|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_INT_PREDICT_LAMBDA/44217
|
-58.88% |
19353.908 |
7958.615 |
112.160 |
-4.55% |
112.160 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint64_t_To_uint32_t_
|
-51.98% |
35243.705 |
16924.701 |
97.322 |
-52.07% |
97.322 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_HYDRO_2D_LAMBDA/5001
|
-51.79% |
7866.279 |
3792.420 |
1369.217 |
-58.39% |
1369.217 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_HYDRO_2D_LAMBDA/44217
|
-51.37% |
69087.279 |
33595.772 |
13585.381 |
-63.05% |
13585.381 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint64_t_To_uint16_t_
|
-51.26% |
35645.677 |
17372.024 |
134.201 |
-51.31% |
134.201 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C/miniGMG/miniGMG
Profile
|
-51.24% |
9.247 |
4.509 |
0.077 |
-50.94% |
0.077 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint64_t_To_uint8_t_
|
-49.74% |
37134.490 |
18664.497 |
13.686 |
-49.64% |
13.686 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_DIFF_PREDICT_LAMBDA/44217
|
-44.33% |
24245.553 |
13497.103 |
321.017 |
-41.58% |
321.017 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint16_t_To_uint64_t_
|
-44.02% |
18654.697 |
10443.109 |
4.904 |
-44.08% |
4.904 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIRST_DIFF_LAMBDA/44217
|
-42.05% |
178.039 |
103.165 |
0.154 |
-28.76% |
0.154 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_DIFF_PREDICT_RAW/44217
|
-41.48% |
23073.803 |
13503.554 |
315.584 |
-42.04% |
315.584 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint8_t_To_uint64_t_
|
-41.05% |
17829.710 |
10510.631 |
10.817 |
-40.95% |
10.817 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_DIFF_PREDICT_LAMBDA/5001
|
-40.98% |
2569.563 |
1516.579 |
25.576 |
-39.56% |
25.576 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_DIFF_PREDICT_RAW/5001
|
-40.95% |
2564.906 |
1514.510 |
22.449 |
-41.18% |
22.449 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint64_t_To_uint32_t_
|
-40.78% |
38206.696 |
22625.975 |
21.204 |
-40.70% |
21.204 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_INT_PREDICT_LAMBDA/5001
|
-38.33% |
1479.169 |
912.208 |
1.812 |
0.82% |
1.812 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/64
|
-36.67% |
6181.725 |
3914.750 |
2.037 |
-36.68% |
2.037 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/32
|
-36.66% |
1396.277 |
884.427 |
0.044 |
-36.65% |
0.044 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/16
|
-36.55% |
279.504 |
177.359 |
0.014 |
-36.54% |
0.014 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/256
|
-36.22% |
107138.601 |
68337.800 |
74.925 |
-36.22% |
74.925 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/128
|
-36.07% |
26265.330 |
16791.136 |
7.416 |
-36.09% |
7.416 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint32_t_To_uint64_t_
|
-35.79% |
22612.999 |
14520.020 |
855.165 |
-36.11% |
855.165 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint64_t_To_uint8_t_
|
-34.23% |
30069.957 |
19775.829 |
16.782 |
-34.32% |
16.782 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint64_t_To_uint16_t_
|
-33.95% |
28956.872 |
19125.098 |
16.500 |
-33.94% |
16.500 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIRST_DIFF_RAW/44217
|
-30.88% |
148.068 |
102.347 |
0.764 |
-28.17% |
0.764 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint64_t_To_uint16_t_
|
-28.59% |
25912.165 |
18503.930 |
46.991 |
-28.55% |
46.991 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC128
|
-28.18% |
1296.294 |
931.031 |
6.701 |
-27.98% |
6.701 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint32_t_To_uint8_t_
|
-27.90% |
13467.326 |
9709.553 |
39.635 |
-27.91% |
39.635 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_PIC_2D_LAMBDA/44217
|
-27.82% |
11917.027 |
8601.887 |
598.439 |
-21.54% |
598.439 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC64
|
-27.42% |
655.515 |
475.773 |
3.445 |
-27.21% |
3.445 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC32
|
-27.16% |
334.936 |
243.956 |
1.574 |
-26.94% |
1.574 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC128
|
-26.91% |
555.768 |
406.218 |
0.032 |
-27.14% |
0.032 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC16
|
-26.52% |
174.176 |
127.982 |
0.516 |
-26.36% |
0.516 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC64
|
-25.91% |
291.403 |
215.890 |
0.181 |
-26.02% |
0.181 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint8_t>/51
|
-25.84% |
123.895 |
91.883 |
0.008 |
-0.66% |
0.008 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint64_t_To_uint8_t_
|
-24.84% |
27191.402 |
20436.409 |
41.080 |
-24.93% |
41.080 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC32
|
-23.93% |
158.751 |
120.762 |
0.010 |
-23.99% |
0.010 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC128
|
-23.33% |
604.017 |
463.126 |
0.056 |
-23.32% |
0.056 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC128
|
-23.32% |
603.982 |
463.159 |
0.017 |
-23.31% |
0.017 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_PIC_2D_LAMBDA/5001
|
-23.21% |
1180.961 |
906.917 |
36.404 |
-17.96% |
36.404 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIRST_SUM_LAMBDA/44217
|
-22.99% |
177.165 |
136.438 |
0.333 |
-18.34% |
0.333 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC64
|
-22.56% |
313.519 |
242.793 |
0.012 |
-22.56% |
0.012 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC64
|
-22.56% |
313.510 |
242.795 |
0.007 |
-22.55% |
0.007 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint16_t_To_uint64_t_
|
-22.39% |
13355.555 |
10364.817 |
0.784 |
-21.53% |
0.784 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC127
|
-21.97% |
615.209 |
480.045 |
0.013 |
-21.97% |
0.013 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC127
|
-21.96% |
615.166 |
480.051 |
0.017 |
-21.97% |
0.017 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint8_t_To_uint32_t_
|
-21.67% |
6583.359 |
5156.945 |
6.233 |
-21.65% |
6.233 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint16_t_To_uint32_t_
|
-21.59% |
7108.965 |
5573.840 |
1.238 |
-21.51% |
1.238 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_only_autovec_uint8_t_
|
-21.35% |
182337.361 |
143399.389 |
52.530 |
-21.36% |
52.530 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC32
|
-21.20% |
168.336 |
132.643 |
0.011 |
-21.20% |
0.011 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC32
|
-21.19% |
168.321 |
132.648 |
0.010 |
-21.20% |
0.010 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC16
|
-20.64% |
92.260 |
73.213 |
0.005 |
-20.66% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC128
