|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchAutoVec<uint8_t>/65
|
-63.25% |
106.976 |
39.310 |
0.001 |
3.77% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchAutoVec<uint8_t>/127
|
-63.05% |
199.895 |
73.856 |
0.001 |
1.97% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchAutoVec<uint16_t>/127
|
-43.75% |
224.906 |
126.505 |
0.002 |
11.32% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchAutoVec<uint16_t>/65
|
-42.49% |
120.555 |
69.327 |
0.002 |
10.22% |
0.002 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<1, LessThanZero, None>
|
-33.29% |
8789.089 |
5863.401 |
0.028 |
-0.00% |
0.028 |
|
MicroBenchmarks/LoopInterchange/LoopInterchange.test:BENCHMARK_LI1
|
-21.85% |
3161.031 |
2470.331 |
69.806 |
-2.12% |
69.806 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_xor_runtime_checks_pass<16, int>
|
-21.80% |
19.487 |
15.238 |
0.005 |
-0.05% |
0.005 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIRST_DIFF_RAW/171
|
-21.65% |
0.373 |
0.292 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIRST_DIFF_LAMBDA/171
|
-21.65% |
0.373 |
0.292 |
0.004 |
0.00% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint16_t>/10
|
-21.15% |
13.580 |
10.708 |
0.006 |
-0.12% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_only_novec_uint8_t_
|
-18.48% |
266476.607 |
217230.292 |
19.452 |
-0.00% |
19.452 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_only_autovec_uint8_t_
|
-18.45% |
266398.575 |
217236.499 |
20.394 |
-0.00% |
20.394 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint16_t>/10
|
-18.39% |
20.727 |
16.916 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint8_t>/65
|
-18.37% |
79.675 |
65.040 |
0.002 |
-13.70% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint32_t_To_uint8_t_
|
-16.99% |
21452.470 |
17808.523 |
6.820 |
-0.06% |
6.820 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint32_t_To_uint8_t_
|
-16.98% |
21452.484 |
17809.164 |
7.419 |
-0.07% |
7.419 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint32_t_To_uint8_t_
|
-16.97% |
21452.133 |
17810.644 |
6.590 |
-0.05% |
6.590 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint16_t>/16
|
-16.12% |
17.869 |
14.989 |
0.006 |
-0.13% |
0.006 |
|
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
|
-14.56% |
11.418 |
9.755 |
0.015 |
-0.03% |
0.015 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopTC7
|
-14.35% |
74.581 |
63.877 |
0.003 |
-0.01% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC7
|
-14.33% |
74.572 |
63.885 |
0.001 |
0.00% |
0.001 |
|
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/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC7
|
-14.29% |
74.543 |
63.888 |
0.001 |
0.00% |
0.001 |
|
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>/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>/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>/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>/16
|
-14.28% |
5.003 |
4.289 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint8_t>/10
|
-13.34% |
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 |
25.492 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint8_t>/16
|
-12.79% |
52.180 |
45.504 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint8_t>/16
|
-11.91% |
30.019 |
26.444 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_no_runtime_checks_needed<4, int>
|
-11.11% |
6.433 |
5.718 |
0.000 |
-11.12% |
0.000 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<3, EqZero, First>
|
-11.07% |
2934.092 |
2609.301 |
15.676 |
-0.01% |
15.676 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint8_t>/28
|
-11.03% |
86.491 |
76.950 |
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 |
0.003 |
-0.02% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint8_t>/28
|
-10.61% |
47.174 |
42.169 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint8_t>/51
|
-9.86% |
152.243 |
137.226 |
0.003 |
0.00% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint8_t>/51
|
