|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_HYDRO_2D_LAMBDA/44217
|
-61.49% |
87244.656 |
33595.772 |
13585.381 |
-63.05% |
13585.381 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_INT_PREDICT_LAMBDA/44217
|
-58.85% |
19341.847 |
7958.615 |
112.160 |
-4.55% |
112.160 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_HYDRO_2D_LAMBDA/5001
|
-55.85% |
8589.517 |
3792.420 |
1369.217 |
-58.39% |
1369.217 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint64_t_To_uint32_t_
|
-52.26% |
35454.102 |
16924.701 |
97.322 |
-52.07% |
97.322 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint64_t_To_uint16_t_
|
-51.72% |
35981.778 |
17372.024 |
134.201 |
-51.31% |
134.201 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C/miniGMG/miniGMG
Profile
|
-51.35% |
9.267 |
4.509 |
0.077 |
-50.94% |
0.077 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint64_t_To_uint8_t_
|
-49.92% |
37266.960 |
18664.497 |
13.686 |
-49.64% |
13.686 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_DISC_ORD_LAMBDA/44217
|
-48.27% |
13213.286 |
6835.624 |
2094.030 |
-51.36% |
2094.030 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_DIFF_PREDICT_LAMBDA/44217
|
-44.22% |
24197.353 |
13497.103 |
321.017 |
-41.58% |
321.017 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint16_t_To_uint64_t_
|
-44.13% |
18691.648 |
10443.109 |
4.904 |
-44.08% |
4.904 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_DIFF_PREDICT_RAW/44217
|
-42.22% |
23371.316 |
13503.554 |
315.584 |
-42.04% |
315.584 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_DIFF_PREDICT_LAMBDA/5001
|
-40.90% |
2566.104 |
1516.579 |
25.576 |
-39.56% |
25.576 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint8_t_To_uint64_t_
|
-40.90% |
17784.339 |
10510.631 |
10.817 |
-40.95% |
10.817 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_DIFF_PREDICT_RAW/5001
|
-40.79% |
2557.886 |
1514.510 |
22.449 |
-41.18% |
22.449 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint64_t_To_uint32_t_
|
-40.72% |
38168.473 |
22625.975 |
21.204 |
-40.70% |
21.204 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIRST_DIFF_LAMBDA/44217
|
-39.14% |
169.505 |
103.165 |
0.154 |
-28.76% |
0.154 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/64
|
-36.67% |
6181.109 |
3914.750 |
2.037 |
-36.68% |
2.037 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/32
|
-36.66% |
1396.330 |
884.427 |
0.044 |
-36.65% |
0.044 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/16
|
-36.54% |
279.497 |
177.359 |
0.014 |
-36.54% |
0.014 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/256
|
-36.19% |
107088.000 |
68337.800 |
74.925 |
-36.22% |
74.925 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/128
|
-36.06% |
26260.736 |
16791.136 |
7.416 |
-36.09% |
7.416 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint32_t_To_uint64_t_
|
-36.03% |
22697.467 |
14520.020 |
855.165 |
-36.11% |
855.165 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint64_t_To_uint8_t_
|
-34.91% |
30382.895 |
19775.829 |
16.782 |
-34.32% |
16.782 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint64_t_To_uint16_t_
|
-34.31% |
29114.930 |
19125.098 |
16.500 |
-33.94% |
16.500 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_with_cond_arith_novec_int32_t_
|
-31.04% |
885400.208 |
610589.930 |
1517.739 |
-17.51% |
1517.739 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_with_cond_arith_novec_uint8_t_
|
-29.63% |
870471.235 |
612537.647 |
112.079 |
-17.86% |
112.079 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint64_t_To_uint16_t_
|
-28.60% |
25917.626 |
18503.930 |
46.991 |
-28.55% |
46.991 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint32_t_To_uint8_t_
|
-28.20% |
13523.458 |
9709.553 |
39.635 |
-27.91% |
39.635 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC128
|
-27.95% |
1292.223 |
931.031 |
6.701 |
-27.98% |
6.701 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_PIC_2D_LAMBDA/44217
|
-27.76% |
11908.086 |
8601.887 |
598.439 |
-21.54% |
598.439 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC128
|
-27.30% |
558.760 |
406.218 |
0.032 |
-27.14% |
0.032 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC64
|
-27.27% |
654.123 |
475.773 |
3.445 |
-27.21% |
3.445 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC32
|
-27.10% |
334.637 |
243.956 |
1.574 |
-26.94% |
1.574 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC16
|
-26.59% |
174.339 |
127.982 |
0.516 |
-26.36% |
0.516 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_FLOYD_DITHER/512
|
-26.57% |
8849.688 |
6498.315 |
22.392 |
-2.21% |
22.392 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC64
|
-26.12% |
292.202 |
215.890 |
0.181 |
-26.02% |
0.181 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint64_t_To_uint8_t_
|
-24.89% |
27207.545 |
20436.409 |
41.080 |
-24.93% |
41.080 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_FLOYD_DITHER/128
|
-24.88% |
568.795 |
427.303 |
2.376 |
-2.77% |
2.376 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIRST_DIFF_RAW/44217
|
-24.69% |
135.903 |
102.347 |
0.764 |
-28.17% |
0.764 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_FLOYD_DITHER/256
|
-24.35% |
2299.866 |
1739.865 |
4.571 |
0.36% |
4.571 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC32
|
-24.03% |
158.964 |
120.762 |
0.010 |
-23.99% |
0.010 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIRST_SUM_LAMBDA/44217
|
-23.78% |
179.001 |
136.438 |
0.333 |
-18.34% |
0.333 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC128
|
-23.31% |
603.893 |
463.126 |
0.056 |
-23.32% |
0.056 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_PIC_2D_LAMBDA/5001
|
-23.31% |
1182.572 |
906.917 |
36.404 |
-17.96% |
36.404 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC128
|
-23.31% |
603.912 |
463.159 |
0.017 |
-23.31% |
0.017 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint16_t_To_uint64_t_
|
-22.83% |
13430.447 |
10364.817 |
0.784 |
-21.53% |
0.784 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC64
|
-22.56% |
313.511 |
242.793 |
0.012 |
-22.56% |
0.012 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC64
|
-22.55% |
313.501 |
242.795 |
0.007 |
-22.55% |
0.007 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint8_t_To_uint32_t_
|
-22.14% |
6623.734 |
5156.945 |
6.233 |
-21.65% |