|
-20.36% |
274.047 |
218.240 |
1.312 |
-20.57% |
1.312 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC127
|
-20.29% |
274.682 |
218.953 |
0.525 |
-20.51% |
0.525 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint8_t>/51
|
-20.29% |
191.513 |
152.662 |
0.004 |
-1.13% |
0.004 |
|
MultiSource/Benchmarks/Trimaran/enc-pc1/enc-pc1
Profile
|
-20.12% |
1.105 |
0.882 |
0.000 |
-20.10% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC63
|
-20.05% |
324.789 |
259.684 |
0.011 |
-20.04% |
0.011 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC63
|
-20.04% |
324.778 |
259.680 |
0.011 |
-20.05% |
0.011 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC127
|
-19.67% |
640.903 |
514.823 |
0.229 |
-19.62% |
0.229 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint32_t_To_uint8_t_
|
-19.25% |
13890.049 |
11215.997 |
91.588 |
-19.31% |
91.588 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC64
|
-19.18% |
150.475 |
121.607 |
2.052 |
-18.18% |
2.052 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint16_t_To_uint8_t_
|
-19.09% |
3817.029 |
3088.474 |
0.232 |
-19.11% |
0.232 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC16
|
-18.96% |
95.742 |
77.587 |
0.005 |
-18.96% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC16
|
-18.96% |
95.739 |
77.586 |
0.004 |
-18.96% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint8_t>/28
|
-18.94% |
82.594 |
66.951 |
0.002 |
-0.93% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC63
|
-18.84% |
150.983 |
122.542 |
2.900 |
-18.26% |
2.900 |
|
SingleSource/Benchmarks/Adobe-C++/loop_unroll
Profile
|
-18.78% |
2.982 |
2.422 |
0.002 |
-22.04% |
0.002 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, EqZero, None>
|
-18.75% |
20511.267 |
16665.852 |
0.686 |
-18.75% |
0.686 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint32_t_To_uint16_t_
|
-18.74% |
10333.372 |
8396.638 |
559.781 |
-15.23% |
559.781 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint32_t_To_uint16_t_
|
-18.66% |
13804.338 |
11228.848 |
8.145 |
-18.67% |
8.145 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint64_t_To_uint32_t_
|
-18.61% |
27094.581 |
22051.970 |
22.431 |
-18.48% |
22.431 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC8
|
-18.57% |
58.784 |
47.869 |
0.002 |
-18.54% |
0.002 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIRST_SUM_RAW/44217
|
-18.43% |
166.345 |
135.680 |
0.602 |
-18.43% |
0.602 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC16
|
-18.25% |
92.978 |
76.006 |
0.026 |
-18.38% |
0.026 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, EqZero, Last>
|
-18.16% |
14101.451 |
11540.635 |
0.102 |
-18.18% |
0.102 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC32
|
-17.90% |
160.888 |
132.097 |
0.113 |
-18.15% |
0.113 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC4
|
-17.87% |
17.521 |
14.390 |
0.031 |
-17.87% |
0.031 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_with_cond_arith_novec_uint8_t_
|
-17.87% |
745777.863 |
612537.647 |
112.079 |
-17.86% |
112.079 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC128
|
-17.65% |
570.726 |
469.993 |
0.285 |
-17.63% |
0.285 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC8
|
-17.63% |
23.152 |
19.070 |
0.097 |
-17.64% |
0.097 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC64
|
-17.63% |
297.364 |
244.945 |
0.031 |
-17.72% |
0.031 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_with_cond_arith_novec_int32_t_
|
-17.51% |
740166.178 |
610589.930 |
1517.739 |
-17.51% |
1517.739 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint8_t>/28
|
-17.40% |
122.003 |
100.775 |
0.035 |
-2.11% |
0.035 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC31
|
-16.73% |
179.591 |
149.549 |
0.003 |
-16.73% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC31
|
-16.72% |
179.580 |
149.550 |
0.016 |
-16.72% |
0.016 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC32
|
-16.46% |
87.040 |
72.709 |
1.692 |
-14.79% |
1.692 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_HYDRO_1D_RAW/171
|
-16.21% |
0.444 |
0.372 |
0.000 |
-15.84% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_HYDRO_1D_LAMBDA/171
|
-15.98% |
0.442 |
0.372 |
0.000 |
-15.87% |
0.000 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, EqZero, None>
|
-15.89% |
16024.399 |
13477.442 |
13.643 |
-15.89% |
13.643 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC8
|
-15.80% |
59.446 |
50.054 |
0.003 |
-15.80% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC8
|
-15.79% |
23.778 |
20.022 |
0.001 |
-15.80% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC8
|
-15.79% |
59.443 |
50.060 |
0.001 |
-15.80% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint16_t_To_uint32_t_
|
-15.67% |
7462.940 |
6293.361 |
0.689 |
-15.66% |
0.689 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint8_t_To_uint64_t_
|
-15.66% |
12926.911 |
10902.790 |
33.328 |
-16.55% |
33.328 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint64_t_To_uint8_t_
|
-15.52% |
22055.664 |
18632.040 |
44.707 |
-15.49% |
44.707 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_VOL3D_CALC_RAW/2
|
-15.50% |
8.757 |
7.400 |
0.001 |
-15.50% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_VOL3D_CALC_LAMBDA/2
|
-15.48% |
8.757 |
7.401 |
0.000 |
-15.49% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint32_t_To_uint8_t_
|
-15.42% |
10652.098 |
9009.341 |
28.483 |
-14.97% |
28.483 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_no_runtime_checks_needed<16, int>
|
-15.39% |
24.404 |
20.648 |
0.001 |
-15.39% |
0.001 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, EqZero, Mid>
|
-15.38% |
16666.482 |
14103.064 |
1.147 |
-15.38% |
1.147 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, EqZero, Last>
|
-15.38% |
16667.265 |
14104.026 |
1.051 |
-15.38% |
1.051 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint64_t_To_uint16_t_
|
-15.36% |
19397.175 |
16417.044 |
161.523 |
-13.52% |
161.523 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, EqZero, First>
|
-15.36% |
16670.381 |
14109.648 |
0.219 |
-15.36% |
0.219 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC127
|
-14.94% |
605.882 |
515.388 |
0.026 |
-14.92% |
0.026 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC128
|
-14.70% |
1103.429 |
941.272 |
0.092 |
-14.69% |
0.092 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_PIC_2D_RAW/5001
|
-14.58% |
1089.717 |
930.866 |
19.437 |
-13.68% |
19.437 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/64
|
-14.54% |
1912.888 |
1634.701 |
1.558 |
-14.56% |
1.558 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint8_t_To_uint16_t_
