|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC15
|
-35.09% |
27.159 |
17.630 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopWithReductionTC31
|
-34.29% |
50.030 |
32.876 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopWithReductionTC32
|
-34.26% |
51.462 |
33.830 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC32
|
-34.26% |
51.461 |
33.831 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC64
|
-33.82% |
97.202 |
64.325 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint64_t_To_uint8_t_
|
-33.55% |
28596.993 |
19003.095 |
14.254 |
-0.03% |
14.254 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC63
|
-33.34% |
95.059 |
63.370 |
0.002 |
-0.01% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC16
|
-33.34% |
27.874 |
18.582 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC31
|
-33.33% |
49.315 |
32.876 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopWithReductionTC16
|
-33.33% |
27.875 |
18.583 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopWithReductionTC64
|
-33.33% |
96.486 |
64.324 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopWithReductionTC15
|
-33.33% |
26.444 |
17.630 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopWithReductionTC63
|
-33.33% |
95.056 |
63.372 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC3
|
-32.05% |
27.873 |
18.939 |
0.000 |
-0.01% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC2
|
-31.33% |
7.862 |
5.399 |
0.017 |
-0.37% |
0.017 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopWithReductionTC2
|
-31.07% |
7.862 |
5.420 |
0.023 |
-0.67% |
0.023 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC8
|
-30.43% |
16.438 |
11.436 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC7
|
-28.57% |
15.009 |
10.721 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopWithReductionTC7
|
-28.57% |
15.009 |
10.721 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopWithReductionTC8
|
-26.09% |
16.439 |
12.150 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC4
|
-25.00% |
11.436 |
8.576 |
0.000 |
-0.01% |
0.000 |
|
SingleSource/Benchmarks/Shootout-C++/Shootout-C++-ary3
Profile
|
-24.43% |
6.024 |
4.553 |
0.066 |
-0.81% |
0.066 |
|
SingleSource/Benchmarks/BenchmarkGame/puzzle
Profile
|
-23.68% |
1.120 |
0.855 |
0.001 |
0.02% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC2
|
-23.05% |
9.291 |
7.150 |
0.003 |
-0.00% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC128
|
-22.50% |
193.695 |
150.113 |
3.420 |
-4.54% |
3.420 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopWithReductionTC127
|
-22.15% |
192.253 |
149.661 |
0.083 |
-0.05% |
0.083 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_only_novec_int64_t_
|
-21.87% |
864430.693 |
675392.650 |
846.518 |
-0.14% |
846.518 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopWithReductionTC128
|
-21.82% |
192.978 |
150.863 |
2.574 |
-1.60% |
2.574 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint16_t>/999
|
-21.68% |
2169.116 |
1698.959 |
3.040 |
0.04% |
3.040 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint16_t>/999
|
-21.42% |
1100.685 |
864.883 |
1.984 |
0.09% |
1.984 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_nested_cond_load_novec_int64_t_
|
-21.12% |
1293628.466 |
1020476.608 |
754.167 |
-0.11% |
754.167 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint16_t>/256
|
-20.47% |
576.057 |
458.157 |
2.042 |
-0.16% |
2.042 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopWithReductionTC4
|
-20.00% |
10.721 |
8.577 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint16_t>/256
|
-19.67% |
305.186 |
245.154 |
0.770 |
-0.01% |
0.770 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint16_t>/51
|
-19.57% |
131.510 |
105.780 |
0.003 |
0.00% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint16_t>/51
|
-19.26% |
77.904 |
62.898 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint16_t>/28
|
-18.42% |
54.319 |
44.313 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint16_t>/28
|
-18.26% |
82.193 |
67.184 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC127
|
-18.21% |
192.260 |
157.246 |
1.003 |
0.00% |
1.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint16_t_To_uint64_t_
|
-16.65% |
14302.732 |
11921.283 |
6.101 |
-0.01% |
6.101 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint8_t_To_uint32_t_
|
-16.60% |
14301.896 |
11927.269 |
0.176 |
-0.01% |
0.176 |
|
