|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_HYDRO_2D_LAMBDA/44217
|
-65.61% |
92565.536 |
31831.504 |
8824.912 |
-64.99% |
8824.912 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_HYDRO_2D_LAMBDA/5001
|
-62.33% |
9741.390 |
3669.200 |
945.998 |
-59.74% |
945.998 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_INT_PREDICT_RAW/44217
|
-57.96% |
19036.272 |
8002.301 |
85.278 |
-11.57% |
85.278 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_DISC_ORD_LAMBDA/44217
|
-54.73% |
14317.860 |
6481.888 |
1712.251 |
-53.88% |
1712.251 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint64_t_To_uint32_t_
|
-52.33% |
35218.547 |
16788.448 |
184.774 |
-52.46% |
184.774 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint64_t_To_uint16_t_
|
-51.82% |
35667.815 |
17184.326 |
67.708 |
-51.84% |
67.708 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint64_t_To_uint8_t_
|
-49.55% |
37040.701 |
18687.448 |
2.173 |
-49.58% |
2.173 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C/miniGMG/miniGMG
Profile
|
-47.88% |
8.821 |
4.598 |
0.288 |
-49.97% |
0.288 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_DIFF_PREDICT_RAW/44217
|
-44.29% |
24172.004 |
13467.157 |
249.624 |
-42.20% |
249.624 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint16_t_To_uint64_t_
|
-43.92% |
18657.278 |
10462.873 |
2.129 |
-43.97% |
2.129 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_INT_PREDICT_RAW/5001
|
-42.44% |
1580.577 |
909.750 |
5.137 |
-0.40% |
5.137 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIRST_DIFF_RAW/44217
|
-41.49% |
175.770 |
102.844 |
1.609 |
-27.82% |
1.609 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint8_t_To_uint64_t_
|
-40.99% |
17840.646 |
10527.923 |
7.445 |
-40.85% |
7.445 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_DIFF_PREDICT_RAW/5001
|
-40.76% |
2546.325 |
1508.454 |
26.799 |
-41.41% |
26.799 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_PIC_1D_LAMBDA/44217
|
-40.71% |
13433.195 |
7964.807 |
1459.789 |
-40.85% |
1459.789 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint64_t_To_uint32_t_
|
-40.60% |
38235.818 |
22710.741 |
11.462 |
-40.48% |
11.462 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/32
|
-36.70% |
1396.260 |
883.824 |
0.068 |
-36.69% |
0.068 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/64
|
-36.68% |
6181.817 |
3914.604 |
0.279 |
-36.68% |
0.279 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/16
|
-36.64% |
279.513 |
177.096 |
0.010 |
-36.63% |
0.010 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/256
|
-36.21% |
107113.172 |
68331.900 |
50.694 |
-36.23% |
50.694 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/128
|
-36.12% |
26266.109 |
16779.046 |
8.978 |
-36.13% |
8.978 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint32_t_To_uint64_t_
|
-35.52% |
22558.616 |
14545.487 |
259.995 |
-35.99% |
259.995 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint64_t_To_uint8_t_
|
-34.78% |
30344.913 |
19790.086 |
16.437 |
-34.28% |
16.437 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint64_t_To_uint16_t_
|
-33.84% |
28936.204 |
19142.799 |
46.574 |
-33.87% |
46.574 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint64_t_To_uint16_t_
|
-28.42% |
25905.616 |
18542.477 |
17.116 |
-28.40% |
17.116 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint32_t_To_uint8_t_
|
-27.94% |
13486.379 |
9718.304 |
4.661 |
-27.85% |
4.661 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC128
|
-27.53% |
1292.642 |
936.752 |
2.916 |
-27.54% |
2.916 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_PIC_2D_RAW/44217
|
-27.43% |
11916.494 |
8647.280 |
517.570 |
-22.90% |
517.570 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_PIC_2D_LAMBDA/44217
|
-27.33% |
11845.096 |
8608.122 |
23.635 |
-21.48% |
23.635 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC128
|
-27.17% |
559.486 |
407.501 |
0.060 |
-26.91% |
0.060 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC64
|
-27.08% |
654.389 |
477.180 |
1.979 |
-26.99% |
1.979 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC32
|
-27.04% |
334.936 |
244.363 |
0.987 |
-26.82% |
0.987 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC16
|
-26.70% |
174.767 |
128.109 |
0.642 |
-26.28% |
0.642 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC64
|
-25.96% |
293.336 |
217.191 |
0.052 |
-25.58% |
0.052 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint64_t_To_uint8_t_
|
-24.51% |
27134.396 |
20484.489 |
33.173 |
-24.75% |
33.173 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC32
|
-23.81% |
160.185 |
122.052 |
0.056 |
-23.18% |
0.056 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIRST_SUM_RAW/44217
|
-23.80% |
178.207 |
135.788 |
0.059 |
-18.37% |
0.059 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC128
|
-22.96% |
602.762 |
464.384 |
0.034 |
-23.11% |
0.034 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC128
|
-22.96% |
602.738 |
464.378 |
0.026 |
-23.11% |
0.026 |
|
MicroBenchmarks/ImageProcessing/Blur/blur.test:BENCHMARK_boxBlurKernel/1024
|
-22.89% |
30088.248 |
23199.710 |
96.999 |
-23.05% |
96.999 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint8_t_To_uint32_t_
|
-22.21% |
6642.445 |
5167.404 |
1.890 |
-21.49% |
1.890 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC127
|
-21.90% |
614.566 |
480.006 |
0.041 |
-21.98% |
0.041 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC127
|
-21.89% |
614.581 |
480.023 |
0.058 |
-21.97% |
0.058 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC64
|
-21.85% |
312.268 |
244.040 |
0.021 |
-22.16% |
0.021 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC64
|
-21.84% |
312.237 |
244.042 |
0.012 |
-22.16% |
0.012 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIND_FIRST_MIN_LAMBDA/5001
|
-21.63% |
45.611 |
35.744 |
0.289 |
-21.02% |
0.289 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint16_t_To_uint64_t_
|
-21.63% |
13230.406 |
10368.652 |
0.586 |
-21.50% |
0.586 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint16_t_To_uint32_t_
|
-21.48% |
7108.668 |
5581.715 |
1.493 |
-21.40% |
1.493 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC4
|
-21.43% |
17.520 |
13.766 |
0.000 |
-21.43% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_only_autovec_uint8_t_
|
-21.36% |
182345.847 |
143403.142 |
104.066 |
-21.36% |
104.066 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIND_FIRST_MIN_LAMBDA/44217
|
-21.27% |
389.461 |
306.613 |
0.224 |
-21.30% |
0.224 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIND_FIRST_MIN_LAMBDA/171
|
-21.27% |
1.500 |
1.181 |
0.000 |
-21.28% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC127
|
