onsuccess: #102: 1: [TCWG CI] https://ci.linaro.org/job/tcwg_bmk-code_speed-cpu2017rate--llvm-arm-master-O2_LTO-build/102/

Results :
  | # reset_artifacts:
  | -10
  | # build_bmk_llvm:
  | -3
  | # benchmark -- -O2_LTO_marm:
  | 1

check_regression status : 0

1 files changed, 222 insertions, 68 deletions

diff --git a/notify/output-bmk-results.log b/notify/output-bmk-results.log
index 04e7258..e530c16 100644
--- a/notify/output-bmk-results.log
+++ b/notify/output-bmk-results.log
@@ -103,25 +103,70 @@ output-bmk-results.py(22):        self.outf = open(filename, mode)
 output-bmk-results.py(23):        self.csvwriter = csv.writer(self.outf)
 output-bmk-results.py(258):     print(results_df)
           benchmark                    symbol  ...       status_x       status_y
-0         505.mcf_r        mcf_r_base.default  ...             -1        success
-2      510.parest_r     parest_r_base.default  ...  failed-to-run  failed-to-run
-3      511.povray_r     povray_r_base.default  ...  failed-to-run  failed-to-run
-4         519.lbm_r        lbm_r_base.default  ...  failed-to-run  failed-to-run
-5         519.lbm_r        lbm_r_base.default  ...  failed-to-run  failed-to-run
-6     520.omnetpp_r    omnetpp_r_base.default  ...  failed-to-run  failed-to-run
-7   523.xalancbmk_r   cpuxalan_r_base.default  ...  failed-to-run  failed-to-run
-8   523.xalancbmk_r   cpuxalan_r_base.default  ...  failed-to-run  failed-to-run
-9        525.x264_r       x264_r_base.default  ...  failed-to-run  failed-to-run
-10    526.blender_r    blender_r_base.default  ...  failed-to-run  failed-to-run
-11  531.deepsjeng_r  deepsjeng_r_base.default  ...        success        success
-12    538.imagick_r    imagick_r_base.default  ...  failed-to-run             -1
-14    538.imagick_r    imagick_r_base.default  ...  failed-to-run  failed-to-run
-15      541.leela_r      leela_r_base.default  ...  failed-to-run             -1
-16      541.leela_r      leela_r_base.default  ...  failed-to-run  failed-to-run
-18        544.nab_r        nab_r_base.default  ...  failed-to-run  failed-to-run
-19         557.xz_r         xz_r_base.default  ...        success        success
+0   500.perlbench_r  perlbench_r_base.default  ...  failed-to-run  failed-to-run
+1         502.gcc_r     cpugcc_r_base.default  ...  failed-to-run  failed-to-run
+2         505.mcf_r        mcf_r_base.default  ...        success        success
+4        508.namd_r       namd_r_base.default  ...  failed-to-run  failed-to-run
+5      510.parest_r     parest_r_base.default  ...  failed-to-run  failed-to-run
+6      511.povray_r     povray_r_base.default  ...  failed-to-run  failed-to-run
+7         519.lbm_r        lbm_r_base.default  ...  failed-to-run  failed-to-run
+8         519.lbm_r        lbm_r_base.default  ...  failed-to-run  failed-to-run
+9     520.omnetpp_r    omnetpp_r_base.default  ...  failed-to-run  failed-to-run
+10  523.xalancbmk_r   cpuxalan_r_base.default  ...  failed-to-run  failed-to-run
+11  523.xalancbmk_r   cpuxalan_r_base.default  ...  failed-to-run  failed-to-run
+12       525.x264_r       x264_r_base.default  ...  failed-to-run  failed-to-run
+13    526.blender_r    blender_r_base.default  ...  failed-to-run  failed-to-run
+14  531.deepsjeng_r  deepsjeng_r_base.default  ...        success        success
+15    538.imagick_r    imagick_r_base.default  ...             -1  failed-to-run
+16    538.imagick_r    imagick_r_base.default  ...             -1  failed-to-run
+18      541.leela_r      leela_r_base.default  ...             -1  failed-to-run
+19      541.leela_r      leela_r_base.default  ...             -1  failed-to-run
+21        544.nab_r        nab_r_base.default  ...  failed-to-run  failed-to-run
+22         557.xz_r         xz_r_base.default  ...        success        success
 
-[17 rows x 20 columns]
+[20 rows x 20 columns]
+output-bmk-results.py(261):     for index, row in results_df.iterrows():