-9.70% |
78.624 |
70.999 |
0.000 |
-0.00% |
0.000 |
|
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/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 |
9206.118 |
0.192 |
-0.00% |
0.192 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<6, LessThanZero, First>
|
-8.32% |
11704.657 |
10731.158 |
2.743 |
-0.01% |
2.743 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint8_t>/999
|
-8.25% |
2867.515 |
2630.906 |
0.051 |
-0.00% |
0.051 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint8_t>/256
|
-8.22% |
744.063 |
682.914 |
0.004 |
-0.00% |
0.004 |
|
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 |
1327.232 |
0.039 |
0.00% |
0.039 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint8_t>/256
|
-7.80% |
384.527 |
354.545 |
0.019 |
0.00% |
0.019 |
|
SingleSource/Benchmarks/Linpack/linpack-pc
Profile
|
-7.72% |
10.102 |
9.322 |
0.005 |
-0.01% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint16_t>/51
|
-7.34% |
42.169 |
39.073 |
0.000 |
-0.00% |
0.000 |
|
MultiSource/Benchmarks/Ptrdist/yacr2/yacr2
Profile
|
-7.28% |
1.313 |
1.218 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIRST_DIFF_RAW/5001
|
-6.98% |
10.731 |
9.982 |
0.000 |
0.00% |
0.000 |
|
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_novec_int32_t_
|
-6.74% |
561686.699 |
523846.154 |
2878.117 |
-0.16% |
2878.117 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_only_autovec_int32_t_
|
-6.72% |
561647.153 |
523914.925 |
1834.495 |
0.21% |
1834.495 |
|
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/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/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>/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>/28
|
-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
|
-6.66% |
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
|
-6.26% |
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/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC64
|
-5.71% |
148.567 |
140.085 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC15
|
-5.56% |
136.533 |
128.945 |
0.010 |
0.01% |
0.010 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC15
|
-5.55% |
136.524 |
128.949 |
0.006 |
-0.00% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_csa_with_cond_arith_novec_uint8_t_
|
-5.51% |
418651.107 |
395564.972 |
497.971 |
0.05% |
497.971 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_csa_with_cond_arith_autovec_uint8_t_
|
-5.48% |
418628.144 |
395669.118 |
528.398 |
0.16% |
528.398 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopTC15
|
-5.36% |
136.246 |
128.943 |
0.005 |
-0.00% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint64_t>/10
|
-5.31% |
31.450 |
29.780 |
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
|
-4.75% |
79.336 |
75.567 |
0.024 |
-0.05% |
0.024 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<3, LessThanZero, First>
|
-4.35% |
22448.289 |
21470.830 |
0.552 |
-0.00% |
0.552 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint64_t>/256
|
-4.18% |
5.718 |
5.479 |
0.000 |
0.00% |
0.000 |
|
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>/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>/16
|
-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>/999
|
-4.17% |
5.718 |
5.480 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC8
|
-4.01% |
79.062 |
75.894 |
0.084 |
-0.01% |
0.084 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC8
|
-3.97% |
78.995 |
75.856 |
0.081 |
0.06% |
0.081 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C++/HPCCG/HPCCG
Profile
|
-3.88% |
6.529 |
6.276 |
0.042 |
-0.23% |
0.042 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint8_t>/16
|
-3.85% |
18.585 |
17.868 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, GreaterThanZero, First>
|
-3.85% |
38067.863 |
36600.491 |
1.721 |
-0.00% |
1.721 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<3, LessThanZero, Mid>
|
-3.85% |
25373.681 |
24397.086 |
0.865 |
-0.01% |
0.865 |
|
