|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_HYDRO_2D_LAMBDA/44217
|
-59.96% |
83913.203 |
33595.772 |
13585.381 |
-63.05% |
13585.381 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_INT_PREDICT_RAW/44217
|
-58.94% |
19498.200 |
8005.064 |
94.646 |
-11.54% |
94.646 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_HYDRO_2D_LAMBDA/5001
|
-58.08% |
9047.544 |
3792.420 |
1369.217 |
-58.39% |
1369.217 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint64_t_To_uint32_t_
|
-52.15% |
35370.805 |
16924.701 |
97.322 |
-52.07% |
97.322 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint64_t_To_uint16_t_
|
-51.59% |
35885.805 |
17372.024 |
134.201 |
-51.31% |
134.201 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint64_t_To_uint8_t_
|
-49.92% |
37268.712 |
18664.497 |
13.686 |
-49.64% |
13.686 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_DISC_ORD_LAMBDA/44217
|
-48.34% |
13232.131 |
6835.624 |
2094.030 |
-51.36% |
2094.030 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C/miniGMG/miniGMG
Profile
|
-44.59% |
8.138 |
4.509 |
0.077 |
-50.94% |
0.077 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_DIFF_PREDICT_RAW/44217
|
-44.12% |
24163.937 |
13503.554 |
315.584 |
-42.04% |
315.584 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint16_t_To_uint64_t_
|
-43.96% |
18636.547 |
10443.109 |
4.904 |
-44.08% |
4.904 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIRST_DIFF_RAW/44217
|
-43.19% |
180.150 |
102.347 |
0.764 |
-28.17% |
0.764 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_DIFF_PREDICT_LAMBDA/44217
|
-42.18% |
23344.556 |
13497.103 |
321.017 |
-41.58% |
321.017 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint8_t_To_uint64_t_
|
-41.10% |
17844.864 |
10510.631 |
10.817 |
-40.95% |
10.817 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_DIFF_PREDICT_LAMBDA/5001
|
-40.95% |
2568.225 |
1516.579 |
25.576 |
-39.56% |
25.576 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint64_t_To_uint32_t_
|
-40.77% |
38198.606 |
22625.975 |
21.204 |
-40.70% |
21.204 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_DIFF_PREDICT_RAW/5001
|
-40.75% |
2556.339 |
1514.510 |
22.449 |
-41.18% |
22.449 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/64
|
-36.69% |
6183.016 |
3914.750 |
2.037 |
-36.68% |
2.037 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/32
|
-36.66% |
1396.250 |
884.427 |
0.044 |
-36.65% |
0.044 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/16
|
-36.55% |
279.542 |
177.359 |
0.014 |
-36.54% |
0.014 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/256
|
-36.20% |
107114.208 |
68337.800 |
74.925 |
-36.22% |
74.925 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/128
|
-36.07% |
26265.253 |
16791.136 |
7.416 |
-36.09% |
7.416 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint32_t_To_uint64_t_
|
-35.98% |
22680.753 |
14520.020 |
855.165 |
-36.11% |
855.165 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint64_t_To_uint16_t_
|
-34.83% |
29347.015 |
19125.098 |
16.500 |
-33.94% |
16.500 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint64_t_To_uint8_t_
|
-34.62% |
30245.862 |
19775.829 |
16.782 |
-34.32% |
16.782 |
|
MultiSource/Benchmarks/MiBench/automotive-bitcount/automotive-bitcount
Profile
|
-31.12% |
0.178 |
0.123 |
0.001 |
-0.91% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint64_t_To_uint16_t_
|
-28.59% |
25912.810 |
18503.930 |
46.991 |
-28.55% |
46.991 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC128
|
-28.19% |
1296.455 |
931.031 |
6.701 |
-27.98% |
6.701 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint32_t_To_uint8_t_
|
-28.12% |
13507.526 |
9709.553 |
39.635 |
-27.91% |
39.635 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIRST_DIFF_LAMBDA/44217
|
-28.06% |
143.413 |
103.165 |
0.154 |
-28.76% |
0.154 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_PIC_2D_LAMBDA/44217
|
-28.06% |
11957.547 |
8601.887 |
598.439 |
-21.54% |
598.439 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC128
|
-27.49% |
560.255 |
406.218 |
0.032 |
-27.14% |
0.032 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC64
|
-27.49% |
656.177 |
475.773 |
3.445 |
-27.21% |
3.445 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC32
|
-27.27% |
335.428 |
243.956 |
1.574 |
-26.94% |
1.574 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC16
|
-26.82% |
174.887 |
127.982 |
0.516 |
-26.36% |
0.516 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC64
|
-26.47% |
293.603 |
215.890 |
0.181 |
-26.02% |
0.181 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint8_t>/51
|
-25.83% |
123.886 |
91.883 |
0.008 |
-0.66% |
0.008 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_PIC_2D_RAW/44217
|
-25.47% |
11895.579 |
8865.216 |
886.976 |
-20.96% |
886.976 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIRST_SUM_RAW/44217
|
-25.41% |
181.902 |
135.680 |
0.602 |
-18.43% |
0.602 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint64_t_To_uint8_t_
|
-24.78% |
27167.649 |
20436.409 |
41.080 |
-24.93% |
41.080 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC32
|
-24.68% |
160.334 |
120.762 |
0.010 |
-23.99% |
0.010 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC128
|
-23.16% |
602.720 |
463.159 |
0.017 |
-23.31% |
0.017 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC128
|
-23.15% |
602.671 |
463.126 |
0.056 |
-23.32% |
0.056 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint16_t_To_uint64_t_
|
-22.41% |
13358.486 |
10364.817 |
0.784 |
-21.53% |
0.784 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC64
|
-22.25% |
312.264 |
242.795 |
0.007 |
-22.55% |
0.007 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC64
|
-22.24% |
312.232 |
242.793 |
0.012 |
-22.56% |
0.012 |
|
SingleSource/Benchmarks/Adobe-C++/loop_unroll
Profile
|
-21.99% |
3.105 |
2.422 |
0.002 |
-22.04% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint8_t_To_uint32_t_
|
-21.90% |
6603.217 |
5156.945 |
6.233 |
-21.65% |
6.233 |
|
MultiSource/Benchmarks/Trimaran/enc-pc1/enc-pc1
Profile
|
-21.90% |
1.130 |
0.882 |
0.000 |
-20.10% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC127
|
-21.89% |
614.588 |
480.045 |
0.013 |
-21.97% |
0.013 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC127
|
-21.89% |
614.581 |
480.051 |
0.017 |
-21.97% |
0.017 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_PIC_2D_RAW/5001
|
-21.84% |
1190.909 |
930.866 |
19.437 |
-13.68% |
19.437 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC16
|
-21.83% |
93.661 |
73.213 |
0.005 |
-20.66% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint16_t_To_uint32_t_
|
-21.58% |
7107.647 |
5573.840 |
