ROCm/composable_kernel
1
0
Fork 0
mirror of https://github.com/ROCm/composable_kernel.git synced 2026-07-03 13:48:30 +00:00
Code Issues Packages Projects Releases Wiki Activity

Remove spurious ck_tile changes that were presumably introduced somewhere in the repeated merging from develop.

Browse Source
This commit is contained in:
kiefer
2025-10-03 11:07:21 +00:00
parent 8c8063134a
commit 22fb5c5d75
29 changed files with 53 additions and 344 deletions
Download Patch File Download Diff File Expand all files Collapse all files

144
example/68_gemm_add/run_gemm_add_example.inc
View File

@@ -1,144 +0,0 @@
#pragma once
bool run_gemm_add(const ProblemSize& problem_size, const ExecutionConfig& config)
{
using namespace ck::literals;
auto& [M, N, K, StrideA, StrideB, StrideD, StrideE] = problem_size;
auto f_host_tensor_descriptor =
[](std::size_t row, std::size_t col, std::size_t stride, auto layout) {
if(std::is_same<decltype(layout), ck::tensor_layout::gemm::RowMajor>::value)
{
return HostTensorDescriptor({row, col}, {stride, 1_uz});
}
else
{
return HostTensorDescriptor({row, col}, {1_uz, stride});
}
};
Tensor<ADataType> a_m_k(f_host_tensor_descriptor(M, K, StrideA, ALayout{}));
Tensor<BDataType> b_k_n(f_host_tensor_descriptor(K, N, StrideB, BLayout{}));
Tensor<DDataType> d_m_n(f_host_tensor_descriptor(M, N, StrideD, DLayout{}));
Tensor<EDataType> e_m_n_host_result(f_host_tensor_descriptor(M, N, StrideE, ELayout{}));
Tensor<EDataType> e_m_n_device_result(f_host_tensor_descriptor(M, N, StrideE, ELayout{}));
std::cout << "a_m_k: " << a_m_k.mDesc << std::endl;
std::cout << "b_k_n: " << b_k_n.mDesc << std::endl;
std::cout << "d_m_n: " << d_m_n.mDesc << std::endl;
std::cout << "e_m_n: " << e_m_n_host_result.mDesc << std::endl;
switch(config.init_method)
{
case 0: break;
case 1:
a_m_k.GenerateTensorValue(GeneratorTensor_2<ADataType>{-5, 5});
b_k_n.GenerateTensorValue(GeneratorTensor_2<BDataType>{-5, 5});
d_m_n.GenerateTensorValue(GeneratorTensor_2<DDataType>{-5, 5});
break;
default:
a_m_k.GenerateTensorValue(GeneratorTensor_3<ADataType>{0.0, 1.0});
b_k_n.GenerateTensorValue(GeneratorTensor_3<BDataType>{-0.5, 0.5});
d_m_n.GenerateTensorValue(GeneratorTensor_3<DDataType>{-0.5, 0.5});
}
DeviceMem a_device_buf(sizeof(ADataType) * a_m_k.mDesc.GetElementSpaceSize());
DeviceMem b_device_buf(sizeof(BDataType) * b_k_n.mDesc.GetElementSpaceSize());
DeviceMem d_device_buf(sizeof(DDataType) * d_m_n.mDesc.GetElementSpaceSize());