MultiSource/Benchmarks/mafft/pairlocalalign
Profile
|
-3.68% |
48.630 |
46.840 |
0.016 |
-0.01% |
0.016 |
|
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 |
33.998 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC4
|
-3.43% |
35.206 |
33.998 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, GreaterThanZero, None>
|
-3.34% |
43922.951 |
42457.181 |
3.374 |
0.00% |
3.374 |
|
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 |
29275.085 |
0.440 |
-0.01% |
0.440 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, LessThanZero, Mid>
|
-3.22% |
22695.575 |
21964.314 |
0.536 |
-0.01% |
0.536 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<5, GreaterThanZero, Mid>
|
-3.22% |
18152.659 |
17567.804 |
0.660 |
-0.01% |
0.660 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<3, LessThanZero, None>
|
-3.13% |
31228.532 |
30250.821 |
0.991 |
-0.01% |
0.991 |
|
MultiSource/Benchmarks/MallocBench/espresso/espresso
Profile
|
-2.98% |
0.856 |
0.830 |
0.001 |
-0.17% |
0.001 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<16, LessThanZero, Mid>
|
-2.94% |
6229.534 |
6046.305 |
0.204 |
-0.01% |
0.204 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<16, EqZero, Mid>
|
-2.93% |
6228.741 |
6046.329 |
0.490 |
-0.01% |
0.490 |
|
External/SPEC/CFP2017rate/511.povray_r/511.povray_r
Profile
|
-2.93% |
14.556 |
14.130 |
0.011 |
-0.16% |
0.011 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<32, GreaterThanZero, Mid>
|
-2.90% |
3117.092 |
3026.787 |
2.396 |
-0.01% |
2.396 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<5, LessThanZero, None>
|
-2.78% |
21080.824 |
20494.876 |
0.407 |
-0.00% |
0.407 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<5, GreaterThanZero, None>
|
-2.78% |
21080.908 |
20495.535 |
0.316 |
-0.00% |
0.316 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<7, LessThanZero, Last>
|
-2.57% |
16314.055 |
15895.311 |
0.371 |
-0.00% |
0.371 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC16
|
-2.53% |
143.388 |
139.758 |
0.002 |
-0.02% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC16
|
-2.53% |
143.401 |
139.774 |
0.006 |
-0.01% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopTC16
|
-2.51% |
143.348 |
139.754 |
0.019 |
-0.01% |
0.019 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint32_t>/16
|
-2.51% |
28.590 |
27.874 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<31, LessThanZero, First>
|
-2.51% |
2336.374 |
2277.846 |
0.312 |
-0.03% |
0.312 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<63, EqZero, First>
|
-2.41% |
1157.128 |
1129.245 |
0.020 |
-0.00% |
0.020 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<8, LessThanZero, None>
|
-2.38% |
15377.264 |
15011.408 |
0.132 |
-0.00% |
0.132 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<15, LessThanZero, Mid>
|
-2.37% |
8202.592 |
8008.100 |
0.290 |
-0.01% |
0.290 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopWithReductionTC128
|
-2.24% |
158.655 |
155.096 |
0.010 |
-0.01% |
0.010 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC128
|
-2.24% |
158.652 |
155.100 |
0.009 |
-0.00% |
0.009 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC128
|
-2.24% |
158.647 |
155.096 |
0.026 |
-0.00% |
0.026 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC128
|
-2.23% |
158.652 |
155.112 |
0.024 |
0.00% |
0.024 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC128
|
-2.23% |
158.652 |
155.118 |
0.004 |
0.01% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC128
|
-2.23% |
158.646 |
155.113 |
0.016 |
-0.00% |
0.016 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1LoopWithReductionTC128
|
-2.21% |
158.640 |
155.132 |
0.010 |
-0.01% |
0.010 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint32_t>/10
|
-2.18% |
32.880 |
32.162 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint64_t>/16
|
-2.05% |
46.457 |
45.505 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_nested_cond_load_novec_uint8_t_
|
-1.94% |
708505.071 |
694781.655 |
2158.433 |