1.238 |
-21.51% |
1.238 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_only_autovec_uint8_t_
|
-21.36% |
182340.283 |
143399.389 |
52.530 |
-21.36% |
52.530 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC16
|
-20.63% |
97.759 |
77.587 |
0.005 |
-18.96% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC32
|
-20.61% |
167.083 |
132.643 |
0.011 |
-21.20% |
0.011 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC32
|
-20.61% |
167.076 |
132.648 |
0.010 |
-21.20% |
0.010 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC128
|
-20.55% |
274.691 |
218.240 |
1.312 |
-20.57% |
1.312 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC127
|
-20.40% |
275.058 |
218.953 |
0.525 |
-20.51% |
0.525 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint8_t>/51
|
-20.27% |
191.481 |
152.662 |
0.004 |
-1.13% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC63
|
-19.89% |
324.159 |
259.684 |
0.011 |
-20.04% |
0.011 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC63
|
-19.89% |
324.151 |
259.680 |
0.011 |
-20.05% |
0.011 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC127
|
-19.85% |
642.314 |
514.823 |
0.229 |
-19.62% |
0.229 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint8_t_To_uint64_t_
|
-19.77% |
13589.395 |
10902.790 |
33.328 |
-16.55% |
33.328 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint32_t_To_uint8_t_
|
-19.34% |
13904.868 |
11215.997 |
91.588 |
-19.31% |
91.588 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_PIC_2D_LAMBDA/5001
|
-19.27% |
1123.433 |
906.917 |
36.404 |
-17.96% |
36.404 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint16_t_To_uint8_t_
|
-19.09% |
3817.037 |
3088.474 |
0.232 |
-19.11% |
0.232 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, EqZero, None>
|
-18.75% |
20512.115 |
16665.852 |
0.686 |
-18.75% |
0.686 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint32_t_To_uint16_t_
|
-18.65% |
13803.567 |
11228.848 |
8.145 |
-18.67% |
8.145 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint64_t_To_uint32_t_
|
-18.63% |
27099.460 |
22051.970 |
22.431 |
-18.48% |
22.431 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC63
|
-18.37% |
150.116 |
122.542 |
2.900 |
-18.26% |
2.900 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC64
|
-18.25% |
148.762 |
121.607 |
2.052 |
-18.18% |
2.052 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, EqZero, Last>
|
-18.17% |
14102.855 |
11540.635 |
0.102 |
-18.18% |
0.102 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_with_cond_arith_novec_uint8_t_
|
-17.90% |
746047.260 |
612537.647 |
112.079 |
-17.86% |
112.079 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC16
|
-17.88% |
94.481 |
77.586 |
0.004 |
-18.96% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC4
|
-17.87% |
17.521 |
14.390 |
0.031 |
-17.87% |
0.031 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_INT_PREDICT_RAW/5001
|
-17.82% |
1101.576 |
905.298 |
8.645 |
-0.89% |
8.645 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC8
|
-17.63% |
23.151 |
19.070 |
0.097 |
-17.64% |
0.097 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_with_cond_arith_novec_int32_t_
|
-17.56% |
740626.275 |
610589.930 |
1517.739 |
-17.51% |
1517.739 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC32
|
-17.54% |
160.190 |
132.097 |
0.113 |
-18.15% |
0.113 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC128
|
-17.47% |
569.500 |
469.993 |
0.285 |
-17.63% |
0.285 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC64
|
-17.42% |
296.619 |
244.945 |
0.031 |
-17.72% |
0.031 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC16
|
-17.37% |
91.987 |
76.006 |
0.026 |
-18.38% |
0.026 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC8
|
-16.85% |
57.572 |
47.869 |
0.002 |
-18.54% |
0.002 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIRST_SUM_LAMBDA/44217
|
-16.71% |
163.820 |
136.438 |
0.333 |
-18.34% |
0.333 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC31
|
-16.47% |
179.037 |
149.550 |
0.016 |
-16.72% |
0.016 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC31
|
-16.43% |
178.953 |
149.549 |
0.003 |
-16.73% |
0.003 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_HYDRO_1D_RAW/171
|
-16.20% |
0.444 |
0.372 |
0.000 |
-15.84% |
0.000 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, EqZero, None>
|
-15.90% |
16026.418 |
13477.442 |
13.643 |
-15.89% |
13.643 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC8
|
-15.79% |
23.778 |
20.022 |
0.001 |
-15.80% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_HYDRO_1D_LAMBDA/171
|
-15.77% |
0.441 |
0.372 |
0.000 |
-15.87% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint16_t_To_uint32_t_
|
-15.68% |
7463.468 |
6293.361 |
0.689 |
-15.66% |
0.689 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint8_t>/28
|
-15.68% |
119.508 |
100.775 |
0.035 |
-2.11% |
0.035 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint64_t_To_uint8_t_
|
-15.60% |
22075.327 |
18632.040 |
44.707 |
-15.49% |
44.707 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_VOL3D_CALC_RAW/2
|
-15.51% |
8.757 |
7.400 |
0.001 |
-15.50% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_VOL3D_CALC_LAMBDA/2
|
-15.49% |
8.757 |
7.401 |
0.000 |
-15.49% |
0.000 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, EqZero, Last>
|
-15.40% |
16671.829 |
14104.026 |
1.051 |
-15.38% |
1.051 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_no_runtime_checks_needed<16, int>
|
-15.39% |
24.405 |
20.648 |
0.001 |
-15.39% |
0.001 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, EqZero, Mid>
|
-15.39% |
16668.089 |
14103.064 |
1.147 |
-15.38% |
1.147 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint8_t>/28
|
-15.36% |
79.102 |
66.951 |
0.002 |
-0.93% |
0.002 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, EqZero, First>
|
-15.35% |
16668.177 |
14109.648 |
0.219 |
-15.36% |
0.219 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint32_t_To_uint8_t_
|
-15.32% |
10639.533 |
9009.341 |
28.483 |
-14.97% |
28.483 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC127
|
-14.83% |
605.137 |
515.388 |
0.026 |
-14.92% |
0.026 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC32
|
-14.74% |
85.281 |
72.709 |
1.692 |
-14.79% |
1.692 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/64
|
-14.62% |
1914.575 |
1634.701 |
1.558 |
-14.56% |
1.558 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC4
|
-14.61% |
112.945 |
96.449 |
1.820 |
-14.71% |
1.820 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC128
|
-14.59% |
1102.119 |
941.272 |
0.092 |
-14.69% |
0.092 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint8_t_To_uint16_t_