+output-bmk-results.py(263):         classif, short_diag = get_status_diag(row)
+ --- modulename: output-bmk-results, funcname: get_status_diag
+output-bmk-results.py(113):     bmk = row["benchmark"]
+output-bmk-results.py(115):     short_diag=""
+output-bmk-results.py(116):     classif=""
+output-bmk-results.py(118):     if row["status_x"]!="failed-to-build" and row["status_y"]=="failed-to-build":
+output-bmk-results.py(121):     elif row["status_x"]=="success" and row["status_y"]=="failed-to-run":
+output-bmk-results.py(124):     elif row["status_x"]=="failed-to-build" and row["status_y"]=="failed-to-run":
+output-bmk-results.py(127):     elif row["status_x"]=="failed-to-run" and row["status_y"]=="success":
+output-bmk-results.py(130):     elif row["status_x"]=="failed-to-build" and row["status_y"]=="success":
+output-bmk-results.py(134):     return classif, short_diag
+output-bmk-results.py(265):         if classif != change_kind:
+output-bmk-results.py(266):             continue;
+output-bmk-results.py(261):     for index, row in results_df.iterrows():
+output-bmk-results.py(263):         classif, short_diag = get_status_diag(row)
+ --- modulename: output-bmk-results, funcname: get_status_diag
+output-bmk-results.py(113):     bmk = row["benchmark"]
+output-bmk-results.py(115):     short_diag=""
+output-bmk-results.py(116):     classif=""
+output-bmk-results.py(118):     if row["status_x"]!="failed-to-build" and row["status_y"]=="failed-to-build":
+output-bmk-results.py(121):     elif row["status_x"]=="success" and row["status_y"]=="failed-to-run":
+output-bmk-results.py(124):     elif row["status_x"]=="failed-to-build" and row["status_y"]=="failed-to-run":
+output-bmk-results.py(127):     elif row["status_x"]=="failed-to-run" and row["status_y"]=="success":
+output-bmk-results.py(130):     elif row["status_x"]=="failed-to-build" and row["status_y"]=="success":
+output-bmk-results.py(134):     return classif, short_diag
+output-bmk-results.py(265):         if classif != change_kind:
+output-bmk-results.py(266):             continue;
+output-bmk-results.py(261):     for index, row in results_df.iterrows():
+output-bmk-results.py(263):         classif, short_diag = get_status_diag(row)
+ --- modulename: output-bmk-results, funcname: get_status_diag
+output-bmk-results.py(113):     bmk = row["benchmark"]
+output-bmk-results.py(115):     short_diag=""
+output-bmk-results.py(116):     classif=""
+output-bmk-results.py(118):     if row["status_x"]!="failed-to-build" and row["status_y"]=="failed-to-build":
+output-bmk-results.py(121):     elif row["status_x"]=="success" and row["status_y"]=="failed-to-run":
+output-bmk-results.py(124):     elif row["status_x"]=="failed-to-build" and row["status_y"]=="failed-to-run":
+output-bmk-results.py(127):     elif row["status_x"]=="failed-to-run" and row["status_y"]=="success":
+output-bmk-results.py(130):     elif row["status_x"]=="failed-to-build" and row["status_y"]=="success":
+output-bmk-results.py(134):     return classif, short_diag
+output-bmk-results.py(265):         if classif != change_kind:
+output-bmk-results.py(266):             continue;
 output-bmk-results.py(261):     for index, row in results_df.iterrows():
 output-bmk-results.py(263):         classif, short_diag = get_status_diag(row)
  --- modulename: output-bmk-results, funcname: get_status_diag
@@ -378,25 +423,70 @@ output-bmk-results.py(22):        self.outf = open(filename, mode)
 output-bmk-results.py(23):        self.csvwriter = csv.writer(self.outf)
 output-bmk-results.py(258):     print(results_df)
           benchmark                    symbol  ...       status_x       status_y
-0         505.mcf_r        mcf_r_base.default  ...             -1        success
-2      510.parest_r     parest_r_base.default  ...  failed-to-run  failed-to-run
-3      511.povray_r     povray_r_base.default  ...  failed-to-run  failed-to-run
-4         519.lbm_r        lbm_r_base.default  ...  failed-to-run  failed-to-run
