User API + reorganized lib folders (#30)
* User API + reorganized lib folders
- omnitrace_user_start_trace
- omnitrace_user_stop_trace
- omnitrace_user_start_thread_trace
- omnitrace_user_stop_thread_trace
- omnitrace_user_push_region
- omnitrace_user_pop_region
* New OpenMP examples/tests
* Fix to KokkosP
* OMPT support
- fixed omnitrace instrumenting reporting
- common invoke improvements
- component::user_region
* exclude kmp_threadprivate_
* Separate omnitrace into multiple files
* PTL and timemory submodule updates
* Active guards + USE_OMPT guards in omnitrace-dl
* Tweak transpose default iterations
* omnitrace-precommit build target
* Omnitrace exe restructuring pt 2
- Never instrument functions with less than 4 instructions
- Never instrument ompt_start_tool or nanosleep
- module_function serializes heuristics
- removed hash stuff from omnitrace
- removed instr_procedures lambda
- WAITPID_DEBUG_MESSAGE
* set_state, "_hidden" fix, CI exceptions, backtrace fix
- set_state function
- fixed "_hidden" from appearing in print macros using __FUNCTION__
- OMNITRACE_CI_THROW
- more CI checks in library
- fixed backtrace init value sample issue being ignored
* Tweaks to OMPT tests
* cmake-formatting
* Removed debug output from backtrace processing
* Fix warnings and verbosity
* omnitrace-dl fix for libomp
* omnitrace-avail fixes
- remove second omnitrace_init_library call
- fix -r option not working
* Additional testing
- source/bin/tests
- tests for omnitrace-exe
- tests for omnitrace-avail
* cmake-format
* Reduce runtime of openmp-lu
* Update openmp-lu and tests timeout
* openmp-lu and CI tweaks
- decrease iterations
- OMP_NUM_THREADS=2
- install clang and libomp-dev in linux-ci
- fix data-files in linux-ci
[ROCm/rocprofiler-systems commit: d80752bc69]
This commit is contained in:
committed by
GitHub
parent
a23bf28aaa
commit
083035dd8b
@@ -7,6 +7,8 @@ set(CMAKE_CXX_VISIBILITY_PRESET "default")
|
||||
|
||||
add_subdirectory(transpose)
|
||||
add_subdirectory(parallel-overhead)
|
||||
add_subdirectory(user-api)
|
||||
add_subdirectory(openmp)
|
||||
|
||||
option(BUILD_SHARED_LIBS "Build dynamic libraries" ON)
|
||||
|
||||
|
||||
@@ -55,17 +55,3 @@ if(NOT CMAKE_PROJECT_NAME STREQUAL PROJECT_NAME)
|
||||
set_target_properties(${PROJECT_NAME} PROPERTIES RUNTIME_OUTPUT_DIRECTORY
|
||||
${CMAKE_BINARY_DIR})
|
||||
endif()
|
||||
|
||||
enable_testing()
|
||||
if(LULESH_USE_MPI)
|
||||
add_test(
|
||||
NAME lulesh
|
||||
COMMAND ${MPIEXEC_EXECUTABLE} ${MPIEXEC_NUMPROC_FLAG} 8
|
||||
$<TARGET_FILE:${PROJECT_NAME}> -i 100 -s 20 -p
|
||||
WORKING_DIRECTORY ${PROJECT_BINARY_DIR})
|
||||
else()
|
||||
add_test(
|
||||
NAME lulesh
|
||||
COMMAND $<TARGET_FILE:${PROJECT_NAME}> -i 100 -s 20 -p
|
||||
WORKING_DIRECTORY ${PROJECT_BINARY_DIR})
|
||||
endif()
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
@@ -0,0 +1,23 @@
|
||||
/* CLASS = B */
|
||||
/*
|
||||
c This file is generated automatically by the setparams utility.
|
||||
c It sets the number of processors and the class_npb of the NPB
|
||||
c in this directory. Do not modify it by hand.