|
-14.54% |
3757.063 |
3210.866 |
8.115 |
-14.53% |
8.115 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/256
|
-14.46% |
31449.398 |
26902.931 |
25.015 |
-14.46% |
25.015 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC127
|
-14.45% |
1094.448 |
936.266 |
0.089 |
-14.52% |
0.089 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/32
|
-14.43% |
473.015 |
404.751 |
0.073 |
-14.43% |
0.073 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC64
|
-14.38% |
561.280 |
480.587 |
0.027 |
-14.53% |
0.027 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/16
|
-14.21% |
115.466 |
99.053 |
0.009 |
-14.21% |
0.009 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint32_t_To_uint16_t_
|
-14.16% |
12809.477 |
10995.106 |
10.963 |
-14.35% |
10.963 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC63
|
-14.13% |
553.822 |
475.566 |
0.029 |
-14.27% |
0.029 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/128
|
-14.12% |
7907.678 |
6791.502 |
3.463 |
-14.22% |
3.463 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIRST_SUM_RAW/5001
|
-14.08% |
20.270 |
17.416 |
0.216 |
0.40% |
0.216 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC16
|
-14.07% |
33.163 |
28.496 |
0.033 |
-14.08% |
0.033 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint32_t_To_uint16_t_
|
-14.02% |
10900.266 |
9371.730 |
583.005 |
-12.72% |
583.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC8
|
-13.99% |
58.194 |
50.054 |
0.003 |
-15.80% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC32
|
-13.98% |
290.965 |
250.297 |
0.008 |
-14.28% |
0.008 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC8
|
-13.97% |
58.190 |
50.060 |
0.001 |
-15.80% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_with_cond_arith_autovec_int64_t_
|
-13.94% |
790680.850 |
680423.413 |
1653.587 |
-14.05% |
1653.587 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_INT_PREDICT_LAMBDA/44217
|
-13.91% |
9244.557 |
7958.615 |
112.160 |
-4.55% |
112.160 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_with_cond_arith_novec_int64_t_
|
-13.87% |
789940.427 |
680409.874 |
909.389 |
-13.66% |
909.389 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC3
|
-13.86% |
51.936 |
44.736 |
0.002 |
-13.86% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC1
|
-13.86% |
51.935 |
44.736 |
0.002 |
-13.86% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC8
|
-13.86% |
51.937 |
44.739 |
0.001 |
-13.86% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC4
|
-13.86% |
51.934 |
44.738 |
0.001 |
-13.86% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC2
|
-13.86% |
51.934 |
44.738 |
0.002 |
-13.86% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC7
|
-13.85% |
51.932 |
44.741 |
0.000 |
-13.85% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_VOL3D_CALC_RAW/0
|
-13.71% |
1269.511 |
1095.453 |
1.106 |
-13.42% |
1.106 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC63
|
-13.67% |
376.003 |
324.597 |
0.092 |
-13.31% |
0.092 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, EqZero, First>
|
-13.63% |
14103.424 |
12181.684 |
0.662 |
-13.62% |
0.662 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, EqZero, Mid>
|
-13.62% |
14102.938 |
12182.193 |
12.820 |
-13.62% |
12.820 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_VOL3D_CALC_LAMBDA/0
|
-13.57% |
1267.830 |
1095.744 |
1.057 |
-13.56% |
1.057 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC31
|
-13.47% |
283.450 |
245.282 |
0.008 |
-13.66% |
0.008 |
|
External/SPEC/CFP2017rate/508.namd_r/508.namd_r
Profile
|
-13.35% |
223.259 |
193.461 |
0.383 |
-13.47% |
0.383 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC16
|
-13.26% |
155.810 |
135.153 |
0.008 |
-13.90% |
0.008 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_VOL3D_CALC_LAMBDA/1
|
-13.18% |
260.235 |
225.930 |
0.155 |
-13.16% |
0.155 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_VOL3D_CALC_RAW/1
|
-13.13% |
260.058 |
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_
|
-12.96% |
4541.556 |
3953.145 |
0.316 |
-12.96% |
0.316 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint32_t_To_uint8_t_
|
-12.95% |
11038.766 |
9609.435 |
35.708 |
-13.66% |
35.708 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint64_t_To_uint16_t_
|
-12.88% |
18844.789 |
16417.044 |
161.523 |
-13.52% |
161.523 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC63
|
-12.71% |
332.272 |
290.052 |
0.010 |
-12.85% |
0.010 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC31
|
-12.49% |
87.188 |
76.297 |
0.018 |
-11.40% |
0.018 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint16_t_To_uint8_t_
|
-12.44% |
4744.065 |
4153.868 |
0.345 |
-12.42% |
0.345 |
|
MultiSource/Benchmarks/MiBench/security-rijndael/security-rijndael
Profile
|
-12.42% |
0.335 |
0.293 |
0.000 |
-12.34% |
0.000 |
|
SingleSource/Benchmarks/Shootout-C++/Shootout-C++-matrix
Profile
|
-12.30% |
2.509 |
2.201 |
0.000 |
-12.26% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC15
|
-12.23% |
148.293 |
130.153 |
0.004 |
-12.54% |
0.004 |
|
MicroBenchmarks/ImageProcessing/Dilate/Dilate.test:BENCHMARK_DILATE/1024
|
-12.19% |
7538.515 |
6619.725 |
169.309 |
-6.90% |
169.309 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_HYDRO_2D_RAW/5001
|
-12.09% |
9281.142 |
8159.058 |
294.201 |
-7.25% |
294.201 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC8
|
-12.06% |
88.230 |
77.592 |
0.006 |
-13.21% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC16
|
-11.82% |
51.934 |
45.794 |
0.093 |
-11.84% |
0.093 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC2
|
-11.76% |
21.275 |
18.772 |
0.001 |
-11.77% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint8_t>/16
|
-11.61% |
82.943 |
73.315 |
0.016 |
-2.83% |
0.016 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC15
|
-11.45% |
51.936 |
45.989 |
0.004 |
-11.46% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC15
|
-11.18% |
106.372 |
94.480 |
0.005 |
-11.71% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC15
|
-11.17% |
106.370 |
94.484 |
0.006 |
-11.70% |
0.006 |
|
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/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC3
|
-11.11% |
22.526 |
20.024 |
0.001 |
-11.11% |
0.001 |
|
MicroBenchmarks/ImageProcessing/Blur/blur.test:BENCHMARK_boxBlurKernel/1024
|
-11.02% |
30089.516 |
26772.869 |
48.819 |
-11.20% |
48.819 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC32
|
-11.01% |
53.188 |
47.330 |
0.049 |
-11.02% |
0.049 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint8_t>/16
|
-10.66% |
59.535 |
53.187 |
0.006 |
-1.17% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC4
|
-10.53% |
23.777 |