|
-14.54% |
3757.009 |
3210.866 |
8.115 |
-14.53% |
8.115 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC64
|
-14.53% |
562.287 |
480.587 |
0.027 |
-14.53% |
0.027 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC127
|
-14.52% |
1095.334 |
936.266 |
0.089 |
-14.52% |
0.089 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/32
|
-14.43% |
473.014 |
404.751 |
0.073 |
-14.43% |
0.073 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/256
|
-14.37% |
31417.367 |
26902.931 |
25.015 |
-14.46% |
25.015 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIRST_SUM_LAMBDA/5001
|
-14.31% |
20.373 |
17.457 |
0.253 |
-0.86% |
0.253 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC4
|
-14.27% |
112.500 |
96.449 |
1.820 |
-14.71% |
1.820 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint32_t_To_uint16_t_
|
-14.23% |
12819.055 |
10995.106 |
10.963 |
-14.35% |
10.963 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/16
|
-14.21% |
115.466 |
99.053 |
0.009 |
-14.21% |
0.009 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC63
|
-14.20% |
554.285 |
475.566 |
0.029 |
-14.27% |
0.029 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint32_t_To_uint16_t_
|
-14.14% |
10914.633 |
9371.730 |
583.005 |
-12.72% |
583.005 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/128
|
-14.13% |
7909.140 |
6791.502 |
3.463 |
-14.22% |
3.463 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC32
|
-14.12% |
291.449 |
250.297 |
0.008 |
-14.28% |
0.008 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC16
|
-14.07% |
33.163 |
28.496 |
0.033 |
-14.08% |
0.033 |
|
External/SPEC/CFP2017rate/508.namd_r/508.namd_r
Profile
|
-13.87% |
224.627 |
193.461 |
0.383 |
-13.47% |
0.383 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC16
|
-13.87% |
156.918 |
135.153 |
0.008 |
-13.90% |
0.008 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC2
|
-13.87% |
51.941 |
44.738 |
0.002 |
-13.86% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC3
|
-13.86% |
51.937 |
44.736 |
0.002 |
-13.86% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC4
|
-13.86% |
51.938 |
44.738 |
0.001 |
-13.86% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC8
|
-13.86% |
51.937 |
44.739 |
0.001 |
-13.86% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC1
|
-13.86% |
51.934 |
44.736 |
0.002 |
-13.86% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC7
|
-13.86% |
51.939 |
44.741 |
0.000 |
-13.85% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC7
|
-13.83% |
27.596 |
23.779 |
0.059 |
-17.03% |
0.059 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_with_cond_arith_novec_int64_t_
|
-13.83% |
789617.202 |
680409.874 |
909.389 |
-13.66% |
909.389 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint32_t_To_uint8_t_
|
-13.71% |
11135.679 |
9609.435 |
35.708 |
-13.66% |
35.708 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_with_cond_arith_autovec_int64_t_
|
-13.70% |
788461.848 |
680423.413 |
1653.587 |
-14.05% |
1653.587 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_VOL3D_CALC_RAW/0
|
-13.67% |
1268.945 |
1095.453 |
1.106 |
-13.42% |
1.106 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_VOL3D_CALC_LAMBDA/0
|
-13.63% |
1268.605 |
1095.744 |
1.057 |
-13.56% |
1.057 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, EqZero, First>
|
-13.63% |
14103.429 |
12181.684 |
0.662 |
-13.62% |
0.662 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, EqZero, Mid>
|
-13.62% |
14103.140 |
12182.193 |
12.820 |
-13.62% |
12.820 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC31
|
-13.47% |
283.461 |
245.282 |
0.008 |
-13.66% |
0.008 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC15
|
-13.43% |
44.813 |
38.793 |
0.001 |
-12.69% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC63
|
-13.30% |
374.401 |
324.597 |
0.092 |
-13.31% |
0.092 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_VOL3D_CALC_LAMBDA/1
|
-13.18% |
260.227 |
225.930 |
0.155 |
-13.16% |
0.155 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_VOL3D_CALC_RAW/1
|
-13.17% |
260.156 |
225.905 |
0.181 |
-13.16% |
0.181 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC128
|
-13.08% |
81.348 |
70.706 |
0.004 |
-13.08% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint8_t_To_uint16_t_
|
-12.97% |
4542.366 |
3953.145 |
0.316 |
-12.96% |
0.316 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC8
|
-12.92% |
89.108 |
77.592 |
0.006 |
-13.21% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC63
|
-12.82% |
332.723 |
290.052 |
0.010 |
-12.85% |
0.010 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC31
|
-12.46% |
87.157 |
76.297 |
0.018 |
-11.40% |
0.018 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint16_t_To_uint8_t_
|
-12.42% |
4743.166 |
4153.868 |
0.345 |
-12.42% |
0.345 |
|
MultiSource/Benchmarks/MiBench/security-rijndael/security-rijndael
Profile
|
-12.36% |
0.335 |
0.293 |
0.000 |
-12.34% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC4
|
-12.31% |
55.661 |
48.808 |
0.001 |
-12.31% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC15
|
-12.30% |
148.414 |
130.153 |
0.004 |
-12.54% |
0.004 |
|
SingleSource/Benchmarks/Shootout-C++/Shootout-C++-matrix
Profile
|
-12.29% |
2.509 |
2.201 |
0.000 |
-12.26% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC4
|
-12.12% |
41.301 |
36.294 |
0.001 |
-12.12% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC4
|
-12.12% |
41.296 |
36.292 |
0.000 |
-12.13% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint8_t>/16
|
-12.03% |
83.346 |
73.315 |
0.016 |
-2.83% |
0.016 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint64_t_To_uint32_t_
|
-12.01% |
18539.910 |
16313.462 |
490.343 |
-8.42% |
490.343 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC16
|
-11.83% |
51.940 |
45.794 |
0.093 |
-11.84% |
0.093 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC2
|
-11.77% |
21.276 |
18.772 |
0.001 |
-11.77% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC15
|
-11.70% |
107.003 |
94.484 |
0.006 |
-11.70% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC15
|
-11.70% |
106.997 |
94.480 |
0.005 |
-11.71% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC2
|
-11.48% |
38.170 |
33.790 |
0.001 |
-11.48% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC15
|
-11.45% |
51.936 |
45.989 |
0.004 |
-11.46% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint8_t>/16
|
-11.42% |
60.042 |
53.187 |
0.006 |
-1.17% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC3
|
-11.11% |
22.527 |
20.024 |
0.001 |
-11.11% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC4
|
-11.11% |
22.526 |