SingleSource/Benchmarks/CoyoteBench/huffbench
Profile
|
-16.49% |
38.291 |
31.978 |
0.045 |
-0.17% |
0.045 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint16_t>/16
|
-16.45% |
56.464 |
47.173 |
0.001 |
-0.00% |
0.001 |
|
SingleSource/Benchmarks/Shootout/Shootout-sieve
Profile
|
-15.95% |
8.486 |
7.132 |
0.017 |
-0.67% |
0.017 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint16_t>/10
|
-14.75% |
43.597 |
37.166 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopWithReductionTC3
|
-14.29% |
10.006 |
8.576 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint16_t>/16
|
-13.79% |
41.456 |
35.737 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1LoopWithReductionTC64
|
-13.46% |
74.331 |
64.325 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_DIFF_PREDICT_RAW/171
|
-12.80% |
4.223 |
3.682 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_DIFF_PREDICT_LAMBDA/171
|
-12.61% |
4.213 |
3.682 |
0.008 |
0.04% |
0.008 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_csa_with_cond_arith_autovec_int64_t_
|
-12.13% |
781650.279 |
686868.369 |
143.101 |
0.01% |
143.101 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC1
|
-11.11% |
6.432 |
5.718 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC63
|
-11.00% |
138.653 |
123.406 |
0.004 |
-0.00% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC128
|
-10.75% |
285.885 |
255.148 |
0.006 |
0.00% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC64
|
-10.62% |
140.086 |
125.205 |
0.033 |
-0.01% |
0.033 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC127
|
-10.35% |
283.019 |
253.718 |
0.005 |
0.00% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC31
|
-10.20% |
69.328 |
62.255 |
0.177 |
-0.02% |
0.177 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC32
|
-10.00% |
71.471 |
64.323 |
0.002 |
0.00% |
0.002 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_DIFF_PREDICT_LAMBDA/5001
|
-9.81% |
206.558 |
186.303 |
7.628 |
-0.04% |
7.628 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_BAND_LIN_EQ_RAW/171
|
-9.54% |
0.247 |
0.224 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint64_t>/16
|
-9.23% |
46.457 |
42.168 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC3
|
-9.09% |
7.862 |
7.147 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_BAND_LIN_EQ_LAMBDA/171
|
-9.01% |
0.246 |
0.224 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint16_t>/10
|
-8.99% |
35.023 |
31.875 |
0.136 |
-0.90% |
0.136 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_with_cond_arith_autovec_int32_t_
|
-8.93% |
438130.818 |
399004.556 |
302.601 |
-0.01% |
302.601 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_cond_load_autovec_int32_t_
|
-8.89% |
598240.442 |
545085.271 |
3884.333 |
0.07% |
3884.333 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC15
|
-8.84% |
35.021 |
31.923 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_with_cond_arith_autovec_uint8_t_
|
-8.73% |
439029.486 |
400722.381 |
1203.041 |
-0.66% |
1203.041 |
|
SingleSource/Benchmarks/Shootout/Shootout-matrix
Profile
|
-8.52% |
4.822 |
4.411 |
0.019 |
-0.17% |
0.019 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC16
|
-8.31% |
37.165 |
34.077 |
0.048 |
-0.05% |
0.048 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchVecWithRuntimeChecks4PointersAllDisjointIncreasing/1000
|
-8.30% |
2868143.443 |
2630195.489 |
32.533 |
-0.01% |
32.533 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchVecWithRuntimeChecks4PointersAllDisjointDecreasing/1000
|
-8.30% |
2868217.213 |
2630281.955 |
14.066 |
-0.00% |
14.066 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchVecWithRuntimeChecks4PointersDEqualsA/1000
|
-8.30% |
2868139.344 |
2630214.286 |
29.602 |
0.00% |
29.602 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchVecWithRuntimeChecks4PointersDAfterA/1000
|
-8.30% |
2868135.246 |
2630221.805 |
42.643 |
-0.00% |
42.643 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchVecWithRuntimeChecks4PointersDBeforeA/1000
|
-8.28% |
2868344.262 |
2630800.752 |
15.752 |
0.00% |
15.752 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint64_t>/51
|
-8.27% |
95.063 |
87.197 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint64_t>/999
|
-8.22% |
2883.909 |
2646.737 |
2.717 |
-0.01% |
2.717 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint32_t>/999
|
-8.18% |
2883.199 |
2647.369 |
3.934 |
0.00% |
3.934 |
|
