|
SingleSource/Benchmarks/BenchmarkGame/puzzle
Profile
|
-24.79% |
1.120 |
0.842 |
0.007 |
-1.19% |
0.007 |
|
SingleSource/Benchmarks/Shootout-C++/Shootout-C++-ary3
Profile
|
-24.55% |
6.082 |
4.589 |
0.040 |
-0.01% |
0.040 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC2
|
-23.08% |
9.292 |
7.147 |
0.002 |
-0.04% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint16_t_To_uint8_t_
|
-22.27% |
21466.838 |
16685.729 |
0.278 |
-0.00% |
0.278 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint16_t_To_uint8_t_
|
-22.26% |
21462.836 |
16686.095 |
0.143 |
-0.00% |
0.143 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint8_t>/999
|
-21.93% |
2170.653 |
1694.597 |
0.029 |
0.00% |
0.029 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint8_t>/999
|
-21.55% |
1101.410 |
864.090 |
0.021 |
-0.01% |
0.021 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_nested_cond_load_novec_int64_t_
|
-21.40% |
1297398.148 |
1019735.080 |
1855.153 |
-0.18% |
1855.153 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_only_novec_int64_t_
|
-21.38% |
859264.128 |
675588.406 |
750.371 |
-0.12% |
750.371 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint8_t>/256
|
-21.16% |
577.498 |
455.279 |
0.009 |
-0.00% |
0.009 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint8_t>/256
|
-19.63% |
305.906 |
245.861 |
0.004 |
-0.00% |
0.004 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_PRESSURE_CALC_LAMBDA/5001
|
-19.31% |
49.920 |
40.279 |
2.286 |
1.77% |
2.286 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint8_t>/51
|
-19.10% |
78.623 |
63.609 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint8_t>/51
|
-18.58% |
130.799 |
106.497 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint8_t>/28
|
-16.89% |
55.036 |
45.740 |
0.003 |
-0.01% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint16_t_To_uint8_t_
|
-16.68% |
14314.411 |
11927.173 |
0.211 |
-0.01% |
0.211 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint8_t>/28
|
-16.67% |
81.482 |
67.899 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint8_t_To_uint16_t_
|
-16.64% |
14310.950 |
11929.414 |
0.262 |
-0.00% |
0.262 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC63
|
-16.60% |
75.983 |
63.370 |
0.003 |
-0.01% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopFrom_uint16_t_To_uint8_t_
|
-16.59% |
14301.700 |
11929.751 |
0.245 |
0.00% |
0.245 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint8_t_To_uint16_t_
|
-16.58% |
14301.659 |
11930.177 |
0.169 |
-0.00% |
0.169 |
|
SingleSource/Benchmarks/CoyoteBench/huffbench
Profile
|
-16.37% |
38.288 |
32.022 |
0.010 |
-0.04% |
0.010 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC63
|
-15.13% |
74.669 |
63.374 |
0.001 |
0.00% |
0.001 |
|
SingleSource/Benchmarks/Shootout/Shootout-sieve
Profile
|
-14.75% |
8.396 |
7.158 |
0.035 |
-0.32% |
0.035 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint8_t>/16
|
-14.10% |
55.750 |
47.887 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopWithReductionTC64
|
-13.64% |
74.484 |
64.327 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_DIFF_PREDICT_RAW/171
|
-12.69% |
4.216 |
3.681 |
0.008 |
-0.04% |
0.008 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_DIFF_PREDICT_LAMBDA/171
|
-12.65% |
4.213 |
3.680 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_csa_with_cond_arith_autovec_int64_t_
|
-12.43% |
783612.975 |
686220.588 |
252.640 |
-0.08% |
252.640 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_csa_with_cond_arith_novec_int64_t_
|
-12.20% |
784106.502 |
688456.158 |
201.442 |
-0.11% |
201.442 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint8_t>/16
|
-11.87% |
42.170 |
37.166 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint8_t>/10
|
-11.67% |
42.884 |
37.880 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint64_t_To_uint8_t_
|
-11.33% |
21453.554 |
19023.143 |
2.942 |
-0.02% |
2.942 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC16
