From 76deac0a63897786bc11cab5f156d22b04db082a Mon Sep 17 00:00:00 2001
From: Rodrigo Arias Mallo <rodrigo.arias@bsc.es>
Date: Tue, 30 Mar 2021 15:59:52 +0200
Subject: [PATCH] creams: update figures using one single pipeline

---
 garlic/fig/creams/gran.R        |  71 ------------
 garlic/fig/creams/granularity.R |  97 ++++++++++++++++
 garlic/fig/creams/ss.R          | 198 ++++++++++++++++++--------------
 garlic/fig/index.nix            |  12 +-
 4 files changed, 212 insertions(+), 166 deletions(-)
 delete mode 100644 garlic/fig/creams/gran.R
 create mode 100644 garlic/fig/creams/granularity.R

diff --git a/garlic/fig/creams/gran.R b/garlic/fig/creams/gran.R
deleted file mode 100644
index d0d3149..0000000
--- a/garlic/fig/creams/gran.R
+++ /dev/null
@@ -1,71 +0,0 @@
-library(ggplot2)
-library(dplyr)
-library(scales)
-library(jsonlite)
-
-args=commandArgs(trailingOnly=TRUE)
-
-# Read the timetable from args[1]
-input_file = "input.json"
-if (length(args)>0) { input_file = args[1] }
-
-# Load the dataset in NDJSON format
-dataset = jsonlite::stream_in(file(input_file), verbose=FALSE) %>%
-  jsonlite::flatten()
-
-# We only need some colums
-df = select(dataset, unit, config.nodes, config.gitBranch,
-    config.granul, time, total_time) %>%
-  rename(nodes=config.nodes, gitBranch=config.gitBranch,
-    granul=config.granul)
-
-df$unit = as.factor(df$unit)
-df$nnodes = df$nodes
-df$nodes = as.factor(df$nodes)
-df$gitBranch = as.factor(df$gitBranch)
-df$granul = as.factor(df$granul)
-
-# Remove the "garlic/" prefix from the gitBranch
-levels(df$gitBranch) <- substring((levels(df$gitBranch)), 8)
-
-# Compute new columns
-D=group_by(df, unit) %>%
-  mutate(tnorm = time / median(time) - 1) %>%
-  mutate(bad = ifelse(max(abs(tnorm)) >= 0.01, 1, 0)) %>%
-  mutate(variability = ifelse(bad > 0, "large", "ok")) %>%
-  mutate(mtime = median(time)) %>%
-  mutate(nmtime = mtime*nnodes) %>%
-  mutate(ntime = time*nnodes) %>%
-  ungroup() %>%
-  mutate(min_nmtime = min(nmtime)) %>%
-  mutate(rnmtime = nmtime / min_nmtime) %>%
-  mutate(rntime = ntime / min_nmtime) %>%
-  mutate(rmeff = 1.0 / rnmtime) %>%
-  mutate(reff = 1.0 / rntime) %>%
-  group_by(gitBranch) %>%
-  mutate(tmax = max(mtime)) %>%
-  mutate(speedup=tmax/time) %>%
-  mutate(eff=speedup/nnodes) %>%
-  mutate(mspeedup=tmax/mtime) %>%
-  mutate(meff=mspeedup/nnodes) %>%
-  ungroup()
-
-D$bad = as.factor(D$bad > 0)
-D$variability = as.factor(D$variability)
-
-ppi=300
-h=5
-w=5
-
-png("time.png", width=w*1.5*ppi, height=h*ppi, res=ppi)
-p = ggplot(D, aes(x=granul, y=mtime, linetype=gitBranch, shape=nodes)) +
-  geom_line(aes(group=interaction(nodes, gitBranch))) +
-  geom_point(aes(y=time)) +
-  scale_y_continuous(trans=log2_trans()) +
-  labs(x="Granularity", y="Time (s)",
-    title="Creams granularity",
-    subtitle=input_file) +
-  theme_bw() +
-  theme(plot.subtitle=element_text(size=8))
-print(p)
-dev.off()
diff --git a/garlic/fig/creams/granularity.R b/garlic/fig/creams/granularity.R
new file mode 100644
index 0000000..d77740a
--- /dev/null
+++ b/garlic/fig/creams/granularity.R
@@ -0,0 +1,97 @@
+library(ggplot2)
+library(dplyr, warn.conflicts = FALSE)
+library(scales)
+library(jsonlite)
+library(viridis, warn.conflicts = FALSE)
+library(stringr)
+
+args = commandArgs(trailingOnly=TRUE)
