Analysis Scripts: Cleanup computeSMTslowdown.py and libSMT.py

- Don't print superfluous data
- Remove some commented-out code
- Print summary statistics in a format more similar to that used in
  the paper
- Automatically strip the `_all` postfix from the paired benchmarks

2 files changed, 20 insertions, 11 deletions

diff --git a/smt_analysis/computeSMTslowdown.py b/smt_analysis/computeSMTslowdown.py
index 805def1..ba9fa84 100755
--- a/smt_analysis/computeSMTslowdown.py
+++ b/smt_analysis/computeSMTslowdown.py
@@ -34,8 +34,8 @@ OK_PAIRS_ONLY = len(sys.argv) > 4 and "--cij-ok" in sys.argv[4]
 if not LEVEL_C_ANALYSIS:
     baseline_times, baseline_sample_cnt, baseline_max_times = load_baseline(sys.argv[3])
     paired_times, paired_offsets, name_to_idx, idx_to_name = load_paired(sys.argv[1], sys.argv[2], len(list(baseline_times.keys())))
-    for key in baseline_times:
-        print(key,max(baseline_times[key]))
+#    for key in baseline_times:
+#        print(key,max(baseline_times[key]))
 else:
     # Paired times use an abuse of the baseline file format
     baseline_times, baseline_sample_cnt, baseline_max_times = load_baseline(sys.argv[2])
@@ -94,18 +94,23 @@ for b1 in reliableNames:
             print("{:>10.3}".format(M), end=" ")
     print("")
 # Print some statistics about the distribution
-print("Average: {:>5.3} with standard deviation {:>5.3} using `{}`".format(np.mean(M_vals), np.std(M_vals), sample_f.__name__))
+print("Overall average is {:>5.3} with standard deviation {:>5.3} using `{}`".format(np.mean(M_vals), np.std(M_vals), sample_f.__name__))
 Ms = np.asarray(M_vals, dtype=np.float32)
 if not LEVEL_C_ANALYSIS:
     print(np.sum(Ms <= 0), "of", len(M_vals), "M_i:j values are at most zero -", 100*np.sum(Ms <= 0)/len(M_vals), "percent")
     print(np.sum(Ms > 1), "of", len(M_vals), "M_i:j values are greater than one -", 100*np.sum(Ms > 1)/len(M_vals), "percent")
     M_vals_to_plot = Ms[np.logical_and(Ms > 0, Ms <= 1)]
+    # Sims' analysis
+    mean = np.mean(list(M_vals_to_plot))
+    std = np.std(list(M_vals_to_plot))
+    print("For {} of {} M_i:j values in (0, 1], average: {:>5.3} with std. dev. {:>4.3} (coeff. var. {:>4.3}) using `{}`".format(len(M_vals_to_plot), len(M_vals), mean, std, std/mean, sample_f.__name__))
 else:
     print(np.sum(Ms <= 1), "of", len(M_vals), "M_i:j values are at most one -", 100*np.sum(Ms <= 1)/len(M_vals), "percent")
     print(np.sum(Ms > 2), "of", len(M_vals), "M_i:j values are greater than two -", 100*np.sum(Ms > 2)/len(M_vals), "percent")
     M_vals_to_plot = Ms
+    # Sims' analysis
+    print("For {} of {} M_i:j values in (1, 2], average: {:>5.3} with std. dev. {:>4.3} (coeff. var. {:>4.3}) using `{}`".format(len(M_vals_to_plot), len(M_vals), np.mean(list(M_vals_to_plot)), np.std(list(M_vals_to_plot)), np.mean(list(M_vals_to_plot))/np.std(list(M_vals_to_plot)), sample_f.__name__))
 
-print("Using Sim's analysis, average: {:>5.3} with standard deviation {:>5.3} using `{}`".format(np.mean(list(M_vals_to_plot)), np.std(list(M_vals_to_plot)), sample_f.__name__))
 print(plt.hist(M_vals_to_plot, bins=10))
 
 ##### BELOW TEXT IS OLD OFFSET CODE (patched) #####
diff --git a/smt_analysis/libSMT.py b/smt_analysis/libSMT.py
index cca2fce..c0b5178 100755
--- a/smt_analysis/libSMT.py
+++ b/smt_analysis/libSMT.py
@@ -38,6 +38,14 @@ def load_baseline(f):
                 max_res[s[BENCH_NAME]] = max(int(s[TOTAL_NS]), max_res[s[BENCH_NAME]])
     return res, samples, max_res
 
+# Remove the _all prefix if it exists and return the result
+# @param pair_name Name to strip (eg. pointer_all)
+# @returns Stripped name (eg. pointer)
+def strip_pair_postfix(pair_name):
+    if pair_name[-4:] == "_all":
+        return pair_name[:-4]
+    return pair_name
+
 # This parses the result data from paired, threaded timing experiements
 # @param file1 The -A file name
 # @param file2 The -B file name
@@ -93,12 +101,8 @@ def load_paired(file1, file2, benchmarkCount):
             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)
@@ -110,14 +114,14 @@ def load_paired(file1, file2, benchmarkCount):
                     bench2 = bench2 + 1
                     job_idx = 0
                 else:
-                    name_to_idx[lineArr1[FIRST_PROG]] = bench1
-                    idx_to_name[bench1] = lineArr1[FIRST_PROG]
+                    name_to_idx[strip_pair_postfix(lineArr1[FIRST_PROG])] = bench1
+                    idx_to_name[bench1] = strip_pair_postfix(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")
+    print("Average offset is: {:.2f} nanoseconds".format(avg_off/avg_off_samp))
     return time, offset, name_to_idx, idx_to_name
 
 # Paired times use an abuse of the baseline file format