
#include <cstdlib>
#include "ck/ck.hpp"
#include "ck/tensor_operation/gpu/device/tensor_layout.hpp"
#include "ck/tensor_operation/gpu/device/gemm_specialization.hpp"
#include "ck/tensor_operation/gpu/device/impl/device_gemm_wmma.hpp"
#include "ck/library/tensor_operation_instance/add_device_operation_instance.hpp"
namespace ck {
namespace tensor_operation {
namespace device {
namespace instance {
using F16 = ck::half_t;
using F32 = float;
using Row = ck::tensor_layout::gemm::RowMajor;
using Col = ck::tensor_layout::gemm::ColumnMajor;
template <ck::index_t... Is>
using S = ck::Sequence<Is...>;
using PassThrough = ck::tensor_operation::element_wise::PassThrough;
// static constexpr auto GemmDefault = ck::tensor_operation::device::GemmSpecialization::Default;
static constexpr auto GemmMNKPadding = ck::tensor_operation::device::GemmSpecialization::MNKPadding;
// Compilation parameters for a[m, k] * b[n, k] = c[m, n]
using device_gemm_wmma_f16_f16_f16_mk_nk_mn_instances = std::tuple<
// clang-format off
//######################| ALayout| BLayout| CLayout| AData| BData| CData| AccData| CShuffle| A| B| C| GEMM| NumPrefetch| Block| MPer| NPer| KPer| K1| MPer| NPer| M| N| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockLds| BBlockTransfer| BBlockTransfer| BBlockTransfer| BlockTransfer| BBlockTransfer| BBlockTransfer| BBlockLds| CShuffle| CShuffle| CShuffleBlockTransfer| CShuffleBlockTransfer|
//######################| | | | Type| Type| Type| Type| DataType| Elementwise| Elementwise| Elementwise| Specialization| | Size| Block| Block| Block| | WMMA| WMMA| Repeat| Repeat| ThreadCluster| ThreadCluster| SrcAccessOrder| SrcVectorDim| SrcScalar| DstScalar| AddExtraM| ThreadCluster| ThreadCluster| SrcAccessOrder| SrcVectorDim| SrcScalar| DstScalar| AddExtraN| MRepeat| MRepeat| ClusterLengths| ScalarPerVector|
//######################| | | | | | | | | Operation| Operation| Operation| | | | | | | | | | | | Lengths_K0_M_K1| ArrangeOrder| | | PerVector| PerVector_K1| | Lengths_K0_N_K1| ArrangeOrder| | | PerVector| PerVector_K1| | PerStore| PerStore| MBlock_MPerBlock| |
//######################| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | NBlock_NPerBlock| |
/* Prefetch 2, consume enormous vgpr resource*/
// 8 Waves
DeviceGemmWmma_CShuffle< Row, Col, Row, F16, F16, F16, F32, F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding, 2, 256, 128, 128, 32, 8, 16, 16, 4, 2, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, true, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, true, 1, 1, S<1, 32, 1, 8>, 8>,
// 4 Waves
DeviceGemmWmma_CShuffle< Row, Col, Row, F16, F16, F16, F32, F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding, 2, 128, 128, 64, 64, 8, 16, 16, 4, 2, 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, 1, S<1, 32, 1, 4>, 8>,
// 2 Waves
DeviceGemmWmma_CShuffle< Row, Col, Row, F16, F16, F16, F32, F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding, 2, 64, 64, 32, 32, 8, 16, 16, 4, 1, S<4, 16, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, true, S<4, 16, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, true, 1, 1, S<1, 16, 1, 4>, 8>,
// 1 Wave
DeviceGemmWmma_CShuffle< Row, Col, Row, F16, F16, F16, F32, F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding, 2, 32, 16, 16, 32, 8, 16, 16, 1, 1, S<2, 16, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, true, S<2, 16, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, true, 1, 1, S<1, 16, 1, 2>, 8>,
/* Prefetch 1, prefer larger KPerBlock value for better latency hiding*/
// 8 Waves
DeviceGemmWmma_CShuffle< Row, Col, Row, F16, F16, F16, F32, F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding, 1, 256, 128, 256, 64, 8, 16, 16, 4, 4, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, true, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, true, 1, 1, S<1, 32, 1, 8>, 8>,
DeviceGemmWmma_CShuffle< Row, Col, Row, F16, F16, F16, F32, F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding, 1, 256, 128, 128, 64, 8, 16, 16, 4, 2, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, true, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, true, 1, 1, S<1, 32, 1, 8>, 8>,
DeviceGemmWmma_CShuffle< Row, Col, Row, F16, F16, F16, F32, F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding, 1, 256, 128, 160, 64, 8, 16, 16, 2, 5, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, true, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, true, 1, 1, S<1, 64, 1, 4>, 8>,
// 4 Waves
DeviceGemmWmma_CShuffle< Row, Col, Row, F16, F16, F16, F32, F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding, 1, 128, 128, 128, 32, 8, 16, 16, 4, 4, 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, 1, S<1, 32, 1, 4>, 8>,
DeviceGemmWmma_CShuffle< Row, Col, Row, F16, F16, F16, F32, F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding, 1, 128, 256, 64, 64, 8, 16, 16, 8, 2, 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, 1, S<1, 32, 1, 4>, 8>,
DeviceGemmWmma_CShuffle< Row, Col, Row, F16, F16, F16, F32, F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding, 1, 128, 64, 256, 64, 8, 16, 16, 2, 8, 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, 1, S<1, 32, 1, 4>, 8>,
DeviceGemmWmma_CShuffle< Row, Col, Row, F16, F16, F16, F32, F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding, 1, 128, 64, 80, 64, 8, 16, 16, 1, 5, S<4, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, true, S<8, 16, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, true, 1, 1, S<1, 64, 1, 2>, 8>,
// 2 Waves
DeviceGemmWmma_CShuffle< Row, Col, Row, F16, F16, F16, F32, F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding, 1, 64, 16, 64, 64, 8, 16, 16, 1, 2, S<4, 16, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, true, S<4, 16, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, true, 1, 1, S<1, 16, 1, 4>, 8>,
DeviceGemmWmma_CShuffle< Row, Col, Row, F16, F16, F16, F32, F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding, 1, 64, 64, 32, 64, 8, 16, 16, 4, 1, S<4, 16, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, true, S<4, 16, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, true, 1, 1, S<1, 16, 1, 4>, 8>,
DeviceGemmWmma_CShuffle< Row, Col, Row, F16, F16, F16, F32, F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding, 1, 64, 32, 64, 64, 8, 16, 16, 2, 2, S<4, 16, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, true, S<4, 16, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, true, 1, 1, S<1, 16, 1, 4>, 8>,
// 1 Wave
DeviceGemmWmma_CShuffle< Row, Col, Row, F16, F16, F16, F32, F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding, 1, 32, 16, 32, 64, 8, 16, 16, 1, 2, S<2, 16, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, true, S<2, 16, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, true, 1, 1, S<1, 16, 1, 2>, 8>,
DeviceGemmWmma_CShuffle< Row, Col, Row, F16, F16, F16, F32, F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding, 1, 32, 16, 16, 64, 8, 16, 16, 1, 1, S<2, 16, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, true, S<2, 16, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, true, 1, 1, S<1, 16, 1, 2>, 8>
// clang-format on
>;
void add_device_gemm_wmma_f16_f16_f16_mk_nk_mn_instances(
std::vector<std::unique_ptr<
DeviceGemm<Row, Col, Row, F16, F16, F16, PassThrough, PassThrough, PassThrough>>>&
instances)
{
add_device_operation_instances(instances, device_gemm_wmma_f16_f16_f16_mk_nk_mn_instances{});
}
} // namespace instance
} // namespace device
} // namespace tensor_operation
} // namespace ck
library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_c_shuffle_f16_f16_f16_mk_kn_mn_instance.cpp
View file @ ae3d6cb6
......@@ -34,6 +34,15 @@ static constexpr auto MNPadding = ck::tensor_operation::device::GemmSpecializati
static constexpr auto MNKPadding = ck::tensor_operation::device::GemmSpecialization::MNKPadding;
using device_gemm_xdl_c_shuffle_f16_f16_f16_mk_kn_mn_generic_instances = std::tuple<
// clang-format off
//#####################| ALayout| BLayout| CLayout| AData| BData| CData| AccData| CShuffle| A| B| C| GEMM| NumGemmK| Block| MPer| NPer| KPer| AK1| BK1| MPer| NPer| MXdl| NXdl| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockLds| BBlockTransfer| BBlockTransfer| BBlockTransfer| BlockTransfer| BBlockTransfer| BBlockTransfer| BBlockLds| CShuffle| CShuffle| CBlockTransferClusterLengths| CBlockTransfer| LoopScheduler| Pipeline|
//#####################| | | | Type| Type| Type| Type| DataType| Elementwise| Elementwise| Elementwise| Specialization| Prefetch| Size| Block| Block| Block| | | XDL| XDL| Per| Per| ThreadCluster| ThreadCluster| SrcAccessOrder| SrcVectorDim| SrcScalar| DstScalar| AddExtraM| ThreadCluster| ThreadCluster| SrcAccessOrder| SrcVectorDim| SrcScalar| DstScalar| AddExtraN| MXdlPerWave| NXdlPerWave| _MBlock_MWaveMPerXdl| ScalarPerVector| | |
//#####################| | | | | | | | | Operation| Operation| Operation| | Stage| | | | | | | | | Wave| Wave| Lengths_K0_M_K1| ArrangeOrder| | | PerVector| PerVector_K1| | Lengths_K0_N_K1| ArrangeOrder| | | PerVector| PerVector_K1| | PerShuffle| PerShuffle| _NBlock_NWaveNPerXdl| _NWaveNPerXdl| | |
DeviceGemm_Xdl_CShuffle< Row, Row, Row, F16, F16, F16, F32, F16, PassThrough, PassThrough, PassThrough, MNKPadding, 1, 128, 128, 128, 32, 8, 8, 32, 32, 4, 2, S<4, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 1, 8, 1, S<4, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 1, 8, 1, 1, 1, S<1, 16, 1, 8>, 1, LoopScheduler::Default, PipelineVersion::v1>
// clang-format on
>;
// Compilation parameters for a[m, k] * b[k, n] = c[m, n]
template <ck::tensor_operation::device::GemmSpecialization GemmSpec>
using device_gemm_xdl_c_shuffle_f16_f16_f16_mk_kn_mn_instances = std::tuple<
......@@ -108,6 +117,9 @@ void add_device_gemm_xdl_c_shuffle_f16_f16_f16_mk_kn_mn_instances(
DeviceGemm<Row, Row, Row, F16, F16, F16, PassThrough, PassThrough, PassThrough>>>&
instances)
{
add_device_operation_instances(
instances, device_gemm_xdl_c_shuffle_f16_f16_f16_mk_kn_mn_generic_instances{});
add_device_operation_instances(
instances, device_gemm_xdl_c_shuffle_f16_f16_f16_mk_kn_mn_instances<GemmDefault>{});
......
library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_c_shuffle_f16_f16_f16_mk_nk_mn_instance.cpp
View file @ ae3d6cb6
......@@ -32,6 +32,17 @@ static constexpr auto GemmDefault = ck::tensor_operation::device::GemmSpecializa
static constexpr auto MNPadding = ck::tensor_operation::device::GemmSpecialization::MNPadding;
static constexpr auto MNKPadding = ck::tensor_operation::device::GemmSpecialization::MNKPadding;
// Compilation parameters for a[m, k] * b[n, k] = c[m, n]
using device_gemm_xdl_c_shuffle_f16_f16_f16_mk_nk_mn_generic_instances = std::tuple<
// clang-format off
//#####################| ALayout| BLayout| CLayout| AData| BData| CData| AccData| CShuffle| A| B| C| GEMM| NumGemmK| Block| MPer| NPer| KPer| AK1| BK1| MPer| NPer| MXdl| NXdl| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockLds| BBlockTransfer| BBlockTransfer| BBlockTransfer| BlockTransfer| BBlockTransfer| BBlockTransfer| BBlockLds| CShuffle| CShuffle| CBlockTransferClusterLengths| CBlockTransfer| LoopScheduler| Pipeline|
//#####################| | | | Type| Type| Type| Type| DataType| Elementwise| Elementwise| Elementwise| Specialization| Prefetch| Size| Block| Block| Block| | | XDL| XDL| Per| Per| ThreadCluster| ThreadCluster| SrcAccessOrder| SrcVectorDim| SrcScalar| DstScalar| AddExtraM| ThreadCluster| ThreadCluster| SrcAccessOrder| SrcVectorDim| SrcScalar| DstScalar| AddExtraN| MXdlPerWave| NXdlPerWave| _MBlock_MWaveMPerXdl| ScalarPerVector| | |
//#####################| | | | | | | | | Operation| Operation| Operation| | Stage| | | | | | | | | Wave| Wave| Lengths_K0_M_K1| ArrangeOrder| | | PerVector| PerVector_K1| | Lengths_K0_N_K1| ArrangeOrder| | | PerVector| PerVector_K1| | PerShuffle| PerShuffle| _NBlock_NWaveNPerXdl| _NWaveNPerXdl| | |
//#####################| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
DeviceGemm_Xdl_CShuffle< Row, Col, Row, F16, F16, F16, F32, F16, PassThrough, PassThrough, PassThrough, MNKPadding, 1, 128, 128, 128, 32, 8, 8, 32, 32, 4, 2, S<4, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 1, 8, 1, S<4, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 1, 8, 1, 1, 1, S<1, 16, 1, 8>, 1, LoopScheduler::Default, PipelineVersion::v1>
// clang-format on
>;
template <ck::tensor_operation::device::GemmSpecialization GemmSpec>
// Compilation parameters for a[m, k] * b[n, k] = c[m, n]
using device_gemm_xdl_c_shuffle_f16_f16_f16_mk_nk_mn_instances = std::tuple<
......@@ -97,6 +108,9 @@ void add_device_gemm_xdl_c_shuffle_f16_f16_f16_mk_nk_mn_instances(
DeviceGemm<Row, Col, Row, F16, F16, F16, PassThrough, PassThrough, PassThrough>>>&
instances)
{
add_device_operation_instances(
instances, device_gemm_xdl_c_shuffle_f16_f16_f16_mk_nk_mn_generic_instances{});
add_device_operation_instances(
instances, device_gemm_xdl_c_shuffle_f16_f16_f16_mk_nk_mn_instances<GemmDefault>{});
......