SingleSource/Benchmarks/Polybench/stencils/jacobi-2d/jacobi-2d
Profile
|
-8.13% |
52.793 |
48.500 |
0.599 |
-2.89% |
0.599 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint64_t>/999
|
-8.12% |
1461.657 |
1342.976 |
3.014 |
-0.01% |
3.014 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint32_t>/999
|
-8.03% |
1460.936 |
1343.680 |
0.018 |
-0.00% |
0.018 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<7, EqZero, First>
|
-8.00% |
10462.056 |
9624.940 |
7.231 |
0.00% |
7.231 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint64_t>/256
|
-8.00% |
759.755 |
699.001 |
0.006 |
-0.00% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC7
|
-7.97% |
17.868 |
16.443 |
0.222 |
-0.05% |
0.222 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC127
|
-7.94% |
152.953 |
140.801 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_nested_cond_load_novec_uint8_t_
|
-7.88% |
577357.023 |
531834.877 |
2041.370 |
-0.52% |
2041.370 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint64_t>/28
|
-7.87% |
63.613 |
58.608 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint32_t>/256
|
-7.72% |
759.063 |
700.450 |
1.391 |
-0.00% |
1.391 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC3
|
-7.69% |
9.291 |
8.577 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopWithReductionTC1
|
-7.63% |
5.079 |
4.692 |
0.044 |
0.12% |
0.044 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchVecWithRuntimeChecks4PointersDEqualsA/32
|
-7.58% |
94378.910 |
87227.165 |
2.892 |
-0.00% |
2.892 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchVecWithRuntimeChecks4PointersDAfterA/32
|
-7.57% |
94377.646 |
87229.120 |
1.426 |
-0.01% |
1.426 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchVecWithRuntimeChecks4PointersDBeforeA/32
|
-7.57% |
94378.185 |
87231.057 |
1.520 |
0.00% |
1.520 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchVecWithRuntimeChecks4PointersAllDisjointIncreasing/32
|
-7.57% |
94375.758 |
87230.903 |
0.244 |
-0.00% |
0.244 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchVecWithRuntimeChecks4PointersAllDisjointDecreasing/32
|
-7.57% |
94371.949 |
87229.283 |
2.764 |
-0.00% |
2.764 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, GreaterThanZero, Last>
|
-7.39% |
39528.349 |
36605.794 |
14.852 |
-0.00% |
14.852 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint64_t>/256
|
-7.31% |
400.969 |
371.645 |
0.015 |
-0.00% |
0.015 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC8
|
-7.15% |
20.013 |
18.582 |
0.000 |
-0.01% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint32_t>/256
|
-7.15% |
400.262 |
371.659 |
0.005 |
-0.00% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint64_t>/51
|
-6.90% |
165.821 |
154.380 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint32_t>/51
|
-6.87% |
166.533 |
155.098 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint16_t>/256
|
-6.85% |
228.663 |
212.994 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_only_novec_int32_t_
|
-6.77% |
607242.820 |
566108.086 |
6172.031 |
-0.08% |
6172.031 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC3
|
-6.67% |
10.721 |
10.006 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_nested_cond_load_autovec_uint8_t_
|
-6.65% |
579471.284 |
540920.125 |
633.153 |
0.24% |
633.153 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_INT_PREDICT_RAW/5001
|
-6.52% |
120.598 |
112.740 |
1.213 |
0.34% |
1.213 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint64_t>/28
|
-6.43% |
100.064 |
93.627 |
0.003 |
-0.00% |
0.003 |
|
MultiSource/Benchmarks/SciMark2-C/scimark2
Profile
|
-6.21% |
55.514 |
52.066 |
0.017 |
-0.01% |
0.017 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint64_t>/10
|
-6.07% |
23.587 |
22.156 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint64_t>/256
|
-6.06% |
23.586 |
22.156 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint64_t>/16
|
-6.06% |
23.586 |
22.156 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint64_t>/51
|
-6.06% |
23.586 |
22.156 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint32_t>/51
|
-6.06% |
94.346 |
88.627 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint64_t>/28
|
-6.06% |
23.586 |
22.157 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC1
|
-6.05% |
13.212 |
12.413 |
0.047 |
0.00% |
0.047 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint16_t>/127
|
-6.05% |
168.878 |
158.669 |
0.721 |
-0.62% |
