|
MultiSource/Benchmarks/Trimaran/enc-md5/enc-md5
Profile
|
-76.75% |
12.643 |
2.940 |
0.001 |
0.00% |
0.001 |
|
MultiSource/Benchmarks/Ptrdist/yacr2/yacr2
Profile
|
-28.68% |
2.836 |
2.022 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_with_cond_arith_novec_int64_t_
|
-27.59% |
1044463.436 |
756279.251 |
596.595 |
0.00% |
596.595 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_with_cond_arith_autovec_int64_t_
|
-27.58% |
1044878.546 |
756653.213 |
770.077 |
0.00% |
770.077 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_with_cond_arith_autovec_int32_t_
|
-27.04% |
515728.518 |
376261.319 |
723.535 |
0.00% |
723.535 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_with_cond_arith_novec_int32_t_
|
-26.79% |
515829.116 |
377635.596 |
376.074 |
0.00% |
376.074 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_with_cond_arith_autovec_uint8_t_
|
-25.31% |
124920.394 |
93307.680 |
199.581 |
0.00% |
199.581 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_with_cond_arith_novec_uint8_t_
|
-25.30% |
124916.399 |
93310.429 |
199.534 |
0.00% |
199.534 |
|
SingleSource/Benchmarks/Shootout/Shootout-ary3
Profile
|
-23.62% |
0.985 |
0.752 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint64_t>/16
|
-22.83% |
32.544 |
25.114 |
0.008 |
0.00% |
0.008 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint64_t>/10
|
-20.04% |
24.373 |
19.488 |
0.246 |
0.00% |
0.246 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint8_t>/16
|
-19.60% |
60.094 |
48.316 |
0.005 |
0.00% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint8_t>/10
|
-19.38% |
41.303 |
33.300 |
0.004 |
0.00% |
0.004 |
|
MultiSource/Benchmarks/Olden/em3d/em3d
Profile
|
-17.89% |
18.304 |
15.029 |
0.004 |
0.00% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint64_t>/16
|
-17.72% |
53.215 |
43.784 |
0.007 |
0.00% |
0.007 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint16_t>/28
|
-16.07% |
104.498 |
87.708 |
0.060 |
0.00% |
0.060 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint8_t>/16
|
-15.82% |
33.992 |
28.615 |
0.035 |
0.00% |
0.035 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint64_t>/10
|
-15.80% |
38.640 |
32.536 |
0.001 |
0.00% |
0.001 |
|
MultiSource/Benchmarks/SciMark2-C/scimark2
Profile
|
-15.14% |
166.680 |
141.439 |
0.078 |
0.00% |
0.078 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint16_t>/16
|
-13.82% |
66.954 |
57.700 |
0.037 |
0.00% |
0.037 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint16_t>/10
|
-11.29% |
48.181 |
42.740 |
0.034 |
0.00% |
0.034 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_INT_PREDICT_RAW/5001
|
-11.18% |
1902.919 |
1690.229 |
- |
0.00% |
- |
|
MultiSource/Benchmarks/TSVC/LoopRestructuring-dbl/LoopRestructuring-dbl
Profile
|
-10.49% |
55.687 |
49.844 |
1.495 |
0.00% |
1.495 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_BAND_LIN_EQ_RAW/44217
|
-10.34% |
187.670 |
168.273 |
- |
0.00% |
- |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint16_t>/28
|
-10.19% |
58.554 |
52.589 |
0.013 |
0.00% |
0.013 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_only_novec_int64_t_
|
-9.94% |
1045645.924 |
941673.120 |
924.138 |
0.00% |
924.138 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_only_autovec_int64_t_
|
-9.85% |
1046245.511 |
943175.884 |
786.227 |
0.00% |
786.227 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_only_autovec_int32_t_
|
-8.69% |
515323.384 |
470558.068 |
289.724 |
0.00% |
289.724 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_only_novec_int32_t_
|
-8.58% |
515135.584 |
470945.961 |
504.208 |
0.00% |
504.208 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint8_t>/28
|
-8.51% |
157.975 |
144.536 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint16_t>/999
|
-8.40% |
4647.048 |
4256.786 |
0.190 |
0.00% |
0.190 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint16_t>/256
|
-8.39% |
1207.632 |
1106.305 |
0.101 |
0.00% |
0.101 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint8_t>/51
|
-8.38% |
272.488 |
249.650 |
0.009 |
0.00% |
0.009 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint16_t>/999
