-
Notifications
You must be signed in to change notification settings - Fork 858
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Merge pull request #1909 from hjelmn/threads
Fix performance regression caused by enabling opal thread support
- Loading branch information
Showing
4 changed files
with
181 additions
and
155 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,174 @@ | ||
/* -*- Mode: C; c-basic-offset:4 ; indent-tabs-mode:nil -*- */ | ||
/* | ||
* Copyright (c) 2004-2005 The Trustees of Indiana University and Indiana | ||
* University Research and Technology | ||
* Corporation. All rights reserved. | ||
* Copyright (c) 2004-2007 The University of Tennessee and The University | ||
* of Tennessee Research Foundation. All rights | ||
* reserved. | ||
* Copyright (c) 2004-2006 High Performance Computing Center Stuttgart, | ||
* University of Stuttgart. All rights reserved. | ||
* Copyright (c) 2004-2005 The Regents of the University of California. | ||
* All rights reserved. | ||
* Copyright (c) 2007-2014 Cisco Systems, Inc. All rights reserved. | ||
* Copyright (c) 2014 Research Organization for Information Science | ||
* and Technology (RIST). All rights reserved. | ||
* Copyright (c) 2015-2016 Los Alamos National Security, LLC. All rights | ||
* reserved. | ||
* $COPYRIGHT$ | ||
* | ||
* Additional copyrights may follow | ||
* | ||
* $HEADER$ | ||
*/ | ||
|
||
#if !defined(OPAL_THREAD_USAGE_H) | ||
#define OPAL_THREAD_USAGE_H | ||
|
||
#include "opal_config.h" | ||
|
||
#include "opal/sys/atomic.h" | ||
#include "opal/prefetch.h" | ||
|
||
OPAL_DECLSPEC extern bool opal_uses_threads; | ||
|
||
/** | ||
* Check and see if the process is using multiple threads. | ||
* | ||
* @retval true If the process may have more than one thread. | ||
* @retval false If the process only has a single thread. | ||
* | ||
* The value that this function returns is influenced by: | ||
* | ||
* - how MPI_INIT or MPI_INIT_THREAD was invoked, | ||
* - what the final MPI thread level was determined to be, | ||
* - whether the OMPI or MPI libraries are multi-threaded | ||
* | ||
* MPI_INIT and MPI_INIT_THREAD (specifically, back-end OMPI startup | ||
* functions) invoke opal_set_using_threads() to influence the value of | ||
* this function, depending on their situation. Some examples: | ||
* | ||
* - if MPI_INIT is invoked, and the ompi components in use are | ||
* single-threaded, this value will be false. | ||
* | ||
* - if MPI_INIT_THREAD is invoked with MPI_THREAD_MULTIPLE, we have | ||
* thread support, and the final thread level is determined to be | ||
* MPI_THREAD_MULTIPLE, this value will be true. | ||
* | ||
* - if the process is a single-threaded OMPI executable (e.g., mpicc), | ||
* this value will be false. | ||
* | ||
* Hence, this function will return false if there is guaranteed to | ||
* only be one thread in the process. If there is even the | ||
* possibility that we may have multiple threads, true will be | ||
* returned. | ||
*/ | ||
#define opal_using_threads() opal_uses_threads | ||
|
||
/** | ||
* Set whether the process is using multiple threads or not. | ||
* | ||