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/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_HYDRO_2D_RAW/44217
|
-10.46% |
91931.035 |
82312.231 |
2076.699 |
-2.76% |
2076.699 |
|
SingleSource/Benchmarks/Misc/richards_benchmark
Profile
|
-10.38% |
2.201 |
1.972 |
0.001 |
0.97% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC16
|
-10.35% |
36.293 |
32.538 |
0.000 |
-10.35% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC4
|
-10.31% |
54.419 |
48.808 |
0.001 |
-12.31% |
0.001 |
|
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/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC7
|
-10.08% |
80.720 |
72.580 |
0.004 |
-10.74% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint64_t_To_uint32_t_
|
-10.07% |
18140.473 |
16313.462 |
490.343 |
-8.42% |
490.343 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint8_t_To_uint16_t_
|
-9.92% |
5846.300 |
5266.625 |
23.701 |
-9.98% |
23.701 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC8
|
-9.76% |
25.656 |
23.151 |
0.001 |
-9.76% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC8
|
-9.76% |
25.654 |
23.151 |
0.001 |
-9.77% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_only_autovec_int64_t_
|
-9.72% |
333574.887 |
301151.383 |
182.018 |
-9.64% |
182.018 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC7
|
-9.53% |
26.281 |
23.777 |
0.002 |
-9.53% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC7
|
-9.52% |
26.279 |
23.776 |
0.002 |
-9.53% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC31
|
-9.44% |
195.877 |
177.386 |
0.009 |
-9.71% |
0.009 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint8_t>/999
|
-9.43% |
318.513 |
288.491 |
0.006 |
-0.70% |
0.006 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_DIFF_PREDICT_RAW/171
|
-9.40% |
12.266 |
11.114 |
0.053 |
-6.86% |
0.053 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC4
|
-9.37% |
40.046 |
36.294 |
0.001 |
-12.12% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC4
|
-9.37% |
40.044 |
36.292 |
0.000 |
-12.13% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC127
|
-9.25% |
101.367 |
91.986 |
0.002 |
-9.71% |
0.002 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_DEL_DOT_VEC_2D_LAMBDA/1
|
-9.21% |
287.025 |
260.580 |
0.145 |
-9.24% |
0.145 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_DEL_DOT_VEC_2D_RAW/1
|
-9.19% |
287.091 |
260.711 |
0.022 |
-9.16% |
0.022 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC64
|
-8.93% |
93.231 |
84.904 |
0.053 |
-8.94% |
0.053 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC7
|
-8.89% |
28.156 |
25.654 |
0.002 |
-8.90% |
0.002 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_runtime_checks_fail<4, int>
|
-8.88% |
16.823 |
15.330 |
0.000 |
-3.64% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_INT_PREDICT_LAMBDA/5001
|
-8.87% |
1001.036 |
912.208 |
1.812 |
0.82% |
1.812 |
|
MultiSource/Benchmarks/FreeBench/pifft/pifft
Profile
|
-8.78% |
0.359 |
0.328 |
0.000 |
-8.57% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_DEL_DOT_VEC_2D_RAW/2
|
-8.72% |
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/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_HYDRO_2D_LAMBDA/171
|
-8.58% |
88.902 |
81.274 |
0.691 |
-8.33% |
0.691 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint8_t>/16
|
-8.52% |
68.402 |
62.573 |
0.005 |
1.99% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC8
|
-8.51% |
29.410 |
26.907 |
0.001 |
-8.51% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC2
|
-8.48% |
36.922 |
33.790 |
0.001 |
-11.48% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint8_t_To_uint32_t_
|
-8.33% |
12777.773 |
11713.431 |
50.695 |
-8.34% |
50.695 |
|
MicroBenchmarks/ImageProcessing/Dilate/Dilate.test:BENCHMARK_DILATE/128
|
-8.31% |
224.086 |
205.456 |
2.680 |
-9.87% |
2.680 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint16_t_To_uint8_t_
|
-8.20% |
6811.513 |
6252.916 |
24.605 |
-8.26% |
24.605 |
|
SingleSource/Benchmarks/Misc/salsa20
Profile
|
-8.15% |
15.387 |
14.133 |
0.006 |
-8.13% |
0.006 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_DEL_DOT_VEC_2D_RAW/0
|
-8.10% |
1802.090 |
1656.166 |
6.796 |
-8.03% |
6.796 |
|
MultiSource/Benchmarks/McCat/12-IOtest/iotest
Profile
|
-8.06% |
1.844 |
1.695 |
0.021 |
-7.10% |
0.021 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC16
|
-7.84% |
31.913 |
29.410 |
0.001 |
-7.84% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC16
|
-7.84% |
31.912 |
29.410 |
0.001 |
-7.84% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC16
|
-7.84% |
31.912 |
29.409 |
0.001 |
-6.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC32
|
-7.80% |
40.044 |
36.919 |
0.001 |
-7.82% |
0.001 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C++/miniFE/miniFE
Profile
|
-7.79% |
16.037 |
14.787 |
0.059 |
-7.40% |
0.059 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIRST_DIFF_RAW/5001
|
-7.74% |
12.920 |
11.920 |
0.132 |
-1.13% |
0.132 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint8_t>/10
|
-7.71% |
64.539 |
59.562 |
0.010 |
-3.46% |
0.010 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC15
|
-7.69% |
32.536 |
30.033 |
0.002 |
-7.70% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC15
|
-7.69% |
32.537 |
30.035 |
0.001 |
-7.69% |
0.001 |
|
MultiSource/Benchmarks/Trimaran/enc-md5/enc-md5
Profile
|
-7.66% |
3.507 |
3.239 |
0.000 |
-7.62% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC128
|
-7.65% |
173.334 |
160.075 |
0.036 |
-7.65% |
0.036 |
|
MultiSource/Benchmarks/VersaBench/beamformer/beamformer
Profile
|
-7.65% |
5.202 |
4.805 |
0.000 |
-7.62% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIRST_SUM_LAMBDA/5001
|
-7.58% |
18.890 |
17.457 |
0.253 |
-0.86% |
0.253 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_DIFF_PREDICT_LAMBDA/171
|
-7.48% |
12.011 |
11.113 |
0.035 |
-7.28% |
0.035 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_xor_no_runtime_checks_needed<16, int>
|
-7.41% |
16.895 |
15.644 |
0.001 |
-7.41% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_DEL_DOT_VEC_2D_LAMBDA/0
|
-7.33% |
1794.868 |
1663.368 |
12.621 |
-7.18% |
12.621 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC7
|
-7.21% |
32.538 |
30.193 |
0.109 |
-7.21% |
0.109 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint8_t>/127
|
-7.21% |
138.908 |
128.897 |
0.004 |
-7.21% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint16_t_To_uint64_t_
|
-7.17% |
20219.236 |
18769.784 |
47.909 |
-6.82% |
47.909 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopWithReductionTC127
|
-7.15% |
87.602 |
81.341 |
0.005 |
0.76% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint16_t>/28
|