0.721 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_PRESSURE_CALC_RAW/171
|
-6.02% |
1.317 |
1.238 |
0.000 |
0.00% |
0.000 |
|
SingleSource/Benchmarks/BenchmarkGame/n-body
Profile
|
-5.98% |
2.630 |
2.473 |
0.000 |
0.01% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_DIFF_PREDICT_LAMBDA/44217
|
-5.96% |
5396.977 |
5075.145 |
28.958 |
-0.37% |
28.958 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1LoopWithReductionTC8
|
-5.88% |
12.150 |
11.435 |
0.000 |
-0.01% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC4
|
-5.88% |
12.150 |
11.436 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<6, GreaterThanZero, Mid>
|
-5.87% |
16581.486 |
15608.642 |
9.572 |
-0.00% |
9.572 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<6, EqZero, Mid>
|
-5.87% |
16580.988 |
15608.435 |
9.732 |
-0.00% |
9.732 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_INT_PREDICT_LAMBDA/5001
|
-5.73% |
120.006 |
113.134 |
0.164 |
0.03% |
0.164 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint32_t>/28
|
-5.68% |
62.898 |
59.323 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint32_t>/28
|
-5.67% |
100.775 |
95.058 |
0.002 |
-0.01% |
0.002 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_DIFF_PREDICT_RAW/44217
|
-5.58% |
5380.287 |
5080.268 |
9.776 |
-0.26% |
9.776 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_INT_PREDICT_LAMBDA/44217
|
-5.56% |
3733.401 |
3525.727 |
7.746 |
-0.77% |
7.746 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint64_t>/16
|
-5.43% |
65.753 |
62.180 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/128
|
-5.41% |
2921.025 |
2762.913 |
8.773 |
-0.01% |
8.773 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint32_t>/16
|
-5.38% |
66.470 |
62.896 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1LoopWithReductionTC1
|
-5.27% |
4.989 |
4.727 |
0.036 |
-0.10% |
0.036 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_INT_PREDICT_RAW/44217
|
-5.25% |
3729.406 |
3533.505 |
11.819 |
-0.28% |
11.819 |
|
MultiSource/Benchmarks/Olden/tsp/tsp
Profile
|
-5.10% |
3.267 |
3.100 |
0.007 |
0.08% |
0.007 |
|
SingleSource/Benchmarks/McGill/queens
Profile
|
-4.93% |
3.395 |
3.227 |
0.000 |
-0.01% |
0.000 |
|
MultiSource/Benchmarks/ASC_Sequoia/AMGmk/AMGmk
Profile
|
-4.93% |
37.478 |
35.630 |
0.554 |
-3.73% |
0.554 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/64
|
-4.85% |
725.422 |
690.259 |
0.984 |
-0.01% |
0.984 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/32
|
-4.82% |
178.952 |
170.324 |
0.353 |
-0.21% |
0.353 |
|
MultiSource/Applications/obsequi/Obsequi
Profile
|
-4.76% |
4.425 |
4.214 |
0.008 |
0.09% |
0.008 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint32_t>/16
|
-4.69% |
45.744 |
43.599 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint16_t>/256
|
-4.54% |
414.800 |
395.972 |
0.006 |
-0.00% |
0.006 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_PIC_2D_LAMBDA/44217
|
-4.41% |
1599.448 |
1528.887 |
1.315 |
0.06% |
1.315 |
|
MicroBenchmarks/harris/harris.test:BENCHMARK_HARRIS/1024/1024
|
-4.33% |
55594.077 |
53188.462 |
110.788 |
-0.54% |
110.788 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<8, EqZero, First>
|
-4.15% |
8790.781 |
8426.086 |
9.410 |
0.00% |
9.410 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC128
|
-4.04% |
157.924 |
151.537 |
1.668 |
0.00% |
1.668 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC1
|
-4.04% |
5.053 |
4.849 |
0.048 |
-0.43% |
0.048 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/256
|
-4.01% |
11928.898 |
11451.000 |
18.211 |
0.31% |
18.211 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC7
|
-3.85% |
18.583 |
17.868 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint32_t>/10
|
-3.85% |
37.166 |
35.736 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<3, EqZero, Mid>
|
-3.84% |
25374.615 |
24400.544 |
42.172 |
-0.04% |
42.172 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint64_t>/10
|
-3.78% |
37.881 |
36.450 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_PIC_2D_RAW/44217
|
-3.55% |
1595.725 |
1539.140 |
4.830 |
0.43% |
4.830 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_csa_with_cond_arith_novec_uint8_t_
|
-3.54% |
282647.465 |
272631.148 |
1397.063 |
0.05% |
1397.063 |
|
SingleSource/Benchmarks/Misc/mandel
Profile
|
-3.54% |
1.328 |
1.281 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint8_t>/28
|
-3.51% |
40.740 |