-5         519.lbm_r        lbm_r_base.default  ...  failed-to-run  failed-to-run
-6     520.omnetpp_r    omnetpp_r_base.default  ...  failed-to-run  failed-to-run
-7   523.xalancbmk_r   cpuxalan_r_base.default  ...  failed-to-run  failed-to-run
-8   523.xalancbmk_r   cpuxalan_r_base.default  ...  failed-to-run  failed-to-run
-9        525.x264_r       x264_r_base.default  ...  failed-to-run  failed-to-run
-10    526.blender_r    blender_r_base.default  ...  failed-to-run  failed-to-run
-11  531.deepsjeng_r  deepsjeng_r_base.default  ...        success        success
-12    538.imagick_r    imagick_r_base.default  ...  failed-to-run             -1
-14    538.imagick_r    imagick_r_base.default  ...  failed-to-run  failed-to-run
-15      541.leela_r      leela_r_base.default  ...  failed-to-run             -1
-16      541.leela_r      leela_r_base.default  ...  failed-to-run  failed-to-run
-18        544.nab_r        nab_r_base.default  ...  failed-to-run  failed-to-run
-19         557.xz_r         xz_r_base.default  ...        success        success
+0   500.perlbench_r  perlbench_r_base.default  ...  failed-to-run  failed-to-run
+1         502.gcc_r     cpugcc_r_base.default  ...  failed-to-run  failed-to-run
+2         505.mcf_r        mcf_r_base.default  ...        success        success
+4        508.namd_r       namd_r_base.default  ...  failed-to-run  failed-to-run
+5      510.parest_r     parest_r_base.default  ...  failed-to-run  failed-to-run
+6      511.povray_r     povray_r_base.default  ...  failed-to-run  failed-to-run
+7         519.lbm_r        lbm_r_base.default  ...  failed-to-run  failed-to-run
+8         519.lbm_r        lbm_r_base.default  ...  failed-to-run  failed-to-run
+9     520.omnetpp_r    omnetpp_r_base.default  ...  failed-to-run  failed-to-run
+10  523.xalancbmk_r   cpuxalan_r_base.default  ...  failed-to-run  failed-to-run
+11  523.xalancbmk_r   cpuxalan_r_base.default  ...  failed-to-run  failed-to-run
+12       525.x264_r       x264_r_base.default  ...  failed-to-run  failed-to-run
+13    526.blender_r    blender_r_base.default  ...  failed-to-run  failed-to-run
+14  531.deepsjeng_r  deepsjeng_r_base.default  ...        success        success
+15    538.imagick_r    imagick_r_base.default  ...             -1  failed-to-run
+16    538.imagick_r    imagick_r_base.default  ...             -1  failed-to-run
+18      541.leela_r      leela_r_base.default  ...             -1  failed-to-run
+19      541.leela_r      leela_r_base.default  ...             -1  failed-to-run
+21        544.nab_r        nab_r_base.default  ...  failed-to-run  failed-to-run
+22         557.xz_r         xz_r_base.default  ...        success        success
 
-[17 rows x 20 columns]
+[20 rows x 20 columns]
+output-bmk-results.py(261):     for index, row in results_df.iterrows():
+output-bmk-results.py(263):         classif, short_diag = get_status_diag(row)
+ --- modulename: output-bmk-results, funcname: get_status_diag
+output-bmk-results.py(113):     bmk = row["benchmark"]
+output-bmk-results.py(115):     short_diag=""
+output-bmk-results.py(116):     classif=""
+output-bmk-results.py(118):     if row["status_x"]!="failed-to-build" and row["status_y"]=="failed-to-build":
+output-bmk-results.py(121):     elif row["status_x"]=="success" and row["status_y"]=="failed-to-run":
+output-bmk-results.py(124):     elif row["status_x"]=="failed-to-build" and row["status_y"]=="failed-to-run":
+output-bmk-results.py(127):     elif row["status_x"]=="failed-to-run" and row["status_y"]=="success":
+output-bmk-results.py(130):     elif row["status_x"]=="failed-to-build" and row["status_y"]=="success":
+output-bmk-results.py(134):     return classif, short_diag
+output-bmk-results.py(265):         if classif != change_kind:
+output-bmk-results.py(266):             continue;
+output-bmk-results.py(261):     for index, row in results_df.iterrows():