-20.78% |
274.641 |
217.568 |
1.435 |
-21.01% |
1.435 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_PIC_2D_RAW/5001
|
-20.64% |
1150.540 |
913.040 |
32.952 |
-15.33% |
32.952 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC128
|
-20.64% |
274.388 |
217.751 |
1.021 |
-20.74% |
1.021 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_PIC_2D_LAMBDA/5001
|
-20.57% |
1186.528 |
942.470 |
15.624 |
-14.75% |
15.624 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC16
|
-20.30% |
93.515 |
74.535 |
0.026 |
-19.23% |
0.026 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC64
|
-20.03% |
149.689 |
119.713 |
4.735 |
-19.46% |
4.735 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC63
|
-19.89% |
324.165 |
259.689 |
0.016 |
-20.05% |
0.016 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC63
|
-19.89% |
324.142 |
259.684 |
0.017 |
-20.04% |
0.017 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC32
|
-19.85% |
167.071 |
133.906 |
0.022 |
-20.45% |
0.022 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC32
|
-19.85% |
167.069 |
133.913 |
0.005 |
-20.45% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC127
|
-19.85% |
642.241 |
514.784 |
0.062 |
-19.63% |
0.062 |
|
SingleSource/Benchmarks/Adobe-C++/loop_unroll
Profile
|
-19.78% |
2.985 |
2.395 |
0.003 |
-22.92% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint32_t_To_uint8_t_
|
-19.65% |
13982.962 |
11235.750 |
66.018 |
-19.17% |
66.018 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC32
|
-19.50% |
86.805 |
69.882 |
2.760 |
-18.10% |
2.760 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint8_t_To_uint64_t_
|
-19.34% |
13538.823 |
10920.298 |
10.701 |
-16.42% |
10.701 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC63
|
-19.32% |
150.163 |
121.144 |
7.696 |
-19.19% |
7.696 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC16
|
-19.23% |
97.619 |
78.846 |
0.003 |
-17.65% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint16_t_To_uint8_t_
|
-19.10% |
3818.546 |
3089.077 |
0.889 |
-19.09% |
0.889 |
|
MultiSource/Benchmarks/MiBench/automotive-bitcount/automotive-bitcount
Profile
|
-18.86% |
0.125 |
0.101 |
0.000 |
-18.00% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_VOL3D_CALC_LAMBDA/2
|
-18.81% |
8.757 |
7.110 |
0.001 |
-18.81% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_VOL3D_CALC_RAW/2
|
-18.79% |
8.756 |
7.111 |
0.000 |
-18.80% |
0.000 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, EqZero, None>
|
-18.75% |
20511.553 |
16665.792 |
0.590 |
-18.75% |
0.590 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint32_t_To_uint16_t_
|
-18.70% |
13802.717 |
11221.631 |
22.382 |
-18.73% |
22.382 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint64_t_To_uint32_t_
|
-18.62% |
27105.391 |
22057.215 |
25.154 |
-18.46% |
25.154 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC128
|
-18.52% |
569.542 |
464.049 |
3.477 |
-18.67% |
3.477 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC31
|
-18.33% |
87.601 |
71.543 |
2.035 |
-16.92% |
2.035 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, EqZero, Last>
|
-18.17% |
14103.303 |
11540.344 |
0.632 |
-18.18% |
0.632 |
|
MultiSource/Benchmarks/Trimaran/enc-pc1/enc-pc1
Profile
|
-18.13% |
1.105 |
0.904 |
0.000 |
-18.11% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_with_cond_arith_novec_uint8_t_
|
-17.87% |
746013.502 |
612708.768 |
469.814 |
-17.84% |
469.814 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC8
|
-17.67% |
23.152 |
19.062 |
0.079 |
-17.67% |
0.079 |
|
MultiSource/Benchmarks/MiBench/security-rijndael/security-rijndael
Profile
|
-17.45% |
0.336 |
0.277 |
0.000 |
-17.22% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_with_cond_arith_novec_int32_t_
|
-17.37% |
739881.934 |
611373.248 |
1245.914 |
-17.40% |
1245.914 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC64
|
-16.98% |
296.572 |
246.220 |
0.019 |
-17.30% |
0.019 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC31
|
-16.96% |
180.097 |
149.548 |
0.007 |
-16.72% |
0.007 |
|
MicroBenchmarks/ImageProcessing/Dilate/Dilate.test:BENCHMARK_DILATE/1024
|
-16.71% |
7451.279 |
6206.265 |
276.877 |
-12.72% |
276.877 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC32
|
-16.61% |
160.172 |
133.574 |
0.011 |
-17.24% |
0.011 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC16
|
-16.55% |
94.484 |
78.844 |
0.003 |
-17.65% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC31
|
-16.43% |
178.955 |
149.549 |
0.008 |
-16.73% |
0.008 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_HYDRO_1D_RAW/171
|
-16.20% |
0.444 |
0.372 |
0.000 |
-15.84% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_VOL3D_CALC_RAW/1
|
-16.15% |
260.035 |
218.044 |
0.127 |
-16.18% |
0.127 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_VOL3D_CALC_RAW/0
|
-16.13% |
1268.306 |
1063.726 |
0.761 |
-15.92% |
0.761 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_VOL3D_CALC_LAMBDA/1
|
-16.13% |
260.267 |
218.287 |
0.188 |
-16.10% |
0.188 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_VOL3D_CALC_LAMBDA/0
|
-15.95% |
1265.784 |
1063.891 |
1.733 |
-16.07% |
1.733 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC16
|
-15.94% |
91.937 |
77.279 |
0.015 |
-17.02% |
0.015 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_HYDRO_1D_LAMBDA/171
|
-15.87% |
0.442 |
0.372 |
0.000 |
-15.88% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC8
|
-15.78% |
23.777 |
20.024 |
0.001 |
-15.79% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint16_t_To_uint32_t_
|
-15.63% |
7463.259 |
6296.745 |
0.535 |
-15.62% |
0.535 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIRST_DIFF_LAMBDA/44217
|
-15.62% |
119.024 |
100.429 |
0.952 |
-30.65% |
0.952 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint32_t_To_uint16_t_
|
-15.46% |
11004.704 |
9303.143 |
542.716 |
-13.36% |
542.716 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_no_runtime_checks_needed<16, int>
|
-15.38% |
24.403 |
20.648 |
0.001 |
-15.39% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint64_t_To_uint8_t_
|
-15.17% |
22002.185 |
18665.524 |
15.567 |
-15.34% |
15.567 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC16
|
-15.10% |
33.165 |
28.157 |
0.572 |
-15.10% |
0.572 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC8
|
-14.99% |
57.565 |
48.938 |
0.084 |
-16.72% |
0.084 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint32_t_To_uint8_t_
|
-14.89% |
10633.746 |
9049.961 |
7.336 |
-14.59% |
7.336 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC127
|
-14.88% |
605.118 |
515.078 |
0.169 |
-14.97% |
0.169 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC4
|
-14.82% |
113.607 |
96.776 |