20.023 |
0.001 |
-11.11% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC4
|
-11.11% |
22.526 |
20.024 |
0.000 |
-11.11% |
0.000 |
|
MicroBenchmarks/ImageProcessing/Blur/blur.test:BENCHMARK_boxBlurKernel/1024
|
-11.05% |
30098.956 |
26772.869 |
48.819 |
-11.20% |
48.819 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC32
|
-11.01% |
53.184 |
47.330 |
0.049 |
-11.02% |
0.049 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC7
|
-10.74% |
81.317 |
72.580 |
0.004 |
-10.74% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC4
|
-10.54% |
23.778 |
21.273 |
0.002 |
-10.54% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC64
|
-10.47% |
53.813 |
48.181 |
0.002 |
-10.47% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC16
|
-10.34% |
36.291 |
32.538 |
0.000 |
-10.35% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_BAND_LIN_EQ_LAMBDA/171
|
-10.28% |
0.384 |
0.344 |
0.000 |
-5.99% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_BAND_LIN_EQ_RAW/171
|
-10.28% |
0.384 |
0.344 |
0.000 |
-5.99% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_DIFF_PREDICT_LAMBDA/171
|
-10.25% |
12.382 |
11.113 |
0.035 |
-7.28% |
0.035 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint8_t_To_uint16_t_
|
-9.94% |
5848.048 |
5266.625 |
23.701 |
-9.98% |
23.701 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC8
|
-9.76% |
25.655 |
23.151 |
0.001 |
-9.76% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC8
|
-9.76% |
25.655 |
23.151 |
0.001 |
-9.77% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC127
|
-9.63% |
101.789 |
91.986 |
0.002 |
-9.71% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_only_autovec_int64_t_
|
-9.60% |
333137.122 |
301151.383 |
182.018 |
-9.64% |
182.018 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC31
|
-9.54% |
196.092 |
177.386 |
0.009 |
-9.71% |
0.009 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC7
|
-9.53% |
26.281 |
23.776 |
0.002 |
-9.53% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC7
|
-9.53% |
26.281 |
23.777 |
0.002 |
-9.53% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint8_t>/999
|
-9.42% |
318.501 |
288.491 |
0.006 |
-0.70% |
0.006 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_INT_PREDICT_RAW/44217
|
-9.26% |
8822.329 |
8005.064 |
94.646 |
-11.54% |
94.646 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_DEL_DOT_VEC_2D_LAMBDA/1
|
-9.21% |
287.027 |
260.580 |
0.145 |
-9.24% |
0.145 |
|
MicroBenchmarks/ImageProcessing/Dilate/Dilate.test:BENCHMARK_DILATE/1024
|
-9.18% |
7288.706 |
6619.725 |
169.309 |
-6.90% |
169.309 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_DEL_DOT_VEC_2D_RAW/1
|
-9.15% |
286.962 |
260.711 |
0.022 |
-9.16% |
0.022 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_PRESSURE_CALC_LAMBDA/5001
|
-9.06% |
46.449 |
42.243 |
1.066 |
-3.94% |
1.066 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC64
|
-8.94% |
93.238 |
84.904 |
0.053 |
-8.94% |
0.053 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC7
|
-8.89% |
28.157 |
25.654 |
0.002 |
-8.90% |
0.002 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIRST_DIFF_LAMBDA/5001
|
-8.74% |
12.864 |
11.739 |
0.253 |
-3.70% |
0.253 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_DISC_ORD_LAMBDA/5001
|
-8.73% |
638.878 |
583.107 |
13.963 |
-8.51% |
13.963 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_DEL_DOT_VEC_2D_RAW/2
|
-8.71% |
3.510 |
3.204 |
0.000 |
-8.71% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_DEL_DOT_VEC_2D_LAMBDA/2
|
-8.70% |
3.510 |
3.204 |
0.000 |
-8.69% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint8_t>/51
|
-8.65% |
138.351 |
126.387 |
0.007 |
7.42% |
0.007 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_runtime_checks_pass<4, int>
|
-8.62% |
16.775 |
15.329 |
0.001 |
-8.25% |
0.001 |
|
MultiSource/Benchmarks/FreeBench/pifft/pifft
Profile
|
-8.53% |
0.359 |
0.328 |
0.000 |
-8.57% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC8
|
-8.51% |
29.410 |
26.907 |
0.001 |
-8.51% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint8_t_To_uint32_t_
|
-8.27% |
12769.759 |
11713.431 |
50.695 |
-8.34% |
50.695 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_HYDRO_2D_LAMBDA/171
|
-8.26% |
88.592 |
81.274 |
0.691 |
-8.33% |
0.691 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint16_t_To_uint8_t_
|
-8.22% |
6812.717 |
6252.916 |
24.605 |
-8.26% |
24.605 |
|
SingleSource/Benchmarks/Misc/salsa20
Profile
|
-8.14% |
15.386 |
14.133 |
0.006 |
-8.13% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC3
|
-7.90% |
47.557 |
43.801 |
0.001 |
-7.90% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC16
|
-7.85% |
31.914 |
29.410 |
0.001 |
-7.84% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC16
|
-7.84% |
31.913 |
29.410 |
0.001 |
-7.84% |
0.001 |
|
MultiSource/Benchmarks/TSVC/NodeSplitting-dbl/NodeSplitting-dbl
Profile
|
-7.81% |
28.145 |
25.946 |
0.170 |
-1.78% |
0.170 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC32
|
-7.81% |
40.047 |
36.919 |
0.001 |
-7.82% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint16_t>/28
|
-7.80% |
122.857 |
113.275 |
0.018 |
-6.32% |
0.018 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_DEL_DOT_VEC_2D_RAW/0
|
-7.76% |
1795.511 |
1656.166 |
6.796 |
-8.03% |
6.796 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC15
|
-7.70% |
32.538 |
30.033 |
0.002 |
-7.70% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC3
|
-7.69% |
16.268 |
15.017 |
0.001 |
-7.69% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC15
|
-7.69% |
32.538 |
30.035 |
0.001 |
-7.69% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC128
|
-7.65% |
173.343 |
160.075 |
0.036 |
-7.65% |
0.036 |
|
MultiSource/Benchmarks/Trimaran/enc-md5/enc-md5
Profile
|
-7.63% |
3.506 |
3.239 |
0.000 |
-7.62% |
0.000 |
|
MultiSource/Benchmarks/VersaBench/beamformer/beamformer
Profile
|
-7.63% |
5.202 |
4.805 |
0.000 |
-7.62% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_DEL_DOT_VEC_2D_LAMBDA/0
|
-7.57% |
1799.566 |
1663.368 |
12.621 |
-7.18% |
12.621 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_xor_no_runtime_checks_needed<16, int>
|
-7.40% |
16.895 |
15.644 |
0.001 |
-7.41% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint16_t_To_uint64_t_
|
-7.31% |
20249.111 |
18769.784 |
47.909 |
-6.82% |
47.909 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC128
|
-7.27% |
68.829 |
63.827 |
0.009 |
-7.23% |
0.009 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint8_t>/127
|
-7.21% |
138.917 |
128.897 |
0.004 |
-7.21% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC7
|
-7.20% |
32.537 |
30.193 |
0.109 |
-7.21% |
