|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC7
|
-46.15% |
18.583 |
10.006 |
0.000 |
-6.67% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC8
|
-37.50% |
17.154 |
10.721 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopWithReductionTC8
|
-37.50% |
17.153 |
10.721 |
0.000 |
-6.25% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC15
|
-36.84% |
27.159 |
17.153 |
0.000 |
-0.01% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC16
|
-36.67% |
28.590 |
18.106 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC16
|
-36.67% |
28.589 |
18.106 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC7
|
-36.36% |
15.723 |
10.006 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC2
|
-35.81% |
8.577 |
5.505 |
0.004 |
0.45% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1LoopWithReductionTC31
|
-35.19% |
50.030 |
32.423 |
0.003 |
-0.01% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopWithReductionTC31
|
-35.19% |
50.028 |
32.425 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC15
|
-35.14% |
26.446 |
17.153 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1LoopWithReductionTC15
|
-35.14% |
26.445 |
17.154 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC15
|
-35.14% |
26.445 |
17.153 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopWithReductionTC15
|
-35.13% |
26.445 |
17.154 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC15
|
-35.13% |
26.444 |
17.153 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC15
|
-35.13% |
26.444 |
17.154 |
0.000 |
-0.01% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC16
|
-35.05% |
27.875 |
18.106 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1LoopWithReductionTC16
|
-35.04% |
27.874 |
18.106 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC16
|
-35.04% |
27.874 |
18.106 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC16
|
-35.04% |
27.875 |
18.107 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopWithReductionTC16
|
-35.04% |
27.874 |
18.106 |
0.000 |
-0.01% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC8
|
-34.78% |
16.439 |
10.721 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1LoopWithReductionTC8
|
-34.78% |
16.439 |
10.721 |
0.000 |
-6.26% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC8
|
-34.78% |
16.439 |
10.721 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC63
|
-34.33% |
95.775 |
62.894 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC63
|
-34.33% |
95.775 |
62.896 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1LoopWithReductionTC63
|
-34.33% |
95.773 |
62.894 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC63
|
-34.33% |
95.775 |
62.896 |
0.000 |
-0.01% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopWithReductionTC63
|
-34.33% |
95.772 |
62.894 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC63
|
-34.33% |
95.773 |
62.895 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC63
|
-34.33% |
95.772 |
62.896 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1LoopWithReductionTC32
|
-34.27% |
50.747 |
33.354 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC32
|
-34.27% |
50.747 |
33.354 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopWithReductionTC32
|
-34.27% |
50.746 |
33.354 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC32
|
-34.27% |
50.747 |
33.355 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC32
|
-34.27% |
50.747 |
33.355 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC32
|
-34.27% |
50.745 |
33.355 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC32
|
-34.27% |
50.745 |
33.355 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC31
|
-34.26% |
49.316 |
32.422 |
0.004 |
-0.01% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC31
|
-34.26% |
49.317 |
32.423 |
0.005 |
-0.01% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC31
|
-34.25% |
49.316 |
32.425 |
2.487 |
-0.01% |
2.487 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC31
|
-34.25% |
49.317 |
32.425 |
0.003 |
0.01% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC31
|
-34.25% |
49.316 |
32.425 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC64
|
-33.83% |
96.490 |
63.848 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC64
|
-33.83% |
96.490 |
63.850 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC64
|
-33.83% |
96.490 |
63.850 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC64
|
-33.83% |
96.489 |
63.850 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC64
|
-33.83% |
96.488 |
63.850 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopWithReductionTC64
|
-33.83% |
96.489 |
63.850 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1LoopWithReductionTC64
|
-33.83% |
96.487 |
63.850 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC7
|
-33.33% |
15.010 |
10.006 |
0.000 |