DeviceMem e_device_buf(sizeof(EDataType) * e_m_n_device_result.mDesc.GetElementSpaceSize());
a_device_buf.ToDevice(a_m_k.mData.data());
b_device_buf.ToDevice(b_k_n.mData.data());
d_device_buf.ToDevice(d_m_n.mData.data());
e_device_buf.ToDevice(e_m_n_device_result.mData.data());
auto a_element_op = AElementOp{};
auto b_element_op = BElementOp{};
auto cde_element_op = CDEElementOp{};
// do GEMM
auto device_op = DeviceOpInstance{};
auto invoker = device_op.MakeInvoker();
auto argument =
device_op.MakeArgument(a_device_buf.GetDeviceBuffer(),
b_device_buf.GetDeviceBuffer(),
std::array<const void*, 1>{d_device_buf.GetDeviceBuffer()},
e_device_buf.GetDeviceBuffer(),
M,
N,
K,
StrideA,
StrideB,
std::array<ck::index_t, 1>{StrideD},
StrideE,
1,
a_element_op,
b_element_op,
cde_element_op);
if(!device_op.IsSupportedArgument(argument))
{
throw std::runtime_error(
"wrong! device_gemm with the specified compilation parameters does "
"not support this GEMM problem");
}
float ave_time = invoker.Run(argument, StreamConfig{nullptr, config.time_kernel});
std::size_t flop = std::size_t(2) * M * N * K;
std::size_t num_btype =
sizeof(ADataType) * M * K + sizeof(BDataType) * K * N + sizeof(EDataType) * M * N;
float tflops = static_cast<float>(flop) / 1.E9 / ave_time;
float gb_per_sec = num_btype / 1.E6 / ave_time;
std::cout << "Perf: " << ave_time << " ms, " << tflops << " TFlops, " << gb_per_sec << " GB/s"
<< device_op.GetTypeString() << std::endl;
e_device_buf.FromDevice(e_m_n_device_result.mData.data());
if(config.do_verification)
{
Tensor<CShuffleDataType> c_m_n({M, N});
using ReferenceGemmInstance = ck::tensor_operation::host::ReferenceGemm<ADataType,
BDataType,
CShuffleDataType,
AccDataType,
AElementOp,
BElementOp,
PassThrough>;
auto ref_gemm = ReferenceGemmInstance{};
auto ref_invoker = ref_gemm.MakeInvoker();
auto ref_argument =
ref_gemm.MakeArgument(a_m_k, b_k_n, c_m_n, a_element_op, b_element_op, PassThrough{});
ref_invoker.Run(ref_argument);
for(int m = 0; m < M; ++m)
{
for(int n = 0; n < N; ++n)
{
cde_element_op(e_m_n_host_result(m, n), c_m_n(m, n), d_m_n(m, n));
}
}
e_device_buf.FromDevice(e_m_n_device_result.mData.data());
return ck::utils::check_err(e_m_n_device_result, e_m_n_host_result);
}
return true;
}
bool run_gemm_add_example(int argc, char* argv[])
{
ProblemSize problem_size;
ExecutionConfig config;
return parse_cmd_args(argc, argv, problem_size, config) && run_gemm_add(problem_size, config);
}