-0.31% |
2158.433 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_FLOYD_DITHER/256
|
-1.88% |
1191.569 |
1169.225 |
1.016 |
0.01% |
1.016 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_FLOYD_DITHER/128
|
-1.84% |
291.887 |
286.512 |
0.105 |
-0.05% |
0.105 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_HYDRO_2D_RAW/44217
|
-1.83% |
29443.083 |
28903.042 |
107.061 |
-0.81% |
107.061 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<64, GreaterThanZero, Last>
|
-1.82% |
2477.986 |
2432.862 |
2.296 |
-0.01% |
2.296 |
|
MultiSource/Applications/hexxagon/hexxagon
Profile
|
-1.72% |
6.241 |
6.133 |
0.007 |
0.00% |
0.007 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_FLOYD_DITHER/512
|
-1.71% |
4884.924 |
4801.338 |
6.977 |
0.06% |
6.977 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_VOL3D_CALC_LAMBDA/2
|
-1.63% |
6.882 |
6.770 |
0.002 |
-0.01% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_nested_cond_load_autovec_uint8_t_
|
-1.59% |
709532.653 |
698215.647 |
1291.284 |
-0.17% |
1291.284 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint32_t>/28
|
-1.57% |
45.745 |
45.029 |
0.000 |
-0.00% |
0.000 |
|
SingleSource/Benchmarks/Misc/ReedSolomon
Profile
|
-1.56% |
9.492 |
9.344 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC2
|
-1.52% |
19.337 |
19.044 |
0.010 |
-0.02% |
0.010 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopTC2
|
-1.44% |
19.340 |
19.061 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint32_t>/16
|
-1.43% |
50.032 |
49.316 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC2
|
-1.39% |
19.341 |
19.072 |
0.022 |
-0.01% |
0.022 |
|
External/SPEC/CINT2017rate/523.xalancbmk_r/523.xalancbmk_r
Profile
|
-1.39% |
154.799 |
152.653 |
0.313 |
-0.02% |
0.313 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_VOL3D_CALC_RAW/0
|
-1.38% |
903.853 |
891.350 |
1.435 |
0.02% |
1.435 |
|
SingleSource/Benchmarks/Adobe-C++/stepanov_vector
Profile
|
-1.37% |
5.797 |
5.718 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint32_t_To_uint64_t_
|
-1.32% |
22488.316 |
22192.375 |
27.143 |
-0.03% |
27.143 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<63, EqZero, None>
|
-1.31% |
3047.028 |
3006.998 |
1.245 |
-0.03% |
1.245 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint32_t_To_uint64_t_
|
-1.28% |
22490.855 |
22202.042 |
18.386 |
-0.02% |
18.386 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<63, GreaterThanZero, None>
|
-1.27% |
3045.714 |
3007.134 |
1.369 |
-0.07% |
1.369 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint32_t_To_uint64_t_
|
-1.26% |
22494.073 |
22209.881 |
18.552 |
0.00% |
18.552 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC31
|
-1.26% |
276.089 |
272.620 |
0.020 |
-0.03% |
0.020 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopTC31
|
-1.25% |
276.096 |
272.657 |
0.033 |
-0.02% |
0.033 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC31
|
-1.24% |
276.078 |
272.648 |
0.035 |
-0.02% |
0.035 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint64_t>/28
|
-1.23% |
77.911 |
76.952 |
0.002 |
0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC3
|
-1.20% |
27.489 |
27.160 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopTC3
|
-1.20% |
27.489 |
27.160 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC3
|
-1.19% |
27.488 |
27.160 |
0.002 |
0.00% |
0.002 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_ENERGY_CALC_LAMBDA/171
|
-1.19% |
5.364 |
5.300 |
0.009 |
0.01% |
0.009 |
|
MultiSource/Benchmarks/Ptrdist/anagram/anagram
Profile
|
-1.14% |
1.869 |
1.848 |
0.006 |
-0.01% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint32_t>/256
|
-1.09% |
197.998 |
195.836 |
0.014 |
-0.00% |
0.014 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_VOL3D_CALC_LAMBDA/0
|
-1.08% |
902.295 |
892.550 |
0.182 |
0.00% |
0.182 |
|
MicroBenchmarks/Builtins/Int128/Builtins.test:BM_DivideIntrinsic128UniformDivisor<__uint128_t>
|
-1.01% |
88.778 |
87.885 |
0.046 |
-0.03% |
0.046 |