6.233 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC127
|
-21.96% |
615.151 |
480.045 |
0.013 |
-21.97% |
0.013 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC127
|
-21.96% |
615.147 |
480.051 |
0.017 |
-21.97% |
0.017 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint16_t_To_uint32_t_
|
-21.60% |
7109.509 |
5573.840 |
1.238 |
-21.51% |
1.238 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_only_autovec_uint8_t_
|
-21.39% |
182410.498 |
143399.389 |
52.530 |
-21.36% |
52.530 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC32
|
-21.20% |
168.326 |
132.643 |
0.011 |
-21.20% |
0.011 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC32
|
-21.19% |
168.323 |
132.648 |
0.010 |
-21.20% |
0.010 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint8_t>/51
|
-21.05% |
193.363 |
152.662 |
0.004 |
-1.13% |
0.004 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_PIC_2D_RAW/44217
|
-21.02% |
11224.597 |
8865.216 |
886.976 |
-20.96% |
886.976 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_INT_PREDICT_RAW/5001
|
-20.84% |
1143.662 |
905.298 |
8.645 |
-0.89% |
8.645 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC16
|
-20.66% |
92.282 |
73.213 |
0.005 |
-20.66% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC127
|
-20.27% |
274.614 |
218.953 |
0.525 |
-20.51% |
0.525 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC128
|
-20.17% |
273.370 |
218.240 |
1.312 |
-20.57% |
1.312 |
|
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
|
-20.04% |
324.773 |
259.684 |
0.011 |
-20.04% |
0.011 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC63
|
-20.04% |
324.764 |
259.680 |
0.011 |
-20.05% |
0.011 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC127
|
-19.67% |
640.894 |
514.823 |
0.229 |
-19.62% |
0.229 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint32_t_To_uint8_t_
|
-19.30% |
13898.758 |
11215.997 |
91.588 |
-19.31% |
91.588 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint16_t_To_uint8_t_
|
-19.12% |
3818.664 |
3088.474 |
0.232 |
-19.11% |
0.232 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC16
|
-18.96% |
95.739 |
77.586 |
0.004 |
-18.96% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC16
|
-18.96% |
95.736 |
77.587 |
0.005 |
-18.96% |
0.005 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_INT_PREDICT_LAMBDA/5001
|
-18.82% |
1123.715 |
912.208 |
1.812 |
0.82% |
1.812 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, EqZero, None>
|
-18.75% |
20511.854 |
16665.852 |
0.686 |
-18.75% |
0.686 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint64_t_To_uint32_t_
|
-18.70% |
27123.944 |
22051.970 |
22.431 |
-18.48% |
22.431 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint32_t_To_uint16_t_
|
-18.69% |
13809.477 |
11228.848 |
8.145 |
-18.67% |
8.145 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC8
|
-18.62% |
58.821 |
47.869 |
0.002 |
-18.54% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC16
|
-18.48% |
93.235 |
76.006 |
0.026 |
-18.38% |
0.026 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC63
|
-18.39% |
150.149 |
122.542 |
2.900 |
-18.26% |
2.900 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC32
|
-18.17% |
161.428 |
132.097 |
0.113 |
-18.15% |
0.113 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, EqZero, Last>
|
-18.17% |
14103.122 |
11540.635 |
0.102 |
-18.18% |
0.102 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC64
|
-18.15% |
148.565 |
121.607 |
2.052 |
-18.18% |
2.052 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC4
|
-17.87% |
17.522 |
14.390 |
0.031 |
-17.87% |
0.031 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC64
|
-17.76% |
297.848 |
244.945 |
0.031 |
-17.72% |
0.031 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIRST_SUM_RAW/44217
|
-17.67% |
164.792 |
135.680 |
0.602 |
-18.43% |
0.602 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC128
|
-17.66% |
570.777 |
469.993 |
0.285 |
-17.63% |
0.285 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC8
|
-17.63% |
23.150 |
19.070 |
0.097 |
-17.64% |
0.097 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC7
|
-17.14% |
28.697 |
23.779 |
0.059 |
-17.03% |
0.059 |
|
MultiSource/Benchmarks/TSVC/LinearDependence-flt/LinearDependence-flt
Profile
|
-17.13% |
16.387 |
13.579 |
0.829 |
-1.77% |
0.829 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint16_t>/28
|
-17.08% |
80.883 |
67.066 |
0.010 |
-1.80% |
0.010 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint32_t_To_uint16_t_
|
-17.01% |
10117.252 |
8396.638 |
559.781 |
-15.23% |
559.781 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint8_t>/28
|
-16.99% |
121.397 |
100.775 |
0.035 |
-2.11% |
0.035 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC31
|
-16.72% |
179.583 |
149.550 |
0.016 |
-16.72% |
0.016 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC31
|
-16.72% |
179.580 |
149.549 |
0.003 |
-16.73% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint8_t>/51
|
-16.69% |
110.295 |
91.883 |
0.008 |
-0.66% |
0.008 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint16_t>/28
|
-16.56% |
119.541 |
99.749 |
0.081 |
-0.14% |
0.081 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_HYDRO_1D_RAW/171
|
-15.91% |
0.442 |
0.372 |
0.000 |
-15.84% |
0.000 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, EqZero, None>
|
-15.89% |
16024.050 |
13477.442 |
13.643 |
-15.89% |
13.643 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_HYDRO_1D_LAMBDA/171
|
-15.88% |
0.442 |
0.372 |
0.000 |
-15.87% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC8
|
-15.80% |
59.448 |
50.054 |
0.003 |
-15.80% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC8
|
-15.79% |
59.446 |
50.060 |
0.001 |
-15.80% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC8
|
-15.79% |
23.777 |
20.022 |
0.001 |
-15.80% |
0.001 |
|
SingleSource/Benchmarks/Adobe-C++/loop_unroll
Profile
|
-15.71% |
2.874 |
2.422 |
0.002 |
-22.04% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint16_t_To_uint32_t_
|
-15.67% |
7462.513 |
6293.361 |
0.689 |
-15.66% |
0.689 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint8_t_To_uint64_t_
|
-15.60% |
12917.835 |
10902.790 |
33.328 |
-16.55% |
33.328 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint64_t_To_uint8_t_
|
-15.58% |
22069.618 |
18632.040 |
44.707 |
-15.49% |
