|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchAutoVec<uint8_t>/65
|
-64.59% |
106.976 |
37.881 |
0.001 |
-3.64% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchAutoVec<uint8_t>/127
|
-63.77% |
199.895 |
72.428 |
0.001 |
-1.94% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchAutoVec<uint16_t>/127
|
-49.47% |
224.906 |
113.637 |
0.004 |
-10.17% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchAutoVec<uint16_t>/65
|
-47.83% |
120.555 |
62.895 |
0.002 |
-9.27% |
0.002 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<1, LessThanZero, None>
|
-33.29% |
8789.089 |
5863.471 |
0.106 |
-0.00% |
0.106 |
|
SingleSource/Benchmarks/Shootout-C++/Shootout-C++-nestedloop
Profile
|
-24.31% |
0.300 |
0.227 |
0.000 |
-24.36% |
0.000 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_xor_runtime_checks_pass<16, int>
|
-21.77% |
19.487 |
15.244 |
0.000 |
-0.01% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIRST_DIFF_RAW/171
|
-21.65% |
0.373 |
0.292 |
0.002 |
0.00% |
0.002 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIRST_DIFF_LAMBDA/171
|
-21.65% |
0.373 |
0.292 |
0.003 |
0.00% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint16_t>/10
|
-21.05% |
13.580 |
10.721 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopInterchange/LoopInterchange.test:BENCHMARK_LI1
|
-19.38% |
3161.031 |
2548.325 |
71.801 |
-3.87% |
71.801 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_only_novec_uint8_t_
|
-18.48% |
266476.607 |
217226.567 |
17.935 |
-0.01% |
17.935 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_only_autovec_uint8_t_
|
-18.46% |
266398.575 |
217234.327 |
27.919 |
-0.00% |
27.919 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint16_t>/10
|
-18.39% |
20.727 |
16.915 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint32_t_To_uint8_t_
|
-16.96% |
21452.484 |
17813.213 |
8.143 |
-0.02% |
8.143 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint32_t_To_uint8_t_
|
-16.96% |
21452.470 |
17813.925 |
6.997 |
-0.03% |
6.997 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint32_t_To_uint8_t_
|
-16.96% |
21452.133 |
17813.666 |
6.938 |
-0.02% |
6.938 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint16_t>/16
|
-16.03% |
17.869 |
15.005 |
0.002 |
0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint8_t>/10
|
-14.97% |
35.023 |
29.781 |
0.000 |
-0.00% |
0.000 |
|
MultiSource/Benchmarks/VersaBench/8b10b/8b10b
Profile
|
-14.50% |
11.418 |
9.761 |
0.009 |
-0.03% |
0.009 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopTC7
|
-14.34% |
74.581 |
63.883 |
0.016 |
0.00% |
0.016 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC7
|
-14.34% |
74.572 |
63.877 |
0.002 |
-0.01% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC7
|
-14.30% |
74.543 |
63.882 |
0.004 |
0.00% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_two_loads<uint8_t>/28
|
-14.29% |
5.004 |
4.288 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_two_loads<uint8_t>/51
|
-14.29% |
5.003 |
4.288 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_two_loads<uint8_t>/256
|
-14.29% |
5.003 |
4.288 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_two_loads<uint8_t>/10
|
-14.29% |
5.003 |
4.288 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_two_loads<uint8_t>/999
|
-14.29% |
5.003 |
4.288 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_two_loads<uint8_t>/16
|
-14.29% |
5.003 |
4.288 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint8_t>/10
|
-13.33% |
21.443 |
18.583 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint16_t>/16
|
-13.01% |
29.304 |
25.493 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint8_t>/16
|
-12.79% |
52.180 |
45.506 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint8_t>/16
|
-11.91% |
30.019 |
26.445 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<3, EqZero, First>
|
-11.06% |
2934.092 |
2609.447 |
20.422 |
-0.00% |
20.422 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint8_t>/28
|
-11.03% |
86.491 |
76.953 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint16_t>/28
|
-10.86% |
26.446 |
23.574 |
0.004 |
-0.00% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint8_t>/28
|
-10.61% |
47.174 |
42.168 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchAutoVec<uint32_t>/65
|
-10.60% |
141.514 |
126.506 |
0.002 |
-10.61% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchAutoVec<uint32_t>/127
|
-10.13% |
282.319 |
253.732 |
0.001 |
-10.13% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint8_t>/51
|
-9.86% |
152.243 |
137.233 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint8_t>/51
|
-9.70% |
78.624 |