-7.14% |
121.991 |
113.275 |
0.018 |
-6.32% |
0.018 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint16_t_To_uint64_t_
|
-7.14% |
25071.673 |
23282.541 |
23.716 |
-6.82% |
23.716 |
|
SingleSource/Benchmarks/Misc/pi
Profile
|
-7.03% |
1.783 |
1.657 |
0.000 |
-7.01% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_DISC_ORD_LAMBDA/5001
|
-7.01% |
627.051 |
583.107 |
13.963 |
-8.51% |
13.963 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC15
|
-6.94% |
45.051 |
41.924 |
0.003 |
-6.94% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC15
|
-6.91% |
54.441 |
50.680 |
0.004 |
-6.91% |
0.004 |
|
SingleSource/Benchmarks/Misc/oourafft
Profile
|
-6.85% |
15.394 |
14.339 |
0.056 |
-5.00% |
0.056 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC31
|
-6.72% |
74.459 |
69.456 |
0.003 |
-6.72% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC3
|
-6.67% |
46.931 |
43.801 |
0.001 |
-7.90% |
0.001 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_runtime_checks_pass<4, int>
|
-6.66% |
16.423 |
15.329 |
0.001 |
-8.25% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC15
|
-6.66% |
539.370 |
503.457 |
11.380 |
-4.17% |
11.380 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_HYDRO_2D_RAW/171
|
-6.66% |
88.771 |
82.863 |
0.198 |
-6.50% |
0.198 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC63
|
-6.56% |
114.515 |
106.999 |
0.006 |
-6.56% |
0.006 |
|
SingleSource/Benchmarks/Misc/flops-6
Profile
|
-6.51% |
1.312 |
1.227 |
0.001 |
-6.50% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopWithReductionTC128
|
-6.45% |
77.588 |
72.583 |
0.003 |
0.86% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC127
|
-6.43% |
2403.087 |
2248.570 |
19.768 |
-7.34% |
19.768 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC127
|
-6.43% |
68.207 |
63.824 |
0.003 |
-6.54% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_only_autovec_int32_t_
|
-6.42% |
180978.536 |
169351.125 |
1098.114 |
-6.50% |
1098.114 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC127
|
-6.42% |
194.614 |
182.114 |
0.329 |
-6.42% |
0.329 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC128
|
-6.42% |
68.204 |
63.827 |
0.009 |
-7.23% |
0.009 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC15
|
-6.35% |
39.420 |
36.915 |
0.002 |
-6.36% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint16_t>/127
|
-6.32% |
138.921 |
130.146 |
0.011 |
-6.31% |
0.011 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint32_t_To_uint64_t_
|
-6.22% |
21519.403 |
20181.178 |
36.835 |
-5.92% |
36.835 |
|
SingleSource/Benchmarks/Misc-C++/Large/sphereflake
Profile
|
-6.22% |
20.013 |
18.768 |
0.004 |
-6.17% |
0.004 |
|
SingleSource/Benchmarks/Polybench/stencils/jacobi-2d/jacobi-2d
Profile
|
-6.22% |
32.000 |
30.011 |
0.335 |
-6.87% |
0.335 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC1
|
-6.17% |
88.909 |
83.420 |
1.158 |
-6.25% |
1.158 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC16
|
-6.16% |
40.671 |
38.166 |
0.002 |
-6.17% |
0.002 |
|
MultiSource/Benchmarks/MiBench/telecomm-gsm/telecomm-gsm
Profile
|
-6.09% |
0.663 |
0.623 |
0.000 |
-6.11% |
0.000 |
|
External/SPEC/CFP2017rate/538.imagick_r/538.imagick_r
Profile
|
-6.08% |
292.246 |
274.482 |
0.103 |
-6.03% |
0.103 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_ADI_LAMBDA/5001
|
-6.02% |
2251.358 |
2115.863 |
46.956 |
-5.33% |
46.956 |
|
MultiSource/Benchmarks/Rodinia/hotspot/hotspot
Profile
|
-5.98% |
2.037 |
1.915 |
0.004 |
-5.95% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint16_t>/16
|
-5.97% |
84.514 |
79.469 |
0.011 |
-4.81% |
0.011 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint8_t>/51
|
-5.97% |
134.406 |
126.387 |
0.007 |
7.42% |
0.007 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint8_t>/65
|
-5.93% |
95.120 |
89.477 |
0.003 |
-5.92% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC63
|
-5.93% |
73.834 |
69.453 |
0.004 |
-6.43% |
0.004 |
|
SingleSource/Benchmarks/McGill/queens
Profile
|
-5.92% |
3.084 |
2.902 |
0.000 |
0.00% |
0.000 |
|
MultiSource/Applications/aha/aha
Profile
|
-5.89% |
5.004 |
4.709 |
0.005 |
-0.58% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC3
|
-5.88% |
21.274 |
20.024 |
0.001 |
0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint16_t>/51
|
-5.71% |
109.494 |
103.241 |
0.055 |
-4.68% |
0.055 |
|
MultiSource/Benchmarks/Ptrdist/ks/ks
Profile
|
-5.68% |
2.992 |
2.822 |
0.001 |
-0.90% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC16
|
-5.67% |
33.165 |
31.285 |
0.001 |
-5.67% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC32
|
-5.64% |
44.427 |
41.923 |
0.002 |
-5.64% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC32
|
-5.64% |
44.423 |
41.920 |
0.002 |
-5.64% |
0.002 |
|
MultiSource/Applications/lambda-0.1.3/lambda
Profile
|
-5.57% |
15.948 |
15.060 |
0.015 |
-5.10% |
0.015 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC31
|
-5.56% |
45.052 |
42.548 |
0.001 |
-5.56% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint32_t>/999
|
-5.55% |
1365.167 |
1289.388 |
0.079 |
-5.54% |
0.079 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC31
|
-5.55% |
45.051 |
42.551 |
0.001 |
-5.58% |
0.001 |
|
MultiSource/Benchmarks/SciMark2-C/scimark2
Profile
|
-5.51% |
107.677 |
101.749 |
0.002 |
-5.47% |
0.002 |
|
MultiSource/Applications/siod/siod
Profile
|
-5.47% |
8.333 |
7.877 |
0.003 |
-1.03% |
0.003 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_PIC_2D_LAMBDA/171
|
-5.47% |
13.522 |
12.783 |
0.049 |
-5.29% |
0.049 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC31
|
-5.46% |
242.576 |
229.325 |
0.148 |
-4.94% |
0.148 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint32_t>/127
|
-5.46% |
137.663 |
130.150 |
0.002 |
-5.88% |
0.002 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_PIC_2D_RAW/171
|
-5.44% |
13.560 |
12.823 |
0.064 |
-5.29% |
0.064 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint32_t>/999
|
-5.40% |
696.521 |
658.903 |
0.042 |
-5.40% |
0.042 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint8_t>/10
|
-5.39% |
48.809 |
46.179 |
0.022 |
-0.48% |
0.022 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIRST_DIFF_LAMBDA/5001
|
-5.35% |
12.402 |
11.739 |
0.253 |
-3.70% |
0.253 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC1
|
-5.27% |
11.889 |
11.263 |
0.000 |
-0.01% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC1
|
-5.26% |
11.888 |
11.263 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC1
|
-5.26% |
11.888 |
11.263 |
0.000 |
-0.01% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC15
|
-5.15% |
127.647 |
121.076 |
0.004 |
-5.60% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint8_t_To_uint16_t_