|
-8.27% |
2365.086 |
2169.404 |
0.076 |
0.00% |
0.076 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint8_t>/256
|
-8.24% |
1245.804 |
1143.154 |
0.020 |
0.00% |
0.020 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint16_t>/256
|
-8.22% |
642.905 |
590.042 |
0.016 |
0.00% |
0.016 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint8_t>/999
|
-8.21% |
4805.013 |
4410.395 |
0.413 |
0.00% |
0.413 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint16_t>/51
|
-8.11% |
266.237 |
244.647 |
0.008 |
0.00% |
0.008 |
|
SingleSource/Benchmarks/Adobe-C++/simple_types_constant_folding
Profile
|
-8.11% |
2.366 |
2.175 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint8_t>/999
|
-8.09% |
2443.259 |
2245.683 |
0.052 |
0.00% |
0.052 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint8_t>/256
|
-8.08% |
662.339 |
608.816 |
0.015 |
0.00% |
0.015 |
|
MultiSource/Benchmarks/ASC_Sequoia/AMGmk/AMGmk
Profile
|
-7.96% |
43.459 |
39.999 |
0.050 |
0.00% |
0.050 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C++/HPCCG/HPCCG
Profile
|
-7.94% |
4.652 |
4.283 |
0.039 |
0.00% |
0.039 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint16_t>/28
|
-7.85% |
155.494 |
143.288 |
0.002 |
0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint16_t>/16
|
-7.50% |
100.115 |
92.606 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint8_t>/51
|
-7.37% |
172.925 |
160.186 |
0.017 |
0.00% |
0.017 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint16_t>/10
|
-7.28% |
81.654 |
75.711 |
0.001 |
0.00% |
0.001 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C++/miniFE/miniFE
Profile
|
-7.25% |
17.849 |
16.554 |
0.097 |
0.00% |
0.097 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint16_t>/51
|
-7.21% |
169.256 |
157.055 |
0.004 |
0.00% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint8_t>/10
|
-6.75% |
24.538 |
22.882 |
0.430 |
0.00% |
0.430 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint8_t>/999
|
-6.68% |
51.627 |
48.178 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint16_t>/16
|
-6.66% |
89.163 |
83.221 |
0.002 |
0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint8_t>/256
|
-6.66% |
51.617 |
48.180 |
0.003 |
0.00% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint8_t>/28
|
-6.64% |
122.638 |
114.501 |
0.005 |
0.00% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint8_t>/28
|
-6.63% |
51.601 |
48.178 |
0.002 |
0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint8_t>/51
|
-6.58% |
51.577 |
48.182 |
0.002 |
0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint16_t>/28
|
-6.25% |
120.135 |
112.629 |
0.002 |
0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint32_t>/999
|
-5.96% |
4194.518 |
3944.354 |
0.155 |
0.00% |
0.155 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint16_t>/16
|
-5.95% |
39.993 |
37.613 |
0.016 |
0.00% |
0.016 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint64_t>/999
|
-5.70% |
5517.621 |
5203.033 |
0.192 |
0.00% |
0.192 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint16_t>/10
|
-5.69% |
76.960 |
72.581 |
0.003 |
0.00% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint32_t>/999
|
-5.68% |
1453.725 |
1371.082 |
0.206 |
0.00% |
0.206 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint32_t>/256
|
-5.64% |
1087.542 |
1026.163 |
0.078 |
0.00% |
0.078 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint64_t>/999
|
-5.63% |
2804.568 |
2646.540 |
0.343 |
0.00% |
0.343 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint32_t>/999
|
-5.57% |
2131.884 |
2013.037 |
0.049 |
0.00% |
0.049 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint32_t>/51
|
-5.56% |
241.837 |
228.383 |
0.017 |
0.00% |
0.017 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint32_t>/256
|
-5.55% |
581.001 |
548.735 |
0.033 |
0.00% |
0.033 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint8_t>/256
|
-5.54% |
744.568 |
703.293 |
0.029 |
0.00% |
0.029 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint16_t>/256
|
-5.54% |
745.223 |
703.913 |
0.020 |
0.00% |