2.394 |
-14.42% |
2.394 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC128
|
-14.43% |
1102.172 |
943.164 |
0.032 |
-14.51% |
0.032 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC127
|
-14.36% |
1094.667 |
937.478 |
0.043 |
-14.41% |
0.043 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint8_t_To_uint16_t_
|
-14.15% |
3756.965 |
3225.384 |
2.332 |
-14.14% |
2.332 |
|
SingleSource/Benchmarks/Misc/salsa20
Profile
|
-14.14% |
15.387 |
13.212 |
0.001 |
-14.12% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint32_t_To_uint16_t_
|
-14.12% |
12801.272 |
10994.245 |
25.886 |
-14.36% |
25.886 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC64
|
-14.05% |
561.339 |
482.451 |
0.027 |
-14.20% |
0.027 |
|
External/SPEC/CFP2017rate/508.namd_r/508.namd_r
Profile
|
-14.04% |
224.735 |
193.191 |
0.312 |
-13.59% |
0.312 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC63
|
-13.91% |
553.842 |
476.817 |
0.022 |
-14.05% |
0.022 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_with_cond_arith_novec_int64_t_
|
-13.91% |
791422.422 |
681370.540 |
875.500 |
-13.54% |
875.500 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC7
|
-13.86% |
51.937 |
44.737 |
0.002 |
-13.86% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC8
|
-13.86% |
51.937 |
44.738 |
0.004 |
-13.86% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC3
|
-13.86% |
51.934 |
44.737 |
0.003 |
-13.86% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC2
|
-13.86% |
51.939 |
44.740 |
0.002 |
-13.85% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC1
|
-13.86% |
51.938 |
44.740 |
0.001 |
-13.85% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC4
|
-13.86% |
51.936 |
44.740 |
0.002 |
-13.85% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_with_cond_arith_autovec_int64_t_
|
-13.78% |
789939.465 |
681050.486 |
1087.049 |
-13.97% |
1087.049 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC63
|
-13.66% |
375.756 |
324.411 |
0.011 |
-13.36% |
0.011 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint32_t_To_uint8_t_
|
-13.64% |
11012.250 |
9509.660 |
17.611 |
-14.55% |
17.611 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC32
|
-13.34% |
290.954 |
252.144 |
0.025 |
-13.65% |
0.025 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC16
|
-13.16% |
51.941 |
45.108 |
0.403 |
-13.16% |
0.403 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC128
|
-13.08% |
81.348 |
70.710 |
0.002 |
-13.07% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC31
|
-13.03% |
283.441 |
246.510 |
0.017 |
-13.23% |
0.017 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint8_t_To_uint16_t_
|
-12.96% |
4542.564 |
3953.764 |
0.300 |
-12.95% |
0.300 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC63
|
-12.80% |
332.284 |
289.766 |
0.141 |
-12.94% |
0.141 |
|
SingleSource/Benchmarks/Shootout-C++/Shootout-C++-matrix
Profile
|
-12.73% |
2.509 |
2.190 |
0.000 |
-12.70% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint16_t_To_uint8_t_
|
-12.42% |
4743.642 |
4154.438 |
0.270 |
-12.40% |
0.270 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC16
|
-12.06% |
155.819 |
137.032 |
0.005 |
-12.70% |
0.005 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, EqZero, None>
|
-12.00% |
16026.155 |
14102.404 |
0.900 |
-11.99% |
0.900 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIRST_SUM_RAW/5001
|
-11.87% |
20.184 |
17.788 |
0.626 |
2.55% |
0.626 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC8
|
-11.83% |
58.196 |
51.312 |
0.001 |
-13.69% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC8
|
-11.83% |
58.190 |
51.308 |
0.001 |
-13.69% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC2
|
-11.77% |
21.276 |
18.772 |
0.001 |
-11.77% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC15
|
-11.46% |
51.937 |
45.985 |
0.004 |
-11.46% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC15
|
-11.23% |
148.026 |
131.403 |
0.019 |
-11.70% |
0.019 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint32_t_To_uint16_t_
|
-11.21% |
9710.157 |
8621.942 |
182.063 |
-12.95% |
182.063 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC15
|
-11.18% |
106.378 |
94.485 |
0.007 |
-11.70% |
0.007 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC15
|
-11.17% |
106.369 |
94.482 |
0.031 |
-11.70% |
0.031 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC3
|
-11.11% |
22.526 |
20.022 |
0.001 |
-11.12% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC4
|
-11.11% |
22.527 |
20.023 |
0.002 |
-11.11% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC4
|
-11.11% |
22.526 |
20.023 |
0.000 |
-11.12% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_HYDRO_1D_RAW/5001
|
-10.88% |
17.420 |
15.524 |
0.720 |
-6.96% |
0.720 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_PRESSURE_CALC_RAW/5001
|
-10.64% |
47.371 |
42.330 |
0.829 |
-5.09% |
0.829 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_BAND_LIN_EQ_LAMBDA/171
|
-10.61% |
0.384 |
0.343 |
0.000 |
-6.33% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_BAND_LIN_EQ_RAW/171
|
-10.60% |
0.384 |
0.343 |
0.000 |
-6.33% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint64_t_To_uint16_t_
|
-10.58% |
19236.994 |
17200.887 |
240.704 |
-9.39% |
240.704 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC4
|
-10.53% |
23.778 |
21.275 |
0.001 |
-10.53% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC64
|
-10.46% |
53.810 |
48.182 |
0.000 |
-10.47% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint32_t_To_uint64_t_
|
-10.38% |
17041.048 |
15272.052 |
408.980 |
-11.19% |
408.980 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC16
|
-10.35% |
36.294 |
32.538 |
0.000 |
-10.35% |
0.000 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/16
|
-10.17% |
115.459 |
103.719 |
0.010 |
-10.17% |
0.010 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint64_t_To_uint32_t_
|
-10.15% |
18250.294 |
16397.912 |
206.023 |
-7.95% |
206.023 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint8_t_To_uint16_t_
|
-10.04% |
5851.462 |
5263.836 |
8.427 |
-10.03% |
8.427 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/64
|
-10.03% |
1913.420 |
1721.532 |
0.306 |
-10.02% |
0.306 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/32
|
-9.99% |
472.975 |
425.727 |
0.019 |
-9.99% |
0.019 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/256
|
-9.95% |
31443.383 |
28313.467 |
25.521 |
-9.97% |
25.521 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC16
|
-9.81% |
31.913 |
28.782 |
0.001 |
-8.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC8
|
-9.76% |
25.655 |
23.151 |
0.001 |
-9.76% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC8
|
-9.75% |
25.655 |
23.152 |