+
+# Set the input dataset if given in argv[1], or use "input" as default
+if (length(args)>0) { input_file = args[1] } else { input_file = "input" }
+
+df = jsonlite::stream_in(file(input_file), verbose=FALSE) %>%
+
+  jsonlite::flatten() %>%
+
+  select(unit,
+    config.nodes,
+    config.gitBranch,
+    config.granul,
+    config.iterations,
+    time,
+    total_time) %>%
+
+  rename(nodes=config.nodes,
+    gitBranch=config.gitBranch,
+    granul=config.granul,
+    iterations=config.iterations) %>%
+
+  # Remove the "garlic/" prefix from the gitBranch
+  mutate(branch = str_replace(gitBranch, "garlic/", "")) %>%
+
+  # Computations  before converting to factor
+  mutate(time.iter = time / iterations) %>%
+
+  # Convert to factors
+  mutate(unit = as.factor(unit)) %>%
+  mutate(nodesFactor = as.factor(nodes)) %>%
+  mutate(gitBranch = as.factor(gitBranch)) %>%
+  mutate(granul = as.factor(granul)) %>%
+  mutate(iterations = as.factor(iterations)) %>%
+  mutate(unit = as.factor(unit)) %>%
+
+  # Compute median times
+  group_by(unit) %>%
+  mutate(median.time = median(time)) %>%
+  mutate(normalized.time = time / median.time - 1) %>%
+  mutate(log.median.time = log(median.time)) %>%
+  mutate(median.time.iter = median(time.iter)) %>%
+  ungroup()
+
+dpi = 300
+h = 6
+w = 6
+
+# ---------------------------------------------------------------------
+
+p = ggplot(df, aes(x=granul, y=normalized.time)) +
+  geom_boxplot() +
+  geom_hline(yintercept=c(-0.01, 0.01), linetype="dashed", color="red") +
+  theme_bw() +
+  facet_wrap(branch ~ .) +
+  labs(x="granul", y="Normalized time",
+       title="Creams granularity: normalized time", 
+    subtitle=input_file) + 
+  theme(plot.subtitle=element_text(size=8))
+
+ggsave("normalized.time.png", plot=p, width=w, height=h, dpi=dpi)
+ggsave("normalized.time.pdf", plot=p, width=w, height=h, dpi=dpi)
+
+# ---------------------------------------------------------------------
+
+p = ggplot(df, aes(x=granul, y=time)) +
+  geom_point(shape=21, size=3) +
+  geom_line(aes(y=median.time, group=iterations)) +
+  theme_bw() +
+  facet_wrap(branch ~ .) +
+  labs(x="granul", y="Time (s)", title="Creams granularity: time", 
+    subtitle=input_file) + 
+  theme(plot.subtitle=element_text(size=8))
+
+ggsave("time.png", plot=p, width=w, height=h, dpi=dpi)
+ggsave("time.pdf", plot=p, width=w, height=h, dpi=dpi)
+
+# ---------------------------------------------------------------------
+
+p = ggplot(df, aes(x=granul, y=time.iter, color=iterations)) +
+  geom_point(shape=21, size=3) +
+  geom_line(aes(y=median.time.iter, group=iterations)) +
+  theme_bw() +
+  facet_wrap(branch ~ .) +
+  labs(x="granul", y="Time (s)", title="Creams granularity: time / iterations", 
+    subtitle=input_file) + 
+  theme(plot.subtitle=element_text(size=8))
+
+ggsave("time.iter.png", plot=p, width=w, height=h, dpi=dpi)
+ggsave("time.iter.pdf", plot=p, width=w, height=h, dpi=dpi)
diff --git a/garlic/fig/creams/ss.R b/garlic/fig/creams/ss.R
index 5f274a8..1f09842 100644
--- a/garlic/fig/creams/ss.R
+++ b/garlic/fig/creams/ss.R
@@ -1,107 +1,127 @@
 library(ggplot2)
-library(dplyr)
+library(dplyr, warn.conflicts = FALSE)
 library(scales)
 library(jsonlite)
+library(viridis, warn.conflicts = FALSE)
+library(stringr)
 