|
-5.09% |
3625.683 |
3440.957 |
24.789 |
-5.30% |
24.789 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_BAND_LIN_EQ_LAMBDA/5001
|
-5.06% |
21.409 |
20.326 |
0.067 |
-2.28% |
0.067 |
|
External/SPEC/CINT2017rate/500.perlbench_r/500.perlbench_r
Profile
|
-5.04% |
153.193 |
145.467 |
0.247 |
-0.84% |
0.247 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_PRESSURE_CALC_RAW/44217
|
-4.87% |
507.656 |
482.938 |
3.353 |
-3.84% |
3.353 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint32_t>/256
|
-4.82% |
364.219 |
346.659 |
0.014 |
-4.81% |
0.014 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint16_t>/10
|
-4.78% |
65.707 |
62.568 |
0.004 |
-3.61% |
0.004 |
|
SingleSource/Benchmarks/Misc/revertBits
Profile
|
-4.72% |
0.641 |
0.611 |
0.000 |
-4.71% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_PRESSURE_CALC_LAMBDA/44217
|
-4.66% |
500.218 |
476.928 |
2.898 |
-4.33% |
2.898 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_FLOYD_DITHER/256
|
-4.63% |
1824.387 |
1739.865 |
4.571 |
0.36% |
4.571 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint16_t>/65
|
-4.62% |
95.117 |
90.727 |
0.006 |
-4.61% |
0.006 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_runtime_checks_fail<16, int>
|
-4.61% |
54.444 |
51.933 |
0.005 |
-4.60% |
0.005 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_runtime_checks_pass<16, int>
|
-4.60% |
54.439 |
51.935 |
0.003 |
-4.60% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC1
|
-4.56% |
13.140 |
12.541 |
0.008 |
5.47% |
0.008 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC2
|
-4.55% |
13.766 |
13.139 |
0.001 |
-0.11% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC7
|
-4.53% |
350.947 |
335.065 |
3.723 |
-5.54% |
3.723 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint32_t_To_uint16_t_
|
-4.49% |
9837.354 |
9395.328 |
26.616 |
-4.90% |
26.616 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC31
|
-4.47% |
70.084 |
66.949 |
0.004 |
-4.47% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC7
|
-4.46% |
70.080 |
66.953 |
0.002 |
-5.32% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC7
|
-4.46% |
70.082 |
66.957 |
0.003 |
-5.32% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_cond_load_autovec_int64_t_
|
-4.42% |
556010.681 |
531414.071 |
447.747 |
-3.84% |
447.747 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC64
|
-4.35% |
43.174 |
41.294 |
0.002 |
-4.36% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC63
|
-4.35% |
43.176 |
41.299 |
0.001 |
-4.61% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint8_t>/10
|
-4.32% |
54.284 |
51.939 |
0.190 |
0.00% |
0.190 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_ENERGY_CALC_RAW/171
|
-4.29% |
14.202 |
13.593 |
0.026 |
-4.55% |
0.026 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint64_t>/999
|
-4.27% |
3595.245 |
3441.672 |
0.263 |
-4.26% |
0.263 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint64_t_To_uint32_t_
|
-4.25% |
19390.528 |
18567.374 |
53.454 |
-3.76% |
53.454 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint64_t>/999
|
-4.24% |
1811.192 |
1734.333 |
0.062 |
-4.25% |
0.062 |
|
MicroBenchmarks/ImageProcessing/Blur/blur.test:BENCHMARK_boxBlurKernel/128
|
-4.20% |
436.419 |
418.079 |
4.204 |
-3.73% |
4.204 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC31
|
-4.13% |
93.981 |
90.099 |
0.005 |
-4.00% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint8_t_To_uint64_t_
|
-4.13% |
23381.729 |
22416.341 |
43.411 |
-4.55% |
43.411 |
|
MultiSource/Benchmarks/MiBench/consumer-typeset/consumer-typeset
Profile
|
-4.13% |
0.749 |
0.718 |
0.004 |
0.04% |
0.004 |
|
SingleSource/Benchmarks/Misc/flops-5
Profile
|
-4.10% |
2.020 |
1.938 |
0.001 |
-4.13% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint64_t>/256
|
-4.09% |
935.630 |
897.370 |
0.214 |
-4.08% |
0.214 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC32
|
-4.07% |
61.323 |
58.830 |
0.017 |
-4.06% |
0.017 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_ENERGY_CALC_LAMBDA/171
|
-4.05% |
14.197 |
13.622 |
0.017 |
-4.39% |
0.017 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC31
|
-4.05% |
61.946 |
59.440 |
0.002 |
-4.04% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC3
|
-4.01% |
15.644 |
15.017 |
0.001 |
-7.69% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_only_autovec_uint8_t_
|
-3.98% |
96175.835 |
92343.413 |
2.456 |
-3.97% |
2.456 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint32_t>/256
|
-3.97% |
221.532 |
212.740 |
0.008 |
-3.96% |
0.008 |
|
MultiSource/Benchmarks/VersaBench/ecbdes/ecbdes
Profile
|
-3.97% |
5.150 |
4.946 |
0.000 |
-3.76% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC32
|
-3.96% |
63.196 |
60.696 |
0.002 |
-3.96% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint64_t_To_uint8_t_
|
-3.91% |
19739.800 |
18968.889 |
29.644 |
-4.40% |
29.644 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint16_t_To_uint8_t_
|
-3.88% |
2873.718 |
2762.227 |
18.671 |
-4.03% |
18.671 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopWithReductionTC3
|
-3.84% |
16.268 |
15.644 |
0.042 |
-0.00% |
0.042 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_only_novec_uint8_t_
|
-3.81% |
420293.142 |
404293.806 |
19.866 |
2.12% |
19.866 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint8_t>/28
|
-3.79% |
88.448 |
85.096 |
0.003 |
3.79% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC32
|
-3.76% |
50.059 |
48.178 |
0.002 |
-3.74% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC2
|
-3.70% |
16.895 |
16.270 |
0.000 |
3.95% |
0.000 |
|
MultiSource/Applications/JM/lencod/lencod
Profile
|
-3.67% |
33.041 |
31.830 |
0.032 |
-2.18% |
0.032 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint64_t>/256
|
-3.66% |
514.413 |
495.596 |
0.017 |
-3.65% |
0.017 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC4
|
-3.65% |
25.654 |
24.717 |
0.037 |
1.28% |
0.037 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC64
|
-3.61% |
69.458 |
66.954 |
0.001 |
-3.60% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC64
|
-3.60% |
69.453 |
66.952 |
0.004 |
-3.61% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC63
|
-3.57% |
70.084 |
67.579 |
0.001 |
-3.57% |
0.001 |
|
SingleSource/Benchmarks/BenchmarkGame/n-body
Profile
|
-3.57% |
2.731 |
2.634 |
0.000 |
21.71% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC63
|
-3.57% |
70.079 |
67.577 |
0.003 |
-3.59% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC2
|
-3.57% |
16.895 |
16.292 |
0.032 |
0.13% |
0.032 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint16_t_To_uint32_t_
|
-3.53% |
11238.973 |
10842.696 |
53.611 |
-4.41% |