44.707 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_VOL3D_CALC_RAW/2
|
-15.49% |
8.756 |
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_
|
-15.41% |
10650.072 |
9009.341 |
28.483 |
-14.97% |
28.483 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_no_runtime_checks_needed<16, int>
|
-15.39% |
24.403 |
20.648 |
0.001 |
-15.39% |
0.001 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, EqZero, Mid>
|
-15.38% |
16666.984 |
14103.064 |
1.147 |
-15.38% |
1.147 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, EqZero, Last>
|
-15.38% |
16667.596 |
14104.026 |
1.051 |
-15.38% |
1.051 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, EqZero, First>
|
-15.36% |
16670.745 |
14109.648 |
0.219 |
-15.36% |
0.219 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_PIC_2D_RAW/5001
|
-15.23% |
1098.080 |
930.866 |
19.437 |
-13.68% |
19.437 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC32
|
-15.20% |
85.742 |
72.709 |
1.692 |
-14.79% |
1.692 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint64_t_To_uint16_t_
|
-15.02% |
19319.733 |
16417.044 |
161.523 |
-13.52% |
161.523 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC4
|
-15.00% |
113.464 |
96.449 |
1.820 |
-14.71% |
1.820 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC127
|
-14.92% |
605.758 |
515.388 |
0.026 |
-14.92% |
0.026 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIRST_SUM_LAMBDA/5001
|
-14.85% |
20.500 |
17.457 |
0.253 |
-0.86% |
0.253 |
|
External/SPEC/CFP2017rate/508.namd_r/508.namd_r
Profile
|
-14.71% |
226.840 |
193.461 |
0.383 |
-13.47% |
0.383 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC128
|
-14.69% |
1103.385 |
941.272 |
0.092 |
-14.69% |
0.092 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/64
|
-14.64% |
1915.043 |
1634.701 |
1.558 |
-14.56% |
1.558 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC64
|
-14.57% |
562.568 |
480.587 |
0.027 |
-14.53% |
0.027 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint8_t_To_uint16_t_
|
-14.54% |
3757.281 |
3210.866 |
8.115 |
-14.53% |
8.115 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC127
|
-14.52% |
1095.340 |
936.266 |
0.089 |
-14.52% |
0.089 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint16_t>/51
|
-14.46% |
106.194 |
90.840 |
0.025 |
0.09% |
0.025 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/256
|
-14.44% |
31443.532 |
26902.931 |
25.015 |
-14.46% |
25.015 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/32
|
-14.43% |
473.022 |
404.751 |
0.073 |
-14.43% |
0.073 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_VOL3D_CALC_LAMBDA/0
|
-14.39% |
1279.904 |
1095.744 |
1.057 |
-13.56% |
1.057 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_with_cond_arith_novec_int64_t_
|
-14.37% |
794604.635 |
680409.874 |
909.389 |
-13.66% |
909.389 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC32
|
-14.34% |
292.208 |
250.297 |
0.008 |
-14.28% |
0.008 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint32_t_To_uint16_t_
|
-14.30% |
12829.628 |
10995.106 |
10.963 |
-14.35% |
10.963 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint32_t_To_uint64_t_
|
-14.23% |
18049.868 |
15481.634 |
766.852 |
-9.97% |
766.852 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC63
|
-14.23% |
554.451 |
475.566 |
0.029 |
-14.27% |
0.029 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/128
|
-14.22% |
7916.910 |
6791.502 |
3.463 |
-14.22% |
3.463 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/16
|
-14.21% |
115.458 |
99.053 |
0.009 |
-14.21% |
0.009 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_VOL3D_CALC_RAW/0
|
-14.20% |
1276.783 |
1095.453 |
1.106 |
-13.42% |
1.106 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC16
|
-14.08% |
33.164 |
28.496 |
0.033 |
-14.08% |
0.033 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_with_cond_arith_autovec_int64_t_
|
-14.05% |
791630.726 |
680423.413 |
1653.587 |
-14.05% |
1653.587 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC16
|
-13.94% |
157.053 |
135.153 |
0.008 |
-13.90% |
0.008 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_PIC_1D_LAMBDA/5001
|
-13.91% |
355.112 |
305.722 |
18.636 |
-13.38% |
18.636 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_INT_PREDICT_RAW/44217
|
-13.88% |
9295.253 |
8005.064 |
94.646 |
-11.54% |
94.646 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC1
|
-13.86% |
51.936 |
44.736 |
0.002 |
-13.86% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC3
|
-13.86% |
51.936 |
44.736 |
0.002 |
-13.86% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC2
|
-13.86% |
51.938 |
44.738 |
0.002 |
-13.86% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC4
|
-13.86% |
51.935 |
44.738 |
0.001 |
-13.86% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC7
|
-13.86% |
51.939 |
44.741 |
0.000 |
-13.85% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC8
|
-13.85% |
51.932 |
44.739 |
0.001 |
-13.86% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC31
|
-13.66% |
284.100 |
245.282 |
0.008 |
-13.66% |
0.008 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, EqZero, First>
|
-13.63% |
14103.728 |
12181.684 |
0.662 |
-13.62% |
0.662 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, EqZero, Mid>
|
-13.62% |
14103.566 |
12182.193 |
12.820 |
-13.62% |
12.820 |
|
MultiSource/Benchmarks/McCat/08-main/main
Profile
|
-13.48% |
0.155 |
0.134 |
0.000 |
-0.53% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint16_t>/16
|
-13.42% |
60.707 |
52.561 |
0.006 |
-1.26% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC63
|
-13.28% |
374.292 |
324.597 |
0.092 |
-13.31% |
0.092 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC8
|
-13.27% |
89.468 |
77.592 |
0.006 |
-13.21% |
0.006 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_VOL3D_CALC_LAMBDA/1
|
-13.17% |
260.192 |
225.930 |
0.155 |
-13.16% |
0.155 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_VOL3D_CALC_RAW/1
|
-13.13% |
260.052 |
225.905 |
0.181 |
-13.16% |
0.181 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC128
|
-13.07% |
81.340 |
70.706 |
0.004 |
-13.08% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint8_t_To_uint16_t_
|
-12.97% |
4542.384 |
3953.145 |
0.316 |
-12.96% |
0.316 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC63
|
-12.87% |
332.894 |
290.052 |
0.010 |
-12.85% |
0.010 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC15
