From ae4f00b9fdb50444c270ba6ce2a81e6de732401f Mon Sep 17 00:00:00 2001 From: Reynaldo Morillo Date: Tue, 2 May 2017 21:12:31 -0400 Subject: [PATCH] Created a more file of small_data analysis called complete_analysis (which isn't complete yet, I need analysis3.csv). Added code to generate plot for blocks vs time vs algorithm for 1 thread. --- data_analysis.R | 19 ++-- parallel/complete_analysis.csv | 184 +++++++++++++++++++++++++++++++++ 2 files changed, 197 insertions(+), 6 deletions(-) create mode 100644 parallel/complete_analysis.csv diff --git a/data_analysis.R b/data_analysis.R index f3435ab..390e2b6 100644 --- a/data_analysis.R +++ b/data_analysis.R @@ -7,10 +7,12 @@ library(ggplot2) # Load the data # Change path to file # data_path <- '../parallel/analysis.csv' # You can use this instead -data_path <- '/home/reynaldo/Documents/School/Spring2017/HPC/project/parallel_mcmc/parallel/analysis.csv' +data_path <- '/home/reynaldo/Documents/School/Spring2017/HPC/project/parallel_mcmc/parallel/complete_analysis.csv' perf_data <- read.csv(file=data_path, header=TRUE, sep=",") melted_data <- melt(perf_data, id=c("trial", "block", "thread")) five_hundred_trials <- melted_data[which(melted_data$trial == 500), ] +five_hundred_trials$thread = as.factor(five_hundred_trials$thread) + # Generate Plots @@ -23,7 +25,6 @@ base_plot <- base_plot + ggtitle("Blocks vs Time") + theme(plot.title = element_ base_plot # Find which combination of blocks and threads works best -five_hundred_trials$thread = as.factor(five_hundred_trials$thread) ours_five_hundred_trials <- five_hundred_trials[which(five_hundred_trials$variable == "our_time"), ] ours_five_hundred_trials <- ours_five_hundred_trials[which(!is.na(ours_five_hundred_trials$thread)), ] @@ -34,10 +35,16 @@ line_base <- line_base + xlab("Blocks") + ylab("Time (seconds)") + labs(colour line_base <- line_base + ggtitle("Blocks vs Time vs Threads") + theme(plot.title = element_text(hjust = 0.5)) line_base -# Line Plot -line_base <- ggplot(five_hundred_trials, aes(x=block, y=value, group=variable, shape=variable, color=variable)) + + +# Best Number of threads vs The other implementations for Blocks vs Time +one_threads_500_trials <- five_hundred_trials[which(five_hundred_trials$thread == 1), ] + +line_base <- ggplot(one_threads_500_trials, aes(x=block, y=value, group=variable, shape=variable, color=variable)) + geom_line() + geom_point() -line_base <- line_base + xlab("Blocks") + ylab("Time (seconds)") -line_base <- line_base + ggtitle("Blocks vs Time") + theme(plot.title = element_text(hjust = 0.5)) +line_base <- line_base + xlab("Blocks") + ylab("Time (seconds)") + labs(colour = "Implementations", shape="Implementations") +line_base <- line_base + ggtitle("Blocks vs Time vs Implementation") + theme(plot.title = element_text(hjust = 0.5)) line_base + + + diff --git a/parallel/complete_analysis.csv b/parallel/complete_analysis.csv new file mode 100644 index 0000000..0bf716e --- /dev/null +++ b/parallel/complete_analysis.csv @@ -0,0 +1,184 @@ +trial,block,thread,seq_time,our_time,their_time +1000,10,1,2.48,7.14,5.51 +1000,10,1,2.53,6.67,5.51 +1000,10,16,2.50,139.07,5.48 +1000,10,16,2.54,178.51,5.44 +1000,10,2,2.51,8.21,5.53 +1000,10,2,2.52,8.76,5.73 +1000,10,32,2.51,538.93,5.67 +1000,10,4,2.52,13.49,5.76 +1000,10,4,2.56,16.78,5.43 +1000,10,8,2.48,38.57,5.68 +1000,10,8,2.50,49.38,5.51 +1000,1,1,2.52,15.32,3.50 +1000,1,1,2.56,17.62,5.64 +1000,1,16,2.50,27.86,5.47 +1000,1,16,2.52,4.98,3.51 +1000,1,2,2.49,9.16,3.48 +1000,1,2,2.50,11.39,5.43 +1000,1,32,2.48,52.96,5.74 +1000,1,32,2.54,8.68,3.48 +1000,1,4,2.53,8.39,5.42 +1000,1,4,2.56,6.09,3.47 +1000,1,8,2.53,7.11,5.84 +1000,1,8,2.54,4.80,3.48 +1000,2,1,2.50,11.11,5.80 +1000,2,1,2.53,9.06,3.53 +1000,2,16,2.49,8.60,3.49 +1000,2,16,2.53,12.81,5.52 +1000,2,2,2.52,6.00,3.49 +1000,2,2,2.53,8.29,5.54 +1000,2,32,2.51,33.89,5.45 +1000,2,32,2.54,24.51,3.52 +1000,2,4,2.49,7.04,5.56 +1000,2,4,2.52,4.74,3.48 +1000,2,8,2.48,27.41,5.68 +1000,2,8,2.48,4.85,3.46 +1000,3,1,2.50,6.92,3.48 +1000,3,1,2.51,9.33,5.67 +1000,3,16,2.50,15.13,3.48 +1000,3,16,2.50,21.80,5.75 +1000,3,2,2.48,5.03,3.43 +1000,3,2,2.49,7.32,5.64 +1000,3,32,2.51,51.25,3.50 +1000,3,32,2.55,68.31,5.77 +1000,3,4,2.48,4.48,3.49 +1000,3,4,2.51,20.97,5.62 +1000,3,8,2.51,6.26,3.49 +1000,3,8,2.54,9.66,5.54 +1000,4,1,2.51,8.08,5.41 +1000,4,1,2.56,5.88,3.52 +1000,4,16,2.51,33.86,5.76 +1000,4,16,2.52,26.73,5.79 +1000,4,2,2.48,7.51,5.56 +1000,4,2,2.49,4.64,3.43 +1000,4,32,2.49,116.94,5.75 +1000,4,32,2.53,90.77,5.67 +1000,4,4,2.49,9.10,5.70 +1000,4,4,2.53,7.95,5.80 +1000,4,8,2.52,10.62,5.57 +1000,4,8,2.55,12.74,5.42 +1000,5,1,2.48,7.32,5.71 +1000,5,1,2.48,7.45,5.60 +1000,5,16,2.55,49.56,5.50 +1000,5,16,2.58,38.65,5.47 +1000,5,2,2.48,6.85,5.81 +1000,5,2,2.51,7.19,5.40 +1000,5,32,2.52,139.01,5.45 +1000,5,32,2.60,178.62,5.43 +1000,5,4,2.50,32.43,5.55 +1000,5,4,2.52,7.65,5.66 +1000,5,8,2.51,17.09,5.76 +1000,5,8,2.54,13.71,5.54 +1000,6,1,2.49,7.02,5.72 +1000,6,1,2.50,7.37,5.83 +1000,6,16,2.48,53.47,5.64 +1000,6,16,2.51,68.46,5.76 +1000,6,2,2.53,6.64,5.64 +1000,6,2,2.55,7.03,5.40 +1000,6,32,2.50,253.79,5.50 +1000,6,32,2.51,197.33,5.52 +1000,6,4,2.48,8.74,5.50 +1000,6,4,2.50,9.83,5.65 +1000,6,8,2.48,17.27,5.44 +1000,6,8,2.54,23.41,5.85 +1000,7,1,2.49,6.93,5.51 +1000,7,1,2.50,7.14,5.43 +1000,7,16,2.51,70.84,5.40 +1000,7,16,2.51,90.67,5.52 +1000,7,2,2.48,6.81,5.54 +1000,7,2,2.48,7.59,5.54 +1000,7,32,2.51,342.33,5.46 +1000,7,32,2.54,266.71,5.59 +1000,7,4,2.50,9.88,5.60 +1000,7,4,2.52,11.09,5.50 +1000,7,8,2.49,27.16,5.48 +1000,7,8,2.50,21.47,5.72 +1000,8,1,2.49,6.63,5.56 +1000,8,1,2.52,6.93,5.61 +1000,8,16,2.51,116.35,5.51 +1000,8,16,2.52,90.62,5.77 +1000,8,2,2.52,7.20,5.69 +1000,8,2,2.53,26.16,5.58 +1000,8,32,2.49,444.95,5.70 +1000,8,32,2.54,346.69,5.90 +1000,8,4,2.48,12.75,5.58 +1000,8,4,2.56,12.69,5.52 +1000,8,8,2.50,33.50,5.39 +1000,8,8,2.51,26.50,5.41 +1000,9,1,2.53,7.05,5.69 +1000,9,1,2.57,6.84,5.53 +1000,9,16,2.52,145.90,5.79 +1000,9,16,2.53,113.43,6.01 +1000,9,2,2.52,8.06,5.59 +1000,9,2,2.53,7.56,5.47 +1000,9,32,2.52,437.83,5.73 +1000,9,32,2.52,560.67,5.59 +1000,9,4,2.51,12.51,5.68 +1000,9,4,2.52,14.89,5.59 +1000,9,8,2.51,41.42,6.13 +1000,9,8,2.52,32.33,5.51 +1500,1,1,3.77,24.00,6.07 +1500,1,2,3.76,14.91,5.99 +1500,1,4,3.76,10.19,6.00 +1500,1,8,3.78,8.27,5.87 +500,10,1,1.25,5.79,4.94 +500,10,16,1.27,91.35,5.14 +500,10,2,1.25,6.78,5.38 +500,10,32,1.25,347.22,4.99 +500,10,4,1.25,10.76,5.09 +500,10,8,1.28,27.12,5.07 +500,1,1,1.32,11.04,5.19 +500,1,16,1.23,11.17,5.09 +500,1,2,1.25,7.83,5.12 +500,1,32,1.23,19.00,5.06 +500,1,4,1.23,6.29,5.26 +500,1,8,1.23,5.71,4.91 +500,2,1,1.24,7.77,4.93 +500,2,16,1.26,8.75,5.10 +500,2,2,1.23,6.46,5.08 +500,2,32,1.24,19.14,5.01 +500,2,4,1.31,5.81,5.20 +500,2,8,1.31,11.47,5.36 +500,3,1,1.26,6.83,5.16 +500,3,16,1.24,13.03,5.14 +500,3,2,1.25,5.91,5.15 +500,3,32,1.26,36.76,5.08 +500,3,4,1.28,9.60,5.05 +500,3,8,1.30,7.16,5.15 +500,4,1,1.28,6.42,5.03 +500,4,16,1.24,19.18,5.13 +500,4,2,1.25,7.63,5.07 +500,4,32,1.29,60.84,5.30 +500,4,4,1.27,6.24,5.02 +500,4,8,1.25,8.76,5.15 +500,5,1,1.27,6.14,5.01 +500,5,16,1.24,26.93,4.97 +500,5,2,1.28,5.66,5.10 +500,5,32,1.27,91.70,5.16 +500,5,4,1.29,7.33,5.05 +500,5,8,1.23,10.78,5.47 +500,6,1,1.24,5.86,5.38 +500,6,16,1.25,36.46,5.02 +500,6,2,1.24,5.90,5.24 +500,6,32,1.25,129.10,5.10 +500,6,4,1.25,7.49,4.99 +500,6,8,1.23,13.03,5.03 +500,7,1,1.27,5.94,5.04 +500,7,16,1.30,48.24,4.95 +500,7,2,1.25,6.21,5.07 +500,7,32,1.26,173.50,5.05 +500,7,4,1.23,7.91,5.04 +500,7,8,1.24,15.93,5.00 +500,8,1,1.24,5.87,5.11 +500,8,16,1.26,60.60,4.93 +500,8,2,1.26,6.27,5.56 +500,8,32,1.23,224.66,5.02 +500,8,4,1.25,8.68,5.42 +500,8,8,1.24,19.21,5.11 +500,9,1,1.28,6.08,5.30 +500,9,16,1.25,75.13,5.04 +500,9,2,1.25,6.55,5.15 +500,9,32,1.26,282.70,4.96 +500,9,4,1.31,9.61,5.14 +500,9,8,1.30,23.06,4.95