Update

analysis/data_stat.py

@@ -3,37 +3,37 @@ import re
 from enum import Enum
 
 class Stat(Enum):
-    CPU = 'cpu'
+    CPU = 'CPU'
 
-    CORES = 'cores'
+    CORES = 'Cores'
-    ITERATIONS = 'iterations'
+    ITERATIONS = 'Iterations'
-    BASELINE_TIME_S = 'baseline time (sec)'
+    BASELINE_TIME_S = 'Baseline Time (sec)'
-    BASELINE_DELAY_S = 'baseline delay (sec)'
+    BASELINE_DELAY_S = 'Baseline Delay (sec)'
 
-    SOLVER = 'solver'
+    SOLVER = 'Solver'
 
-    MATRIX_TYPE = 'matrix type'
+    MATRIX_TYPE = 'Matrix Type'
-    MATRIX_FILE = 'matrix file'
+    MATRIX_FILE = 'Matrix File'
-    MATRIX_FORMAT = 'matrix format'
+    MATRIX_FORMAT = 'Format'
-    MATRIX_SHAPE = 'matrix shape'
+    MATRIX_SHAPE = 'Matrix Shape'
-    MATRIX_ROWS = 'matrix rows'
+    MATRIX_ROWS = 'Rows'
-    MATRIX_SIZE = 'matrix size'
+    MATRIX_SIZE = 'Matrix Size'
-    MATRIX_NNZ = 'matrix nnz'
+    MATRIX_NNZ = 'Number of Non-Zeros'
-    MATRIX_DENSITY = 'matrix density'
+    MATRIX_DENSITY = 'Density'
  
     #POWER_BEFORE = 'power before'
     #POWER = 'power'
     #POWER_AFTER = 'power after'
-    TIME_S = 'time (sec)'
+    TIME_S = 'Time (s)'
-    TIME_S_1KI = 'time (sec) per 1k iterations'
+    TIME_S_1KI = 'Time (s) per 1k Iterations'
-    J = 'joules'
+    J = 'Joules'
-    J_1KI = 'joules per 1k iterations'
+    J_1KI = 'Joules per 1k iterations'
-    J_D = 'Δ joules'
+    J_D = 'Δ Joules'
-    J_D_1KI = 'Δ joules per 1k iterations'
+    J_D_1KI = 'Δ Joules per 1k iterations'
-    W = 'watts'
+    W = 'Watts'
-    W_1KI = 'watts per 1k iterations'
+    W_1KI = 'Watts per 1k iterations'
-    W_D = 'Δ watts'
+    W_D = 'Δ Watts'
-    W_D_1KI = 'Δ watts per 1k iterations'
+    W_D_1KI = 'Δ Watts per 1k iterations'
     #DELTA_WATT = 'Δ watt'
 
     TASK_CLK = 'task clock (msec)'

pytorch/analyze.py

@@ -19,15 +19,32 @@ class Plot(Enum):
     BOX = 'box'
     LINE = 'line'
 
-def accumulate(data_list: list[dict[str, str | int | float]], category: Stat, value: Stat):
+def accumulate(
-    #print(category.name)
+    data_list: list[dict[str, str | int | float]],
-    #print(value.name)
+    category: Stat,
-    category_list = np.array([stats[category.name] for stats in data_list if value.name in stats])
+    category2: Stat,
+    value: Stat
+) -> dict[np.ndarray]:
+    result: dict[np.ndarray] = dict()
+
     value_list = np.array([stats[value.name] for stats in data_list if value.name in stats])
 
-    result: dict[np.ndarray] = dict()
+    if category2 is None:
-    for category in np.sort(np.unique(category_list)):
+        category_list = np.array([(stats[category.name])
-        result[category] = value_list[category_list == category]
+            for stats in data_list if value.name in stats])
+
+        for category in np.unique(category_list):
+            result[category] = value_list[category_list == category]
+    else:
+        category_list = np.array([(stats[category.name],
+                                   stats[category2.name])
+            for stats in data_list if value.name in stats], dtype='object')
+
+        for category in category_list:
+            mask = np.logical_and(category_list[:, 0] == category[0], category_list[:, 1] == category[1])
+            assert (tuple(category) not in result.keys()
+                or np.array_equal(result[tuple(category)], value_list[mask]))
+            result[tuple(category)] = value_list[mask]
 
     return result
 
@@ -41,25 +58,58 @@ def box_plot(ax, data_list: list[dict[str, str | int | float]], x: Stat, y: Stat
 
 def line_plot(
     ax, data_list: list[dict[str, str | int | float]],
-    x: Stat, y: Stat, color: Stat,
+    x: Stat, y: Stat, color: Stat, linestyle: Stat
-    font_size: int
 ):
-    print(x)
+    x_data: dict[str, np.ndarray] = accumulate(data_list, color, linestyle, x)
-    print(y)
+    y_data: dict[str, np.ndarray] = accumulate(data_list, color, linestyle, y)
-    print(color)
-    x_data: dict[str, np.ndarray] = accumulate(data_list, color, x)
-    y_data: dict[str, np.ndarray] = accumulate(data_list, color, y)
 
-    for category in x_data.keys():
+    linestyle_tuple = [
+        ('solid',                 (0, ())),
+        #('loosely dotted',        (0, (1, 10))),
+        ('dotted',                (0, (1, 1))),
+        #('densely dotted',        (0, (1, 1))),
+        ('long dash with offset', (5, (10, 3))),
+        ('loosely dashed',        (0, (5, 10))),
+        ('dashed',                (0, (5, 5))),
+        ('densely dashed',        (0, (5, 1))),
+
+        ('loosely dashdotted',    (0, (3, 10, 1, 10))),
+        ('dashdotted',            (0, (3, 5, 1, 5))),
+        ('densely dashdotted',    (0, (3, 1, 1, 1))),
+
+        ('dashdotdotted',         (0, (3, 5, 1, 5, 1, 5))),
+        ('loosely dashdotdotted', (0, (3, 10, 1, 10, 1, 10))),
+        ('densely dashdotdotted', (0, (3, 1, 1, 1, 1, 1)))]
+
+    if linestyle is None:
+        color_mapping = dict(zip(
+            sorted({color for color in x_data.keys()}),
+            matplotlib.colors.BASE_COLORS.values()))
+    else:
+        color_mapping = dict(zip(
+            sorted({color for (color, _) in x_data.keys()}),
+            matplotlib.colors.BASE_COLORS.values()))
+        linestyle_mapping = dict(zip(
+            sorted({linestyle for (_, linestyle) in x_data.keys()}),
+            [linestyle for (_, linestyle) in linestyle_tuple]))
+    for category in sorted(x_data.keys()):
         sorted_indices = np.argsort(x_data[category])
         x_data[category] = x_data[category][sorted_indices]
         y_data[category] = y_data[category][sorted_indices]
-        ax.plot(x_data[category], y_data[category], label=category)
+        if linestyle is None:
+            ax.plot(x_data[category], y_data[category], label=str(category), marker='o')
+        else:
+            ax.plot(x_data[category], y_data[category], label=str(category[0]) + ", " + str(category[1]),
+                    color=color_mapping[category[0]],
+                    linestyle=linestyle_mapping[category[1]],
+                    marker='o')
         #print("Plotted x data: " + str(x_data[category]))
         #print("Plotted y data: " + str(y_data[category]))
+    #for category, (_, linestyle) in zip(sorted(x_data.keys()), linestyle_tuple):
+        #ax.plot(x_data[category], y_data[category], label=category, marker='o', linestyle=linestyle)
 
-    ax.set_ylabel(y.value, fontsize=font_size)
+    #ax.set_yscale('log')
-    ax.grid(True)
+    #ax.set_xscale('log')
 
 def visualize(
     data_list: list[dict[str, str | int | float]],
@@ -70,6 +120,9 @@ def visualize(
     x: Stat,
     ys: list[Stat],
     color: Stat,
+    linestyle: Stat,
+    x_log: bool,
+    y_log: bool,
     filter_list: list[str],
     title: str
 ):
@@ -98,22 +151,32 @@ def visualize(
     print(int(math.ceil(len(ys) / rows)))
     fig, axes = plt.subplots(rows, int(math.ceil(len(ys) / rows)),
                              figsize = (16 * size_multiplier, 9 * size_multiplier))
+    print(len(axes))
 
     match plot:
         case Plot.BOX:
             for i, y in enumerate(ys):
-                box_plot(axes[i % rows][int(i / rows)], data_list, x, y)
+                ax = axes[i % rows][int(i / rows)]
+                box_plot(ax, data_list, x, y)
         case Plot.LINE:
             for i, y in enumerate(ys):
-                ax = axes[i % rows][int(i / rows)]
+                ax = axes[i % rows]
-                line_plot(ax, data_list, x, y, color, font_size)
+                if len(ys) > len(axes):
+                    ax = ax[int(i / rows)]
+                line_plot(ax, data_list, x, y, color, linestyle)
+
+                ax.set_ylabel(y.value, fontsize=font_size)
+                ax.grid(True)
+                if x_log:
+                    ax.set_xscale('log')
+                if y_log:
+                    ax.set_yscale('log')
                 if type(ax.get_xaxis().get_major_formatter()) is matplotlib.ticker.ScalarFormatter:
                     ax.get_xaxis().get_major_formatter().set_scientific(False)
                 if type(ax.get_yaxis().get_major_formatter()) is matplotlib.ticker.ScalarFormatter:
                     ax.get_yaxis().get_major_formatter().set_scientific(False)
-                #ax.ticklabel_format(axis='both', style='plain')
 
-    handles, labels = axes[i % rows][int(i / rows)].get_legend_handles_labels()
+    handles, labels = ax.get_legend_handles_labels()
 #    else:
 #        fig, ax = plt.subplots()
 #
@@ -135,8 +198,12 @@ def visualize(
 #            #title = f"{plot.value}_plot_of_{y.replace(' ', '_')}_vs_{x.replace(' ', '_')}_by_{color.replace(' ', '_')}_excluding_{filter_list}"
 #            title = "altra_spmv"
     #title = f'{plot.value} plot of {[y.value for y in ys]} vs {x.value} by {color.value} excluding {filter_list}'
-    #fig.suptitle(title, fontsize = font_size)
+    fig.suptitle(title, fontsize = font_size)
-    fig.legend(handles, labels, fontsize = font_size)
+    fig.legend(handles, labels,
+        title=color.value if linestyle is None
+                          else color.value + ", " + linestyle.value,
+        title_fontsize=font_size,
+        fontsize = font_size)
     fig.supxlabel(x.value, fontsize = font_size)
 
     #title = f'{plot.value} plot of {[y.name for y in ys]} vs {x.name} by {color.name} excluding {filter_list}'
@@ -175,6 +242,13 @@ def main():
     parser.add_argument('-c', '--color',
                         choices=[c.name.lower() for c in Stat],
                         help = 'the name of the color')
+    parser.add_argument('-l', '--linestyle',
+                        choices=[l.name.lower() for l in Stat],
+                        help = 'the name of the marker')
+    parser.add_argument('--x_log', action='store_true',
+                        help = 'set x axis scale to log')
+    parser.add_argument('--y_log', action='store_true',
+                        help = 'set y axis scale to log')
     parser.add_argument('-f', '--filter', nargs = '+',
                         help = 'a comma-separated string of names and values to filter out.',
                         default = [])
@@ -184,6 +258,7 @@ def main():
     args.ys = ([Stat[y.upper()] for y in args.ys]
         if args.ys is not None else None)
     args.color = Stat[args.color.upper()] if args.color is not None else None
+    args.linestyle = Stat[args.linestyle.upper()] if args.linestyle is not None else None
 
     data_list: list[dict] = list()
 
@@ -202,6 +277,9 @@ def main():
         args.x,
         args.ys,
         args.color,
+        args.linestyle,
+        args.x_log,
+        args.y_log,
         args.filter,
         args.title
     )