+output-bmk-results.py(263):         classif, short_diag = get_status_diag(row)
+ --- modulename: output-bmk-results, funcname: get_status_diag
+output-bmk-results.py(113):     bmk = row["benchmark"]
+output-bmk-results.py(115):     short_diag=""
+output-bmk-results.py(116):     classif=""
+output-bmk-results.py(118):     if row["status_x"]!="failed-to-build" and row["status_y"]=="failed-to-build":
+output-bmk-results.py(121):     elif row["status_x"]=="success" and row["status_y"]=="failed-to-run":
+output-bmk-results.py(124):     elif row["status_x"]=="failed-to-build" and row["status_y"]=="failed-to-run":
+output-bmk-results.py(127):     elif row["status_x"]=="failed-to-run" and row["status_y"]=="success":
+output-bmk-results.py(130):     elif row["status_x"]=="failed-to-build" and row["status_y"]=="success":
+output-bmk-results.py(134):     return classif, short_diag
+output-bmk-results.py(265):         if classif != change_kind:
+output-bmk-results.py(266):             continue;
+output-bmk-results.py(261):     for index, row in results_df.iterrows():
+output-bmk-results.py(263):         classif, short_diag = get_status_diag(row)
+ --- modulename: output-bmk-results, funcname: get_status_diag
+output-bmk-results.py(113):     bmk = row["benchmark"]
+output-bmk-results.py(115):     short_diag=""
+output-bmk-results.py(116):     classif=""
+output-bmk-results.py(118):     if row["status_x"]!="failed-to-build" and row["status_y"]=="failed-to-build":
+output-bmk-results.py(121):     elif row["status_x"]=="success" and row["status_y"]=="failed-to-run":
+output-bmk-results.py(124):     elif row["status_x"]=="failed-to-build" and row["status_y"]=="failed-to-run":
+output-bmk-results.py(127):     elif row["status_x"]=="failed-to-run" and row["status_y"]=="success":
+output-bmk-results.py(130):     elif row["status_x"]=="failed-to-build" and row["status_y"]=="success":
+output-bmk-results.py(134):     return classif, short_diag
+output-bmk-results.py(265):         if classif != change_kind:
+output-bmk-results.py(266):             continue;
 output-bmk-results.py(261):     for index, row in results_df.iterrows():
 output-bmk-results.py(263):         classif, short_diag = get_status_diag(row)
  --- modulename: output-bmk-results, funcname: get_status_diag
@@ -735,6 +825,28 @@ output-bmk-results.py(110):     return default_threshold[(change_kind,metric,mod
 output-bmk-results.py(228):         print("DEBUG: checking {0}.{1} : {2},{3} : {4}={5}% (threshold={6}%)"\
 output-bmk-results.py(229):              .format(sym_type, change_kind, row["benchmark"], row["symbol"], metric, 100-row["rel_" + metric], threshold))
 output-bmk-results.py(228):         print("DEBUG: checking {0}.{1} : {2},{3} : {4}={5}% (threshold={6}%)"\
+DEBUG: checking exe.regression : 523.xalancbmk_r,cpuxalan_r_base.default : sample=-1% (threshold=3%)
+output-bmk-results.py(232):         if not is_entry_xxx[change_kind](metric, row["rel_" + metric], threshold):
+ --- modulename: output-bmk-results, funcname: is_entry_regression
+output-bmk-results.py(183):     if metric in metric_utils.higher_regress_metrics:
+output-bmk-results.py(184):         return (result - 100 > threshold)
+output-bmk-results.py(233):             continue
+output-bmk-results.py(224):     for index, row in out_df.iterrows():
+output-bmk-results.py(226):         threshold = get_threshold(sym_type, metric, mode, row["benchmark"], row["symbol"])
+ --- modulename: output-bmk-results, funcname: get_threshold
+output-bmk-results.py(98):     if metric == "sample":
+output-bmk-results.py(99):        spec_thr = get_specific_thresholds(metric, mode, bmk, symb)
+ --- modulename: output-bmk-results, funcname: get_specific_thresholds
+output-bmk-results.py(57):     if specific_variability is None:
+output-bmk-results.py(60):     var = specific_variability[ (specific_variability['benchmark'] == bmk) & (specific_variability['symbol'].str.strip() == symb)]
