Hendrik/xgboost
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

remove is_bootstrap parameter (#102)

Browse Source 
* apply openmp simd

* clean __buildin detection, moving windows build check from xgboost project, add openmp support for vectorize reduce

* apply openmp only to rabit

* orgnize rabit signature

* remove is_bootstrap, use load_checkpoint as implict flag

* visual studio don't support latest openmp

* orgnize omp declarations

* replace memory copy with vector cast

* Revert "replace memory copy with vector cast"

This reverts commit 28de4792dcdff40d83d458510d23b7ef0b191d79.

* Revert "orgnize omp declarations"

This reverts commit 31341233d31ce93ccf34d700262b1f3f6690bbfe.

* remove openmp settings, merge into a upcoming pr

* mis

* per feedback, update comments
This commit is contained in:
Chen Qin
2019-09-10 11:45:50 -07:00
committed by Nan Zhu
parent 5797dcb64e
commit 9a7ac85d7e
13 changed files with 56 additions and 137 deletions
Download Patch File Download Diff File Expand all files Collapse all files

36
include/rabit/internal/engine.h
View File

@@ -9,39 +9,15 @@
#include <string>
#include "../serializable.h"
// keeps rabit api caller signature
#ifndef RABIT_API_CALLER_SIGNATURE
#define RABIT_API_CALLER_SIGNATURE
#ifdef __has_builtin
#if __has_builtin(__builtin_FILE)
#if (defined(__GNUC__) && !defined(__clang__))
#define _FILE __builtin_FILE()
#else
#define _FILE "N/A"
#endif // __has_builtin(__builtin_FILE)
#if __has_builtin(__builtin_LINE)
#define _LINE __builtin_LINE()
#else
#define _LINE -1
#endif // __has_builtin(__builtin_LINE)
#if __has_builtin(__builtin_FUNCTION)
#define _CALLER __builtin_FUNCTION()
#else
#define _CALLER "N/A"
#endif // __has_builtin(__builtin_FUNCTION)
#else
#define _FILE "N/A"
#define _LINE -1
#define _CALLER "N/A"
#endif // __has_builtin
#endif // RABIT_API_CALLER_SIGNATURE
#endif // (defined(__GNUC__) && !defined(__clang__))
namespace MPI {
/*! \brief MPI data type just to be compatible with MPI reduce function*/
@@ -88,7 +64,6 @@ class IEngine {
* will be called by the function before performing Allreduce in order to initialize the data in sendrecvbuf.
* If the result of Allreduce can be recovered directly, then prepare_func will NOT be called
* \param prepare_arg argument used to pass into the lazy preprocessing function
* \param is_bootstrap if this allreduce is needed to bootstrap failed node
* \param _file caller file name used to generate unique cache key
* \param _line caller line number used to generate unique cache key
* \param _caller caller function name used to generate unique cache key
@@ -99,7 +74,6 @@ class IEngine {
ReduceFunction reducer,
PreprocFunction prepare_fun = NULL,
void *prepare_arg = NULL,
bool is_bootstrap = false,
const char* _file = _FILE,
const int _line = _LINE,
const char* _caller = _CALLER) = 0;
@@ -108,13 +82,11 @@ class IEngine {
* \param sendrecvbuf_ buffer for both sending and receiving data
* \param size the size of the data to be broadcasted
* \param root the root worker id to broadcast the data
* \param is_bootstrap if this broadcast is needed to bootstrap failed node
* \param _file caller file name used to generate unique cache key
* \param _line caller line number used to generate unique cache key
* \param _caller caller function name used to generate unique cache key
*/
virtual void Broadcast(void *sendrecvbuf_, size_t size, int root,
bool is_bootstrap = false,
const char* _file = _FILE,
const int _line = _LINE,
const char* _caller = _CALLER) = 0;
@@ -254,7 +226,6 @@ enum DataType {
* will be called by the function before performing Allreduce, to initialize the data in sendrecvbuf_.
* If the result of Allreduce can be recovered directly, then prepare_func will NOT be called
* \param prepare_arg argument used to pass into the lazy preprocessing function.
* \param is_bootstrap if this allreduce is needed to bootstrap failed node
* \param _file caller file name used to generate unique cache key
* \param _line caller line number used to generate unique cache key
* \param _caller caller function name used to generate unique cache key
@@ -267,7 +238,6 @@ void Allreduce_(void *sendrecvbuf,
mpi::OpType op,
IEngine::PreprocFunction prepare_fun = NULL,
void *prepare_arg = NULL,
bool is_bootstrap = false,
const char* _file = _FILE,
const int _line = _LINE,
const char* _caller = _CALLER);
@@ -296,7 +266,6 @@ class ReduceHandle {
* will be called by the function before performing Allreduce in order to initialize the data in sendrecvbuf_.
* If the result of Allreduce can be recovered directly, then prepare_func will NOT be called
* \param prepare_arg argument used to pass into the lazy preprocessing function
* \param is_bootstrap if this allreduce is needed to bootstrap failed node
* \param _file caller file name used to generate unique cache key
* \param _line caller line number used to generate unique cache key
* \param _caller caller function name used to generate unique cache key
@@ -306,7 +275,6 @@ class ReduceHandle {
size_t count,
IEngine::PreprocFunction prepare_fun = NULL,
void *prepare_arg = NULL,
bool is_bootstrap = false,
const char* _file = _FILE,
const int _line = _LINE,
const char* _caller = _CALLER);

