Welcome to MilkyWay@home

Posts by trigggl

1) Message boards : News : Separation updated to 1.00 (Message 52951)
Posted 9 Feb 2012 by Profile trigggl
Post:
Is it the app or the boinc client causing my starting "Time Remaining" to stay at 3 hours?
2) Message boards : News : Separation updated to 1.00 (Message 52949)
Posted 9 Feb 2012 by Profile trigggl
Post:
What problem are you having? The 4870 drivers were broken with the OpenCL stuff from 11.8 to 11.12 or so. 12.1 works.

I'm currently at 11.8 because anything (stable) after that broke other OpenCL apps. I see that 12.1 is in Gentoo Portage, so I'll try that. Thanks for the info.

I installed 12.1 and now Sep. 1.00 is working on my 4870 with Gentoo x86_64. Ironically, now the old app is failing.

My task times went from 2:38 to 2:28.
3) Message boards : News : Separation updated to 1.00 (Message 52910)
Posted 9 Feb 2012 by Profile trigggl
Post:
What problem are you having? The 4870 drivers were broken with the OpenCL stuff from 11.8 to 11.12 or so. 12.1 works.

I'm currently at 11.8 because anything (stable) after that broke other OpenCL apps. I see that 12.1 is in Gentoo Portage, so I'll try that. Thanks for the info.
4) Message boards : News : Separation updated to 1.00 (Message 52908)
Posted 9 Feb 2012 by Profile trigggl
Post:
Anyone actually manage to get the Linux x86_64 opencl app to work? I have an HD 4870 and it looks like I've been upgraded out of the ability to crunch. The 4870 doesn't like the new AMD drivers and it doesn't appear that the new app likes the old one.

This couldn't have waited til after the double credit day?
5) Message boards : Number crunching : Not getting WU's (Message 52866)
Posted 8 Feb 2012 by Profile trigggl
Post:
ATI isn't even a selection in the preferences anymore. How does that get missed?
It was gone for maybe 2 hours. BOINC relies on too much strstr(something, "ati") everywhere and the applications with ATI in the name are all deprecated now.

So, the answer to my question is "very easily". I can understand that.
6) Message boards : Number crunching : Not getting WU's (Message 52855)
Posted 8 Feb 2012 by Profile trigggl
Post:
ATI isn't even a selection in the preferences anymore. How does that get missed?
7) Message boards : Number crunching : 1 task at a time (Message 51437)
Posted 17 Oct 2011 by Profile trigggl
Post:
Is it normal for me to only get one task at a time? It seems like I should at least get 2 so one can be crunching while the other is being replaced by a new one.

Am I the only one this is happening to?

EDIT: nevermind, I'm getting 10 now. It started downloading after I changed Moo! to a share of 0. Apparently suspending isn't enough.
8) Message boards : Number crunching : Suddenly most results invalid (Message 51436)
Posted 17 Oct 2011 by Profile trigggl
Post:
Actually I've now managed to get it to happen on the R770 (4850/4870) but nothing else.

Perfect. That's what I'm running.
9) Message boards : Number crunching : Deadline problem (Message 34702)
Posted 19 Dec 2009 by Profile trigggl
Post:
The technology race marches on. The needs of the project change over time and older hardware gets left behind. Such is life. I overcame that by purchasing a 3850 card for the AGP slot in my 3.0GHz P4. But some will still have the same problem regarding available apps for their platform. Maybe you could ask Gipsel to do you one....or just find a project that suits your aging hardware.

Currently crunching the Winter Solstice challenge at Primegrid with my aging IBM ppc64 at the moment. Einstein's new app won't compile for me, so I'll be moving to Enigma after that. The machine is running as an mp3 server 24 hours a day, it might as well be doing something the 98% of the time it's inactive. Some projects are easier to compile than others and Milkyway just happens to be one of the easy ones to compile. Pirates is easy to compile, too, if they would just put out a steady stream of work. I can only crunch the projects with source code because I always have to compile my own.
10) Message boards : Number crunching : Cruncher's MW Concerns (Message 34622)
Posted 17 Dec 2009 by Profile trigggl
Post:
I have a machine that I've been using to crunch Milkyway that is kind of slow, but very stable. I was surprised to see the longer work units, but what is the problem for me is the amount of time given to finish them. If work units are going to be made for longer run times it would be helpful to give more time to finish them.