39.310 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC1
|
-3.47% |
5.126 |
4.949 |
0.040 |
0.56% |
0.040 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC8
|
-3.45% |
20.727 |
20.012 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint64_t>/10
|
-3.39% |
42.170 |
40.739 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopTC1
|
-3.37% |
13.194 |
12.749 |
0.021 |
-0.11% |
0.021 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, GreaterThanZero, None>
|
-3.33% |
43919.752 |
42458.086 |
0.970 |
-0.00% |
0.970 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_HYDRO_1D_RAW/5001
|
-3.27% |
14.486 |
14.011 |
0.052 |
-0.52% |
0.052 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_single_load<uint16_t>/256
|
-3.23% |
22.157 |
21.442 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_single_load<uint16_t>/51
|
-3.23% |
22.157 |
21.441 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_single_load<uint16_t>/16
|
-3.23% |
22.157 |
21.441 |
0.000 |
-0.01% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_single_load<uint16_t>/28
|
-3.23% |
22.157 |
21.442 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_single_load<uint16_t>/999
|
-3.23% |
22.157 |
21.442 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_single_load<uint16_t>/10
|
-3.22% |
22.156 |
21.442 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<3, GreaterThanZero, Last>
|
-3.21% |
30249.341 |
29277.134 |
14.515 |
0.01% |
14.515 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<3, EqZero, None>
|
-3.12% |
31227.372 |
30251.588 |
0.799 |
-0.00% |
0.799 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<16, GreaterThanZero, First>
|
-3.11% |
5862.779 |
5680.629 |
1.320 |
-0.01% |
1.320 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<7, GreaterThanZero, Mid>
|
-3.03% |
13806.521 |
13388.025 |
0.407 |
-0.01% |
0.407 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, GreaterThanZero, Last>
|
-3.02% |
24161.668 |
23430.962 |
3.650 |
-0.00% |
3.650 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint64_t>/10
|
-2.94% |
48.602 |
47.173 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint32_t>/10
|
-2.90% |
49.317 |
47.886 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<8, EqZero, Mid>
|
-2.84% |
12815.877 |
12452.032 |
11.139 |
0.00% |
11.139 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<5, EqZero, None>
|
-2.78% |
21080.161 |
20495.052 |
0.544 |
-0.00% |
0.544 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint16_t>/999
|
-2.72% |
764.076 |
743.310 |
0.013 |
0.00% |
0.013 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC128
|
-2.69% |
157.948 |
153.700 |
1.191 |
-0.00% |
1.191 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC2
|
-2.65% |
5.575 |
5.428 |
0.004 |
0.03% |
0.004 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<6, GreaterThanZero, None>
|
-2.63% |
18530.760 |
18043.535 |
0.236 |
0.00% |
0.236 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_HYDRO_1D_LAMBDA/5001
|
-2.61% |
14.472 |
14.095 |
0.041 |
-0.39% |
0.041 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint64_t>/16
|
-2.60% |
55.035 |
53.605 |
0.001 |
-0.00% |
0.001 |
|
SingleSource/Benchmarks/BenchmarkGame/nsieve-bits
Profile
|
-2.54% |
1.582 |
1.542 |
0.016 |
-1.56% |
0.016 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1LoopWithReductionTC127
|
-2.53% |
155.456 |
151.520 |
0.003 |
-0.01% |
0.003 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/16
|
-2.50% |
43.729 |
42.635 |
0.063 |
0.00% |
0.063 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC7
|
-2.49% |
61.478 |
59.945 |
0.009 |
-0.01% |
0.009 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<7, LessThanZero, Last>
|
-2.48% |
16731.952 |
16316.462 |
2.280 |
-0.00% |
2.280 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC1
|
-2.48% |
5.050 |
4.925 |
0.007 |
0.00% |
0.007 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_csa_with_cond_arith_autovec_uint8_t_
|
-2.39% |
282587.327 |
275847.431 |
1696.002 |
-0.00% |
1696.002 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<8, GreaterThanZero, None>
|
-2.38% |
15377.543 |
15011.537 |
0.372 |
0.00% |
0.372 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_PIC_2D_RAW/5001
|
-2.36% |
178.775 |
174.554 |
0.894 |
-0.58% |
0.894 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint64_t>/16
|
-2.28% |
31.449 |
30.733 |
0.000 |
0.00% |
0.000 |
|
MultiSource/Benchmarks/Trimaran/enc-3des/enc-3des