-6.66% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC7
|
-33.33% |
15.009 |
10.006 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopWithReductionTC7
|
-33.33% |
15.009 |
10.006 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1LoopWithReductionTC4
|
-31.25% |
11.436 |
7.862 |
0.000 |
-0.01% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC4
|
-31.25% |
11.436 |
7.862 |
0.000 |
-8.34% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopWithReductionTC2
|
-31.09% |
7.862 |
5.418 |
0.028 |
0.29% |
0.028 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC2
|
-31.04% |
7.862 |
5.422 |
0.038 |
0.14% |
0.038 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC2
|
-30.75% |
7.862 |
5.444 |
0.030 |
1.59% |
0.030 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC2
|
-30.51% |
7.862 |
5.463 |
0.032 |
1.02% |
0.032 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1LoopWithReductionTC2
|
-30.44% |
7.862 |
5.469 |
0.020 |
0.75% |
0.020 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC8
|
-30.44% |
16.439 |
11.436 |
0.000 |
6.65% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC8
|
-30.43% |
16.439 |
11.436 |
0.000 |
6.66% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC2
|
-30.04% |
7.862 |
5.500 |
0.025 |
-0.15% |
0.025 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC3
|
-28.57% |
10.006 |
7.147 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1LoopWithReductionTC7
|
-28.57% |
15.009 |
10.721 |
0.000 |
7.13% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC3
|
-28.57% |
10.006 |
7.147 |
0.000 |
-9.09% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC7
|
-28.57% |
15.009 |
10.721 |
0.000 |
7.13% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint8_t>/16
|
-26.90% |
40.740 |
29.780 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC4
|
-26.67% |
10.721 |
7.862 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC4
|
-26.67% |
10.721 |
7.862 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopWithReductionTC4
|
-26.66% |
10.721 |
7.862 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint8_t>/16
|
-26.47% |
24.300 |
17.868 |
0.000 |
-3.86% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint8_t>/28
|
-26.28% |
37.165 |
27.397 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint8_t>/10
|
-25.64% |
27.875 |
20.727 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint8_t>/28
|
-25.09% |
66.470 |
49.793 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint8_t>/51
|
-24.71% |
60.751 |
45.742 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint8_t>/10
|
-24.00% |
17.868 |
13.580 |
0.000 |
-5.01% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint8_t>/51
|
-23.87% |
115.790 |
88.148 |
0.003 |
-0.01% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopWithReductionTC3
|
-23.08% |
9.292 |
7.147 |
0.000 |
-9.09% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1LoopWithReductionTC3
|
-23.08% |
9.292 |
7.147 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC3
|
-23.08% |
9.291 |
7.147 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC3
|
-23.08% |
9.291 |
7.147 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint16_t_To_uint64_t_
|
-21.92% |
28596.928 |
22328.580 |
8.246 |
-0.05% |
8.246 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint16_t_To_uint64_t_
|
-21.91% |
28596.495 |
22330.492 |
0.582 |
-0.03% |
0.582 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint16_t_To_uint64_t_
|
-21.91% |
28597.165 |
22332.014 |
7.276 |
-0.06% |
7.276 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint8_t>/999
|
-21.63% |
2154.948 |
1688.896 |
0.033 |
0.63% |
0.033 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_nested_cond_load_autovec_int32_t_
|
-21.40% |
1134490.260 |
891686.224 |
1561.450 |
3.96% |
1561.450 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_nested_cond_load_novec_int32_t_
|
-21.37% |
1134547.812 |
892045.045 |
1709.604 |
4.06% |
1709.604 |
|
MultiSource/Benchmarks/Prolangs-C/gnugo/gnugo
Profile
|
-21.17% |
0.091 |
0.071 |
0.000 |
-20.71% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint8_t>/999
|
-20.31% |
1086.364 |
865.705 |
1.652 |
0.22% |
1.652 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC4
|
-20.01% |
10.721 |
8.576 |
0.000 |
9.08% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC4
|
-20.00% |
10.721 |
8.577 |
0.000 |
9.08% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint8_t>/256
|
-19.85% |
561.778 |
450.285 |
0.006 |
2.43% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1LoopWithReductionTC128
|
-19.63% |
192.975 |
155.092 |
0.024 |
-2.24% |
0.024 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC128
|
-19.63% |
192.975 |
155.095 |
0.013 |
-2.24% |
0.013 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC128
|
-19.62% |
192.978 |
155.109 |
0.034 |
-2.23% |