0.109 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC127
|
-7.20% |
68.774 |
63.824 |
0.003 |
-6.54% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint8_t>/10
|
-7.05% |
64.080 |
59.562 |
0.010 |
-3.46% |
0.010 |
|
SingleSource/Benchmarks/Misc/pi
Profile
|
-7.03% |
1.783 |
1.657 |
0.000 |
-7.01% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint16_t_To_uint64_t_
|
-6.98% |
25029.536 |
23282.541 |
23.716 |
-6.82% |
23.716 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC15
|
-6.94% |
45.052 |
41.924 |
0.003 |
-6.94% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC15
|
-6.90% |
54.436 |
50.680 |
0.004 |
-6.91% |
0.004 |
|
SingleSource/Benchmarks/Misc/oourafft
Profile
|
-6.79% |
15.383 |
14.339 |
0.056 |
-5.00% |
0.056 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC63
|
-6.76% |
74.491 |
69.453 |
0.004 |
-6.43% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC31
|
-6.73% |
74.471 |
69.456 |
0.003 |
-6.72% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint8_t>/28
|
-6.67% |
91.175 |
85.096 |
0.003 |
3.79% |
0.003 |
|
SingleSource/Benchmarks/Polybench/stencils/jacobi-2d/jacobi-2d
Profile
|
-6.63% |
32.140 |
30.011 |
0.335 |
-6.87% |
0.335 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC63
|
-6.56% |
114.515 |
106.999 |
0.006 |
-6.56% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC127
|
-6.54% |
2405.892 |
2248.570 |
19.768 |
-7.34% |
19.768 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C++/miniFE/miniFE
Profile
|
-6.51% |
15.817 |
14.787 |
0.059 |
-7.40% |
0.059 |
|
SingleSource/Benchmarks/Misc/flops-6
Profile
|
-6.45% |
1.312 |
1.227 |
0.001 |
-6.50% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC127
|
-6.41% |
194.593 |
182.114 |
0.329 |
-6.42% |
0.329 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_only_autovec_int32_t_
|
-6.41% |
180945.148 |
169351.125 |
1098.114 |
-6.50% |
1098.114 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC15
|
-6.36% |
39.421 |
36.915 |
0.002 |
-6.36% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint16_t>/127
|
-6.31% |
138.914 |
130.146 |
0.011 |
-6.31% |
0.011 |
|
MultiSource/Benchmarks/McCat/12-IOtest/iotest
Profile
|
-6.25% |
1.808 |
1.695 |
0.021 |
-7.10% |
0.021 |
|
SingleSource/Benchmarks/Misc-C++/Large/sphereflake
Profile
|
-6.20% |
20.009 |
18.768 |
0.004 |
-6.17% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC16
|
-6.17% |
40.675 |
38.166 |
0.002 |
-6.17% |
0.002 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_DIFF_PREDICT_RAW/171
|
-6.12% |
11.838 |
11.114 |
0.053 |
-6.86% |
0.053 |
|
MultiSource/Benchmarks/MiBench/telecomm-gsm/telecomm-gsm
Profile
|
-6.08% |
0.663 |
0.623 |
0.000 |
-6.11% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint16_t>/16
|
-6.08% |
84.614 |
79.469 |
0.011 |
-4.81% |
0.011 |
|
External/SPEC/CFP2017rate/538.imagick_r/538.imagick_r
Profile
|
-6.08% |
292.250 |
274.482 |
0.103 |
-6.03% |
0.103 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint32_t_To_uint64_t_
|
-6.02% |
21474.887 |
20181.178 |
36.835 |
-5.92% |
36.835 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC16
|
-6.02% |
31.292 |
29.409 |
0.001 |
-6.01% |
0.001 |
|
MultiSource/Benchmarks/Rodinia/hotspot/hotspot
Profile
|
-5.95% |
2.036 |
1.915 |
0.004 |
-5.95% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC1
|
-5.93% |
88.681 |
83.420 |
1.158 |
-6.25% |
1.158 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint8_t>/65
|
-5.93% |
95.116 |
89.477 |
0.003 |
-5.92% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint32_t>/127
|
-5.87% |
138.270 |
130.150 |
0.002 |
-5.88% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint16_t>/51
|
-5.80% |
109.592 |
103.241 |
0.055 |
-4.68% |
0.055 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC16
|
-5.66% |
33.161 |
31.285 |
0.001 |
-5.67% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC32
|
-5.64% |
44.426 |
41.920 |
0.002 |
-5.64% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC32
|
-5.64% |
44.427 |
41.923 |
0.002 |
-5.64% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC7
|
-5.59% |
354.892 |
335.065 |
3.723 |
-5.54% |
3.723 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC15
|
-5.58% |
128.237 |
121.076 |
0.004 |
-5.60% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC31
|
-5.57% |
45.063 |
42.551 |
0.001 |
-5.58% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC31
|
-5.56% |
45.051 |
42.548 |
0.001 |
-5.56% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint32_t>/999
|
-5.54% |
1365.046 |
1289.388 |
0.079 |
-5.54% |
0.079 |
|
MultiSource/Benchmarks/SciMark2-C/scimark2
Profile
|
-5.53% |
107.710 |
101.749 |
0.002 |
-5.47% |
0.002 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_PRESSURE_CALC_LAMBDA/44217
|
-5.44% |
504.391 |
476.928 |
2.898 |
-4.33% |
2.898 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint32_t>/999
|
-5.39% |
696.472 |
658.903 |
0.042 |
-5.40% |
0.042 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint8_t>/10
|
-5.38% |
48.807 |
46.179 |
0.022 |
-0.48% |
0.022 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC7
|
-5.31% |
70.710 |
66.957 |
0.003 |
-5.32% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint8_t>/10
|
-5.30% |
73.347 |
69.456 |
0.004 |
-1.77% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC7
|
-5.30% |
70.702 |
66.953 |
0.002 |
-5.32% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint8_t_To_uint16_t_
|
-5.25% |
3631.707 |
3440.957 |
24.789 |
-5.30% |
24.789 |
|
MultiSource/Applications/lambda-0.1.3/lambda
Profile
|
-5.19% |
15.885 |
15.060 |
0.015 |
-5.10% |
0.015 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_PIC_2D_RAW/171
|
-5.18% |
13.523 |
12.823 |
0.064 |
-5.29% |
0.064 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_HYDRO_2D_RAW/171
|
-5.17% |
87.381 |
82.863 |
0.198 |
-6.50% |
0.198 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC32
|
-5.13% |
24.404 |
23.151 |
0.001 |
-5.14% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC31
|
-5.13% |
24.404 |
23.152 |
0.005 |
-5.13% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC31
|
-5.13% |
24.403 |
23.152 |
0.002 |
-5.13% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC32
|
-5.13% |
24.403 |
23.152 |
0.001 |
-5.12% |
0.001 |
|
MicroBenchmarks/ImageProcessing/Dilate/Dilate.test:BENCHMARK_DILATE/128
|
-5.05% |
216.394 |
205.456 |
2.680 |
-9.87% |
2.680 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_PIC_2D_LAMBDA/171
|
-5.02% |
13.458 |
12.783 |
0.049 |
-5.29% |
0.049 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC31
|
-4.93% |
241.217 |
229.325 |
0.148 |
-4.94% |
0.148 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint16_t>/10