0.000 |
-9.76% |
0.000 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/128
|
-9.70% |
7909.355 |
7141.790 |
2.300 |
-9.80% |
2.300 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_DIFF_PREDICT_RAW/171
|
-9.67% |
12.298 |
11.109 |
0.116 |
-6.90% |
0.116 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC7
|
-9.62% |
32.539 |
29.409 |
0.000 |
-9.62% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC7
|
-9.52% |
26.280 |
23.777 |
0.001 |
-9.53% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC1
|
-9.50% |
13.137 |
11.890 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC31
|
-9.45% |
195.844 |
177.343 |
0.034 |
-9.74% |
0.034 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint8_t>/51
|
-9.41% |
121.579 |
110.144 |
0.035 |
19.07% |
0.035 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC7
|
-9.39% |
26.281 |
23.812 |
0.032 |
-9.40% |
0.032 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC127
|
-9.37% |
101.503 |
91.987 |
0.003 |
-9.71% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_cond_load_novec_int32_t_
|
-9.34% |
442258.547 |
400938.632 |
71.649 |
-2.38% |
71.649 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_only_autovec_int64_t_
|
-9.33% |
332345.130 |
301345.582 |
473.609 |
-9.58% |
473.609 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC8
|
-9.21% |
88.222 |
80.095 |
0.003 |
-10.41% |
0.003 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_DEL_DOT_VEC_2D_RAW/1
|
-9.21% |
286.938 |
260.518 |
0.156 |
-9.22% |
0.156 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_DEL_DOT_VEC_2D_LAMBDA/1
|
-9.16% |
286.952 |
260.662 |
0.149 |
-9.21% |
0.149 |
|
MultiSource/Benchmarks/FreeBench/pifft/pifft
Profile
|
-9.12% |
0.360 |
0.327 |
0.001 |
-8.75% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC32
|
-9.02% |
53.188 |
48.393 |
0.013 |
-9.02% |
0.013 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC7
|
-8.89% |
28.157 |
25.654 |
0.001 |
-8.90% |
0.001 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_runtime_checks_pass<4, int>
|
-8.81% |
16.812 |
15.330 |
0.001 |
-8.25% |
0.001 |
|
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% |
3.509 |
3.204 |
0.000 |
-8.70% |
0.000 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_runtime_checks_fail<4, int>
|
-8.66% |
16.783 |
15.329 |
0.000 |
-3.64% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC7
|
-8.53% |
80.723 |
73.834 |
0.004 |
-9.20% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC8
|
-8.52% |
29.411 |
26.905 |
0.001 |
-8.52% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint16_t_To_uint8_t_
|
-8.51% |
6809.873 |
6230.482 |
12.294 |
-8.59% |
12.294 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIRST_DIFF_LAMBDA/5001
|
-8.48% |
12.891 |
11.797 |
0.325 |
-3.23% |
0.325 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint8_t_To_uint32_t_
|
-8.35% |
12800.665 |
11731.537 |
20.630 |
-8.19% |
20.630 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC64
|
-8.06% |
93.238 |
85.719 |
0.004 |
-8.07% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC16
|
-7.85% |
31.914 |
29.409 |
0.002 |
-7.85% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC16
|
-7.85% |
31.913 |
29.409 |
0.001 |
-7.84% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC32
|
-7.81% |
40.045 |
36.919 |
0.001 |
-7.82% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint16_t_To_uint64_t_
|
-7.80% |
20217.022 |
18639.951 |
93.870 |
-7.46% |
93.870 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_PRESSURE_CALC_LAMBDA/5001
|
-7.74% |
45.770 |
42.229 |
0.984 |
-3.97% |
0.984 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC15
|
-7.69% |
32.536 |
30.035 |
0.001 |
-7.69% |
0.001 |
|
MultiSource/Benchmarks/VersaBench/beamformer/beamformer
Profile
|
-7.68% |
5.201 |
4.802 |
0.003 |
-7.67% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC15
|
-7.65% |
54.439 |
50.277 |
0.016 |
-7.65% |
0.016 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_HYDRO_2D_LAMBDA/171
|
-7.57% |
88.846 |
82.122 |
0.510 |
-7.37% |
0.510 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_DEL_DOT_VEC_2D_LAMBDA/0
|
-7.57% |
1800.486 |
1664.229 |
5.530 |
-7.13% |
5.530 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC31
|
-7.55% |
74.465 |
68.843 |
0.013 |
-7.55% |
0.013 |
|
MultiSource/Benchmarks/Trimaran/enc-md5/enc-md5
Profile
|
-7.54% |
3.508 |
3.243 |
0.000 |
-7.49% |
0.000 |
|
MultiSource/Applications/lambda-0.1.3/lambda
Profile
|
-7.43% |
15.898 |
14.717 |
0.007 |
-7.27% |
0.007 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC2
|
-7.41% |
16.896 |
15.644 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_xor_no_runtime_checks_needed<16, int>
|
-7.41% |
16.894 |
15.643 |
0.001 |
-7.42% |
0.001 |
|
MicroBenchmarks/ImageProcessing/Dilate/Dilate.test:BENCHMARK_DILATE/128
|
-7.41% |
226.320 |
209.556 |
6.226 |
-8.08% |
6.226 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint16_t_To_uint64_t_
|
-7.29% |
25024.032 |
23199.290 |
46.308 |
-7.15% |
46.308 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC128
|
-7.22% |
173.340 |
160.833 |
0.004 |
-7.21% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint8_t>/127
|
-7.21% |
138.909 |
128.894 |
0.019 |
-7.21% |
0.019 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIND_FIRST_MIN_RAW/171
|
-7.18% |
1.497 |
1.390 |
0.000 |
-7.14% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_HYDRO_2D_RAW/171
|
-7.14% |
88.492 |
82.178 |
0.522 |
-7.28% |
0.522 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC15
|
-7.07% |
45.111 |
41.924 |
0.002 |
-6.94% |
0.002 |
|
SingleSource/Benchmarks/Misc/pi
Profile
|
-7.00% |
1.782 |
1.657 |
0.000 |
-7.02% |
0.000 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C++/miniFE/miniFE
Profile
|
-6.99% |
15.894 |
14.783 |
0.099 |
-7.43% |
0.099 |
|
MultiSource/Benchmarks/McCat/12-IOtest/iotest
Profile
|
-6.98% |
1.808 |
1.682 |
0.015 |
-7.83% |
0.015 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC63
|
-6.96% |
114.511 |
106.539 |
0.070 |
-6.96% |
0.070 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_DEL_DOT_VEC_2D_RAW/0
|
-6.92% |
1791.866 |
1667.923 |
1.024 |
-7.38% |
1.024 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint8_t>/28
|
-6.87% |
81.373 |
75.785 |
0.027 |
12.13% |
0.027 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC4
|
-6.84% |
54.407 |
50.683 |
0.003 |
-8.95% |
0.003 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_BAND_LIN_EQ_RAW/5001
|
-6.76% |
21.481 |
20.029 |
0.277 |
-2.88% |
0.277 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC127
|
-6.61% |
194.607 |
181.750 |
0.111 |
-6.61% |
0.111 |
|
SingleSource/Benchmarks/Misc/flops-6
Profile
|
-6.55% |
1.311 |
1.225 |
0.001 |
-6.63% |