+output-bmk-results.py(61):     if var.empty:
+output-bmk-results.py(62):         return np.nan
+output-bmk-results.py(100):        if not np.isnan(spec_thr):
+output-bmk-results.py(107):     if metric == "num_vect_loops" or metric == "num_sve_loops":
+output-bmk-results.py(110):     return default_threshold[(change_kind,metric,mode)]
+output-bmk-results.py(228):         print("DEBUG: checking {0}.{1} : {2},{3} : {4}={5}% (threshold={6}%)"\
+output-bmk-results.py(229):              .format(sym_type, change_kind, row["benchmark"], row["symbol"], metric, 100-row["rel_" + metric], threshold))
+output-bmk-results.py(228):         print("DEBUG: checking {0}.{1} : {2},{3} : {4}={5}% (threshold={6}%)"\
 DEBUG: checking exe.regression : 523.xalancbmk_r,cpuxalan_r_base.default : sample=0% (threshold=3%)
 output-bmk-results.py(232):         if not is_entry_xxx[change_kind](metric, row["rel_" + metric], threshold):
  --- modulename: output-bmk-results, funcname: is_entry_regression
@@ -757,7 +869,7 @@ output-bmk-results.py(110):     return default_threshold[(change_kind,metric,mod
 output-bmk-results.py(228):         print("DEBUG: checking {0}.{1} : {2},{3} : {4}={5}% (threshold={6}%)"\
 output-bmk-results.py(229):              .format(sym_type, change_kind, row["benchmark"], row["symbol"], metric, 100-row["rel_" + metric], threshold))
 output-bmk-results.py(228):         print("DEBUG: checking {0}.{1} : {2},{3} : {4}={5}% (threshold={6}%)"\
-DEBUG: checking exe.regression : 523.xalancbmk_r,cpuxalan_r_base.default : sample=1% (threshold=3%)
+DEBUG: checking exe.regression : 531.deepsjeng_r,deepsjeng_r_base.default : sample=1% (threshold=3%)
 output-bmk-results.py(232):         if not is_entry_xxx[change_kind](metric, row["rel_" + metric], threshold):
  --- modulename: output-bmk-results, funcname: is_entry_regression
 output-bmk-results.py(183):     if metric in metric_utils.higher_regress_metrics:
@@ -779,7 +891,29 @@ output-bmk-results.py(110):     return default_threshold[(change_kind,metric,mod
 output-bmk-results.py(228):         print("DEBUG: checking {0}.{1} : {2},{3} : {4}={5}% (threshold={6}%)"\
 output-bmk-results.py(229):              .format(sym_type, change_kind, row["benchmark"], row["symbol"], metric, 100-row["rel_" + metric], threshold))
 output-bmk-results.py(228):         print("DEBUG: checking {0}.{1} : {2},{3} : {4}={5}% (threshold={6}%)"\
-DEBUG: checking exe.regression : 531.deepsjeng_r,deepsjeng_r_base.default : sample=0% (threshold=3%)
+DEBUG: checking exe.regression : 538.imagick_r,imagick_r_base.default : sample=0% (threshold=3%)
+output-bmk-results.py(232):         if not is_entry_xxx[change_kind](metric, row["rel_" + metric], threshold):
+ --- modulename: output-bmk-results, funcname: is_entry_regression
+output-bmk-results.py(183):     if metric in metric_utils.higher_regress_metrics:
+output-bmk-results.py(184):         return (result - 100 > threshold)
+output-bmk-results.py(233):             continue
+output-bmk-results.py(224):     for index, row in out_df.iterrows():
+output-bmk-results.py(226):         threshold = get_threshold(sym_type, metric, mode, row["benchmark"], row["symbol"])
+ --- modulename: output-bmk-results, funcname: get_threshold
+output-bmk-results.py(98):     if metric == "sample":
+output-bmk-results.py(99):        spec_thr = get_specific_thresholds(metric, mode, bmk, symb)
+ --- modulename: output-bmk-results, funcname: get_specific_thresholds
+output-bmk-results.py(57):     if specific_variability is None:
+output-bmk-results.py(60):     var = specific_variability[ (specific_variability['benchmark'] == bmk) & (specific_variability['symbol'].str.strip() == symb)]
+output-bmk-results.py(61):     if var.empty:
+output-bmk-results.py(62):         return np.nan
+output-bmk-results.py(100):        if not np.isnan(spec_thr):
+output-bmk-results.py(107):     if metric == "num_vect_loops" or metric == "num_sve_loops":