|
-4.86% |
65.767 |
62.568 |
0.004 |
-3.61% |
0.004 |
|
MicroBenchmarks/ImageProcessing/Blur/blur.test:BENCHMARK_boxBlurKernel/128
|
-4.84% |
439.346 |
418.079 |
4.204 |
-3.73% |
4.204 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint32_t>/256
|
-4.81% |
364.171 |
346.659 |
0.014 |
-4.81% |
0.014 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_BAND_LIN_EQ_RAW/5001
|
-4.79% |
21.289 |
20.268 |
0.180 |
-1.72% |
0.180 |
|
SingleSource/Benchmarks/Misc/revertBits
Profile
|
-4.72% |
0.641 |
0.611 |
0.000 |
-4.71% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_BAND_LIN_EQ_LAMBDA/5001
|
-4.69% |
21.327 |
20.326 |
0.067 |
-2.28% |
0.067 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint16_t>/65
|
-4.61% |
95.109 |
90.727 |
0.006 |
-4.61% |
0.006 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_runtime_checks_fail<16, int>
|
-4.60% |
54.438 |
51.933 |
0.005 |
-4.60% |
0.005 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_runtime_checks_pass<16, int>
|
-4.60% |
54.437 |
51.935 |
0.003 |
-4.60% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint32_t_To_uint16_t_
|
-4.57% |
9844.897 |
9395.328 |
26.616 |
-4.90% |
26.616 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC8
|
-4.48% |
26.858 |
25.654 |
0.001 |
-4.68% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC31
|
-4.48% |
70.086 |
66.949 |
0.004 |
-4.47% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint8_t_To_uint64_t_
|
-4.46% |
23461.938 |
22416.341 |
43.411 |
-4.55% |
43.411 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC1
|
-4.36% |
14.393 |
13.765 |
0.001 |
-4.35% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC1
|
-4.36% |
14.394 |
13.766 |
0.001 |
-4.36% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC64
|
-4.36% |
43.177 |
41.294 |
0.002 |
-4.36% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC3
|
-4.36% |
14.393 |
13.766 |
0.001 |
-4.35% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC8
|
-4.36% |
14.392 |
13.765 |
0.001 |
-4.36% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC8
|
-4.36% |
14.392 |
13.765 |
0.001 |
-4.36% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC15
|
-4.36% |
14.392 |
13.765 |
0.001 |
-4.36% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC2
|
-4.35% |
14.392 |
13.766 |
0.000 |
-4.35% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC2
|
-4.35% |
14.392 |
13.765 |
0.000 |
-4.35% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC16
|
-4.35% |
14.393 |
13.766 |
0.000 |
-4.35% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC63
|
-4.35% |
43.177 |
41.299 |
0.001 |
-4.61% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC3
|
-4.35% |
14.391 |
13.765 |
0.000 |
-4.36% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC4
|
-4.35% |
14.392 |
13.766 |
0.001 |
-4.35% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC16
|
-4.35% |
14.392 |
13.767 |
0.000 |
-4.35% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC7
|
-4.35% |
14.392 |
13.766 |
0.001 |
-4.34% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC15
|
-4.35% |
14.391 |
13.766 |
0.001 |
-4.35% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC4
|
-4.35% |
14.392 |
13.766 |
0.000 |
-4.35% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC7
|
-4.35% |
14.391 |
13.766 |
0.001 |
-4.35% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint64_t_To_uint32_t_
|
-4.30% |
19400.843 |
18567.374 |
53.454 |
-3.76% |
53.454 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint64_t>/999
|
-4.28% |
3595.609 |
3441.672 |
0.263 |
-4.26% |
0.263 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint64_t>/999
|
-4.24% |
1811.115 |
1734.333 |
0.062 |
-4.25% |
0.062 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_ENERGY_CALC_RAW/171
|
-4.24% |
14.195 |
13.593 |
0.026 |
-4.55% |
0.026 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_ENERGY_CALC_LAMBDA/5001
|
-4.23% |
438.037 |
419.501 |
3.442 |
-4.23% |
3.442 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_runtime_checks_fail<4, int>
|
-4.17% |
15.997 |
15.330 |
0.000 |
-3.64% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint64_t_To_uint8_t_
|
-4.16% |
19792.953 |
18968.889 |
29.644 |
-4.40% |
29.644 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_ENERGY_CALC_LAMBDA/171
|
-4.15% |
14.211 |
13.622 |
0.017 |
-4.39% |
0.017 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_PRESSURE_CALC_RAW/44217
|
-4.14% |
503.775 |
482.938 |
3.353 |
-3.84% |
3.353 |
|
SingleSource/Benchmarks/Misc/flops-5
Profile
|
-4.12% |
2.021 |
1.938 |
0.001 |
-4.13% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint64_t>/256
|
-4.08% |
935.520 |
897.370 |
0.214 |
-4.08% |
0.214 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC32
|
-4.07% |
61.324 |
58.830 |
0.017 |
-4.06% |
0.017 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC31
|
-4.05% |
61.948 |
59.440 |
0.002 |
-4.04% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC32
|
-4.00% |
31.285 |
30.033 |
0.001 |
-4.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC31
|
-3.99% |
93.839 |
90.099 |
0.005 |
-4.00% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_cond_load_autovec_int64_t_
|
-3.98% |
553450.044 |
531414.071 |
447.747 |
-3.84% |
447.747 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint32_t>/65
|
-3.97% |
94.480 |
90.725 |
0.005 |
-3.98% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_only_autovec_uint8_t_
|
-3.97% |
96160.599 |
92343.413 |
2.456 |
-3.97% |
2.456 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC32
|
-3.96% |
63.199 |
60.696 |
0.002 |
-3.96% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint32_t>/256
|
-3.96% |
221.504 |
212.740 |
0.008 |
-3.96% |
0.008 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<31, EqZero, First>
|
-3.94% |
3346.058 |
3214.126 |
4.263 |
-3.95% |
4.263 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint16_t_To_uint8_t_
|
-3.86% |
2873.206 |
2762.227 |
18.671 |
-4.03% |
18.671 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_only_novec_uint8_t_
|
-3.81% |
420296.445 |
404293.806 |
19.866 |
2.12% |
19.866 |
|
MultiSource/Benchmarks/VersaBench/ecbdes/ecbdes
Profile
|
-3.80% |
5.141 |
4.946 |
0.000 |
-3.76% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC32
|
-3.75% |
50.053 |
48.178 |
0.002 |
-3.74% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint16_t_To_uint32_t_
|
-3.65% |
11252.894 |
10842.696 |
53.611 |
-4.41% |
53.611 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint64_t>/256
|
-3.64% |
514.340 |
495.596 |
0.017 |
-3.65% |
0.017 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC64
|
-3.61% |
69.457 |
66.952 |