* @param have Boolean indicating whether the process is using | ||
* multiple threads or not. | ||
* | ||
* @retval opal_using_threads The new return value from | ||
* opal_using_threads(). | ||
* | ||
* This function is used to influence the return value of | ||
* opal_using_threads(). If configure detected that we have thread | ||
* support, the return value of future invocations of | ||
* opal_using_threads() will be the parameter's value. If configure | ||
* detected that we have no thread support, then the retuen from | ||
* opal_using_threads() will always be false. | ||
*/ | ||
static inline bool opal_set_using_threads(bool have) | ||
{ | ||
opal_uses_threads = have; | ||
return opal_using_threads(); | ||
} | ||
|
||
|
||
/** | ||
* Use an atomic operation for increment/decrement if opal_using_threads() | ||
* indicates that threads are in use by the application or library. | ||
*/ | ||
|
||
static inline int32_t | ||
OPAL_THREAD_ADD32(volatile int32_t *addr, int delta) | ||
{ | ||
int32_t ret; | ||
|
||
if (OPAL_UNLIKELY(opal_using_threads())) { | ||
ret = opal_atomic_add_32(addr, delta); | ||
} else { | ||
ret = (*addr += delta); | ||
} | ||
|
||
return ret; | ||
} | ||
|
||
#if OPAL_HAVE_ATOMIC_MATH_64 | ||
static inline int64_t | ||
OPAL_THREAD_ADD64(volatile int64_t *addr, int delta) | ||
{ | ||
int64_t ret; | ||
|
||
if (OPAL_UNLIKELY(opal_using_threads())) { | ||
ret = opal_atomic_add_64(addr, delta); | ||
} else { | ||
ret = (*addr += delta); | ||
} | ||
|
||
return ret; | ||
} | ||
#endif | ||
|
||
static inline size_t | ||
OPAL_THREAD_ADD_SIZE_T(volatile size_t *addr, int delta) | ||
{ | ||
size_t ret; | ||
|
||
if (OPAL_UNLIKELY(opal_using_threads())) { | ||
ret = opal_atomic_add_size_t(addr, delta); | ||
} else { | ||
ret = (*addr += delta); | ||
} | ||
|
||
return ret; | ||
} | ||
|
||
/* BWB: FIX ME: remove if possible */ | ||
#define OPAL_CMPSET(x, y, z) ((*(x) == (y)) ? ((*(x) = (z)), 1) : 0) | ||
|
||
#if OPAL_HAVE_ATOMIC_CMPSET_32 | ||
#define OPAL_ATOMIC_CMPSET_32(x, y, z) \ | ||
(opal_using_threads() ? opal_atomic_cmpset_32(x, y, z) : OPAL_CMPSET(x, y, z)) | ||
#endif | ||
#if OPAL_HAVE_ATOMIC_CMPSET_64 | ||
#define OPAL_ATOMIC_CMPSET_64(x, y, z) \ | ||
(opal_using_threads() ? opal_atomic_cmpset_64(x, y, z) : OPAL_CMPSET(x, y, z)) | ||
#endif | ||
#if OPAL_HAVE_ATOMIC_CMPSET_32 || OPAL_HAVE_ATOMIC_CMPSET_64 | ||
#define OPAL_ATOMIC_CMPSET(x, y, z) \ | ||
(opal_using_threads() ? opal_atomic_cmpset(x, y, z) : OPAL_CMPSET(x, y, z)) | ||
#endif | ||
#if OPAL_HAVE_ATOMIC_CMPSET_32 || OPAL_HAVE_ATOMIC_CMPSET_64 | ||
#define OPAL_ATOMIC_CMPSET_PTR(x, y, z) \ | ||
(opal_using_threads() ? opal_atomic_cmpset_ptr(x, y, z) : OPAL_CMPSET(x, y, z)) | ||
#endif | ||
|
||
static inline void *opal_thread_swap_ptr (volatile void *ptr, void *newvalue) | ||
{ | ||
if (opal_using_threads ()) { | ||
return opal_atomic_swap_ptr (ptr, newvalue); | ||
} | ||
|
||
void *old = ((void **) ptr)[0]; | ||
((void **) ptr)[0] = newvalue; | ||
|
||
return old; | ||
} | ||
|
||
#define OPAL_ATOMIC_SWAP_PTR(x, y) opal_thread_swap_ptr (x, y) | ||
|
||
#endif /* !defined(OPAL_THREAD_USAGE_H) */ |