+output-bmk-results.py(110):     return default_threshold[(change_kind,metric,mode)]
+output-bmk-results.py(228):         print("DEBUG: checking {0}.{1} : {2},{3} : {4}={5}% (threshold={6}%)"\
+output-bmk-results.py(229):              .format(sym_type, change_kind, row["benchmark"], row["symbol"], metric, 100-row["rel_" + metric], threshold))
+output-bmk-results.py(228):         print("DEBUG: checking {0}.{1} : {2},{3} : {4}={5}% (threshold={6}%)"\
+DEBUG: checking exe.regression : 538.imagick_r,imagick_r_base.default : sample=0% (threshold=3%)
 output-bmk-results.py(232):         if not is_entry_xxx[change_kind](metric, row["rel_" + metric], threshold):
  --- modulename: output-bmk-results, funcname: is_entry_regression
 output-bmk-results.py(183):     if metric in metric_utils.higher_regress_metrics:
@@ -951,6 +1085,28 @@ output-bmk-results.py(110):     return default_threshold[(change_kind,metric,mod
 output-bmk-results.py(228):         print("DEBUG: checking {0}.{1} : {2},{3} : {4}={5}% (threshold={6}%)"\
 output-bmk-results.py(229):              .format(sym_type, change_kind, row["benchmark"], row["symbol"], metric, 100-row["rel_" + metric], threshold))
 output-bmk-results.py(228):         print("DEBUG: checking {0}.{1} : {2},{3} : {4}={5}% (threshold={6}%)"\
+DEBUG: checking exe.improvement : 523.xalancbmk_r,cpuxalan_r_base.default : sample=-1% (threshold=3%)
+output-bmk-results.py(232):         if not is_entry_xxx[change_kind](metric, row["rel_" + metric], threshold):
+ --- modulename: output-bmk-results, funcname: is_entry_improvement
+output-bmk-results.py(192):     if metric in metric_utils.higher_regress_metrics:
+output-bmk-results.py(193):         return (100 - result > threshold)
+output-bmk-results.py(233):             continue
+output-bmk-results.py(224):     for index, row in out_df.iterrows():
+output-bmk-results.py(226):         threshold = get_threshold(sym_type, metric, mode, row["benchmark"], row["symbol"])
+ --- modulename: output-bmk-results, funcname: get_threshold
+output-bmk-results.py(98):     if metric == "sample":
+output-bmk-results.py(99):        spec_thr = get_specific_thresholds(metric, mode, bmk, symb)
+ --- modulename: output-bmk-results, funcname: get_specific_thresholds
+output-bmk-results.py(57):     if specific_variability is None:
+output-bmk-results.py(60):     var = specific_variability[ (specific_variability['benchmark'] == bmk) & (specific_variability['symbol'].str.strip() == symb)]
+output-bmk-results.py(61):     if var.empty:
+output-bmk-results.py(62):         return np.nan
+output-bmk-results.py(100):        if not np.isnan(spec_thr):
+output-bmk-results.py(107):     if metric == "num_vect_loops" or metric == "num_sve_loops":
+output-bmk-results.py(110):     return default_threshold[(change_kind,metric,mode)]
+output-bmk-results.py(228):         print("DEBUG: checking {0}.{1} : {2},{3} : {4}={5}% (threshold={6}%)"\
+output-bmk-results.py(229):              .format(sym_type, change_kind, row["benchmark"], row["symbol"], metric, 100-row["rel_" + metric], threshold))
+output-bmk-results.py(228):         print("DEBUG: checking {0}.{1} : {2},{3} : {4}={5}% (threshold={6}%)"\
 DEBUG: checking exe.improvement : 523.xalancbmk_r,cpuxalan_r_base.default : sample=0% (threshold=3%)
 output-bmk-results.py(232):         if not is_entry_xxx[change_kind](metric, row["rel_" + metric], threshold):
  --- modulename: output-bmk-results, funcname: is_entry_improvement
@@ -973,7 +1129,29 @@ output-bmk-results.py(110):     return default_threshold[(change_kind,metric,mod
 output-bmk-results.py(228):         print("DEBUG: checking {0}.{1} : {2},{3} : {4}={5}% (threshold={6}%)"\
 output-bmk-results.py(229):              .format(sym_type, change_kind, row["benchmark"], row["symbol"], metric, 100-row["rel_" + metric], threshold))
 output-bmk-results.py(228):         print("DEBUG: checking {0}.{1} : {2},{3} : {4}={5}% (threshold={6}%)"\
-DEBUG: checking exe.improvement : 523.xalancbmk_r,cpuxalan_r_base.default : sample=1% (threshold=3%)