0.004 |
-3.61% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC64
|
-3.61% |
69.459 |
66.954 |
0.001 |
-3.60% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC63
|
-3.59% |
70.096 |
67.577 |
0.003 |
-3.59% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC63
|
-3.57% |
70.081 |
67.579 |
0.001 |
-3.57% |
0.001 |
|
SingleSource/Benchmarks/BenchmarkGame/n-body
Profile
|
-3.56% |
2.731 |
2.634 |
0.000 |
21.71% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC31
|
-3.44% |
60.266 |
58.191 |
0.003 |
-3.46% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint16_t>/999
|
-3.44% |
1013.664 |
978.799 |
0.049 |
-3.46% |
0.049 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC31
|
-3.35% |
31.075 |
30.033 |
0.001 |
-3.71% |
0.001 |
|
External/SPEC/CFP2017rate/544.nab_r/544.nab_r
Profile
|
-3.33% |
476.310 |
460.471 |
0.201 |
-3.64% |
0.201 |
|
MultiSource/Benchmarks/Rodinia/pathfinder/pathfinder
Profile
|
-3.32% |
1.265 |
1.223 |
0.010 |
-2.79% |
0.010 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC63
|
-3.27% |
1731.485 |
1674.876 |
21.759 |
-3.58% |
21.759 |
|
SingleSource/Benchmarks/Shootout/Shootout-lists
Profile
|
-3.22% |
11.316 |
10.952 |
0.001 |
-3.18% |
0.001 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<32, EqZero, Last>
|
-3.21% |
7045.217 |
6818.931 |
50.511 |
-3.32% |
50.511 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint16_t>/999
|
-3.16% |
515.004 |
498.712 |
0.014 |
-3.17% |
0.014 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint32_t>/10
|
-3.14% |
47.158 |
45.676 |
0.002 |
-1.36% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1BigLoopWithReductionTC1
|
-3.14% |
20.025 |
19.397 |
0.001 |
-3.14% |
0.001 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_FLOYD_DITHER/256
|
-3.08% |
1795.222 |
1739.865 |
4.571 |
0.36% |
4.571 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchVecWithRuntimeChecks4PointersDBeforeA/1000
|
-3.08% |
5020489.187 |
4865688.910 |
265.603 |
-3.07% |
265.603 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_PIC_1D_RAW/44217
|
-3.06% |
14105.492 |
13674.513 |
97.044 |
0.53% |
97.044 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint8_t>/51
|
-3.02% |
230.328 |
223.369 |
0.008 |
8.82% |
0.008 |
|
MultiSource/Benchmarks/BitBench/drop3/drop3
Profile
|
-2.88% |
0.731 |
0.710 |
0.001 |
-2.82% |
0.001 |
|
External/SPEC/CFP2017rate/519.lbm_r/519.lbm_r
Profile
|
-2.87% |
199.780 |
194.041 |
1.739 |
-3.31% |
1.739 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<31, GreaterThanZero, Last>
|
-2.80% |
8332.004 |
8098.480 |
22.231 |
-2.38% |
22.231 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_acosf_autovec_float_
|
-2.79% |
844.557 |
820.957 |
0.027 |
-2.82% |
0.027 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_acosf_novec_float_
|
-2.79% |
844.415 |
820.862 |
0.027 |
-2.82% |
0.027 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC1
|
-2.78% |
22.526 |
21.900 |
0.001 |
-2.78% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC1
|
-2.78% |
22.528 |
21.902 |
0.003 |
-2.77% |
0.003 |
|
MultiSource/Applications/JM/lencod/lencod
Profile
|
-2.75% |
32.730 |
31.830 |
0.032 |
-2.18% |
0.032 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint32_t>/10
|
-2.67% |
57.902 |
56.357 |
0.035 |
-1.21% |
0.035 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C/CoMD/CoMD
Profile
|
-2.64% |
9.898 |
9.637 |
0.002 |
-2.65% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC63
|
-2.62% |
120.150 |
117.004 |
0.007 |
-2.61% |
0.007 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint8_t_To_uint32_t_
|
-2.57% |
7077.887 |
6895.711 |
2.421 |
-2.57% |
2.421 |
|
SingleSource/Benchmarks/Misc-C++/oopack_v1p8
Profile
|
-2.54% |
0.479 |
0.467 |
0.000 |
-9.93% |
0.000 |
|
MultiSource/Benchmarks/TSVC/ControlLoops-dbl/ControlLoops-dbl
Profile
|
-2.53% |
11.019 |
10.740 |
0.018 |
-2.53% |
0.018 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint16_t_To_uint8_t_
|
-2.51% |
4514.789 |
4401.428 |
12.111 |
-2.56% |
12.111 |
|
MultiSource/Benchmarks/mafft/pairlocalalign
Profile
|
-2.48% |
94.007 |
91.673 |
0.346 |
-2.54% |
0.346 |
|
MultiSource/Benchmarks/Ptrdist/yacr2/yacr2
Profile
|
-2.48% |
2.077 |
2.025 |
0.000 |
-2.36% |
0.000 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_FLOYD_DITHER/128
|
-2.46% |
438.059 |
427.303 |
2.376 |
-2.77% |
2.376 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint8_t>/16
|
-2.42% |
64.122 |
62.573 |
0.005 |
1.99% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC63
|
-2.35% |
107.012 |
104.499 |
0.001 |
-2.34% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint8_t>/28
|
-2.34% |
140.312 |
137.031 |
0.009 |
5.78% |
0.009 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint16_t>/16
|
-2.32% |
53.812 |
52.561 |
0.006 |
-1.26% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchVecWithRuntimeChecks4PointersDBeforeA/32
|
-2.32% |
166180.390 |
162319.631 |
95.837 |
-2.34% |
95.837 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_FLOYD_DITHER/512
|
-2.30% |
6651.214 |
6498.315 |
22.392 |
-2.21% |
22.392 |
|
SingleSource/Benchmarks/Misc-C++/Large/ray
Profile
|
-2.26% |
12.104 |
11.831 |
0.000 |
-2.23% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC64
|
-2.25% |
111.395 |
108.884 |
0.051 |
-2.24% |
0.051 |
|
SingleSource/Benchmarks/Shootout/Shootout-matrix
Profile
|
-2.24% |
3.864 |
3.777 |
0.000 |
-2.22% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint16_t>/10
|
-2.22% |
46.209 |
45.181 |
0.005 |
-0.99% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint64_t>/51
|
-2.19% |
229.013 |
224.006 |
0.005 |
-2.18% |
0.005 |
|
External/SPEC/CINT2017rate/523.xalancbmk_r/523.xalancbmk_r
Profile
|
-2.17% |
244.965 |
239.647 |
0.466 |
-0.54% |
0.466 |
|
SingleSource/Benchmarks/Misc/flops-1
Profile
|
-2.17% |
9.002 |
8.807 |
0.000 |
-2.15% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_csa_with_cond_arith_novec_int64_t_
|
-2.16% |
748737.167 |
732595.762 |
1091.713 |
-1.63% |
1091.713 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC128
|
-2.10% |
119.520 |
117.013 |
0.005 |
-2.10% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC127
|
-2.10% |
120.151 |
117.631 |
0.006 |
-2.09% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC127
|
-2.09% |
120.143 |
117.634 |
0.011 |
-2.08% |
0.011 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC128
|
-2.09% |
119.517 |
117.022 |
0.002 |
-2.09% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint32_t_To_uint64_t_
|
-1.98% |
26356.228 |
25835.616 |
46.527 |
-1.69% |
46.527 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<16, EqZero, None>
|
-1.96% |
8176.442 |
8016.153 |