library/src/tensor_operation_instance/gpu/gemm_bilinear/device_gemm_bilinear_wmma_c_shuffle_i8_i8_i8_i8_km_kn_mn_mn_instance.cpp
View file @ ae3d6cb6
......@@ -36,32 +36,32 @@ static constexpr auto GemmMNKPadding = ck::tensor_operation::device::GemmSpecial
// e[m, n] = bilinear(a[m, k] * b[k, n], d[m, n])
using device_gemm_bilinear_wmma_c_shuffle_i8_i8_i8_i8_km_kn_mn_mn_instances = std::tuple<
// clang-format off
//################################| A| B| Ds| E| AData| BData| DsData| EData| AccData| CShuffle| A| B| CDE| GEMM| Block| MPer| NPer| K0Per| K1| MPer| NPer| MRepeat| NRepeat| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockLds| BBlockTransfer| BBlockTransfer| BBlockTransfer| BlockTransfer| BBlockTransfer| BBlockTransfer| BBlockLds| CShuffle| CShuffle| CBlockTransferClusterLengths| CBlockTransfer|
//################################| Layout| Layout| Layout| Layout| Type| Type| Type| Type| Type| DataType| Elementwise| Elementwise| Elementwise| Specialization| Size| Block| Block| Block| | WMMA| WMMA| | | ThreadCluster| ThreadCluster| SrcAccessOrder| SrcVectorDim| SrcScalar| DstScalar| AddExtraM| ThreadCluster| ThreadCluster| SrcAccessOrder| SrcVectorDim| SrcScalar| DstScalar| AddExtraN| MXdlPerWave| NXdlPerWave| _MBlock_MWaveMPerXdl| ScalarPerVector|
//################################| | | | | | | | | | | Operation| Operation| Operation| | | | | | | | | | | Lengths_K0_M_K1| ArrangeOrder| | | PerVector| PerVector_K1| | Lengths_K0_N_K1| ArrangeOrder| | | PerVector| PerVector_K1| | PerShuffle| PerShuffle| _NBlock_NWaveNPerXdl| _NWaveNPerXdl|
//################################| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
DeviceGemmMultipleD_Wmma_CShuffle< Col, Row, Row_Tuple, Row, I8, I8, I8_Tuple, I8, I32, I32, PassThrough, PassThrough, Bilinear, GemmDefault, 256, 128, 128, 4, 16, 16, 16, 4, 2, S<4, 64, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 16, 1, S<4, 64, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 16, 1, 1, 2, S<1, 32, 1, 8>, 16>,
DeviceGemmMultipleD_Wmma_CShuffle< Col, Row, Row_Tuple, Row, I8, I8, I8_Tuple, I8, I32, I32, PassThrough, PassThrough, Bilinear, GemmDefault, 128, 64, 64, 4, 16, 16, 16, 2, 2, S<4, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 16, 1, S<4, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 16, 1, 1, 2, S<1, 32, 1, 4>, 16>,
DeviceGemmMultipleD_Wmma_CShuffle< Col, Row, Row_Tuple, Row, I8, I8, I8_Tuple, I8, I32, I32, PassThrough, PassThrough, Bilinear, GemmDefault, 64, 32, 32, 4, 16, 16, 16, 1, 2, S<4, 16, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 16, 1, S<4, 16, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 16, 1, 1, 2, S<1, 32, 1, 2>, 16>,
DeviceGemmMultipleD_Wmma_CShuffle< Col, Row, Row_Tuple, Row, I8, I8, I8_Tuple, I8, I32, I32, PassThrough, PassThrough, Bilinear, GemmDefault, 32, 16, 16, 4, 16, 16, 16, 1, 1, S<4, 8, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 16, 1, S<4, 8, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 16, 1, 1, 1, S<1, 16, 1, 2>, 8>,
//################################| A| B| Ds| E| AData| BData| AccData| CShuffle| DsData| EData| A| B| CDE| GEMM| Prefetch| Block| MPer| NPer| K0Per| K1| MPer| NPer| MRepeat| NRepeat| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockLds| BBlockTransfer| BBlockTransfer| BBlockTransfer| BlockTransfer| BBlockTransfer| BBlockTransfer| BBlockLds| CShuffle| CShuffle| CBlockTransferClusterLengths| CBlockTransfer|
//################################| Layout| Layout| Layout| Layout| Type| Type| Type| DataType| Type| Type| Elementwise| Elementwise| Elementwise| Specialization| Stage| Size| Block| Block| Block| | WMMA| WMMA| | | ThreadCluster| ThreadCluster| SrcAccessOrder| SrcVectorDim| SrcScalar| DstScalar| AddExtraM| ThreadCluster| ThreadCluster| SrcAccessOrder| SrcVectorDim| SrcScalar| DstScalar| AddExtraN| MXdlPerWave| NXdlPerWave| _MBlock_MWaveMPerXdl| ScalarPerVector|
//################################| | | | | | | | | | | Operation| Operation| Operation| | | | | | | | | | | | Lengths_K0_M_K1| ArrangeOrder| | | PerVector| PerVector_K1| | Lengths_K0_N_K1| ArrangeOrder| | | PerVector| PerVector_K1| | PerShuffle| PerShuffle| _NBlock_NWaveNPerXdl| _NWaveNPerXdl|
//################################| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
DeviceGemmMultipleD_Wmma_CShuffle< Col, Row, Row_Tuple, Row, I8, I8, I32, I32, I8_Tuple, I8, PassThrough, PassThrough, Bilinear, GemmDefault, 1, 256, 128, 128, 64, 16, 16, 16, 4, 2, S<4, 64, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 16, 1, S<4, 64, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 16, 1, 1, 2, S<1, 32, 1, 8>, 16>,
DeviceGemmMultipleD_Wmma_CShuffle< Col, Row, Row_Tuple, Row, I8, I8, I32, I32, I8_Tuple, I8, PassThrough, PassThrough, Bilinear, GemmDefault, 1, 128, 64, 64, 64, 16, 16, 16, 2, 2, S<4, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 16, 1, S<4, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 16, 1, 1, 2, S<1, 32, 1, 4>, 16>,
DeviceGemmMultipleD_Wmma_CShuffle< Col, Row, Row_Tuple, Row, I8, I8, I32, I32, I8_Tuple, I8, PassThrough, PassThrough, Bilinear, GemmDefault, 1, 64, 32, 32, 64, 16, 16, 16, 1, 2, S<4, 16, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 16, 1, S<4, 16, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 16, 1, 1, 2, S<1, 32, 1, 2>, 16>,
DeviceGemmMultipleD_Wmma_CShuffle< Col, Row, Row_Tuple, Row, I8, I8, I32, I32, I8_Tuple, I8, PassThrough, PassThrough, Bilinear, GemmDefault, 1, 32, 16, 16, 64, 16, 16, 16, 1, 1, S<4, 8, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 16, 1, S<4, 8, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 16, 1, 1, 1, S<1, 16, 1, 2>, 8>,
// M/N/K padding
//################################| A| B| Ds| E| AData| BData| DsData| EData| AccData| CShuffle| A| B| CDE| GEMM| Block| MPer| NPer| K0Per| K1| MPer| NPer| MRepeat| NRepeat| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockLds| BBlockTransfer| BBlockTransfer| BBlockTransfer| BlockTransfer| BBlockTransfer| BBlockTransfer| BBlockLds| CShuffle| CShuffle| CBlockTransferClusterLengths| CBlockTransfer|
//################################| Layout| Layout| Layout| Layout| Type| Type| Type| Type| Type| DataType| Elementwise| Elementwise| Elementwise| Specialization| Size| Block| Block| Block| | WMMA| WMMA| | | ThreadCluster| ThreadCluster| SrcAccessOrder| SrcVectorDim| SrcScalar| DstScalar| AddExtraM| ThreadCluster| ThreadCluster| SrcAccessOrder| SrcVectorDim| SrcScalar| DstScalar| AddExtraN| MXdlPerWave| NXdlPerWave| _MBlock_MWaveMPerXdl| ScalarPerVector|
//################################| | | | | | | | | | | Operation| Operation| Operation| | | | | | | | | | | Lengths_K0_M_K1| ArrangeOrder| | | PerVector| PerVector_K1| | Lengths_K0_N_K1| ArrangeOrder| | | PerVector| PerVector_K1| | PerShuffle| PerShuffle| _NBlock_NWaveNPerXdl| _NWaveNPerXdl|
//################################| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
DeviceGemmMultipleD_Wmma_CShuffle< Col, Row, Row_Tuple, Row, I8, I8, I8_Tuple, I8, I32, I32, PassThrough, PassThrough, Bilinear, GemmMNKPadding, 256, 128, 128, 4, 16, 16, 16, 4, 2, S<4, 64, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 16, 1, S<4, 64, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 16, 1, 1, 2, S<1, 32, 1, 8>, 16>,
DeviceGemmMultipleD_Wmma_CShuffle< Col, Row, Row_Tuple, Row, I8, I8, I8_Tuple, I8, I32, I32, PassThrough, PassThrough, Bilinear, GemmMNKPadding, 128, 64, 64, 4, 16, 16, 16, 2, 2, S<4, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 16, 1, S<4, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 16, 1, 1, 2, S<1, 32, 1, 4>, 16>,
DeviceGemmMultipleD_Wmma_CShuffle< Col, Row, Row_Tuple, Row, I8, I8, I8_Tuple, I8, I32, I32, PassThrough, PassThrough, Bilinear, GemmMNKPadding, 64, 32, 32, 4, 16, 16, 16, 1, 2, S<4, 16, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 16, 1, S<4, 16, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 16, 1, 1, 2, S<1, 32, 1, 2>, 16>,
DeviceGemmMultipleD_Wmma_CShuffle< Col, Row, Row_Tuple, Row, I8, I8, I8_Tuple, I8, I32, I32, PassThrough, PassThrough, Bilinear, GemmMNKPadding, 32, 16, 16, 4, 16, 16, 16, 1, 1, S<4, 8, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 16, 1, S<4, 8, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 16, 1, 1, 1, S<1, 16, 1, 2>, 8>,
DeviceGemmMultipleD_Wmma_CShuffle< Col, Row, Row_Tuple, Row, I8, I8, I8_Tuple, I8, I32, I32, PassThrough, PassThrough, Bilinear, GemmMNKPadding, 256, 128, 128, 8, 8, 16, 16, 4, 2, S<4, 64, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 8, 1, S<4, 64, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 8, 1, 1, 2, S<1, 32, 1, 8>, 8>,
DeviceGemmMultipleD_Wmma_CShuffle< Col, Row, Row_Tuple, Row, I8, I8, I8_Tuple, I8, I32, I32, PassThrough, PassThrough, Bilinear, GemmMNKPadding, 128, 64, 64, 8, 8, 16, 16, 2, 2, S<4, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 8, 1, S<4, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 8, 1, 1, 2, S<1, 32, 1, 4>, 8>,
DeviceGemmMultipleD_Wmma_CShuffle< Col, Row, Row_Tuple, Row, I8, I8, I8_Tuple, I8, I32, I32, PassThrough, PassThrough, Bilinear, GemmMNKPadding, 64, 32, 32, 8, 8, 16, 16, 1, 2, S<4, 16, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 8, 1, S<4, 16, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 8, 1, 1, 2, S<1, 32, 1, 2>, 8>,
DeviceGemmMultipleD_Wmma_CShuffle< Col, Row, Row_Tuple, Row, I8, I8, I8_Tuple, I8, I32, I32, PassThrough, PassThrough, Bilinear, GemmMNKPadding, 32, 16, 16, 8, 8, 16, 16, 1, 1, S<4, 8, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 8, 1, S<4, 8, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 8, 1, 1, 1, S<1, 16, 1, 2>, 8>,
DeviceGemmMultipleD_Wmma_CShuffle< Col, Row, Row_Tuple, Row, I8, I8, I8_Tuple, I8, I32, I32, PassThrough, PassThrough, Bilinear, GemmMNKPadding, 256, 128, 128, 8, 4, 16, 16, 4, 2, S<4, 64, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 4, 1, S<4, 64, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 4, 1, 1, 2, S<1, 32, 1, 8>, 4>,
DeviceGemmMultipleD_Wmma_CShuffle< Col, Row, Row_Tuple, Row, I8, I8, I8_Tuple, I8, I32, I32, PassThrough, PassThrough, Bilinear, GemmMNKPadding, 128, 64, 64, 8, 4, 16, 16, 2, 2, S<4, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 4, 1, S<4, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 4, 1, 1, 2, S<1, 32, 1, 4>, 4>,
DeviceGemmMultipleD_Wmma_CShuffle< Col, Row, Row_Tuple, Row, I8, I8, I8_Tuple, I8, I32, I32, PassThrough, PassThrough, Bilinear, GemmMNKPadding, 64, 32, 32, 8, 4, 16, 16, 1, 2, S<4, 16, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 4, 1, S<4, 16, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 4, 1, 1, 2, S<1, 32, 1, 2>, 4>,
DeviceGemmMultipleD_Wmma_CShuffle< Col, Row, Row_Tuple, Row, I8, I8, I8_Tuple, I8, I32, I32, PassThrough, PassThrough, Bilinear, GemmMNKPadding, 32, 16, 16, 8, 4, 16, 16, 1, 1, S<4, 8, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 4, 1, S<4, 8, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 4, 1, 1, 1, S<1, 16, 1, 2>, 4>
//################################| A| B| Ds| E| AData| BData| AccData| CShuffle| DsData| EData| A| B| CDE| GEMM| Prefetch| Block| MPer| NPer| K0Per| K1| MPer| NPer| MRepeat| NRepeat| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockLds| BBlockTransfer| BBlockTransfer| BBlockTransfer| BlockTransfer| BBlockTransfer| BBlockTransfer| BBlockLds| CShuffle| CShuffle| CBlockTransferClusterLengths| CBlockTransfer|
//################################| Layout| Layout| Layout| Layout| Type| Type| Type| DataType| Type| Type| Elementwise| Elementwise| Elementwise| Specialization| Stage| Size| Block| Block| Block| | WMMA| WMMA| | | ThreadCluster| ThreadCluster| SrcAccessOrder| SrcVectorDim| SrcScalar| DstScalar| AddExtraM| ThreadCluster| ThreadCluster| SrcAccessOrder| SrcVectorDim| SrcScalar| DstScalar| AddExtraN| MXdlPerWave| NXdlPerWave| _MBlock_MWaveMPerXdl| ScalarPerVector|
//################################| | | | | | | | | | | Operation| Operation| Operation| | | | | | | | | | | | Lengths_K0_M_K1| ArrangeOrder| | | PerVector| PerVector_K1| | Lengths_K0_N_K1| ArrangeOrder| | | PerVector| PerVector_K1| | PerShuffle| PerShuffle| _NBlock_NWaveNPerXdl| _NWaveNPerXdl|
//################################| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
DeviceGemmMultipleD_Wmma_CShuffle< Col, Row, Row_Tuple, Row, I8, I8, I32, I32, I8_Tuple, I8, PassThrough, PassThrough, Bilinear, GemmMNKPadding, 1, 256, 128, 128, 64, 16, 16, 16, 4, 2, S<4, 64, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 16, 1, S<4, 64, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 16, 1, 1, 2, S<1, 32, 1, 8>, 16>,
DeviceGemmMultipleD_Wmma_CShuffle< Col, Row, Row_Tuple, Row, I8, I8, I32, I32, I8_Tuple, I8, PassThrough, PassThrough, Bilinear, GemmMNKPadding, 1, 128, 64, 64, 64, 16, 16, 16, 2, 2, S<4, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 16, 1, S<4, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 16, 1, 1, 2, S<1, 32, 1, 4>, 16>,
DeviceGemmMultipleD_Wmma_CShuffle< Col, Row, Row_Tuple, Row, I8, I8, I32, I32, I8_Tuple, I8, PassThrough, PassThrough, Bilinear, GemmMNKPadding, 1, 64, 32, 32, 64, 16, 16, 16, 1, 2, S<4, 16, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 16, 1, S<4, 16, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 16, 1, 1, 2, S<1, 32, 1, 2>, 16>,
DeviceGemmMultipleD_Wmma_CShuffle< Col, Row, Row_Tuple, Row, I8, I8, I32, I32, I8_Tuple, I8, PassThrough, PassThrough, Bilinear, GemmMNKPadding, 1, 32, 16, 16, 64, 16, 16, 16, 1, 1, S<4, 8, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 16, 1, S<4, 8, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 16, 1, 1, 1, S<1, 16, 1, 2>, 8>,
DeviceGemmMultipleD_Wmma_CShuffle< Col, Row, Row_Tuple, Row, I8, I8, I32, I32, I8_Tuple, I8, PassThrough, PassThrough, Bilinear, GemmMNKPadding, 1, 256, 128, 128, 64, 8, 16, 16, 4, 2, S<4, 64, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 8, 1, S<4, 64, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 8, 1, 1, 2, S<1, 32, 1, 8>, 8>,
DeviceGemmMultipleD_Wmma_CShuffle< Col, Row, Row_Tuple, Row, I8, I8, I32, I32, I8_Tuple, I8, PassThrough, PassThrough, Bilinear, GemmMNKPadding, 1, 128, 64, 64, 64, 8, 16, 16, 2, 2, S<4, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 8, 1, S<4, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 8, 1, 1, 2, S<1, 32, 1, 4>, 8>,
DeviceGemmMultipleD_Wmma_CShuffle< Col, Row, Row_Tuple, Row, I8, I8, I32, I32, I8_Tuple, I8, PassThrough, PassThrough, Bilinear, GemmMNKPadding, 1, 64, 32, 32, 64, 8, 16, 16, 1, 2, S<4, 16, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 8, 1, S<4, 16, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 8, 1, 1, 2, S<1, 32, 1, 2>, 8>,
DeviceGemmMultipleD_Wmma_CShuffle< Col, Row, Row_Tuple, Row, I8, I8, I32, I32, I8_Tuple, I8, PassThrough, PassThrough, Bilinear, GemmMNKPadding, 1, 32, 16, 16, 64, 8, 16, 16, 1, 1, S<4, 8, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 8, 1, S<4, 8, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 8, 1, 1, 1, S<1, 16, 1, 2>, 8>,
DeviceGemmMultipleD_Wmma_CShuffle< Col, Row, Row_Tuple, Row, I8, I8, I32, I32, I8_Tuple, I8, PassThrough, PassThrough, Bilinear, GemmMNKPadding, 1, 256, 128, 128, 32, 4, 16, 16, 4, 2, S<4, 64, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 4, 1, S<4, 64, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 4, 1, 1, 2, S<1, 32, 1, 8>, 4>,
DeviceGemmMultipleD_Wmma_CShuffle< Col, Row, Row_Tuple, Row, I8, I8, I32, I32, I8_Tuple, I8, PassThrough, PassThrough, Bilinear, GemmMNKPadding, 1, 128, 64, 64, 32, 4, 16, 16, 2, 2, S<4, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 4, 1, S<4, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 4, 1, 1, 2, S<1, 32, 1, 4>, 4>,
DeviceGemmMultipleD_Wmma_CShuffle< Col, Row, Row_Tuple, Row, I8, I8, I32, I32, I8_Tuple, I8, PassThrough, PassThrough, Bilinear, GemmMNKPadding, 1, 64, 32, 32, 32, 4, 16, 16, 1, 2, S<4, 16, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 4, 1, S<4, 16, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 4, 1, 1, 2, S<1, 32, 1, 2>, 4>,
DeviceGemmMultipleD_Wmma_CShuffle< Col, Row, Row_Tuple, Row, I8, I8, I32, I32, I8_Tuple, I8, PassThrough, PassThrough, Bilinear, GemmMNKPadding, 1, 32, 16, 16, 32, 4, 16, 16, 1, 1, S<4, 8, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 4, 1, S<4, 8, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 4, 1, 1, 1, S<1, 16, 1, 2>, 4>
// clang-format on
>;
......