70.996 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopWithReductionTC3
|
-9.09% |
7.862 |
7.147 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC3
|
-9.09% |
7.862 |
7.147 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint8_t>/127
|
-9.05% |
150.129 |
136.539 |
0.014 |
-9.03% |
0.014 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC4
|
-8.34% |
8.577 |
7.862 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<7, EqZero, First>
|
-8.32% |
10041.817 |
9206.130 |
0.281 |
-0.00% |
0.281 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<6, LessThanZero, First>
|
-8.31% |
11704.657 |
10731.486 |
4.009 |
-0.00% |
4.009 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint8_t>/999
|
-8.25% |
2867.515 |
2630.901 |
0.066 |
0.00% |
0.066 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint8_t>/256
|
-8.21% |
744.063 |
682.951 |
0.011 |
-0.00% |
0.011 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint16_t>/28
|
-8.20% |
46.457 |
42.647 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint8_t>/999
|
-8.16% |
1445.209 |
1327.216 |
0.042 |
-0.00% |
0.042 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint8_t>/256
|
-7.81% |
384.527 |
354.513 |
0.017 |
-0.00% |
0.017 |
|
SingleSource/Benchmarks/Linpack/linpack-pc
Profile
|
-7.68% |
10.102 |
9.326 |
0.006 |
0.07% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint16_t>/51
|
-7.35% |
42.169 |
39.072 |
0.001 |
-0.00% |
0.001 |
|
MultiSource/Benchmarks/Ptrdist/yacr2/yacr2
Profile
|
-7.28% |
1.313 |
1.218 |
0.000 |
0.01% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_only_novec_int32_t_
|
-6.98% |
561686.699 |
522455.357 |
3678.127 |
-0.20% |
3678.127 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIRST_DIFF_RAW/5001
|
-6.98% |
10.731 |
9.982 |
0.010 |
-0.00% |
0.010 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIRST_DIFF_LAMBDA/5001
|
-6.98% |
10.730 |
9.981 |
0.002 |
0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_only_autovec_int32_t_
|
-6.86% |
561647.153 |
523090.231 |
1740.386 |
0.00% |
1740.386 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_single_load<uint16_t>/16
|
-6.67% |
3.574 |
3.335 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_single_load<uint16_t>/10
|
-6.67% |
3.574 |
3.335 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC7
|
-6.67% |
10.721 |
10.006 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_single_load<uint16_t>/256
|
-6.67% |
3.574 |
3.335 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_single_load<uint16_t>/51
|
-6.67% |
3.574 |
3.335 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_single_load<uint16_t>/28
|
-6.66% |
3.574 |
3.335 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC7
|
-6.66% |
10.720 |
10.006 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_single_load<uint16_t>/999
|
-6.66% |
3.574 |
3.335 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1LoopWithReductionTC8
|
-6.25% |
11.436 |
10.721 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopWithReductionTC8
|
-6.25% |
11.435 |
10.721 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_csa_with_cond_arith_novec_uint8_t_
|
-5.79% |
418651.107 |
394414.552 |
92.425 |
-0.36% |
92.425 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_csa_with_cond_arith_autovec_uint8_t_
|
-5.78% |
418628.144 |
394413.288 |
48.993 |
-0.33% |
48.993 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC64
|
-5.70% |
148.567 |
140.092 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC15
|
-5.56% |
136.533 |
128.938 |
0.012 |
0.00% |
0.012 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC15
|
-5.55% |
136.524 |
128.941 |
0.012 |
-0.00% |
0.012 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopTC15
|
-5.36% |
136.246 |
128.945 |
0.006 |
-0.00% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint64_t>/10
|
-5.31% |
31.450 |
29.781 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint8_t>/10
|
-5.01% |
14.296 |
13.580 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint16_t>/51
|
-4.71% |
79.336 |
75.596 |
0.014 |
-0.01% |
0.014 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<3, LessThanZero, First>
|
-4.35% |
22448.289 |
21471.012 |
0.499 |
-0.00% |
0.499 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint64_t>/10
|
-4.17% |
5.718 |
5.480 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint64_t>/256
|
-4.17% |
5.718 |
5.480 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint64_t>/999
|
-4.17% |
5.718 |
5.480 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint64_t>/51
|
-4.17% |
5.718 |
5.480 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint64_t>/28
|
-4.17% |
5.718 |