+DEBUG: checking exe.improvement : 531.deepsjeng_r,deepsjeng_r_base.default : sample=1% (threshold=3%)
+output-bmk-results.py(232):         if not is_entry_xxx[change_kind](metric, row["rel_" + metric], threshold):
+ --- modulename: output-bmk-results, funcname: is_entry_improvement
+output-bmk-results.py(192):     if metric in metric_utils.higher_regress_metrics:
+output-bmk-results.py(193):         return (100 - result > threshold)
+output-bmk-results.py(233):             continue
+output-bmk-results.py(224):     for index, row in out_df.iterrows():
+output-bmk-results.py(226):         threshold = get_threshold(sym_type, metric, mode, row["benchmark"], row["symbol"])
+ --- modulename: output-bmk-results, funcname: get_threshold
+output-bmk-results.py(98):     if metric == "sample":
+output-bmk-results.py(99):        spec_thr = get_specific_thresholds(metric, mode, bmk, symb)
+ --- modulename: output-bmk-results, funcname: get_specific_thresholds
+output-bmk-results.py(57):     if specific_variability is None:
+output-bmk-results.py(60):     var = specific_variability[ (specific_variability['benchmark'] == bmk) & (specific_variability['symbol'].str.strip() == symb)]
+output-bmk-results.py(61):     if var.empty:
+output-bmk-results.py(62):         return np.nan
+output-bmk-results.py(100):        if not np.isnan(spec_thr):
+output-bmk-results.py(107):     if metric == "num_vect_loops" or metric == "num_sve_loops":
+output-bmk-results.py(110):     return default_threshold[(change_kind,metric,mode)]
+output-bmk-results.py(228):         print("DEBUG: checking {0}.{1} : {2},{3} : {4}={5}% (threshold={6}%)"\
+output-bmk-results.py(229):              .format(sym_type, change_kind, row["benchmark"], row["symbol"], metric, 100-row["rel_" + metric], threshold))
+output-bmk-results.py(228):         print("DEBUG: checking {0}.{1} : {2},{3} : {4}={5}% (threshold={6}%)"\
+DEBUG: checking exe.improvement : 538.imagick_r,imagick_r_base.default : sample=0% (threshold=3%)
 output-bmk-results.py(232):         if not is_entry_xxx[change_kind](metric, row["rel_" + metric], threshold):
  --- modulename: output-bmk-results, funcname: is_entry_improvement
 output-bmk-results.py(192):     if metric in metric_utils.higher_regress_metrics:
@@ -995,7 +1173,7 @@ output-bmk-results.py(110):     return default_threshold[(change_kind,metric,mod
 output-bmk-results.py(228):         print("DEBUG: checking {0}.{1} : {2},{3} : {4}={5}% (threshold={6}%)"\
 output-bmk-results.py(229):              .format(sym_type, change_kind, row["benchmark"], row["symbol"], metric, 100-row["rel_" + metric], threshold))
 output-bmk-results.py(228):         print("DEBUG: checking {0}.{1} : {2},{3} : {4}={5}% (threshold={6}%)"\
-DEBUG: checking exe.improvement : 531.deepsjeng_r,deepsjeng_r_base.default : sample=0% (threshold=3%)
+DEBUG: checking exe.improvement : 538.imagick_r,imagick_r_base.default : sample=0% (threshold=3%)
 output-bmk-results.py(232):         if not is_entry_xxx[change_kind](metric, row["rel_" + metric], threshold):
  --- modulename: output-bmk-results, funcname: is_entry_improvement
 output-bmk-results.py(192):     if metric in metric_utils.higher_regress_metrics:
@@ -1123,7 +1301,7 @@ output-bmk-results.py(110):     return default_threshold[(change_kind,metric,mod
 output-bmk-results.py(228):         print("DEBUG: checking {0}.{1} : {2},{3} : {4}={5}% (threshold={6}%)"\
 output-bmk-results.py(229):              .format(sym_type, change_kind, row["benchmark"], row["symbol"], metric, 100-row["rel_" + metric], threshold))
 output-bmk-results.py(228):         print("DEBUG: checking {0}.{1} : {2},{3} : {4}={5}% (threshold={6}%)"\
-DEBUG: checking symbol.regression : 538.imagick_r,libc.so.6 : sample=67% (threshold=15%)
+DEBUG: checking symbol.regression : 538.imagick_r,libc.so.6 : sample=0% (threshold=15%)
 output-bmk-results.py(232):         if not is_entry_xxx[change_kind](metric, row["rel_" + metric], threshold):