53.611 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint16_t>/999
|
-3.45% |
1013.804 |
978.799 |
0.049 |
-3.46% |
0.049 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopWithReductionTC4
|
-3.45% |
18.146 |
17.520 |
0.000 |
-0.00% |
0.000 |
|
MultiSource/Benchmarks/Rodinia/pathfinder/pathfinder
Profile
|
-3.42% |
1.266 |
1.223 |
0.010 |
-2.79% |
0.010 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_ENERGY_CALC_LAMBDA/5001
|
-3.42% |
434.370 |
419.501 |
3.442 |
-4.23% |
3.442 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC7
|
-3.34% |
37.544 |
36.291 |
0.002 |
-0.01% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint32_t>/65
|
-3.34% |
93.858 |
90.725 |
0.005 |
-3.98% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC63
|
-3.30% |
1731.977 |
1674.876 |
21.759 |
-3.58% |
21.759 |
|
External/SPEC/CFP2017rate/511.povray_r/511.povray_r
Profile
|
-3.29% |
34.511 |
33.375 |
0.030 |
-1.22% |
0.030 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<16, LessThanZero, None>
|
-3.26% |
8322.464 |
8051.464 |
97.459 |
-1.83% |
97.459 |
|
SingleSource/Benchmarks/Shootout/Shootout-lists
Profile
|
-3.21% |
11.316 |
10.952 |
0.001 |
-3.18% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint16_t>/999
|
-3.17% |
515.013 |
498.712 |
0.014 |
-3.17% |
0.014 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1BigLoopWithReductionTC1
|
-3.13% |
20.024 |
19.397 |
0.001 |
-3.14% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC31
|
-3.13% |
60.069 |
58.191 |
0.003 |
-3.46% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchVecWithRuntimeChecks4PointersDBeforeA/1000
|
-3.09% |
5020760.173 |
4865688.910 |
265.603 |
-3.07% |
265.603 |
|
External/SPEC/CINT2017rate/531.deepsjeng_r/531.deepsjeng_r
Profile
|
-2.97% |
267.534 |
259.593 |
0.401 |
-0.20% |
0.401 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_ENERGY_CALC_RAW/5001
|
-2.96% |
433.759 |
420.937 |
2.679 |
-1.82% |
2.679 |
|
MultiSource/Benchmarks/BitBench/drop3/drop3
Profile
|
-2.89% |
0.731 |
0.710 |
0.001 |
-2.82% |
0.001 |
|
External/SPEC/CFP2017rate/519.lbm_r/519.lbm_r
Profile
|
-2.88% |
199.805 |
194.041 |
1.739 |
-3.31% |
1.739 |
|
MicroBenchmarks/ImageProcessing/Dilate/Dilate.test:BENCHMARK_DILATE/512
|
-2.88% |
3606.986 |
3503.051 |
36.979 |
-2.26% |
36.979 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_acosf_novec_float_
|
-2.82% |
844.663 |
820.862 |
0.027 |
-2.82% |
0.027 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_acosf_autovec_float_
|
-2.80% |
844.623 |
820.957 |
0.027 |
-2.82% |
0.027 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC1
|
-2.78% |
22.527 |
21.900 |
0.001 |
-2.78% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC1
|
-2.77% |
22.525 |
21.902 |
0.003 |
-2.77% |
0.003 |
|
MultiSource/Benchmarks/TSVC/ControlLoops-flt/ControlLoops-flt
Profile
|
-2.74% |
5.520 |
5.369 |
0.011 |
-1.44% |
0.011 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C/CoMD/CoMD
Profile
|
-2.73% |
9.908 |
9.637 |
0.002 |
-2.65% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC31
|
-2.64% |
23.778 |
23.152 |
0.002 |
-5.13% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC32
|
-2.63% |
23.777 |
23.151 |
0.001 |
-5.14% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC31
|
-2.63% |
23.777 |
23.152 |
0.005 |
-5.13% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopWithReductionTC7
|
-2.63% |
23.778 |
23.153 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC32
|
-2.63% |
23.777 |
23.152 |
0.001 |
-5.12% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC63
|
-2.61% |
120.142 |
117.004 |
0.007 |
-2.61% |
0.007 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<64, GreaterThanZero, None>
|
-2.58% |
3044.406 |
2965.771 |
2.093 |
1.78% |
2.093 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint8_t_To_uint32_t_
|
-2.55% |
7076.494 |
6895.711 |
2.421 |
-2.57% |
2.421 |
|
SingleSource/Benchmarks/Misc-C++/oopack_v1p8
Profile
|
-2.51% |
0.479 |
0.467 |
0.000 |
-9.93% |
0.000 |
|
External/SPEC/CFP2017rate/544.nab_r/544.nab_r
Profile
|
-2.49% |
472.233 |
460.471 |
0.201 |
-3.64% |
0.201 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_ENERGY_CALC_LAMBDA/44217
|
-2.49% |
4356.452 |
4248.181 |
6.558 |
-1.76% |
6.558 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint64_t>/10
|
-2.46% |
56.449 |
55.062 |
0.002 |
-0.06% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint16_t_To_uint8_t_
|
-2.45% |
4512.093 |
4401.428 |
12.111 |
-2.56% |
12.111 |
|
MultiSource/Benchmarks/mafft/pairlocalalign
Profile
|
-2.44% |
93.966 |
91.673 |
0.346 |
-2.54% |
0.346 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_FLOYD_DITHER/128
|
-2.44% |
437.971 |
427.303 |
2.376 |
-2.77% |
2.376 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<63, LessThanZero, First>
|
-2.41% |
1640.117 |
1600.645 |
0.619 |
-0.04% |
0.619 |
|
MultiSource/Applications/ClamAV/clamscan
Profile
|
-2.40% |
0.497 |
0.485 |
0.004 |
-0.95% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint16_t>/16
|
-2.34% |
53.822 |
52.561 |
0.006 |
-1.26% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC63
|
-2.34% |
107.005 |
104.499 |
0.001 |
-2.34% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchVecWithRuntimeChecks4PointersDBeforeA/32
|
-2.33% |
166194.770 |
162319.631 |
95.837 |
-2.34% |
95.837 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<63, GreaterThanZero, None>
|
-2.33% |
4742.197 |
4631.649 |
9.039 |
0.08% |
9.039 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_FLOYD_DITHER/512
|
-2.33% |
6653.191 |
6498.315 |
22.392 |
-2.21% |
22.392 |
|
SingleSource/Benchmarks/Misc-C++/Large/ray
Profile
|
-2.29% |
12.108 |
11.831 |
0.000 |
-2.23% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC64
|
-2.25% |
111.388 |
108.884 |
0.051 |
-2.24% |
0.051 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint16_t>/10
|
-2.24% |
46.217 |
45.181 |
0.005 |
-0.99% |
0.005 |
|
SingleSource/Benchmarks/Shootout/Shootout-matrix
Profile
|
-2.23% |
3.864 |
3.777 |
0.000 |
-2.22% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint64_t>/51
|
-2.19% |
229.014 |
224.006 |
0.005 |
-2.18% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC63
|
-2.19% |
130.497 |
127.644 |
0.008 |
-1.94% |
0.008 |
|
SingleSource/Benchmarks/Misc/flops-1
Profile
|
-2.17% |
9.002 |
8.807 |
0.000 |
-2.15% |
0.000 |
|
SingleSource/Benchmarks/Misc/ReedSolomon
Profile
|
-2.17% |
20.760 |
20.310 |
0.001 |
-2.34% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopTC16
|
-2.15% |
277.843 |
271.874 |
1.937 |
-1.57% |
1.937 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint8_t>/51
|
-2.14% |
228.261 |
223.369 |
0.008 |
8.82% |
0.008 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC8