5.480 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint64_t>/16
|
-4.16% |
5.718 |
5.480 |
0.000 |
-0.00% |
0.000 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C++/HPCCG/HPCCG
Profile
|
-3.96% |
6.529 |
6.271 |
0.031 |
-0.18% |
0.031 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint8_t>/16
|
-3.85% |
18.585 |
17.868 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, GreaterThanZero, First>
|
-3.85% |
38067.863 |
36602.092 |
1.099 |
-0.00% |
1.099 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<3, LessThanZero, Mid>
|
-3.85% |
25373.681 |
24397.846 |
5.145 |
0.00% |
5.145 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC8
|
-3.82% |
79.062 |
76.039 |
0.025 |
0.01% |
0.025 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC8
|
-3.80% |
78.995 |
75.992 |
0.009 |
-0.11% |
0.009 |
|
MultiSource/Benchmarks/mafft/pairlocalalign
Profile
|
-3.68% |
48.630 |
46.839 |
0.011 |
-0.30% |
0.011 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint32_t>/10
|
-3.57% |
20.013 |
19.298 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC4
|
-3.43% |
35.208 |
33.999 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopTC4
|
-3.43% |
35.207 |
33.999 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC4
|
-3.42% |
35.206 |
34.001 |
0.013 |
0.00% |
0.013 |
|
SingleSource/Benchmarks/BenchmarkGame/puzzle
Profile
|
-3.38% |
1.201 |
1.160 |
0.003 |
-1.38% |
0.003 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, GreaterThanZero, None>
|
-3.34% |
43922.951 |
42456.481 |
4.143 |
0.00% |
4.143 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC2
|
-3.33% |
14.294 |
13.818 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1BigLoopWithReductionTC2
|
-3.33% |
14.294 |
13.818 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<3, GreaterThanZero, Last>
|
-3.23% |
30251.470 |
29275.503 |
0.514 |
-0.00% |
0.514 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<5, GreaterThanZero, Mid>
|
-3.22% |
18152.659 |
17567.764 |
3.363 |
-0.00% |
3.363 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, LessThanZero, Mid>
|
-3.22% |
22695.575 |
21964.417 |
0.760 |
-0.00% |
0.760 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<3, LessThanZero, None>
|
-3.13% |
31228.532 |
30251.653 |
0.646 |
-0.00% |
0.646 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_ADI_LAMBDA/171
|
-3.06% |
12.975 |
12.578 |
0.055 |
7.59% |
0.055 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_IMP_HYDRO_2D_RAW/171
|
-3.04% |
11.959 |
11.596 |
0.121 |
-2.67% |
0.121 |
|
MultiSource/Benchmarks/MallocBench/espresso/espresso
Profile
|
-3.01% |
0.856 |
0.830 |
0.001 |
-0.13% |
0.001 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<32, GreaterThanZero, Mid>
|
-2.90% |
3117.092 |
3026.835 |
0.083 |
-0.00% |
0.083 |
|
External/SPEC/CFP2017rate/511.povray_r/511.povray_r
Profile
|
-2.79% |
14.556 |
14.149 |
0.012 |
-0.16% |
0.012 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<5, LessThanZero, None>
|
-2.78% |
21080.824 |
20494.847 |
0.333 |
-0.00% |
0.333 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<5, GreaterThanZero, None>
|
-2.78% |
21080.908 |
20495.462 |
0.456 |
-0.00% |
0.456 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<7, LessThanZero, Last>
|
-2.57% |
16314.055 |
15895.568 |
0.483 |
-0.01% |
0.483 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC16
|
-2.52% |
143.388 |
139.768 |
0.021 |
-0.00% |
0.021 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC16
|
-2.52% |
143.401 |
139.787 |
0.003 |
0.00% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopTC16
|
-2.51% |
143.348 |
139.756 |
0.004 |
-0.02% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint32_t>/16
|
-2.50% |
28.590 |
27.875 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<31, LessThanZero, First>
|
-2.48% |
2336.374 |
2278.497 |
0.073 |
-0.00% |
0.073 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<63, EqZero, First>
|
-2.41% |
1157.128 |
1129.235 |
0.035 |
-0.00% |
0.035 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<8, LessThanZero, None>
|
-2.38% |
15377.264 |
15011.430 |
0.315 |
-0.00% |
0.315 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<15, LessThanZero, Mid>
|
-2.37% |
8202.592 |
8008.306 |
0.230 |
0.00% |
0.230 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_FLOYD_DITHER/512
|
-2.28% |
4884.924 |
4773.585 |
14.865 |
-0.27% |
14.865 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC128
|
-2.24% |
158.652 |
155.094 |
0.014 |
0.00% |
0.014 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC128
|
-2.24% |
158.652 |
155.098 |
0.008 |
0.00% |
0.008 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1LoopWithReductionTC128