43
include/rabit/internal/rabit-inl.h
View File

@@ -94,10 +94,9 @@ struct BitOR {
};
template<typename OP, typename DType>
inline void Reducer(const void *src_, void *dst_, int len, const MPI::Datatype &dtype) {
const DType *src = (const DType*)src_;
DType *dst = (DType*)dst_; // NOLINT(*)
for (int i = 0; i < len; ++i) {
const DType* src = (const DType*)src_;
DType* dst = (DType*)dst_; // NOLINT(*)
for (int i = 0; i < len; i++) {
OP::Reduce(dst[i], src[i]);
}
}
@@ -129,42 +128,39 @@ inline std::string GetProcessorName(void) {
}
// broadcast data to all other nodes from root
inline void Broadcast(void *sendrecv_data, size_t size, int root,
bool is_bootstrap,
const char* _file,
const int _line,
const char* _caller) {
engine::GetEngine()->Broadcast(sendrecv_data, size, root,
is_bootstrap, _file, _line, _caller);
_file, _line, _caller);
}
template<typename DType>
inline void Broadcast(std::vector<DType> *sendrecv_data, int root,
bool is_bootstrap,
const char* _file,
const int _line,
const char* _caller) {
size_t size = sendrecv_data->size();
Broadcast(&size, sizeof(size), root, is_bootstrap, _file, _line, _caller);
Broadcast(&size, sizeof(size), root, _file, _line, _caller);
if (sendrecv_data->size() != size) {
sendrecv_data->resize(size);
}
if (size != 0) {
Broadcast(&(*sendrecv_data)[0], size * sizeof(DType), root,
is_bootstrap, _file, _line, _caller);
_file, _line, _caller);
}
}
inline void Broadcast(std::string *sendrecv_data, int root,
bool is_bootstrap,
const char* _file,
const int _line,
const char* _caller) {
size_t size = sendrecv_data->length();
Broadcast(&size, sizeof(size), root, is_bootstrap, _file, _line, _caller);
Broadcast(&size, sizeof(size), root, _file, _line, _caller);
if (sendrecv_data->length() != size) {
sendrecv_data->resize(size);
}
if (size != 0) {
Broadcast(&(*sendrecv_data)[0], size * sizeof(char), root,
is_bootstrap, _file, _line, _caller);
_file, _line, _caller);
}
}
@@ -173,13 +169,12 @@ template<typename OP, typename DType>
inline void Allreduce(DType *sendrecvbuf, size_t count,
void (*prepare_fun)(void *arg),
void *prepare_arg,
bool is_bootstrap,
const char* _file,
const int _line,
const char* _caller) {
engine::Allreduce_(sendrecvbuf, sizeof(DType), count, op::Reducer<OP, DType>,
engine::mpi::GetType<DType>(), OP::kType, prepare_fun, prepare_arg,
is_bootstrap, _file, _line, _caller);
_file, _line, _caller);
}
// C++11 support for lambda prepare function
@@ -190,13 +185,12 @@ inline void InvokeLambda_(void *fun) {
template<typename OP, typename DType>
inline void Allreduce(DType *sendrecvbuf, size_t count,
std::function<void()> prepare_fun,
bool is_bootstrap,
const char* _file,
const int _line,
const char* _caller) {
engine::Allreduce_(sendrecvbuf, sizeof(DType), count, op::Reducer<OP, DType>,
engine::mpi::GetType<DType>(), OP::kType, InvokeLambda_, &prepare_fun,
