|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_HYDRO_2D_LAMBDA/44217
|
-64.99% |
90930.583 |
31831.504 |
8824.912 |
-18.26% |
8824.912 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_HYDRO_2D_LAMBDA/5001
|
-59.74% |
9113.303 |
3669.200 |
945.998 |
-18.91% |
945.998 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_DISC_ORD_LAMBDA/44217
|
-53.88% |
14054.040 |
6481.888 |
1712.251 |
-16.24% |
1712.251 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint64_t_To_uint32_t_
|
-52.46% |
35313.629 |
16788.448 |
184.774 |
-1.37% |
184.774 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint64_t_To_uint16_t_
|
-51.84% |
35680.148 |
17184.326 |
67.708 |
-4.02% |
67.708 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C/miniGMG/miniGMG
Profile
|
-49.97% |
9.190 |
4.598 |
0.288 |
-0.95% |
0.288 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint64_t_To_uint8_t_
|
-49.58% |
37062.972 |
18687.448 |
2.173 |
-0.11% |
2.173 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint16_t_To_uint64_t_
|
-43.97% |
18675.093 |
10462.873 |
2.129 |
-0.05% |
2.129 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_DIFF_PREDICT_RAW/44217
|
-42.20% |
23299.816 |
13467.157 |
249.624 |
-0.28% |
249.624 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_DIFF_PREDICT_LAMBDA/44217
|
-41.61% |
23102.783 |
13489.546 |
336.932 |
-0.08% |
336.932 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_DIFF_PREDICT_RAW/5001
|
-41.41% |
2574.764 |
1508.454 |
26.799 |
-1.29% |
26.799 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint8_t_To_uint64_t_
|
-40.85% |
17799.596 |
10527.923 |
7.445 |
0.04% |
7.445 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_PIC_1D_LAMBDA/44217
|
-40.85% |
13464.463 |
7964.807 |
1459.789 |
-13.15% |
1459.789 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_HYDRO_2D_RAW/44217
|
-40.63% |
84652.625 |
50255.420 |
12875.078 |
3.11% |
12875.078 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint64_t_To_uint32_t_
|
-40.48% |
38155.754 |
22710.741 |
11.462 |
0.20% |
11.462 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_DIFF_PREDICT_LAMBDA/5001
|
-39.86% |
2509.400 |
1509.263 |
39.987 |
-0.98% |
39.987 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/32
|
-36.69% |
1396.116 |
883.824 |
0.068 |
-0.01% |
0.068 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/64
|
-36.68% |
6182.288 |
3914.604 |
0.279 |
-0.01% |
0.279 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/16
|
-36.63% |
279.469 |
177.096 |
0.010 |
-0.01% |
0.010 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/256
|
-36.23% |
107153.285 |
68331.900 |
50.694 |
-0.06% |
50.694 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/128
|
-36.13% |
26271.873 |
16779.046 |
8.978 |
-0.05% |
8.978 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint32_t_To_uint64_t_
|
-35.99% |
22724.955 |
14545.487 |
259.995 |
-4.53% |
259.995 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint64_t_To_uint8_t_
|
-34.28% |
30110.831 |
19790.086 |
16.437 |
-0.00% |
16.437 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint64_t_To_uint16_t_
|
-33.87% |
28949.218 |
19142.799 |
46.574 |
-0.08% |
46.574 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIRST_DIFF_LAMBDA/44217
|
-30.65% |
144.820 |
100.429 |
0.952 |
1.70% |
0.952 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint64_t_To_uint16_t_
|
-28.40% |
25897.435 |
18542.477 |
17.116 |
-0.22% |
17.116 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint32_t_To_uint8_t_
|
-27.85% |
13469.278 |
9718.304 |
4.661 |
-0.60% |
4.661 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIRST_DIFF_RAW/44217
|
-27.82% |
142.491 |
102.844 |
1.609 |
0.74% |
1.609 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC128
|
-27.54% |
1292.822 |
936.752 |
2.916 |
0.42% |
2.916 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC64
|
-26.99% |
653.610 |
477.180 |
1.979 |
-0.15% |
1.979 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC128
|
-26.91% |
557.537 |
407.501 |
0.060 |
-0.00% |
0.060 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC32
|
-26.82% |
333.930 |
244.363 |
0.987 |
-0.06% |
0.987 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC16
|
-26.28% |
173.787 |
128.109 |
0.642 |
0.07% |
0.642 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC64
|
-25.58% |
291.827 |
217.191 |
0.052 |
0.00% |
0.052 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint64_t_To_uint8_t_
|
-24.75% |
27222.887 |
20484.489 |
33.173 |
-0.14% |
33.173 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC32
|
-23.18% |
158.873 |
122.052 |
0.056 |
0.00% |
0.056 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC128
|
-23.11% |
603.966 |
464.378 |
0.026 |
0.01% |
0.026 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC128
|
-23.11% |
603.957 |
464.384 |
0.034 |
-0.01% |
0.034 |
|
MicroBenchmarks/ImageProcessing/Blur/blur.test:BENCHMARK_boxBlurKernel/1024
|
-23.05% |
30148.993 |
23199.710 |
96.999 |
-0.55% |
96.999 |
|
SingleSource/Benchmarks/Adobe-C++/loop_unroll
Profile
|
-22.92% |
3.107 |
2.395 |
0.003 |
-0.03% |
0.003 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_PIC_2D_RAW/44217
|
-22.90% |
11216.281 |
8647.280 |
517.570 |
0.02% |
517.570 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC64
|
-22.16% |
313.505 |
244.040 |
0.021 |
-0.00% |
0.021 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC64
|
-22.16% |
313.505 |
244.042 |
0.012 |
-0.00% |
0.012 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC127
|
-21.98% |
615.213 |
480.006 |
0.041 |
-0.00% |
0.041 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC127
|
-21.97% |
615.198 |
480.023 |
0.058 |
0.00% |
0.058 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint16_t_To_uint64_t_
|
-21.50% |
13208.286 |
10368.652 |
0.586 |
-0.02% |
0.586 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint8_t_To_uint32_t_
|
-21.49% |
6582.228 |
5167.404 |
1.890 |
0.04% |
1.890 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_PIC_2D_LAMBDA/44217
|
-21.48% |
10963.150 |
8608.122 |
23.635 |
-0.14% |
23.635 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC4
|
-21.43% |
17.520 |
13.766 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint16_t_To_uint32_t_
|
-21.40% |
7100.968 |
5581.715 |
1.493 |
0.02% |
1.493 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_only_autovec_uint8_t_
|
-21.36% |
182351.670 |