0.001 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_xor_runtime_checks_fail<16, int>
|
-6.52% |
28.784 |
26.906 |
0.003 |
-6.52% |
0.003 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_xor_runtime_checks_pass<16, int>
|
-6.52% |
28.782 |
26.905 |
0.000 |
-6.52% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC127
|
-6.43% |
68.208 |
63.824 |
0.001 |
-6.54% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC128
|
-6.42% |
68.205 |
63.823 |
0.002 |
-7.24% |
0.002 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_BAND_LIN_EQ_LAMBDA/5001
|
-6.42% |
21.421 |
20.045 |
0.056 |
-3.63% |
0.056 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIRST_SUM_LAMBDA/44217
|
-6.40% |
143.463 |
134.281 |
1.005 |
-19.63% |
1.005 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_only_autovec_int32_t_
|
-6.37% |
180803.845 |
169279.532 |
163.032 |
-6.54% |
163.032 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC15
|
-6.34% |
39.421 |
36.920 |
0.000 |
-6.35% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint16_t>/127
|
-6.31% |
138.915 |
130.154 |
0.005 |
-6.30% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC127
|
-6.30% |
2408.216 |
2256.416 |
34.489 |
-7.01% |
34.489 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC4
|
-6.25% |
40.045 |
37.543 |
0.002 |
-9.10% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC4
|
-6.24% |
40.046 |
37.545 |
0.002 |
-9.09% |
0.002 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIND_FIRST_MIN_RAW/5001
|
-6.23% |
45.264 |
42.444 |
0.010 |
-6.39% |
0.010 |
|
SingleSource/Benchmarks/Misc-C++/Large/sphereflake
Profile
|
-6.23% |
20.012 |
18.766 |
0.003 |
-6.18% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC16
|
-6.16% |
40.673 |
38.168 |
0.003 |
-6.16% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC32
|
-6.12% |
61.323 |
57.568 |
0.003 |
-6.12% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC1
|
-6.07% |
88.890 |
83.499 |
2.060 |
-6.16% |
2.060 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_nested_cond_load_novec_int32_t_
|
-6.03% |
666834.086 |
626632.756 |
63.913 |
-2.87% |
63.913 |
|
MultiSource/Benchmarks/MiBench/telecomm-gsm/telecomm-gsm
Profile
|
-6.02% |
0.664 |
0.624 |
0.000 |
-5.96% |
0.000 |
|
SingleSource/Benchmarks/Misc/perlin
Profile
|
-5.98% |
6.599 |
6.204 |
0.000 |
-5.97% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC63
|
-5.94% |
73.844 |
69.456 |
0.006 |
-6.42% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint8_t>/65
|
-5.92% |
95.119 |
89.484 |
0.004 |
-5.92% |
0.004 |
|
SingleSource/Benchmarks/Misc/oourafft
Profile
|
-5.89% |
15.364 |
14.459 |
0.049 |
-4.20% |
0.049 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint32_t>/127
|
-5.89% |
138.294 |
130.151 |
0.005 |
-5.88% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC3
|
-5.88% |
21.276 |
20.024 |
0.000 |
0.01% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopWithReductionTC128
|
-5.88% |
77.588 |
73.025 |
0.913 |
1.47% |
0.913 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint32_t_To_uint64_t_
|
-5.85% |
21534.484 |
20274.224 |
69.716 |
-5.49% |
69.716 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopWithReductionTC127
|
-5.82% |
86.976 |
81.913 |
0.483 |
1.47% |
0.483 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC16
|
-5.66% |
33.165 |
31.287 |
0.000 |
-5.66% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC32
|
-5.63% |
44.424 |
41.921 |
0.003 |
-5.64% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC32
|
-5.63% |
44.427 |
41.925 |
0.001 |
-5.64% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC31
|
-5.56% |
45.053 |
42.549 |
0.001 |
-5.58% |
0.001 |
|
MultiSource/Benchmarks/SciMark2-C/scimark2
Profile
|
-5.55% |
107.702 |
101.720 |
0.069 |
-5.50% |
0.069 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC31
|
-5.55% |
45.050 |
42.549 |
0.003 |
-5.56% |
0.003 |
|
External/SPEC/CFP2017rate/538.imagick_r/538.imagick_r
Profile
|
-5.51% |
291.406 |
275.358 |
0.315 |
-5.73% |
0.315 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint8_t_To_uint16_t_
|
-5.47% |
3628.908 |
3430.274 |
5.415 |
-5.59% |
5.415 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC31
|
-5.46% |
242.458 |
229.209 |
0.027 |
-4.98% |
0.027 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint32_t>/999
|
-5.38% |
696.443 |
658.955 |
0.041 |
-5.39% |
0.041 |
|
SingleSource/Benchmarks/Polybench/stencils/jacobi-2d/jacobi-2d
Profile
|
-5.37% |
32.057 |
30.334 |
0.087 |
-5.86% |
0.087 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIND_FIRST_MIN_RAW/44217
|
-5.37% |
389.258 |
368.370 |
0.256 |
-5.45% |
0.256 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC1
|
-5.27% |
11.889 |
11.263 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint32_t>/999
|
-5.21% |
1364.961 |
1293.844 |
0.090 |
-5.22% |
0.090 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_PIC_2D_LAMBDA/171
|
-5.17% |
13.455 |
12.760 |
0.055 |
-5.47% |
0.055 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC15
|
-5.14% |
127.652 |
121.086 |
0.017 |
-5.59% |
0.017 |
|
MultiSource/Benchmarks/Rodinia/hotspot/hotspot
Profile
|
-5.07% |
2.035 |
1.931 |
0.003 |
-5.14% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC32
|
-4.99% |
50.056 |
47.558 |
0.035 |
-4.98% |
0.035 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_PIC_2D_RAW/171
|
-4.97% |
13.503 |
12.831 |
0.057 |
-5.23% |
0.057 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC4
|
-4.88% |
25.656 |
24.404 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint32_t>/256
|
-4.81% |
364.175 |
346.650 |
0.012 |
-4.81% |
0.012 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC15
|
-4.81% |
32.537 |
30.974 |
0.001 |
-4.81% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1LoopWithReductionTC3
|
-4.76% |
13.140 |
12.515 |
0.001 |
5.26% |
0.001 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<32, LessThanZero, None>
|
-4.70% |
4630.366 |
4412.816 |
29.219 |
0.01% |
29.219 |
|
SingleSource/Benchmarks/Misc/revertBits
Profile
|
-4.67% |
0.641 |
0.611 |
0.000 |
-4.69% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC31
|
-4.67% |
93.871 |
89.487 |
0.119 |
-4.65% |
0.119 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint16_t>/65
|
-4.62% |
95.122 |
90.732 |
0.005 |
-4.61% |
0.005 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIRST_SUM_LAMBDA/5001
|
-4.61% |
18.643 |
17.783 |
0.332 |
0.99% |
0.332 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_runtime_checks_fail<16, int>
|
-4.60% |
54.438 |
51.933 |
0.002 |
-4.60% |
0.002 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_runtime_checks_pass<16, int>
|
-4.59% |
54.438 |
51.936 |
0.001 |
-4.59% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC1