2.397 |
-1.97% |
2.397 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopTC16
|
-1.96% |
277.298 |
271.874 |
1.937 |
-1.57% |
1.937 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_ENERGY_CALC_RAW/5001
|
-1.95% |
429.312 |
420.937 |
2.679 |
-1.82% |
2.679 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_EOS_RAW/171
|
-1.89% |
0.873 |
0.856 |
0.000 |
-1.69% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_ENERGY_CALC_LAMBDA/44217
|
-1.86% |
4328.589 |
4248.181 |
6.558 |
-1.76% |
6.558 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<16, EqZero, Mid>
|
-1.84% |
8657.343 |
8497.694 |
1.664 |
-1.84% |
1.664 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint16_t>/256
|
-1.84% |
272.853 |
267.824 |
0.022 |
-1.84% |
0.022 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint16_t_To_uint32_t_
|
-1.83% |
13556.435 |
13307.866 |
23.534 |
-1.30% |
23.534 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C/SimpleMOC/SimpleMOC
Profile
|
-1.75% |
10.445 |
10.262 |
0.037 |
-1.37% |
0.037 |
|
MultiSource/Benchmarks/ASC_Sequoia/AMGmk/AMGmk
Profile
|
-1.75% |
33.360 |
32.777 |
0.052 |
-0.85% |
0.052 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_EOS_LAMBDA/171
|
-1.72% |
0.871 |
0.856 |
0.001 |
-1.71% |
0.001 |
|
External/SPEC/CFP2017rate/511.povray_r/511.povray_r
Profile
|
-1.72% |
33.959 |
33.375 |
0.030 |
-1.22% |
0.030 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<32, LessThanZero, Mid>
|
-1.72% |
4570.400 |
4491.985 |
3.843 |
-1.73% |
3.843 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint64_t>/51
|
-1.69% |
148.302 |
145.792 |
0.004 |
-1.70% |
0.004 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_INT_PREDICT_RAW/171
|
-1.69% |
6.918 |
6.801 |
0.001 |
-1.79% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_csa_with_in_loop_arith_novec_int64_t_
|
-1.68% |
1029077.753 |
1011764.347 |
519.522 |
-1.59% |
519.522 |
|
MicroBenchmarks/ImageProcessing/Blur/blur.test:BENCHMARK_boxBlurKernel/512
|
-1.67% |
6619.143 |
6508.393 |
24.322 |
-1.59% |
24.322 |
|
MultiSource/Benchmarks/TSVC/Equivalencing-flt/Equivalencing-flt
Profile
|
-1.67% |
3.096 |
3.045 |
0.014 |
-0.34% |
0.014 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_erf_autovec_double_
|
-1.65% |
888.964 |
874.267 |
0.398 |
-1.67% |
0.398 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_csa_with_cond_arith_autovec_int64_t_
|
-1.65% |
746010.126 |
733711.266 |
758.431 |
-1.51% |
758.431 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_erf_novec_double_
|
-1.64% |
888.925 |
874.389 |
0.222 |
-1.68% |
0.222 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_INT_PREDICT_LAMBDA/171
|
-1.61% |
6.925 |
6.813 |
0.009 |
-1.62% |
0.009 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<16, GreaterThanZero, First>
|
-1.59% |
8614.006 |
8477.114 |
10.941 |
-0.22% |
10.941 |
|
SingleSource/Benchmarks/Misc/mandel-2
Profile
|
-1.58% |
2.536 |
2.496 |
0.000 |
-1.54% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_ENERGY_CALC_RAW/44217
|
-1.58% |
4347.556 |
4278.951 |
10.624 |
-1.21% |
10.624 |
|
MicroBenchmarks/ImageProcessing/Dilate/Dilate.test:BENCHMARK_DILATE/256
|
-1.56% |
1058.647 |
1042.155 |
2.202 |
-2.35% |
2.202 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint32_t>/28
|
-1.55% |
72.485 |
71.359 |
0.060 |
-1.23% |
0.060 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<6, LessThanZero, Mid>
|
-1.55% |
23851.572 |
23482.070 |
2.257 |
-0.36% |
2.257 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<64, EqZero, None>
|
-1.53% |
2942.820 |
2897.865 |
3.027 |
-1.07% |
3.027 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC63
|
-1.46% |
129.534 |
127.644 |
0.008 |
-1.94% |
0.008 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, LessThanZero, None>
|
-1.45% |
37600.000 |
37055.461 |
45.421 |
-1.39% |
45.421 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C++/PENNANT/PENNANT
Profile
|
-1.43% |
4.799 |
4.730 |
0.016 |
-1.80% |
0.016 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<32, GreaterThanZero, Mid>
|
-1.42% |
4557.761 |
4493.067 |
0.836 |
-1.37% |
0.836 |
|
MultiSource/Benchmarks/Olden/health/health
Profile
|
-1.42% |
1.593 |
1.571 |
0.002 |
-1.29% |
0.002 |
|
MultiSource/Benchmarks/MallocBench/cfrac/cfrac
Profile
|
-1.41% |
2.781 |
2.742 |
0.001 |
-1.36% |
0.001 |
|
MultiSource/Benchmarks/TSVC/ControlLoops-flt/ControlLoops-flt
Profile
|
-1.39% |
5.444 |
5.369 |
0.011 |
-1.44% |
0.011 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<64, LessThanZero, Last>
|
-1.31% |
4185.499 |
4130.837 |
1.225 |
-0.96% |
1.225 |
|
External/SPEC/CINT2017rate/525.x264_r/525.x264_r
Profile
|
-1.31% |
129.590 |
127.898 |
0.112 |
-1.20% |
0.112 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC2
|
-1.28% |
13.310 |
13.139 |
0.001 |
-0.11% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC127
|
-1.27% |
197.115 |
194.607 |
0.008 |
-1.26% |
0.008 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC128
|
-1.27% |
198.364 |
195.843 |
0.006 |
-1.27% |
0.006 |
|
MultiSource/Benchmarks/TSVC/Searching-flt/Searching-flt
Profile
|
-1.24% |
4.140 |
4.088 |
0.017 |
0.10% |
0.017 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<7, EqZero, None>
|
-1.21% |
27195.354 |
26866.634 |
3.635 |
-1.16% |
3.635 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_nested_cond_load_novec_int32_t_
|
-1.19% |
649717.237 |
641992.268 |
328.119 |
-0.49% |
328.119 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_nested_cond_load_novec_uint8_t_
|
-1.17% |
504533.926 |
498624.910 |
170.788 |
-1.21% |
170.788 |
|
MultiSource/Applications/siod/siod
Profile
|
-1.16% |
7.969 |
7.877 |
0.003 |
-1.03% |
0.003 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<8, LessThanZero, Mid>
|
-1.15% |
19453.091 |
19229.767 |
0.423 |
-1.05% |
0.423 |
|
MultiSource/Benchmarks/nbench/nbench
Profile
|
-1.15% |
6.104 |
6.034 |
0.001 |
-1.52% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint32_t>/51
|
-1.11% |
77.849 |
76.984 |
0.021 |
-1.82% |
0.021 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint8_t>/10
|
-1.09% |
52.510 |
51.939 |
0.190 |
0.00% |
0.190 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint32_t>/51
|
-1.07% |
118.263 |
117.002 |
0.005 |
-1.07% |
0.005 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<16, LessThanZero, Last>
|
-1.05% |
13141.822 |
13003.976 |
26.180 |
-1.05% |
26.180 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint8_t_To_uint32_t_
|
-1.03% |
12110.101 |
11985.677 |
9.010 |
-1.13% |
9.010 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<3, LessThanZero, Mid>
|
-1.01% |
37665.286 |
37286.499 |
69.707 |
-1.02% |
69.707 |