143403.142 |
104.066 |
-0.01% |
104.066 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIND_FIRST_MIN_LAMBDA/44217
|
-21.30% |
389.578 |
306.613 |
0.224 |
-0.02% |
0.224 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIND_FIRST_MIN_LAMBDA/171
|
-21.28% |
1.501 |
1.181 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIND_FIRST_MIN_LAMBDA/5001
|
-21.02% |
45.257 |
35.744 |
0.289 |
-0.07% |
0.289 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC127
|
-21.01% |
275.455 |
217.568 |
1.435 |
-1.37% |
1.435 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC128
|
-20.74% |
274.741 |
217.751 |
1.021 |
-1.67% |
1.021 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC32
|
-20.45% |
168.326 |
133.906 |
0.022 |
-0.00% |
0.022 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC32
|
-20.45% |
168.333 |
133.913 |
0.005 |
-0.00% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC63
|
-20.05% |
324.799 |
259.689 |
0.016 |
-0.00% |
0.016 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC63
|
-20.04% |
324.785 |
259.684 |
0.017 |
-0.00% |
0.017 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIRST_SUM_LAMBDA/44217
|
-19.63% |
167.087 |
134.281 |
1.005 |
-0.96% |
1.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC127
|
-19.63% |
640.493 |
514.784 |
0.062 |
-0.01% |
0.062 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC64
|
-19.46% |
148.631 |
119.713 |
4.735 |
-0.67% |
4.735 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC16
|
-19.23% |
92.280 |
74.535 |
0.026 |
-0.03% |
0.026 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC63
|
-19.19% |
149.912 |
121.144 |
7.696 |
-0.57% |
7.696 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC7
|
-19.18% |
28.661 |
23.163 |
0.133 |
-0.28% |
0.133 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint32_t_To_uint8_t_
|
-19.17% |
13900.786 |
11235.750 |
66.018 |
-0.79% |
66.018 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint16_t_To_uint8_t_
|
-19.09% |
3818.115 |
3089.077 |
0.889 |
-0.00% |
0.889 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_csa_with_cond_arith_autovec_uint8_t_
|
-18.92% |
210082.683 |
170342.327 |
26.460 |
-0.01% |
26.460 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_VOL3D_CALC_LAMBDA/2
|
-18.81% |
8.757 |
7.110 |
0.001 |
-0.02% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_VOL3D_CALC_RAW/2
|
-18.80% |
8.757 |
7.111 |
0.000 |
-0.01% |
0.000 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, EqZero, None>
|
-18.75% |
20511.394 |
16665.792 |
0.590 |
0.00% |
0.590 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint32_t_To_uint16_t_
|
-18.73% |
13807.248 |
11221.631 |
22.382 |
-0.05% |
22.382 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC128
|
-18.67% |
570.579 |
464.049 |
3.477 |
-1.35% |
3.477 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint64_t_To_uint32_t_
|
-18.46% |
27051.416 |
22057.215 |
25.154 |
-0.10% |
25.154 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIRST_SUM_RAW/44217
|
-18.37% |
166.336 |
135.788 |
0.059 |
0.01% |
0.059 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, EqZero, Last>
|
-18.18% |
14104.915 |
11540.344 |
0.632 |
-0.00% |
0.632 |
|
MultiSource/Benchmarks/Trimaran/enc-pc1/enc-pc1
Profile
|
-18.11% |
1.104 |
0.904 |
0.000 |
-0.02% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC32
|
-18.10% |
85.325 |
69.882 |
2.760 |
-1.12% |
2.760 |
|
MultiSource/Benchmarks/MiBench/automotive-bitcount/automotive-bitcount
Profile
|
-18.00% |
0.124 |
0.101 |
0.000 |
-0.01% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_with_cond_arith_novec_uint8_t_
|
-17.84% |
745760.891 |
612708.768 |
469.814 |
-0.01% |
469.814 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC8
|
-17.67% |
23.153 |
19.062 |
0.079 |
0.47% |
0.079 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC16
|
-17.65% |
95.739 |
78.844 |
0.003 |
0.00% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC16
|
-17.65% |
95.740 |
78.846 |
0.003 |
-0.00% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_with_cond_arith_novec_int32_t_
|
-17.40% |
740190.367 |
611373.248 |
1245.914 |
0.01% |
1245.914 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC64
|
-17.30% |
297.710 |
246.220 |
0.019 |
0.00% |
0.019 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC32
|
-17.24% |
161.394 |
133.574 |
0.011 |
-0.04% |
0.011 |
|
MultiSource/Benchmarks/MiBench/security-rijndael/security-rijndael
Profile
|
-17.22% |
0.335 |
0.277 |
0.000 |
0.08% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC16
|
-17.02% |
93.125 |
77.279 |
0.015 |
-0.01% |
0.015 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC31
|
-16.92% |
86.114 |
71.543 |
2.035 |
-1.42% |
2.035 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC31
|
-16.73% |
179.585 |
149.549 |
0.008 |
-0.00% |
0.008 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC31
|
-16.72% |
179.581 |
149.548 |
0.007 |
-0.00% |
0.007 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC8
|
-16.72% |
58.764 |
48.938 |
0.084 |
-0.37% |
0.084 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint8_t_To_uint64_t_
|
-16.42% |
13065.090 |
10920.298 |
10.701 |
-0.00% |
10.701 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_VOL3D_CALC_RAW/1
|
-16.18% |
260.130 |
218.044 |
0.127 |
-0.06% |
0.127 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_VOL3D_CALC_LAMBDA/1
|
-16.10% |
260.168 |
218.287 |
0.188 |
0.01% |
0.188 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_VOL3D_CALC_LAMBDA/0
|
-16.07% |
1267.594 |
1063.891 |
1.733 |
-0.10% |
1.733 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_VOL3D_CALC_RAW/0
|
-15.92% |
1265.194 |
1063.726 |
0.761 |
0.01% |
0.761 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_HYDRO_1D_LAMBDA/171
|
-15.88% |
0.442 |
0.372 |
0.000 |
-0.01% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_HYDRO_1D_RAW/171
|
-15.84% |
0.442 |
0.372 |
0.000 |
-0.01% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC8
|
-15.79% |
23.778 |
20.024 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint16_t_To_uint32_t_
|
-15.62% |
7462.263 |
6296.745 |
0.535 |
-0.03% |
0.535 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_no_runtime_checks_needed<16, int>
|
-15.39% |
24.403 |
20.648 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint64_t_To_uint8_t_
|
-15.34% |
22047.281 |
18665.524 |
15.567 |
0.01% |
