adding analysis results and updating labbook

BioEM_labbook.org

@@ -112,7 +112,7 @@ mpiexec -n 2 $BUILD_DIR/bioEM --Inputfile $TUTORIAL_DIR/Param_Input --Modelfile
 # Loading necessary modules if needed (check installation gcc/Intel)
 
 # Environment variables
-export OMP_NUM_THREADS=5
+export OMP_NUM_THREADS=20
 export OMP_PLACES=cores
 export FFTALGO=1
 export GPU=1
@@ -123,13 +123,44 @@ export GPUWORKLOAD=100
 INPUT_DIR="$HOME/BioEM_project/inputs"
 BUILD_DIR="$HOME/BioEM_project/build"
 
-# Running only few iterations, reading already generated maps (only if they are avaialble in the same folder
-BIOEM_DEBUG_BREAK=4 BIOEM_DEBUG_OUTPUT=2 mpiexec -n 2 $BUILD_DIR/bioEM --Inputfile $INPUT_DIR/INPUT_FRH_Sep2016 --Modelfile $INPUT_DIR/Mod_X-ray_PDB --Particlesfile $INPUT_DIR/2000FRH_Part --LoadMapDump
+# Running only few iterations, reading already generated maps (only if they are available in the same folder
+BIOEM_DEBUG_BREAK=20 BIOEM_DEBUG_OUTPUT=2 mpiexec -n 2 $BUILD_DIR/bioEM --Inputfile $INPUT_DIR/INPUT_FRH_Sep2016 --Modelfile $INPUT_DIR/Mod_X-ray_PDB --Particlesfile $INPUT_DIR/2000FRH_Part --LoadMapDump
+
+# To check if the execution provided correct results
+/afs/ipp-garching.mpg.de/u/sluka/BioEM_fork/Tutorial_BioEM/MODEL_COMPARISION/subtract_LogP.sh $INPUT_DIR/Output_Probabilities_20_ref Output_Probabilities | tail
 
 # Running full example
 BIOEM_DEBUG_OUTPUT=0 mpiexec -n 2 $BUILD_DIR/bioEM --Inputfile $INPUT_DIR/INPUT_FRH_Sep2016 --Modelfile $INPUT_DIR/Mod_X-ray_PDB --Particlesfile $INPUT_DIR/2000FRH_Part
 #+END_SRC
 
+**** Running multiple experiments example
+
+#+BEGIN_SRC 
+# Loading necessary modules if needed (check installation gcc/Intel)
+
+# Environment variables
+export OMP_NUM_THREADS=20
+export OMP_PLACES=cores
+export FFTALGO=1
+export GPU=1
+export GPUDEVICE=-1
+export GPUWORKLOAD=100
+
+# Paths
+INPUT_DIR="$HOME/BioEM_project/inputs"
+BUILD_DIR="$HOME/BioEM_project/build"
+
+echo "Time, Workload, GPUs, OMP_THREADS" > results.csv
+
+# Running multiple experiments
+res=$(BIOEM_DEBUG_BREAK=50 BIOEM_DEBUG_OUTPUT=0 BIOEM_AUTOTUNING=0 GPUWORKLOAD=100 OMP_NUM_THREADS=5 mpiexec -n 2 $BUILD_DIR/bioEM --Inputfile $INPUT_DIR/INPUT_FRH_Sep2016 --Modelfile $INPUT_DIR/Mod_X-ray_PDB --Particlesfile $INPUT_DIR/2000FRH_Part --LoadMapDump | tail -1 | cut -d ' ' -f 5)
+
+# Write results into file
+echo "$res, 100, 1, 5" >> results.csv
+
+#+END_SRC
+
+
 *** [error] miy (Minsky) machine - problems at CUDA runtime
 **** Machine description
      - 3 identical machine with IBM Power 8+ architecture
@@ -1129,3 +1160,51 @@ bioEM: tpp.c:63: __pthread_tpp_change_priority: Assertion `new_prio == -1 || (ne
        + Just measure the timings on GPUs and CPUs for an iteration, and then from that derive the optimal balance
        + Possibly rebalance every X iterations (or projections/orientations) if the balance changed
 	 
+** 2017-06-16
+*** TODO Developing autotuning on dvl machine [2/4]
+    :LOGBOOK:
+    - State "TODO"       from              [2017-06-16 Fri 16:58]
+    :END:
+   - Added nicer error detection and print for the Driver CUDA errors
+   - Problem on dvl device was related to the part that tests all CUDA devices, searching for the fastest one. Commenting out this part made both MPI and non-MPI executions possible.
+   - [ ] Still it seems that when initializing device 1 then 0, this causes a problem (initialization 0 then 1 seems to be fine). Need to inspect this problem in more details
+   - [X] When changing the code, do constantly checks if numerically everything is still correct. Possibly rely on subtract_LogP.sh script available in Tutorial_Bio/MODEL_COMPARISON
+     + If comparing only first 20 models, there is significant difference between the obtained Output_Probabilities and the ones sent by Markus together with the inputs. Hence another Output_Probabilities_20_ref as a reference was created
+   - [X] When changing workload during the execution, never getting the best performance for that workload (compared to when the same workload is tested without autotuning).=Actually, this was solved by doing deviceFinishRun() -> deviceStartRun(). These functions introduce overhead, but it seems that they are necessary
+   - [ ] Create a script for typical runs
+
+*** Simple analysis of the results
+
+#+begin_src R :results output graphics :file :file (org-babel-temp-file "figure" ".png") :exports both :width 600 :height 400 :session org-R
+library(ggplot2)
+
+df <- read.csv("data/results1.csv")
+
+df$Workload <- factor(df$Workload, levels=c(" 60%", " 80%", " 100%", " Auto"))
+df$GPUs <- as.factor(as.character(paste("#GPUs =", df$GPUs)))
+df$OMP_THREADS <- as.factor(as.character(paste("#OMPs =", df$OMP_THREADS)))
+df$OMP_THREADS <- factor(df$OMP_THREADS, levels=c("#OMPs = 5", "#OMPs = 20"))
+
+ggplot(df, aes(x=Workload, y=Time, fill=Workload)) + geom_bar(stat="identity") + facet_grid(GPUs ~ OMP_THREADS) + theme_bw() + ylab("Overall execution time [s]") + xlab("Workload processed on GPUs")
+#+end_src
+
+#+RESULTS:
+[[file:/tmp/babel-2425YP4/figure2425NIt.png]]
+
+        - Maybe it would be good to save these results
+
+#+begin_src R :results output graphics :file analysis/results1_analysis.pdf :exports both :width 6 :height 4 :session org-R
+library(ggplot2)
+
+df <- read.csv("data/results1.csv")
+
+df$Workload <- factor(df$Workload, levels=c(" 60%", " 80%", " 100%", " Auto"))
+df$GPUs <- as.factor(as.character(paste("#GPUs =", df$GPUs)))
+df$OMP_THREADS <- as.factor(as.character(paste("#OMPs =", df$OMP_THREADS)))
+df$OMP_THREADS <- factor(df$OMP_THREADS, levels=c("#OMPs = 5", "#OMPs = 20"))
+
+ggplot(df, aes(x=Workload, y=Time, fill=Workload)) + geom_bar(stat="identity") + facet_grid(GPUs ~ OMP_THREADS) + theme_bw() + ylab("Overall execution time [s]") + xlab("Workload processed on GPUs")
+#+end_src
+
+#+RESULTS:
+[[file:analysis/results1_analysis.pdf]]