0.034 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC128
|
-19.62% |
192.973 |
155.105 |
0.017 |
-2.23% |
0.017 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopWithReductionTC128
|
-19.62% |
192.974 |
155.106 |
0.016 |
-2.24% |
0.016 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC128
|
-19.62% |
192.975 |
155.109 |
0.011 |
-2.23% |
0.011 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC128
|
-19.61% |
192.974 |
155.137 |
0.032 |
-2.21% |
0.032 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC127
|
-18.29% |
191.549 |
156.521 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC127
|
-18.29% |
191.550 |
156.522 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC127
|
-18.29% |
191.550 |
156.524 |
0.003 |
0.00% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC127
|
-18.28% |
191.546 |
156.523 |
0.000 |
-0.01% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC127
|
-18.28% |
191.544 |
156.523 |
0.041 |
-0.01% |
0.041 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1LoopWithReductionTC127
|
-18.28% |
191.542 |
156.522 |
0.003 |
-0.01% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopWithReductionTC127
|
-18.28% |
191.544 |
156.526 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint32_t_To_uint8_t_
|
-16.97% |
21449.592 |
17809.251 |
8.917 |
-16.98% |
8.917 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint32_t_To_uint8_t_
|
-16.92% |
21449.891 |
17819.992 |
5.564 |
-16.93% |
5.564 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint32_t_To_uint8_t_
|
-16.92% |
21449.698 |
17820.265 |
4.003 |
-16.93% |
4.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint8_t>/256
|
-16.20% |
290.895 |
243.762 |
1.297 |
-0.35% |
1.297 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC3
|
-15.38% |
9.291 |
7.862 |
0.000 |
9.99% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_two_loads<uint8_t>/51
|
-14.29% |
5.003 |
4.288 |
0.000 |
-14.29% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_two_loads<uint8_t>/999
|
-14.28% |
5.003 |
4.288 |
0.000 |
-14.29% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_two_loads<uint8_t>/10
|
-14.28% |
5.003 |
4.288 |
0.000 |
-14.29% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_two_loads<uint8_t>/16
|
-14.28% |
5.003 |
4.288 |
0.000 |
-14.29% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_two_loads<uint8_t>/256
|
-14.28% |
5.003 |
4.288 |
0.000 |
-14.29% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_two_loads<uint8_t>/28
|
-14.28% |
5.003 |
4.288 |
0.000 |
-14.29% |
0.000 |
|
MultiSource/Benchmarks/VersaBench/8b10b/8b10b
Profile
|
-14.26% |
11.424 |
9.795 |
0.008 |
-14.21% |
0.008 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC1
|
-12.50% |
5.718 |
5.003 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC2
|
-9.09% |
7.862 |
7.147 |
0.000 |
3.44% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC2
|
-9.09% |
7.862 |
7.148 |
0.000 |
3.45% |
0.000 |
|
SingleSource/Benchmarks/Linpack/linpack-pc
Profile
|
-8.56% |
10.180 |
9.309 |
0.003 |
-7.85% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint16_t>/999
|
-8.28% |
2867.394 |
2630.109 |
0.031 |
-0.01% |
0.031 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint16_t>/256
|
-8.18% |
744.048 |
683.193 |
0.035 |
0.00% |
0.035 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint16_t>/999
|
-8.08% |
1443.026 |
1326.497 |
0.027 |
-0.01% |
0.027 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint16_t>/51
|
-7.70% |
148.668 |
137.225 |
0.002 |
-0.01% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint16_t>/256
|
-7.29% |
382.390 |
354.501 |
0.006 |
0.18% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint16_t>/28
|
-7.19% |
82.910 |
76.951 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_only_novec_int32_t_
|
-6.74% |
560306.090 |
522561.521 |
3925.057 |
-6.97% |
3925.057 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_single_load<uint64_t>/51
|
-6.67% |
3.574 |
3.335 |
0.000 |
-0.01% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_single_load<uint64_t>/256
|
-6.67% |
3.574 |
3.335 |
0.000 |
-0.01% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_single_load<uint64_t>/10
|
-6.67% |
3.574 |
3.335 |
0.000 |
-0.01% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_single_load<uint64_t>/16
|
-6.67% |
3.574 |
3.335 |
0.000 |
-0.01% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_single_load<uint64_t>/999
|
-6.67% |
3.574 |
3.335 |
0.000 |
-0.01% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_single_load<uint16_t>/999
|
-6.67% |
3.574 |
3.335 |
0.000 |
-6.66% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_single_load<uint64_t>/28
|
-6.67% |
3.574 |
3.335 |
0.000 |
-0.01% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_single_load<uint16_t>/51
|
-6.67% |
3.574 |
3.335 |
0.000 |