145
example/69_gemm_add_relu/run_gemm_add_relu_example.inc
View File

@@ -1,145 +0,0 @@
#pragma once
bool run_gemm_add_relu(const ProblemSize& problem_size, const ExecutionConfig& config)
{
using namespace ck::literals;
auto& [M, N, K, StrideA, StrideB, StrideD, StrideE] = problem_size;
auto f_host_tensor_descriptor =
[](std::size_t row, std::size_t col, std::size_t stride, auto layout) {
if(std::is_same<decltype(layout), ck::tensor_layout::gemm::RowMajor>::value)
{
return HostTensorDescriptor({row, col}, {stride, 1_uz});
}
else
{
return HostTensorDescriptor({row, col}, {1_uz, stride});
}
};
Tensor<ADataType> a_m_k(f_host_tensor_descriptor(M, K, StrideA, ALayout{}));
Tensor<BDataType> b_k_n(f_host_tensor_descriptor(K, N, StrideB, BLayout{}));
Tensor<DDataType> d_m_n(f_host_tensor_descriptor(M, N, StrideD, DLayout{}));
Tensor<EDataType> e_m_n_host_result(f_host_tensor_descriptor(M, N, StrideE, ELayout{}));
Tensor<EDataType> e_m_n_device_result(f_host_tensor_descriptor(M, N, StrideE, ELayout{}));
std::cout << "a_m_k: " << a_m_k.mDesc << std::endl;
std::cout << "b_k_n: " << b_k_n.mDesc << std::endl;
std::cout << "d_m_n: " << d_m_n.mDesc << std::endl;
std::cout << "e_m_n: " << e_m_n_host_result.mDesc << std::endl;
switch(config.init_method)
{
case 0: break;
case 1:
a_m_k.GenerateTensorValue(GeneratorTensor_2<ADataType>{-5, 5});
b_k_n.GenerateTensorValue(GeneratorTensor_2<BDataType>{-5, 5});
d_m_n.GenerateTensorValue(GeneratorTensor_2<DDataType>{-5, 5});
break;
default:
a_m_k.GenerateTensorValue(GeneratorTensor_3<ADataType>{0.0, 1.0});
b_k_n.GenerateTensorValue(GeneratorTensor_3<BDataType>{-0.5, 0.5});
d_m_n.GenerateTensorValue(GeneratorTensor_3<DDataType>{-0.5, 0.5});
}
DeviceMem a_device_buf(sizeof(ADataType) * a_m_k.mDesc.GetElementSpaceSize());
DeviceMem b_device_buf(sizeof(BDataType) * b_k_n.mDesc.GetElementSpaceSize());
DeviceMem d_device_buf(sizeof(DDataType) * d_m_n.mDesc.GetElementSpaceSize());
DeviceMem e_device_buf(sizeof(EDataType) * e_m_n_device_result.mDesc.GetElementSpaceSize());
a_device_buf.ToDevice(a_m_k.mData.data());
b_device_buf.ToDevice(b_k_n.mData.data());
d_device_buf.ToDevice(d_m_n.mData.data());
e_device_buf.ToDevice(e_m_n_device_result.mData.data());
auto a_element_op = AElementOp{};
auto b_element_op = BElementOp{};
auto cde_element_op = CDEElementOp{};
// do GEMM
auto device_op = DeviceOpInstance{};
auto invoker = device_op.MakeInvoker();
auto argument =
device_op.MakeArgument(a_device_buf.GetDeviceBuffer(),
b_device_buf.GetDeviceBuffer(),
std::array<const void*, 1>{d_device_buf.GetDeviceBuffer()},
e_device_buf.GetDeviceBuffer(),
M,
N,
K,
StrideA,
StrideB,
std::array<ck::index_t, 1>{StrideD},
StrideE,
1,
a_element_op,
b_element_op,
cde_element_op);
if(!device_op.IsSupportedArgument(argument))
{
throw std::runtime_error(
"wrong! device_gemm with the specified compilation parameters does "
"not support this GEMM problem");
}
float ave_time = invoker.Run(argument, StreamConfig{nullptr, config.time_kernel});
std::size_t flop = std::size_t(2) * M * N * K;
std::size_t num_btype =
sizeof(ADataType) * M * K + sizeof(BDataType) * K * N + sizeof(EDataType) * M * N;
float tflops = static_cast<float>(flop) / 1.E9 / ave_time;
float gb_per_sec = num_btype / 1.E6 / ave_time;
std::cout << "Perf: " << ave_time << " ms, " << tflops << " TFlops, " << gb_per_sec << " GB/s"
<< device_op.GetTypeString() << std::endl;
e_device_buf.FromDevice(e_m_n_device_result.mData.data());
if(config.do_verification)
{
Tensor<CShuffleDataType> c_m_n({M, N});
using ReferenceGemmInstance = ck::tensor_operation::host::ReferenceGemm<ADataType,
BDataType,
CShuffleDataType,
AccDataType,
AElementOp,
BElementOp,
PassThrough>;
auto ref_gemm = ReferenceGemmInstance{};
auto ref_invoker = ref_gemm.MakeInvoker();
auto ref_argument =
ref_gemm.MakeArgument(a_m_k, b_k_n, c_m_n, a_element_op, b_element_op, PassThrough{});
ref_invoker.Run(ref_argument);
for(int m = 0; m < M; ++m)
{
for(int n = 0; n < N; ++n)
{
cde_element_op(e_m_n_host_result(m, n), c_m_n(m, n), d_m_n(m, n));
}
}
e_device_buf.FromDevice(e_m_n_device_result.mData.data());
return ck::utils::check_err(e_m_n_device_result, e_m_n_host_result) ? 0 : 1;
}
return 0;
}
bool run_gemm_add_relu_example(int argc, char* argv[])
{
ProblemSize problem_size;
ExecutionConfig config;
return !parse_cmd_args(argc, argv, problem_size, config) ||
run_gemm_add_relu(problem_size, config);
}