|
-12.85% |
44.516 |
38.793 |
0.001 |
-12.69% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint32_t_To_uint8_t_
|
-12.79% |
11018.299 |
9609.435 |
35.708 |
-13.66% |
35.708 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint16_t>/16
|
-12.61% |
81.970 |
71.631 |
0.078 |
-0.39% |
0.078 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC15
|
-12.61% |
148.932 |
130.153 |
0.004 |
-12.54% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint8_t>/16
|
-12.57% |
83.855 |
73.315 |
0.016 |
-2.83% |
0.016 |
|
MultiSource/Benchmarks/MiBench/security-rijndael/security-rijndael
Profile
|
-12.53% |
0.335 |
0.293 |
0.000 |
-12.34% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint8_t>/28
|
-12.46% |
76.484 |
66.951 |
0.002 |
-0.93% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint16_t_To_uint8_t_
|
-12.43% |
4743.629 |
4153.868 |
0.345 |
-12.42% |
0.345 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC31
|
-12.40% |
87.102 |
76.297 |
0.018 |
-11.40% |
0.018 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC4
|
-12.36% |
55.692 |
48.808 |
0.001 |
-12.31% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC4
|
-12.12% |
41.300 |
36.292 |
0.000 |
-12.13% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC4
|
-12.12% |
41.299 |
36.294 |
0.001 |
-12.12% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC16
|
-11.83% |
51.936 |
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:benchForIC4VW1BigLoopWithReductionTC15
|
-11.71% |
107.007 |
94.480 |
0.005 |
-11.71% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC15
|
-11.70% |
107.003 |
94.484 |
0.006 |
-11.70% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC2
|
-11.48% |
38.172 |
33.790 |
0.001 |
-11.48% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC15
|
-11.45% |
51.938 |
45.989 |
0.004 |
-11.46% |
0.004 |
|
MicroBenchmarks/ImageProcessing/Blur/blur.test:BENCHMARK_boxBlurKernel/1024
|
-11.18% |
30143.777 |
26772.869 |
48.819 |
-11.20% |
48.819 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC4
|
-11.12% |
22.528 |
20.024 |
0.000 |
-11.11% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC3
|
-11.11% |
22.527 |
20.024 |
0.001 |
-11.11% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC4
|
-11.11% |
22.525 |
20.023 |
0.001 |
-11.11% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC32
|
-11.01% |
53.188 |
47.330 |
0.049 |
-11.02% |
0.049 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC7
|
-10.79% |
81.355 |
72.580 |
0.004 |
-10.74% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC4
|
-10.53% |
23.776 |
21.273 |
0.002 |
-10.54% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC64
|
-10.46% |
53.811 |
48.181 |
0.002 |
-10.47% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC16
|
-10.35% |
36.292 |
32.538 |
0.000 |
-10.35% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_DIFF_PREDICT_LAMBDA/171
|
-10.13% |
12.366 |
11.113 |
0.035 |
-7.28% |
0.035 |
|
SingleSource/Benchmarks/Misc-C++/oopack_v1p8
Profile
|
-10.01% |
0.519 |
0.467 |
0.000 |
-9.93% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIRST_DIFF_LAMBDA/5001
|
-10.00% |
13.043 |
11.739 |
0.253 |
-3.70% |
0.253 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint8_t>/999
|
-9.97% |
320.426 |
288.491 |
0.006 |
-0.70% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint8_t_To_uint16_t_
|
-9.97% |
5849.533 |
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
|
-9.75% |
25.653 |
23.151 |
0.001 |
-9.77% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint64_t_To_uint32_t_
|
-9.73% |
18071.460 |
16313.462 |
490.343 |
-8.42% |
490.343 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC31
|
-9.72% |
196.486 |
177.386 |
0.009 |
-9.71% |
0.009 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC127
|
-9.66% |
101.821 |
91.986 |
0.002 |
-9.71% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_only_autovec_int64_t_
|
-9.63% |
333247.916 |
301151.383 |
182.018 |
-9.64% |
182.018 |
|
MultiSource/Benchmarks/McCat/12-IOtest/iotest
Profile
|
-9.57% |
1.875 |
1.695 |
0.021 |
-7.10% |
0.021 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC7
|
-9.53% |
26.282 |
23.776 |
0.002 |
-9.53% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC7
|
-9.53% |
26.282 |
23.777 |
0.002 |
-9.53% |
0.002 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_DEL_DOT_VEC_2D_LAMBDA/1
|
-9.23% |
287.092 |
260.580 |
0.145 |
-9.24% |
0.145 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_DEL_DOT_VEC_2D_RAW/1
|
-9.19% |
287.106 |
260.711 |
0.022 |
-9.16% |
0.022 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC64
|
-8.94% |
93.243 |
84.904 |
0.053 |
-8.94% |
0.053 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint16_t>/10
|
-8.94% |
49.614 |
45.181 |
0.005 |
-0.99% |
0.005 |
|
MicroBenchmarks/ImageProcessing/Dilate/Dilate.test:BENCHMARK_DILATE/128
|
-8.89% |
225.512 |
205.456 |
2.680 |
-9.87% |
2.680 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC7
|
-8.89% |
28.158 |
25.654 |
0.002 |
-8.90% |
0.002 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_runtime_checks_pass<4, int>
|
-8.79% |
16.807 |
15.329 |
0.001 |
-8.25% |
0.001 |
|
MultiSource/Benchmarks/FreeBench/pifft/pifft
Profile
|
-8.75% |
0.359 |
0.328 |
0.000 |
-8.57% |
0.000 |
|
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/ImageProcessing/Dilate/Dilate.test:BENCHMARK_DILATE/1024
|
-8.65% |
7246.791 |
6619.725 |
169.309 |
-6.90% |
169.309 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint8_t>/10
|
-8.51% |
65.099 |
59.562 |
0.010 |
-3.46% |
0.010 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC8
|
-8.50% |
29.408 |
26.907 |
0.001 |
-8.51% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint8_t_To_uint32_t_
|
-8.42% |
12790.622 |
11713.431 |
50.695 |
-8.34% |
50.695 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_HYDRO_2D_LAMBDA/171
|
-8.22% |
88.557 |
81.274 |
0.691 |
-8.33% |
0.691 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint16_t_To_uint8_t_
|
-8.22% |
6813.088 |
6252.916 |
24.605 |
-8.26% |
24.605 |
|
SingleSource/Benchmarks/Misc/salsa20
Profile
|
-8.14% |
15.387 |
14.133 |
0.006 |
-8.13% |
0.006 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_HYDRO_1D_RAW/5001
|
-8.12% |
17.261 |
15.859 |
0.513 |
-4.96% |
0.513 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC3
|
-7.90% |
47.560 |