-args=commandArgs(trailingOnly=TRUE)
+args = commandArgs(trailingOnly=TRUE)
 
-# Read the timetable from args[1]
-input_file = "input.json"
-if (length(args)>0) { input_file = args[1] }
+# Set the input dataset if given in argv[1], or use "input" as default
+if (length(args)>0) { input_file = args[1] } else { input_file = "input" }
 
-# Load the dataset in NDJSON format
-dataset = jsonlite::stream_in(file(input_file), verbose=FALSE) %>%
-  jsonlite::flatten()
+df = jsonlite::stream_in(file(input_file), verbose=FALSE) %>%
 
-# We only need some colums
-df = select(dataset, unit, config.nodes, config.gitBranch, time) %>%
-  rename(nodes=config.nodes, gitBranch=config.gitBranch)
+  jsonlite::flatten() %>%
 
-df$unit = as.factor(df$unit)
-df$nnodes = df$nodes
-df$nodes = as.factor(df$nodes)
-df$gitBranch = as.factor(df$gitBranch)
+  select(unit,
+    config.nodes,
+    config.gitBranch,
+    config.granul,
+    config.iterations,
+    time,
+    total_time) %>%
 
-# Remove the "garlic/" prefix from the gitBranch
-levels(df$gitBranch) <- substring((levels(df$gitBranch)), 8)
+  rename(nodes=config.nodes,
+    gitBranch=config.gitBranch,
+    granul=config.granul,
+    iterations=config.iterations) %>%
 
-# Compute new columns
-D=group_by(df, unit) %>%
-  mutate(tnorm = time / median(time) - 1) %>%
-  mutate(bad = ifelse(max(abs(tnorm)) >= 0.01, 1, 0)) %>%
-  mutate(variability = ifelse(bad > 0, "large", "ok")) %>%
-  mutate(mtime = median(time)) %>%
-  mutate(nmtime = mtime*nnodes) %>%
-  mutate(ntime = time*nnodes) %>%
-  ungroup() %>%
-  mutate(min_nmtime = min(nmtime)) %>%
-  mutate(rnmtime = nmtime / min_nmtime) %>%
-  mutate(rntime = ntime / min_nmtime) %>%
-  mutate(rmeff = 1.0 / rnmtime) %>%
-  mutate(reff = 1.0 / rntime) %>%
-  group_by(gitBranch) %>%
-  mutate(tmax = max(mtime)) %>%
-  mutate(speedup=tmax/time) %>%
-  mutate(eff=speedup/nnodes) %>%
-  mutate(mspeedup=tmax/mtime) %>%
-  mutate(meff=mspeedup/nnodes) %>%
+  # Remove the "garlic/" prefix from the gitBranch
+  mutate(branch = str_replace(gitBranch, "garlic/", "")) %>%
+
+  # Computations  before converting to factor
+  mutate(time.nodes = time * nodes) %>%
+  mutate(time.nodes.iter = time.nodes / iterations) %>%
+
+  # Convert to factors
+  mutate(unit = as.factor(unit)) %>%
+  mutate(nodes = as.factor(nodes)) %>%
+  mutate(gitBranch = as.factor(gitBranch)) %>%
+  mutate(granul = as.factor(granul)) %>%
+  mutate(iterations = as.factor(iterations)) %>%
+  mutate(unit = as.factor(unit)) %>%
+
+  # Compute median times
+  group_by(unit) %>%
+  mutate(median.time = median(time)) %>%
+  mutate(median.time.nodes = median(time.nodes)) %>%
+  mutate(normalized.time = time / median.time - 1) %>%
+  mutate(log.median.time = log(median.time)) %>%
+  mutate(median.time.nodes.iter = median(time.nodes.iter)) %>%
   ungroup()
 
-D$bad = as.factor(D$bad > 0)
-D$variability = as.factor(D$variability)
+dpi = 300
+h = 5
+w = 8
 
-ppi=300
-h=5
-w=5
+# ---------------------------------------------------------------------
 
-png("variability.png", width=1.5*w*ppi, height=h*ppi, res=ppi)
-p = ggplot(data=D, aes(x=nodes, y=tnorm, color=variability)) +
+p = ggplot(df, aes(x=nodes, y=normalized.time, fill=granul, color=iterations)) +
+  geom_boxplot() +
+  geom_hline(yintercept=c(-0.01, 0.01), linetype="dashed", color="red") +
   theme_bw() +
-  theme(plot.subtitle=element_text(size=8)) +
-  # Add the maximum allowed error lines
-  geom_hline(yintercept=c(-0.01, 0.01),
-    linetype="dashed", color="gray") +
-  # Draw boxplots
-  geom_boxplot(aes(fill=gitBranch)) +
-  scale_color_manual(values=c("brown", "black")) +
-  # Labels
-  labs(x="Nodes", y="Normalized time", title="Creams strong scaling",
-    subtitle=input_file)
-print(p)
-dev.off()
+  facet_wrap(branch ~ .) +
+  labs(x="nodes", y="Normalized time",
+    title="Creams strong scaling: normalized time", 
+    subtitle=input_file) + 
+  theme(plot.subtitle=element_text(size=8))
 
-png("time.png", width=w*1.5*ppi, height=h*ppi, res=ppi)
-p = ggplot(D, aes(x=nodes, y=mtime, color=gitBranch)) +
-  theme_bw() +
-  theme(plot.subtitle=element_text(size=8)) +
-  geom_line(aes(group=gitBranch)) +
-  #geom_point() +
-  geom_point(aes(shape=variability), size=3) +
-  scale_shape_manual(values=c(21, 19)) +
-  #  position=position_dodge(width=0.3)) +
-  #scale_x_continuous(trans=log2_trans()) +
-  scale_y_continuous(trans=log2_trans()) +
-  labs(x="Nodes", y="Time (s)",
-    title="Creams strong scaling (lower is better)",
-    subtitle=input_file)
-print(p)
-dev.off()
+ggsave("normalized.time.png", plot=p, width=w, height=h, dpi=dpi)
+ggsave("normalized.time.pdf", plot=p, width=w, height=h, dpi=dpi)
 
-png("refficiency.png", width=w*1.5*ppi, height=h*ppi, res=ppi)
-p = ggplot(D, aes(x=nodes, y=rmeff, color=gitBranch)) +
+# ---------------------------------------------------------------------
+
+p = ggplot(df, aes(x=nodes, y=time, color=gitBranch)) +
+  geom_point(shape=21, size=3) +
+  geom_line(aes(y=median.time, group=gitBranch)) +
   theme_bw() +
-  theme(plot.subtitle=element_text(size=8)) +
-  geom_line(aes(group=gitBranch)) +
-  geom_point(aes(shape=variability), size=3) +
-  #geom_boxplot(aes(y=reff),
-  #  position=position_dodge(width=0.0)) +
-  scale_shape_manual(values=c(21, 19)) +
-  #geom_point(aes(y=rntime),
-  #  position=position_dodge(width=0.3)) +
-  #scale_x_continuous(trans=log2_trans()) +
-  #scale_y_continuous(trans=log2_trans()) +
-  labs(x="Nodes", y="Relative efficiency (to best)",
-    title="Creams strong scaling (higher is better)",
-    subtitle=input_file)
-print(p)
-dev.off()
+#  facet_wrap(branch ~ .) +
+  labs(x="nodes", y="Time (s)", title="Creams strong scaling: time", 
+    subtitle=input_file) + 
+  theme(plot.subtitle=element_text(size=8))
+
+ggsave("time.png", plot=p, width=w, height=h, dpi=dpi)
+ggsave("time.pdf", plot=p, width=w, height=h, dpi=dpi)
+
+# ---------------------------------------------------------------------
+
+p = ggplot(df, aes(x=nodes, y=median.time.nodes, color=branch)) +
+  geom_point(shape=21, size=3) +
+  geom_line(aes(group=branch)) +
+  theme_bw() +
+  #facet_wrap(branch ~ .) +
+  labs(x="nodes", y="Median time * nodes (s)", title="Creams strong scaling: median time * nodes", 
+    subtitle=input_file) + 
+  theme(plot.subtitle=element_text(size=8))
+
+ggsave("median.time.nodes.png", plot=p, width=w, height=h, dpi=dpi)
+ggsave("median.time.nodes.pdf", plot=p, width=w, height=h, dpi=dpi)
+
+# ---------------------------------------------------------------------
+
+p = ggplot(df, aes(x=nodes, y=time.nodes, color=branch)) +
+  geom_boxplot() +
+  theme_bw() +
+  facet_wrap(branch ~ .) +
+  labs(x="nodes", y="Time * nodes (s)", title="Creams strong scaling: time * nodes", 
+    subtitle=input_file) + 
+  theme(plot.subtitle=element_text(size=8))
+
+ggsave("time.nodes.boxplot.png", plot=p, width=w, height=h, dpi=dpi)
+ggsave("time.nodes.boxplot.pdf", plot=p, width=w, height=h, dpi=dpi)
+
+# ---------------------------------------------------------------------
+
+#p = ggplot(df, aes(x=nodes, y=time.nodes.iter, color=branch)) +
+#  geom_point(shape=21, size=3) +
+#  geom_line(aes(y=median.time.nodes.iter, group=interaction(granul,iterations))) +
+#  theme_bw() +
+#  #facet_wrap(branch ~ .) +
+#  labs(x="nodes", y="Time * nodes / iterations (s)",
+#    title="Creams strong scaling: time * nodes / iterations", 
+#    subtitle=input_file) + 
+#  theme(plot.subtitle=element_text(size=8))
+#
+#ggsave("time.nodes.iter.png", plot=p, width=w, height=h, dpi=dpi)
+#ggsave("time.nodes.iter.pdf", plot=p, width=w, height=h, dpi=dpi)
diff --git a/garlic/fig/index.nix b/garlic/fig/index.nix
index 137c629..201d68f 100644
--- a/garlic/fig/index.nix
+++ b/garlic/fig/index.nix
@@ -52,12 +52,12 @@ in
   };
 
   creams = with exp.creams; {
-    ss = stdPlot ./creams/ss.R [ ss.hybrid ss.pure ];
-    gran1 = stdPlot ./creams/gran.R [ gran.node1 ];
-    gran2 = stdPlot ./creams/gran.R [ gran.node2 ];
-    gran4 = stdPlot ./creams/gran.R [ gran.node4 ];
-    gran8 = stdPlot ./creams/gran.R [ gran.node8 ];
-    gran16 = stdPlot ./creams/gran.R [ gran.node16 ];
+    ss = stdPlot ./creams/ss.R [ ss ];
+    granularity = stdPlot ./creams/granularity.R [ granularity ];
+
+    # Extended version (we could use another R script for those plots
+    big.ss = stdPlot ./creams/ss.R [ big.ss ];
+    big.granularity = stdPlot ./creams/granularity.R [ big.granularity ];
   };
 
   osu = with exp.osu; {