  --- modulename: output-bmk-results, funcname: is_entry_regression
 output-bmk-results.py(183):     if metric in metric_utils.higher_regress_metrics:
@@ -1207,37 +1385,12 @@ output-bmk-results.py(110):     return default_threshold[(change_kind,metric,mod
 output-bmk-results.py(228):         print("DEBUG: checking {0}.{1} : {2},{3} : {4}={5}% (threshold={6}%)"\
 output-bmk-results.py(229):              .format(sym_type, change_kind, row["benchmark"], row["symbol"], metric, 100-row["rel_" + metric], threshold))
 output-bmk-results.py(228):         print("DEBUG: checking {0}.{1} : {2},{3} : {4}={5}% (threshold={6}%)"\
-DEBUG: checking symbol.improvement : 538.imagick_r,libc.so.6 : sample=67% (threshold=15%)
+DEBUG: checking symbol.improvement : 538.imagick_r,libc.so.6 : sample=0% (threshold=15%)
 output-bmk-results.py(232):         if not is_entry_xxx[change_kind](metric, row["rel_" + metric], threshold):
  --- modulename: output-bmk-results, funcname: is_entry_improvement
 output-bmk-results.py(192):     if metric in metric_utils.higher_regress_metrics:
 output-bmk-results.py(193):         return (100 - result > threshold)
-output-bmk-results.py(235):         percent_change, short_diag, long_diag = get_short_long_diag(row, metric, sym_type, change_kind)
- --- modulename: output-bmk-results, funcname: get_short_long_diag
-output-bmk-results.py(137):     bmk = row["benchmark"]
-output-bmk-results.py(139):     rel_value = row["rel_" + metric]
-output-bmk-results.py(140):     prev_value = row[metric + "_x"]
-output-bmk-results.py(141):     curr_value = row[metric + "_y"]
-output-bmk-results.py(142):     if metric == "num_vect_loops" or metric == "num_sve_loops":
-output-bmk-results.py(152):     suffix = ""
-output-bmk-results.py(153):     if metric == "sample":
-output-bmk-results.py(154):         prefix_regression = "slowed down by"
-output-bmk-results.py(155):         prefix_improvement = "sped up by"
-output-bmk-results.py(156):         suffix = "perf samples"
-output-bmk-results.py(167):     if sym_type=="symbol":
-output-bmk-results.py(168):       item=bmk+":"+row["symbol"]
-output-bmk-results.py(172):     short_diag = "{1} {2}% - {0}".format(item, locals()["prefix_" + change_kind], abs(rel_value - 100))
-output-bmk-results.py(173):     long_diag = "{0} - from {1} to {2} {3}".format(short_diag, prev_value, curr_value, suffix)
-output-bmk-results.py(174):     return abs(rel_value - 100), short_diag, long_diag
-output-bmk-results.py(239):         if metric == "sample" \
-output-bmk-results.py(240):           and row['symbol_md5sum_x'] == row['symbol_md5sum_y'] \
-output-bmk-results.py(241):           and row['symbol_md5sum_x'] != "-1" \
-output-bmk-results.py(242):           and row['symbol_md5sum_x'] != "d41d8cd98f00b204e9800998ecf8427e":
-output-bmk-results.py(243):             f_skip.write_csv((row["benchmark"], row["symbol"], short_diag, long_diag))
- --- modulename: output-bmk-results, funcname: write_csv
-output-bmk-results.py(41):     if not self.predicate or not self.csvwriter:
-output-bmk-results.py(43):     self.csvwriter.writerow(arr)
-output-bmk-results.py(244):             continue
+output-bmk-results.py(233):             continue
 output-bmk-results.py(224):     for index, row in out_df.iterrows():
 output-bmk-results.py(226):         threshold = get_threshold(sym_type, metric, mode, row["benchmark"], row["symbol"])
  --- modulename: output-bmk-results, funcname: get_threshold
@@ -1276,6 +1429,7 @@ output-bmk-results.py(305):     f_skip.close()
 output-bmk-results.py(29):     if not self.outf:
 output-bmk-results.py(31):     self.outf.close()
 output-bmk-results.py(32):     if os.stat(self.filename).st_size == 0:
+output-bmk-results.py(33):        os.remove(self.filename)
 output-bmk-results.py(306):     f_regr.close()
  --- modulename: output-bmk-results, funcname: close
 output-bmk-results.py(29):     if not self.outf: