diff options
Diffstat (limited to 'notify')
-rw-r--r-- | notify/any.skipped | 1 | ||||
-rw-r--r-- | notify/exe.regression | 1 | ||||
-rw-r--r-- | notify/extra-bisect-params | 2 | ||||
-rw-r--r-- | notify/jira/comment-template.txt | 4 | ||||
-rw-r--r-- | notify/mail-body.txt | 15 | ||||
-rw-r--r-- | notify/mail-recipients.txt | 2 | ||||
-rw-r--r-- | notify/mail-subject.txt | 2 | ||||
-rw-r--r-- | notify/output-bmk-results.log | 172 | ||||
-rw-r--r-- | notify/results.regressions | 1 |
9 files changed, 77 insertions, 123 deletions
diff --git a/notify/any.skipped b/notify/any.skipped deleted file mode 100644 index fa1ba6a..0000000 --- a/notify/any.skipped +++ /dev/null @@ -1 +0,0 @@ -541.leela_r,leela_r_base.default,541.leela_r run OK,541.leela_r run OK
diff --git a/notify/exe.regression b/notify/exe.regression new file mode 100644 index 0000000..501f9d5 --- /dev/null +++ b/notify/exe.regression @@ -0,0 +1 @@ +-1,541.leela_r,leela_r_base.default,541.leela_r failed to run,541.leela_r failed to run
diff --git a/notify/extra-bisect-params b/notify/extra-bisect-params index fa6c7c9..f144c18 100644 --- a/notify/extra-bisect-params +++ b/notify/extra-bisect-params @@ -1 +1 @@ -extra_build_params= +extra_build_params=++benchmarks 541.leela_r diff --git a/notify/jira/comment-template.txt b/notify/jira/comment-template.txt index 6e02c0a..f4dc34f 100644 --- a/notify/jira/comment-template.txt +++ b/notify/jira/comment-template.txt @@ -1,3 +1,3 @@ [LLVM-651] -No change -Details: https://ci.linaro.org/job/tcwg_bmk-code_speed-cpu2017rate--llvm-arm-master-O2-build/71/artifact/artifacts/notify/mail-body.txt/*view*/ +541.leela_r failed to run +Details: https://ci.linaro.org/job/tcwg_bmk-code_speed-cpu2017rate--llvm-arm-master-O2-build/73/artifact/artifacts/notify/mail-body.txt/*view*/ diff --git a/notify/mail-body.txt b/notify/mail-body.txt index 62a03c8..a2b43c5 100644 --- a/notify/mail-body.txt +++ b/notify/mail-body.txt @@ -2,15 +2,10 @@ Dear contributor, our automatic CI has detected problems related to your patch(e In CI config tcwg_bmk-code_speed-cpu2017rate/llvm-arm-master-O2 after: - | 629 commits in llvm - | a09e32e5fe13 [InstSimplify] Respect UseInstrInfo in more folds - | 78c7201d6835 [NewGVN] Regenerate test checks (NFC) - | 1d3e38bfb763 [NewGVN] Add test for #53218 (NFC) - | e158add121dd [InstCombine] Canonicalize `icmp eq/ne (A ^ C), B` to `icmp eq/ne (A ^ B), C` (#67273) - | 31631d307fe0 [X86][FP16] Add missing handling for FP16 constrained cmp intrinsics (#67400) - | ... and 624 more commits in llvm + | baseline build -No change +the following benchmarks slowed down by more than 3%: +- 541.leela_r failed to run
Below reproducer instructions can be used to re-build both "first_bad" and "last_good" cross-toolchains used in this bisection. Naturally, the scripts will fail when triggerring benchmarking jobs if you don\'t have access to Linaro TCWG CI. @@ -27,6 +22,6 @@ This benchmarking CI is work-in-progress, and we welcome feedback and suggestion -----------------8<--------------------------8<--------------------------8<-------------------------- The information below can be used to reproduce a debug environment: -Current build : https://ci.linaro.org/job/tcwg_bmk-code_speed-cpu2017rate--llvm-arm-master-O2-build/71/artifact/artifacts -Reference build : https://ci.linaro.org/job/tcwg_bmk-code_speed-cpu2017rate--llvm-arm-master-O2-build/70/artifact/artifacts +Current build : https://ci.linaro.org/job/tcwg_bmk-code_speed-cpu2017rate--llvm-arm-master-O2-build/73/artifact/artifacts +Reference build : https://ci.linaro.org/job/tcwg_bmk-code_speed-cpu2017rate--llvm-arm-master-O2-build/71/artifact/artifacts diff --git a/notify/mail-recipients.txt b/notify/mail-recipients.txt index 56b65bb..aa219ef 100644 --- a/notify/mail-recipients.txt +++ b/notify/mail-recipients.txt @@ -1 +1 @@ -bcc:tcwg-validation@linaro.org,maxim.kuvyrkov@linaro.org +bcc:tcwg-validation@linaro.org diff --git a/notify/mail-subject.txt b/notify/mail-subject.txt index 652d9d8..18c8226 100644 --- a/notify/mail-subject.txt +++ b/notify/mail-subject.txt @@ -1 +1 @@ -[Linaro-TCWG-CI] 629 commits in llvm: No change +[Linaro-TCWG-CI] baseline build: 541.leela_r failed to run diff --git a/notify/output-bmk-results.log b/notify/output-bmk-results.log index aa6bfe1..5d15716 100644 --- a/notify/output-bmk-results.log +++ b/notify/output-bmk-results.log @@ -291,9 +291,7 @@ output-bmk-results.py(99): spec_thr = get_specific_thresholds(metric, mod 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(63): elif len(var)>1: -output-bmk-results.py(68): if var.iloc[0]['sample_variation_average']>0 : -output-bmk-results.py(83): return np.nan +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)] @@ -371,7 +369,7 @@ output-bmk-results.py(105): return spec_thr output-bmk-results.py(220): print("DEBUG: checking {0}.{1} : {2},{3} : {4}={5}% (threshold={6}%)"\ output-bmk-results.py(221): .format(sym_type, change_kind, row["benchmark"], row["symbol"], metric, 100-row["rel_" + metric], threshold)) output-bmk-results.py(220): print("DEBUG: checking {0}.{1} : {2},{3} : {4}={5}% (threshold={6}%)"\ -DEBUG: checking exe.regression : 531.deepsjeng_r,deepsjeng_r_base.default : sample=1% (threshold=3%) +DEBUG: checking exe.regression : 531.deepsjeng_r,deepsjeng_r_base.default : sample=0% (threshold=3.12%) output-bmk-results.py(224): if not is_entry_xxx[change_kind](metric, row["rel_" + metric], threshold): --- modulename: output-bmk-results, funcname: is_entry_regression output-bmk-results.py(175): if metric in metric_utils.higher_regress_metrics: @@ -386,19 +384,49 @@ output-bmk-results.py(99): spec_thr = get_specific_thresholds(metric, mod 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(63): elif len(var)>1: +output-bmk-results.py(68): if var.iloc[0]['sample_variation_average']>0 : +output-bmk-results.py(83): 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(220): print("DEBUG: checking {0}.{1} : {2},{3} : {4}={5}% (threshold={6}%)"\ output-bmk-results.py(221): .format(sym_type, change_kind, row["benchmark"], row["symbol"], metric, 100-row["rel_" + metric], threshold)) output-bmk-results.py(220): print("DEBUG: checking {0}.{1} : {2},{3} : {4}={5}% (threshold={6}%)"\ -DEBUG: checking exe.regression : 541.leela_r,leela_r_base.default : sample=100% (threshold=3%) +DEBUG: checking exe.regression : 541.leela_r,leela_r_base.default : sample=-2147483547% (threshold=3%) output-bmk-results.py(224): if not is_entry_xxx[change_kind](metric, row["rel_" + metric], threshold): --- modulename: output-bmk-results, funcname: is_entry_regression output-bmk-results.py(175): if metric in metric_utils.higher_regress_metrics: output-bmk-results.py(176): return (result - 100 > threshold) -output-bmk-results.py(225): continue +output-bmk-results.py(227): 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(113): bmk = row["benchmark"] +output-bmk-results.py(114): rel_value = row["rel_" + metric] +output-bmk-results.py(115): prev_value = row[metric + "_x"] +output-bmk-results.py(116): curr_value = row[metric + "_y"] +output-bmk-results.py(118): if metric == "sample": +output-bmk-results.py(119): if curr_value == 999999999: +output-bmk-results.py(122): elif curr_value == 888888888: +output-bmk-results.py(123): short_diag = "{0} failed to run".format(bmk) +output-bmk-results.py(124): return -1, short_diag, short_diag +output-bmk-results.py(231): if metric == "sample" \ +output-bmk-results.py(232): and row['symbol_md5sum_x'] == row['symbol_md5sum_y'] \ +output-bmk-results.py(233): and row['symbol_md5sum_x'] != "-1" \ +output-bmk-results.py(238): print("DEBUG: *** {0},{1} : {2}".format(row["benchmark"], row["symbol"], long_diag)) +DEBUG: *** 541.leela_r,leela_r_base.default : 541.leela_r failed to run +output-bmk-results.py(240): f_out.write_csv((percent_change, 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(241): if change_kind == "regression": +output-bmk-results.py(242): f_regr.write("# {0},{1}\n".format(row["symbol"], long_diag)) + --- modulename: output-bmk-results, funcname: write +output-bmk-results.py(36): if not self.predicate or not self.outf: +output-bmk-results.py(38): self.outf.write(string) +output-bmk-results.py(243): f_ebp.write("++benchmarks {0} ".format(row["benchmark"])) + --- modulename: output-bmk-results, funcname: write +output-bmk-results.py(36): if not self.predicate or not self.outf: +output-bmk-results.py(38): self.outf.write(string) output-bmk-results.py(216): for index, row in out_df.iterrows(): output-bmk-results.py(218): threshold = get_threshold(sym_type, metric, mode, row["benchmark"], row["symbol"]) --- modulename: output-bmk-results, funcname: get_threshold @@ -454,7 +482,6 @@ output-bmk-results.py(245): f_out.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(263): output_bmk_results_1(exe_df, "exe", "improvement", None, f_skip, None, run_step_artifacts, metric, mode, details) --- modulename: output-bmk-results, funcname: output_bmk_results_1 output-bmk-results.py(210): f_out = Outfile("{0}/{1}.{2}".format(run_step_artifacts, sym_type, change_kind), "w", predicate=(details=="verbose")) @@ -658,9 +685,7 @@ output-bmk-results.py(99): spec_thr = get_specific_thresholds(metric, mod 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(63): elif len(var)>1: -output-bmk-results.py(68): if var.iloc[0]['sample_variation_average']>0 : -output-bmk-results.py(83): return np.nan +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)] @@ -738,7 +763,7 @@ output-bmk-results.py(105): return spec_thr output-bmk-results.py(220): print("DEBUG: checking {0}.{1} : {2},{3} : {4}={5}% (threshold={6}%)"\ output-bmk-results.py(221): .format(sym_type, change_kind, row["benchmark"], row["symbol"], metric, 100-row["rel_" + metric], threshold)) output-bmk-results.py(220): print("DEBUG: checking {0}.{1} : {2},{3} : {4}={5}% (threshold={6}%)"\ -DEBUG: checking exe.improvement : 531.deepsjeng_r,deepsjeng_r_base.default : sample=1% (threshold=3%) +DEBUG: checking exe.improvement : 531.deepsjeng_r,deepsjeng_r_base.default : sample=0% (threshold=3.12%) output-bmk-results.py(224): if not is_entry_xxx[change_kind](metric, row["rel_" + metric], threshold): --- modulename: output-bmk-results, funcname: is_entry_improvement output-bmk-results.py(184): if metric in metric_utils.higher_regress_metrics: @@ -753,40 +778,21 @@ output-bmk-results.py(99): spec_thr = get_specific_thresholds(metric, mod 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(63): elif len(var)>1: +output-bmk-results.py(68): if var.iloc[0]['sample_variation_average']>0 : +output-bmk-results.py(83): 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(220): print("DEBUG: checking {0}.{1} : {2},{3} : {4}={5}% (threshold={6}%)"\ output-bmk-results.py(221): .format(sym_type, change_kind, row["benchmark"], row["symbol"], metric, 100-row["rel_" + metric], threshold)) output-bmk-results.py(220): print("DEBUG: checking {0}.{1} : {2},{3} : {4}={5}% (threshold={6}%)"\ -DEBUG: checking exe.improvement : 541.leela_r,leela_r_base.default : sample=100% (threshold=3%) +DEBUG: checking exe.improvement : 541.leela_r,leela_r_base.default : sample=-2147483547% (threshold=3%) output-bmk-results.py(224): if not is_entry_xxx[change_kind](metric, row["rel_" + metric], threshold): --- modulename: output-bmk-results, funcname: is_entry_improvement output-bmk-results.py(184): if metric in metric_utils.higher_regress_metrics: output-bmk-results.py(185): return (100 - result > threshold) -output-bmk-results.py(227): 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(113): bmk = row["benchmark"] -output-bmk-results.py(114): rel_value = row["rel_" + metric] -output-bmk-results.py(115): prev_value = row[metric + "_x"] -output-bmk-results.py(116): curr_value = row[metric + "_y"] -output-bmk-results.py(118): if metric == "sample": -output-bmk-results.py(119): if curr_value == 999999999: -output-bmk-results.py(122): elif curr_value == 888888888: -output-bmk-results.py(125): elif prev_value == 999999999 and curr_value == 888888888: -output-bmk-results.py(128): elif prev_value == 888888888 and curr_value < 888888888: -output-bmk-results.py(129): short_diag = "{0} run OK".format(bmk) -output-bmk-results.py(130): return -1, short_diag, short_diag -output-bmk-results.py(231): if metric == "sample" \ -output-bmk-results.py(232): and row['symbol_md5sum_x'] == row['symbol_md5sum_y'] \ -output-bmk-results.py(233): and row['symbol_md5sum_x'] != "-1" \ -output-bmk-results.py(234): and row['symbol_md5sum_x'] != "d41d8cd98f00b204e9800998ecf8427e": -output-bmk-results.py(235): 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(236): continue +output-bmk-results.py(225): continue output-bmk-results.py(216): for index, row in out_df.iterrows(): output-bmk-results.py(218): threshold = get_threshold(sym_type, metric, mode, row["benchmark"], row["symbol"]) --- modulename: output-bmk-results, funcname: get_threshold @@ -875,7 +881,7 @@ output-bmk-results.py(105): return spec_thr output-bmk-results.py(220): print("DEBUG: checking {0}.{1} : {2},{3} : {4}={5}% (threshold={6}%)"\ output-bmk-results.py(221): .format(sym_type, change_kind, row["benchmark"], row["symbol"], metric, 100-row["rel_" + metric], threshold)) output-bmk-results.py(220): print("DEBUG: checking {0}.{1} : {2},{3} : {4}={5}% (threshold={6}%)"\ -DEBUG: checking symbol.regression : 505.mcf_r,[.] primal_bea_mpp : sample=-1% (threshold=15%) +DEBUG: checking symbol.regression : 505.mcf_r,[.] primal_bea_mpp : sample=1% (threshold=15%) output-bmk-results.py(224): if not is_entry_xxx[change_kind](metric, row["rel_" + metric], threshold): --- modulename: output-bmk-results, funcname: is_entry_regression output-bmk-results.py(175): if metric in metric_utils.higher_regress_metrics: @@ -902,7 +908,7 @@ output-bmk-results.py(105): return spec_thr output-bmk-results.py(220): print("DEBUG: checking {0}.{1} : {2},{3} : {4}={5}% (threshold={6}%)"\ output-bmk-results.py(221): .format(sym_type, change_kind, row["benchmark"], row["symbol"], metric, 100-row["rel_" + metric], threshold)) output-bmk-results.py(220): print("DEBUG: checking {0}.{1} : {2},{3} : {4}={5}% (threshold={6}%)"\ -DEBUG: checking symbol.regression : 505.mcf_r,[.] price_out_impl : sample=-1% (threshold=15%) +DEBUG: checking symbol.regression : 505.mcf_r,[.] price_out_impl : sample=0% (threshold=15%) output-bmk-results.py(224): if not is_entry_xxx[change_kind](metric, row["rel_" + metric], threshold): --- modulename: output-bmk-results, funcname: is_entry_regression output-bmk-results.py(175): if metric in metric_utils.higher_regress_metrics: @@ -929,7 +935,7 @@ output-bmk-results.py(105): return spec_thr output-bmk-results.py(220): print("DEBUG: checking {0}.{1} : {2},{3} : {4}={5}% (threshold={6}%)"\ output-bmk-results.py(221): .format(sym_type, change_kind, row["benchmark"], row["symbol"], metric, 100-row["rel_" + metric], threshold)) output-bmk-results.py(220): print("DEBUG: checking {0}.{1} : {2},{3} : {4}={5}% (threshold={6}%)"\ -DEBUG: checking symbol.regression : 505.mcf_r,[.] cost_compare : sample=-2% (threshold=15%) +DEBUG: checking symbol.regression : 505.mcf_r,[.] cost_compare : sample=-4% (threshold=15%) output-bmk-results.py(224): if not is_entry_xxx[change_kind](metric, row["rel_" + metric], threshold): --- modulename: output-bmk-results, funcname: is_entry_regression output-bmk-results.py(175): if metric in metric_utils.higher_regress_metrics: @@ -956,7 +962,7 @@ output-bmk-results.py(105): return spec_thr output-bmk-results.py(220): print("DEBUG: checking {0}.{1} : {2},{3} : {4}={5}% (threshold={6}%)"\ output-bmk-results.py(221): .format(sym_type, change_kind, row["benchmark"], row["symbol"], metric, 100-row["rel_" + metric], threshold)) output-bmk-results.py(220): print("DEBUG: checking {0}.{1} : {2},{3} : {4}={5}% (threshold={6}%)"\ -DEBUG: checking symbol.regression : 505.mcf_r,[.] replace_weaker_arc : sample=1% (threshold=15%) +DEBUG: checking symbol.regression : 505.mcf_r,[.] replace_weaker_arc : sample=0% (threshold=15%) output-bmk-results.py(224): if not is_entry_xxx[change_kind](metric, row["rel_" + metric], threshold): --- modulename: output-bmk-results, funcname: is_entry_regression output-bmk-results.py(175): if metric in metric_utils.higher_regress_metrics: @@ -983,7 +989,7 @@ output-bmk-results.py(105): return spec_thr output-bmk-results.py(220): print("DEBUG: checking {0}.{1} : {2},{3} : {4}={5}% (threshold={6}%)"\ output-bmk-results.py(221): .format(sym_type, change_kind, row["benchmark"], row["symbol"], metric, 100-row["rel_" + metric], threshold)) output-bmk-results.py(220): print("DEBUG: checking {0}.{1} : {2},{3} : {4}={5}% (threshold={6}%)"\ -DEBUG: checking symbol.regression : 531.deepsjeng_r,[.] _Z5fevalP7state_tiP12t_eval_comps : sample=4% (threshold=15%) +DEBUG: checking symbol.regression : 531.deepsjeng_r,[.] _Z5fevalP7state_tiP12t_eval_comps : sample=-6% (threshold=15%) output-bmk-results.py(224): if not is_entry_xxx[change_kind](metric, row["rel_" + metric], threshold): --- modulename: output-bmk-results, funcname: is_entry_regression output-bmk-results.py(175): if metric in metric_utils.higher_regress_metrics: @@ -1010,7 +1016,7 @@ output-bmk-results.py(105): return spec_thr output-bmk-results.py(220): print("DEBUG: checking {0}.{1} : {2},{3} : {4}={5}% (threshold={6}%)"\ output-bmk-results.py(221): .format(sym_type, change_kind, row["benchmark"], row["symbol"], metric, 100-row["rel_" + metric], threshold)) output-bmk-results.py(220): print("DEBUG: checking {0}.{1} : {2},{3} : {4}={5}% (threshold={6}%)"\ -DEBUG: checking symbol.regression : 531.deepsjeng_r,[.] _Z7ProbeTTP7state_tPiiiPjS1_S1_S1_S1_i : sample=1% (threshold=15%) +DEBUG: checking symbol.regression : 531.deepsjeng_r,[.] _Z7ProbeTTP7state_tPiiiPjS1_S1_S1_S1_i : sample=2% (threshold=15%) output-bmk-results.py(224): if not is_entry_xxx[change_kind](metric, row["rel_" + metric], threshold): --- modulename: output-bmk-results, funcname: is_entry_regression output-bmk-results.py(175): if metric in metric_utils.higher_regress_metrics: @@ -1037,7 +1043,7 @@ output-bmk-results.py(105): return spec_thr output-bmk-results.py(220): print("DEBUG: checking {0}.{1} : {2},{3} : {4}={5}% (threshold={6}%)"\ output-bmk-results.py(221): .format(sym_type, change_kind, row["benchmark"], row["symbol"], metric, 100-row["rel_" + metric], threshold)) output-bmk-results.py(220): print("DEBUG: checking {0}.{1} : {2},{3} : {4}={5}% (threshold={6}%)"\ -DEBUG: checking symbol.regression : 531.deepsjeng_r,[.] _Z6searchP7state_tiiiii : sample=-9% (threshold=15%) +DEBUG: checking symbol.regression : 531.deepsjeng_r,[.] _Z4makeP7state_ti : sample=0% (threshold=15%) output-bmk-results.py(224): if not is_entry_xxx[change_kind](metric, row["rel_" + metric], threshold): --- modulename: output-bmk-results, funcname: is_entry_regression output-bmk-results.py(175): if metric in metric_utils.higher_regress_metrics: @@ -1064,31 +1070,7 @@ output-bmk-results.py(105): return spec_thr output-bmk-results.py(220): print("DEBUG: checking {0}.{1} : {2},{3} : {4}={5}% (threshold={6}%)"\ output-bmk-results.py(221): .format(sym_type, change_kind, row["benchmark"], row["symbol"], metric, 100-row["rel_" + metric], threshold)) output-bmk-results.py(220): print("DEBUG: checking {0}.{1} : {2},{3} : {4}={5}% (threshold={6}%)"\ -DEBUG: checking symbol.regression : 531.deepsjeng_r,[.] _Z4makeP7state_ti : sample=-5% (threshold=15.059999999999999%) -output-bmk-results.py(224): if not is_entry_xxx[change_kind](metric, row["rel_" + metric], threshold): - --- modulename: output-bmk-results, funcname: is_entry_regression -output-bmk-results.py(175): if metric in metric_utils.higher_regress_metrics: -output-bmk-results.py(176): return (result - 100 > threshold) -output-bmk-results.py(225): continue -output-bmk-results.py(216): for index, row in out_df.iterrows(): -output-bmk-results.py(218): 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(63): elif len(var)>1: -output-bmk-results.py(68): if var.iloc[0]['sample_variation_average']>0 : -output-bmk-results.py(83): 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(220): print("DEBUG: checking {0}.{1} : {2},{3} : {4}={5}% (threshold={6}%)"\ -output-bmk-results.py(221): .format(sym_type, change_kind, row["benchmark"], row["symbol"], metric, 100-row["rel_" + metric], threshold)) -output-bmk-results.py(220): print("DEBUG: checking {0}.{1} : {2},{3} : {4}={5}% (threshold={6}%)"\ -DEBUG: checking symbol.regression : 531.deepsjeng_r,[.] _Z3seeP7state_tiiii : sample=2% (threshold=15%) +DEBUG: checking symbol.regression : 531.deepsjeng_r,[.] _Z6searchP7state_tiiiii : sample=8% (threshold=15%) output-bmk-results.py(224): if not is_entry_xxx[change_kind](metric, row["rel_" + metric], threshold): --- modulename: output-bmk-results, funcname: is_entry_regression output-bmk-results.py(175): if metric in metric_utils.higher_regress_metrics: @@ -1115,7 +1097,7 @@ output-bmk-results.py(105): return spec_thr output-bmk-results.py(220): print("DEBUG: checking {0}.{1} : {2},{3} : {4}={5}% (threshold={6}%)"\ output-bmk-results.py(221): .format(sym_type, change_kind, row["benchmark"], row["symbol"], metric, 100-row["rel_" + metric], threshold)) output-bmk-results.py(220): print("DEBUG: checking {0}.{1} : {2},{3} : {4}={5}% (threshold={6}%)"\ -DEBUG: checking symbol.regression : 557.xz_r,[.] lzma_mf_bt4_find : sample=-2% (threshold=15%) +DEBUG: checking symbol.regression : 557.xz_r,[.] lzma_mf_bt4_find : sample=1% (threshold=15%) output-bmk-results.py(224): if not is_entry_xxx[change_kind](metric, row["rel_" + metric], threshold): --- modulename: output-bmk-results, funcname: is_entry_regression output-bmk-results.py(175): if metric in metric_utils.higher_regress_metrics: @@ -1142,7 +1124,7 @@ output-bmk-results.py(105): return spec_thr output-bmk-results.py(220): print("DEBUG: checking {0}.{1} : {2},{3} : {4}={5}% (threshold={6}%)"\ output-bmk-results.py(221): .format(sym_type, change_kind, row["benchmark"], row["symbol"], metric, 100-row["rel_" + metric], threshold)) output-bmk-results.py(220): print("DEBUG: checking {0}.{1} : {2},{3} : {4}={5}% (threshold={6}%)"\ -DEBUG: checking symbol.regression : 557.xz_r,[.] lzma_lzma_optimum_normal : sample=3% (threshold=15%) +DEBUG: checking symbol.regression : 557.xz_r,[.] lzma_lzma_optimum_normal : sample=-2% (threshold=15%) output-bmk-results.py(224): if not is_entry_xxx[change_kind](metric, row["rel_" + metric], threshold): --- modulename: output-bmk-results, funcname: is_entry_regression output-bmk-results.py(175): if metric in metric_utils.higher_regress_metrics: @@ -1169,7 +1151,7 @@ output-bmk-results.py(105): return spec_thr output-bmk-results.py(220): print("DEBUG: checking {0}.{1} : {2},{3} : {4}={5}% (threshold={6}%)"\ output-bmk-results.py(221): .format(sym_type, change_kind, row["benchmark"], row["symbol"], metric, 100-row["rel_" + metric], threshold)) output-bmk-results.py(220): print("DEBUG: checking {0}.{1} : {2},{3} : {4}={5}% (threshold={6}%)"\ -DEBUG: checking symbol.regression : 557.xz_r,[.] lzma_mf_bt4_skip : sample=1% (threshold=15%) +DEBUG: checking symbol.regression : 557.xz_r,[.] lzma_mf_bt4_skip : sample=-2% (threshold=15%) output-bmk-results.py(224): if not is_entry_xxx[change_kind](metric, row["rel_" + metric], threshold): --- modulename: output-bmk-results, funcname: is_entry_regression output-bmk-results.py(175): if metric in metric_utils.higher_regress_metrics: @@ -1214,7 +1196,7 @@ output-bmk-results.py(105): return spec_thr output-bmk-results.py(220): print("DEBUG: checking {0}.{1} : {2},{3} : {4}={5}% (threshold={6}%)"\ output-bmk-results.py(221): .format(sym_type, change_kind, row["benchmark"], row["symbol"], metric, 100-row["rel_" + metric], threshold)) output-bmk-results.py(220): print("DEBUG: checking {0}.{1} : {2},{3} : {4}={5}% (threshold={6}%)"\ -DEBUG: checking symbol.improvement : 505.mcf_r,[.] primal_bea_mpp : sample=-1% (threshold=15%) +DEBUG: checking symbol.improvement : 505.mcf_r,[.] primal_bea_mpp : sample=1% (threshold=15%) output-bmk-results.py(224): if not is_entry_xxx[change_kind](metric, row["rel_" + metric], threshold): --- modulename: output-bmk-results, funcname: is_entry_improvement output-bmk-results.py(184): if metric in metric_utils.higher_regress_metrics: @@ -1241,7 +1223,7 @@ output-bmk-results.py(105): return spec_thr output-bmk-results.py(220): print("DEBUG: checking {0}.{1} : {2},{3} : {4}={5}% (threshold={6}%)"\ output-bmk-results.py(221): .format(sym_type, change_kind, row["benchmark"], row["symbol"], metric, 100-row["rel_" + metric], threshold)) output-bmk-results.py(220): print("DEBUG: checking {0}.{1} : {2},{3} : {4}={5}% (threshold={6}%)"\ -DEBUG: checking symbol.improvement : 505.mcf_r,[.] price_out_impl : sample=-1% (threshold=15%) +DEBUG: checking symbol.improvement : 505.mcf_r,[.] price_out_impl : sample=0% (threshold=15%) output-bmk-results.py(224): if not is_entry_xxx[change_kind](metric, row["rel_" + metric], threshold): --- modulename: output-bmk-results, funcname: is_entry_improvement output-bmk-results.py(184): if metric in metric_utils.higher_regress_metrics: @@ -1268,7 +1250,7 @@ output-bmk-results.py(105): return spec_thr output-bmk-results.py(220): print("DEBUG: checking {0}.{1} : {2},{3} : {4}={5}% (threshold={6}%)"\ output-bmk-results.py(221): .format(sym_type, change_kind, row["benchmark"], row["symbol"], metric, 100-row["rel_" + metric], threshold)) output-bmk-results.py(220): print("DEBUG: checking {0}.{1} : {2},{3} : {4}={5}% (threshold={6}%)"\ -DEBUG: checking symbol.improvement : 505.mcf_r,[.] cost_compare : sample=-2% (threshold=15%) +DEBUG: checking symbol.improvement : 505.mcf_r,[.] cost_compare : sample=-4% (threshold=15%) output-bmk-results.py(224): if not is_entry_xxx[change_kind](metric, row["rel_" + metric], threshold): --- modulename: output-bmk-results, funcname: is_entry_improvement output-bmk-results.py(184): if metric in metric_utils.higher_regress_metrics: @@ -1295,7 +1277,7 @@ output-bmk-results.py(105): return spec_thr output-bmk-results.py(220): print("DEBUG: checking {0}.{1} : {2},{3} : {4}={5}% (threshold={6}%)"\ output-bmk-results.py(221): .format(sym_type, change_kind, row["benchmark"], row["symbol"], metric, 100-row["rel_" + metric], threshold)) output-bmk-results.py(220): print("DEBUG: checking {0}.{1} : {2},{3} : {4}={5}% (threshold={6}%)"\ -DEBUG: checking symbol.improvement : 505.mcf_r,[.] replace_weaker_arc : sample=1% (threshold=15%) +DEBUG: checking symbol.improvement : 505.mcf_r,[.] replace_weaker_arc : sample=0% (threshold=15%) output-bmk-results.py(224): if not is_entry_xxx[change_kind](metric, row["rel_" + metric], threshold): --- modulename: output-bmk-results, funcname: is_entry_improvement output-bmk-results.py(184): if metric in metric_utils.higher_regress_metrics: @@ -1322,7 +1304,7 @@ output-bmk-results.py(105): return spec_thr output-bmk-results.py(220): print("DEBUG: checking {0}.{1} : {2},{3} : {4}={5}% (threshold={6}%)"\ output-bmk-results.py(221): .format(sym_type, change_kind, row["benchmark"], row["symbol"], metric, 100-row["rel_" + metric], threshold)) output-bmk-results.py(220): print("DEBUG: checking {0}.{1} : {2},{3} : {4}={5}% (threshold={6}%)"\ -DEBUG: checking symbol.improvement : 531.deepsjeng_r,[.] _Z5fevalP7state_tiP12t_eval_comps : sample=4% (threshold=15%) +DEBUG: checking symbol.improvement : 531.deepsjeng_r,[.] _Z5fevalP7state_tiP12t_eval_comps : sample=-6% (threshold=15%) output-bmk-results.py(224): if not is_entry_xxx[change_kind](metric, row["rel_" + metric], threshold): --- modulename: output-bmk-results, funcname: is_entry_improvement output-bmk-results.py(184): if metric in metric_utils.higher_regress_metrics: @@ -1349,7 +1331,7 @@ output-bmk-results.py(105): return spec_thr output-bmk-results.py(220): print("DEBUG: checking {0}.{1} : {2},{3} : {4}={5}% (threshold={6}%)"\ output-bmk-results.py(221): .format(sym_type, change_kind, row["benchmark"], row["symbol"], metric, 100-row["rel_" + metric], threshold)) output-bmk-results.py(220): print("DEBUG: checking {0}.{1} : {2},{3} : {4}={5}% (threshold={6}%)"\ -DEBUG: checking symbol.improvement : 531.deepsjeng_r,[.] _Z7ProbeTTP7state_tPiiiPjS1_S1_S1_S1_i : sample=1% (threshold=15%) +DEBUG: checking symbol.improvement : 531.deepsjeng_r,[.] _Z7ProbeTTP7state_tPiiiPjS1_S1_S1_S1_i : sample=2% (threshold=15%) output-bmk-results.py(224): if not is_entry_xxx[change_kind](metric, row["rel_" + metric], threshold): --- modulename: output-bmk-results, funcname: is_entry_improvement output-bmk-results.py(184): if metric in metric_utils.higher_regress_metrics: @@ -1376,7 +1358,7 @@ output-bmk-results.py(105): return spec_thr output-bmk-results.py(220): print("DEBUG: checking {0}.{1} : {2},{3} : {4}={5}% (threshold={6}%)"\ output-bmk-results.py(221): .format(sym_type, change_kind, row["benchmark"], row["symbol"], metric, 100-row["rel_" + metric], threshold)) output-bmk-results.py(220): print("DEBUG: checking {0}.{1} : {2},{3} : {4}={5}% (threshold={6}%)"\ -DEBUG: checking symbol.improvement : 531.deepsjeng_r,[.] _Z6searchP7state_tiiiii : sample=-9% (threshold=15%) +DEBUG: checking symbol.improvement : 531.deepsjeng_r,[.] _Z4makeP7state_ti : sample=0% (threshold=15%) output-bmk-results.py(224): if not is_entry_xxx[change_kind](metric, row["rel_" + metric], threshold): --- modulename: output-bmk-results, funcname: is_entry_improvement output-bmk-results.py(184): if metric in metric_utils.higher_regress_metrics: @@ -1403,31 +1385,7 @@ output-bmk-results.py(105): return spec_thr output-bmk-results.py(220): print("DEBUG: checking {0}.{1} : {2},{3} : {4}={5}% (threshold={6}%)"\ output-bmk-results.py(221): .format(sym_type, change_kind, row["benchmark"], row["symbol"], metric, 100-row["rel_" + metric], threshold)) output-bmk-results.py(220): print("DEBUG: checking {0}.