library/src/tensor_operation_instance/gpu/gemm_bilinear/device_gemm_bilinear_wmma_c_shuffle_i8_i8_i8_i8_km_nk_mn_mn_instance.cpp
View file @ ae3d6cb6
......@@ -36,32 +36,32 @@ static constexpr auto GemmMNKPadding = ck::tensor_operation::device::GemmSpecial
// e[m, n] = bilinear(a[m, k] * b[k, n], d[m, n])
using device_gemm_bilinear_wmma_c_shuffle_i8_i8_i8_i8_km_nk_mn_mn_instances = std::tuple<
// clang-format off
//################################| A| B| Ds| E| AData| BData| DsData| EData| AccData| CShuffle| A| B| CDE| GEMM| Block| MPer| NPer| K0Per| K1| MPer| NPer| MRepeat| NRepeat| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockLds| BBlockTransfer| BBlockTransfer| BBlockTransfer| BlockTransfer| BBlockTransfer| BBlockTransfer| BBlockLds| CShuffle| CShuffle| CBlockTransferClusterLengths| CBlockTransfer|
//################################| Layout| Layout| Layout| Layout| Type| Type| Type| Type| Type| DataType| Elementwise| Elementwise| Elementwise| Specialization| Size| Block| Block| Block| | WMMA| WMMA| | | ThreadCluster| ThreadCluster| SrcAccessOrder| SrcVectorDim| SrcScalar| DstScalar| AddExtraM| ThreadCluster| ThreadCluster| SrcAccessOrder| SrcVectorDim| SrcScalar| DstScalar| AddExtraN| MXdlPerWave| NXdlPerWave| _MBlock_MWaveMPerXdl| ScalarPerVector|
//################################| | | | | | | | | | | Operation| Operation| Operation| | | | | | | | | | | Lengths_K0_M_K1| ArrangeOrder| | | PerVector| PerVector_K1| | Lengths_K0_N_K1| ArrangeOrder| | | PerVector| PerVector_K1| | PerShuffle| PerShuffle| _NBlock_NWaveNPerXdl| _NWaveNPerXdl|
//################################| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
DeviceGemmMultipleD_Wmma_CShuffle< Col, Col, Row_Tuple, Row, I8, I8, I8_Tuple, I8, I32, I32, PassThrough, PassThrough, Bilinear, GemmDefault, 256, 128, 128, 4, 16, 16, 16, 4, 2, S<4, 64, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 16, 1, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, 1, 1, 2, S<1, 32, 1, 8>, 16>,
DeviceGemmMultipleD_Wmma_CShuffle< Col, Col, Row_Tuple, Row, I8, I8, I8_Tuple, I8, I32, I32, PassThrough, PassThrough, Bilinear, GemmDefault, 128, 64, 64, 4, 16, 16, 16, 2, 2, S<4, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 16, 1, S<4, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, 1, 1, 2, S<1, 32, 1, 4>, 16>,
DeviceGemmMultipleD_Wmma_CShuffle< Col, Col, Row_Tuple, Row, I8, I8, I8_Tuple, I8, I32, I32, PassThrough, PassThrough, Bilinear, GemmDefault, 64, 32, 32, 4, 16, 16, 16, 1, 2, S<4, 16, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 16, 1, S<4, 16, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, 1, 1, 2, S<1, 32, 1, 2>, 16>,
DeviceGemmMultipleD_Wmma_CShuffle< Col, Col, Row_Tuple, Row, I8, I8, I8_Tuple, I8, I32, I32, PassThrough, PassThrough, Bilinear, GemmDefault, 32, 16, 16, 4, 16, 16, 16, 1, 1, S<4, 8, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 16, 1, S<2, 16, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, 1, 1, 1, S<1, 16, 1, 2>, 8>,
//################################| A| B| Ds| E| AData| BData| AccData| CShuffle| DsData| EData| A| B| CDE| GEMM| Prefetch| Block| MPer| NPer| K0Per| K1| MPer| NPer| MRepeat| NRepeat| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockLds| BBlockTransfer| BBlockTransfer| BBlockTransfer| BlockTransfer| BBlockTransfer| BBlockTransfer| BBlockLds| CShuffle| CShuffle| CBlockTransferClusterLengths| CBlockTransfer|
//################################| Layout| Layout| Layout| Layout| Type| Type| Type| DataType| Type| Type| Elementwise| Elementwise| Elementwise| Specialization| Stage| Size| Block| Block| Block| | WMMA| WMMA| | | ThreadCluster| ThreadCluster| SrcAccessOrder| SrcVectorDim| SrcScalar| DstScalar| AddExtraM| ThreadCluster| ThreadCluster| SrcAccessOrder| SrcVectorDim| SrcScalar| DstScalar| AddExtraN| MXdlPerWave| NXdlPerWave| _MBlock_MWaveMPerXdl| ScalarPerVector|
//################################| | | | | | | | | | | Operation| Operation| Operation| | | | | | | | | | | | Lengths_K0_M_K1| ArrangeOrder| | | PerVector| PerVector_K1| | Lengths_K0_N_K1| ArrangeOrder| | | PerVector| PerVector_K1| | PerShuffle| PerShuffle| _NBlock_NWaveNPerXdl| _NWaveNPerXdl|
//################################| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
DeviceGemmMultipleD_Wmma_CShuffle< Col, Col, Row_Tuple, Row, I8, I8, I32, I32, I8_Tuple, I8, PassThrough, PassThrough, Bilinear, GemmDefault, 1, 256, 128, 128, 64, 16, 16, 16, 4, 2, S<4, 64, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 16, 1, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, 1, 1, 2, S<1, 32, 1, 8>, 16>,
DeviceGemmMultipleD_Wmma_CShuffle< Col, Col, Row_Tuple, Row, I8, I8, I32, I32, I8_Tuple, I8, PassThrough, PassThrough, Bilinear, GemmDefault, 1, 128, 64, 64, 64, 16, 16, 16, 2, 2, S<4, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 16, 1, S<4, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, 1, 1, 2, S<1, 32, 1, 4>, 16>,
DeviceGemmMultipleD_Wmma_CShuffle< Col, Col, Row_Tuple, Row, I8, I8, I32, I32, I8_Tuple, I8, PassThrough, PassThrough, Bilinear, GemmDefault, 1, 64, 32, 32, 64, 16, 16, 16, 1, 2, S<4, 16, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 16, 1, S<4, 16, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, 1, 1, 2, S<1, 32, 1, 2>, 16>,
DeviceGemmMultipleD_Wmma_CShuffle< Col, Col, Row_Tuple, Row, I8, I8, I32, I32, I8_Tuple, I8, PassThrough, PassThrough, Bilinear, GemmDefault, 1, 32, 16, 16, 64, 16, 16, 16, 1, 1, S<4, 8, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 16, 1, S<2, 16, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, 1, 1, 1, S<1, 16, 1, 2>, 8>,
// M/N/K padding
//################################| A| B| Ds| E| AData| BData| DsData| EData| AccData| CShuffle| A| B| CDE| GEMM| Block| MPer| NPer| K0Per| K1| MPer| NPer| MRepeat| NRepeat| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockLds| BBlockTransfer| BBlockTransfer| BBlockTransfer| BlockTransfer| BBlockTransfer| BBlockTransfer| BBlockLds| CShuffle| CShuffle| CBlockTransferClusterLengths| CBlockTransfer|
//################################| Layout| Layout| Layout| Layout| Type| Type| Type| Type| Type| DataType| Elementwise| Elementwise| Elementwise| Specialization| Size| Block| Block| Block| | WMMA| WMMA| | | ThreadCluster| ThreadCluster| SrcAccessOrder| SrcVectorDim| SrcScalar| DstScalar| AddExtraM| ThreadCluster| ThreadCluster| SrcAccessOrder| SrcVectorDim| SrcScalar| DstScalar| AddExtraN| MXdlPerWave| NXdlPerWave| _MBlock_MWaveMPerXdl| ScalarPerVector|
//################################| | | | | | | | | | | Operation| Operation| Operation| | | | | | | | | | | Lengths_K0_M_K1| ArrangeOrder| | | PerVector| PerVector_K1| | Lengths_K0_N_K1| ArrangeOrder| | | PerVector| PerVector_K1| | PerShuffle| PerShuffle| _NBlock_NWaveNPerXdl| _NWaveNPerXdl|
//################################| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
DeviceGemmMultipleD_Wmma_CShuffle< Col, Col, Row_Tuple, Row, I8, I8, I8_Tuple, I8, I32, I32, PassThrough, PassThrough, Bilinear, GemmMNKPadding, 256, 128, 128, 4, 16, 16, 16, 4, 2, S<4, 64, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 16, 1, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, 1, 1, 2, S<1, 32, 1, 8>, 16>,
DeviceGemmMultipleD_Wmma_CShuffle< Col, Col, Row_Tuple, Row, I8, I8, I8_Tuple, I8, I32, I32, PassThrough, PassThrough, Bilinear, GemmMNKPadding, 128, 64, 64, 4, 16, 16, 16, 2, 2, S<4, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 16, 1, S<4, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, 1, 1, 2, S<1, 32, 1, 4>, 16>,
DeviceGemmMultipleD_Wmma_CShuffle< Col, Col, Row_Tuple, Row, I8, I8, I8_Tuple, I8, I32, I32, PassThrough, PassThrough, Bilinear, GemmMNKPadding, 64, 32, 32, 4, 16, 16, 16, 1, 2, S<4, 16, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 16, 1, S<4, 16, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, 1, 1, 2, S<1, 32, 1, 2>, 16>,
DeviceGemmMultipleD_Wmma_CShuffle< Col, Col, Row_Tuple, Row, I8, I8, I8_Tuple, I8, I32, I32, PassThrough, PassThrough, Bilinear, GemmMNKPadding, 32, 16, 16, 4, 16, 16, 16, 1, 1, S<4, 8, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 16, 1, S<2, 16, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, 1, 1, 1, S<1, 16, 1, 2>, 8>,
DeviceGemmMultipleD_Wmma_CShuffle< Col, Col, Row_Tuple, Row, I8, I8, I8_Tuple, I8, I32, I32, PassThrough, PassThrough, Bilinear, GemmMNKPadding, 256, 128, 128, 8, 8, 16, 16, 4, 2, S<4, 64, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 8, 1, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, 1, 2, S<1, 32, 1, 8>, 8>,
DeviceGemmMultipleD_Wmma_CShuffle< Col, Col, Row_Tuple, Row, I8, I8, I8_Tuple, I8, I32, I32, PassThrough, PassThrough, Bilinear, GemmMNKPadding, 128, 64, 64, 8, 8, 16, 16, 2, 2, S<4, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 8, 1, S<4, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, 1, 2, S<1, 32, 1, 4>, 8>,
DeviceGemmMultipleD_Wmma_CShuffle< Col, Col, Row_Tuple, Row, I8, I8, I8_Tuple, I8, I32, I32, PassThrough, PassThrough, Bilinear, GemmMNKPadding, 64, 32, 32, 8, 8, 16, 16, 1, 2, S<4, 16, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 8, 1, S<4, 16, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, 1, 2, S<1, 32, 1, 2>, 8>,
DeviceGemmMultipleD_Wmma_CShuffle< Col, Col, Row_Tuple, Row, I8, I8, I8_Tuple, I8, I32, I32, PassThrough, PassThrough, Bilinear, GemmMNKPadding, 32, 16, 16, 8, 8, 16, 16, 1, 1, S<4, 8, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 8, 1, S<2, 16, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, 1, 1, S<1, 16, 1, 2>, 8>,
DeviceGemmMultipleD_Wmma_CShuffle< Col, Col, Row_Tuple, Row, I8, I8, I8_Tuple, I8, I32, I32, PassThrough, PassThrough, Bilinear, GemmMNKPadding, 256, 128, 128, 8, 4, 16, 16, 4, 2, S<4, 64, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 4, 1, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 4, 4, 1, 1, 2, S<1, 32, 1, 8>, 4>,
DeviceGemmMultipleD_Wmma_CShuffle< Col, Col, Row_Tuple, Row, I8, I8, I8_Tuple, I8, I32, I32, PassThrough, PassThrough, Bilinear, GemmMNKPadding, 128, 64, 64, 8, 4, 16, 16, 2, 2, S<4, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 4, 1, S<4, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 4, 4, 1, 1, 2, S<1, 32, 1, 4>, 4>,
DeviceGemmMultipleD_Wmma_CShuffle< Col, Col, Row_Tuple, Row, I8, I8, I8_Tuple, I8, I32, I32, PassThrough, PassThrough, Bilinear, GemmMNKPadding, 64, 32, 32, 8, 4, 16, 16, 1, 2, S<4, 16, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 4, 1, S<4, 16, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 4, 4, 1, 1, 2, S<1, 32, 1, 2>, 4>,
DeviceGemmMultipleD_Wmma_CShuffle< Col, Col, Row_Tuple, Row, I8, I8, I8_Tuple, I8, I32, I32, PassThrough, PassThrough, Bilinear, GemmMNKPadding, 32, 16, 16, 8, 4, 16, 16, 1, 1, S<4, 8, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 4, 1, S<2, 16, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 4, 4, 1, 1, 1, S<1, 16, 1, 2>, 4>
//################################| A| B| Ds| E| AData| BData| AccData| CShuffle| DsData| EData| A| B| CDE| GEMM| Prefetch| Block| MPer| NPer| K0Per| K1| MPer| NPer| MRepeat| NRepeat| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockLds| BBlockTransfer| BBlockTransfer| BBlockTransfer| BlockTransfer| BBlockTransfer| BBlockTransfer| BBlockLds| CShuffle| CShuffle| CBlockTransferClusterLengths| CBlockTransfer|
//################################| Layout| Layout| Layout| Layout| Type| Type| Type| DataType| Type| Type| Elementwise| Elementwise| Elementwise| Specialization| Stage| Size| Block| Block| Block| | WMMA| WMMA| | | ThreadCluster| ThreadCluster| SrcAccessOrder| SrcVectorDim| SrcScalar| DstScalar| AddExtraM| ThreadCluster| ThreadCluster| SrcAccessOrder| SrcVectorDim| SrcScalar| DstScalar| AddExtraN| MXdlPerWave| NXdlPerWave| _MBlock_MWaveMPerXdl| ScalarPerVector|
//################################| | | | | | | | | | | Operation| Operation| Operation| | | | | | | | | | | | Lengths_K0_M_K1| ArrangeOrder| | | PerVector| PerVector_K1| | Lengths_K0_N_K1| ArrangeOrder| | | PerVector| PerVector_K1| | PerShuffle| PerShuffle| _NBlock_NWaveNPerXdl| _NWaveNPerXdl|
//################################| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
DeviceGemmMultipleD_Wmma_CShuffle< Col, Col, Row_Tuple, Row, I8, I8, I32, I32, I8_Tuple, I8, PassThrough, PassThrough, Bilinear, GemmMNKPadding, 1, 256, 128, 128, 64, 16, 16, 16, 4, 2, S<4, 64, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 16, 1, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, 1, 1, 2, S<1, 32, 1, 8>, 16>,
DeviceGemmMultipleD_Wmma_CShuffle< Col, Col, Row_Tuple, Row, I8, I8, I32, I32, I8_Tuple, I8, PassThrough, PassThrough, Bilinear, GemmMNKPadding, 1, 128, 64, 64, 64, 16, 16, 16, 2, 2, S<4, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 16, 1, S<4, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, 1, 1, 2, S<1, 32, 1, 4>, 16>,
DeviceGemmMultipleD_Wmma_CShuffle< Col, Col, Row_Tuple, Row, I8, I8, I32, I32, I8_Tuple, I8, PassThrough, PassThrough, Bilinear, GemmMNKPadding, 1, 64, 32, 32, 64, 16, 16, 16, 1, 2, S<4, 16, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 16, 1, S<4, 16, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, 1, 1, 2, S<1, 32, 1, 2>, 16>,
DeviceGemmMultipleD_Wmma_CShuffle< Col, Col, Row_Tuple, Row, I8, I8, I32, I32, I8_Tuple, I8, PassThrough, PassThrough, Bilinear, GemmMNKPadding, 1, 32, 16, 16, 64, 16, 16, 16, 1, 1, S<4, 8, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 16, 1, S<2, 16, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, 1, 1, 1, S<1, 16, 1, 2>, 8>,
DeviceGemmMultipleD_Wmma_CShuffle< Col, Col, Row_Tuple, Row, I8, I8, I32, I32, I8_Tuple, I8, PassThrough, PassThrough, Bilinear, GemmMNKPadding, 1, 256, 128, 128, 64, 8, 16, 16, 4, 2, S<4, 64, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 8, 1, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, 1, 2, S<1, 32, 1, 8>, 8>,
DeviceGemmMultipleD_Wmma_CShuffle< Col, Col, Row_Tuple, Row, I8, I8, I32, I32, I8_Tuple, I8, PassThrough, PassThrough, Bilinear, GemmMNKPadding, 1, 128, 64, 64, 64, 8, 16, 16, 2, 2, S<4, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 8, 1, S<4, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, 1, 2, S<1, 32, 1, 4>, 8>,
DeviceGemmMultipleD_Wmma_CShuffle< Col, Col, Row_Tuple, Row, I8, I8, I32, I32, I8_Tuple, I8, PassThrough, PassThrough, Bilinear, GemmMNKPadding, 1, 64, 32, 32, 64, 8, 16, 16, 1, 2, S<4, 16, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 8, 1, S<4, 16, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, 1, 2, S<1, 32, 1, 2>, 8>,
DeviceGemmMultipleD_Wmma_CShuffle< Col, Col, Row_Tuple, Row, I8, I8, I32, I32, I8_Tuple, I8, PassThrough, PassThrough, Bilinear, GemmMNKPadding, 1, 32, 16, 16, 64, 8, 16, 16, 1, 1, S<4, 8, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 8, 1, S<2, 16, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, 1, 1, S<1, 16, 1, 2>, 8>,
DeviceGemmMultipleD_Wmma_CShuffle< Col, Col, Row_Tuple, Row, I8, I8, I32, I32, I8_Tuple, I8, PassThrough, PassThrough, Bilinear, GemmMNKPadding, 1, 256, 128, 128, 32, 4, 16, 16, 4, 2, S<4, 64, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 4, 1, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 4, 4, 1, 1, 2, S<1, 32, 1, 8>, 4>,
DeviceGemmMultipleD_Wmma_CShuffle< Col, Col, Row_Tuple, Row, I8, I8, I32, I32, I8_Tuple, I8, PassThrough, PassThrough, Bilinear, GemmMNKPadding, 1, 128, 64, 64, 32, 4, 16, 16, 2, 2, S<4, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 4, 1, S<4, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 4, 4, 1, 1, 2, S<1, 32, 1, 4>, 4>,
DeviceGemmMultipleD_Wmma_CShuffle< Col, Col, Row_Tuple, Row, I8, I8, I32, I32, I8_Tuple, I8, PassThrough, PassThrough, Bilinear, GemmMNKPadding, 1, 64, 32, 32, 32, 4, 16, 16, 1, 2, S<4, 16, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 4, 1, S<4, 16, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 4, 4, 1, 1, 2, S<1, 32, 1, 2>, 4>,
DeviceGemmMultipleD_Wmma_CShuffle< Col, Col, Row_Tuple, Row, I8, I8, I32, I32, I8_Tuple, I8, PassThrough, PassThrough, Bilinear, GemmMNKPadding, 1, 32, 16, 16, 32, 4, 16, 16, 1, 1, S<4, 8, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 4, 1, S<2, 16, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 4, 4, 1, 1, 1, S<1, 16, 1, 2>, 4>
// clang-format on
>;
......
library/src/tensor_operation_instance/gpu/gemm_bilinear/device_gemm_bilinear_wmma_c_shuffle_i8_i8_i8_i8_mk_kn_mn_mn_instance.cpp
View file @ ae3d6cb6
......@@ -36,32 +36,32 @@ static constexpr auto GemmMNKPadding = ck::tensor_operation::device::GemmSpecial
// e[m, n] = bilinear(a[m, k] * b[k, n], d[m, n])
using device_gemm_bilinear_wmma_c_shuffle_i8_i8_i8_i8_mk_kn_mn_mn_instances = std::tuple<
// clang-format off
//################################| A| B| Ds| E| AData| BData| DsData| EData| AccData| CShuffle| A| B| CDE| GEMM| Block| MPer| NPer| K0Per| K1| MPer| NPer| MRepeat| NRepeat| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockLds| BBlockTransfer| BBlockTransfer| BBlockTransfer| BlockTransfer| BBlockTransfer| BBlockTransfer| BBlockLds| CShuffle| CShuffle| CBlockTransferClusterLengths| CBlockTransfer|
//################################| Layout| Layout| Layout| Layout| Type| Type| Type| Type| Type| DataType| Elementwise| Elementwise| Elementwise| Specialization| Size| Block| Block| Block| | WMMA| WMMA| | | ThreadCluster| ThreadCluster| SrcAccessOrder| SrcVectorDim| SrcScalar| DstScalar| AddExtraM| ThreadCluster| ThreadCluster| SrcAccessOrder| SrcVectorDim| SrcScalar| DstScalar| AddExtraN| MXdlPerWave| NXdlPerWave| _MBlock_MWaveMPerXdl| ScalarPerVector|
//################################| | | | | | | | | | | Operation| Operation| Operation| | | | | | | | | | | Lengths_K0_M_K1| ArrangeOrder| | | PerVector| PerVector_K1| | Lengths_K0_N_K1| ArrangeOrder| | | PerVector| PerVector_K1| | PerShuffle| PerShuffle| _NBlock_NWaveNPerXdl| _NWaveNPerXdl|
//################################| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
DeviceGemmMultipleD_Wmma_CShuffle< Row, Row, Row_Tuple, Row, I8, I8, I8_Tuple, I8, I32, I32, PassThrough, PassThrough, Bilinear, GemmDefault, 256, 128, 128, 4, 16, 16, 16, 4, 2, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, 1, S<4, 64, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 16, 1, 1, 2, S<1, 32, 1, 8>, 16>,
DeviceGemmMultipleD_Wmma_CShuffle< Row, Row, Row_Tuple, Row, I8, I8, I8_Tuple, I8, I32, I32, PassThrough, PassThrough, Bilinear, GemmDefault, 128, 64, 64, 4, 16, 16, 16, 2, 2, S<4, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, 1, S<4, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 16, 1, 1, 2, S<1, 32, 1, 4>, 16>,
DeviceGemmMultipleD_Wmma_CShuffle< Row, Row, Row_Tuple, Row, I8, I8, I8_Tuple, I8, I32, I32, PassThrough, PassThrough, Bilinear, GemmDefault, 64, 32, 32, 4, 16, 16, 16, 1, 2, S<4, 16, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, 1, S<4, 16, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 16, 1, 1, 2, S<1, 32, 1, 2>, 16>,
DeviceGemmMultipleD_Wmma_CShuffle< Row, Row, Row_Tuple, Row, I8, I8, I8_Tuple, I8, I32, I32, PassThrough, PassThrough, Bilinear, GemmDefault, 32, 16, 16, 4, 16, 16, 16, 1, 1, S<2, 16, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, 1, S<4, 8, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 16, 1, 1, 1, S<1, 16, 1, 2>, 8>,
//################################| A| B| Ds| E| AData| BData| AccData| CShuffle| DsData| EData| A| B| CDE| GEMM| Prefetch| Block| MPer| NPer| K0Per| K1| MPer| NPer| MRepeat| NRepeat| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockLds| BBlockTransfer| BBlockTransfer| BBlockTransfer| BlockTransfer| BBlockTransfer| BBlockTransfer| BBlockLds| CShuffle| CShuffle| CBlockTransferClusterLengths| CBlockTransfer|
//################################| Layout| Layout| Layout| Layout| Type| Type| Type| DataType| Type| Type| Elementwise| Elementwise| Elementwise| Specialization| Stage| Size| Block| Block| Block| | WMMA| WMMA| | | ThreadCluster| ThreadCluster| SrcAccessOrder| SrcVectorDim| SrcScalar| DstScalar| AddExtraM| ThreadCluster| ThreadCluster| SrcAccessOrder| SrcVectorDim| SrcScalar| DstScalar| AddExtraN| MXdlPerWave| NXdlPerWave| _MBlock_MWaveMPerXdl| ScalarPerVector|
//################################| | | | | | | | | | | Operation| Operation| Operation| | | | | | | | | | | | Lengths_K0_M_K1| ArrangeOrder| | | PerVector| PerVector_K1| | Lengths_K0_N_K1| ArrangeOrder| | | PerVector| PerVector_K1| | PerShuffle| PerShuffle| _NBlock_NWaveNPerXdl| _NWaveNPerXdl|
//################################| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
DeviceGemmMultipleD_Wmma_CShuffle< Row, Row, Row_Tuple, Row, I8, I8, I32, I32, I8_Tuple, I8, PassThrough, PassThrough, Bilinear, GemmDefault, 1, 256, 128, 128, 64, 16, 16, 16, 4, 2, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, 1, S<4, 64, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 16, 1, 1, 2, S<1, 32, 1, 8>, 16>,
DeviceGemmMultipleD_Wmma_CShuffle< Row, Row, Row_Tuple, Row, I8, I8, I32, I32, I8_Tuple, I8, PassThrough, PassThrough, Bilinear, GemmDefault, 1, 128, 64, 64, 64, 16, 16, 16, 2, 2, S<4, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, 1, S<4, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 16, 1, 1, 2, S<1, 32, 1, 4>, 16>,
DeviceGemmMultipleD_Wmma_CShuffle< Row, Row, Row_Tuple, Row, I8, I8, I32, I32, I8_Tuple, I8, PassThrough, PassThrough, Bilinear, GemmDefault, 1, 64, 32, 32, 64, 16, 16, 16, 1, 2, S<4, 16, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, 1, S<4, 16, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 16, 1, 1, 2, S<1, 32, 1, 2>, 16>,
DeviceGemmMultipleD_Wmma_CShuffle< Row, Row, Row_Tuple, Row, I8, I8, I32, I32, I8_Tuple, I8, PassThrough, PassThrough, Bilinear, GemmDefault, 1, 32, 16, 16, 64, 16, 16, 16, 1, 1, S<2, 16, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, 1, S<4, 8, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 16, 1, 1, 1, S<1, 16, 1, 2>, 8>,
// M/N/K padding
//################################| A| B| Ds| E| AData| BData| DsData| EData| AccData| CShuffle| A| B| CDE| GEMM| Block| MPer| NPer| K0Per| K1| MPer| NPer| MRepeat| NRepeat| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockLds| BBlockTransfer| BBlockTransfer| BBlockTransfer| BlockTransfer| BBlockTransfer| BBlockTransfer| BBlockLds| CShuffle| CShuffle| CBlockTransferClusterLengths| CBlockTransfer|
//################################| Layout| Layout| Layout| Layout| Type| Type| Type| Type| Type| DataType| Elementwise| Elementwise| Elementwise| Specialization| Size| Block| Block| Block| | WMMA| WMMA| | | ThreadCluster| ThreadCluster| SrcAccessOrder| SrcVectorDim| SrcScalar| DstScalar| AddExtraM| ThreadCluster| ThreadCluster| SrcAccessOrder| SrcVectorDim| SrcScalar| DstScalar| AddExtraN| MXdlPerWave| NXdlPerWave| _MBlock_MWaveMPerXdl| ScalarPerVector|
//################################| | | | | | | | | | | Operation| Operation| Operation| | | | | | | | | | | Lengths_K0_M_K1| ArrangeOrder| | | PerVector| PerVector_K1| | Lengths_K0_N_K1| ArrangeOrder| | | PerVector| PerVector_K1| | PerShuffle| PerShuffle| _NBlock_NWaveNPerXdl| _NWaveNPerXdl|
//################################| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
DeviceGemmMultipleD_Wmma_CShuffle< Row, Row, Row_Tuple, Row, I8, I8, I8_Tuple, I8, I32, I32, PassThrough, PassThrough, Bilinear, GemmMNKPadding, 256, 128, 128, 4, 16, 16, 16, 4, 2, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, 1, S<4, 64, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 16, 1, 1, 2, S<1, 32, 1, 8>, 16>,
DeviceGemmMultipleD_Wmma_CShuffle< Row, Row, Row_Tuple, Row, I8, I8, I8_Tuple, I8, I32, I32, PassThrough, PassThrough, Bilinear, GemmMNKPadding, 128, 64, 64, 4, 16, 16, 16, 2, 2, S<4, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, 1, S<4, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 16, 1, 1, 2, S<1, 32, 1, 4>, 16>,
DeviceGemmMultipleD_Wmma_CShuffle< Row, Row, Row_Tuple, Row, I8, I8, I8_Tuple, I8, I32, I32, PassThrough, PassThrough, Bilinear, GemmMNKPadding, 64, 32, 32, 4, 16, 16, 16, 1, 2, S<4, 16, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, 1, S<4, 16, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 16, 1, 1, 2, S<1, 32, 1, 2>, 16>,
DeviceGemmMultipleD_Wmma_CShuffle< Row, Row, Row_Tuple, Row, I8, I8, I8_Tuple, I8, I32, I32, PassThrough, PassThrough, Bilinear, GemmMNKPadding, 32, 16, 16, 4, 16, 16, 16, 1, 1, S<2, 16, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, 1, S<4, 8, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 16, 1, 1, 1, S<1, 16, 1, 2>, 8>,
DeviceGemmMultipleD_Wmma_CShuffle< Row, Row, Row_Tuple, Row, I8, I8, I8_Tuple, I8, I32, I32, PassThrough, PassThrough, Bilinear, GemmMNKPadding, 256, 128, 128, 8, 8, 16, 16, 4, 2, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, S<4, 64, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 8, 1, 1, 2, S<1, 32, 1, 8>, 8>,
DeviceGemmMultipleD_Wmma_CShuffle< Row, Row, Row_Tuple, Row, I8, I8, I8_Tuple, I8, I32, I32, PassThrough, PassThrough, Bilinear, GemmMNKPadding, 128, 64, 64, 8, 8, 16, 16, 2, 2, S<4, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, S<4, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 8, 1, 1, 2, S<1, 32, 1, 4>, 8>,
DeviceGemmMultipleD_Wmma_CShuffle< Row, Row, Row_Tuple, Row, I8, I8, I8_Tuple, I8, I32, I32, PassThrough, PassThrough, Bilinear, GemmMNKPadding, 64, 32, 32, 8, 8, 16, 16, 1, 2, S<4, 16, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, S<4, 16, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 8, 1, 1, 2, S<1, 32, 1, 2>, 8>,
DeviceGemmMultipleD_Wmma_CShuffle< Row, Row, Row_Tuple, Row, I8, I8, I8_Tuple, I8, I32, I32, PassThrough, PassThrough, Bilinear, GemmMNKPadding, 32, 16, 16, 8, 8, 16, 16, 1, 1, S<2, 16, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, S<4, 8, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 8, 1, 1, 1, S<1, 16, 1, 2>, 8>,
DeviceGemmMultipleD_Wmma_CShuffle< Row, Row, Row_Tuple, Row, I8, I8, I8_Tuple, I8, I32, I32, PassThrough, PassThrough, Bilinear, GemmMNKPadding, 256, 128, 128, 8, 4, 16, 16, 4, 2, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 4, 4, 1, S<4, 64, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 4, 1, 1, 2, S<1, 32, 1, 8>, 4>,
DeviceGemmMultipleD_Wmma_CShuffle< Row, Row, Row_Tuple, Row, I8, I8, I8_Tuple, I8, I32, I32, PassThrough, PassThrough, Bilinear, GemmMNKPadding, 128, 64, 64, 8, 4, 16, 16, 2, 2, S<4, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 4, 4, 1, S<4, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 4, 1, 1, 2, S<1, 32, 1, 4>, 4>,
DeviceGemmMultipleD_Wmma_CShuffle< Row, Row, Row_Tuple, Row, I8, I8, I8_Tuple, I8, I32, I32, PassThrough, PassThrough, Bilinear, GemmMNKPadding, 64, 32, 32, 8, 4, 16, 16, 1, 2, S<4, 16, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 4, 4, 1, S<4, 16, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 4, 1, 1, 2, S<1, 32, 1, 2>, 4>,
DeviceGemmMultipleD_Wmma_CShuffle< Row, Row, Row_Tuple, Row, I8, I8, I8_Tuple, I8, I32, I32, PassThrough, PassThrough, Bilinear, GemmMNKPadding, 32, 16, 16, 8, 4, 16, 16, 1, 1, S<2, 16, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 4, 4, 1, S<4, 8, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 4, 1, 1, 1, S<1, 16, 1, 2>, 4>
//################################| A| B| Ds| E| AData| BData| AccData| CShuffle| DsData| EData| A| B| CDE| GEMM| Prefetch| Block| MPer| NPer| K0Per| K1| MPer| NPer| MRepeat| NRepeat| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockLds| BBlockTransfer| BBlockTransfer| BBlockTransfer| BlockTransfer| BBlockTransfer| BBlockTransfer| BBlockLds| CShuffle| CShuffle| CBlockTransferClusterLengths| CBlockTransfer|
//################################| Layout| Layout| Layout| Layout| Type| Type| Type| DataType| Type| Type| Elementwise| Elementwise| Elementwise| Specialization| Stage| Size| Block| Block| Block| | WMMA| WMMA| | | ThreadCluster| ThreadCluster| SrcAccessOrder| SrcVectorDim| SrcScalar| DstScalar| AddExtraM| ThreadCluster| ThreadCluster| SrcAccessOrder| SrcVectorDim| SrcScalar| DstScalar| AddExtraN| MXdlPerWave| NXdlPerWave| _MBlock_MWaveMPerXdl| ScalarPerVector|
//################################| | | | | | | | | | | Operation| Operation| Operation| | | | | | | | | | | | Lengths_K0_M_K1| ArrangeOrder| | | PerVector| PerVector_K1| | Lengths_K0_N_K1| ArrangeOrder| | | PerVector| PerVector_K1| | PerShuffle| PerShuffle| _NBlock_NWaveNPerXdl| _NWaveNPerXdl|