-6.67% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_single_load<uint16_t>/28
|
-6.67% |
3.574 |
3.335 |
0.000 |
-6.67% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_single_load<uint16_t>/10
|
-6.67% |
3.574 |
3.335 |
0.000 |
-6.67% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_single_load<uint16_t>/256
|
-6.67% |
3.574 |
3.335 |
0.000 |
-6.67% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_single_load<uint16_t>/16
|
-6.67% |
3.574 |
3.335 |
0.000 |
-6.67% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint16_t>/16
|
-6.38% |
48.603 |
45.504 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint16_t>/51
|
-6.29% |
75.763 |
70.995 |
0.002 |
-0.01% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_only_autovec_int32_t_
|
-6.26% |
560070.513 |
525007.463 |
1725.193 |
-6.52% |
1725.193 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_csa_with_in_loop_arith_novec_int32_t_
|
-5.98% |
362517.617 |
340853.314 |
380.066 |
-0.16% |
380.066 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_csa_with_in_loop_arith_autovec_int32_t_
|
-5.91% |
362487.830 |
341074.489 |
307.336 |
0.01% |
307.336 |
|
MultiSource/Benchmarks/Ptrdist/yacr2/yacr2
Profile
|
-5.46% |
1.313 |
1.241 |
0.000 |
-5.49% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint16_t>/10
|
-5.31% |
31.449 |
29.779 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint16_t>/28
|
-4.84% |
44.314 |
42.168 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint64_t>/10
|
-4.76% |
15.010 |
14.294 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint64_t>/256
|
-4.17% |
5.718 |
5.479 |
0.000 |
-4.18% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint64_t>/999
|
-4.17% |
5.718 |
5.480 |
0.000 |
-4.17% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint64_t>/28
|
-4.17% |
5.718 |
5.480 |
0.000 |
-4.17% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint64_t>/16
|
-4.17% |
5.718 |
5.480 |
0.000 |
-4.17% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint64_t>/10
|
-4.17% |
5.718 |
5.480 |
0.000 |
-4.17% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint64_t>/51
|
-4.17% |
5.718 |
5.480 |
0.000 |
-4.17% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_only_autovec_uint8_t_
|
-4.00% |
639476.712 |
613868.421 |
27.914 |
30.67% |
27.914 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_only_novec_uint8_t_
|
-4.00% |
639508.676 |
613934.211 |
29.522 |
30.67% |
29.522 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint32_t>/256
|
-3.86% |
203.699 |
195.839 |
0.022 |
-1.09% |
0.022 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint64_t>/16
|
-3.34% |
21.442 |
20.727 |
0.001 |
-0.00% |
0.001 |
|
MultiSource/Applications/aha/aha
Profile
|
-2.94% |
3.756 |
3.645 |
0.001 |
-2.93% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint16_t>/16
|
-2.64% |
27.160 |
26.445 |
0.001 |
-0.01% |
0.001 |
|
External/SPEC/CFP2017rate/526.blender_r/526.blender_r
Profile
|
-2.13% |
390.908 |
382.571 |
0.291 |
-0.96% |
0.291 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint64_t>/28
|
-2.09% |
34.308 |
33.592 |
0.001 |
-0.00% |
0.001 |
|
MultiSource/Benchmarks/MallocBench/espresso/espresso
Profile
|
-1.94% |
0.847 |
0.830 |
0.001 |
-2.98% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC16
|
-1.88% |
37.880 |
37.166 |
0.000 |
1.95% |
0.000 |
|
MultiSource/Benchmarks/Ptrdist/anagram/anagram
Profile
|
-1.87% |
1.882 |
1.847 |
0.001 |
-1.21% |
0.001 |
|
External/SPEC/CFP2017rate/511.povray_r/511.povray_r
Profile
|
-1.65% |
14.453 |
14.214 |
0.066 |
-2.35% |
0.066 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint64_t>/256
|
-1.44% |
199.425 |
196.550 |
0.006 |
-0.73% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint32_t_To_uint64_t_
|
-1.31% |
22485.531 |
22190.079 |
10.634 |
-1.33% |
10.634 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint32_t_To_uint64_t_
|
-1.28% |
22485.939 |
22198.077 |
9.711 |
-1.30% |
9.711 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint64_t>/51
|
-1.24% |
57.895 |
57.178 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint32_t_To_uint64_t_
|
-1.24% |
22478.204 |
22200.254 |
12.867 |
-1.31% |
12.867 |
|
SingleSource/Benchmarks/Polybench/stencils/adi/adi
Profile
|
-1.20% |
61.310 |
60.572 |
0.068 |
-1.13% |
0.068 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC1
|
-1.12% |
14.123 |
13.965 |
0.016 |
15.47% |
0.016 |
|
MultiSource/Benchmarks/mafft/pairlocalalign
Profile
|
-1.11% |
47.569 |
47.039 |
0.011 |
-3.27% |
0.011 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint32_t>/999
|
-1.07% |
734.040 |
726.159 |
0.009 |
-0.29% |
0.009 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC31
|
-1.02% |
70.042 |
69.329 |
0.001 |
1.03% |
0.001 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/32
|
-1.00% |
172.060 |
170.332 |
0.016 |
0.00% |
0.016 |