Profile
|
-2.23% |
3.143 |
3.073 |
0.000 |
-0.03% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint8_t>/16
|
-2.22% |
32.163 |
31.448 |
0.001 |
-0.00% |
0.001 |
|
MultiSource/Benchmarks/TSVC/ControlLoops-flt/ControlLoops-flt
Profile
|
-2.19% |
8.365 |
8.181 |
0.031 |
-1.07% |
0.031 |
|
MicroBenchmarks/harris/harris.test:BENCHMARK_HARRIS/512/512
|
-2.12% |
14061.800 |
13763.863 |
84.393 |
-0.23% |
84.393 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint32_t>/127
|
-2.10% |
170.828 |
167.242 |
0.005 |
-0.01% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint64_t>/10
|
-2.08% |
34.307 |
33.592 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopTC7
|
-2.07% |
62.337 |
61.044 |
0.026 |
-0.10% |
0.026 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_with_cond_arith_autovec_int64_t_
|
-2.05% |
424913.803 |
416187.760 |
2459.434 |
-0.19% |
2459.434 |
|
SingleSource/Benchmarks/Polybench/stencils/seidel-2d/seidel-2d
Profile
|
-2.05% |
164.310 |
160.940 |
0.158 |
-0.04% |
0.158 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC15
|
-2.00% |
35.736 |
35.021 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC1
|
-1.98% |
13.160 |
12.899 |
0.003 |
-0.10% |
0.003 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C/CoMD/CoMD
Profile
|
-1.94% |
5.064 |
4.966 |
0.012 |
-0.09% |
0.012 |
|
SingleSource/Benchmarks/Misc/perlin
Profile
|
-1.90% |
7.274 |
7.136 |
0.000 |
-0.01% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC16
|
-1.89% |
37.880 |
37.164 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint8_t>/10
|
-1.89% |
37.880 |
37.165 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC16
|
-1.89% |
37.880 |
37.165 |
0.002 |
-0.00% |
0.002 |
|
MultiSource/Benchmarks/Fhourstones-3.1/fhourstones3.1
Profile
|
-1.86% |
2.471 |
2.425 |
0.004 |
0.01% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_csa_with_in_loop_arith_novec_int64_t_
|
-1.80% |
930777.036 |
914003.916 |
4593.277 |
-0.07% |
4593.277 |
|
SingleSource/Benchmarks/CoyoteBench/lpbench
Profile
|
-1.80% |
7.740 |
7.600 |
0.008 |
-0.05% |
0.008 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint64_t>/28
|
-1.79% |
40.025 |
39.310 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint64_t>/28
|
-1.77% |
80.764 |
79.334 |
0.002 |
0.00% |
0.002 |
|
SingleSource/Benchmarks/Misc/flops-8
Profile
|
-1.73% |
1.768 |
1.738 |
0.000 |
-0.01% |
0.000 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C/Pathfinder/PathFinder
Profile
|
-1.73% |
7.177 |
7.053 |
0.004 |
-2.27% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_csa_with_cond_arith_autovec_int32_t_
|
-1.68% |
551106.750 |
541873.307 |
3210.864 |
-0.18% |
3210.864 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint64_t>/16
|
-1.66% |
42.883 |
42.170 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint8_t>/16
|
-1.59% |
45.028 |
44.313 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_PIC_2D_LAMBDA/5001
|
-1.59% |
178.893 |
176.056 |
0.112 |
-0.09% |
0.112 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint64_t>/51
|
-1.53% |
93.630 |
92.200 |
0.001 |
-0.00% |
0.001 |
|
MultiSource/Applications/siod/siod
Profile
|
-1.49% |
5.461 |
5.380 |
0.021 |
-0.63% |
0.021 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_csa_with_cond_arith_novec_int32_t_
|
-1.41% |
543062.693 |
535383.963 |
2128.018 |
-0.10% |
2128.018 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint16_t>/999
|
-1.35% |
1478.076 |
1458.099 |
0.014 |
-0.00% |
0.014 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint64_t>/51
|
-1.28% |
55.750 |
55.035 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_only_novec_uint8_t_
|
-1.22% |
336079.342 |
331983.349 |
310.152 |
-0.20% |
310.152 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint64_t>/28
|
-1.19% |
60.038 |
59.323 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_GEN_LIN_RECUR_RAW/44217
|
-1.14% |
511.928 |
506.111 |
0.066 |
-0.00% |
0.066 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC63
|
-1.12% |
305.755 |
302.344 |
0.005 |
0.00% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint8_t>/51
|
-1.11% |
64.327 |
63.612 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint64_t>/51
|
-1.10% |
130.082 |
128.651 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC31
|
-1.02% |
70.041 |
69.326 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC64
|
-1.01% |
141.514 |
140.083 |
0.003 |
-0.00% |
0.003 |