|
-2.24% |
158.640 |
155.091 |
0.029 |
-0.01% |
0.029 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC128
|
-2.24% |
158.647 |
155.099 |
0.022 |
-0.00% |
0.022 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopWithReductionTC128
|
-2.23% |
158.655 |
155.111 |
0.013 |
-0.00% |
0.013 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC128
|
-2.23% |
158.652 |
155.108 |
0.005 |
0.00% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC128
|
-2.23% |
158.646 |
155.109 |
0.011 |
0.00% |
0.011 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint32_t>/10
|
-2.18% |
32.880 |
32.163 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_FLOYD_DITHER/128
|
-2.16% |
291.887 |
285.587 |
0.974 |
-0.41% |
0.974 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint64_t>/16
|
-2.05% |
46.457 |
45.506 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_FLOYD_DITHER/256
|
-1.85% |
1191.569 |
1169.484 |
1.294 |
0.00% |
1.294 |
|
MultiSource/Applications/hexxagon/hexxagon
Profile
|
-1.80% |
6.241 |
6.129 |
0.006 |
-0.04% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_nested_cond_load_novec_uint8_t_
|
-1.72% |
708505.071 |
696352.941 |
626.314 |
-0.22% |
626.314 |
|
MultiSource/Benchmarks/ASC_Sequoia/AMGmk/AMGmk
Profile
|
-1.69% |
35.444 |
34.844 |
0.190 |
0.13% |
0.190 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_nested_cond_load_autovec_uint8_t_
|
-1.67% |
709532.653 |
697677.355 |
794.734 |
-0.35% |
794.734 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_VOL3D_CALC_LAMBDA/2
|
-1.60% |
6.882 |
6.771 |
0.001 |
-0.02% |
0.001 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<31, LessThanZero, None>
|
-1.59% |
5255.366 |
5171.750 |
1.125 |
-0.02% |
1.125 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint32_t>/28
|
-1.57% |
45.745 |
45.028 |
0.000 |
-0.00% |
0.000 |
|
SingleSource/Benchmarks/Misc/ReedSolomon
Profile
|
-1.56% |
9.492 |
9.344 |
0.019 |
-0.01% |
0.019 |
|
External/SPEC/CINT2017rate/505.mcf_r/505.mcf_r
Profile
|
-1.52% |
150.782 |
148.485 |
0.698 |
-0.42% |
0.698 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC2
|
-1.46% |
19.337 |
19.054 |
0.003 |
-0.05% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopTC2
|
-1.44% |
19.340 |
19.061 |
0.002 |
-0.01% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint32_t>/16
|
-1.43% |
50.032 |
49.317 |
0.001 |
-0.00% |
0.001 |
|
SingleSource/Benchmarks/Adobe-C++/stepanov_vector
Profile
|
-1.40% |
5.797 |
5.716 |
0.001 |
-0.03% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC2
|
-1.39% |
19.341 |
19.073 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<63, EqZero, None>
|
-1.35% |
3047.028 |
3006.022 |
0.581 |
-0.04% |
0.581 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint32_t_To_uint64_t_
|
-1.31% |
22494.073 |
22199.206 |
14.284 |
0.05% |
14.284 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint32_t_To_uint64_t_
|
-1.30% |
22488.316 |
22196.427 |
19.695 |
-0.05% |
19.695 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint32_t_To_uint64_t_
|
-1.29% |
22490.855 |
22199.759 |
10.832 |
-0.00% |
10.832 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<63, GreaterThanZero, None>
|
-1.28% |
3045.714 |
3006.814 |
0.289 |
-0.00% |
0.289 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopTC31
|
-1.25% |
276.096 |
272.639 |
0.024 |
-0.01% |
0.024 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC31
|
-1.25% |
276.089 |
272.636 |
0.042 |
-0.00% |
0.042 |
|
External/SPEC/CINT2017rate/523.xalancbmk_r/523.xalancbmk_r
Profile
|
-1.24% |
154.799 |
152.878 |
0.685 |
-0.15% |
0.685 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC31
|
-1.23% |
276.078 |
272.672 |
0.021 |
-0.00% |
0.021 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint64_t>/28
|
-1.23% |
77.911 |
76.951 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopTC3
|
-1.20% |
27.489 |
27.159 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC3
|
-1.20% |
27.489 |
27.160 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC3
|
-1.20% |
27.488 |
27.159 |
0.001 |
-0.00% |
0.001 |
|
External/SPEC/CFP2017rate/510.parest_r/510.parest_r
Profile
|
-1.18% |
185.471 |
183.279 |
0.696 |
-0.26% |
0.696 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_ENERGY_CALC_LAMBDA/171
|
-1.15% |
5.364 |
5.303 |
0.007 |
-0.05% |
0.007 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint32_t>/256
|
-1.09% |
197.998 |
195.843 |
0.019 |
-0.00% |
0.019 |
|
MultiSource/Benchmarks/Ptrdist/anagram/anagram
Profile
|
-1.06% |
1.869 |
1.849 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_HYDRO_2D_RAW/44217
|
-1.05% |
29443.083 |
29134.083 |
106.466 |
-0.25% |
106.466 |