|
-11.30% |
37.881 |
33.600 |
0.256 |
-1.45% |
0.256 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC128
|
-10.75% |
285.893 |
255.148 |
0.015 |
0.00% |
0.015 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC15
|
-10.67% |
35.736 |
31.925 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC64
|
-10.62% |
140.089 |
125.206 |
0.015 |
-0.01% |
0.015 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC63
|
-10.53% |
137.940 |
123.412 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC127
|
-10.35% |
283.036 |
253.737 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_DIFF_PREDICT_RAW/5001
|
-10.27% |
207.509 |
186.189 |
0.505 |
0.01% |
0.505 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC31
|
-10.25% |
69.331 |
62.226 |
0.021 |
-0.07% |
0.021 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC32
|
-10.00% |
71.474 |
64.326 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_DIFF_PREDICT_LAMBDA/5001
|
-9.83% |
206.704 |
186.389 |
2.488 |
0.01% |
2.488 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_only_novec_int32_t_
|
-9.77% |
607251.736 |
547937.252 |
8749.598 |
-2.24% |
8749.598 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_BAND_LIN_EQ_RAW/171
|
-9.54% |
0.247 |
0.224 |
0.000 |
-0.01% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC127
|
-9.42% |
155.453 |
140.809 |
2.742 |
0.01% |
2.742 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint64_t>/16
|
-9.23% |
46.458 |
42.169 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1LoopWithReductionTC1
|
-9.16% |
5.100 |
4.633 |
0.079 |
-1.32% |
0.079 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC3
|
-9.09% |
7.862 |
7.147 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_BAND_LIN_EQ_LAMBDA/171
|
-9.02% |
0.246 |
0.224 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint8_t>/51
|
-8.83% |
97.205 |
88.627 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint8_t>/16
|
-8.82% |
48.602 |
44.314 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_with_cond_arith_autovec_int64_t_
|
-8.80% |
451530.293 |
411807.531 |
8823.917 |
-0.59% |
8823.917 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint8_t>/28
|
-8.70% |
65.757 |
60.037 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_cond_load_autovec_int32_t_
|
-8.53% |
592397.133 |
541888.268 |
5966.113 |
-0.52% |
5966.113 |
|
SingleSource/Benchmarks/Shootout/Shootout-matrix
Profile
|
-8.51% |
4.822 |
4.412 |
0.010 |
-0.15% |
0.010 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<63, LessThanZero, First>
|
-8.31% |
1237.920 |
1135.044 |
0.008 |
-0.00% |
0.008 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint64_t>/51
|
-8.28% |
95.060 |
87.192 |
0.003 |
-0.01% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint8_t>/999
|
-8.25% |
2884.671 |
2646.578 |
0.073 |
-0.01% |
0.073 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint32_t>/999
|
-8.21% |
2883.958 |
2647.289 |
0.036 |
0.00% |
0.036 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint64_t>/999
|
-8.18% |
2882.665 |
2646.797 |
2.348 |
-0.00% |
2.348 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint64_t>/999
|
-8.07% |
1460.922 |
1342.976 |
5.378 |
-0.01% |
5.378 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint8_t>/999
|
-8.07% |
1461.649 |
1343.655 |
0.031 |
-0.01% |
0.031 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint32_t>/999
|
-8.07% |
1461.573 |
1343.669 |
0.028 |
-0.00% |
0.028 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint8_t>/10
|
-8.01% |
35.737 |
32.876 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<5, GreaterThanZero, First>
|
-8.00% |
14643.042 |
13471.419 |
4.821 |
0.00% |
4.821 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC128
|
-7.94% |
163.676 |
150.678 |
2.985 |
-4.18% |
2.985 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC7
|
-7.93% |
17.868 |
16.451 |
0.053 |
-0.01% |
0.053 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint8_t>/256