|
-2.11% |
26.208 |
25.654 |
0.001 |
-4.68% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC128
|
-2.09% |
119.521 |
117.022 |
0.002 |
-2.09% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC128
|
-2.09% |
119.512 |
117.013 |
0.005 |
-2.10% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC127
|
-2.09% |
120.143 |
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:benchForLoopWithReductionAutoVecTC31
|
-2.05% |
30.660 |
30.033 |
0.001 |
-3.71% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC32
|
-2.04% |
30.658 |
30.033 |
0.001 |
-4.01% |
0.001 |
|
MultiSource/Applications/sgefa/sgefa
Profile
|
-2.03% |
0.577 |
0.565 |
0.003 |
-1.46% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopWithReductionTC63
|
-2.03% |
57.481 |
56.316 |
0.004 |
1.11% |
0.004 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<64, EqZero, None>
|
-1.95% |
2955.513 |
2897.865 |
3.027 |
-1.07% |
3.027 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint64_t>/28
|
-1.92% |
87.419 |
85.740 |
0.013 |
-0.02% |
0.013 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint16_t>/256
|
-1.84% |
272.844 |
267.824 |
0.022 |
-1.84% |
0.022 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_EOS_RAW/171
|
-1.84% |
0.872 |
0.856 |
0.000 |
-1.69% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_EOS_LAMBDA/171
|
-1.83% |
0.872 |
0.856 |
0.001 |
-1.71% |
0.001 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C/SimpleMOC/SimpleMOC
Profile
|
-1.83% |
10.453 |
10.262 |
0.037 |
-1.37% |
0.037 |
|
External/SPEC/CINT2017rate/523.xalancbmk_r/523.xalancbmk_r
Profile
|
-1.82% |
244.094 |
239.647 |
0.466 |
-0.54% |
0.466 |
|
MultiSource/Benchmarks/Fhourstones-3.1/fhourstones3.1
Profile
|
-1.81% |
4.047 |
3.974 |
0.007 |
0.05% |
0.007 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC15
|
-1.78% |
70.079 |
68.833 |
0.002 |
0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_csa_with_in_loop_arith_novec_int64_t_
|
-1.70% |
1029274.049 |
1011764.347 |
519.522 |
-1.59% |
519.522 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint64_t>/51
|
-1.69% |
148.303 |
145.792 |
0.004 |
-1.70% |
0.004 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_INT_PREDICT_RAW/171
|
-1.67% |
6.916 |
6.801 |
0.001 |
-1.79% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_erf_autovec_double_
|
-1.67% |
889.072 |
874.267 |
0.398 |
-1.67% |
0.398 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_erf_novec_double_
|
-1.65% |
889.050 |
874.389 |
0.222 |
-1.68% |
0.222 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_INT_PREDICT_LAMBDA/171
|
-1.63% |
6.926 |
6.813 |
0.009 |
-1.62% |
0.009 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<3, GreaterThanZero, Mid>
|
-1.62% |
37984.197 |
37369.389 |
23.863 |
-0.10% |
23.863 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<7, GreaterThanZero, Mid>
|
-1.59% |
20468.782 |
20142.540 |
2.128 |
-0.01% |
2.128 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_cond_load_novec_uint8_t_
|
-1.58% |
299881.938 |
295133.315 |
39.025 |
-6.04% |
39.025 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_csa_with_cond_arith_novec_int64_t_
|
-1.58% |
744375.706 |
732595.762 |
1091.713 |
-1.63% |
1091.713 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, GreaterThanZero, Mid>
|
-1.58% |
31937.240 |
31433.260 |
18.277 |
-0.02% |
18.277 |
|
SingleSource/Benchmarks/Misc/mandel-2
Profile
|
-1.57% |
2.536 |
2.496 |
0.000 |
-1.54% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint32_t_To_uint64_t_
|
-1.56% |
26244.782 |
25835.616 |
46.527 |
-1.69% |
46.527 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC8
|
-1.55% |
41.923 |
41.272 |
0.007 |
1.45% |
0.007 |
|
MultiSource/Benchmarks/FreeBench/fourinarow/fourinarow
Profile
|
-1.54% |
0.654 |
0.644 |
0.000 |
-1.05% |
0.000 |
|
MultiSource/Benchmarks/Fhourstones/fhourstones
Profile
|
-1.54% |
10.921 |
10.753 |
0.041 |
-0.14% |
0.041 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<6, LessThanZero, Mid>
|
-1.50% |
23838.985 |
23482.070 |
2.257 |
-0.36% |
2.257 |
|
MultiSource/Benchmarks/Olden/health/health
Profile
|
-1.47% |
1.594 |
1.571 |
0.002 |
-1.29% |
0.002 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C++/PENNANT/PENNANT
Profile
|
-1.47% |
4.801 |
4.730 |
0.016 |
-1.80% |
0.016 |
|
External/SPEC/CINT2017rate/525.x264_r/525.x264_r
Profile
|
-1.42% |
129.735 |
127.898 |
0.112 |
-1.20% |
0.112 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopWithReductionTC31
|
-1.41% |
44.427 |
43.800 |
0.001 |
1.43% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_csa_with_cond_arith_novec_uint8_t_
|
-1.40% |
336628.758 |
331919.650 |
1601.257 |
-3.43% |
1601.257 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_csa_with_cond_arith_autovec_int64_t_
|
-1.39% |
744025.450 |
733711.266 |
758.431 |
-1.51% |
758.431 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint16_t_To_uint32_t_
|
-1.31% |
13485.113 |
13307.866 |
23.534 |
-1.30% |
23.534 |
|
MultiSource/Benchmarks/TSVC/ControlLoops-dbl/ControlLoops-dbl
Profile
|
-1.31% |
10.882 |
10.740 |
0.018 |
-2.53% |
0.018 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, LessThanZero, Mid>
|
-1.27% |
31897.455 |
31492.105 |
137.557 |
-0.91% |
137.557 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC127
|
-1.27% |
197.109 |
194.607 |
0.008 |
-1.26% |
0.008 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC128
|
-1.27% |
198.360 |
195.843 |
0.006 |
-1.27% |
0.006 |
|
MicroBenchmarks/ImageProcessing/Blur/blur.test:BENCHMARK_boxBlurKernel/512
|
-1.18% |
6586.011 |
6508.393 |
24.322 |
-1.59% |
24.322 |
|
MultiSource/Benchmarks/nbench/nbench
Profile
|
-1.17% |
6.105 |
6.034 |
0.001 |
-1.52% |
0.001 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<63, EqZero, Mid>
|
-1.17% |
4117.945 |
4069.800 |
1.669 |
-0.02% |
1.669 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<6, GreaterThanZero, First>
|
-1.17% |
16199.791 |
16011.015 |
1.869 |
0.00% |
1.869 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, GreaterThanZero, Last>
|
-1.15% |
35662.767 |
35250.992 |
2.614 |
0.00% |
2.614 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint32_t>/51
|
-1.07% |
118.271 |
117.002 |
0.005 |
-1.07% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint8_t>/28
|
-1.07% |
138.512 |
137.031 |
0.009 |
5.78% |
0.009 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint32_t>/10
|
-1.05% |
56.957 |
56.357 |
0.035 |
-1.21% |
0.035 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<31, LessThanZero, Mid>
|
-1.05% |
7843.064 |
7760.630 |
12.084 |
-0.00% |
12.084 |
|
SingleSource/Benchmarks/Misc/fbench
Profile
|
-1.01% |
5.685 |
5.627 |
0.000 |
-2.32% |
0.000 |