What I've been using is an IBM RS6000 ppc64 that has a 400MHz processor. It finished(not in time) the recent work unit in 80 hours, about 10 more hours than what was allowed. Can we give the work units a few more days to complete, or at least one?
11) Message boards : Application Code Discussion : Update request to the make.linux file (ppc,ppc64) (Message 16692)
Posted 23 Mar 2009 by Profile trigggl
Post:
I made an update to the 'make.linux' file to include ppc and ppc64. While I didn't confirm it for ppc, I did confirm it for ppc64 and the changes were simple enough that I'm confident it will work on ppc as well. The 'code' tags took away the 'tab' spaces so I posted it with 'pre'. I can email it if necessary. I can also supply the ppc64 binary that I compiled. Maybe someone out there could compile the ppc version.

APP_VERSION = 0.18
APP_NAME = your_app_name

BOINC_DIR = /usr/include/boinc
BOINC_API_DIR = $(BOINC_DIR)
BOINC_LIB_DIR = $(BOINC_DIR)
BOINC_LINK_DIR = /home/greg/boinc
BOINC_LIB_LINK_DIR = $(BOINC_LINK_DIR)/lib
BOINC_API_LINK_DIR = $(BOINC_LINK_DIR)/api

VARIANTFLAGS = -DGMLE_BOINC -DBOINC_APP_VERSION=$(APP_VERSION) -DBOINC_APP_NAME='"$(APP_NAME)"'

CXXFLAGS_ALL = $(VARIANTFLAGS) \
	-g \
	-I$(BOINC_DIR)

CXX_i686 = g++
CXXFLAGS_i686 = -m32 -O2 -ftree-vectorize -funroll-loops $(CXXFLAGS_ALL)
LDFLAGS_i686 = -L/usr/X11R6/lib -L../../linux32_libboinc
#LDFLAGS_i686 = -L$(BOINC_LIB_LINK_DIR) -L$(BOINC_API_LINK_DIR)

CXX_x86_64 = g++
CXXFLAGS_x86_64 = -O2 -msse2 -ftree-vectorize -funroll-loops $(CXXFLAGS_ALL)
LDFLAGS_x86_64 = -L/usr/local/lib
#LDFLAGS_x86_64 = -L/usr/local/lib -L/usr/X11R6/lib
#LDFLAGS_x86_64 = -L$(BOINC_LIB_LINK_DIR) -L$(BOINC_API_LINK_DIR)

CXX_ppc64 = g++
CXXFLAGS_ppc64 = -m64 -O2 -ftree-vectorize -funroll-loops $(CXXFLAGS_ALL)
LDFLAGS_ppc64 = -L/usr/local/lib
#LDFLAGS_ppc64 = -L/usr/local/lib -L/usr/X11R6/lib
#LDFLAGS_ppc64 = -L$(BOINC_LIB_LINK_DIR) -L$(BOINC_API_LINK_DIR)

CXX_ppc = g++
CXXFLAGS_ppc = -m32 -O2 -ftree-vectorize -funroll-loops $(CXXFLAGS_ALL)
LDFLAGS_ppc = -L/usr/local/lib
#LDFLAGS_ppc = -L/usr/local/lib -L/usr/X11R6/lib
#LDFLAGS_ppc = -L$(BOINC_LIB_LINK_DIR) -L$(BOINC_API_LINK_DIR)

APP_DIR = ../astronomy
FGDO_DIR = ..
SCHED_DIR = $(FGDO_DIR)/evaluation
SEARCH_DIR = $(FGDO_DIR)/searches
UTIL_DIR = $(FGDO_DIR)/util

APP_OBJS = \
	$(APP_DIR)/boinc_astronomy.o \
	$(APP_DIR)/atSurveyGeometry.o \
	$(APP_DIR)/numericalIntegration.o \
	$(APP_DIR)/parameters.o \
	$(APP_DIR)/probability.o \
	$(APP_DIR)/stCoords.o \
	$(APP_DIR)/stCnum.o \
	$(APP_DIR)/stMath.o \
	$(APP_DIR)/stVector.o \
	$(APP_DIR)/star_points.o \
	$(APP_DIR)/evaluation_optimized.o \
	$(APP_DIR)/evaluation_state.o
SEARCH_OBJS = \
	$(SEARCH_DIR)/search_parameters.o
UTIL_OBJS = \
	$(UTIL_DIR)/io_util.o \
	$(UTIL_DIR)/settings.o