0
example/ck_tile/38_block_scale_gemm/gemm_quant_basic.cpp Normal file → Executable file
View File

0
example/ck_tile/38_block_scale_gemm/run_gemm_quant_example.inc Normal file → Executable file
View File

46
include/ck/tensor_operation/gpu/device/device_gemm_multiple_d.hpp
View File

@@ -149,6 +149,52 @@ struct DeviceGemmMultipleDSplitKBPreShuffle : public BaseOperator
#endif
};
template <typename ALayout,
typename BLayout,
typename DsLayout,
typename ELayout,
typename ADataType,
typename AScaleDataType,
typename BDataType,
typename BScaleDataType,
typename DsDataType,
typename EDataType,
index_t ScaleBlockSize,
typename AElementwiseOperation,
typename BElementwiseOperation,
typename CDEElementwiseOperation>
struct DeviceMoEGemmMXBPreShuffle : public BaseOperator
{
static constexpr index_t NumDTensor = DsDataType::Size();
#ifndef CK_CODE_GEN_RTC
virtual std::unique_ptr<BaseArgument>
MakeArgumentPointer(const void* p_a,
const void* p_a_scale,
const void* p_b,
const void* p_b_scale,
std::array<const void*, NumDTensor> p_ds,
void* p_e,
ck::index_t M,
ck::index_t N,
ck::index_t K,
ck::index_t StrideA,
ck::index_t StrideAScale,
ck::index_t StrideB,
ck::index_t StrideBScale,
std::array<ck::index_t, NumDTensor> StrideDs,
ck::index_t StrideE,
ck::index_t KBatch,
AElementwiseOperation a_element_op,
BElementwiseOperation b_element_op,
CDEElementwiseOperation cde_element_op) = 0;
virtual std::unique_ptr<BaseInvoker> MakeInvokerPointer() = 0;
virtual int GetPreShuffleParameters() = 0;
#endif
};
/// @brief Wrapper for backward compatibility that allows to use instances of
/// DeviceGemmMultipleDSplitK in contexts where DeviceGemmMultipleD is expected.
///

1
include/ck_tile/host.hpp
View File

@@ -16,7 +16,6 @@
#include "ck_tile/host/host_tensor.hpp"
#include "ck_tile/host/joinable_thread.hpp"
#include "ck_tile/host/kernel_launch.hpp"
#include "ck_tile/host/permute_pk_int4.hpp"
#include "ck_tile/host/ranges.hpp"
#include "ck_tile/host/reference/reference_batched_dropout.hpp"
#include "ck_tile/host/reference/reference_batched_dropout_randval.hpp"

2
include/ck_tile/ops/add_rmsnorm2d_rdquant.hpp
View File

@@ -9,7 +9,5 @@
#include "ck_tile/ops/add_rmsnorm2d_rdquant/pipeline/add_rmsnorm2d_rdquant_fwd_pipeline_problem.hpp"
#include "ck_tile/ops/add_rmsnorm2d_rdquant/pipeline/add_rmsnorm2d_rdquant_fwd_pipeline_three_pass.hpp"
#include "ck_tile/ops/common/generic_2d_block_shape.hpp"
#include "ck_tile/ops/common/load_interleaved_pk_type.hpp"
#include "ck_tile/ops/common/streamk_common.hpp"
#include "ck_tile/ops/common/tensor_layout.hpp"
#include "ck_tile/ops/common/utils.hpp"

2
include/ck_tile/ops/batched_transpose.hpp
View File

@@ -12,7 +12,5 @@
#include "ck_tile/ops/batched_transpose/pipeline/batched_transpose_policy.hpp"
#include "ck_tile/ops/batched_transpose/pipeline/batched_transpose_problem.hpp"
#include "ck_tile/ops/common/generic_2d_block_shape.hpp"
#include "ck_tile/ops/common/load_interleaved_pk_type.hpp"
#include "ck_tile/ops/common/streamk_common.hpp"
#include "ck_tile/ops/common/tensor_layout.hpp"
#include "ck_tile/ops/common/utils.hpp"