|
||||
*/
|
||||
#define NA 75000
|
||||
#define NONZER 13
|
||||
#define NITER 75
|
||||
#define SHIFT 60.0
|
||||
#define RCOND 1.0e-1
|
||||
#define CONVERTDOUBLE FALSE
|
||||
#define COMPILETIME "01 Mar 2022"
|
||||
#define NPBVERSION "4.1"
|
||||
#define LIBVERSION "201511"
|
||||
#define COMPILERVERSION "11.1.0"
|
||||
#define CS1 "g++ -std=c++14"
|
||||
#define CS2 "$(CC)"
|
||||
#define CS3 "-lm"
|
||||
#define CS4 "-I../common "
|
||||
#define CS5 "-O3 -fopenmp -mcmodel=medium"
|
||||
#define CS6 "-O3 -fopenmp -mcmodel=medium"
|
||||
#define CS7 "randdp"
|
||||
@@ -0,0 +1,27 @@
|
||||
set(CMAKE_RUNTIME_OUTPUT_DIRECTORY ${CMAKE_BINARY_DIR})
|
||||
set(CMAKE_LIBRARY_OUTPUT_DIRECTORY ${CMAKE_BINARY_DIR})
|
||||
set(CMAKE_ARCHIVE_OUTPUT_DIRECTORY ${CMAKE_BINARY_DIR})
|
||||
|
||||
file(GLOB common_source ${CMAKE_CURRENT_SOURCE_DIR}/common/*.cpp)
|
||||
add_library(openmp-common OBJECT ${common_source})
|
||||
target_include_directories(openmp-common PUBLIC ${CMAKE_CURRENT_SOURCE_DIR}/common)
|
||||
|
||||
add_executable(openmp-cg ${CMAKE_CURRENT_SOURCE_DIR}/CG/cg.cpp
|
||||
$<TARGET_OBJECTS:openmp-common>)
|
||||
add_executable(openmp-lu ${CMAKE_CURRENT_SOURCE_DIR}/LU/lu.cpp
|
||||
$<TARGET_OBJECTS:openmp-common>)
|
||||
|
||||
find_program(CLANGXX_EXECUTABLE NAMES clang++)
|
||||
if(CLANGXX_EXECUTABLE)
|
||||
target_compile_options(openmp-common PUBLIC -W -Wall -fopenmp=libomp)
|
||||
target_compile_options(openmp-cg PRIVATE -W -Wall -fopenmp=libomp)
|
||||
target_link_libraries(openmp-cg PRIVATE omp)
|
||||
target_compile_options(openmp-lu PRIVATE -W -Wall -fopenmp=libomp)
|
||||
target_link_libraries(openmp-lu PRIVATE omp)
|
||||
omnitrace_custom_compilation(COMPILER ${CLANGXX_EXECUTABLE} TARGET openmp-common)
|
||||
omnitrace_custom_compilation(COMPILER ${CLANGXX_EXECUTABLE} TARGET openmp-cg)
|
||||
omnitrace_custom_compilation(COMPILER ${CLANGXX_EXECUTABLE} TARGET openmp-lu)
|
||||
else()
|
||||
find_package(OpenMP REQUIRED)
|
||||
target_link_libraries(openmp-common PUBLIC OpenMP::OpenMP_CXX)
|
||||
endif()
|
||||
File diff suppressed because it is too large
Load Diff
@@ -0,0 +1,27 @@
|
||||
/* CLASS = W */
|
||||
/*
|
||||
c This file is generated automatically by the setparams utility.
|
||||
c It sets the number of processors and the class_npb of the NPB
|
||||
c in this directory. Do not modify it by hand.
|
||||
*/
|
||||
|
||||
/* full problem size */
|
||||
#define ISIZ1 25
|
||||
#define ISIZ2 25
|
||||
#define ISIZ3 25
|
||||
/* number of iterations and how often to print the norm */
|
||||
#define ITMAX_DEFAULT 150
|
||||
#define INORM_DEFAULT 150
|
||||
#define DT_DEFAULT 1.5e-3
|
||||
#define CONVERTDOUBLE FALSE
|
||||
#define COMPILETIME "07 Mar 2022"
|
||||
#define NPBVERSION "4.1"
|
||||
#define LIBVERSION "201511"
|
||||
#define COMPILERVERSION "11.1.0"
|
||||
#define CS1 "g++ -std=c++14"
|
||||
#define CS2 "$(CC)"
|
||||
#define CS3 "-lm"
|
||||
#define CS4 "-I../common "
|
||||
#define CS5 "-O3 -fopenmp -mcmodel=medium"
|
||||
#define CS6 "-O3 -fopenmp -mcmodel=medium"
|
||||
#define CS7 "randdp"
|
||||
@@ -0,0 +1,159 @@
|
||||
/*
|
||||
MIT License
|
||||
|
||||
Copyright (c) 2021 Parallel Applications Modelling Group - GMAP
|
||||
GMAP website: https://gmap.pucrs.br
|
||||
|
||||
Pontifical Catholic University of Rio Grande do Sul (PUCRS)
|
||||
Av. Ipiranga, 6681, Porto Alegre - Brazil, 90619-900
|
||||
|
||||
Permission is hereby granted, free of charge, to any person obtaining a copy
|
||||
of this software and associated documentation files (the "Software"), to deal
|
||||
in the Software without restriction, including without limitation the rights
|
||||
to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
|
||||
copies of the Software, and to permit persons to whom the Software is
|
||||
furnished to do so, subject to the following conditions:
|
||||
|
||||
The above copyright notice and this permission notice shall be included in all
|
||||
copies or substantial portions of the Software.
|
||||
|
||||
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
|
||||
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
|
||||
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
|
||||
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
|
||||
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
|
||||
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
|
||||
SOFTWARE.