|
-7.90% |
760.491 |
700.420 |
0.020 |
-0.01% |
0.020 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint64_t>/28
|
-7.87% |
63.612 |
58.607 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint64_t>/256
|
-7.82% |
758.325 |
698.997 |
0.010 |
-0.00% |
0.010 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint32_t>/256
|
-7.81% |
759.744 |
700.431 |
0.005 |
0.00% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC2
|
-7.70% |
9.292 |
8.576 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint8_t>/28
|
-7.64% |
102.920 |
95.059 |
0.002 |
0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint16_t>/127
|
-7.56% |
170.105 |
157.237 |
1.224 |
0.25% |
1.224 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_cond_load_autovec_int64_t_
|
-7.55% |
864000.000 |
798773.973 |
686.997 |
-0.02% |
686.997 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint32_t>/256
|
-7.31% |
400.948 |
371.653 |
0.005 |
0.00% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint64_t>/51
|
-7.30% |
166.536 |
154.377 |
0.003 |
-0.01% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint8_t>/16
|
-7.29% |
68.616 |
63.612 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint8_t>/256
|
-7.29% |
402.404 |
373.078 |
0.011 |
-0.01% |
0.011 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint8_t>/51
|
-7.24% |
167.963 |
155.805 |
0.003 |
-0.01% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint64_t>/256
|
-7.15% |
400.255 |
371.652 |
0.010 |
-0.00% |
0.010 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint8_t>/10
|
-7.15% |
40.025 |
37.165 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC8
|
-7.14% |
20.013 |
18.584 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint64_t>/28
|
-7.09% |
100.778 |
93.628 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_IMP_HYDRO_2D_LAMBDA/44217
|
-6.78% |
6906.020 |
6437.679 |
179.715 |
-2.30% |
179.715 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC3
|
-6.67% |
10.721 |
10.006 |
0.000 |
-0.01% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC3
|
-6.66% |
10.721 |
10.006 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint32_t>/51
|
-6.46% |
165.814 |
155.098 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint64_t>/16
|
-6.46% |
66.473 |
62.181 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_INT_PREDICT_RAW/5001
|
-6.37% |
120.317 |
112.648 |
0.412 |
0.26% |
0.412 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint16_t>/256
|
-6.29% |
227.291 |
212.989 |
0.001 |
-0.00% |
0.001 |
|
MultiSource/Benchmarks/SciMark2-C/scimark2
Profile
|
-6.26% |
55.534 |
52.059 |
0.019 |
-0.03% |
0.019 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_DIFF_PREDICT_RAW/44217
|
-6.15% |
5409.620 |
5076.708 |
2.309 |
0.27% |
2.309 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_INT_PREDICT_LAMBDA/5001
|
-6.13% |
119.931 |
112.577 |
0.353 |
-0.25% |
0.353 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, EqZero, First>
|
-6.10% |
10253.069 |
9627.723 |
4.057 |
-0.00% |
4.057 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint32_t>/51
|
-6.06% |
94.340 |
88.624 |
0.002 |
-0.00% |
0.002 |
|
SingleSource/Benchmarks/BenchmarkGame/n-body
Profile
|
-6.03% |
2.632 |
2.473 |
0.001 |
0.03% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_DIFF_PREDICT_LAMBDA/44217
|
-5.89% |
5417.157 |
5097.986 |
21.864 |
0.06% |
21.864 |
|
MultiSource/Benchmarks/TSVC/LoopRerolling-dbl/LoopRerolling-dbl
Profile
|
-5.76% |
11.604 |
10.935 |
0.088 |
0.05% |
0.088 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint32_t>/28
|
-5.68% |
62.894 |
59.323 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint8_t>/10
|
-5.56% |
51.463 |
48.602 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_INT_PREDICT_RAW/44217
|
-5.53% |
3737.113 |
3530.414 |
19.893 |
-0.37% |
19.893 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/128
|
-5.41% |
2920.600 |
2762.680 |
8.815 |
-0.02% |