0.020 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint8_t>/999
|
-5.54% |
2847.792 |
2690.010 |
0.031 |
0.00% |
0.031 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint16_t>/999
|
-5.54% |
2848.455 |
2690.679 |
0.040 |
0.00% |
0.040 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint32_t>/256
|
-5.53% |
745.255 |
704.022 |
0.069 |
0.00% |
0.069 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint8_t>/51
|
-5.52% |
170.196 |
160.806 |
0.003 |
0.00% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint32_t>/28
|
-5.50% |
142.352 |
134.524 |
0.005 |
0.00% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint32_t>/51
|
-5.50% |
170.815 |
161.429 |
0.013 |
0.00% |
0.013 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint16_t>/51
|
-5.49% |
170.824 |
161.437 |
0.006 |
0.00% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint32_t>/999
|
-5.48% |
2846.931 |
2690.972 |
0.145 |
0.00% |
0.145 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint8_t>/256
|
-5.48% |
399.822 |
377.929 |
0.004 |
0.00% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint32_t>/256
|
-5.47% |
400.495 |
378.587 |
0.011 |
0.00% |
0.011 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint16_t>/256
|
-5.47% |
400.440 |
378.555 |
0.009 |
0.00% |
0.009 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint64_t>/51
|
-5.44% |
310.351 |
293.461 |
0.012 |
0.00% |
0.012 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint32_t>/16
|
-5.41% |
92.607 |
87.598 |
0.003 |
0.00% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint16_t>/10
|
-5.39% |
52.248 |
49.430 |
0.003 |
0.00% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint16_t>/999
|
-5.39% |
52.248 |
49.431 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint16_t>/51
|
-5.39% |
52.248 |
49.432 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint16_t>/999
|
-5.39% |
1451.132 |
1372.923 |
0.121 |
0.00% |
0.121 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint16_t>/28
|
-5.39% |
52.247 |
49.432 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint16_t>/16
|
-5.39% |
52.246 |
49.430 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint16_t>/256
|
-5.39% |
52.246 |
49.431 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint8_t>/999
|
-5.36% |
1450.661 |
1372.897 |
0.476 |
0.00% |
0.476 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint64_t>/999
|
-5.34% |
1529.178 |
1447.535 |
0.189 |
0.00% |
0.189 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint64_t>/999
|
-5.31% |
3006.073 |
2846.325 |
0.456 |
0.00% |
0.456 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint64_t>/51
|
-5.24% |
178.325 |
168.978 |
0.211 |
0.00% |
0.211 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint32_t>/51
|
-5.13% |
110.143 |
104.490 |
0.010 |
0.00% |
0.010 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint8_t>/51
|
-5.08% |
110.746 |
105.116 |
0.004 |
0.00% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint32_t>/51
|
-5.01% |
156.117 |
148.291 |
0.002 |
0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint16_t>/16
|
-4.95% |
29.623 |
28.157 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint64_t>/51
|
-4.93% |
113.886 |
108.266 |
0.125 |
0.00% |
0.125 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint32_t>/16
|
-4.87% |
83.532 |
79.467 |
0.003 |
0.00% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint64_t>/51
|
-4.78% |
196.478 |
187.087 |
0.004 |
0.00% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_two_loads<uint8_t>/256
|
-4.76% |
39.419 |
37.541 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_two_loads<uint8_t>/999
|
-4.76% |
39.419 |
37.541 |
0.002 |
0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_two_loads<uint8_t>/51
|
-4.76% |
39.420 |
37.543 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_two_loads<uint16_t>/256
|
-4.69% |
40.045 |
38.166 |
0.002 |
0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_two_loads<uint32_t>/256
|
-4.69% |
40.046 |
38.167 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_two_loads<uint64_t>/999
|
-4.69% |
40.048 |
38.169 |
0.011 |
0.00% |