15.567 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_PIC_2D_RAW/5001
|
-15.33% |
1078.372 |
913.040 |
32.952 |
0.50% |
32.952 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC16
|
-15.10% |
33.164 |
28.157 |
0.572 |
-0.00% |
0.572 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC127
|
-14.97% |
605.768 |
515.078 |
0.169 |
-0.05% |
0.169 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_PIC_2D_LAMBDA/5001
|
-14.75% |
1105.490 |
942.470 |
15.624 |
-0.94% |
15.624 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint32_t_To_uint8_t_
|
-14.59% |
10595.349 |
9049.961 |
7.336 |
0.39% |
7.336 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint32_t_To_uint8_t_
|
-14.55% |
11129.319 |
9509.660 |
17.611 |
0.12% |
17.611 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC128
|
-14.51% |
1103.306 |
943.164 |
0.032 |
0.01% |
0.032 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC4
|
-14.42% |
113.088 |
96.776 |
2.394 |
0.22% |
2.394 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC127
|
-14.41% |
1095.285 |
937.478 |
0.043 |
0.00% |
0.043 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint32_t_To_uint16_t_
|
-14.36% |
12837.101 |
10994.245 |
25.886 |
-0.07% |
25.886 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC64
|
-14.20% |
562.307 |
482.451 |
0.027 |
0.00% |
0.027 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint8_t_To_uint16_t_
|
-14.14% |
3756.543 |
3225.384 |
2.332 |
-0.17% |
2.332 |
|
SingleSource/Benchmarks/Misc/salsa20
Profile
|
-14.12% |
15.384 |
13.212 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC15
|
-14.09% |
44.431 |
38.169 |
0.007 |
-0.00% |
0.007 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC63
|
-14.05% |
554.742 |
476.817 |
0.022 |
0.00% |
0.022 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_with_cond_arith_autovec_int64_t_
|
-13.97% |
791606.520 |
681050.486 |
1087.049 |
-0.03% |
1087.049 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC8
|
-13.86% |
51.939 |
44.738 |
0.004 |
-0.01% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC3
|
-13.86% |
51.935 |
44.737 |
0.003 |
-0.01% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC7
|
-13.86% |
51.935 |
44.737 |
0.002 |
-0.01% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC4
|
-13.85% |
51.934 |
44.740 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC1
|
-13.85% |
51.934 |
44.740 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC2
|
-13.85% |
51.934 |
44.740 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC8
|
-13.69% |
59.450 |
51.308 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC8
|
-13.69% |
59.450 |
51.312 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC32
|
-13.65% |
291.986 |
252.144 |
0.025 |
-0.00% |
0.025 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_csa_with_cond_arith_autovec_int32_t_
|
-13.64% |
396356.005 |
342289.361 |
599.037 |
0.04% |
599.037 |
|
External/SPEC/CFP2017rate/508.namd_r/508.namd_r
Profile
|
-13.59% |
223.577 |
193.191 |
0.312 |
-0.08% |
0.312 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_with_cond_arith_novec_int64_t_
|
-13.54% |
788035.947 |
681370.540 |
875.500 |
-0.08% |
875.500 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC63
|
-13.36% |
374.427 |
324.411 |
0.011 |
-0.00% |
0.011 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint32_t_To_uint16_t_
|
-13.36% |
10737.333 |
9303.143 |
542.716 |
-8.04% |
542.716 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC31
|
-13.23% |
284.084 |
246.510 |
0.017 |
-0.01% |
0.017 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC16
|
-13.16% |
51.941 |
45.108 |
0.403 |
-0.54% |
0.403 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC128
|
-13.07% |
81.345 |
70.710 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint32_t_To_uint16_t_
|
-12.95% |
9904.984 |
8621.942 |
182.063 |
-6.42% |
182.063 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint8_t_To_uint16_t_
|
-12.95% |
4541.860 |
3953.764 |
0.300 |
-0.01% |
0.300 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC63
|
-12.94% |
332.823 |
289.766 |
0.141 |
-0.05% |
0.141 |
|
MicroBenchmarks/ImageProcessing/Dilate/Dilate.test:BENCHMARK_DILATE/1024
|
-12.72% |
7110.540 |
6206.265 |
276.877 |
-1.49% |
276.877 |
|
SingleSource/Benchmarks/Shootout-C++/Shootout-C++-matrix
Profile
|
-12.70% |
2.508 |
2.190 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC16
|
-12.70% |
156.964 |
137.032 |
0.005 |
0.00% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint16_t_To_uint8_t_
|
-12.40% |
4742.772 |
4154.438 |
0.270 |
-0.00% |
0.270 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, EqZero, None>
|
-11.99% |
16023.286 |
14102.404 |
0.900 |
-0.00% |
0.900 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC2
|
-11.77% |
21.276 |
18.772 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC15
|
-11.70% |
107.009 |
94.485 |
0.007 |
-0.00% |
0.007 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC15
|
-11.70% |
107.003 |
94.482 |
0.031 |
-0.00% |
0.031 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC15
|
-11.70% |
148.810 |
131.403 |
0.019 |
-0.00% |
0.019 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_INT_PREDICT_RAW/44217
|
-11.57% |
9049.170 |
8002.301 |
85.278 |
-1.50% |
85.278 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC15
|
-11.46% |
51.939 |
45.985 |
0.004 |
-0.01% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint32_t_To_uint64_t_
|
-11.19% |
17196.059 |
15272.052 |
408.980 |
0.07% |
408.980 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC4
|
-11.12% |
22.527 |
20.023 |
0.000 |
-0.01% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC3
|
-11.12% |
22.526 |
20.022 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC4
|
-11.11% |
22.527 |
20.023 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_with_cond_arith_autovec_uint8_t_
|
-10.95% |
295250.544 |
262912.705 |
182.274 |
-0.01% |
182.274 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC4
|
-10.53% |
23.779 |
21.275 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC64
|
-10.47% |
53.816 |
48.182 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC8
|
-10.41% |
89.401 |
80.095 |
0.003 |
0.00% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC16
|
-10.35% |
36.293 |
32.538 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/16
|
-10.17% |
115.465 |
103.719 |
0.010 |
-0.01% |
0.010 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint8_t_To_uint16_t_