3
include/ck_tile/ops/common.hpp
View File

@@ -4,7 +4,6 @@
#pragma once
#include "ck_tile/ops/common/generic_2d_block_shape.hpp"
#include "ck_tile/ops/common/load_interleaved_pk_type.hpp"
#include "ck_tile/ops/common/streamk_common.hpp"
#include "ck_tile/ops/common/tensor_layout.hpp"
#include "ck_tile/ops/common/utils.hpp"
#include "ck_tile/ops/common/streamk_common.hpp"

2
include/ck_tile/ops/elementwise.hpp
View File

@@ -10,7 +10,5 @@
#include "ck_tile/ops/elementwise/pipeline/elementwise_shape.hpp"
#include "ck_tile/ops/elementwise/unary_element_wise_operation.hpp"
#include "ck_tile/ops/common/generic_2d_block_shape.hpp"
#include "ck_tile/ops/common/load_interleaved_pk_type.hpp"
#include "ck_tile/ops/common/streamk_common.hpp"
#include "ck_tile/ops/common/tensor_layout.hpp"
#include "ck_tile/ops/common/utils.hpp"

2
include/ck_tile/ops/epilogue.hpp
View File

@@ -8,7 +8,5 @@
#include "ck_tile/ops/epilogue/default_2d_epilogue.hpp"
#include "ck_tile/ops/epilogue/dynamic_quant_epilogue.hpp"
#include "ck_tile/ops/common/generic_2d_block_shape.hpp"
#include "ck_tile/ops/common/load_interleaved_pk_type.hpp"
#include "ck_tile/ops/common/streamk_common.hpp"
#include "ck_tile/ops/common/tensor_layout.hpp"
#include "ck_tile/ops/common/utils.hpp"

2
include/ck_tile/ops/flatmm.hpp
View File

@@ -14,7 +14,5 @@
#include "ck_tile/ops/flatmm/pipeline/flatmm_pipeline_agmem_bgmem_creg_v1_policy.hpp"
#include "ck_tile/ops/flatmm/pipeline/tile_flatmm_shape.hpp"
#include "ck_tile/ops/common/generic_2d_block_shape.hpp"
#include "ck_tile/ops/common/load_interleaved_pk_type.hpp"
#include "ck_tile/ops/common/streamk_common.hpp"
#include "ck_tile/ops/common/tensor_layout.hpp"
#include "ck_tile/ops/common/utils.hpp"

2
include/ck_tile/ops/fmha.hpp
View File

@@ -60,7 +60,5 @@
#include "ck_tile/ops/fmha/pipeline/tile_fmha_shape.hpp"
#include "ck_tile/ops/fmha/pipeline/tile_fmha_traits.hpp"
#include "ck_tile/ops/common/generic_2d_block_shape.hpp"
#include "ck_tile/ops/common/load_interleaved_pk_type.hpp"
#include "ck_tile/ops/common/streamk_common.hpp"
#include "ck_tile/ops/common/tensor_layout.hpp"
#include "ck_tile/ops/common/utils.hpp"

2
include/ck_tile/ops/fused_moe.hpp
View File

@@ -16,7 +16,5 @@
#include "ck_tile/ops/fused_moe/pipeline/moe_sorting_pipeline.hpp"
#include "ck_tile/ops/fused_moe/pipeline/moe_sorting_policy.hpp"
#include "ck_tile/ops/common/generic_2d_block_shape.hpp"
#include "ck_tile/ops/common/load_interleaved_pk_type.hpp"
#include "ck_tile/ops/common/streamk_common.hpp"
#include "ck_tile/ops/common/tensor_layout.hpp"
#include "ck_tile/ops/common/utils.hpp"