0.011 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_two_loads<uint32_t>/51
|
-4.69% |
40.046 |
38.167 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_two_loads<uint32_t>/999
|
-4.69% |
40.046 |
38.168 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_two_loads<uint16_t>/999
|
-4.69% |
40.046 |
38.169 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_two_loads<uint16_t>/51
|
-4.69% |
40.046 |
38.169 |
0.002 |
0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_two_loads<uint64_t>/51
|
-4.69% |
40.045 |
38.169 |
0.018 |
0.00% |
0.018 |
|
MultiSource/Benchmarks/TSVC/IndirectAddressing-flt/IndirectAddressing-flt
Profile
|
-4.48% |
15.747 |
15.041 |
0.024 |
0.00% |
0.024 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint32_t>/28
|
-4.45% |
112.632 |
107.623 |
0.002 |
0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC15
|
-4.36% |
273.341 |
261.436 |
3.732 |
0.00% |
3.732 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint32_t>/51
|
-4.35% |
50.371 |
48.178 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint32_t>/256
|
-4.35% |
50.371 |
48.178 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint32_t>/16
|
-4.35% |
50.371 |
48.180 |
0.002 |
0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint32_t>/999
|
-4.35% |
50.370 |
48.180 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint32_t>/28
|
-4.35% |
50.370 |
48.181 |
0.001 |
0.00% |
0.001 |
|
External/SPEC/CINT2017rate/525.x264_r/525.x264_r
Profile
|
-4.26% |
142.176 |
136.114 |
0.165 |
0.00% |
0.165 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint16_t>/51
|
-4.01% |
109.500 |
105.107 |
0.006 |
0.00% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC15
|
-4.00% |
272.396 |
261.509 |
3.728 |
0.00% |
3.728 |
|
SingleSource/Benchmarks/Misc-C++/oopack_v1p8
Profile
|
-3.90% |
0.479 |
0.460 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopTC15
|
-3.83% |
271.926 |
261.509 |
3.739 |
0.00% |
3.739 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_DISC_ORD_RAW/5001
|
-3.69% |
668.254 |
643.586 |
- |
0.00% |
- |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint64_t>/51
|
-3.30% |
56.940 |
55.062 |
0.002 |
0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint64_t>/999
|
-3.30% |
56.939 |
55.061 |
0.004 |
0.00% |
0.004 |
|
External/SPEC/CINT2017rate/523.xalancbmk_r/523.xalancbmk_r
Profile
|
-3.24% |
209.538 |
202.753 |
0.730 |
0.00% |
0.730 |
|
MultiSource/Benchmarks/MiBench/consumer-lame/consumer-lame
Profile
|
-3.23% |
0.682 |
0.660 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC16
|
-3.13% |
265.793 |
257.480 |
1.474 |
0.00% |
1.474 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC7
|
-3.12% |
161.315 |
156.276 |
1.462 |
0.00% |
1.462 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopTC16
|
-3.03% |
265.574 |
257.522 |
1.413 |
0.00% |
1.413 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC15
|
-2.92% |
21.274 |
20.652 |
0.005 |
0.00% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopTC7
|
-2.88% |
160.984 |
156.342 |
1.391 |
0.00% |
1.391 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC16
|
-2.84% |
265.585 |
258.048 |
1.327 |
0.00% |
1.327 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<64, LessThanZero, Last>
|
-2.78% |
4169.969 |
4054.101 |
- |
0.00% |
- |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint64_t>/256
|
-2.77% |
355.305 |
345.459 |
0.012 |
0.00% |
0.012 |
|
MultiSource/Benchmarks/VersaBench/8b10b/8b10b
Profile
|
-2.68% |
9.299 |
9.050 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC16
|
-2.64% |
21.214 |
20.653 |
0.004 |
0.00% |
0.004 |
|
MultiSource/Applications/hexxagon/hexxagon
Profile
|
-2.62% |
8.514 |
8.291 |
0.020 |
0.00% |
0.020 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC7
|
-2.58% |
160.668 |
156.518 |
1.349 |
0.00% |
1.349 |
|
MultiSource/Benchmarks/TSVC/Recurrences-flt/Recurrences-flt
Profile
|
-2.54% |
6.937 |
6.761 |
0.064 |
0.00% |
0.064 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint64_t>/10
|
-2.53% |
30.662 |
29.886 |
0.029 |
0.00% |
0.029 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint16_t>/10
|
-2.33% |
30.782 |
30.064 |
0.036 |
0.00% |
0.036 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint64_t>/16
|
-2.07% |
38.037 |
37.252 |
0.028 |
0.00% |
0.028 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC15
|
-2.05% |
21.081 |
20.649 |
0.003 |
0.00% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_two_loads<uint64_t>/28
|
-2.02% |
16.894 |
16.554 |
0.060 |
0.00% |
0.060 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_two_loads<uint64_t>/10
|
-2.00% |
16.894 |
16.557 |
0.115 |
0.00% |
0.115 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_two_loads<uint64_t>/16
|
-1.99% |
16.894 |
16.558 |
0.049 |
0.00% |
0.049 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint64_t>/28
|
-1.85% |
53.057 |
52.076 |
0.081 |
0.00% |
0.081 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_csa_with_cond_arith_autovec_int64_t_
|
-1.81% |
693303.386 |
680760.475 |
1039.585 |
0.00% |
1039.585 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_two_loads<uint64_t>/256
|
-1.81% |
20.022 |
19.660 |
0.037 |
0.00% |
0.037 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_csa_with_cond_arith_novec_int64_t_
|
-1.76% |
693019.961 |
680811.014 |
821.756 |
0.00% |
821.756 |
|
MultiSource/Benchmarks/TSVC/IndirectAddressing-dbl/IndirectAddressing-dbl
Profile
|
-1.75% |
18.523 |
18.199 |
0.046 |
0.00% |
0.046 |
|
MultiSource/Applications/sgefa/sgefa
Profile
|
-1.74% |
0.642 |
0.631 |
0.002 |
0.00% |
0.002 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, GreaterThanZero, Mid>
|
-1.71% |
30654.876 |
30131.141 |
- |
0.00% |
- |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_BAND_LIN_EQ_LAMBDA/5001
|
-1.65% |
22.519 |
22.148 |
- |
0.00% |
- |
|
SingleSource/Benchmarks/Shootout/Shootout-matrix
Profile
|
-1.60% |
4.693 |
4.617 |
0.000 |
0.00% |
0.000 |
|
MultiSource/Applications/sqlite3/sqlite3
Profile
|
-1.59% |
12.283 |
12.088 |
0.015 |
0.00% |
0.015 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint16_t>/10
|
-1.55% |
22.245 |
21.900 |
0.001 |
0.00% |
0.001 |
|
MultiSource/Benchmarks/TSVC/Expansion-flt/Expansion-flt
Profile
|
-1.49% |
12.429 |
12.244 |
0.013 |
0.00% |
0.013 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_csa_with_in_loop_arith_autovec_int32_t_
|
-1.48% |
375998.947 |
370441.022 |
1115.116 |
0.00% |
1115.116 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<64, EqZero, None>
|
-1.39% |
2890.138 |
2850.073 |
- |
0.00% |
- |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_nested_cond_load_autovec_int64_t_
|
-1.36% |
617543.258 |
609146.927 |
3184.675 |
0.00% |
3184.675 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC15
|
-1.36% |
20.932 |
20.648 |
0.005 |
0.00% |
0.005 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_PIC_1D_RAW/171
|
-1.31% |
9.067 |
8.948 |
- |
0.00% |
- |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC1
|
-1.24% |
108.324 |
106.978 |
0.502 |
0.00% |
0.502 |
|
SingleSource/Benchmarks/CoyoteBench/huffbench
Profile
|
-1.18% |
50.629 |
50.031 |
0.005 |
0.00% |
0.005 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_HYDRO_2D_RAW/5001
|
-1.16% |
16481.951 |
16290.072 |
- |
0.00% |
- |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint64_t>/10
|
-1.16% |
40.674 |
40.201 |
0.024 |
0.00% |
0.024 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_ADI_LAMBDA/5001
|
-1.14% |
1799.188 |
1778.609 |
- |
0.00% |
- |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_cond_load_autovec_int32_t_
|
-1.14% |
251596.724 |
248735.153 |
732.728 |
0.00% |
732.728 |
|
MultiSource/Applications/lambda-0.1.3/lambda
Profile
|
-1.13% |
11.808 |
11.675 |
0.012 |
0.00% |
0.012 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIRST_SUM_LAMBDA/44217
|
-1.10% |
184.992 |
182.956 |
- |
0.00% |
- |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_FIR_RAW/44217
|
-1.09% |
796.299 |
787.635 |
- |
0.00% |
- |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC2
|
-1.07% |
108.197 |
107.035 |
0.447 |
0.00% |
0.447 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_INT_PREDICT_LAMBDA/5001
|
-1.06% |
1980.823 |
1959.817 |
- |
0.00% |
- |