|
-10.03% |
5850.367 |
5263.836 |
8.427 |
0.07% |
8.427 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/64
|
-10.02% |
1913.314 |
1721.532 |
0.306 |
-0.02% |
0.306 |
|
SingleSource/Benchmarks/Misc-C++/oopack_v1p8
Profile
|
-10.00% |
0.519 |
0.467 |
0.000 |
-0.06% |
0.000 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/32
|
-9.99% |
473.003 |
425.727 |
0.019 |
-0.00% |
0.019 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/256
|
-9.97% |
31449.377 |
28313.467 |
25.521 |
-0.06% |
25.521 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/128
|
-9.80% |
7917.293 |
7141.790 |
2.300 |
-0.01% |
2.300 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC8
|
-9.76% |
25.656 |
23.151 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC8
|
-9.76% |
25.657 |
23.152 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC31
|
-9.74% |
196.470 |
177.343 |
0.034 |
0.02% |
0.034 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC127
|
-9.71% |
101.879 |
91.987 |
0.003 |
-0.00% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC7
|
-9.62% |
32.539 |
29.409 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_only_autovec_int64_t_
|
-9.58% |
333280.792 |
301345.582 |
473.609 |
0.13% |
473.609 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC7
|
-9.53% |
26.282 |
23.777 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_with_cond_arith_autovec_int32_t_
|
-9.47% |
940875.108 |
851779.940 |
271.495 |
-0.03% |
271.495 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC7
|
-9.40% |
26.282 |
23.812 |
0.032 |
0.10% |
0.032 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint64_t_To_uint16_t_
|
-9.39% |
18983.917 |
17200.887 |
240.704 |
-1.45% |
240.704 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_DEL_DOT_VEC_2D_RAW/1
|
-9.22% |
286.991 |
260.518 |
0.156 |
-0.07% |
0.156 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_DEL_DOT_VEC_2D_LAMBDA/1
|
-9.21% |
287.120 |
260.662 |
0.149 |
-0.00% |
0.149 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC7
|
-9.20% |
81.312 |
73.834 |
0.004 |
-0.00% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC4
|
-9.10% |
41.302 |
37.543 |
0.002 |
-0.01% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC4
|
-9.09% |
41.299 |
37.545 |
0.002 |
0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC32
|
-9.02% |
53.193 |
48.393 |
0.013 |
0.02% |
0.013 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC4
|
-8.95% |
55.663 |
50.683 |
0.003 |
-0.00% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC7
|
-8.90% |
28.160 |
25.654 |
0.001 |
-0.01% |
0.001 |
|
MultiSource/Benchmarks/FreeBench/pifft/pifft
Profile
|
-8.75% |
0.359 |
0.327 |
0.001 |
-0.32% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_DEL_DOT_VEC_2D_RAW/2
|
-8.71% |
3.510 |
3.204 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC4
|
-8.71% |
14.393 |
13.140 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC16
|
-8.71% |
14.393 |
13.140 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_DEL_DOT_VEC_2D_LAMBDA/2
|
-8.70% |
3.510 |
3.204 |
0.000 |
-0.01% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC3
|
-8.70% |
14.393 |
13.140 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC3
|
-8.70% |
14.392 |
13.140 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC8
|
-8.70% |
14.393 |
13.141 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC8
|
-8.70% |
14.392 |
13.140 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC15
|
-8.70% |
14.392 |
13.140 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC1
|
-8.70% |
14.392 |
13.140 |
0.000 |
-0.01% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC15
|
-8.70% |
14.392 |
13.141 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC4
|
-8.70% |
14.392 |
13.140 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC7
|
-8.70% |
14.391 |
13.140 |
0.000 |
-0.01% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC1
|
-8.70% |
14.393 |
13.142 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC7
|
-8.69% |
14.392 |
13.141 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC2
|
-8.69% |
14.392 |
13.141 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC16
|
-8.69% |
14.392 |
13.140 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC2
|
-8.69% |
14.391 |
13.140 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint16_t_To_uint8_t_
|
-8.59% |
6815.821 |
6230.482 |
12.294 |
-0.01% |
12.294 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC8
|
-8.52% |
29.411 |
26.905 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_runtime_checks_pass<4, int>
|
-8.25% |
16.708 |
15.330 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint8_t_To_uint32_t_
|
-8.19% |
12778.752 |
11731.537 |
20.630 |
-0.39% |
20.630 |
|
MicroBenchmarks/ImageProcessing/Dilate/Dilate.test:BENCHMARK_DILATE/128
|
-8.08% |
227.968 |
209.556 |
6.226 |
3.41% |
6.226 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC64
|
-8.07% |
93.242 |
85.719 |
0.004 |
-0.02% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC16
|
-8.01% |
31.289 |
28.782 |
0.001 |
-0.15% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint64_t_To_uint32_t_
|
-7.95% |
17813.492 |
16397.912 |
206.023 |
0.39% |
206.023 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC16
|
-7.85% |
31.913 |
29.409 |
0.002 |
-0.01% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC16
|
-7.84% |
31.911 |
29.409 |
0.001 |
-0.00% |
0.001 |
|
MultiSource/Benchmarks/McCat/12-IOtest/iotest
Profile
|
-7.83% |
1.825 |
1.682 |
0.015 |
0.19% |
0.015 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC32
|
-7.82% |
40.050 |
36.919 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC15
|
-7.69% |
32.538 |
30.035 |
0.001 |
-0.00% |
0.001 |
|
MultiSource/Benchmarks/VersaBench/beamformer/beamformer
Profile
|
-7.67% |
5.201 |
4.802 |
0.003 |
-0.02% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC15
|
-7.65% |
54.442 |
50.277 |
0.016 |
-0.02% |
0.016 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC31
|
-7.55% |
74.464 |
68.843 |
0.013 |
0.00% |
0.013 |
|
MultiSource/Benchmarks/Trimaran/enc-md5/enc-md5
Profile
|
-7.49% |
3.506 |
3.243 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint16_t_To_uint64_t_
|
-7.46% |
20143.016 |
18639.951 |
93.870 |
0.08% |
93.870 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C++/miniFE/miniFE
Profile
|
-7.43% |
15.969 |
14.783 |
0.099 |