8.815 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopFrom_uint32_t_To_uint64_t_
|
-5.39% |
14316.409 |
13544.656 |
8.369 |
-0.12% |
8.369 |
|
MultiSource/Benchmarks/Olden/tsp/tsp
Profile
|
-5.33% |
3.273 |
3.099 |
0.007 |
0.04% |
0.007 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint32_t_To_uint64_t_
|
-5.33% |
14304.152 |
13541.188 |
9.579 |
-0.12% |
9.579 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint32_t_To_uint64_t_
|
-5.27% |
14307.927 |
13553.746 |
0.985 |
0.01% |
0.985 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC1
|
-5.16% |
13.087 |
12.412 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopWithReductionTC2
|
-5.11% |
5.718 |
5.426 |
0.018 |
-0.56% |
0.018 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint32_t>/28
|
-5.00% |
100.058 |
95.058 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint16_t>/256
|
-4.99% |
258.025 |
245.148 |
1.220 |
-0.01% |
1.220 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_PIC_2D_RAW/44217
|
-4.98% |
1612.498 |
1532.139 |
12.902 |
-0.02% |
12.902 |
|
MicroBenchmarks/harris/harris.test:BENCHMARK_HARRIS/1024/1024
|
-4.94% |
55709.923 |
52955.154 |
204.094 |
-0.97% |
204.094 |
|
SingleSource/Benchmarks/McGill/queens
Profile
|
-4.94% |
3.395 |
3.227 |
0.000 |
-0.01% |
0.000 |
|
MultiSource/Applications/obsequi/Obsequi
Profile
|
-4.92% |
4.428 |
4.210 |
0.007 |
-0.00% |
0.007 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/64
|
-4.84% |
725.260 |
690.142 |
1.065 |
-0.02% |
1.065 |
|
MultiSource/Applications/kimwitu++/kc
Profile
|
-4.73% |
0.281 |
0.268 |
0.001 |
-1.29% |
0.001 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/256
|
-4.70% |
11957.271 |
11395.672 |
23.825 |
-0.04% |
23.825 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint32_t>/16
|
-4.68% |
45.740 |
43.599 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_INT_PREDICT_LAMBDA/44217
|
-4.51% |
3713.516 |
3545.929 |
7.620 |
-0.20% |
7.620 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/32
|
-4.51% |
178.973 |
170.905 |
0.372 |
0.12% |
0.372 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint64_t>/10
|
-4.35% |
49.317 |
47.172 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint32_t>/16
|
-4.35% |
65.754 |
62.895 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint16_t>/256
|
-4.10% |
412.890 |
395.951 |
0.002 |
-0.01% |
0.002 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_PIC_2D_LAMBDA/44217
|
-3.89% |
1610.979 |
1548.240 |
3.727 |
0.25% |
3.727 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC7
|
-3.84% |
18.583 |
17.869 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint32_t>/10
|
-3.84% |
37.165 |
35.736 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint16_t>/10
|
-3.77% |
37.880 |
36.450 |
0.000 |
-0.01% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint64_t>/10
|
-3.77% |
37.881 |
36.451 |
0.000 |
-0.00% |
0.000 |
|
SingleSource/Benchmarks/Misc/mandel
Profile
|
-3.55% |
1.328 |
1.281 |
0.000 |
-0.01% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC8
|
-3.45% |
20.728 |
20.013 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC8
|
-3.45% |
20.727 |
20.013 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, GreaterThanZero, None>
|
-3.33% |
43917.179 |
42455.328 |
0.989 |
0.00% |
0.989 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopTC1
|
-3.27% |
13.199 |
12.768 |
0.091 |
0.03% |
0.091 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<3, GreaterThanZero, Last>
|
-3.23% |
30251.405 |
29274.092 |
1.368 |
-0.00% |
1.368 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<3, EqZero, Last>
|
-3.22% |
30250.281 |
29274.845 |
0.447 |
-0.00% |
0.447 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, GreaterThanZero, Mid>
|
-3.22% |
22695.837 |
21964.137 |
0.388 |
-0.01% |
0.388 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC127
|
-3.20% |
156.529 |
151.517 |
0.005 |
-0.00% |