|
||||
|
||||
------------------------------------------------------------------------------
|
||||
|
||||
The original NPB 3.4.1 version was written in Fortran and belongs to:
|
||||
http://www.nas.nasa.gov/Software/NPB/
|
||||
|
||||
------------------------------------------------------------------------------
|
||||
|
||||
The serial C++ version is a translation of the original NPB 3.4.1
|
||||
Serial C++ version: https://github.com/GMAP/NPB-CPP/tree/master/NPB-SER
|
||||
|
||||
Authors of the C++ code:
|
||||
Dalvan Griebler <dalvangriebler@gmail.com>
|
||||
Gabriell Araujo <hexenoften@gmail.com>
|
||||
Júnior Löff <loffjh@gmail.com>
|
||||
*/
|
||||
|
||||
#include <cmath>
|
||||
#include <cstdio>
|
||||
#include <cstdlib>
|
||||
|
||||
/*****************************************************************/
|
||||
/****** C _ P R I N T _ R E S U L T S ******/
|
||||
/*****************************************************************/
|
||||
void
|
||||
c_print_results(char* name, char class_npb, int n1, int n2, int n3, int niter, double t,
|
||||
double mops, char* optype, int passed_verification, char* npbversion,
|
||||
char* compiletime, char* compilerversion, char* libversion,
|
||||
char* totalthreads, char* cc, char* clink, char* c_lib, char* c_inc,
|
||||
char* cflags, char* clinkflags, char* rand)
|
||||
{
|
||||
printf("\n\n %s Benchmark Completed\n", name);
|
||||
printf(" class_npb = %c\n", class_npb);
|
||||
if((name[0] == 'I') && (name[1] == 'S'))
|
||||
{
|
||||
if(n3 == 0)
|
||||
{
|
||||
long nn = n1;
|
||||
if(n2 != 0)
|
||||
{
|
||||
nn *= n2;
|
||||
}
|
||||
printf(" Size = %12ld\n", nn); /* as in IS */
|
||||
}
|
||||
else
|
||||
{
|
||||
printf(" Size = %4dx%4dx%4d\n", n1, n2, n3);
|
||||
}
|
||||
}
|
||||
else
|
||||
{
|
||||
char size[16];
|
||||
int j;
|
||||
if((n2 == 0) && (n3 == 0))
|
||||
{
|
||||
if((name[0] == 'E') && (name[1] == 'P'))
|
||||
{
|
||||
sprintf(size, "%15.0lf", pow(2.0, n1));
|
||||
j = 14;
|
||||
if(size[j] == '.')
|
||||
{
|
||||
size[j] = ' ';
|
||||
j--;
|
||||
}
|
||||
size[j + 1] = '\0';
|
||||
printf(" Size = %15s\n", size);
|
||||
}
|
||||
else
|
||||
{
|
||||
printf(" Size = %12d\n", n1);
|
||||
}
|
||||
}
|
||||
else
|
||||
{
|
||||
printf(" Size = %4dx%4dx%4d\n", n1, n2, n3);
|
||||
}
|
||||
}
|
||||
printf(" Total threads = %12s\n", totalthreads);
|
||||
printf(" Iterations = %12d\n", niter);
|
||||
printf(" Time in seconds = %12.2f\n", t);
|
||||
printf(" Mop/s total = %12.2f\n", mops);
|
||||
printf(" Operation type = %24s\n", optype);
|
||||
if(passed_verification < 0)
|
||||
{
|
||||
printf(" Verification = NOT PERFORMED\n");
|
||||
}
|
||||
else if(passed_verification)
|
||||
{
|
||||
printf(" Verification = SUCCESSFUL\n");
|
||||
}
|
||||
else
|
||||
{
|
||||
printf(" Verification = UNSUCCESSFUL\n");
|
||||
}
|
||||
printf(" Version = %12s\n", npbversion);
|
||||
printf(" Compile date = %12s\n", compiletime);
|
||||
printf(" Compiler ver = %12s\n", compilerversion);
|
||||
printf(" OpenMP version = %12s\n", libversion);
|
||||
printf("\n Compile options:\n");
|
||||
printf(" CC = %s\n", cc);
|
||||
printf(" CLINK = %s\n", clink);
|
||||
printf(" C_LIB = %s\n", c_lib);
|
||||
printf(" C_INC = %s\n", c_inc);
|
||||
printf(" CFLAGS = %s\n", cflags);
|
||||
printf(" CLINKFLAGS = %s\n", clinkflags);
|
||||
printf(" RAND = %s\n", rand);
|
||||
#ifdef SMP
|
||||
evalue = getenv("MP_SET_NUMTHREADS");
|
||||
printf(" MULTICPUS = %s\n", evalue);
|
||||
#endif
|
||||
/*
|
||||
* printf(" Please send the results of this run to:\n\n");
|
||||
* printf(" NPB Development Team\n");
|
||||
* printf(" Internet: npb@nas.nasa.gov\n \n");
|
||||
* printf(" If email is not available, send this to:\n\n");
|
||||
* printf(" MS T27A-1\n");
|
||||
* printf(" NASA Ames Research Center\n");
|
||||
* printf(" Moffett Field, CA 94035-1000\n\n");
|
||||
* printf(" Fax: 650-604-3957\n\n");
|
||||
*/
|
||||
printf("\n\n");
|
||||
|
||||
printf("----------------------------------------------------------------------\n");
|
||||
printf(" NPB-CPP is developed by: \n");
|
||||
printf(" Dalvan Griebler\n");
|
||||
printf(" Gabriell Araujo (Sequential Porting)\n");
|
||||
printf(" Júnior Löff (Parallel Implementation)\n");
|
||||
printf("\n");
|
||||
printf(" In case of questions or problems, please send an e-mail to us:\n");
|
||||
printf(" dalvan.griebler; gabriell.araujo; junior.loff@edu.pucrs.br\n");
|
||||
printf("----------------------------------------------------------------------\n");
|
||||
printf("\n");
|
||||
}
|
||||
@@ -0,0 +1,184 @@
|
||||
/*
|
||||
MIT License
|
||||
|
||||
Copyright (c) 2021 Parallel Applications Modelling Group - GMAP
|
||||
GMAP website: https://gmap.pucrs.br
|
||||
|
||||
Pontifical Catholic University of Rio Grande do Sul (PUCRS)
|
||||
Av. Ipiranga, 6681, Porto Alegre - Brazil, 90619-900
|
||||
|
||||
Permission is hereby granted, free of charge, to any person obtaining a copy
|
||||
of this software and associated documentation files (the "Software"), to deal
|
||||
in the Software without restriction, including without limitation the rights
|
||||
to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
|
||||
copies of the Software, and to permit persons to whom the Software is
|
||||
furnished to do so, subject to the following conditions:
|
||||
|
||||
The above copyright notice and this permission notice shall be included in all
|
||||
copies or substantial portions of the Software.
|
||||
|
||||
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
|
||||
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
|
||||
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
|
||||
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
|
||||
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
|
||||
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
|
||||
SOFTWARE.
|
||||
|
||||
------------------------------------------------------------------------------
|
||||
|
||||
The original NPB 3.4.1 version was written in Fortran and belongs to:
|
||||
http://www.nas.nasa.gov/Software/NPB/
|
||||
|
||||
------------------------------------------------------------------------------
|
||||
|
||||
The serial C++ version is a translation of the original NPB 3.4.1
|
||||
Serial C++ version: https://github.com/GMAP/NPB-CPP/tree/master/NPB-SER
|
||||
|
||||
Authors of the C++ code:
|
||||
Dalvan Griebler <dalvangriebler@gmail.com>
|
||||
Gabriell Araujo <hexenoften@gmail.com>
|
||||
Júnior Löff <loffjh@gmail.com>
|
||||
*/
|
||||
|
||||
#if defined(USE_POW)
|
||||
# define r23 pow(0.5, 23.0)
|
||||
# define r46 (r23 * r23)
|
||||
# define t23 pow(2.0, 23.0)
|
||||
# define t46 (t23 * t23)
|
||||
#else
|
||||
# define r23 \
|
||||
(0.5 * 0.5 * 0.5 * 0.5 * 0.5 * 0.5 * 0.5 * 0.5 * 0.5 * 0.5 * 0.5 * 0.5 * 0.5 * \
|
||||
0.5 * 0.5 * 0.5 * 0.5 * 0.5 * 0.5 * 0.5 * 0.5 * 0.5 * 0.5)
|
||||
# define r46 (r23 * r23)
|
||||
# define t23 \
|
||||
(2.0 * 2.0 * 2.0 * 2.0 * 2.0 * 2.0 * 2.0 * 2.0 * 2.0 * 2.0 * 2.0 * 2.0 * 2.0 * \
|
||||
2.0 * 2.0 * 2.0 * 2.0 * 2.0 * 2.0 * 2.0 * 2.0 * 2.0 * 2.0)
|
||||
# define t46 (t23 * t23)
|
||||
#endif
|
||||
|
||||
/*
|
||||
* ---------------------------------------------------------------------
|
||||
*
|
||||
* this routine returns a uniform pseudorandom double precision number in the
|
||||
* range (0, 1) by using the linear congruential generator
|
||||
*
|
||||
* x_{k+1} = a x_k (mod 2^46)
|
||||
*
|
||||
* where 0 < x_k < 2^46 and 0 < a < 2^46. this scheme generates 2^44 numbers
|
||||
* before repeating. the argument A is the same as 'a' in the above formula,
|
||||
* and X is the same as x_0. A and X must be odd double precision integers
|
||||
* in the range (1, 2^46). the returned value RANDLC is normalized to be
|
||||
* between 0 and 1, i.e. RANDLC = 2^(-46) * x_1. X is updated to contain
|
||||
* the new seed x_1, so that subsequent calls to RANDLC using the same
|
||||
* arguments will generate a continuous sequence.
|
||||
*
|
||||
* this routine should produce the same results on any computer with at least
|
||||
* 48 mantissa bits in double precision floating point data. On 64 bit
|
||||
* systems, double precision should be disabled.
|
||||
*
|
||||
* David H. Bailey, October 26, 1990
|
||||
*
|
||||
* ---------------------------------------------------------------------
|
||||
*/
|
||||
double
|
||||
randlc(double* x, double a)
|
||||
{
|
||||
double t1, t2, t3, t4, a1, a2, x1, x2, z;
|
||||
|
||||
/*
|
||||
* ---------------------------------------------------------------------
|
||||
* break A into two parts such that A = 2^23 * A1 + A2.
|
||||
* ---------------------------------------------------------------------
|
||||
*/
|
||||
t1 = r23 * a;
|
||||
a1 = (int) t1;
|
||||
a2 = a - t23 * a1;
|
||||
|
||||
/*
|
||||
* ---------------------------------------------------------------------
|
||||
* break X into two parts such that X = 2^23 * X1 + X2, compute
|
||||
* Z = A1 * X2 + A2 * X1 (mod 2^23), and then
|
||||
* X = 2^23 * Z + A2 * X2 (mod 2^46).
|
||||
* ---------------------------------------------------------------------
|
||||
*/
|
||||
t1 = r23 * (*x);
|
||||
x1 = (int) t1;
|
||||
x2 = (*x) - t23 * x1;
|
||||
t1 = a1 * x2 + a2 * x1;
|
||||
t2 = (int) (r23 * t1);
|
||||
z = t1 - t23 * t2;
|
||||
t3 = t23 * z + a2 * x2;
|
||||
t4 = (int) (r46 * t3);
|
||||
(*x) = t3 - t46 * t4;
|
||||
|
||||
return (r46 * (*x));
|
||||
}
|
||||
|
||||
/*
|
||||
* ---------------------------------------------------------------------
|
||||
*
|
||||
* this routine generates N uniform pseudorandom double precision numbers in
|
||||
* the range (0, 1) by using the linear congruential generator
|
||||
*
|
||||
* x_{k+1} = a x_k (mod 2^46)
|
||||
*
|
||||
* where 0 < x_k < 2^46 and 0 < a < 2^46. this scheme generates 2^44 numbers
|
||||
* before repeating. the argument A is the same as 'a' in the above formula,
|
||||
* and X is the same as x_0. A and X must be odd double precision integers
|
||||
* in the range (1, 2^46). the N results are placed in Y and are normalized
|
||||
* to be between 0 and 1. X is updated to contain the new seed, so that
|
||||
* subsequent calls to VRANLC using the same arguments will generate a
|
||||
* continuous sequence. if N is zero, only initialization is performed, and
|
||||
* the variables X, A and Y are ignored.
|
||||
*
|
||||
* this routine is the standard version designed for scalar or RISC systems.
|
||||
* however, it should produce the same results on any single processor
|
||||
* computer with at least 48 mantissa bits in double precision floating point
|
||||
* data. on 64 bit systems, double precision should be disabled.
|
||||
*
|
||||
* ---------------------------------------------------------------------
|
||||
*/
|
||||
void
|
||||
vranlc(int n, double* x_seed, double a, double y[])
|
||||
{
|
||||
int i;
|
||||
double x, t1, t2, t3, t4, a1, a2, x1, x2, z;
|
||||
|
||||
/*
|
||||
* ---------------------------------------------------------------------
|
||||
* break A into two parts such that A = 2^23 * A1 + A2.
|
||||
* ---------------------------------------------------------------------
|
||||
*/
|
||||
t1 = r23 * a;
|
||||
a1 = (int) t1;
|
||||
a2 = a - t23 * a1;
|
||||
x = *x_seed;
|
||||
|
||||
/*
|
||||
* ---------------------------------------------------------------------
|
||||
* generate N results. this loop is not vectorizable.
|
||||
* ---------------------------------------------------------------------
|
||||
*/
|
||||
for(i = 0; i < n; i++)
|
||||
{
|
||||
/*
|
||||
* ---------------------------------------------------------------------
|
||||
* break X into two parts such that X = 2^23 * X1 + X2, compute
|
||||
* Z = A1 * X2 + A2 * X1 (mod 2^23), and then
|
||||
* X = 2^23 * Z + A2 * X2 (mod 2^46).
|
||||
* ---------------------------------------------------------------------
|
||||
*/
|
||||
t1 = r23 * x;
|
||||
x1 = (int) t1;
|
||||
x2 = x - t23 * x1;
|
||||
t1 = a1 * x2 + a2 * x1;
|
||||
t2 = (int) (r23 * t1);
|
||||
z = t1 - t23 * t2;
|
||||
t3 = t23 * z + a2 * x2;
|
||||
t4 = (int) (r46 * t3);
|
||||
x = t3 - t46 * t4;
|
||||
y[i] = r46 * x;
|
||||
}
|
||||
*x_seed = x;
|
||||
}
|
||||
@@ -0,0 +1,101 @@
|
||||
/*
|
||||
MIT License
|
||||
|
||||
Copyright (c) 2021 Parallel Applications Modelling Group - GMAP
|
||||
GMAP website: https://gmap.pucrs.br
|
||||
|
||||
Pontifical Catholic University of Rio Grande do Sul (PUCRS)
|
||||
Av. Ipiranga, 6681, Porto Alegre - Brazil, 90619-900
|
||||
|
||||
Permission is hereby granted, free of charge, to any person obtaining a copy
|
||||
of this software and associated documentation files (the "Software"), to deal
|
||||
in the Software without restriction, including without limitation the rights
|
||||
to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
|
||||
copies of the Software, and to permit persons to whom the Software is
|
||||
furnished to do so, subject to the following conditions:
|
||||
|
||||
The above copyright notice and this permission notice shall be included in all
|
||||
copies or substantial portions of the Software.
|
||||
|
||||
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
|
||||
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
|
||||
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
|
||||
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
|
||||
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
|
||||
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
|
||||
SOFTWARE.
|
||||
|
||||
------------------------------------------------------------------------------
|
||||
|
||||
The original NPB 3.4.1 version was written in Fortran and belongs to:
|
||||
http://www.nas.nasa.gov/Software/NPB/
|
||||
|
||||
------------------------------------------------------------------------------
|
||||
|
||||
The serial C++ version is a translation of the original NPB 3.4.1
|
||||
Serial C++ version: https://github.com/GMAP/NPB-CPP/tree/master/NPB-SER
|
||||
|
||||
Authors of the C++ code:
|
||||
Dalvan Griebler <dalvangriebler@gmail.com>
|
||||
Gabriell Araujo <hexenoften@gmail.com>
|
||||
Júnior Löff <loffjh@gmail.com>
|
||||
*/
|
||||
|
||||
#include "wtime.hpp"
|
||||
#include <cstdlib>
|
||||
|
||||
/* prototype */
|
||||
void
|
||||
wtime(double*);
|
||||
|
||||
/*****************************************************************/
|
||||
/****** E L A P S E D _ T I M E ******/
|
||||
/*****************************************************************/
|
||||
double
|
||||
elapsed_time(void)
|
||||
{
|
||||
double t;
|
||||
wtime(&t);
|
||||
return (t);
|
||||
}
|
||||
|
||||
double start[64], elapsed[64];
|
||||
|
||||
/*****************************************************************/
|
||||
/****** T I M E R _ C L E A R ******/
|
||||
/*****************************************************************/
|
||||
void
|
||||
timer_clear(int n)
|
||||
{
|
||||
elapsed[n] = 0.0;
|
||||
}
|
||||
|
||||
/*****************************************************************/
|
||||
/****** T I M E R _ S T A R T ******/
|
||||
/*****************************************************************/
|
||||
void
|
||||
timer_start(int n)
|
||||
{
|
||||
start[n] = elapsed_time();
|
||||
}
|
||||
|
||||
/*****************************************************************/
|
||||
/****** T I M E R _ S T O P ******/
|
||||
/*****************************************************************/
|
||||
void
|
||||
timer_stop(int n)
|
||||
{
|
||||
double t, now;
|
||||
now = elapsed_time();
|
||||
t = now - start[n];
|
||||
elapsed[n] += t;
|
||||
}
|
||||
|
||||
/*****************************************************************/
|
||||
/****** T I M E R _ R E A D ******/
|
||||
/*****************************************************************/
|
||||
double
|
||||
timer_read(int n)
|
||||
{
|
||||
return (elapsed[n]);
|
||||
}
|
||||
@@ -0,0 +1,124 @@
|
||||
/*
|
||||
MIT License
|
||||
|
||||
Copyright (c) 2021 Parallel Applications Modelling Group - GMAP
|
||||
GMAP website: https://gmap.pucrs.br
|
||||
|
||||
Pontifical Catholic University of Rio Grande do Sul (PUCRS)
|
||||
Av. Ipiranga, 6681, Porto Alegre - Brazil, 90619-900
|
||||
|
||||
Permission is hereby granted, free of charge, to any person obtaining a copy
|
||||
of this software and associated documentation files (the "Software"), to deal
|
||||
in the Software without restriction, including without limitation the rights
|
||||
to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
|
||||
copies of the Software, and to permit persons to whom the Software is
|
||||
furnished to do so, subject to the following conditions:
|
||||
|
||||
The above copyright notice and this permission notice shall be included in all
|
||||
copies or substantial portions of the Software.
|
||||
|
||||
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
|
||||
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
|
||||
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
|
||||
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
|
||||
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
|
||||
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
|
||||
SOFTWARE.
|
||||
|
||||
------------------------------------------------------------------------------
|
||||
|
||||
The original NPB 3.4.1 version was written in Fortran and belongs to:
|
||||
http://www.nas.nasa.gov/Software/NPB/
|
||||
|
||||
------------------------------------------------------------------------------
|
||||
|
||||
The serial C++ version is a translation of the original NPB 3.4.1
|
||||
Serial C++ version: https://github.com/GMAP/NPB-CPP/tree/master/NPB-SER
|
||||
|
||||
Authors of the C++ code:
|
||||
Dalvan Griebler <dalvangriebler@gmail.com>
|
||||
Gabriell Araujo <hexenoften@gmail.com>
|
||||
Júnior Löff <loffjh@gmail.com>
|
||||
*/
|
||||
|
||||
#include <cmath>
|
||||
#include <cstdio>
|
||||
#include <cstdlib>
|
||||
|
||||
typedef int boolean;
|
||||
typedef struct
|
||||
{
|
||||
double real;
|
||||
double imag;
|
||||
} dcomplex;
|
||||
|
||||
#define TRUE 1
|
||||
#define FALSE 0
|
||||
|
||||
#define max(a, b) (((a) > (b)) ? (a) : (b))
|
||||
#define min(a, b) (((a) < (b)) ? (a) : (b))
|
||||
#define pow2(a) ((a) * (a))
|
||||
|
||||
/* old version of the complex number operations */
|
||||
#define get_real(c) c.real
|
||||
#define get_imag(c) c.imag
|
||||
#define cadd(c, a, b) (c.real = a.real + b.real, c.imag = a.imag + b.imag)
|
||||
#define csub(c, a, b) (c.real = a.real - b.real, c.imag = a.imag - b.imag)
|
||||
#define cmul(c, a, b) \
|
||||
(c.real = a.real * b.real - a.imag * b.imag, \
|
||||
c.imag = a.real * b.imag + a.imag * b.real)
|
||||
#define crmul(c, a, b) (c.real = a.real * b, c.imag = a.imag * b)
|
||||
|
||||
/* latest version of the complex number operations */
|
||||
#define dcomplex_create(r, i) \
|
||||
(dcomplex) { r, i }
|
||||
#define dcomplex_add(a, b) \
|
||||
(dcomplex) { (a).real + (b).real, (a).imag + (b).imag }
|
||||
#define dcomplex_sub(a, b) \
|
||||
(dcomplex) { (a).real - (b).real, (a).imag - (b).imag }
|
||||
#define dcomplex_mul(a, b) \
|
||||
(dcomplex) \
|
||||
{ \
|
||||
((a).real * (b).real) - ((a).imag * (b).imag), \
|
||||
((a).real * (b).imag) + ((a).imag * (b).real) \
|
||||
}
|
||||
#define dcomplex_mul2(a, b) \
|
||||
(dcomplex) { (a).real*(b), (a).imag*(b) }
|
||||
static inline dcomplex
|
||||
dcomplex_div(dcomplex z1, dcomplex z2)
|
||||
{
|
||||
double a = z1.real;
|
||||
double b = z1.imag;
|
||||
double c = z2.real;
|
||||
double d = z2.imag;
|
||||
double divisor = c * c + d * d;
|
||||
double real = (a * c + b * d) / divisor;
|
||||
double imag = (b * c - a * d) / divisor;
|
||||
dcomplex result = (dcomplex){ real, imag };
|
||||
return result;
|
||||
}
|
||||
#define dcomplex_div2(a, b) \
|
||||
(dcomplex) { (a).real / (b), (a).imag / (b) }
|
||||
#define dcomplex_abs(x) sqrt(((x).real * (x).real) + ((x).imag * (x).imag))
|
||||
#define dconjg(x) \
|
||||
(dcomplex) { (x).real, -1.0 * (x).imag }
|
||||
|
||||
extern double
|
||||
randlc(double*, double);
|
||||
extern void
|
||||
vranlc(int, double*, double, double*);
|
||||
extern void
|
||||
timer_clear(int);
|
||||
extern void
|
||||
timer_start(int);
|
||||
extern void
|
||||
timer_stop(int);
|
||||
extern double
|
||||
timer_read(int);
|
||||
|
||||
extern void
|
||||
c_print_results(char* name, char class_npb, int n1, int n2, int n3, int niter, double t,
|
||||
double mops, char* optype, int passed_verification, char* npbversion,
|
||||
char* compiletime, char* compilerversion, char* libversion,
|
||||
char* totalthreads, char* cc, char* clink, char* c_lib, char* c_inc,
|
||||
char* cflags, char* clinkflags, char* rand);
|
||||
@@ -0,0 +1,55 @@
|
||||
/*
|
||||
MIT License
|
||||
|
||||
Copyright (c) 2021 Parallel Applications Modelling Group - GMAP
|
||||
GMAP website: https://gmap.pucrs.br
|
||||
|
||||
Pontifical Catholic University of Rio Grande do Sul (PUCRS)
|
||||
Av. Ipiranga, 6681, Porto Alegre - Brazil, 90619-900
|
||||
|
||||
Permission is hereby granted, free of charge, to any person obtaining a copy
|
||||
of this software and associated documentation files (the "Software"), to deal
|
||||
in the Software without restriction, including without limitation the rights
|
||||
to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
|
||||
copies of the Software, and to permit persons to whom the Software is
|
||||
furnished to do so, subject to the following conditions:
|
||||
|
||||
The above copyright notice and this permission notice shall be included in all
|
||||
copies or substantial portions of the Software.
|
||||
|
||||
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
|
||||
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
|
||||
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
|
||||
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
|
||||
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
|
||||
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
|
||||
SOFTWARE.
|
||||
|
||||
------------------------------------------------------------------------------
|
||||
|
||||
The original NPB 3.4.1 version was written in Fortran and belongs to:
|
||||
http://www.nas.nasa.gov/Software/NPB/
|
||||
|
||||
------------------------------------------------------------------------------
|
||||
|
||||
The serial C++ version is a translation of the original NPB 3.4.1
|
||||
Serial C++ version: https://github.com/GMAP/NPB-CPP/tree/master/NPB-SER
|
||||
|
||||
Authors of the C++ code:
|
||||
Dalvan Griebler <dalvangriebler@gmail.com>
|
||||
Gabriell Araujo <hexenoften@gmail.com>
|
||||
Júnior Löff <loffjh@gmail.com>
|
||||
*/
|
||||
|
||||
#include "wtime.hpp"
|
||||
#include <sys/time.h>
|
||||
|
||||
void
|
||||
wtime(double* t)
|
||||
{
|
||||
static int sec = -1;
|
||||
struct timeval tv;
|
||||
gettimeofday(&tv, 0);
|
||||
if(sec < 0) sec = tv.tv_sec;
|
||||
*t = (tv.tv_sec - sec) + 1.0e-6 * tv.tv_usec;
|
||||
}
|
||||
@@ -0,0 +1,54 @@
|
||||
/*
|
||||
MIT License
|
||||
|
||||
Copyright (c) 2021 Parallel Applications Modelling Group - GMAP
|
||||
GMAP website: https://gmap.pucrs.br
|
||||
|
||||
Pontifical Catholic University of Rio Grande do Sul (PUCRS)
|
||||
Av. Ipiranga, 6681, Porto Alegre - Brazil, 90619-900
|
||||
|
||||
Permission is hereby granted, free of charge, to any person obtaining a copy
|
||||
of this software and associated documentation files (the "Software"), to deal
|
||||
in the Software without restriction, including without limitation the rights
|
||||
to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
|
||||
copies of the Software, and to permit persons to whom the Software is
|
||||
furnished to do so, subject to the following conditions:
|
||||
|
||||
The above copyright notice and this permission notice shall be included in all
|
||||
copies or substantial portions of the Software.
|
||||
|
||||
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
|
||||
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
|
||||
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
|
||||
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
|
||||
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
|
||||
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
|
||||
SOFTWARE.
|
||||
|
||||
------------------------------------------------------------------------------
|
||||
|
||||
The original NPB 3.4.1 version was written in Fortran and belongs to:
|
||||
http://www.nas.nasa.gov/Software/NPB/
|
||||
|
||||
------------------------------------------------------------------------------
|
||||
|
||||
The serial C++ version is a translation of the original NPB 3.4.1
|
||||
Serial C++ version: https://github.com/GMAP/NPB-CPP/tree/master/NPB-SER
|
||||
|
||||
Authors of the C++ code:
|
||||
Dalvan Griebler <dalvangriebler@gmail.com>
|
||||
Gabriell Araujo <hexenoften@gmail.com>
|
||||
Júnior Löff <loffjh@gmail.com>
|
||||
*/
|
||||
|
||||
/*
|
||||
* C/Fortran interface is different on different machines.
|
||||
* you may need to tweak this.
|
||||
*/
|
||||
#if defined(IBM)
|
||||
# define wtime wtime
|
||||
#elif defined(CRAY)
|
||||
# define wtime WTIME
|
||||
#else
|
||||
# define wtime wtime_
|
||||
#endif
|
||||
@@ -95,7 +95,7 @@ transpose_a(int* in, int* out, int M, int N)
|
||||
void
|
||||
run(int rank, int tid, hipStream_t stream, int argc, char** argv)
|
||||
{
|
||||
size_t nitr = 5000;
|
||||
size_t nitr = 500;
|
||||
unsigned int M = 4960 * 2;
|
||||
unsigned int N = 4960 * 2;
|
||||
if(argc > 2) nitr = atoll(argv[2]);
|
||||
|
||||
@@ -0,0 +1,13 @@
|
||||
cmake_minimum_required(VERSION 3.15 FATAL_ERROR)
|
||||
|
||||
project(omnitrace-user-api LANGUAGES CXX)
|
||||
|
||||
set(CMAKE_BUILD_TYPE "Release")
|
||||
find_package(Threads REQUIRED)
|
||||
add_executable(user-api user-api.cpp)
|
||||
target_link_libraries(user-api PRIVATE Threads::Threads omnitrace::omnitrace-user-library)
|
||||
|
||||
if(NOT CMAKE_PROJECT_NAME STREQUAL PROJECT_NAME)
|
||||
set_target_properties(user-api PROPERTIES RUNTIME_OUTPUT_DIRECTORY
|
||||
${CMAKE_BINARY_DIR})
|
||||
endif()
|
||||
@@ -0,0 +1,80 @@
|
||||
|
||||
#include <omnitrace/user.h>
|
||||
|
||||
#include <atomic>
|
||||
#include <cstdio>
|
||||
#include <cstdlib>
|
||||
#include <sstream>
|
||||
#include <thread>
|
||||
#include <vector>
|
||||
|
||||
std::atomic<long> total{ 0 };
|
||||
|
||||
long
|
||||
fib(long n) __attribute__((noinline));
|
||||
|
||||
void
|
||||
run(size_t nitr, long) __attribute__((noinline));
|
||||
|
||||
long
|
||||
fib(long n)
|
||||
{
|
||||
return (n < 2) ? n : fib(n - 1) + fib(n - 2);
|
||||
}
|
||||
|
||||
#define RUN_LABEL \
|
||||
std::string{ std::string{ __FUNCTION__ } + "(" + std::to_string(n) + ") x " + \
|
||||
std::to_string(nitr) } \
|
||||
.c_str()
|
||||
|
||||
void
|
||||
run(size_t nitr, long n)
|
||||
{
|
||||
omnitrace_user_stop_thread_trace();
|
||||
omnitrace_user_push_region(RUN_LABEL);
|
||||
long local = 0;
|
||||
for(size_t i = 0; i < nitr; ++i)
|
||||
local += fib(n);
|
||||
total += local;
|
||||
omnitrace_user_pop_region(RUN_LABEL);
|
||||
omnitrace_user_start_thread_trace();
|
||||
}
|
||||
|
||||
int
|
||||
main(int argc, char** argv)
|
||||
{
|
||||
omnitrace_user_push_region(argv[0]);
|
||||
omnitrace_user_push_region("initialization");
|
||||
size_t nthread = std::min<size_t>(16, std::thread::hardware_concurrency());
|
||||
size_t nitr = 50000;
|
||||
long nfib = 10;
|
||||
if(argc > 1) nfib = atol(argv[1]);
|
||||
if(argc > 2) nthread = atol(argv[2]);
|
||||
if(argc > 3) nitr = atol(argv[3]);
|
||||
omnitrace_user_pop_region("initialization");
|
||||
|
||||
printf("[%s] Threads: %zu\n[%s] Iterations: %zu\n[%s] fibonacci(%li)...\n", argv[0],
|
||||
nthread, argv[0], nitr, argv[0], nfib);
|
||||
|
||||
omnitrace_user_push_region("thread_creation");
|
||||
std::vector<std::thread> threads{};
|
||||
threads.reserve(nthread);
|
||||
for(size_t i = 0; i < nthread; ++i)
|
||||
{
|
||||
size_t _nitr = ((i % 2) == 1) ? (nitr - (0.1 * nitr)) : (nitr + (0.1 * nitr));
|
||||
threads.emplace_back(&run, _nitr, nfib);
|
||||
}
|
||||
omnitrace_user_pop_region("thread_creation");
|
||||
|
||||
run(nitr - 0.25 * nitr, nfib - 0.1 * nfib);
|
||||
|
||||
omnitrace_user_push_region("thread_wait");
|
||||
for(auto& itr : threads)
|
||||
itr.join();
|
||||
omnitrace_user_pop_region("thread_wait");
|
||||
|
||||
printf("[%s] fibonacci(%li) x %lu = %li\n", argv[0], nfib, nthread, total.load());
|
||||
omnitrace_user_pop_region(argv[0]);
|
||||
|
||||
return 0;
|
||||
}
|
||||
Reference in New Issue
Block a user