Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Make ngm work on computers with more than 256 cores #48

Open
wants to merge 2 commits into
base: master
Choose a base branch
from
Open

Make ngm work on computers with more than 256 cores #48

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
09108ab
Avoid magic number for number of cores/threads
hermannschwaerzlerUIBK May 14, 2019
8d9d762
As we #include <thread> we need "-std=c++11" for gcc 4.x
hermannschwaerzlerUIBK May 15, 2019
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 2 additions & 2 deletions CMakeLists.txt
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -39,8 +39,8 @@ IF(NOT CMAKE_CONFIGURATION_TYPES AND NOT CMAKE_BUILD_TYPE)
ENDIF(NOT CMAKE_CONFIGURATION_TYPES AND NOT CMAKE_BUILD_TYPE)

IF(NOT APPLE)
SET (CMAKE_CXX_FLAGS_RELEASE "-L${EXECUTABLE_OUTPUT_PATH}/opencl/lib")
SET (CMAKE_CXX_FLAGS_DEBUG "-L${EXECUTABLE_OUTPUT_PATH}/opencl/lib")
SET (CMAKE_CXX_FLAGS_RELEASE "-L${EXECUTABLE_OUTPUT_PATH}/opencl/lib -std=c++11")
SET (CMAKE_CXX_FLAGS_DEBUG "-L${EXECUTABLE_OUTPUT_PATH}/opencl/lib -std=c++11")
endif()


Expand Down
12 changes: 9 additions & 3 deletions lib/mason/opencl/OclHost.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -10,6 +10,7 @@
#include <string.h>
#include <pthread.h>
#include "IConfig.h"
#include <thread>

pthread_mutex_t mutext_next_sub_block;

Expand Down Expand Up @@ -108,11 +109,16 @@ OclHost::OclHost(int const device_type, int gpu_id, int const cpu_cores) :
cl_device_partition_property props[3];

props[0] = CL_DEVICE_PARTITION_EQUALLY; // Equally
props[1] = 1; // 4 compute units per sub-device
props[1] = 1; // compute units per sub-device
props[2] = 0;

devices = (cl_device_id *) malloc(256 * sizeof(cl_device_id));
ciErrNum = clCreateSubDevices(device_id, props, 256, devices,
unsigned int threads = std::thread::hardware_concurrency();
if ( threads == 0 ) {
threads = 2560;
Log.Message("Number of concurrent threads not well defined or not computable. Using default of %d.", threads);
}
devices = (cl_device_id *) malloc(threads * sizeof(cl_device_id));
ciErrNum = clCreateSubDevices(device_id, props, threads, devices,
&ciDeviceCount);
if (ciErrNum == -18) {
ciDeviceCount = 1;
Expand Down