{1} : {2},{3} : {4}={5}% (threshold={6}%)"\ -DEBUG: checking symbol.improvement : 531.deepsjeng_r,[.] _Z4makeP7state_ti : sample=-5% (threshold=15.059999999999999%) -output-bmk-results.py(224): if not is_entry_xxx[change_kind](metric, row["rel_" + metric], threshold): - --- modulename: output-bmk-results, funcname: is_entry_improvement -output-bmk-results.py(184): if metric in metric_utils.higher_regress_metrics: -output-bmk-results.py(185): return (100 - result > threshold) -output-bmk-results.py(225): continue -output-bmk-results.py(216): for index, row in out_df.iterrows(): -output-bmk-results.py(218): 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(63): elif len(var)>1: -output-bmk-results.py(68): if var.iloc[0]['sample_variation_average']>0 : -output-bmk-results.py(83): 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(220): print("DEBUG: checking {0}.{1} : {2},{3} : {4}={5}% (threshold={6}%)"\ -output-bmk-results.py(221): .format(sym_type, change_kind, row["benchmark"], row["symbol"], metric, 100-row["rel_" + metric], threshold)) -output-bmk-results.py(220): print("DEBUG: checking {0}.{1} : {2},{3} : {4}={5}% (threshold={6}%)"\ -DEBUG: checking symbol.improvement : 531.deepsjeng_r,[.] _Z3seeP7state_tiiii : sample=2% (threshold=15%) +DEBUG: checking symbol.improvement : 531.deepsjeng_r,[.] _Z6searchP7state_tiiiii : sample=8% (threshold=15%) output-bmk-results.py(224): if not is_entry_xxx[change_kind](metric, row["rel_" + metric], threshold): --- modulename: output-bmk-results, funcname: is_entry_improvement output-bmk-results.py(184): if metric in metric_utils.higher_regress_metrics: @@ -1454,7 +1412,7 @@ output-bmk-results.py(105): return spec_thr output-bmk-results.py(220): print("DEBUG: checking {0}.{1} : {2},{3} : {4}={5}% (threshold={6}%)"\ output-bmk-results.py(221): .format(sym_type, change_kind, row["benchmark"], row["symbol"], metric, 100-row["rel_" + metric], threshold)) output-bmk-results.py(220): print("DEBUG: checking {0}.{1} : {2},{3} : {4}={5}% (threshold={6}%)"\ -DEBUG: checking symbol.improvement : 557.xz_r,[.] lzma_mf_bt4_find : sample=-2% (threshold=15%) +DEBUG: checking symbol.improvement : 557.xz_r,[.] lzma_mf_bt4_find : sample=1% (threshold=15%) output-bmk-results.py(224): if not is_entry_xxx[change_kind](metric, row["rel_" + metric], threshold): --- modulename: output-bmk-results, funcname: is_entry_improvement output-bmk-results.py(184): if metric in metric_utils.higher_regress_metrics: @@ -1481,7 +1439,7 @@ output-bmk-results.py(105): return spec_thr output-bmk-results.py(220): print("DEBUG: checking {0}.{1} : {2},{3} : {4}={5}% (threshold={6}%)"\ output-bmk-results.py(221): .format(sym_type, change_kind, row["benchmark"], row["symbol"], metric, 100-row["rel_" + metric], threshold)) output-bmk-results.py(220): print("DEBUG: checking {0}.{1} : {2},{3} : {4}={5}% (threshold={6}%)"\ -DEBUG: checking symbol.improvement : 557.xz_r,[.] lzma_lzma_optimum_normal : sample=3% (threshold=15%) +DEBUG: checking symbol.improvement : 557.xz_r,[.] lzma_lzma_optimum_normal : sample=-2% (threshold=15%) output-bmk-results.py(224): if not is_entry_xxx[change_kind](metric, row["rel_" + metric], threshold): --- modulename: output-bmk-results, funcname: is_entry_improvement output-bmk-results.py(184): if metric in metric_utils.higher_regress_metrics: @@ -1508,7 +1466,7 @@ output-bmk-results.py(105): return spec_thr output-bmk-results.py(220): print("DEBUG: checking {0}.{1} : {2},{3} : {4}={5}% (threshold={6}%)"\ output-bmk-results.py(221): .format(sym_type, change_kind, row["benchmark"], row["symbol"], metric, 100-row["rel_" + metric], threshold)) output-bmk-results.py(220): print("DEBUG: checking {0}.{1} : {2},{3} : {4}={5}% (threshold={6}%)"\ -DEBUG: checking symbol.improvement : 557.xz_r,[.] lzma_mf_bt4_skip : sample=1% (threshold=15%) +DEBUG: checking symbol.improvement : 557.xz_r,[.] lzma_mf_bt4_skip : sample=-2% (threshold=15%) output-bmk-results.py(224): if not is_entry_xxx[change_kind](metric, row["rel_" + metric], threshold): --- modulename: output-bmk-results, funcname: is_entry_improvement output-bmk-results.py(184): if metric in metric_utils.higher_regress_metrics: @@ -1530,12 +1488,12 @@ output-bmk-results.py(270): 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(271): f_regr.close() --- modulename: output-bmk-results, funcname: 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(272): f_ebp.close() --- modulename: output-bmk-results, funcname: close output-bmk-results.py(29): if not self.outf: diff --git a/notify/results.regressions b/notify/results.regressions new file mode 100644 index 0000000..24275d8 --- /dev/null +++ b/notify/results.regressions @@ -0,0 +1 @@ +# leela_r_base.default,541.leela_r failed to run |