Clean up conv example, Instances, profiler and test (#324)

* convnd_fwd fp16 example

* update example

* update example

* update instance

* updating refernce conv

* update reference conv

* update conv fwd profiler

* update conv 1d and 3d instance

* update include path

* clean

* update profiler for conv bwd data and weight

* update conv bwd weight

* clean

* update conv example

* update profiler for conv bwd weight

* update ckprofiler for conv bwd data

* fix reference conv bwd data bug; update conv bwd data test

* update examples

* fix initialization issue

* update test for conv fwd

* clean

* clean

* remove test case too sensitive to error threshhold

* fix test

* clean

* fix build

* adding conv multiple d

* adding conv multiple D

* add matrix padder

* add gemm padding to convnd

* adding group conv

* update gemm multi-d

* refactor

* refactor

* refactor

* clean

* clean

* refactor

* refactor

* reorg

* add ds

* add bias

* clean

* add G

* adding group

* adding group

* adding group

* update Tensor

* clean

* update example

* update DeviceGemmMultipleD_Xdl_CShuffle

* update conv bwd-data and bwd-weight

* upate contraction example

* update gemm and batch gemm with e permute

* fix example build

* instance for grouped conv1d

* update example

* adding group conv instance

* update gemm bilinear instance

* update gemm+add+add+fastgelu instance

* update profiler

* update profiler

* update test

* update test and client example

* clean

* add grouped conv into profiler

* update profiler

* clean

* add test grouped conv, update all conv test to gtest

* update test
This commit is contained in:
Chao Liu
2022-07-29 18:19:25 -05:00
committed by GitHub
parent 85978e0201
commit 500fa99512
373 changed files with 17544 additions and 17013 deletions

View File

@@ -9,9 +9,9 @@
#include "ck/tensor_operation/gpu/device/device_binary_elementwise.hpp"
#include "ck/library/utility/check_err.hpp"
#include "ck/library/host_tensor/device_memory.hpp"
#include "ck/library/host_tensor/host_tensor.hpp"
#include "ck/library/host_tensor/host_tensor_generator.hpp"
#include "ck/library/utility/device_memory.hpp"
#include "ck/library/utility/host_tensor.hpp"
#include "ck/library/utility/host_tensor_generator.hpp"
using F16 = ck::half_t;
using F32 = float;
@@ -92,9 +92,9 @@ int main()
a_m_n.GenerateTensorValue(GeneratorTensor_3<ABDataType>{0.0, 1.0});
b_n.GenerateTensorValue(GeneratorTensor_3<ABDataType>{0.0, 1.0});
DeviceMem a_m_n_device_buf(sizeof(ABDataType) * a_m_n.mDesc.GetElementSpace());
DeviceMem b_n_device_buf(sizeof(ABDataType) * b_n.mDesc.GetElementSpace());
DeviceMem c_m_n_device_buf(sizeof(CDataType) * c_m_n.mDesc.GetElementSpace());
DeviceMem a_m_n_device_buf(sizeof(ABDataType) * a_m_n.mDesc.GetElementSpaceSize());
DeviceMem b_n_device_buf(sizeof(ABDataType) * b_n.mDesc.GetElementSpaceSize());
DeviceMem c_m_n_device_buf(sizeof(CDataType) * c_m_n.mDesc.GetElementSpaceSize());
a_m_n_device_buf.ToDevice(a_m_n.mData.data());
b_n_device_buf.ToDevice(b_n.mData.data());

View File

@@ -9,9 +9,9 @@
#include "ck/tensor_operation/gpu/device/device_binary_elementwise.hpp"
#include "ck/library/utility/check_err.hpp"
#include "ck/library/host_tensor/device_memory.hpp"
#include "ck/library/host_tensor/host_tensor.hpp"
#include "ck/library/host_tensor/host_tensor_generator.hpp"
#include "ck/library/utility/device_memory.hpp"
#include "ck/library/utility/host_tensor.hpp"
#include "ck/library/utility/host_tensor_generator.hpp"
using F16 = ck::half_t;
using F32 = float;
@@ -74,9 +74,9 @@ int main()
a_m.GenerateTensorValue(GeneratorTensor_3<ABDataType>{0.0, 1.0});
b_m_n_k.GenerateTensorValue(GeneratorTensor_3<ABDataType>{0.0, 1.0});
DeviceMem a_m_device_buf(sizeof(ABDataType) * a_m.mDesc.GetElementSpace());
DeviceMem b_m_n_k_device_buf(sizeof(ABDataType) * b_m_n_k.mDesc.GetElementSpace());
DeviceMem c_m_n_k_device_buf(sizeof(CDataType) * c_m_n_k.mDesc.GetElementSpace());
DeviceMem a_m_device_buf(sizeof(ABDataType) * a_m.mDesc.GetElementSpaceSize());
DeviceMem b_m_n_k_device_buf(sizeof(ABDataType) * b_m_n_k.mDesc.GetElementSpaceSize());
DeviceMem c_m_n_k_device_buf(sizeof(CDataType) * c_m_n_k.mDesc.GetElementSpaceSize());
a_m_device_buf.ToDevice(a_m.mData.data());
b_m_n_k_device_buf.ToDevice(b_m_n_k.mData.data());

View File

@@ -8,9 +8,9 @@
#include "ck/tensor_operation/gpu/device/device_binary_elementwise.hpp"
#include "ck/tensor_operation/gpu/element/binary_element_wise_operation.hpp"
#include "ck/library/utility/check_err.hpp"
#include "ck/library/host_tensor/device_memory.hpp"
#include "ck/library/host_tensor/host_tensor.hpp"
#include "ck/library/host_tensor/host_tensor_generator.hpp"
#include "ck/library/utility/device_memory.hpp"
#include "ck/library/utility/host_tensor.hpp"
#include "ck/library/utility/host_tensor_generator.hpp"
using F16 = ck::half_t;
using F32 = float;
@@ -72,9 +72,9 @@ int main()
a_m.GenerateTensorValue(GeneratorTensor_3<ABDataType>{0.0, 1.0});
b_m.GenerateTensorValue(GeneratorTensor_3<ABDataType>{0.0, 1.0});
DeviceMem a_m_device_buf(sizeof(ABDataType) * a_m.mDesc.GetElementSpace());
DeviceMem b_m_device_buf(sizeof(ABDataType) * b_m.mDesc.GetElementSpace());
DeviceMem c_m_device_buf(sizeof(CDataType) * c_m.mDesc.GetElementSpace());
DeviceMem a_m_device_buf(sizeof(ABDataType) * a_m.mDesc.GetElementSpaceSize());
DeviceMem b_m_device_buf(sizeof(ABDataType) * b_m.mDesc.GetElementSpaceSize());
DeviceMem c_m_device_buf(sizeof(CDataType) * c_m.mDesc.GetElementSpaceSize());
a_m_device_buf.ToDevice(a_m.mData.data());
b_m_device_buf.ToDevice(b_m.mData.data());

View File

@@ -9,9 +9,9 @@
#include "ck/tensor_operation/gpu/device/device_binary_elementwise.hpp"
#include "ck/library/utility/check_err.hpp"
#include "ck/library/host_tensor/device_memory.hpp"
#include "ck/library/host_tensor/host_tensor.hpp"
#include "ck/library/host_tensor/host_tensor_generator.hpp"
#include "ck/library/utility/device_memory.hpp"
#include "ck/library/utility/host_tensor.hpp"
#include "ck/library/utility/host_tensor_generator.hpp"
using F16 = ck::half_t;
using F32 = float;
@@ -74,9 +74,9 @@ int main()
a.GenerateTensorValue(GeneratorTensor_3<ABDataType>{0.0, 1.0});
b.GenerateTensorValue(GeneratorTensor_3<ABDataType>{0.0, 1.0});
DeviceMem a_device_buf(sizeof(ABDataType) * a.mDesc.GetElementSpace());
DeviceMem b_device_buf(sizeof(ABDataType) * b.mDesc.GetElementSpace());
DeviceMem c_device_buf(sizeof(CDataType) * c.mDesc.GetElementSpace());
DeviceMem a_device_buf(sizeof(ABDataType) * a.mDesc.GetElementSpaceSize());
DeviceMem b_device_buf(sizeof(ABDataType) * b.mDesc.GetElementSpaceSize());
DeviceMem c_device_buf(sizeof(CDataType) * c.mDesc.GetElementSpaceSize());
a_device_buf.ToDevice(a.mData.data());
b_device_buf.ToDevice(b.mData.data());