43.801 |
0.001 |
-7.90% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC16
|
-7.84% |
31.913 |
29.410 |
0.001 |
-7.84% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC16
|
-7.84% |
31.912 |
29.410 |
0.001 |
-7.84% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_DEL_DOT_VEC_2D_RAW/0
|
-7.83% |
1796.897 |
1656.166 |
6.796 |
-8.03% |
6.796 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC16
|
-7.82% |
31.902 |
29.409 |
0.001 |
-6.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC32
|
-7.81% |
40.047 |
36.919 |
0.001 |
-7.82% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC15
|
-7.70% |
32.538 |
30.033 |
0.002 |
-7.70% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC3
|
-7.70% |
16.269 |
15.017 |
0.001 |
-7.69% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC15
|
-7.69% |
32.536 |
30.035 |
0.001 |
-7.69% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_DISC_ORD_LAMBDA/5001
|
-7.66% |
631.482 |
583.107 |
13.963 |
-8.51% |
13.963 |
|
MultiSource/Benchmarks/Trimaran/enc-md5/enc-md5
Profile
|
-7.66% |
3.507 |
3.239 |
0.000 |
-7.62% |
0.000 |
|
MultiSource/Benchmarks/VersaBench/beamformer/beamformer
Profile
|
-7.65% |
5.203 |
4.805 |
0.000 |
-7.62% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC128
|
-7.64% |
173.324 |
160.075 |
0.036 |
-7.65% |
0.036 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_xor_no_runtime_checks_needed<16, int>
|
-7.41% |
16.896 |
15.644 |
0.001 |
-7.41% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_DEL_DOT_VEC_2D_LAMBDA/0
|
-7.39% |
1796.167 |
1663.368 |
12.621 |
-7.18% |
12.621 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint16_t>/10
|
-7.38% |
62.439 |
57.832 |
0.074 |
-0.27% |
0.074 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint16_t_To_uint64_t_
|
-7.33% |
20254.305 |
18769.784 |
47.909 |
-6.82% |
47.909 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC7
|
-7.21% |
32.540 |
30.193 |
0.109 |
-7.21% |
0.109 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC127
|
-7.21% |
68.780 |
63.824 |
0.003 |
-6.54% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint8_t>/127
|
-7.20% |
138.904 |
128.897 |
0.004 |
-7.21% |
0.004 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_PRESSURE_CALC_LAMBDA/5001
|
-7.12% |
45.480 |
42.243 |
1.066 |
-3.94% |
1.066 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint16_t_To_uint64_t_
|
-7.08% |
25057.587 |
23282.541 |
23.716 |
-6.82% |
23.716 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC63
|
-7.05% |
74.722 |
69.453 |
0.004 |
-6.43% |
0.004 |
|
SingleSource/Benchmarks/Misc/pi
Profile
|
-7.03% |
1.783 |
1.657 |
0.000 |
-7.01% |
0.000 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C++/miniFE/miniFE
Profile
|
-6.98% |
15.898 |
14.787 |
0.059 |
-7.40% |
0.059 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC15
|
-6.95% |
45.054 |
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 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC128
|
-6.82% |
68.498 |
63.827 |
0.009 |
-7.23% |
0.009 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC31
|
-6.73% |
74.464 |
69.456 |
0.003 |
-6.72% |
0.003 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_HYDRO_2D_RAW/171
|
-6.65% |
88.763 |
82.863 |
0.198 |
-6.50% |
0.198 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC127
|
-6.64% |
2408.376 |
2248.570 |
19.768 |
-7.34% |
19.768 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint8_t>/16
|
-6.61% |
56.953 |
53.187 |
0.006 |
-1.17% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC63
|
-6.55% |
114.501 |
106.999 |
0.006 |
-6.56% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_only_autovec_int32_t_
|
-6.54% |
181194.433 |
169351.125 |
1098.114 |
-6.50% |
1098.114 |
|
SingleSource/Benchmarks/Misc/flops-6
Profile
|
-6.43% |
1.311 |
1.227 |
0.001 |
-6.50% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC127
|
-6.42% |
194.603 |
182.114 |
0.329 |
-6.42% |
0.329 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_DIFF_PREDICT_RAW/171
|
-6.36% |
11.869 |
11.114 |
0.053 |
-6.86% |
0.053 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC15
|
-6.36% |
39.420 |
36.915 |
0.002 |
-6.36% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint16_t>/127
|
-6.31% |
138.910 |
130.146 |
0.011 |
-6.31% |
0.011 |
|
SingleSource/Benchmarks/Misc-C++/Large/sphereflake
Profile
|
-6.24% |
20.018 |
18.768 |
0.004 |
-6.17% |
0.004 |
|
SingleSource/Benchmarks/Polybench/stencils/jacobi-2d/jacobi-2d
Profile
|
-6.21% |
31.998 |
30.011 |
0.335 |
-6.87% |
0.335 |
|
MultiSource/Benchmarks/MiBench/telecomm-gsm/telecomm-gsm
Profile
|
-6.21% |
0.664 |
0.623 |
0.000 |
-6.11% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC16
|
-6.17% |
40.676 |
38.166 |
0.002 |
-6.17% |
0.002 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_BAND_LIN_EQ_LAMBDA/171
|
-5.99% |
0.366 |
0.344 |
0.000 |
-5.99% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_BAND_LIN_EQ_RAW/171
|
-5.98% |
0.366 |
0.344 |
0.000 |
-5.99% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC1
|
-5.93% |
88.678 |
83.420 |
1.158 |
-6.25% |
1.158 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint8_t>/65
|
-5.92% |
95.108 |
89.477 |
0.003 |
-5.92% |
0.003 |
|
MultiSource/Benchmarks/Rodinia/hotspot/hotspot
Profile
|
-5.91% |
2.035 |
1.915 |
0.004 |
-5.95% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint32_t>/127
|
-5.89% |
138.299 |
130.150 |
0.002 |
-5.88% |
0.002 |
|
External/SPEC/CFP2017rate/538.imagick_r/538.imagick_r
Profile
|
-5.89% |
291.655 |
274.482 |
0.103 |
-6.03% |
0.103 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint32_t_To_uint64_t_
|
-5.88% |
21443.088 |
20181.178 |
36.835 |
-5.92% |
36.835 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC16
|
-5.67% |
33.163 |
31.285 |
0.001 |
-5.67% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC32
|
-5.64% |
44.425 |
41.920 |
0.002 |
-5.64% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC7
|
-5.64% |
355.083 |
335.065 |
3.723 |
-5.54% |
3.723 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC32
|
-5.63% |
44.426 |
41.923 |
0.002 |
-5.64% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC15
|
-5.61% |
128.274 |
121.076 |
0.004 |
-5.60% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC31
|
-5.59% |
45.069 |
42.551 |
0.001 |
-5.58% |
0.001 |
|
MultiSource/Benchmarks/SciMark2-C/scimark2
Profile
|
-5.58% |
107.759 |
101.749 |
0.002 |
-5.47% |
0.002 |
|
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
|
-5.54% |
1365.005 |
1289.388 |
0.079 |
-5.54% |
0.079 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint32_t>/999
|
-5.39% |
696.454 |
658.903 |
0.042 |
-5.40% |
0.042 |
|
External/SPEC/CFP2017rate/519.lbm_r/519.lbm_r
Profile
|
-5.39% |
205.089 |
194.041 |
1.739 |
-3.31% |
1.739 |
|
MicroBenchmarks/harris/harris.test:BENCHMARK_HARRIS/2048/2048
|
-5.38% |
169310.228 |
160196.073 |
3430.978 |
-4.09% |
3430.978 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC7
|
-5.31% |
70.712 |
66.957 |
0.003 |
-5.32% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC7
|
-5.31% |
70.707 |
66.953 |
0.002 |
-5.32% |
0.002 |
|
MicroBenchmarks/ImageProcessing/Blur/blur.test:BENCHMARK_boxBlurKernel/128
|
-5.30% |
441.489 |
418.079 |
4.204 |
-3.73% |
4.204 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_PIC_2D_LAMBDA/171
|
-5.18% |
13.482 |
12.783 |
0.049 |
-5.29% |
0.049 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_PIC_2D_RAW/171
|
-5.16% |
13.520 |
12.823 |
0.064 |
-5.29% |
0.064 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint8_t_To_uint16_t_
|
-5.15% |
3627.619 |
3440.957 |
24.789 |
-5.30% |
24.789 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC32
|
-5.13% |
24.404 |
23.152 |
0.001 |
-5.12% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC31
|
-5.13% |
24.403 |
23.152 |
0.002 |
-5.13% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC31
|
-5.13% |
24.403 |
23.152 |
0.005 |
-5.13% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC32
|
-5.13% |
24.402 |
23.151 |
0.001 |
-5.14% |
0.001 |
|
MultiSource/Applications/lambda-0.1.3/lambda
Profile
|
-5.04% |
15.859 |
15.060 |
0.015 |
-5.10% |
0.015 |
|
SingleSource/Benchmarks/Misc/oourafft
Profile
|
-5.00% |
15.094 |
14.339 |
0.056 |
-5.00% |
0.056 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC31
|
-4.92% |
241.194 |
229.325 |
0.148 |
-4.94% |
0.148 |
|
MultiSource/Benchmarks/TSVC/NodeSplitting-dbl/NodeSplitting-dbl
Profile
|
-4.89% |
27.282 |
25.946 |
0.170 |
-1.78% |
0.170 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC8
|
-4.82% |
26.954 |
25.654 |
0.001 |
-4.68% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint32_t>/256
|
-4.81% |
364.173 |
346.659 |
0.014 |
-4.81% |
0.014 |
|
SingleSource/Benchmarks/Misc/revertBits
Profile
|
-4.71% |
0.641 |
0.611 |
0.000 |
-4.71% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint8_t_To_uint64_t_
|
-4.67% |
23515.185 |
22416.341 |
43.411 |
-4.55% |
43.411 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_PRESSURE_CALC_LAMBDA/44217
|
-4.66% |
500.237 |
476.928 |
2.898 |
-4.33% |
2.898 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint16_t>/65
|
-4.61% |
95.117 |
90.727 |
0.006 |
-4.61% |
0.006 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_runtime_checks_fail<16, int>
|
-4.61% |
54.441 |
51.933 |
0.005 |
-4.60% |
0.005 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_runtime_checks_pass<16, int>
|
-4.60% |
54.438 |
51.935 |
0.003 |
-4.60% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint32_t_To_uint16_t_
|
-4.53% |
9841.327 |
9395.328 |
26.616 |
-4.90% |
26.616 |
|
External/SPEC/CINT2017rate/523.xalancbmk_r/523.xalancbmk_r
Profile
|
-4.49% |
250.915 |
239.647 |
0.466 |
-0.54% |
0.466 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC31
|
-4.47% |
70.080 |
66.949 |
0.004 |
-4.47% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC8
|
-4.36% |
14.393 |
13.765 |
0.001 |
-4.36% |
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:benchAutoVecForLoopTC2
|
-4.35% |
14.392 |
13.766 |
0.000 |
-4.35% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC3
|
-4.35% |
14.393 |
13.766 |
0.001 |
-4.35% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC8
|
-4.35% |
14.391 |
13.765 |
0.001 |
-4.36% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC4
|
-4.35% |
14.393 |
13.766 |
0.001 |
-4.35% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC63
|
-4.35% |
43.178 |
41.299 |
0.001 |
-4.61% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC15
|
-4.35% |
14.391 |
13.765 |
0.001 |
-4.36% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC4
|
-4.35% |
14.393 |
13.766 |
0.000 |
-4.35% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC16
|
-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:benchAutoVecForBigLoopTC1
|
-4.35% |
14.391 |
13.765 |
0.001 |
-4.35% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC3
|
-4.35% |
14.391 |
13.765 |
0.000 |
-4.36% |
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:benchAutoVecForBigLoopTC7
|
-4.34% |
14.391 |
13.766 |
0.001 |
-4.35% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC16
|
-4.34% |
14.391 |
13.767 |
0.000 |
-4.35% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint64_t_To_uint32_t_
|
-4.33% |
19408.335 |
18567.374 |
53.454 |
-3.76% |
53.454 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint64_t>/999
|
-4.27% |
3595.295 |
3441.672 |
0.263 |
-4.26% |
0.263 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint64_t>/999
|
-4.24% |
1811.047 |
1734.333 |
0.062 |
-4.25% |
0.062 |
|
SingleSource/Benchmarks/Misc/ReedSolomon
Profile
|
-4.22% |
21.206 |
20.310 |
0.001 |
-2.34% |
0.001 |
|
SingleSource/Benchmarks/Misc/flops-5
Profile
|
-4.11% |
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% |
935.536 |
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/SubsetARawLoops/lcalsARaw.test:BM_ENERGY_CALC_RAW/171
|
-4.06% |
14.168 |
13.593 |
0.026 |
-4.55% |
0.026 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint16_t_To_uint8_t_
|
-4.05% |
2878.751 |
2762.227 |
18.671 |
-4.03% |
18.671 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC31
|
-4.04% |
61.944 |
59.440 |
0.002 |
-4.04% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC32
|
-4.00% |
31.283 |
30.033 |
0.001 |
-4.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC31
|
-3.98% |
93.834 |
90.099 |
0.005 |
-4.00% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_only_autovec_uint8_t_
|
-3.98% |
96169.958 |
92343.413 |
2.456 |
-3.97% |
2.456 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint32_t>/65
|
-3.98% |
94.484 |
90.725 |
0.005 |
-3.98% |
0.005 |
|
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
|
-3.95% |
221.500 |
212.740 |
0.008 |
-3.96% |
0.008 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<31, EqZero, First>
|
-3.92% |
3345.427 |
3214.126 |
4.263 |
-3.95% |
4.263 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_cond_load_autovec_int64_t_
|
-3.92% |
553097.605 |
531414.071 |
447.747 |
-3.84% |
447.747 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_ENERGY_CALC_RAW/5001
|
-3.91% |
438.063 |
420.937 |
2.679 |
-1.82% |
2.679 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint64_t_To_uint8_t_
|
-3.88% |
19735.345 |
18968.889 |
29.644 |
-4.40% |
29.644 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_ENERGY_CALC_LAMBDA/171
|
-3.86% |
14.168 |
13.622 |
0.017 |
-4.39% |
0.017 |
|
MultiSource/Benchmarks/VersaBench/ecbdes/ecbdes
Profile
|
-3.79% |
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_
|
-3.71% |
11259.934 |
10842.696 |
53.611 |
-4.41% |
53.611 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint64_t>/256
|
-3.65% |
514.379 |
495.596 |
0.017 |
-3.65% |
0.017 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C/CoMD/CoMD
Profile
|
-3.62% |
9.999 |
9.637 |
0.002 |
-2.65% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC64
|
-3.61% |
69.461 |
66.954 |
0.001 |
-3.60% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC31
|
-3.61% |
60.370 |
58.191 |
0.003 |
-3.46% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC64
|
-3.61% |
69.457 |
66.952 |
0.004 |
-3.61% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC63
|
-3.59% |
70.093 |
67.577 |
0.003 |
-3.59% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC63
|
-3.57% |
70.083 |
67.579 |
0.001 |
-3.57% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC31
|
-3.57% |
31.143 |
30.033 |
0.001 |
-3.71% |
0.001 |
|
External/SPEC/CFP2017rate/544.nab_r/544.nab_r
Profile
|
-3.56% |
477.452 |
460.471 |
0.201 |
-3.64% |
0.201 |
|
MultiSource/Benchmarks/Rodinia/pathfinder/pathfinder
Profile
|
-3.53% |
1.268 |
1.223 |
0.010 |
-2.79% |
0.010 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_only_novec_uint8_t_
|
-3.51% |
418979.402 |
404293.806 |
19.866 |
2.12% |
19.866 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint16_t>/999
|
-3.45% |
1013.785 |
978.799 |
0.049 |
-3.46% |
0.049 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_ENERGY_CALC_LAMBDA/5001
|
-3.43% |
434.421 |
419.501 |
3.442 |
-4.23% |
3.442 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<32, EqZero, Last>
|
-3.33% |
7053.724 |
6818.931 |
50.511 |
-3.32% |
50.511 |
|
MultiSource/Benchmarks/TSVC/ControlLoops-dbl/ControlLoops-dbl
Profile
|
-3.27% |
11.103 |
10.740 |
0.018 |
-2.53% |
0.018 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC32
|
-3.21% |
749.695 |
725.621 |
8.835 |
-3.34% |
8.835 |
|
SingleSource/Benchmarks/Shootout/Shootout-lists
Profile
|
-3.21% |
11.315 |
10.952 |
0.001 |
-3.18% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIRST_SUM_RAW/5001
|
-3.20% |
17.992 |
17.416 |
0.216 |
0.40% |
0.216 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint16_t>/999
|
-3.16% |
514.995 |
498.712 |
0.014 |
-3.17% |
0.014 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1BigLoopWithReductionTC1
|
-3.13% |
20.023 |
19.397 |
0.001 |
-3.14% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchVecWithRuntimeChecks4PointersDBeforeA/1000
|
-3.09% |
5020634.576 |
4865688.910 |
265.603 |
-3.07% |
265.603 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_runtime_checks_fail<4, int>
|
-3.04% |
15.810 |
15.330 |
0.000 |
-3.64% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint8_t>/10
|
-2.90% |
47.560 |
46.179 |
0.022 |
-0.48% |
0.022 |
|
MultiSource/Benchmarks/BitBench/drop3/drop3
Profile
|
-2.89% |
0.731 |
0.710 |
0.001 |
-2.82% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_PRESSURE_CALC_RAW/44217
|
-2.83% |
497.004 |
482.938 |
3.353 |
-3.84% |
3.353 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_acosf_novec_float_
|
-2.81% |
844.611 |
820.862 |
0.027 |
-2.82% |
0.027 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_acosf_autovec_float_
|
-2.79% |
844.554 |
820.957 |
0.027 |
-2.82% |
0.027 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC1
|
-2.77% |
22.525 |
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 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_BAND_LIN_EQ_LAMBDA/5001
|
-2.63% |
20.874 |
20.326 |
0.067 |
-2.28% |
0.067 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC63
|
-2.61% |
120.146 |
117.004 |
0.007 |
-2.61% |
0.007 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint8_t_To_uint32_t_
|
-2.58% |
7078.443 |
6895.711 |
2.421 |
-2.57% |
2.421 |
|
MultiSource/Benchmarks/TSVC/Symbolics-flt/Symbolics-flt
Profile
|
-2.53% |
4.781 |
4.660 |
0.041 |
-0.21% |
0.041 |
|
SingleSource/Benchmarks/Misc-C++/Large/ray
Profile
|
-2.49% |
12.133 |
11.831 |
0.000 |
-2.23% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint16_t_To_uint8_t_
|
-2.48% |
4513.143 |
4401.428 |
12.111 |
-2.56% |
12.111 |
|
MultiSource/Applications/ClamAV/clamscan
Profile
|
-2.45% |
0.497 |
0.485 |
0.004 |
-0.95% |
0.004 |
|
MultiSource/Benchmarks/Ptrdist/yacr2/yacr2
Profile
|
-2.43% |
2.076 |
2.025 |
0.000 |
-2.36% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchVecWithRuntimeChecks4PointersDBeforeA/32
|
-2.35% |
166222.591 |
162319.631 |
95.837 |
-2.34% |
95.837 |
|
SingleSource/Benchmarks/Misc/fbench
Profile
|
-2.34% |
5.762 |
5.627 |
0.000 |
-2.32% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC63
|
-2.33% |
106.994 |
104.499 |
0.001 |
-2.34% |
0.001 |
|
MultiSource/Benchmarks/mafft/pairlocalalign
Profile
|
-2.25% |
93.787 |
91.673 |
0.346 |
-2.54% |
0.346 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_BAND_LIN_EQ_RAW/5001
|
-2.25% |
20.734 |
20.268 |
0.180 |
-1.72% |
0.180 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC64
|
-2.23% |
111.372 |
108.884 |
0.051 |
-2.24% |
0.051 |
|
SingleSource/Benchmarks/Shootout/Shootout-matrix
Profile
|
-2.23% |
3.863 |
3.777 |
0.000 |
-2.22% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint64_t>/51
|
-2.19% |
229.026 |
224.006 |
0.005 |
-2.18% |
0.005 |
|
SingleSource/Benchmarks/Misc/flops-1
Profile
|
-2.17% |
9.002 |
8.807 |
0.000 |
-2.15% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC128
|
-2.10% |
119.522 |
117.013 |
0.005 |
-2.10% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC127
|
-2.09% |
120.139 |
117.631 |
0.006 |
-2.09% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC128