is_bootstrap, _file, _line, _caller);
_file, _line, _caller);
}
#endif // C++11
@@ -244,11 +238,12 @@ inline void ReducerSafe_(const void *src_, void *dst_, int len_, const MPI::Data
const size_t kUnit = sizeof(DType);
const char *psrc = reinterpret_cast<const char*>(src_);
char *pdst = reinterpret_cast<char*>(dst_);
for (int i = 0; i < len_; ++i) {
DType tdst, tsrc;
// use memcpy to avoid alignment issue
std::memcpy(&tdst, pdst + i * kUnit, sizeof(tdst));
std::memcpy(&tsrc, psrc + i * kUnit, sizeof(tsrc));
std::memcpy(&tdst, pdst + (i * kUnit), sizeof(tdst));
std::memcpy(&tsrc, psrc + (i * kUnit), sizeof(tsrc));
freduce(tdst, tsrc);
std::memcpy(pdst + i * kUnit, &tdst, sizeof(tdst));
}
@@ -276,12 +271,11 @@ template<typename DType, void (*freduce)(DType &dst, const DType &src)> // NOLIN
inline void Reducer<DType, freduce>::Allreduce(DType *sendrecvbuf, size_t count,
void (*prepare_fun)(void *arg),
void *prepare_arg,
bool is_bootstrap,
const char* _file,
const int _line,
const char* _caller) {
handle_.Allreduce(sendrecvbuf, sizeof(DType), count, prepare_fun,
prepare_arg, is_bootstrap, _file, _line, _caller);
prepare_arg, _file, _line, _caller);
}
// function to perform reduction for SerializeReducer
template<typename DType>
@@ -330,7 +324,6 @@ inline void SerializeReducer<DType>::Allreduce(DType *sendrecvobj,
size_t max_nbyte, size_t count,
void (*prepare_fun)(void *arg),
void *prepare_arg,
bool is_bootstrap,
const char* _file,
const int _line,
const char* _caller) {
@@ -342,7 +335,7 @@ inline void SerializeReducer<DType>::Allreduce(DType *sendrecvobj,
// invoke here
handle_.Allreduce(BeginPtr(buffer_), max_nbyte, count,
SerializeReduceClosure<DType>::Invoke, &c,
is_bootstrap, _file, _line, _caller);
_file, _line, _caller);
for (size_t i = 0; i < count; ++i) {
utils::MemoryFixSizeBuffer fs(BeginPtr(buffer_) + i * max_nbyte, max_nbyte);
sendrecvobj[i].Load(fs);
@@ -353,23 +346,21 @@ inline void SerializeReducer<DType>::Allreduce(DType *sendrecvobj,
template<typename DType, void (*freduce)(DType &dst, const DType &src)> // NOLINT(*)g
inline void Reducer<DType, freduce>::Allreduce(DType *sendrecvbuf, size_t count,
std::function<void()> prepare_fun,
bool is_bootstrap,
const char* _file,
const int _line,
const char* _caller) {
this->Allreduce(sendrecvbuf, count, InvokeLambda_, &prepare_fun,
is_bootstrap, _file, _line, _caller);
_file, _line, _caller);
}
template<typename DType>
inline void SerializeReducer<DType>::Allreduce(DType *sendrecvobj,
size_t max_nbytes, size_t count,
std::function<void()> prepare_fun,
bool is_bootstrap,
const char* _file,
const int _line,
const char* _caller) {
this->Allreduce(sendrecvobj, max_nbytes, count, InvokeLambda_, &prepare_fun,
is_bootstrap, _file, _line, _caller);
_file, _line, _caller);
}
#endif // DMLC_USE_CXX11
} // namespace rabit