-0.04% |
0.099 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_xor_no_runtime_checks_needed<16, int>
|
-7.42% |
16.896 |
15.643 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_DEL_DOT_VEC_2D_RAW/0
|
-7.38% |
1800.857 |
1667.923 |
1.024 |
0.29% |
1.024 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_HYDRO_2D_LAMBDA/171
|
-7.37% |
88.658 |
82.122 |
0.510 |
-0.34% |
0.510 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_DIFF_PREDICT_LAMBDA/171
|
-7.31% |
11.986 |
11.109 |
0.086 |
-0.00% |
0.086 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_HYDRO_2D_RAW/171
|
-7.28% |
88.626 |
82.178 |
0.522 |
-0.27% |
0.522 |
|
MultiSource/Applications/lambda-0.1.3/lambda
Profile
|
-7.27% |
15.870 |
14.717 |
0.007 |
-0.06% |
0.007 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC128
|
-7.24% |
68.804 |
63.823 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint8_t>/127
|
-7.21% |
138.913 |
128.894 |
0.019 |
-0.01% |
0.019 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC128
|
-7.21% |
173.330 |
160.833 |
0.004 |
0.00% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint16_t_To_uint64_t_
|
-7.15% |
24986.152 |
23199.290 |
46.308 |
-0.15% |
46.308 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIND_FIRST_MIN_RAW/171
|
-7.14% |
1.497 |
1.390 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_DEL_DOT_VEC_2D_LAMBDA/0
|
-7.13% |
1791.999 |
1664.229 |
5.530 |
0.22% |
5.530 |
|
SingleSource/Benchmarks/Misc/pi
Profile
|
-7.02% |
1.782 |
1.657 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC127
|
-7.01% |
2426.612 |
2256.416 |
34.489 |
0.04% |
34.489 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC8
|
-7.00% |
26.912 |
25.029 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC63
|
-6.96% |
114.514 |
106.539 |
0.070 |
-0.01% |
0.070 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC15
|
-6.94% |
45.051 |
41.924 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_DIFF_PREDICT_RAW/171
|
-6.90% |
11.933 |
11.109 |
0.116 |
-0.03% |
0.116 |
|
SingleSource/Benchmarks/Misc/flops-6
Profile
|
-6.63% |
1.312 |
1.225 |
0.001 |
-0.09% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC127
|
-6.61% |
194.608 |
181.750 |
0.111 |
0.02% |
0.111 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC2
|
-6.56% |
38.171 |
35.668 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC127
|
-6.54% |
68.292 |
63.824 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_only_autovec_int32_t_
|
-6.54% |
181119.283 |
169279.532 |
163.032 |
-0.06% |
163.032 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_xor_runtime_checks_pass<16, int>
|
-6.52% |
28.783 |
26.905 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_xor_runtime_checks_fail<16, int>
|
-6.52% |
28.783 |
26.906 |
0.003 |
-0.00% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC63
|
-6.42% |
74.223 |
69.456 |
0.006 |
-0.00% |
0.006 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIND_FIRST_MIN_RAW/5001
|
-6.39% |
45.339 |
42.444 |
0.010 |
0.07% |
0.010 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC15
|
-6.35% |
39.422 |
36.920 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_BAND_LIN_EQ_RAW/171
|
-6.33% |
0.366 |
0.343 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_BAND_LIN_EQ_LAMBDA/171
|
-6.33% |
0.366 |
0.343 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint16_t>/127
|
-6.30% |
138.912 |
130.154 |
0.005 |
0.00% |
0.005 |
|
SingleSource/Benchmarks/Misc-C++/Large/sphereflake
Profile
|
-6.18% |
20.002 |
18.766 |
0.003 |
0.01% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC1
|
-6.16% |
88.984 |
83.499 |
2.060 |
-0.05% |
2.060 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC16
|
-6.16% |
40.674 |
38.168 |
0.003 |
-0.00% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC32
|
-6.12% |
61.321 |
57.568 |
0.003 |
0.00% |
0.003 |
|
SingleSource/Benchmarks/Misc/perlin
Profile
|
-5.97% |
6.598 |
6.204 |
0.000 |
0.00% |
0.000 |
|
MultiSource/Benchmarks/MiBench/telecomm-gsm/telecomm-gsm
Profile
|
-5.96% |
0.663 |
0.624 |
0.000 |
-0.03% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint8_t>/65
|
-5.92% |
95.111 |
89.484 |
0.004 |
-0.00% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint32_t>/127
|
-5.88% |
138.286 |
130.151 |
0.005 |
-0.00% |
0.005 |
|
SingleSource/Benchmarks/Polybench/stencils/jacobi-2d/jacobi-2d
Profile
|
-5.86% |
32.224 |
30.334 |
0.087 |
0.41% |
0.087 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC32
|
-5.79% |
24.402 |
22.989 |
0.338 |
-3.32% |
0.338 |
|
External/SPEC/CFP2017rate/538.imagick_r/538.imagick_r
Profile
|
-5.73% |
292.080 |
275.358 |
0.315 |
0.11% |
0.315 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC16
|
-5.66% |
33.163 |
31.287 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC32
|
-5.64% |
44.427 |
41.921 |
0.003 |
-0.01% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC32
|
-5.64% |
44.429 |
41.925 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC15
|
-5.59% |
128.256 |
121.086 |
0.017 |
0.00% |
0.017 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint8_t_To_uint16_t_
|
-5.59% |
3633.347 |
3430.274 |
5.415 |
0.00% |
5.415 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC31
|
-5.58% |
45.064 |
42.549 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC31
|
-5.56% |
45.052 |
42.549 |
0.003 |
-0.00% |
0.003 |
|
MultiSource/Benchmarks/SciMark2-C/scimark2
Profile
|
-5.50% |
107.639 |
101.720 |
0.069 |
0.03% |
0.069 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_ADI_LAMBDA/5001
|
-5.50% |
2234.931 |
2112.071 |
45.236 |
-1.77% |
45.236 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint32_t_To_uint64_t_
|
-5.49% |
21450.888 |
20274.224 |
69.716 |
0.29% |
69.716 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_PIC_2D_LAMBDA/171
|
-5.47% |
13.498 |
12.760 |
0.055 |
-0.12% |
0.055 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIND_FIRST_MIN_RAW/44217
|
-5.45% |
389.585 |
368.370 |
0.256 |
-0.08% |
0.256 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint32_t>/999
|
-5.39% |
696.521 |
658.955 |
0.041 |
-0.01% |
0.041 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC7
|
-5.33% |
70.719 |
66.951 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC7
|
-5.32% |
70.713 |
66.951 |
0.004 |
-0.00% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC3
|
-5.27% |
47.558 |
45.049 |
0.002 |
-0.01% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC1
|
-5.27% |
11.889 |
11.263 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_PIC_2D_RAW/171
|
-5.23% |
13.539 |
12.831 |
0.057 |
-0.11% |
0.057 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint32_t>/999
|
-5.22% |
1365.037 |
1293.844 |
0.090 |
-0.01% |
0.090 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_cond_load_novec_uint8_t_
|
-5.21% |
314092.103 |
297724.705 |
81.488 |
-0.01% |
81.488 |
|
MultiSource/Benchmarks/Rodinia/hotspot/hotspot
Profile
|
-5.14% |
2.036 |
1.931 |
0.003 |
0.39% |
0.003 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_PRESSURE_CALC_RAW/5001
|
-5.09% |
44.600 |
42.330 |
0.829 |
-1.65% |
0.829 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_HYDRO_1D_LAMBDA/5001
|
-5.06% |
17.173 |
16.304 |
0.142 |
1.12% |
0.142 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC31
|
-4.98% |
241.230 |
229.209 |
0.027 |
0.00% |
0.027 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC32
|
-4.98% |
50.052 |
47.558 |
0.035 |
0.00% |
0.035 |
|
MicroBenchmarks/harris/harris.test:BENCHMARK_HARRIS/2048/2048
|
-4.92% |
167029.260 |
158804.239 |
2820.963 |
2.16% |
2820.963 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC15
|
-4.81% |
32.539 |
30.974 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint32_t>/256
|
-4.81% |
364.169 |
346.650 |
0.012 |
-0.01% |
0.012 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint32_t_To_uint16_t_
|
-4.80% |
9879.809 |
9405.213 |
42.820 |
-0.30% |
42.820 |
|
MicroBenchmarks/ImageProcessing/Dilate/Dilate.test:BENCHMARK_DILATE/256
|
-4.75% |
1067.252 |
1016.607 |
3.153 |
0.10% |
3.153 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC32
|
-4.73% |
24.405 |
23.251 |
0.259 |
-2.19% |
0.259 |
|
SingleSource/Benchmarks/Misc/revertBits
Profile
|
-4.69% |
0.641 |
0.611 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC31
|
-4.65% |
93.853 |
89.487 |
0.119 |
-0.57% |
0.119 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint16_t>/65
|
-4.61% |
95.115 |
90.732 |
0.005 |
-0.01% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC63
|
-4.61% |
43.294 |
41.300 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_runtime_checks_fail<16, int>
|
-4.60% |
54.439 |
51.933 |
0.002 |
-0.01% |
0.002 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_runtime_checks_pass<16, int>
|
-4.59% |
54.438 |
51.936 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_ENERGY_CALC_LAMBDA/171
|
-4.55% |
14.248 |
13.600 |
0.018 |
-0.10% |
0.018 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC2
|
-4.54% |
13.765 |
13.140 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint16_t_To_uint8_t_
|
-4.52% |
2878.208 |
2748.024 |
7.071 |
-0.01% |
7.071 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC31
|
-4.46% |
70.083 |
66.955 |
0.005 |
0.00% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC64
|
-4.35% |
43.175 |
41.297 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint8_t_To_uint64_t_
|
-4.30% |
23483.830 |
22473.222 |
15.132 |
-0.09% |
15.132 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C++/HPCCG/HPCCG
Profile
|
-4.30% |
3.915 |
3.746 |
0.042 |
-0.05% |
0.042 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_ENERGY_CALC_RAW/171
|
-4.27% |
14.241 |
13.632 |
0.013 |
-0.10% |
0.013 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_PRESSURE_CALC_RAW/44217
|
-4.24% |
502.197 |
480.887 |
1.245 |
0.21% |
1.245 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint64_t>/999
|
-4.23% |
1811.241 |
1734.665 |
0.104 |
0.01% |
0.104 |
|
External/SPEC/CFP2017rate/519.lbm_r/519.lbm_r
Profile
|
-4.22% |
200.678 |
192.218 |
1.380 |
0.29% |
1.380 |
|
SingleSource/Benchmarks/Misc/oourafft
Profile
|
-4.20% |
15.093 |
14.459 |
0.049 |
-0.66% |
0.049 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_ENERGY_CALC_LAMBDA/5001
|
-4.20% |
438.042 |
419.658 |
6.922 |
-2.09% |
6.922 |
|
External/SPEC/CFP2017rate/544.nab_r/544.nab_r
Profile
|
-4.16% |
477.880 |
458.018 |
0.105 |
-0.01% |
0.105 |
|
SingleSource/Benchmarks/Misc/flops-5
Profile
|
-4.15% |
2.021 |
1.937 |
0.001 |
0.02% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint64_t>/999
|
-4.14% |
3594.644 |
3445.852 |
0.350 |
-0.01% |
0.350 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint64_t_To_uint8_t_
|
-4.12% |
19841.137 |
19024.562 |
40.425 |
0.09% |
40.425 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint64_t>/256
|
-4.06% |
935.580 |
897.566 |
0.004 |
0.00% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC31
|
-4.04% |
61.945 |
59.445 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC3
|
-4.00% |
15.644 |
15.018 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC32
|
-4.00% |
31.286 |
30.034 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_only_autovec_uint8_t_
|
-3.98% |
96157.793 |
92326.491 |
5.724 |
-0.02% |
5.724 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_INT_PREDICT_LAMBDA/44217
|
-3.98% |
8337.702 |
8005.586 |
79.085 |
-0.32% |
79.085 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint32_t>/65
|
-3.97% |
94.488 |
90.733 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC32
|
-3.96% |
63.198 |
60.696 |
0.000 |
-0.01% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint32_t>/256
|
-3.96% |
221.503 |
212.739 |
0.042 |
-0.01% |
0.042 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint16_t_To_uint32_t_
|
-3.91% |
11342.699 |
10898.666 |
12.483 |
0.21% |
12.483 |
|
MultiSource/Benchmarks/nbench/nbench
Profile
|
-3.89% |
6.127 |
5.888 |
0.003 |
-0.02% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_cond_load_autovec_int64_t_
|
-3.81% |
552633.768 |
531574.866 |
892.698 |
0.05% |
892.698 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC31
|
-3.70% |
31.189 |
30.035 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/ImageProcessing/Dilate/Dilate.test:BENCHMARK_DILATE/512
|
-3.68% |
3584.064 |
3452.047 |
12.677 |
-0.38% |
12.677 |
|
SingleSource/Benchmarks/Shootout/Shootout-matrix
Profile
|
-3.68% |
3.863 |
3.721 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint64_t>/256
|
-3.65% |
514.395 |
495.642 |
0.013 |
-0.00% |
0.013 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<31, EqZero, First>
|
-3.64% |
3346.347 |
3224.411 |
2.562 |
-0.14% |
2.562 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_runtime_checks_fail<4, int>
|
-3.64% |
15.908 |
15.329 |
0.000 |
-0.01% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_BAND_LIN_EQ_LAMBDA/5001
|
-3.63% |
20.799 |
20.045 |
0.056 |
0.37% |
0.056 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC64
|
-3.61% |
69.461 |
66.953 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC64
|
-3.60% |
69.457 |
66.955 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC63
|
-3.58% |
70.092 |
67.582 |
0.013 |
-0.00% |
0.013 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC63
|
-3.57% |
70.083 |
67.578 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/ImageProcessing/Blur/blur.test:BENCHMARK_boxBlurKernel/128
|
-3.48% |
434.276 |
419.148 |
2.382 |
0.55% |
2.382 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint64_t_To_uint32_t_
|
-3.47% |
19292.425 |
18623.180 |
37.031 |
0.25% |
37.031 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC31
|
-3.46% |
60.276 |
58.193 |
0.005 |
0.00% |
0.005 |
|
MultiSource/Benchmarks/TSVC/Equivalencing-dbl/Equivalencing-dbl
Profile
|
-3.43% |
7.621 |
7.359 |
0.085 |
2.28% |
0.085 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC64
|
-3.37% |
111.383 |
107.631 |
0.006 |
-0.00% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint16_t_To_uint8_t_
|
-3.23% |
4517.211 |
4371.324 |
10.309 |
-0.03% |
10.309 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_PRESSURE_CALC_LAMBDA/44217
|
-3.22% |
498.539 |
482.466 |
3.842 |
-0.35% |
3.842 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint16_t>/999
|
-3.16% |
515.023 |
498.753 |
0.013 |
-0.01% |
0.013 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1BigLoopWithReductionTC1
|
-3.14% |
20.025 |
19.397 |
0.004 |
-0.01% |
0.004 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_FLOYD_DITHER/128
|
-3.12% |
439.467 |
425.759 |
1.723 |
-0.31% |
1.723 |
|
SingleSource/Benchmarks/Shootout/Shootout-lists
Profile
|
-3.12% |
11.312 |
10.960 |
0.005 |
0.03% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchVecWithRuntimeChecks4PointersDBeforeA/1000
|
-3.06% |
5019862.993 |
4866129.042 |
562.436 |
-0.00% |
562.436 |
|
MultiSource/Benchmarks/Rodinia/pathfinder/pathfinder
Profile
|
-3.04% |
1.258 |
1.220 |
0.009 |
-0.34% |
0.009 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_nested_cond_load_novec_int32_t_
|
-2.87% |
645149.252 |
626632.756 |
63.913 |
-0.01% |
63.913 |
|
MultiSource/Applications/JM/lencod/lencod
Profile
|
-2.87% |
32.540 |
31.607 |
0.038 |
0.00% |
0.038 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<32, EqZero, Last>
|
-2.85% |
7052.998 |
6851.640 |
24.127 |
0.16% |
24.127 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint16_t>/999
|
-2.84% |
1013.869 |
985.061 |
0.129 |
-0.02% |
0.129 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC1
|
-2.77% |
22.526 |
21.902 |
0.001 |
0.00% |
0.001 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C/CoMD/CoMD
Profile
|
-2.76% |
9.899 |
9.625 |
0.002 |
0.08% |
0.002 |
|
MultiSource/Benchmarks/FreeBench/mason/mason
Profile
|
-2.72% |
0.553 |
0.538 |
0.000 |
-0.01% |
0.000 |
|
MultiSource/Benchmarks/FreeBench/pcompress2/pcompress2
Profile
|
-2.61% |
0.404 |
0.394 |
0.001 |
-0.02% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC63
|
-2.61% |
120.145 |
117.012 |
0.008 |
0.00% |
0.008 |
|
MultiSource/Benchmarks/sim/sim
Profile
|
-2.60% |
9.701 |
9.449 |
0.012 |
-0.13% |
0.012 |
|
MultiSource/Benchmarks/TSVC/Recurrences-dbl/Recurrences-dbl
Profile
|
-2.59% |
10.357 |
10.088 |
0.056 |
-0.30% |
0.056 |
|
MultiSource/Benchmarks/mafft/pairlocalalign
Profile
|
-2.59% |
94.062 |
91.629 |
0.368 |
-0.13% |
0.368 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC31
|
-2.56% |
24.404 |
23.778 |
0.004 |
-0.00% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC31
|
-2.55% |
24.403 |
23.780 |
0.017 |
0.00% |
0.017 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint8_t_To_uint32_t_
|
-2.52% |
7077.318 |
6898.648 |
1.425 |
-0.01% |
1.425 |
|
MultiSource/Benchmarks/FreeBench/fourinarow/fourinarow
Profile
|
-2.43% |
0.651 |
0.635 |
0.001 |
-0.03% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchVecWithRuntimeChecks4PointersDBeforeA/32
|
-2.42% |
166201.466 |
162185.542 |
176.558 |
-0.04% |
176.558 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC63
|
-2.41% |
130.166 |
127.032 |
0.074 |
-0.20% |
0.074 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_cond_load_novec_int32_t_
|
-2.38% |
410715.023 |
400938.632 |
71.649 |
0.13% |
71.649 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_FLOYD_DITHER/512
|
-2.35% |
6645.158 |
6488.801 |
36.026 |
-0.32% |
36.026 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<31, GreaterThanZero, Last>
|
-2.35% |
8295.600 |
8100.508 |
18.323 |
-0.11% |
18.323 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC63
|
-2.34% |
107.004 |
104.500 |
0.003 |
0.00% |
0.003 |
|
SingleSource/Benchmarks/Misc/fbench
Profile
|
-2.32% |
5.761 |
5.627 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_nested_cond_load_novec_uint8_t_
|
-2.28% |
504714.718 |
493208.302 |
421.857 |
-0.06% |
421.857 |
|
SingleSource/Benchmarks/BenchmarkGame/puzzle
Profile
|
-2.22% |
0.869 |
0.849 |
0.003 |
-0.36% |
0.003 |
|
External/SPEC/CINT2017rate/531.deepsjeng_r/531.deepsjeng_r
Profile
|
-2.22% |
260.112 |
254.340 |
0.432 |
-0.36% |
0.432 |
|
SingleSource/Benchmarks/Misc/flops-1
Profile
|
-2.15% |
9.000 |
8.806 |
0.000 |
-0.00% |
0.000 |
|
MultiSource/Benchmarks/Bullet/bullet
Profile
|
-2.12% |
30.431 |
29.784 |
0.165 |
0.20% |
0.165 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC128
|
-2.10% |
119.520 |
117.006 |
0.005 |
-0.01% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC128
|
-2.10% |
119.525 |
117.013 |
0.726 |
-0.00% |
0.726 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_only_autovec_int64_t_
|
-2.09% |
1446971.267 |
1416727.769 |
1477.944 |
-0.15% |
1477.944 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC127
|
-2.09% |
120.146 |
117.635 |
0.003 |
-0.00% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC127
|
-2.09% |
120.138 |
117.633 |
0.009 |
-0.00% |
0.009 |
|
SingleSource/Benchmarks/Misc-C++/Large/ray
Profile
|
-2.08% |
12.101 |
11.849 |
0.002 |
-0.00% |
0.002 |
|
SingleSource/Benchmarks/Misc/ReedSolomon
Profile
|
-1.96% |
20.797 |
20.389 |
0.001 |
0.00% |
0.001 |
|
MultiSource/Benchmarks/Olden/health/health
Profile
|
-1.95% |
1.591 |
1.560 |
0.004 |
-0.21% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint32_t_To_uint64_t_
|
-1.94% |
26280.748 |
25771.151 |
46.689 |
-0.29% |
46.689 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_ENERGY_CALC_RAW/44217
|
-1.91% |
4331.435 |
4248.723 |
6.174 |
-0.12% |
6.174 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_INT_PREDICT_LAMBDA/171
|
-1.88% |
6.925 |
6.795 |
0.009 |
-0.32% |
0.009 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<16, LessThanZero, Mid>
|
-1.88% |
8659.949 |
8497.531 |
4.937 |
-0.18% |
4.937 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint32_t>/10
|
-1.84% |
61.947 |
60.805 |
0.007 |
-0.01% |
0.007 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint16_t>/256
|
-1.84% |
272.838 |
267.812 |
0.024 |
-0.00% |
0.024 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<16, EqZero, Mid>
|
-1.82% |
8657.236 |
8499.283 |
0.614 |
0.01% |
0.614 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_ENERGY_CALC_LAMBDA/44217
|
-1.82% |
4324.422 |
4245.683 |
10.047 |
0.42% |
10.047 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, GreaterThanZero, None>
|
-1.80% |
37175.735 |
36506.197 |
1.428 |
-0.01% |
1.428 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_EOS_RAW/171
|
-1.80% |
0.871 |
0.855 |
0.001 |
-0.06% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC128
|
-1.78% |
211.515 |
207.751 |
1.019 |
0.00% |
1.019 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_INT_PREDICT_RAW/171
|
-1.71% |
6.925 |
6.806 |
0.011 |
0.01% |
0.011 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<32, LessThanZero, Mid>
|
-1.71% |
4570.992 |
4492.995 |
6.231 |
-0.00% |
6.231 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint64_t>/51
|
-1.70% |
148.307 |
145.792 |
0.009 |
-0.01% |
0.009 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C/SimpleMOC/SimpleMOC
Profile
|
-1.67% |
10.405 |
10.232 |
0.031 |
-0.24% |
0.031 |
|
SingleSource/Benchmarks/Adobe-C++/simple_types_loop_invariant
Profile
|
-1.66% |
1.863 |
1.832 |
0.002 |
-0.02% |
0.002 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_EOS_LAMBDA/171
|
-1.65% |
0.871 |
0.856 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<6, GreaterThanZero, None>
|
-1.64% |
29578.660 |
29092.166 |
14.041 |
-0.17% |
14.041 |
|
MultiSource/Benchmarks/VersaBench/ecbdes/ecbdes
Profile
|
-1.63% |
5.139 |
5.056 |
0.001 |
-0.02% |
0.001 |
|
MultiSource/Benchmarks/ASC_Sequoia/CrystalMk/CrystalMk
Profile
|
-1.56% |
15.572 |
15.329 |
0.000 |
-0.00% |
0.000 |
|
SingleSource/Benchmarks/Misc/mandel-2
Profile
|
-1.55% |
2.535 |
2.496 |
0.000 |
-0.01% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint16_t>/16
|
-1.52% |
58.454 |
57.565 |
0.010 |
-0.01% |
0.010 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_csa_with_in_loop_arith_novec_int64_t_
|
-1.50% |
1028155.144 |
1012701.996 |
169.121 |
-0.01% |
169.121 |
|
MultiSource/Benchmarks/Fhourstones-3.1/fhourstones3.1
Profile
|
-1.50% |
3.972 |
3.912 |
0.005 |
-0.04% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint32_t>/28
|
-1.46% |
82.597 |
81.391 |
0.008 |
-0.02% |
0.008 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<3, GreaterThanZero, None>
|
-1.46% |
45142.879 |
44484.717 |
146.402 |
-0.04% |
146.402 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC64
|
-1.45% |
86.350 |
85.102 |
0.168 |
0.00% |
0.168 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC127
|
-1.43% |
220.275 |
217.132 |
0.021 |
-0.00% |
0.021 |
|
MicroBenchmarks/ImageProcessing/Blur/blur.test:BENCHMARK_boxBlurKernel/512
|
-1.41% |
6613.679 |
6520.275 |
9.950 |
0.17% |
9.950 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, LessThanZero, None>
|
-1.41% |
37576.235 |
37047.640 |
28.319 |
-0.13% |
28.319 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint32_t>/51
|
-1.38% |
83.849 |
82.696 |
0.005 |
0.02% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint64_t>/51
|
-1.36% |
229.009 |
225.892 |
0.014 |
-0.00% |
0.014 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, LessThanZero, Mid>
|
-1.36% |
56527.388 |
55759.839 |
5.937 |
-0.01% |
5.937 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint16_t_To_uint32_t_
|
-1.35% |
13483.541 |
13301.802 |
19.120 |
-0.12% |
19.120 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint8_t_To_uint32_t_
|
-1.33% |
12122.484 |
11960.689 |
4.632 |
-0.02% |
4.632 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint16_t>/28
|
-1.33% |
75.469 |
74.468 |
0.009 |
0.00% |
0.009 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<32, GreaterThanZero, Mid>
|
-1.31% |
4555.446 |
4495.995 |
1.135 |
-0.05% |
1.135 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC127
|
-1.27% |
197.100 |
194.593 |
0.013 |
-0.01% |
0.013 |
|
External/SPEC/CINT2017rate/523.xalancbmk_r/523.xalancbmk_r
Profile
|
-1.27% |
240.953 |
237.891 |
1.176 |
-0.08% |
1.176 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC128
|
-1.27% |
198.368 |
195.858 |
0.010 |
-0.00% |
0.010 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopFrom_uint64_t_To_uint16_t_
|
-1.26% |
14835.353 |
14648.823 |
17.199 |
-0.64% |
17.199 |
|
MultiSource/Benchmarks/MallocBench/cfrac/cfrac
Profile
|
-1.20% |
2.780 |
2.747 |
0.005 |
-0.01% |
0.005 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, LessThanZero, Mid>
|
-1.17% |
31782.155 |
31411.052 |
26.204 |
-0.01% |
26.204 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_sinh_novec_double_
|
-1.17% |
2473.865 |
2445.044 |
1.878 |
-0.19% |
1.878 |
|
SingleSource/Benchmarks/Shootout-C++/Shootout-C++-hash2
Profile
|
-1.16% |
9.336 |
9.228 |
0.022 |
-0.33% |
0.022 |
|
MultiSource/Benchmarks/tramp3d-v4/tramp3d-v4
Profile
|
-1.14% |
1.076 |
1.063 |
0.004 |
0.08% |
0.004 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<7, EqZero, None>
|
-1.13% |
27180.943 |
26872.709 |
11.699 |
-0.01% |
11.699 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_sinhf_autovec_float_
|
-1.11% |
2242.663 |
2217.701 |
0.583 |
-0.02% |
0.583 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_sinhf_novec_float_
|
-1.11% |
2241.857 |
2216.947 |
0.587 |
-0.05% |
0.587 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_sinh_autovec_double_
|
-1.09% |
2475.629 |
2448.713 |
0.985 |
-0.02% |
0.985 |
|
SingleSource/Benchmarks/SmallPT/smallpt
Profile
|
-1.08% |
30.029 |
29.705 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint32_t>/51
|
-1.04% |
78.409 |
77.593 |
0.002 |
0.00% |
0.002 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<8, LessThanZero, Mid>
|
-1.03% |
19434.559 |
19235.209 |
1.545 |
-0.01% |
1.545 |