|
-2.08% |
119.513 |
117.022 |
0.002 |
-2.09% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC127
|
-2.08% |
120.131 |
117.634 |
0.011 |
-2.08% |
0.011 |
|
MultiSource/Applications/JM/lencod/lencod
Profile
|
-2.08% |
32.504 |
31.830 |
0.032 |
-2.18% |
0.032 |
|
MultiSource/Benchmarks/tramp3d-v4/tramp3d-v4
Profile
|
-2.06% |
1.078 |
1.056 |
0.008 |
-1.86% |
0.008 |
|
MultiSource/Applications/sgefa/sgefa
Profile
|
-2.05% |
0.577 |
0.565 |
0.003 |
-1.46% |
0.003 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<16, EqZero, None>
|
-1.99% |
8178.690 |
8016.153 |
2.397 |
-1.97% |
2.397 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<16, EqZero, Mid>
|
-1.97% |
8668.459 |
8497.694 |
1.664 |
-1.84% |
1.664 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint32_t_To_uint64_t_
|
-1.97% |
26353.535 |
25835.616 |
46.527 |
-1.69% |
46.527 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC63
|
-1.93% |
130.149 |
127.644 |
0.008 |
-1.94% |
0.008 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint16_t_To_uint32_t_
|
-1.92% |
13568.421 |
13307.866 |
23.534 |
-1.30% |
23.534 |
|
MicroBenchmarks/ImageProcessing/Blur/blur.test:BENCHMARK_boxBlurKernel/512
|
-1.89% |
6634.071 |
6508.393 |
24.322 |
-1.59% |
24.322 |
|
External/SPEC/CFP2017rate/511.povray_r/511.povray_r
Profile
|
-1.89% |
34.018 |
33.375 |
0.030 |
-1.22% |
0.030 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_EOS_LAMBDA/171
|
-1.86% |
0.872 |
0.856 |
0.001 |
-1.71% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint16_t>/256
|
-1.83% |
272.822 |
267.824 |
0.022 |
-1.84% |
0.022 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_ENERGY_CALC_LAMBDA/44217
|
-1.72% |
4322.509 |
4248.181 |
6.558 |
-1.76% |
6.558 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<32, LessThanZero, Mid>
|
-1.72% |
4570.514 |
4491.985 |
3.843 |
-1.73% |
3.843 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_csa_with_in_loop_arith_novec_int64_t_
|
-1.69% |
1029155.741 |
1011764.347 |
519.522 |
-1.59% |
519.522 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint64_t>/51
|
-1.68% |
148.289 |
145.792 |
0.004 |
-1.70% |
0.004 |
|
MultiSource/Benchmarks/ASC_Sequoia/CrystalMk/CrystalMk
Profile
|
-1.68% |
15.575 |
15.314 |
0.000 |
-1.66% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_EOS_RAW/171
|
-1.66% |
0.871 |
0.856 |
0.000 |
-1.69% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_erf_autovec_double_
|
-1.64% |
888.887 |
874.267 |
0.398 |
-1.67% |
0.398 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_erf_novec_double_
|
-1.63% |
888.865 |
874.389 |
0.222 |
-1.68% |
0.222 |
|
SingleSource/Benchmarks/Misc/mandel-2
Profile
|
-1.56% |
2.536 |
2.496 |
0.000 |
-1.54% |
0.000 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<6, LessThanZero, Mid>
|
-1.56% |
23854.541 |
23482.070 |
2.257 |
-0.36% |
2.257 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_INT_PREDICT_RAW/171
|
-1.56% |
6.909 |
6.801 |
0.001 |
-1.79% |
0.001 |
|
MultiSource/Benchmarks/nbench/nbench
Profile
|
-1.55% |
6.129 |
6.034 |
0.001 |
-1.52% |
0.001 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<31, GreaterThanZero, Last>
|
-1.55% |
8225.761 |
8098.480 |
22.231 |
-2.38% |
22.231 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, LessThanZero, None>
|
-1.53% |
37631.442 |
37055.461 |
45.421 |
-1.39% |
45.421 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_INT_PREDICT_LAMBDA/171
|
-1.52% |
6.918 |
6.813 |
0.009 |
-1.62% |
0.009 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_csa_with_cond_arith_autovec_int64_t_
|
-1.48% |
744704.643 |
733711.266 |
758.431 |
-1.51% |
758.431 |
|
SingleSource/Benchmarks/Shootout-C++/Shootout-C++-hash2
Profile
|
-1.48% |
9.322 |
9.184 |
0.021 |
-1.62% |
0.021 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_FIR_RAW/5001
|
-1.47% |
39.243 |
38.667 |
0.063 |
2.49% |
0.063 |
|
SingleSource/Benchmarks/Polybench/stencils/fdtd-2d/fdtd-2d
Profile
|
-1.45% |
19.892 |
19.604 |
0.067 |
-0.43% |
0.067 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C++/PENNANT/PENNANT
Profile
|
-1.44% |
4.799 |
4.730 |
0.016 |
-1.80% |
0.016 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_csa_with_cond_arith_novec_int64_t_
|
-1.40% |
743022.454 |
732595.762 |
1091.713 |
-1.63% |
1091.713 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<8, LessThanZero, Mid>
|
-1.40% |
19502.379 |
19229.767 |
0.423 |
-1.05% |
0.423 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C/SimpleMOC/SimpleMOC
Profile
|
-1.31% |
10.398 |
10.262 |
0.037 |
-1.37% |
0.037 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC128
|
-1.27% |
198.358 |
195.843 |
0.006 |
-1.27% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC127
|
-1.26% |
197.099 |
194.607 |
0.008 |
-1.26% |
0.008 |
|
MultiSource/Benchmarks/MallocBench/cfrac/cfrac
Profile
|
-1.26% |
2.777 |
2.742 |
0.001 |
-1.36% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint16_t>/10
|
-1.25% |
50.058 |
49.432 |
0.054 |
-0.00% |
0.054 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<7, EqZero, None>
|
-1.21% |
27194.592 |
26866.634 |
3.635 |
-1.16% |
3.635 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<32, GreaterThanZero, Mid>
|
-1.15% |
4545.131 |
4493.067 |
0.836 |
-1.37% |
0.836 |
|
MultiSource/Benchmarks/Olden/health/health
Profile
|
-1.08% |
1.588 |
1.571 |
0.002 |
-1.29% |
0.002 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C++/CLAMR/CLAMR
Profile
|
-1.08% |
12.279 |
12.146 |
0.040 |
-0.55% |
0.040 |
|
MultiSource/Benchmarks/ASC_Sequoia/AMGmk/AMGmk
Profile
|
-1.07% |
33.133 |
32.777 |
0.052 |
-0.85% |
0.052 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint32_t>/51
|
-1.06% |
118.259 |
117.002 |
0.005 |
-1.07% |
0.005 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<16, LessThanZero, Last>
|
-1.05% |
13141.553 |
13003.976 |
26.180 |
-1.05% |
26.180 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<64, EqZero, None>
|
-1.04% |
2928.421 |
2897.865 |
3.027 |
-1.07% |
3.027 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint16_t>/999
|
-1.03% |
403.993 |
399.838 |
0.019 |
-0.01% |
0.019 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<64, LessThanZero, Last>
|
-1.02% |
4173.341 |
4130.837 |
1.225 |
-0.96% |
1.225 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint16_t>/10
|
-1.00% |
63.201 |
62.568 |
0.004 |
-3.61% |
0.004 |