0.005 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_PRESSURE_CALC_RAW/171
|
-3.19% |
1.279 |
1.238 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint64_t>/999
|
-3.13% |
22.871 |
22.156 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint64_t>/256
|
-3.13% |
22.871 |
22.156 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint64_t>/10
|
-3.13% |
22.871 |
22.156 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint64_t>/28
|
-3.13% |
22.871 |
22.157 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint64_t>/16
|
-3.13% |
22.872 |
22.157 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint64_t>/51
|
-3.12% |
22.871 |
22.157 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<3, EqZero, None>
|
-3.12% |
31225.018 |
30249.892 |
0.244 |
-0.00% |
0.244 |
|
MicroBenchmarks/harris/harris.test:BENCHMARK_HARRIS/512/512
|
-3.11% |
14126.245 |
13687.255 |
138.093 |
-0.79% |
138.093 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_HYDRO_1D_LAMBDA/5001
|
-3.08% |
14.474 |
14.028 |
0.028 |
-0.86% |
0.028 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint16_t>/16
|
-3.08% |
46.455 |
45.026 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint32_t>/51
|
-3.03% |
23.585 |
22.871 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint32_t>/16
|
-3.03% |
23.585 |
22.871 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint32_t>/28
|
-3.03% |
23.585 |
22.871 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint32_t>/10
|
-3.03% |
23.585 |
22.871 |
0.000 |
-0.01% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint32_t>/256
|
-3.03% |
23.585 |
22.871 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint32_t>/999
|
-3.03% |
23.586 |
22.872 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<6, EqZero, Mid>
|
-3.02% |
16094.893 |
15608.116 |
0.079 |
-0.01% |
0.079 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<6, GreaterThanZero, Mid>
|
-3.01% |
16093.298 |
15608.273 |
0.144 |
-0.01% |
0.144 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_csa_with_in_loop_arith_novec_int64_t_
|
-2.97% |
943353.576 |
915339.895 |
4818.536 |
0.08% |
4818.536 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC7
|
-2.93% |
61.723 |
59.915 |
0.011 |
-0.06% |
0.011 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint16_t>/10
|
-2.90% |
49.315 |
47.886 |
0.000 |
-0.01% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint16_t>/256
|
-2.86% |
473.871 |
460.304 |
0.007 |
-0.00% |
0.007 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<5, EqZero, Last>
|
-2.85% |
20494.979 |
19910.363 |
0.420 |
-0.00% |
0.420 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<32, EqZero, Mid>
|
-2.85% |
3210.515 |
3118.978 |
5.440 |
-0.03% |
5.440 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<5, GreaterThanZero, Last>
|
-2.84% |
20494.905 |
19911.848 |
0.032 |
-0.00% |
0.032 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<8, EqZero, Mid>
|
-2.84% |
12815.877 |
12451.605 |
0.294 |
-0.00% |
0.294 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_csa_with_cond_arith_novec_uint8_t_
|
-2.84% |
278692.246 |
270777.477 |
844.779 |
0.18% |
844.779 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<6, LessThanZero, Last>
|
-2.62% |
18529.818 |
18044.601 |
0.078 |
0.00% |
0.078 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/16
|
-2.50% |
43.729 |
42.634 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<7, EqZero, None>
|
-2.49% |
16731.263 |
16313.903 |
0.022 |
-0.00% |
0.022 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<7, LessThanZero, Last>
|
-2.48% |
16731.669 |
16316.151 |
0.065 |
0.00% |
0.065 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint32_t>/10
|
-2.44% |
29.303 |
28.589 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<8, GreaterThanZero, None>
|
-2.38% |
15376.999 |
15010.811 |
0.380 |
-0.00% |
0.380 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint16_t>/28
|
-2.25% |
63.610 |
62.180 |
0.001 |
-0.01% |
0.001 |
|
MultiSource/Benchmarks/Trimaran/enc-3des/enc-3des
Profile
|
-2.22% |
3.143 |
3.073 |
0.000 |
-0.03% |
0.000 |
|
SingleSource/Benchmarks/CoyoteBench/lpbench
Profile
|
-2.16% |
7.764 |
7.597 |
0.009 |
0.01% |
0.009 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint16_t>/16
|
-2.15% |
66.468 |
65.039 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopTC7
|
-2.00% |
62.224 |
60.977 |
0.065 |
-0.21% |
0.065 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC15
|
-2.00% |
35.738 |
35.023 |
0.000 |
0.00% |
0.000 |
|
MultiSource/Benchmarks/TSVC/ControlLoops-flt/ControlLoops-flt
Profile
|
-1.98% |
8.270 |
8.106 |
0.044 |
-1.98% |
0.044 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC1
|
-1.97% |
13.163 |
12.903 |
0.008 |
-0.07% |
0.008 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC32
|
-1.96% |
72.902 |
71.473 |
0.002 |
-0.00% |
0.002 |
|
MultiSource/Benchmarks/Fhourstones-3.1/fhourstones3.1
Profile
|
-1.95% |
2.467 |
2.418 |
0.003 |
-0.26% |
0.003 |
|
SingleSource/Benchmarks/Misc/perlin
Profile
|
-1.89% |
7.274 |
7.136 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC16
|
-1.89% |
37.882 |
37.167 |
0.000 |
0.00% |
0.000 |
|
SingleSource/Benchmarks/Misc/flops-8
Profile
|
-1.80% |
1.769 |
1.738 |
0.000 |
-0.01% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint8_t>/28
|
-1.79% |
40.025 |
39.310 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_PIC_2D_LAMBDA/5001
|
-1.77% |
178.683 |
175.516 |
0.232 |
0.01% |
0.232 |
|
SingleSource/Benchmarks/Polybench/stencils/seidel-2d/seidel-2d
Profile
|
-1.72% |
163.693 |
160.874 |
0.171 |
-0.08% |
0.171 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint32_t>/127
|
-1.70% |
170.140 |
167.244 |
0.023 |
-0.01% |
0.023 |
|
MultiSource/Benchmarks/TSVC/InductionVariable-flt/InductionVariable-flt
Profile
|
-1.65% |
10.226 |
10.057 |
0.046 |
0.02% |
0.046 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint16_t>/999
|
-1.63% |
878.443 |
864.121 |
2.054 |
0.00% |
2.054 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint16_t>/999
|
-1.62% |
755.509 |
743.296 |
0.023 |
-0.00% |
0.023 |
|
MultiSource/Benchmarks/Bullet/bullet
Profile
|
-1.57% |
14.692 |
14.461 |
0.049 |
-0.40% |
0.049 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint16_t>/51
|
-1.50% |
95.055 |
93.629 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_csa_with_in_loop_arith_novec_uint8_t_
|
-1.48% |
520062.454 |
512385.746 |
625.489 |
0.23% |
625.489 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint32_t>/10
|
-1.47% |
48.601 |
47.887 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint16_t>/28
|
-1.42% |
100.778 |
99.345 |
0.003 |
-0.00% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC128
|
-1.40% |
155.868 |
153.693 |
0.092 |
-0.01% |
0.092 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_csa_with_cond_arith_autovec_uint8_t_
|
-1.27% |
277924.005 |
274393.166 |
821.840 |
0.43% |
821.840 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_GEN_LIN_RECUR_RAW/44217
|
-1.26% |
512.532 |
506.054 |
0.619 |
0.01% |
0.619 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_with_cond_arith_autovec_uint8_t_
|
-1.21% |
402657.652 |
397788.516 |
1842.087 |
-0.05% |
1842.087 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_with_cond_arith_novec_uint8_t_
|
-1.21% |
402726.697 |
397862.500 |
1817.304 |
-0.03% |
1817.304 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint16_t>/999
|
-1.17% |
1475.274 |
1458.035 |
0.037 |
-0.00% |
0.037 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1BigLoopWithReductionTC64
|
-1.15% |
310.745 |
307.165 |
0.012 |
-0.00% |
0.012 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C/CoMD/CoMD
Profile
|
-1.09% |
5.023 |
4.968 |
0.012 |
-0.05% |
0.012 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC63
|
-1.08% |
305.650 |
302.355 |
0.006 |
0.00% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC31
|
-1.02% |
70.043 |
69.330 |
0.000 |
0.00% |
0.000 |