8
include/ck_tile/ops/gemm.hpp
View File

@@ -30,18 +30,18 @@
#include "ck_tile/ops/gemm/block/block_wp_asmem_bsmem_creg_v1_custom_policy.hpp"
#include "ck_tile/ops/gemm/kernel/batched_gemm_kernel.hpp"
#include "ck_tile/ops/gemm/kernel/gemm_kernel.hpp"
#include "ck_tile/ops/gemm/kernel/gemm_multi_abd_kernel.hpp"
#include "ck_tile/ops/gemm/kernel/gemm_multi_d_kernel.hpp"
#include "ck_tile/ops/gemm/kernel/gemm_multi_abd_kernel.hpp"
#include "ck_tile/ops/gemm/kernel/gemm_tile_partitioner.hpp"
#include "ck_tile/ops/gemm/kernel/grouped_gemm_kernel.hpp"
#include "ck_tile/ops/gemm/kernel/streamk_gemm_kernel.hpp"
#include "ck_tile/ops/gemm/kernel/universal_gemm_kernel.hpp"
#include "ck_tile/ops/gemm/pipeline/gemm_pipeline_ag_bg_cr_base.hpp"
#include "ck_tile/ops/gemm/pipeline/gemm_pipeline_ag_bg_cr_comp_async.hpp"
#include "ck_tile/ops/gemm/pipeline/gemm_pipeline_ag_bg_cr_comp_async_default_policy.hpp"
#include "ck_tile/ops/gemm/pipeline/gemm_pipeline_ag_bg_cr_comp_v3.hpp"
#include "ck_tile/ops/gemm/pipeline/gemm_pipeline_ag_bg_cr_comp_v4.hpp"
#include "ck_tile/ops/gemm/pipeline/gemm_pipeline_ag_bg_cr_comp_v4_default_policy.hpp"
#include "ck_tile/ops/gemm/pipeline/gemm_pipeline_ag_bg_cr_comp_async.hpp"
#include "ck_tile/ops/gemm/pipeline/gemm_pipeline_ag_bg_cr_comp_async_default_policy.hpp"
#include "ck_tile/ops/gemm/pipeline/gemm_pipeline_ag_bg_cr_comp_v5.hpp"
#include "ck_tile/ops/gemm/pipeline/gemm_pipeline_ag_bg_cr_comp_v5_default_policy.hpp"
#include "ck_tile/ops/gemm/pipeline/gemm_pipeline_ag_bg_cr_mem.hpp"
@@ -72,7 +72,5 @@
#include "ck_tile/ops/gemm/warp/warp_gemm_smfmac_impl.hpp"
#include "ck_tile/ops/gemm/warp/warp_wmma_gemm.hpp"
#include "ck_tile/ops/common/generic_2d_block_shape.hpp"
#include "ck_tile/ops/common/load_interleaved_pk_type.hpp"
#include "ck_tile/ops/common/streamk_common.hpp"
#include "ck_tile/ops/common/tensor_layout.hpp"
#include "ck_tile/ops/common/utils.hpp"

8
include/ck_tile/ops/gemm_quant.hpp
View File

@@ -3,8 +3,8 @@
#pragma once
#include "ck_tile/ops/gemm_quant/block/block_universal_gemm_ar_flatbr_bquant_cr.hpp"
#include "ck_tile/ops/gemm_quant/block/block_universal_gemm_as_aquant_bs_cr.hpp"
#include "ck_tile/ops/gemm_quant/block/block_universal_gemm_ar_flatbr_bquant_cr.hpp"
#include "ck_tile/ops/gemm_quant/block/block_universal_gemm_as_bs_bquant_cr.hpp"
#include "ck_tile/ops/gemm_quant/kernel/gemm_quant_kernel.hpp"
#include "ck_tile/ops/gemm_quant/kernel/grouped_gemm_quant_kernel.hpp"
@@ -14,13 +14,11 @@
#include "ck_tile/ops/gemm_quant/pipeline/gemm_bquant_pipeline_ag_bg_cr_base.hpp"
#include "ck_tile/ops/gemm_quant/pipeline/gemm_bquant_pipeline_ag_bg_cr_policy.hpp"
#include "ck_tile/ops/gemm_quant/pipeline/gemm_bquant_pipeline_ag_bg_cr_v3.hpp"
#include "ck_tile/ops/gemm_quant/pipeline/gemm_group_quant_utils.hpp"
#include "ck_tile/ops/gemm_quant/pipeline/gemm_quant_pipeline_problem.hpp"
#include "ck_tile/ops/gemm_quant/pipeline/gemm_wp_bquant_pipeline_ag_bg_cr_base_policy.hpp"
#include "ck_tile/ops/gemm_quant/pipeline/gemm_wp_bquant_pipeline_ag_bg_cr_v2.hpp"
#include "ck_tile/ops/gemm_quant/pipeline/gemm_group_quant_utils.hpp"
#include "ck_tile/ops/gemm_quant/pipeline/gemm_quant_pipeline_problem.hpp"
#include "ck_tile/ops/gemm_quant/pipeline/tile_gemm_quant_traits.hpp"
#include "ck_tile/ops/common/generic_2d_block_shape.hpp"
#include "ck_tile/ops/common/load_interleaved_pk_type.hpp"
#include "ck_tile/ops/common/streamk_common.hpp"
#include "ck_tile/ops/common/tensor_layout.hpp"
#include "ck_tile/ops/common/utils.hpp"