//################################| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
DeviceGemmMultipleD_Wmma_CShuffle< Row, Row, Row_Tuple, Row, I8, I8, I32, I32, I8_Tuple, I8, PassThrough, PassThrough, Bilinear, GemmMNKPadding, 1, 256, 128, 128, 64, 16, 16, 16, 4, 2, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, 1, S<4, 64, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 16, 1, 1, 2, S<1, 32, 1, 8>, 16>,
DeviceGemmMultipleD_Wmma_CShuffle< Row, Row, Row_Tuple, Row, I8, I8, I32, I32, I8_Tuple, I8, PassThrough, PassThrough, Bilinear, GemmMNKPadding, 1, 128, 64, 64, 64, 16, 16, 16, 2, 2, S<4, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, 1, S<4, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 16, 1, 1, 2, S<1, 32, 1, 4>, 16>,
DeviceGemmMultipleD_Wmma_CShuffle< Row, Row, Row_Tuple, Row, I8, I8, I32, I32, I8_Tuple, I8, PassThrough, PassThrough, Bilinear, GemmMNKPadding, 1, 64, 32, 32, 64, 16, 16, 16, 1, 2, S<4, 16, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, 1, S<4, 16, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 16, 1, 1, 2, S<1, 32, 1, 2>, 16>,
DeviceGemmMultipleD_Wmma_CShuffle< Row, Row, Row_Tuple, Row, I8, I8, I32, I32, I8_Tuple, I8, PassThrough, PassThrough, Bilinear, GemmMNKPadding, 1, 32, 16, 16, 64, 16, 16, 16, 1, 1, S<2, 16, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, 1, S<4, 8, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 16, 1, 1, 1, S<1, 16, 1, 2>, 8>,
DeviceGemmMultipleD_Wmma_CShuffle< Row, Row, Row_Tuple, Row, I8, I8, I32, I32, I8_Tuple, I8, PassThrough, PassThrough, Bilinear, GemmMNKPadding, 1, 256, 128, 128, 64, 8, 16, 16, 4, 2, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, S<4, 64, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 8, 1, 1, 2, S<1, 32, 1, 8>, 8>,
DeviceGemmMultipleD_Wmma_CShuffle< Row, Row, Row_Tuple, Row, I8, I8, I32, I32, I8_Tuple, I8, PassThrough, PassThrough, Bilinear, GemmMNKPadding, 1, 128, 64, 64, 64, 8, 16, 16, 2, 2, S<4, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, S<4, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 8, 1, 1, 2, S<1, 32, 1, 4>, 8>,
DeviceGemmMultipleD_Wmma_CShuffle< Row, Row, Row_Tuple, Row, I8, I8, I32, I32, I8_Tuple, I8, PassThrough, PassThrough, Bilinear, GemmMNKPadding, 1, 64, 32, 32, 64, 8, 16, 16, 1, 2, S<4, 16, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, S<4, 16, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 8, 1, 1, 2, S<1, 32, 1, 2>, 8>,
DeviceGemmMultipleD_Wmma_CShuffle< Row, Row, Row_Tuple, Row, I8, I8, I32, I32, I8_Tuple, I8, PassThrough, PassThrough, Bilinear, GemmMNKPadding, 1, 32, 16, 16, 64, 8, 16, 16, 1, 1, S<2, 16, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, S<4, 8, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 8, 1, 1, 1, S<1, 16, 1, 2>, 8>,
DeviceGemmMultipleD_Wmma_CShuffle< Row, Row, Row_Tuple, Row, I8, I8, I32, I32, I8_Tuple, I8, PassThrough, PassThrough, Bilinear, GemmMNKPadding, 1, 256, 128, 128, 32, 4, 16, 16, 4, 2, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 4, 4, 1, S<4, 64, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 4, 1, 1, 2, S<1, 32, 1, 8>, 4>,
DeviceGemmMultipleD_Wmma_CShuffle< Row, Row, Row_Tuple, Row, I8, I8, I32, I32, I8_Tuple, I8, PassThrough, PassThrough, Bilinear, GemmMNKPadding, 1, 128, 64, 64, 32, 4, 16, 16, 2, 2, S<4, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 4, 4, 1, S<4, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 4, 1, 1, 2, S<1, 32, 1, 4>, 4>,
DeviceGemmMultipleD_Wmma_CShuffle< Row, Row, Row_Tuple, Row, I8, I8, I32, I32, I8_Tuple, I8, PassThrough, PassThrough, Bilinear, GemmMNKPadding, 1, 64, 32, 32, 32, 4, 16, 16, 1, 2, S<4, 16, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 4, 4, 1, S<4, 16, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 4, 1, 1, 2, S<1, 32, 1, 2>, 4>,
DeviceGemmMultipleD_Wmma_CShuffle< Row, Row, Row_Tuple, Row, I8, I8, I32, I32, I8_Tuple, I8, PassThrough, PassThrough, Bilinear, GemmMNKPadding, 1, 32, 16, 16, 32, 4, 16, 16, 1, 1, S<2, 16, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 4, 4, 1, S<4, 8, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 4, 1, 1, 1, S<1, 16, 1, 2>, 4>
// clang-format on
>;
......
library/src/tensor_operation_instance/gpu/gemm_bilinear/device_gemm_bilinear_wmma_c_shuffle_i8_i8_i8_i8_mk_nk_mn_mn_instance.cpp
View file @ ae3d6cb6
......@@ -38,56 +38,56 @@ using device_gemm_bilinear_wmma_c_shuffle_i8_i8_i8_i8_mk_nk_mn_mn_instances = st
// clang-format off
// no padding
// N % 16 == 0 && K % 16 == 0
//################################| A| B| Ds| E| AData| BData| DsData| EData| AccData| CShuffle| A| B| CDE| GEMM| Block| MPer| NPer| K0Per| K1| MPer| NPer| MRepeat| NRepeat| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockLds| BBlockTransfer| BBlockTransfer| BBlockTransfer| BlockTransfer| BBlockTransfer| BBlockTransfer| BBlockLds| CShuffle| CShuffle| CBlockTransferClusterLengths| CBlockTransfer|
//################################| Layout| Layout| Layout| Layout| Type| Type| Type| Type| Type| DataType| Elementwise| Elementwise| Elementwise| Specialization| Size| Block| Block| Block| | WMMA| WMMA| | | ThreadCluster| ThreadCluster| SrcAccessOrder| SrcVectorDim| SrcScalar| DstScalar| AddExtraM| ThreadCluster| ThreadCluster| SrcAccessOrder| SrcVectorDim| SrcScalar| DstScalar| AddExtraN| MXdlPerWave| NXdlPerWave| _MBlock_MWaveMPerXdl| ScalarPerVector|
//################################| | | | | | | | | | | Operation| Operation| Operation| | | | | | | | | | | Lengths_K0_M_K1| ArrangeOrder| | | PerVector| PerVector_K1| | Lengths_K0_N_K1| ArrangeOrder| | | PerVector| PerVector_K1| | PerShuffle| PerShuffle| _NBlock_NWaveNPerXdl| _NWaveNPerXdl|
//################################| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
DeviceGemmMultipleD_Wmma_CShuffle< Row, Col, Row_Tuple, Row, I8, I8, I8_Tuple, I8, I32, I32, PassThrough, PassThrough, Bilinear, GemmDefault, 256, 128, 128, 4, 16, 16, 16, 4, 2, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, 1, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, 1, 1, 2, S<1, 32, 1, 8>, 16>,
DeviceGemmMultipleD_Wmma_CShuffle< Row, Col, Row_Tuple, Row, I8, I8, I8_Tuple, I8, I32, I32, PassThrough, PassThrough, Bilinear, GemmDefault, 128, 64, 64, 4, 16, 16, 16, 2, 2, S<4, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, 1, S<4, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, 1, 1, 2, S<1, 32, 1, 4>, 16>,
DeviceGemmMultipleD_Wmma_CShuffle< Row, Col, Row_Tuple, Row, I8, I8, I8_Tuple, I8, I32, I32, PassThrough, PassThrough, Bilinear, GemmDefault, 64, 32, 32, 4, 16, 16, 16, 1, 2, S<4, 16, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, 1, S<4, 16, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, 1, 1, 2, S<1, 32, 1, 2>, 16>,
DeviceGemmMultipleD_Wmma_CShuffle< Row, Col, Row_Tuple, Row, I8, I8, I8_Tuple, I8, I32, I32, PassThrough, PassThrough, Bilinear, GemmDefault, 32, 16, 16, 4, 16, 16, 16, 1, 1, S<2, 16, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, 1, S<2, 16, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, 1, 1, 1, S<1, 16, 1, 2>, 8>,
//################################| A| B| Ds| E| AData| BData| AccData| CShuffle| DsData| EData| A| B| CDE| GEMM| Prefetch| Block| MPer| NPer| K0Per| K1| MPer| NPer| MRepeat| NRepeat| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockLds| BBlockTransfer| BBlockTransfer| BBlockTransfer| BlockTransfer| BBlockTransfer| BBlockTransfer| BBlockLds| CShuffle| CShuffle| CBlockTransferClusterLengths| CBlockTransfer|
//################################| Layout| Layout| Layout| Layout| Type| Type| Type| DataType| Type| Type| Elementwise| Elementwise| Elementwise| Specialization| Stage| Size| Block| Block| Block| | WMMA| WMMA| | | ThreadCluster| ThreadCluster| SrcAccessOrder| SrcVectorDim| SrcScalar| DstScalar| AddExtraM| ThreadCluster| ThreadCluster| SrcAccessOrder| SrcVectorDim| SrcScalar| DstScalar| AddExtraN| MXdlPerWave| NXdlPerWave| _MBlock_MWaveMPerXdl| ScalarPerVector|
//################################| | | | | | | | | | | Operation| Operation| Operation| | | | | | | | | | | | Lengths_K0_M_K1| ArrangeOrder| | | PerVector| PerVector_K1| | Lengths_K0_N_K1| ArrangeOrder| | | PerVector| PerVector_K1| | PerShuffle| PerShuffle| _NBlock_NWaveNPerXdl| _NWaveNPerXdl|
//################################| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
DeviceGemmMultipleD_Wmma_CShuffle< Row, Col, Row_Tuple, Row, I8, I8, I32, I32, I8_Tuple, I8, PassThrough, PassThrough, Bilinear, GemmDefault, 1, 256, 128, 128, 64, 16, 16, 16, 4, 2, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, 1, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, 1, 1, 2, S<1, 32, 1, 8>, 16>,
DeviceGemmMultipleD_Wmma_CShuffle< Row, Col, Row_Tuple, Row, I8, I8, I32, I32, I8_Tuple, I8, PassThrough, PassThrough, Bilinear, GemmDefault, 1, 128, 64, 64, 64, 16, 16, 16, 2, 2, S<4, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, 1, S<4, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, 1, 1, 2, S<1, 32, 1, 4>, 16>,
DeviceGemmMultipleD_Wmma_CShuffle< Row, Col, Row_Tuple, Row, I8, I8, I32, I32, I8_Tuple, I8, PassThrough, PassThrough, Bilinear, GemmDefault, 1, 64, 32, 32, 64, 16, 16, 16, 1, 2, S<4, 16, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, 1, S<4, 16, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, 1, 1, 2, S<1, 32, 1, 2>, 16>,
DeviceGemmMultipleD_Wmma_CShuffle< Row, Col, Row_Tuple, Row, I8, I8, I32, I32, I8_Tuple, I8, PassThrough, PassThrough, Bilinear, GemmDefault, 1, 32, 16, 16, 64, 16, 16, 16, 1, 1, S<2, 16, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, 1, S<2, 16, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, 1, 1, 1, S<1, 16, 1, 2>, 8>,
// M/N/K padding
// N % 16 == 0 && K % 16 == 0
//################################| A| B| Ds| E| AData| BData| DsData| EData| AccData| CShuffle| A| B| CDE| GEMM| Block| MPer| NPer| K0Per| K1| MPer| NPer| MRepeat| NRepeat| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockLds| BBlockTransfer| BBlockTransfer| BBlockTransfer| BlockTransfer| BBlockTransfer| BBlockTransfer| BBlockLds| CShuffle| CShuffle| CBlockTransferClusterLengths| CBlockTransfer|
//################################| Layout| Layout| Layout| Layout| Type| Type| Type| Type| Type| DataType| Elementwise| Elementwise| Elementwise| Specialization| Size| Block| Block| Block| | WMMA| WMMA| | | ThreadCluster| ThreadCluster| SrcAccessOrder| SrcVectorDim| SrcScalar| DstScalar| AddExtraM| ThreadCluster| ThreadCluster| SrcAccessOrder| SrcVectorDim| SrcScalar| DstScalar| AddExtraN| MXdlPerWave| NXdlPerWave| _MBlock_MWaveMPerXdl| ScalarPerVector|
//################################| | | | | | | | | | | Operation| Operation| Operation| | | | | | | | | | | Lengths_K0_M_K1| ArrangeOrder| | | PerVector| PerVector_K1| | Lengths_K0_N_K1| ArrangeOrder| | | PerVector| PerVector_K1| | PerShuffle| PerShuffle| _NBlock_NWaveNPerXdl| _NWaveNPerXdl|
//################################| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
DeviceGemmMultipleD_Wmma_CShuffle< Row, Col, Row_Tuple, Row, I8, I8, I8_Tuple, I8, I32, I32, PassThrough, PassThrough, Bilinear, GemmMNKPadding, 256, 128, 128, 4, 16, 16, 16, 4, 2, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, 1, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, 1, 1, 2, S<1, 32, 1, 8>, 16>,
DeviceGemmMultipleD_Wmma_CShuffle< Row, Col, Row_Tuple, Row, I8, I8, I8_Tuple, I8, I32, I32, PassThrough, PassThrough, Bilinear, GemmMNKPadding, 128, 64, 64, 4, 16, 16, 16, 2, 2, S<4, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, 1, S<4, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, 1, 1, 2, S<1, 32, 1, 4>, 16>,
DeviceGemmMultipleD_Wmma_CShuffle< Row, Col, Row_Tuple, Row, I8, I8, I8_Tuple, I8, I32, I32, PassThrough, PassThrough, Bilinear, GemmMNKPadding, 64, 32, 32, 4, 16, 16, 16, 1, 2, S<4, 16, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, 1, S<4, 16, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, 1, 1, 2, S<1, 32, 1, 2>, 16>,
DeviceGemmMultipleD_Wmma_CShuffle< Row, Col, Row_Tuple, Row, I8, I8, I8_Tuple, I8, I32, I32, PassThrough, PassThrough, Bilinear, GemmMNKPadding, 32, 16, 16, 4, 16, 16, 16, 1, 1, S<2, 16, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, 1, S<2, 16, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, 1, 1, 1, S<1, 16, 1, 2>, 8>,
//################################| A| B| Ds| E| AData| BData| AccData| CShuffle| DsData| EData| A| B| CDE| GEMM| Prefetch| Block| MPer| NPer| K0Per| K1| MPer| NPer| MRepeat| NRepeat| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockLds| BBlockTransfer| BBlockTransfer| BBlockTransfer| BlockTransfer| BBlockTransfer| BBlockTransfer| BBlockLds| CShuffle| CShuffle| CBlockTransferClusterLengths| CBlockTransfer|
//################################| Layout| Layout| Layout| Layout| Type| Type| Type| DataType| Type| Type| Elementwise| Elementwise| Elementwise| Specialization| Stage| Size| Block| Block| Block| | WMMA| WMMA| | | ThreadCluster| ThreadCluster| SrcAccessOrder| SrcVectorDim| SrcScalar| DstScalar| AddExtraM| ThreadCluster| ThreadCluster| SrcAccessOrder| SrcVectorDim| SrcScalar| DstScalar| AddExtraN| MXdlPerWave| NXdlPerWave| _MBlock_MWaveMPerXdl| ScalarPerVector|
//################################| | | | | | | | | | | Operation| Operation| Operation| | | | | | | | | | | | Lengths_K0_M_K1| ArrangeOrder| | | PerVector| PerVector_K1| | Lengths_K0_N_K1| ArrangeOrder| | | PerVector| PerVector_K1| | PerShuffle| PerShuffle| _NBlock_NWaveNPerXdl| _NWaveNPerXdl|
//################################| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
DeviceGemmMultipleD_Wmma_CShuffle< Row, Col, Row_Tuple, Row, I8, I8, I32, I32, I8_Tuple, I8, PassThrough, PassThrough, Bilinear, GemmMNKPadding, 1, 256, 128, 128, 64, 16, 16, 16, 4, 2, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, 1, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, 1, 1, 2, S<1, 32, 1, 8>, 16>,
DeviceGemmMultipleD_Wmma_CShuffle< Row, Col, Row_Tuple, Row, I8, I8, I32, I32, I8_Tuple, I8, PassThrough, PassThrough, Bilinear, GemmMNKPadding, 1, 128, 64, 64, 64, 16, 16, 16, 2, 2, S<4, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, 1, S<4, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, 1, 1, 2, S<1, 32, 1, 4>, 16>,
DeviceGemmMultipleD_Wmma_CShuffle< Row, Col, Row_Tuple, Row, I8, I8, I32, I32, I8_Tuple, I8, PassThrough, PassThrough, Bilinear, GemmMNKPadding, 1, 64, 32, 32, 64, 16, 16, 16, 1, 2, S<4, 16, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, 1, S<4, 16, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, 1, 1, 2, S<1, 32, 1, 2>, 16>,
DeviceGemmMultipleD_Wmma_CShuffle< Row, Col, Row_Tuple, Row, I8, I8, I32, I32, I8_Tuple, I8, PassThrough, PassThrough, Bilinear, GemmMNKPadding, 1, 32, 16, 16, 64, 16, 16, 16, 1, 1, S<2, 16, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, 1, S<2, 16, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, 1, 1, 1, S<1, 16, 1, 2>, 8>,
// M/N/K padding
// N % 8 == 0 && K % 8 == 0
//################################| A| B| Ds| E| AData| BData| DsData| EData| AccData| CShuffle| A| B| CDE| GEMM| Block| MPer| NPer| K0Per| K1| MPer| NPer| MRepeat| NRepeat| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockLds| BBlockTransfer| BBlockTransfer| BBlockTransfer| BlockTransfer| BBlockTransfer| BBlockTransfer| BBlockLds| CShuffle| CShuffle| CBlockTransferClusterLengths| CBlockTransfer|
//################################| Layout| Layout| Layout| Layout| Type| Type| Type| Type| Type| DataType| Elementwise| Elementwise| Elementwise| Specialization| Size| Block| Block| Block| | WMMA| WMMA| | | ThreadCluster| ThreadCluster| SrcAccessOrder| SrcVectorDim| SrcScalar| DstScalar| AddExtraM| ThreadCluster| ThreadCluster| SrcAccessOrder| SrcVectorDim| SrcScalar| DstScalar| AddExtraN| MXdlPerWave| NXdlPerWave| _MBlock_MWaveMPerXdl| ScalarPerVector|
//################################| | | | | | | | | | | Operation| Operation| Operation| | | | | | | | | | | Lengths_K0_M_K1| ArrangeOrder| | | PerVector| PerVector_K1| | Lengths_K0_N_K1| ArrangeOrder| | | PerVector| PerVector_K1| | PerShuffle| PerShuffle| _NBlock_NWaveNPerXdl| _NWaveNPerXdl|
//################################| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
DeviceGemmMultipleD_Wmma_CShuffle< Row, Col, Row_Tuple, Row, I8, I8, I8_Tuple, I8, I32, I32, PassThrough, PassThrough, Bilinear, GemmMNKPadding, 256, 128, 128, 8, 8, 16, 16, 4, 2, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, 1, 2, S<1, 32, 1, 8>, 8>,
DeviceGemmMultipleD_Wmma_CShuffle< Row, Col, Row_Tuple, Row, I8, I8, I8_Tuple, I8, I32, I32, PassThrough, PassThrough, Bilinear, GemmMNKPadding, 128, 64, 64, 8, 8, 16, 16, 2, 2, S<4, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, S<4, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, 1, 2, S<1, 32, 1, 4>, 8>,
DeviceGemmMultipleD_Wmma_CShuffle< Row, Col, Row_Tuple, Row, I8, I8, I8_Tuple, I8, I32, I32, PassThrough, PassThrough, Bilinear, GemmMNKPadding, 64, 32, 32, 8, 8, 16, 16, 1, 2, S<4, 16, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, S<4, 16, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, 1, 2, S<1, 32, 1, 2>, 8>,
DeviceGemmMultipleD_Wmma_CShuffle< Row, Col, Row_Tuple, Row, I8, I8, I8_Tuple, I8, I32, I32, PassThrough, PassThrough, Bilinear, GemmMNKPadding, 32, 16, 16, 8, 8, 16, 16, 1, 1, S<2, 16, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, S<2, 16, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, 1, 1, S<1, 16, 1, 2>, 8>,
//################################| A| B| Ds| E| AData| BData| AccData| CShuffle| DsData| EData| A| B| CDE| GEMM| Prefetch| Block| MPer| NPer| K0Per| K1| MPer| NPer| MRepeat| NRepeat| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockLds| BBlockTransfer| BBlockTransfer| BBlockTransfer| BlockTransfer| BBlockTransfer| BBlockTransfer| BBlockLds| CShuffle| CShuffle| CBlockTransferClusterLengths| CBlockTransfer|
//################################| Layout| Layout| Layout| Layout| Type| Type| Type| DataType| Type| Type| Elementwise| Elementwise| Elementwise| Specialization| Stage| Size| Block| Block| Block| | WMMA| WMMA| | | ThreadCluster| ThreadCluster| SrcAccessOrder| SrcVectorDim| SrcScalar| DstScalar| AddExtraM| ThreadCluster| ThreadCluster| SrcAccessOrder| SrcVectorDim| SrcScalar| DstScalar| AddExtraN| MXdlPerWave| NXdlPerWave| _MBlock_MWaveMPerXdl| ScalarPerVector|
//################################| | | | | | | | | | | Operation| Operation| Operation| | | | | | | | | | | | Lengths_K0_M_K1| ArrangeOrder| | | PerVector| PerVector_K1| | Lengths_K0_N_K1| ArrangeOrder| | | PerVector| PerVector_K1| | PerShuffle| PerShuffle| _NBlock_NWaveNPerXdl| _NWaveNPerXdl|
//################################| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
DeviceGemmMultipleD_Wmma_CShuffle< Row, Col, Row_Tuple, Row, I8, I8, I32, I32, I8_Tuple, I8, PassThrough, PassThrough, Bilinear, GemmMNKPadding, 1, 256, 128, 128, 64, 8, 16, 16, 4, 2, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, 1, 2, S<1, 32, 1, 8>, 8>,
DeviceGemmMultipleD_Wmma_CShuffle< Row, Col, Row_Tuple, Row, I8, I8, I32, I32, I8_Tuple, I8, PassThrough, PassThrough, Bilinear, GemmMNKPadding, 1, 128, 64, 64, 64, 8, 16, 16, 2, 2, S<4, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, S<4, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, 1, 2, S<1, 32, 1, 4>, 8>,
DeviceGemmMultipleD_Wmma_CShuffle< Row, Col, Row_Tuple, Row, I8, I8, I32, I32, I8_Tuple, I8, PassThrough, PassThrough, Bilinear, GemmMNKPadding, 1, 64, 32, 32, 64, 8, 16, 16, 1, 2, S<4, 16, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, S<4, 16, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, 1, 2, S<1, 32, 1, 2>, 8>,
DeviceGemmMultipleD_Wmma_CShuffle< Row, Col, Row_Tuple, Row, I8, I8, I32, I32, I8_Tuple, I8, PassThrough, PassThrough, Bilinear, GemmMNKPadding, 1, 32, 16, 16, 64, 8, 16, 16, 1, 1, S<2, 16, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, S<2, 16, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, 1, 1, S<1, 16, 1, 2>, 8>,
// M/N/K padding
// N % 8 == 0 && K % 8 == 0
//################################| A| B| Ds| E| AData| BData| DsData| EData| AccData| CShuffle| A| B| CDE| GEMM| Block| MPer| NPer| K0Per| K1| MPer| NPer| MRepeat| NRepeat| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockLds| BBlockTransfer| BBlockTransfer| BBlockTransfer| BlockTransfer| BBlockTransfer| BBlockTransfer| BBlockLds| CShuffle| CShuffle| CBlockTransferClusterLengths| CBlockTransfer|
//################################| Layout| Layout| Layout| Layout| Type| Type| Type| Type| Type| DataType| Elementwise| Elementwise| Elementwise| Specialization| Size| Block| Block| Block| | WMMA| WMMA| | | ThreadCluster| ThreadCluster| SrcAccessOrder| SrcVectorDim| SrcScalar| DstScalar| AddExtraM| ThreadCluster| ThreadCluster| SrcAccessOrder| SrcVectorDim| SrcScalar| DstScalar| AddExtraN| MXdlPerWave| NXdlPerWave| _MBlock_MWaveMPerXdl| ScalarPerVector|
//################################| | | | | | | | | | | Operation| Operation| Operation| | | | | | | | | | | Lengths_K0_M_K1| ArrangeOrder| | | PerVector| PerVector_K1| | Lengths_K0_N_K1| ArrangeOrder| | | PerVector| PerVector_K1| | PerShuffle| PerShuffle| _NBlock_NWaveNPerXdl| _NWaveNPerXdl|
//################################| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
DeviceGemmMultipleD_Wmma_CShuffle< Row, Col, Row_Tuple, Row, I8, I8, I8_Tuple, I8, I32, I32, PassThrough, PassThrough, Bilinear, GemmMNKPadding, 256, 128, 128, 8, 4, 16, 16, 4, 2, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 4, 4, 1, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 4, 4, 1, 1, 2, S<1, 32, 1, 8>, 4>,
DeviceGemmMultipleD_Wmma_CShuffle< Row, Col, Row_Tuple, Row, I8, I8, I8_Tuple, I8, I32, I32, PassThrough, PassThrough, Bilinear, GemmMNKPadding, 128, 64, 64, 8, 4, 16, 16, 2, 2, S<4, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 4, 4, 1, S<4, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 4, 4, 1, 1, 2, S<1, 32, 1, 4>, 4>,
DeviceGemmMultipleD_Wmma_CShuffle< Row, Col, Row_Tuple, Row, I8, I8, I8_Tuple, I8, I32, I32, PassThrough, PassThrough, Bilinear, GemmMNKPadding, 64, 32, 32, 8, 4, 16, 16, 1, 2, S<4, 16, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 4, 4, 1, S<4, 16, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 4, 4, 1, 1, 2, S<1, 32, 1, 2>, 4>,
DeviceGemmMultipleD_Wmma_CShuffle< Row, Col, Row_Tuple, Row, I8, I8, I8_Tuple, I8, I32, I32, PassThrough, PassThrough, Bilinear, GemmMNKPadding, 32, 16, 16, 8, 4, 16, 16, 1, 1, S<2, 16, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 4, 4, 1, S<2, 16, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 4, 4, 1, 1, 1, S<1, 16, 1, 2>, 4>,
//################################| A| B| Ds| E| AData| BData| AccData| CShuffle| DsData| EData| A| B| CDE| GEMM| Prefetch| Block| MPer| NPer| K0Per| K1| MPer| NPer| MRepeat| NRepeat| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockLds| BBlockTransfer| BBlockTransfer| BBlockTransfer| BlockTransfer| BBlockTransfer| BBlockTransfer| BBlockLds| CShuffle| CShuffle| CBlockTransferClusterLengths| CBlockTransfer|
//################################| Layout| Layout| Layout| Layout| Type| Type| Type| DataType| Type| Type| Elementwise| Elementwise| Elementwise| Specialization| Stage| Size| Block| Block| Block| | WMMA| WMMA| | | ThreadCluster| ThreadCluster| SrcAccessOrder| SrcVectorDim| SrcScalar| DstScalar| AddExtraM| ThreadCluster| ThreadCluster| SrcAccessOrder| SrcVectorDim| SrcScalar| DstScalar| AddExtraN| MXdlPerWave| NXdlPerWave| _MBlock_MWaveMPerXdl| ScalarPerVector|
//################################| | | | | | | | | | | Operation| Operation| Operation| | | | | | | | | | | | Lengths_K0_M_K1| ArrangeOrder| | | PerVector| PerVector_K1| | Lengths_K0_N_K1| ArrangeOrder| | | PerVector| PerVector_K1| | PerShuffle| PerShuffle| _NBlock_NWaveNPerXdl| _NWaveNPerXdl|