PROGS = milkyway_$(APP_VERSION)_i686-pc-linux-gnu milkyway_$(APP_VERSION)_x86_64-pc-linux-gnu milkyway_$(APP_VERSION)_powerpc64-unknown-linux-gnu milkyway_$(APP_VERSION)_powerpc-unknown-linux-gnu

all: $(PROGS)

app_i686: OBJ_CXX = $(CXX_i686)
app_i686: OBJ_CXXFLAGS = $(CXXFLAGS_i686)
app_i686: $(APP_OBJS) $(SEARCH_OBJS) $(UTIL_OBJS) $(BOINC_API_LINK_DIR)/libboinc_api.a $(BOINC_LIB_LINK_DIR)/libboinc.a
	$(CXX_i686) $(LDFLAGS_i686) $(CXXFLAGS_i686) -Wl --export_dynamic -o milkyway_$(APP_VERSION)_i686-pc-linux-gnu $(APP_OBJS) $(SEARCH_OBJS) $(UTIL_OBJS) -lm -lboinc_api -lboinc -pthread

app_x86_64: OBJ_CXX = $(CXX_x86_64)
app_x86_64: OBJ_CXXFLAGS = $(CXXFLAGS_x86_64)
app_x86_64: $(APP_OBJS) $(SEARCH_OBJS) $(UTIL_OBJS) $(BOINC_API_LINK_DIR)/libboinc_api.a $(BOINC_LIB_LINK_DIR)/libboinc.a
	$(CXX_x86_64) $(LDFLAGS_x86_64) $(CXXFLAGS_x86_64) -Wl -static -static-libgcc -o milkyway_$(APP_VERSION)_x86_64-pc-linux-gnu $(APP_OBJS) $(SEARCH_OBJS) $(UTIL_OBJS) -lm -lboinc_api -lboinc -pthread

app_ppc64: OBJ_CXX = $(CXX_ppc64)
app_ppc64: OBJ_CXXFLAGS = $(CXXFLAGS_ppc64)
app_ppc64: $(APP_OBJS) $(SEARCH_OBJS) $(UTIL_OBJS) $(BOINC_API_LINK_DIR)/libboinc_api.a $(BOINC_LIB_LINK_DIR)/libboinc.a
	$(CXX_ppc64) $(LDFLAGS_ppc64) $(CXXFLAGS_ppc64) -Wl -static -static-libgcc -o milkyway_$(APP_VERSION)_powerpc64-unknown-linux-gnu $(APP_OBJS) $(SEARCH_OBJS) $(UTIL_OBJS) -lm -lboinc_api -lboinc -pthread

app_ppc: OBJ_CXX = $(CXX_ppc)
app_ppc: OBJ_CXXFLAGS = $(CXXFLAGS_ppc)
app_ppc: $(APP_OBJS) $(SEARCH_OBJS) $(UTIL_OBJS) $(BOINC_API_LINK_DIR)/libboinc_api.a $(BOINC_LIB_LINK_DIR)/libboinc.a
	$(CXX_ppc) $(LDFLAGS_ppc) $(CXXFLAGS_ppc) -Wl -static -static-libgcc -o milkyway_$(APP_VERSION)_powerpc-unknown-linux-gnu $(APP_OBJS) $(SEARCH_OBJS) $(UTIL_OBJS) -lm -lboinc_api -lboinc -pthread

.C.o:
	$(OBJ_CXX) $(OBJ_CXXFLAGS) $(INC) -Wall -x c++ -c $< -o $@
.c.o:
	$(OBJ_CXX) $(OBJ_CXXFLAGS) $(INC) -Wall -x c++ -c $< -o $@

clean:
	rm -f $(APP_OBJS) $(UTIL_OBJS) $(SEARCH_OBJS)

clean_all:
	rm -f $(PROGS) $(APP_OBJS) $(UTIL_OBJS) $(SEARCH_OBJS)
12) Message boards : Application Code Discussion : What's needed to compile the app? (Message 15032)
Posted 12 Mar 2009 by Profile trigggl
Post:
Well, it took me quite a lot of editing the Makefile and most of the .c files, but I finally did get powerpc64-unknown-linux-gnu compiled. The main problem I was having was that the include files weren't being found despite correct paths. So, I put in the path in the include files.

I'm currently running task ps_s22_12_854135_1236879798_0 and preventing more tasks from being downloaded until the outcome of this first one is known.

Computer ID 55725
CPU type pSeries
POWER3 (630+) [Model 0 ]

I compiled it without specifying my specific cpu, so it is generic and should probably work on any ppc64 running linux. If someone else wants to test it, let me know. I'll recompile one for myself specifying my cpu (power3) if and when the generic one works.




©2024 Astroinformatics Group