0
include/ck_tile/ops/gemm_quant/block/block_universal_gemm_ar_flatbr_bquant_cr.hpp Normal file → Executable file
View File

2
include/ck_tile/ops/grouped_convolution.hpp
View File

@@ -12,7 +12,5 @@
#include "ck_tile/ops/grouped_convolution/utils/transform_conv_bwd_weight_to_gemm.hpp"
#include "ck_tile/ops/grouped_convolution/utils/transform_conv_fwd_to_gemm.hpp"
#include "ck_tile/ops/common/generic_2d_block_shape.hpp"
#include "ck_tile/ops/common/load_interleaved_pk_type.hpp"
#include "ck_tile/ops/common/streamk_common.hpp"
#include "ck_tile/ops/common/tensor_layout.hpp"
#include "ck_tile/ops/common/utils.hpp"

2
include/ck_tile/ops/image_to_column.hpp
View File

@@ -7,7 +7,5 @@
#include "ck_tile/ops/image_to_column/pipeline/block_image_to_column_problem.hpp"
#include "ck_tile/ops/image_to_column/pipeline/tile_image_to_column_shape.hpp"
#include "ck_tile/ops/common/generic_2d_block_shape.hpp"
#include "ck_tile/ops/common/load_interleaved_pk_type.hpp"
#include "ck_tile/ops/common/streamk_common.hpp"
#include "ck_tile/ops/common/tensor_layout.hpp"
#include "ck_tile/ops/common/utils.hpp"

2
include/ck_tile/ops/layernorm2d.hpp
View File

@@ -10,7 +10,5 @@
#include "ck_tile/ops/layernorm2d/pipeline/layernorm2d_fwd_pipeline_two_pass.hpp"
#include "ck_tile/ops/layernorm2d/pipeline/layernorm2d_fwd_traits.hpp"
#include "ck_tile/ops/common/generic_2d_block_shape.hpp"
#include "ck_tile/ops/common/load_interleaved_pk_type.hpp"
#include "ck_tile/ops/common/streamk_common.hpp"
#include "ck_tile/ops/common/tensor_layout.hpp"
#include "ck_tile/ops/common/utils.hpp"

2
include/ck_tile/ops/norm_reduce.hpp
View File

@@ -7,7 +7,5 @@
#include "ck_tile/ops/norm_reduce/block/block_norm_reduce_problem.hpp"
#include "ck_tile/ops/norm_reduce/thread/thread_welford.hpp"
#include "ck_tile/ops/common/generic_2d_block_shape.hpp"
#include "ck_tile/ops/common/load_interleaved_pk_type.hpp"
#include "ck_tile/ops/common/streamk_common.hpp"
#include "ck_tile/ops/common/tensor_layout.hpp"
#include "ck_tile/ops/common/utils.hpp"

2
include/ck_tile/ops/permute.hpp
View File

@@ -6,7 +6,5 @@
#include "ck_tile/ops/permute/kernel/generic_permute_kernel.hpp"
#include "ck_tile/ops/permute/pipeline/generic_petmute_problem.hpp"
#include "ck_tile/ops/common/generic_2d_block_shape.hpp"
#include "ck_tile/ops/common/load_interleaved_pk_type.hpp"
#include "ck_tile/ops/common/streamk_common.hpp"
#include "ck_tile/ops/common/tensor_layout.hpp"
#include "ck_tile/ops/common/utils.hpp"