//################################| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
DeviceGemmMultipleD_Wmma_CShuffle< Row, Col, Row_Tuple, Row, I8, I8, I32, I32, I8_Tuple, I8, PassThrough, PassThrough, Bilinear, GemmMNKPadding, 1, 256, 128, 128, 32, 4, 16, 16, 4, 2, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 4, 4, 1, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 4, 4, 1, 1, 2, S<1, 32, 1, 8>, 4>,
DeviceGemmMultipleD_Wmma_CShuffle< Row, Col, Row_Tuple, Row, I8, I8, I32, I32, I8_Tuple, I8, PassThrough, PassThrough, Bilinear, GemmMNKPadding, 1, 128, 64, 64, 32, 4, 16, 16, 2, 2, S<4, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 4, 4, 1, S<4, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 4, 4, 1, 1, 2, S<1, 32, 1, 4>, 4>,
DeviceGemmMultipleD_Wmma_CShuffle< Row, Col, Row_Tuple, Row, I8, I8, I32, I32, I8_Tuple, I8, PassThrough, PassThrough, Bilinear, GemmMNKPadding, 1, 64, 32, 32, 32, 4, 16, 16, 1, 2, S<4, 16, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 4, 4, 1, S<4, 16, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 4, 4, 1, 1, 2, S<1, 32, 1, 2>, 4>,
DeviceGemmMultipleD_Wmma_CShuffle< Row, Col, Row_Tuple, Row, I8, I8, I32, I32, I8_Tuple, I8, PassThrough, PassThrough, Bilinear, GemmMNKPadding, 1, 32, 16, 16, 32, 4, 16, 16, 1, 1, S<2, 16, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 4, 4, 1, S<2, 16, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 4, 4, 1, 1, 1, S<1, 16, 1, 2>, 4>,
// M/N/K padding
// N % 1 == 0 && K % 8 == 0
//################################| A| B| Ds| E| AData| BData| DsData| EData| AccData| CShuffle| A| B| CDE| GEMM| Block| MPer| NPer| K0Per| K1| MPer| NPer| MRepeat| NRepeat| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockLds| BBlockTransfer| BBlockTransfer| BBlockTransfer| BlockTransfer| BBlockTransfer| BBlockTransfer| BBlockLds| CShuffle| CShuffle| CBlockTransferClusterLengths| CBlockTransfer|
//################################| Layout| Layout| Layout| Layout| Type| Type| Type| Type| Type| DataType| Elementwise| Elementwise| Elementwise| Specialization| Size| Block| Block| Block| | WMMA| WMMA| | | ThreadCluster| ThreadCluster| SrcAccessOrder| SrcVectorDim| SrcScalar| DstScalar| AddExtraM| ThreadCluster| ThreadCluster| SrcAccessOrder| SrcVectorDim| SrcScalar| DstScalar| AddExtraN| MXdlPerWave| NXdlPerWave| _MBlock_MWaveMPerXdl| ScalarPerVector|
//################################| | | | | | | | | | | Operation| Operation| Operation| | | | | | | | | | | Lengths_K0_M_K1| ArrangeOrder| | | PerVector| PerVector_K1| | Lengths_K0_N_K1| ArrangeOrder| | | PerVector| PerVector_K1| | PerShuffle| PerShuffle| _NBlock_NWaveNPerXdl| _NWaveNPerXdl|
//################################| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
DeviceGemmMultipleD_Wmma_CShuffle< Row, Col, Row_Tuple, Row, I8, I8, I8_Tuple, I8, I32, I32, PassThrough, PassThrough, Bilinear, GemmMNKPadding, 256, 128, 128, 8, 8, 16, 16, 4, 2, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, 1, 2, S<1, 32, 1, 8>, 1>,
DeviceGemmMultipleD_Wmma_CShuffle< Row, Col, Row_Tuple, Row, I8, I8, I8_Tuple, I8, I32, I32, PassThrough, PassThrough, Bilinear, GemmMNKPadding, 128, 64, 64, 8, 8, 16, 16, 2, 2, S<4, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, S<4, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, 1, 2, S<1, 32, 1, 4>, 1>,
DeviceGemmMultipleD_Wmma_CShuffle< Row, Col, Row_Tuple, Row, I8, I8, I8_Tuple, I8, I32, I32, PassThrough, PassThrough, Bilinear, GemmMNKPadding, 64, 32, 32, 8, 8, 16, 16, 1, 2, S<4, 16, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, S<4, 16, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, 1, 2, S<1, 32, 1, 2>, 1>,
DeviceGemmMultipleD_Wmma_CShuffle< Row, Col, Row_Tuple, Row, I8, I8, I8_Tuple, I8, I32, I32, PassThrough, PassThrough, Bilinear, GemmMNKPadding, 32, 16, 16, 8, 8, 16, 16, 1, 1, S<2, 16, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, S<2, 16, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, 1, 1, S<1, 16, 1, 2>, 1>
//################################| A| B| Ds| E| AData| BData| AccData| CShuffle| DsData| EData| A| B| CDE| GEMM| Prefetch| Block| MPer| NPer| K0Per| K1| MPer| NPer| MRepeat| NRepeat| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockLds| BBlockTransfer| BBlockTransfer| BBlockTransfer| BlockTransfer| BBlockTransfer| BBlockTransfer| BBlockLds| CShuffle| CShuffle| CBlockTransferClusterLengths| CBlockTransfer|
//################################| Layout| Layout| Layout| Layout| Type| Type| Type| DataType| Type| Type| Elementwise| Elementwise| Elementwise| Specialization| Stage| Size| Block| Block| Block| | WMMA| WMMA| | | ThreadCluster| ThreadCluster| SrcAccessOrder| SrcVectorDim| SrcScalar| DstScalar| AddExtraM| ThreadCluster| ThreadCluster| SrcAccessOrder| SrcVectorDim| SrcScalar| DstScalar| AddExtraN| MXdlPerWave| NXdlPerWave| _MBlock_MWaveMPerXdl| ScalarPerVector|
//################################| | | | | | | | | | | Operation| Operation| Operation| | | | | | | | | | | | Lengths_K0_M_K1| ArrangeOrder| | | PerVector| PerVector_K1| | Lengths_K0_N_K1| ArrangeOrder| | | PerVector| PerVector_K1| | PerShuffle| PerShuffle| _NBlock_NWaveNPerXdl| _NWaveNPerXdl|
//################################| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
DeviceGemmMultipleD_Wmma_CShuffle< Row, Col, Row_Tuple, Row, I8, I8, I32, I32, I8_Tuple, I8, PassThrough, PassThrough, Bilinear, GemmMNKPadding, 1, 256, 128, 128, 64, 8, 16, 16, 4, 2, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, 1, 2, S<1, 32, 1, 8>, 1>,
DeviceGemmMultipleD_Wmma_CShuffle< Row, Col, Row_Tuple, Row, I8, I8, I32, I32, I8_Tuple, I8, PassThrough, PassThrough, Bilinear, GemmMNKPadding, 1, 128, 64, 64, 64, 8, 16, 16, 2, 2, S<4, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, S<4, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, 1, 2, S<1, 32, 1, 4>, 1>,
DeviceGemmMultipleD_Wmma_CShuffle< Row, Col, Row_Tuple, Row, I8, I8, I32, I32, I8_Tuple, I8, PassThrough, PassThrough, Bilinear, GemmMNKPadding, 1, 64, 32, 32, 64, 8, 16, 16, 1, 2, S<4, 16, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, S<4, 16, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, 1, 2, S<1, 32, 1, 2>, 1>,
DeviceGemmMultipleD_Wmma_CShuffle< Row, Col, Row_Tuple, Row, I8, I8, I32, I32, I8_Tuple, I8, PassThrough, PassThrough, Bilinear, GemmMNKPadding, 1, 32, 16, 16, 64, 8, 16, 16, 1, 1, S<2, 16, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, S<2, 16, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, 1, 1, S<1, 16, 1, 2>, 1>
// clang-format on
>;
......
library/src/tensor_operation_instance/gpu/gemm_splitk/CMakeLists.txt
View file @ ae3d6cb6
set(GEMM_SPLITK_INSTANCES)
list(APPEND GEMM_SPLITK_INSTANCES device_gemm_xdl_splitk_f32_f32_f32_mk_kn_mn_instance.cpp
device_gemm_xdl_splitk_f32_f32_f32_mk_nk_mn_instance.cpp
device_gemm_xdl_splitk_f32_f32_f32_km_kn_mn_instance.cpp
device_gemm_xdl_splitk_f32_f32_f32_km_nk_mn_instance.cpp
device_gemm_xdl_splitk_f16_f16_f16_mk_kn_mn_v1_instance.cpp
device_gemm_xdl_splitk_f16_f16_f16_mk_kn_mn_v1_irregular_instance.cpp
device_gemm_xdl_splitk_f16_f16_f16_mk_kn_mn_v1_interwave_instance.cpp
device_gemm_xdl_splitk_f16_f16_f16_mk_kn_mn_v1_interwave_irregular_instance.cpp
device_gemm_xdl_splitk_f16_f16_f16_mk_kn_mn_v2_instance.cpp
device_gemm_xdl_splitk_f16_f16_f16_mk_kn_mn_v2_irregular_instance.cpp
device_gemm_xdl_splitk_f16_f16_f16_mk_nk_mn_v1_instance.cpp
device_gemm_xdl_splitk_f16_f16_f16_mk_nk_mn_v1_irregular_instance.cpp
device_gemm_xdl_splitk_f16_f16_f16_mk_nk_mn_v1_interwave_instance.cpp
device_gemm_xdl_splitk_f16_f16_f16_mk_nk_mn_v1_interwave_irregular_instance.cpp
device_gemm_xdl_splitk_f16_f16_f16_mk_nk_mn_v2_instance.cpp
device_gemm_xdl_splitk_f16_f16_f16_mk_nk_mn_v2_irregular_instance.cpp
device_gemm_xdl_splitk_f16_f16_f16_km_kn_mn_instance.cpp
device_gemm_xdl_splitk_f16_f16_f16_km_nk_mn_instance.cpp
device_gemm_xdl_splitk_fp8_f16_f16_mk_kn_mn_v1_instance.cpp
device_gemm_xdl_splitk_fp8_f16_f16_mk_kn_mn_v1_interwave_instance.cpp
device_gemm_xdl_splitk_fp8_f16_f16_mk_kn_mn_v2_instance.cpp
device_gemm_xdl_splitk_lds_direct_load_f16_f16_f16_mk_nk_mn_instance.cpp
device_gemm_xdl_splitk_fp8_f16_f16_mk_nk_mn_instance.cpp
device_gemm_xdl_splitk_fp8_f16_f16_km_kn_mn_instance.cpp
device_gemm_xdl_splitk_fp8_f16_f16_km_nk_mn_instance.cpp
device_gemm_xdl_splitk_f16_fp8_f16_mk_kn_mn_v1_instance.cpp
device_gemm_xdl_splitk_f16_fp8_f16_mk_kn_mn_v1_interwave_instance.cpp
device_gemm_xdl_splitk_f16_fp8_f16_mk_kn_mn_v2_instance.cpp
device_gemm_xdl_splitk_f16_fp8_f16_mk_kn_mn_irregular_instance.cpp
device_gemm_xdl_splitk_f16_fp8_f16_mk_nk_mn_v1_instance.cpp
device_gemm_xdl_splitk_f16_fp8_f16_mk_nk_mn_v1_interwave_instance.cpp
device_gemm_xdl_splitk_f16_fp8_f16_mk_nk_mn_v2_instance.cpp
device_gemm_xdl_splitk_f16_fp8_f16_km_kn_mn_instance.cpp
device_gemm_xdl_splitk_f16_fp8_f16_km_nk_mn_instance.cpp
device_gemm_xdl_splitk_f16_f16_f16_comp_fp8_mk_kn_mn_instance.cpp
device_gemm_xdl_splitk_f16_f16_f16_comp_fp8_mk_nk_mn_instance.cpp
device_gemm_xdl_splitk_f16_f16_f16_comp_fp8_km_kn_mn_instance.cpp
device_gemm_xdl_splitk_f16_f16_f16_comp_fp8_km_nk_mn_instance.cpp)
list(APPEND GEMM_SPLITK_INSTANCES
device_gemm_xdl_splitk_f32_f32_f32_mk_kn_mn_instance.cpp
device_gemm_xdl_splitk_f32_f32_f32_mk_nk_mn_instance.cpp
device_gemm_xdl_splitk_f32_f32_f32_km_kn_mn_instance.cpp
device_gemm_xdl_splitk_f32_f32_f32_km_nk_mn_instance.cpp
device_gemm_xdl_splitk_f16_f16_f16_mk_kn_mn_v1_instance.cpp
device_gemm_xdl_splitk_f16_f16_f16_mk_kn_mn_v1_irregular_instance.cpp
device_gemm_xdl_splitk_f16_f16_f16_mk_kn_mn_v1_interwave_instance.cpp
device_gemm_xdl_splitk_f16_f16_f16_mk_kn_mn_v1_interwave_irregular_instance.cpp
device_gemm_xdl_splitk_f16_f16_f16_mk_kn_mn_v2_instance.cpp
device_gemm_xdl_splitk_f16_f16_f16_mk_kn_mn_v2_irregular_instance.cpp
device_gemm_xdl_splitk_f16_f16_f16_mk_nk_mn_v1_instance.cpp
device_gemm_xdl_splitk_f16_f16_f16_mk_nk_mn_v1_irregular_instance.cpp
device_gemm_xdl_splitk_f16_f16_f16_mk_nk_mn_v1_interwave_instance.cpp
device_gemm_xdl_splitk_f16_f16_f16_mk_nk_mn_v1_interwave_irregular_instance.cpp
device_gemm_xdl_splitk_f16_f16_f16_mk_nk_mn_v2_instance.cpp
device_gemm_xdl_splitk_f16_f16_f16_mk_nk_mn_v2_irregular_instance.cpp
device_gemm_xdl_splitk_f16_f16_f16_km_kn_mn_instance.cpp
device_gemm_xdl_splitk_f16_f16_f16_km_nk_mn_instance.cpp
device_gemm_xdl_splitk_fp8_f16_f16_mk_kn_mn_v1_instance.cpp
device_gemm_xdl_splitk_fp8_f16_f16_mk_kn_mn_v1_interwave_instance.cpp
device_gemm_xdl_splitk_fp8_f16_f16_mk_kn_mn_v2_instance.cpp
device_gemm_xdl_splitk_lds_direct_load_f16_f16_f16_mk_nk_mn_instance.cpp
device_gemm_xdl_splitk_fp8_f16_f16_mk_nk_mn_instance.cpp
device_gemm_xdl_splitk_fp8_f16_f16_km_kn_mn_instance.cpp
device_gemm_xdl_splitk_fp8_f16_f16_km_nk_mn_instance.cpp
device_gemm_xdl_splitk_f16_fp8_f16_mk_kn_mn_v1_instance.cpp
device_gemm_xdl_splitk_f16_fp8_f16_mk_kn_mn_v1_interwave_instance.cpp
device_gemm_xdl_splitk_f16_fp8_f16_mk_kn_mn_v2_instance.cpp
device_gemm_xdl_splitk_f16_fp8_f16_mk_kn_mn_irregular_instance.cpp
device_gemm_xdl_splitk_f16_fp8_f16_mk_nk_mn_kpb128_instance.cpp
device_gemm_xdl_splitk_f16_fp8_f16_mk_nk_mn_v1_instance.cpp
device_gemm_xdl_splitk_f16_fp8_f16_mk_nk_mn_v1_interwave_instance.cpp
device_gemm_xdl_splitk_f16_fp8_f16_mk_nk_mn_v2_instance.cpp
device_gemm_xdl_splitk_f16_fp8_f16_km_kn_mn_instance.cpp
device_gemm_xdl_splitk_f16_fp8_f16_km_nk_mn_instance.cpp
device_gemm_xdl_splitk_f16_f16_f16_comp_fp8_mk_kn_mn_instance.cpp
device_gemm_xdl_splitk_f16_f16_f16_comp_fp8_mk_nk_mn_instance.cpp
device_gemm_xdl_splitk_f16_f16_f16_comp_fp8_km_kn_mn_instance.cpp
device_gemm_xdl_splitk_f16_f16_f16_comp_fp8_km_nk_mn_instance.cpp
)
add_instance_library(device_gemm_splitk_instance ${GEMM_SPLITK_INSTANCES})
library/src/tensor_operation_instance/gpu/gemm_splitk/device_gemm_xdl_splitk_f16_fp8_f16_mk_nk_mn_kpb128_instance.cpp 0 → 100644
View file @ ae3d6cb6
// SPDX-License-Identifier: MIT
// Copyright (c) 2024, Advanced Micro Devices, Inc. All rights reserved.
#include <cstdlib>
#include "ck/ck.hpp"
#include "ck/tensor_operation/gpu/device/tensor_layout.hpp"
#include "ck/tensor_operation/gpu/device/gemm_specialization.hpp"
#include "ck/tensor_operation/gpu/device/impl/device_gemm_xdl_splitk_c_shuffle.hpp"
#include "ck/library/tensor_operation_instance/add_device_operation_instance.hpp"
namespace ck {
namespace tensor_operation {
namespace device {
namespace instance {
using F8 = ck::f8_t;
using F16 = ck::half_t;
using F32 = float;
using Row = ck::tensor_layout::gemm::RowMajor;
using Col = ck::tensor_layout::gemm::ColumnMajor;
template <ck::index_t... Is>
using S = ck::Sequence<Is...>;
using PassThrough = ck::tensor_operation::element_wise::PassThrough;
static constexpr auto GemmDefault = ck::tensor_operation::device::GemmSpecialization::Default;
static constexpr auto GemmMNPadding = ck::tensor_operation::device::GemmSpecialization::MNPadding;
static constexpr auto GemmKPadding = ck::tensor_operation::device::GemmSpecialization::KPadding;
static constexpr auto GemmMNKPadding = ck::tensor_operation::device::GemmSpecialization::MNKPadding;
template <ck::tensor_operation::device::GemmSpecialization GemmSpec,
ck::PipelineVersion PipVer,
ck::LoopScheduler LoopSche>
using device_gemm_xdl_splitk_f16_f8_f16_mk_nk_mn_irregular_kpb128_instances = std::tuple<
// clang-format off
//#########################|AData| BData| CData| AccData| ALayout| BLayout| CLayout| A| B| C| GEMM| Block| MPer| NPer| K0Per| K1| MPer| NPer| MXdl| NXdl| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockLds| BBlockTransfer| BBlockTransfer| BBlockTransfer| BlockTransfer| BBlockTransfer| BBlockTransfer| BBlockLds| CShuffle| CShuffle| CBlockTransferClusterLengths| CBlockTransfer|
//#########################| Type| Type| Type| Type| | | | Elementwise| Elementwise| Elementwise|Specialization| Size| Block| Block| Block| | XDL| XDL| Per| Per| ThreadCluster| ThreadCluster| SrcAccessOrder| SrcVectorDim| SrcScalar| DstScalar| AddExtraM| ThreadCluster| ThreadCluster| SrcAccessOrder| SrcVectorDim| SrcScalar| DstScalar| AddExtraN| MXdlPerWave| NXdlPerWave| _MBlock_MXdlPerWave_MWaveMPerXdl| ScalarPerVector|
//#########################| | | | | | | | Operation| Operation| Operation| | | | | | | | | Wave| Wave| Lengths_K0_M_K1| ArrangeOrder| | | PerVector| PerVector_K1| | Lengths_K0_N_K1| ArrangeOrder| | | PerVector| PerVector_K1| | PerShuffle| PerShuffle| _NBlock_NXdlPerWave_NWaveNPerXdl| _NWaveNPerXdl|
//#########################| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
DeviceGemmXdlSplitKCShuffle< F16, F8, F16, F32, Row, Col, Row, PassThrough, PassThrough, PassThrough, GemmSpec, 128, 16, 32, 8, 16, 16, 16, 1, 1, S<1, 8, 8, 2>, S<0, 2, 1, 3>, S<0, 2, 1, 3>, 3, 8, 8, true, S<1, 8, 16, 1>, S<0, 2, 1, 3>, S<0, 2, 1, 3>, 3, 16, 16, true, 1, 1, S<1, 16, 1, 8>, 4, F16, PipVer, LoopSche, F16, F8>,
DeviceGemmXdlSplitKCShuffle< F16, F8, F16, F32, Row, Col, Row, PassThrough, PassThrough, PassThrough, GemmSpec, 128, 16, 64, 8, 16, 16, 16, 1, 2, S<1, 8, 8, 2>, S<0, 2, 1, 3>, S<0, 2, 1, 3>, 3, 8, 8, true, S<1, 8, 16, 1>, S<0, 2, 1, 3>, S<0, 2, 1, 3>, 3, 16, 16, true, 1, 1, S<1, 16, 1, 8>, 4, F16, PipVer, LoopSche, F16, F8>,
DeviceGemmXdlSplitKCShuffle< F16, F8, F16, F32, Row, Col, Row, PassThrough, PassThrough, PassThrough, GemmSpec, 128, 16, 128, 8, 16, 16, 16, 1, 4, S<1, 8, 8, 2>, S<0, 2, 1, 3>, S<0, 2, 1, 3>, 3, 8, 8, true, S<1, 8, 16, 1>, S<0, 2, 1, 3>, S<0, 2, 1, 3>, 3, 16, 16, true, 1, 1, S<1, 16, 1, 8>, 4, F16, PipVer, LoopSche, F16, F8>
// clang-format on
>;
void add_device_gemm_xdl_splitk_f16_f8_f16_mk_nk_mn_kpb128_instances(
std::vector<std::unique_ptr<
DeviceGemmSplitK<Row, Col, Row, F16, F8, F16, PassThrough, PassThrough, PassThrough>>>&
instances)
{
// default
add_device_operation_instances(
instances,
device_gemm_xdl_splitk_f16_f8_f16_mk_nk_mn_irregular_kpb128_instances<
GemmDefault,
ck::PipelineVersion::v2,
ck::LoopScheduler::Default>{});
add_device_operation_instances(
instances,
device_gemm_xdl_splitk_f16_f8_f16_mk_nk_mn_irregular_kpb128_instances<
GemmDefault,
ck::PipelineVersion::v1,
ck::LoopScheduler::Interwave>{});
add_device_operation_instances(
instances,
device_gemm_xdl_splitk_f16_f8_f16_mk_nk_mn_irregular_kpb128_instances<
GemmDefault,
ck::PipelineVersion::v1,
ck::LoopScheduler::Default>{});
// MNKPadding
add_device_operation_instances(
instances,
device_gemm_xdl_splitk_f16_f8_f16_mk_nk_mn_irregular_kpb128_instances<
GemmMNKPadding,
ck::PipelineVersion::v2,
ck::LoopScheduler::Default>{});
add_device_operation_instances(
instances,
device_gemm_xdl_splitk_f16_f8_f16_mk_nk_mn_irregular_kpb128_instances<
GemmMNKPadding,
ck::PipelineVersion::v1,
ck::LoopScheduler::Interwave>{});
add_device_operation_instances(
instances,
device_gemm_xdl_splitk_f16_f8_f16_mk_nk_mn_irregular_kpb128_instances<
GemmMNKPadding,
ck::PipelineVersion::v1,
ck::LoopScheduler::Default>{});
// KPadding
add_device_operation_instances(
instances,
device_gemm_xdl_splitk_f16_f8_f16_mk_nk_mn_irregular_kpb128_instances<
GemmKPadding,
ck::PipelineVersion::v2,
ck::LoopScheduler::Default>{});
add_device_operation_instances(
instances,
device_gemm_xdl_splitk_f16_f8_f16_mk_nk_mn_irregular_kpb128_instances<
GemmKPadding,
ck::PipelineVersion::v1,
ck::LoopScheduler::Interwave>{});
add_device_operation_instances(
instances,
device_gemm_xdl_splitk_f16_f8_f16_mk_nk_mn_irregular_kpb128_instances<
GemmKPadding,
ck::PipelineVersion::v1,
ck::LoopScheduler::Default>{});
// MNPadding
add_device_operation_instances(
instances,
device_gemm_xdl_splitk_f16_f8_f16_mk_nk_mn_irregular_kpb128_instances<
GemmMNPadding,
ck::PipelineVersion::v2,
ck::LoopScheduler::Default>{});
add_device_operation_instances(
instances,
device_gemm_xdl_splitk_f16_f8_f16_mk_nk_mn_irregular_kpb128_instances<
GemmMNPadding,
ck::PipelineVersion::v1,
ck::LoopScheduler::Interwave>{});
add_device_operation_instances(
instances,
device_gemm_xdl_splitk_f16_f8_f16_mk_nk_mn_irregular_kpb128_instances<
GemmMNPadding,
ck::PipelineVersion::v1,
ck::LoopScheduler::Default>{});
}
} // namespace instance
} // namespace device
} // namespace tensor_operation
} // namespace ck
library/src/tensor_operation_instance/gpu/grouped_conv2d_bwd_data/CMakeLists.txt
View file @ ae3d6cb6
add_instance_library(device_grouped_conv2d_bwd_data_instance
xdl/device_grouped_conv2d_bwd_data_xdl_gnhwc_gkyxc_gnhwk_f16_instance.cpp
xdl/device_grouped_conv2d_bwd_data_xdl_gnhwc_gkyxc_gnhwk_bf16_instance.cpp
xdl/device_grouped_conv2d_bwd_data_xdl_gnhwc_gkyxc_gnhwk_f32_instance.cpp
xdl/device_grouped_conv2d_bwd_data_xdl_nhwgc_gkyxc_nhwgk_f16_instance.cpp
xdl/device_grouped_conv2d_bwd_data_xdl_nhwgc_gkyxc_nhwgk_bf16_instance.cpp
xdl/device_grouped_conv2d_bwd_data_xdl_nhwgc_gkyxc_nhwgk_f32_instance.cpp
add_instance_library(
device_grouped_conv2d_bwd_data_instance
xdl/device_grouped_conv2d_bwd_data_xdl_gnhwc_gkyxc_gnhwk_f16_instance.cpp
xdl/device_grouped_conv2d_bwd_data_xdl_gnhwc_gkyxc_gnhwk_bf16_instance.cpp
xdl/device_grouped_conv2d_bwd_data_xdl_gnhwc_gkyxc_gnhwk_f32_instance.cpp
xdl/device_grouped_conv2d_bwd_data_xdl_nhwgc_gkyxc_nhwgk_f16_instance.cpp
xdl/device_grouped_conv2d_bwd_data_xdl_nhwgc_gkyxc_nhwgk_bf16_instance.cpp
xdl/device_grouped_conv2d_bwd_data_xdl_nhwgc_gkyxc_nhwgk_f32_instance.cpp
wmma/device_grouped_conv2d_bwd_data_wmma_gnhwc_gkyxc_gnhwk_f16_1x1s1p0_instance.cpp
wmma/device_grouped_conv2d_bwd_data_wmma_nhwgc_gkyxc_nhwgk_f16_1x1s1p0_instance.cpp
wmma/device_grouped_conv2d_bwd_data_wmma_gnhwc_gkyxc_gnhwk_i8_1x1s1p0_instance.cpp
wmma/device_grouped_conv2d_bwd_data_wmma_nhwgc_gkyxc_nhwgk_i8_1x1s1p0_instance.cpp
wmma/device_grouped_conv2d_bwd_data_wmma_gnhwc_gkyxc_gnhwk_f16_instance.cpp
wmma/device_grouped_conv2d_bwd_data_wmma_nhwgc_gkyxc_nhwgk_f16_instance.cpp
wmma/device_grouped_conv2d_bwd_data_wmma_gnhwc_gkyxc_gnhwk_i8_instance.cpp
wmma/device_grouped_conv2d_bwd_data_wmma_nhwgc_gkyxc_nhwgk_i8_instance.cpp)
wmma/device_grouped_conv2d_bwd_data_wmma_gnhwc_gkyxc_gnhwk_f16_1x1s1p0_instance.cpp
wmma/device_grouped_conv2d_bwd_data_wmma_nhwgc_gkyxc_nhwgk_f16_1x1s1p0_instance.cpp
wmma/device_grouped_conv2d_bwd_data_wmma_gnhwc_gkyxc_gnhwk_i8_1x1s1p0_instance.cpp
wmma/device_grouped_conv2d_bwd_data_wmma_nhwgc_gkyxc_nhwgk_i8_1x1s1p0_instance.cpp
wmma/device_grouped_conv2d_bwd_data_wmma_gnhwc_gkyxc_gnhwk_f16_instance.cpp
wmma/device_grouped_conv2d_bwd_data_wmma_nhwgc_gkyxc_nhwgk_f16_instance.cpp
wmma/device_grouped_conv2d_bwd_data_wmma_gnhwc_gkyxc_gnhwk_i8_instance.cpp
wmma/device_grouped_conv2d_bwd_data_wmma_nhwgc_gkyxc_nhwgk_i8_instance.cpp
)
library/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/CMakeLists.txt
View file @ ae3d6cb6
......@@ -17,21 +17,21 @@ add_instance_library(device_grouped_conv2d_fwd_instance
dl/device_grouped_conv2d_fwd_dl_nhwgc_gkyxc_nhwgk_f32_instance.cpp
# WMMA
# GNHWC, GKYXC, GNHWK
wmma/device_grouped_conv2d_fwd_wmma_gnhwc_gkyxc_gnhwk_f16_instance.cpp
wmma/device_grouped_conv2d_fwd_wmma_gnhwc_gkyxc_gnhwk_i8_instance.cpp
wmma/device_grouped_conv2d_fwd_wmma_gnhwc_gkyxc_gnhwk_f16_1x1p0_instance.cpp
wmma/device_grouped_conv2d_fwd_wmma_gnhwc_gkyxc_gnhwk_i8_1x1p0_instance.cpp
wmma/device_grouped_conv2d_fwd_wmma_gnhwc_gkyxc_gnhwk_f16_1x1s1p0_instance.cpp
wmma/device_grouped_conv2d_fwd_wmma_gnhwc_gkyxc_gnhwk_i8_1x1s1p0_instance.cpp
wmma/device_grouped_conv2d_fwd_wmma_gnhwc_gkyxc_gnhwk_f16_oddc_instance.cpp
wmma/device_grouped_conv2d_fwd_wmma_gnhwc_gkyxc_gnhwk_i8_oddc_instance.cpp
# NHWGC, GKYXC, NHWGK
wmma/device_grouped_conv2d_fwd_wmma_nhwgc_gkyxc_nhwgk_f16_instance.cpp
wmma/device_grouped_conv2d_fwd_wmma_nhwgc_gkyxc_nhwgk_i8_instance.cpp
wmma/device_grouped_conv2d_fwd_wmma_nhwgc_gkyxc_nhwgk_f16_1x1p0_instance.cpp
wmma/device_grouped_conv2d_fwd_wmma_nhwgc_gkyxc_nhwgk_i8_1x1p0_instance.cpp
wmma/device_grouped_conv2d_fwd_wmma_nhwgc_gkyxc_nhwgk_f16_1x1s1p0_instance.cpp
wmma/device_grouped_conv2d_fwd_wmma_nhwgc_gkyxc_nhwgk_i8_1x1s1p0_instance.cpp
wmma/device_grouped_conv2d_fwd_wmma_nhwgc_gkyxc_nhwgk_f16_oddc_instance.cpp
wmma/device_grouped_conv2d_fwd_wmma_nhwgc_gkyxc_nhwgk_i8_oddc_instance.cpp
wmma/device_grouped_conv2d_fwd_wmma_gnhwc_gkyxc_gnhwk_f16_instance.cpp
wmma/device_grouped_conv2d_fwd_wmma_gnhwc_gkyxc_gnhwk_i8_instance.cpp
wmma/device_grouped_conv2d_fwd_wmma_gnhwc_gkyxc_gnhwk_f16_1x1p0_instance.cpp
wmma/device_grouped_conv2d_fwd_wmma_gnhwc_gkyxc_gnhwk_i8_1x1p0_instance.cpp
wmma/device_grouped_conv2d_fwd_wmma_gnhwc_gkyxc_gnhwk_f16_1x1s1p0_instance.cpp
wmma/device_grouped_conv2d_fwd_wmma_gnhwc_gkyxc_gnhwk_i8_1x1s1p0_instance.cpp
wmma/device_grouped_conv2d_fwd_wmma_gnhwc_gkyxc_gnhwk_f16_oddc_instance.cpp
wmma/device_grouped_conv2d_fwd_wmma_gnhwc_gkyxc_gnhwk_i8_oddc_instance.cpp
## NHWGC, GKYXC, NHWGK
wmma/device_grouped_conv2d_fwd_wmma_nhwgc_gkyxc_nhwgk_f16_instance.cpp
wmma/device_grouped_conv2d_fwd_wmma_nhwgc_gkyxc_nhwgk_i8_instance.cpp
wmma/device_grouped_conv2d_fwd_wmma_nhwgc_gkyxc_nhwgk_f16_1x1p0_instance.cpp
wmma/device_grouped_conv2d_fwd_wmma_nhwgc_gkyxc_nhwgk_i8_1x1p0_instance.cpp
wmma/device_grouped_conv2d_fwd_wmma_nhwgc_gkyxc_nhwgk_f16_1x1s1p0_instance.cpp
wmma/device_grouped_conv2d_fwd_wmma_nhwgc_gkyxc_nhwgk_i8_1x1s1p0_instance.cpp
wmma/device_grouped_conv2d_fwd_wmma_nhwgc_gkyxc_nhwgk_f16_oddc_instance.cpp
wmma/device_grouped_conv2d_fwd_wmma_nhwgc_gkyxc_nhwgk_i8_oddc_instance.cpp
)
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment