Add script for computing M_i values

Remember, M_i values are the worst-case slowdown of the average-
-case execution time.

Also factor out functions shared with M_ij computation code to a
shared library.

1 files changed, 9 insertions, 145 deletions

diff --git a/smt_analysis/computeSMTslowdown.py b/smt_analysis/computeSMTslowdown.py
index aa7aa21..805def1 100755
--- a/smt_analysis/computeSMTslowdown.py
+++ b/smt_analysis/computeSMTslowdown.py
@@ -3,19 +3,19 @@ from typing import List, Any
 import numpy as np
 from scipy import stats
 import sys
-import os
 import plotille.plotille as plt
 TIMING_ERROR = 1000 #ns
 LEVEL_C_ANALYSIS = False
+from libSMT import *
 
-def print_usage(argv):
+def print_usage():
     print("This program takes in the all-pairs and baseline SMT data and computes how much each program is slowed when SMT in enabled.", file=sys.stderr)
-    print("Level-A/B usage: {} <file -A> <file -B> <baseline file> --cij".format(argv[0]), file=sys.stderr)
-    print("Level-C usage: {} <continuous pairs> <baseline file>".format(argv[0]), file=sys.stderr)
+    print("Level-A/B usage: {} <file -A> <file -B> <baseline file> --cij".format(sys.argv[0]), file=sys.stderr)
+    print("Level-C usage: {} <continuous pairs> <baseline file>".format(sys.argv[0]), file=sys.stderr)
 
 # Check that we got the right number of parameters
 if len(sys.argv) < 3:
-    print_usage(sys.argv)
+    print_usage()
     exit()
 
 if len(sys.argv) > 3:
@@ -24,127 +24,12 @@ else:
     print("Analyzing results using Level-C methodology...")
     LEVEL_C_ANALYSIS = True
 
-# Check that all input files are valid
-for f in sys.argv[1:-1]:
-    if not os.path.exists(f) or os.path.getsize(f) == 0:
-        print("ERROR: File '{}' does not exist or is empty".format(f), file=sys.stderr);
-        print_usage(sys.argv)
-        exit()
+assert_valid_input_files(sys.argv[1:-1], print_usage);
 
 # Print Cij values rather than Mij
 TIMES_ONLY = len(sys.argv) > 4 and "--cij" in sys.argv[4]
 OK_PAIRS_ONLY = len(sys.argv) > 4 and "--cij-ok" in sys.argv[4]
 
-# This parses the result data from unthreaded timing experiments
-# @param f File name to load
-# @returns res Map of benchmark name to sample count
-# @returns samples Map of benchmark name to list of execution time samples
-# @returns max_res May of benchmark to maximum execution time among all samples for that benchmark
-def load_baseline(f):
-    # constants for columns of baseline data files
-    TOTAL_NS = 5
-    BENCH_NAME = 0
-    SAMPLES = 4
-
-    # Load baseline data. This logic is based off the summarize programs
-    res = {} # Map of benchmark to list of all execution time samples
-    samples = {} # Map of benchmark name to sample count
-    max_res = {} # Map of benchmark name to maximum execution time
-
-    with open(f) as fp:
-        for line in fp:
-            s = line.split()
-            if s[BENCH_NAME] not in res:
-                res[s[BENCH_NAME]] = list([int(s[TOTAL_NS])])
-                samples[s[BENCH_NAME]] = int(s[SAMPLES])
-                max_res[s[BENCH_NAME]] = int(s[TOTAL_NS])
-            else:
-                res[s[BENCH_NAME]].append(int(s[TOTAL_NS]))
-                max_res[s[BENCH_NAME]] = max(int(s[TOTAL_NS]), max_res[s[BENCH_NAME]])
-    return res, samples, max_res
-
-# This parses the result data from paired, threaded timing experiements
-# @param file1 The -A file name
-# @param file2 The -B file name
-# @returns time 2D array of benchmark IDs to list of total container execution times
-# @returns offset 2D array of benchmark IDs to list of differences between the start
-#                 of the first and the start of the second benchmark
-# @returns name_to_idx Map of benchmark names to benchmark IDs
-# @returns idx_to_name List which when indexed with benchmark ID will yield the benchmark name
-def load_paired(file1, file2, benchmarkCount):
-    # constants for columns of paired data files
-    FIRST_PROG = 0
-    SECOND_PROG = 1
-    FIRST_CORE = 2
-    SECOND_CORE = 3
-    TRIALS = 4
-    START_S = 5 # Start seconds
-    START_N = 6 # Start nanoseconds
-    END_S = 7   # End seconds
-    END_N = 8   # End nanoseconds
-    RUN_ID = 9
-    JOB_NUM = 10
-
-    with open(file1) as f1:
-        numJobs = int(f1.readline().split()[TRIALS])
-    assert numJobs > 0
-    assert benchmarkCount > 0
-
-    # Total times of each container
-    time=[[[0 for x in range(numJobs)]for y in range(benchmarkCount)]for z in range(benchmarkCount)]
-    # Difference in time between when the first and the second task start in the container
-    offset=[[[0 for x in range(numJobs)]for y in range(benchmarkCount)]for z in range(benchmarkCount)]
-
-    # Some aggregate counters that we update as we go along
-    avg_off = 0
-    avg_off_samp = 0
-
-    # Load paired data
-    bench1 = 0 # Index to what's the current first benchmark being examined
-    bench2 = 0 # Index to what's the current second benchmark being examined
-
-    name_to_idx = {}
-    idx_to_name = [0 for x in range(benchmarkCount)]
-
-    job_idx = 0
-    with open(file1) as f1, open(file2) as f2:
-        for line1, line2 in zip(f1, f2):
-            lineArr1 = line1.split()
-            lineArr2 = line2.split()
-            start1 = int(lineArr1[START_S]) * 10**9 + int(lineArr1[START_N])
-            start2 = int(lineArr2[START_S]) * 10**9 + int(lineArr2[START_N])
-            minStart = min(start1, start2)
-            end1 = int(lineArr1[END_S]) * 10**9 + int(lineArr1[END_N])
-            end2 = int(lineArr2[END_S]) * 10**9 + int(lineArr2[END_N])
-            maxEnd = max(end1, end2)
-            # Time actually co-scheduled is minEnd - maxStart, but Sims uses a different model
-#            time[bench1][bench2][int(lineArr1[JOB_NUM])] = maxEnd - minStart
-            time[bench1][bench2][job_idx] = maxEnd - minStart
-            if lineArr1[SECOND_PROG] == "h264_dec" and lineArr2[JOB_NUM] == 0:
-                print(maxEnd - minStart)
-            # Compute offset: if first job starts at t=0, when does second start?
-#            offset[bench1][bench2][int(lineArr1[JOB_NUM])] = abs(start2-start1)
-            offset[bench1][bench2][job_idx] = abs(start2-start1)
-            # Compute some running statistics
-            avg_off += abs(start2-start1)
-            avg_off_samp += 1
-            # Increment to the next benchmark, this is weird because of the zip()
-            # This is doubly weird because our results are an upper trianguler matrix
-            if job_idx == numJobs - 1: #int(lineArr1[JOB_NUM]) == numJobs - 1:
-                if bench2 < benchmarkCount-1:
-                    bench2 = bench2 + 1
-                    job_idx = 0
-                else:
-                    name_to_idx[lineArr1[FIRST_PROG]] = bench1
-                    idx_to_name[bench1] = lineArr1[FIRST_PROG]
-                    bench1 = bench1 + 1
-                    bench2 = bench1 # bench1 will never again appear as bench2
-                    job_idx = 0
-            else:
-                job_idx += 1
-    print("Average offset is: " + str(avg_off/avg_off_samp) + "ns")
-    return time, offset, name_to_idx, idx_to_name
-
 # Pull in the data
 if not LEVEL_C_ANALYSIS:
     baseline_times, baseline_sample_cnt, baseline_max_times = load_baseline(sys.argv[3])
@@ -152,33 +37,12 @@ if not LEVEL_C_ANALYSIS:
     for key in baseline_times:
         print(key,max(baseline_times[key]))
 else:
-    baseline_times, baseline_sample_cnt, baseline_max_times = load_baseline(sys.argv[2])
     # Paired times use an abuse of the baseline file format
-    paired_times_raw, _, _ = load_baseline(sys.argv[1])
-    benchmarkCount = int(np.sqrt(len(list(paired_times_raw.keys()))))
-    numJobs = len(next(iter(paired_times_raw.values())))
-    paired_times=[[[0 for x in range(numJobs)]for y in range(benchmarkCount)]for z in range(benchmarkCount)]
-    idx_to_name=[]
-    name_to_idx={}
-    bench1 = -1
-    #Generate the indexing approach
-    for pair in sorted(paired_times_raw.keys()):
-        [bench1name, bench2name] = pair.split('+') # Benchmark name is pair concatenated together with a '+' delimiter
-        if bench1 == -1 or bench1name != idx_to_name[-1]:
-            idx_to_name.append(bench1name)
+    baseline_times, baseline_sample_cnt, baseline_max_times = load_baseline(sys.argv[2])
+    paired_times, name_to_idx, idx_to_name = load_fake_paired(sys.argv[1])