2
include/ck_tile/ops/reduce.hpp
View File

@@ -11,7 +11,5 @@
#include "ck_tile/ops/reduce/pipeline/reduce2d_problem.hpp"
#include "ck_tile/ops/reduce/pipeline/reduce2d_shape.hpp"
#include "ck_tile/ops/common/generic_2d_block_shape.hpp"
#include "ck_tile/ops/common/load_interleaved_pk_type.hpp"
#include "ck_tile/ops/common/streamk_common.hpp"
#include "ck_tile/ops/common/tensor_layout.hpp"
#include "ck_tile/ops/common/utils.hpp"

2
include/ck_tile/ops/rmsnorm2d.hpp
View File

@@ -11,7 +11,5 @@
#include "ck_tile/ops/rmsnorm2d/pipeline/rmsnorm2d_fwd_pipeline_two_pass.hpp"
#include "ck_tile/ops/rmsnorm2d/pipeline/rmsnorm2d_fwd_traits.hpp"
#include "ck_tile/ops/common/generic_2d_block_shape.hpp"
#include "ck_tile/ops/common/load_interleaved_pk_type.hpp"
#include "ck_tile/ops/common/streamk_common.hpp"
#include "ck_tile/ops/common/tensor_layout.hpp"
#include "ck_tile/ops/common/utils.hpp"

2
include/ck_tile/ops/smoothquant.hpp
View File

@@ -10,7 +10,5 @@
#include "ck_tile/ops/smoothquant/pipeline/smoothquant_pipeline_problem.hpp"
#include "ck_tile/ops/smoothquant/pipeline/smoothquant_pipeline_two_pass.hpp"
#include "ck_tile/ops/common/generic_2d_block_shape.hpp"
#include "ck_tile/ops/common/load_interleaved_pk_type.hpp"
#include "ck_tile/ops/common/streamk_common.hpp"
#include "ck_tile/ops/common/tensor_layout.hpp"
#include "ck_tile/ops/common/utils.hpp"

2
include/ck_tile/ops/softmax.hpp
View File

@@ -6,7 +6,5 @@
#include "ck_tile/ops/softmax/block/block_softmax_2d.hpp"
#include "ck_tile/ops/softmax/block/block_softmax_2d_problem.hpp"
#include "ck_tile/ops/common/generic_2d_block_shape.hpp"
#include "ck_tile/ops/common/load_interleaved_pk_type.hpp"
#include "ck_tile/ops/common/streamk_common.hpp"
#include "ck_tile/ops/common/tensor_layout.hpp"
#include "ck_tile/ops/common/utils.hpp"

2
include/ck_tile/ops/topk.hpp
View File

@@ -6,7 +6,5 @@
#include "ck_tile/ops/topk/block/block_topk_stream_2d.hpp"
#include "ck_tile/ops/topk/block/block_topk_stream_2d_problem.hpp"
#include "ck_tile/ops/common/generic_2d_block_shape.hpp"
#include "ck_tile/ops/common/load_interleaved_pk_type.hpp"
#include "ck_tile/ops/common/streamk_common.hpp"
#include "ck_tile/ops/common/tensor_layout.hpp"
#include "ck_tile/ops/common/utils.hpp"

2
include/ck_tile/ops/topk_softmax.hpp
View File

@@ -8,7 +8,5 @@
#include "ck_tile/ops/topk_softmax/pipeline/topk_softmax_warp_per_row_policy.hpp"
#include "ck_tile/ops/topk_softmax/pipeline/topk_softmax_warp_per_row_problem.hpp"
#include "ck_tile/ops/common/generic_2d_block_shape.hpp"
#include "ck_tile/ops/common/load_interleaved_pk_type.hpp"
#include "ck_tile/ops/common/streamk_common.hpp"
#include "ck_tile/ops/common/tensor_layout.hpp"
#include "ck_tile/ops/common/utils.hpp"

6
include/ck_tile/utility.hpp
View File

@@ -1,6 +0,0 @@
// SPDX-License-Identifier: MIT
// Copyright (c) 2018-2025, Advanced Micro Devices, Inc. All rights reserved.
#pragma once
#include "ck_tile/utility/json_dump.hpp"