|
-4.56% |
13.769 |
13.142 |
0.001 |
-8.70% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC4
|
-4.55% |
13.766 |
13.140 |
0.001 |
-8.71% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC7
|
-4.55% |
13.766 |
13.140 |
0.000 |
-8.70% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC15
|
-4.55% |
13.767 |
13.140 |
0.000 |
-8.70% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC16
|
-4.55% |
13.767 |
13.140 |
0.002 |
-8.69% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC2
|
-4.55% |
13.767 |
13.141 |
0.001 |
-0.10% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC1
|
-4.55% |
13.766 |
13.140 |
0.000 |
-8.70% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC16
|
-4.55% |
13.766 |
13.140 |
0.001 |
-8.71% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC3
|
-4.55% |
13.766 |
13.140 |
0.001 |
-8.70% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC4
|
-4.54% |
13.766 |
13.140 |
0.000 |
-8.70% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC3
|
-4.54% |
13.765 |
13.140 |
0.001 |
-8.70% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC2
|
-4.54% |
13.766 |
13.141 |
0.000 |
-8.69% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC7
|
-4.54% |
13.766 |
13.141 |
0.001 |
-8.69% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC8
|
-4.54% |
13.766 |
13.141 |
0.000 |
-8.70% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC2
|
-4.54% |
13.766 |
13.140 |
0.000 |
-8.69% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC8
|
-4.54% |
13.765 |
13.140 |
0.000 |
-8.70% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC15
|
-4.54% |
13.766 |
13.141 |
0.000 |
-8.70% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC7
|
-4.47% |
70.085 |
66.951 |
0.002 |
-5.33% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC7
|
-4.47% |
70.084 |
66.951 |
0.004 |
-5.32% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC31
|
-4.47% |
70.086 |
66.955 |
0.005 |
-4.46% |
0.005 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_PRESSURE_CALC_RAW/44217
|
-4.44% |
503.223 |
480.887 |
1.245 |
-4.24% |
1.245 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C++/HPCCG/HPCCG
Profile
|
-4.41% |
3.919 |
3.746 |
0.042 |
-4.30% |
0.042 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint16_t_To_uint8_t_
|
-4.36% |
2873.375 |
2748.024 |
7.071 |
-4.52% |
7.071 |
|
MultiSource/Benchmarks/TSVC/Packing-flt/Packing-flt
Profile
|
-4.35% |
35.388 |
33.847 |
0.446 |
-2.42% |
0.446 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC64
|
-4.35% |
43.174 |
41.297 |
0.001 |
-4.35% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC63
|
-4.35% |
43.177 |
41.300 |
0.001 |
-4.61% |
0.001 |
|
External/SPEC/CFP2017rate/519.lbm_r/519.lbm_r
Profile
|
-4.25% |
200.756 |
192.218 |
1.380 |
-4.22% |
1.380 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_ENERGY_CALC_LAMBDA/171
|
-4.24% |
14.202 |
13.600 |
0.018 |
-4.55% |
0.018 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint64_t>/999
|
-4.23% |
1811.241 |
1734.665 |
0.104 |
-4.23% |
0.104 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_FLOYD_DITHER/256
|
-4.18% |
1820.536 |
1744.436 |
6.088 |
0.63% |
6.088 |
|
SingleSource/Benchmarks/Misc/flops-5
Profile
|
-4.17% |
2.021 |
1.937 |
0.001 |
-4.15% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_PRESSURE_CALC_LAMBDA/44217
|
-4.17% |
503.461 |
482.466 |
3.842 |
-3.22% |
3.842 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1LoopWithReductionTC4
|
-4.16% |
15.017 |
14.391 |
0.000 |
2.26% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint64_t>/999
|
-4.15% |
3594.952 |
3445.852 |
0.350 |
-4.14% |
0.350 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_cond_load_autovec_int64_t_
|
-4.14% |
554550.553 |
531574.866 |
892.698 |
-3.81% |
892.698 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_HYDRO_1D_LAMBDA/5001
|
-4.08% |
16.998 |
16.304 |
0.142 |
-5.06% |
0.142 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint64_t>/256
|
-4.05% |
935.427 |
897.566 |
0.004 |
-4.06% |
0.004 |
|
SingleSource/Benchmarks/Polybench/linear-algebra/kernels/mvt/mvt
Profile
|
-4.04% |
0.857 |
0.823 |
0.003 |
1.18% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC31
|
-4.04% |
61.947 |
59.445 |
0.001 |
-4.04% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_ENERGY_CALC_RAW/171
|
-4.03% |
14.204 |
13.632 |
0.013 |
-4.27% |
0.013 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC3
|
-4.01% |
46.931 |
45.049 |
0.002 |
-5.27% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint8_t_To_uint64_t_
|
-4.01% |
23411.929 |
22473.222 |
15.132 |
-4.30% |
15.132 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_only_autovec_uint8_t_
|
-3.98% |
96157.150 |
92326.491 |
5.724 |
-3.98% |
5.724 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint32_t>/65
|
-3.97% |
94.486 |
90.733 |
0.001 |
-3.97% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC32
|
-3.96% |
63.199 |
60.696 |
0.000 |
-3.96% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint32_t>/256
|
-3.95% |
221.492 |
212.739 |
0.042 |
-3.96% |
0.042 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopWithReductionTC3
|
-3.85% |
16.268 |
15.642 |
0.001 |
-0.00% |
0.001 |
|
External/SPEC/CFP2017rate/544.nab_r/544.nab_r
Profile
|
-3.81% |
476.174 |
458.018 |
0.105 |
-4.16% |
0.105 |
|
MicroBenchmarks/ImageProcessing/Dilate/Dilate.test:BENCHMARK_DILATE/512
|
-3.81% |
3588.880 |
3452.047 |
12.677 |
-3.68% |
12.677 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint64_t_To_uint32_t_
|
-3.78% |
19354.330 |
18623.180 |
37.031 |
-3.47% |
37.031 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC1
|
-3.74% |
22.752 |
21.902 |
0.001 |
-2.77% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC2
|
-3.71% |
16.895 |
16.268 |
0.001 |
-0.01% |
0.001 |
|
SingleSource/Benchmarks/Shootout/Shootout-matrix
Profile
|
-3.69% |
3.864 |
3.721 |
0.000 |
-3.68% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint32_t_To_uint16_t_
|
-3.65% |
9761.595 |
9405.213 |
42.820 |
-4.80% |
42.820 |
|
MultiSource/Benchmarks/nbench/nbench
Profile
|
-3.65% |
6.111 |
5.888 |
0.003 |
-3.89% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint64_t>/256
|
-3.64% |
514.371 |
495.642 |
0.013 |
-3.65% |
0.013 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC64
|
-3.60% |
69.455 |
66.953 |
0.001 |
-3.61% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC64
|
-3.60% |
69.454 |
66.955 |
0.002 |
-3.60% |
0.002 |
|
SingleSource/Benchmarks/BenchmarkGame/n-body
Profile
|
-3.58% |
2.731 |
2.633 |
0.000 |
21.69% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint64_t_To_uint8_t_
|
-3.57% |
19729.887 |
19024.562 |
40.425 |
-4.12% |
40.425 |
|
MultiSource/Benchmarks/TSVC/NodeSplitting-dbl/NodeSplitting-dbl
Profile
|
-3.57% |
26.799 |
25.841 |
0.269 |
-2.17% |
0.269 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC63
|
-3.57% |
70.079 |
67.578 |
0.001 |
-3.57% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC63
|
-3.56% |
70.080 |
67.582 |
0.013 |
-3.58% |
0.013 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopWithReductionTC4
|
-3.46% |
18.147 |
17.520 |
0.001 |
-0.00% |
0.001 |
|
MultiSource/Applications/JM/lencod/lencod
Profile
|
-3.43% |
32.730 |
31.607 |
0.038 |
-2.87% |
0.038 |
|
MultiSource/Benchmarks/Rodinia/pathfinder/pathfinder
Profile
|
-3.42% |
1.263 |
1.220 |
0.009 |
-3.04% |
0.009 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<32, LessThanZero, Mid>
|
-3.40% |
4651.179 |
4492.995 |
6.231 |
-1.71% |
6.231 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC31
|
-3.38% |
60.230 |
58.193 |
0.005 |
-3.46% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC2
|
-3.38% |
36.916 |
35.668 |
0.001 |
-6.56% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC64
|
-3.38% |
111.392 |
107.631 |
0.006 |
-3.37% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC7
|
-3.34% |
37.545 |
36.293 |
0.002 |
-0.01% |
0.002 |
|
MicroBenchmarks/ImageProcessing/Dilate/Dilate.test:BENCHMARK_DILATE/256
|
-3.17% |
1049.895 |
1016.607 |
3.153 |
-4.75% |
3.153 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint16_t_To_uint8_t_
|
-3.16% |
4514.006 |
4371.324 |
10.309 |
-3.23% |
10.309 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint16_t>/999
|
-3.15% |
514.978 |
498.753 |
0.013 |
-3.16% |
0.013 |
|
SingleSource/Benchmarks/Shootout/Shootout-lists
Profile
|
-3.15% |
11.316 |
10.960 |
0.005 |
-3.12% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1BigLoopWithReductionTC1
|
-3.13% |
20.023 |
19.397 |
0.004 |
-3.14% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint16_t_To_uint32_t_
|
-3.11% |
11248.542 |
10898.666 |
12.483 |
-3.91% |
12.483 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchVecWithRuntimeChecks4PointersDBeforeA/1000
|
-3.06% |
5019964.007 |
4866129.042 |
562.436 |
-3.06% |
562.436 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1LoopWithReductionTC7
|
-3.03% |
20.649 |
20.023 |
0.001 |
3.20% |
0.001 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<32, EqZero, None>
|
-3.01% |
4548.494 |
4411.358 |
43.094 |
0.00% |
43.094 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC8
|
-2.98% |
41.923 |
40.674 |
0.003 |
-0.01% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint8_t>/16
|
-2.95% |
59.566 |
57.807 |
0.258 |
7.41% |
0.258 |
|
MicroBenchmarks/ImageProcessing/Blur/blur.test:BENCHMARK_boxBlurKernel/128
|
-2.92% |
431.757 |
419.148 |
2.382 |
-3.48% |
2.382 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_FLOYD_DITHER/128
|
-2.87% |
438.358 |
425.759 |
1.723 |
-3.12% |
1.723 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1LoopWithReductionTC8
|
-2.85% |
22.543 |
21.900 |
0.001 |
2.93% |
0.001 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C/CoMD/CoMD
Profile
|
-2.85% |
9.907 |
9.625 |
0.002 |
-2.76% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint16_t>/999
|
-2.83% |
1013.703 |
985.061 |
0.129 |
-2.84% |
0.129 |
|
MultiSource/Benchmarks/FreeBench/mason/mason
Profile
|
-2.74% |
0.553 |
0.538 |
0.000 |
-2.72% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC8
|
-2.68% |
25.719 |
25.029 |
0.001 |
-7.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopWithReductionTC7
|
-2.64% |
23.779 |
23.151 |
0.001 |
-0.00% |
0.001 |
|
MultiSource/Benchmarks/sim/sim
Profile
|
-2.62% |
9.703 |
9.449 |
0.012 |
-2.60% |
0.012 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC63
|
-2.61% |
120.146 |
117.012 |
0.008 |
-2.61% |
0.008 |
|
SingleSource/Benchmarks/Misc-C++/oopack_v1p8
Profile
|
-2.60% |
0.479 |
0.467 |
0.000 |
-10.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint8_t>/10
|
-2.55% |
48.807 |
47.560 |
0.010 |
2.47% |
0.010 |
|
SingleSource/Benchmarks/BenchmarkGame/puzzle
Profile
|
-2.53% |
0.872 |
0.849 |
0.003 |
-2.22% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint8_t_To_uint32_t_
|
-2.53% |
7077.728 |
6898.648 |
1.425 |
-2.52% |
1.425 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint8_t>/28
|
-2.53% |
125.666 |
122.490 |
0.072 |
18.81% |
0.072 |
|
MicroBenchmarks/LCALS/SubsetBRawLoops/lcalsBRaw.test:BM_INIT3_RAW/171
|
-2.51% |
0.424 |
0.414 |
0.004 |
-0.30% |
0.004 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<31, LessThanZero, First>
|
-2.49% |
3314.766 |
3232.250 |
6.283 |
-0.01% |
6.283 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_FLOYD_DITHER/512
|
-2.48% |
6653.843 |
6488.801 |
36.026 |
-2.35% |
36.026 |
|
MultiSource/Benchmarks/mafft/pairlocalalign
Profile
|
-2.43% |
93.912 |
91.629 |
0.368 |
-2.59% |
0.368 |
|
MultiSource/Benchmarks/FreeBench/fourinarow/fourinarow
Profile
|
-2.43% |
0.651 |
0.635 |
0.001 |
-2.43% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchVecWithRuntimeChecks4PointersDBeforeA/32
|
-2.41% |
166186.372 |
162185.542 |
176.558 |
-2.42% |
176.558 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC63
|
-2.40% |
130.162 |
127.032 |
0.074 |
-2.41% |
0.074 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC63
|
-2.34% |
107.004 |
104.500 |
0.003 |
-2.34% |
0.003 |
|
MultiSource/Benchmarks/Bullet/bullet
Profile
|
-2.31% |
30.487 |
29.784 |
0.165 |
-2.12% |
0.165 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<63, LessThanZero, First>
|
-2.29% |
1640.414 |
1602.872 |
2.167 |
0.05% |
2.167 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_EOS_RAW/5001
|
-2.22% |
30.274 |
29.600 |
0.193 |
-0.54% |
0.193 |
|
SingleSource/Benchmarks/Misc/flops-1
Profile
|
-2.18% |
9.002 |
8.806 |
0.000 |
-2.15% |
0.000 |
|
SingleSource/Benchmarks/Misc-C++/Large/ray
Profile
|
-2.10% |
12.103 |
11.849 |
0.002 |
-2.08% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC128
|
-2.10% |
119.517 |
117.013 |
0.726 |
-2.10% |
0.726 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC128
|
-2.09% |
119.509 |
117.006 |
0.005 |
-2.10% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC127
|
-2.09% |
120.148 |
117.635 |
0.003 |
-2.09% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC127
|
-2.09% |
120.140 |
117.633 |
0.009 |
-2.09% |
0.009 |
|
MultiSource/Benchmarks/Olden/health/health
Profile
|
-2.09% |
1.594 |
1.560 |
0.004 |
-1.95% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint32_t_To_uint64_t_
|
-2.07% |
26317.049 |
25771.151 |
46.689 |
-1.94% |
46.689 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<8, GreaterThanZero, First>
|
-2.04% |
12147.707 |
11899.465 |
8.046 |
0.30% |
8.046 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC32
|
-2.04% |
30.661 |
30.034 |
0.002 |
-4.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC31
|
-2.04% |
30.661 |
30.035 |
0.000 |
-3.70% |
0.000 |
|
External/SPEC/CINT2017rate/531.deepsjeng_r/531.deepsjeng_r
Profile
|
-2.01% |
259.545 |
254.340 |
0.432 |
-2.22% |
0.432 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_nested_cond_load_novec_uint8_t_
|
-1.91% |
502796.089 |
493208.302 |
421.857 |
-2.28% |
421.857 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_EOS_RAW/171
|
-1.91% |
0.872 |
0.855 |
0.001 |
-1.80% |
0.001 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C/SimpleMOC/SimpleMOC
Profile
|
-1.89% |
10.429 |
10.232 |
0.031 |
-1.67% |
0.031 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_ENERGY_CALC_LAMBDA/44217
|
-1.89% |
4327.615 |
4245.683 |
10.047 |
-1.82% |
10.047 |
|
MicroBenchmarks/ImageProcessing/Blur/blur.test:BENCHMARK_boxBlurKernel/512
|
-1.86% |
6643.733 |
6520.275 |
9.950 |
-1.41% |
9.950 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<16, LessThanZero, Mid>
|
-1.85% |
8657.684 |
8497.531 |
4.937 |
-1.88% |
4.937 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint16_t>/256
|
-1.83% |
272.803 |
267.812 |
0.024 |
-1.84% |
0.024 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_only_autovec_int64_t_
|
-1.81% |
1442869.579 |
1416727.769 |
1477.944 |
-2.09% |
1477.944 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint8_t>/16
|
-1.81% |
86.369 |
84.809 |
0.137 |
12.26% |
0.137 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_INT_PREDICT_LAMBDA/171
|
-1.80% |
6.919 |
6.795 |
0.009 |
-1.88% |
0.009 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC15
|
-1.78% |
70.080 |
68.832 |
0.004 |
-0.00% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC128
|
-1.78% |
211.514 |
207.751 |
1.019 |
-1.78% |
1.019 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_ENERGY_CALC_RAW/44217
|
-1.77% |
4325.149 |
4248.723 |
6.174 |
-1.91% |
6.174 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1LoopWithReductionTC15
|
-1.75% |
35.666 |
35.041 |
0.001 |
1.81% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_INT_PREDICT_RAW/171
|
-1.71% |
6.925 |
6.806 |
0.011 |
-1.71% |
0.011 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint64_t>/51
|
-1.68% |
148.285 |
145.792 |
0.009 |
-1.70% |
0.009 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1LoopWithReductionTC16
|
-1.67% |
37.544 |
36.917 |
0.001 |
1.71% |
0.001 |
|
MultiSource/Benchmarks/Fhourstones-3.1/fhourstones3.1
Profile
|
-1.67% |
3.978 |
3.912 |
0.005 |
-1.50% |
0.005 |
|
MultiSource/Benchmarks/VersaBench/ecbdes/ecbdes
Profile
|
-1.66% |
5.141 |
5.056 |
0.001 |
-1.63% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_EOS_LAMBDA/171
|
-1.66% |
0.871 |
0.856 |
0.001 |
-1.65% |
0.001 |
|
MultiSource/Benchmarks/ASC_Sequoia/AMGmk/AMGmk
Profile
|
-1.65% |
33.357 |
32.806 |
0.018 |
-0.76% |
0.018 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint16_t_To_uint32_t_
|
-1.62% |
13521.381 |
13301.802 |
19.120 |
-1.35% |
19.120 |
|
MultiSource/Applications/obsequi/Obsequi
Profile
|
-1.57% |
7.714 |
7.592 |
0.011 |
-0.90% |
0.011 |
|
SingleSource/Benchmarks/Misc/mandel-2
Profile
|
-1.56% |
2.536 |
2.496 |
0.000 |
-1.55% |
0.000 |
|
MultiSource/Benchmarks/TSVC/ControlLoops-flt/ControlLoops-flt
Profile
|
-1.56% |
5.454 |
5.368 |
0.032 |
-1.45% |
0.032 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_csa_with_in_loop_arith_novec_int64_t_
|
-1.49% |
1028049.751 |
1012701.996 |
169.121 |
-1.50% |
169.121 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, LessThanZero, Last>
|
-1.48% |
56598.350 |
55763.188 |
287.570 |
-0.50% |
287.570 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC64
|
-1.44% |
86.348 |
85.102 |
0.168 |
-1.45% |
0.168 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint8_t>/51
|
-1.44% |
197.444 |
194.602 |
0.016 |
25.99% |
0.016 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC127
|
-1.42% |
220.268 |
217.132 |
0.021 |
-1.43% |
0.021 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopWithReductionTC31
|
-1.41% |
44.426 |
43.800 |
0.004 |
1.43% |
0.004 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<31, LessThanZero, None>
|
-1.37% |
8052.774 |
7942.789 |
12.397 |
-0.70% |
12.397 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint64_t>/51
|
-1.36% |
229.013 |
225.892 |
0.014 |
-1.36% |
0.014 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_BAND_LIN_EQ_LAMBDA/44217
|
-1.33% |
175.723 |
173.378 |
0.338 |
4.54% |
0.338 |
|
External/SPEC/CINT2017rate/525.x264_r/525.x264_r
Profile
|
-1.30% |
130.004 |
128.318 |
0.147 |
-0.87% |
0.147 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC127
|
-1.27% |
197.099 |
194.593 |
0.013 |
-1.27% |
0.013 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC128
|
-1.26% |
198.359 |
195.858 |
0.010 |
-1.27% |
0.010 |
|
External/SPEC/CFP2017rate/511.povray_r/511.povray_r
Profile
|
-1.25% |
33.877 |
33.454 |
0.061 |
-0.98% |
0.061 |
|
MultiSource/Benchmarks/MallocBench/cfrac/cfrac
Profile
|
-1.22% |
2.780 |
2.747 |
0.005 |
-1.20% |
0.005 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<32, GreaterThanZero, None>
|
-1.20% |
4464.748 |
4411.077 |
15.637 |
-0.41% |
15.637 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopFrom_uint64_t_To_uint16_t_
|
-1.18% |
14824.221 |
14648.823 |
17.199 |
-1.26% |
17.199 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_sinhf_novec_float_
|
-1.16% |
2242.880 |
2216.947 |
0.587 |
-1.11% |
0.587 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint8_t>/999
|
-1.15% |
326.026 |
322.272 |
0.040 |
10.81% |
0.040 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_sinhf_autovec_float_
|
-1.14% |
2243.363 |
2217.701 |
0.583 |
-1.11% |
0.583 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<3, GreaterThanZero, Mid>
|
-1.14% |
37621.228 |
37192.126 |
105.848 |
0.05% |
105.848 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_sinh_novec_double_
|
-1.14% |
2473.220 |
2445.044 |
1.878 |
-1.17% |
1.878 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, LessThanZero, First>
|
-1.14% |
23989.490 |
23716.612 |
25.196 |
-0.02% |
25.196 |
|
SingleSource/Benchmarks/SmallPT/smallpt
Profile
|
-1.11% |
30.037 |
29.705 |
0.001 |
-1.08% |
0.001 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<8, GreaterThanZero, Mid>
|
-1.06% |
19436.970 |
19230.844 |
1.694 |
0.00% |
1.694 |
|
MultiSource/Applications/hexxagon/hexxagon
Profile
|
-1.05% |
14.886 |
14.730 |
0.003 |
0.83% |
0.003 |
|
External/SPEC/CFP2017rate/526.blender_r/526.blender_r
Profile
|
-1.02% |
889.961 |
880.917 |
1.929 |
-0.48% |
1.929 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C++/CLAMR/CLAMR
Profile
|
-1.01% |
12.271 |
12.147 |
0.024 |
-0.54% |
0.024 |