|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_HYDRO_2D_LAMBDA/44217
|
-64.18% |
88865.479 |
31831.504 |
8824.912 |
-64.99% |
8824.912 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_HYDRO_2D_LAMBDA/5001
|
-60.43% |
9272.607 |
3669.200 |
945.998 |
-59.74% |
945.998 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_DISC_ORD_LAMBDA/44217
|
-54.25% |
14169.502 |
6481.888 |
1712.251 |
-53.88% |
1712.251 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint64_t_To_uint32_t_
|
-52.37% |
35246.326 |
16788.448 |
184.774 |
-52.46% |
184.774 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint64_t_To_uint16_t_
|
-51.99% |
35792.213 |
17184.326 |
67.708 |
-51.84% |
67.708 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C/miniGMG/miniGMG
Profile
|
-49.95% |
9.187 |
4.598 |
0.288 |
-49.97% |
0.288 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint64_t_To_uint8_t_
|
-49.53% |
37027.647 |
18687.448 |
2.173 |
-49.58% |
2.173 |
|
SingleSource/Benchmarks/Polybench/stencils/seidel-2d/seidel-2d
Profile
|
-47.46% |
230.508 |
121.118 |
0.273 |
0.02% |
0.273 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_DIFF_PREDICT_RAW/44217
|
-44.90% |
24439.711 |
13467.157 |
249.624 |
-42.20% |
249.624 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint16_t_To_uint64_t_
|
-43.87% |
18639.654 |
10462.873 |
2.129 |
-43.97% |
2.129 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_DIFF_PREDICT_LAMBDA/44217
|
-41.62% |
23106.077 |
13489.546 |
336.932 |
-41.61% |
336.932 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint8_t_To_uint64_t_
|
-41.05% |
17859.080 |
10527.923 |
7.445 |
-40.85% |
7.445 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_DIFF_PREDICT_LAMBDA/5001
|
-41.04% |
2559.975 |
1509.263 |
39.987 |
-39.86% |
39.987 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_PIC_1D_LAMBDA/44217
|
-41.04% |
13509.061 |
7964.807 |
1459.789 |
-40.85% |
1459.789 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint64_t_To_uint32_t_
|
-40.66% |
38275.289 |
22710.741 |
11.462 |
-40.48% |
11.462 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_DIFF_PREDICT_RAW/5001
|
-40.44% |
2532.671 |
1508.454 |
26.799 |
-41.41% |
26.799 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIRST_DIFF_RAW/44217
|
-38.46% |
167.129 |
102.844 |
1.609 |
-27.82% |
1.609 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/32
|
-36.70% |
1396.194 |
883.824 |
0.068 |
-36.69% |
0.068 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/64
|
-36.67% |
6181.751 |
3914.604 |
0.279 |
-36.68% |
0.279 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/16
|
-36.64% |
279.503 |
177.096 |
0.010 |
-36.63% |
0.010 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/256
|
-36.20% |
107099.327 |
68331.900 |
50.694 |
-36.23% |
50.694 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/128
|
-36.12% |
26265.460 |
16779.046 |
8.978 |
-36.13% |
8.978 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint32_t_To_uint64_t_
|
-35.56% |
22572.826 |
14545.487 |
259.995 |
-35.99% |
259.995 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIRST_DIFF_LAMBDA/44217
|
-34.52% |
153.367 |
100.429 |
0.952 |
-30.65% |
0.952 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint64_t_To_uint8_t_
|
-34.44% |
30186.058 |
19790.086 |
16.437 |
-34.28% |
16.437 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint64_t_To_uint16_t_
|
-33.84% |
28935.744 |
19142.799 |
46.574 |
-33.87% |
46.574 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint64_t_To_uint16_t_
|
-28.45% |
25914.085 |
18542.477 |
17.116 |
-28.40% |
17.116 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_INT_PREDICT_RAW/44217
|
-28.27% |
11156.553 |
8002.301 |
85.278 |
-11.57% |
85.278 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint32_t_To_uint8_t_
|
-28.05% |
13507.676 |
9718.304 |
4.661 |
-27.85% |
4.661 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC128
|
-27.60% |
1293.880 |
936.752 |
2.916 |
-27.54% |
2.916 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC64
|
-27.07% |
654.263 |
477.180 |
1.979 |
-26.99% |
1.979 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC128
|
-27.06% |
558.653 |
407.501 |
0.060 |
-26.91% |
0.060 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC32
|
-26.96% |
334.562 |
244.363 |
0.987 |
-26.82% |
0.987 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_PIC_2D_RAW/44217
|
-26.74% |
11802.951 |
8647.280 |
517.570 |
-22.90% |
517.570 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC16
|
-26.54% |
174.401 |
128.109 |
0.642 |
-26.28% |
0.642 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC64
|
-25.64% |
292.096 |
217.191 |
0.052 |
-25.58% |
0.052 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint64_t_To_uint8_t_
|
-24.85% |
27258.384 |
20484.489 |
33.173 |
-24.75% |
33.173 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIRST_SUM_RAW/44217
|
-23.47% |
177.435 |
135.788 |
0.059 |
-18.37% |
0.059 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_PIC_2D_LAMBDA/44217
|
-23.16% |
11202.662 |
8608.122 |
23.635 |
-21.48% |
23.635 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC32
|
-23.14% |
158.793 |
122.052 |
0.056 |
-23.18% |
0.056 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_PIC_2D_RAW/5001
|
-23.13% |
1187.796 |
913.040 |
32.952 |
-15.33% |
32.952 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC128
|
-23.10% |
603.915 |
464.384 |
0.034 |
-23.11% |
0.034 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC128
|
-23.10% |
603.901 |
464.378 |
0.026 |
-23.11% |
0.026 |
|
MicroBenchmarks/ImageProcessing/Blur/blur.test:BENCHMARK_boxBlurKernel/1024
|
-22.88% |
30084.147 |
23199.710 |
96.999 |
-23.05% |
96.999 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC64
|
-22.16% |
313.514 |
244.042 |
0.012 |
-22.16% |
0.012 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC64
|
-22.16% |
313.508 |
244.040 |
0.021 |
-22.16% |
0.021 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC127
|
-21.98% |
615.246 |
480.023 |
0.058 |
-21.97% |
0.058 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC127
|
-21.97% |
615.182 |
480.006 |
0.041 |
-21.98% |
0.041 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint16_t_To_uint64_t_
|
-21.72% |
13244.797 |
10368.652 |
0.586 |
-21.50% |
0.586 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint16_t_To_uint32_t_
|
-21.57% |
7116.911 |
5581.715 |
1.493 |
-21.40% |
1.493 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint8_t_To_uint32_t_
|
-21.55% |
6587.215 |
5167.404 |
1.890 |
-21.49% |
1.890 |
|
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_
|
-21.38% |
182395.230 |
143403.142 |
104.066 |
-21.36% |
104.066 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIRST_SUM_LAMBDA/44217
|
-21.32% |
170.663 |
134.281 |
1.005 |
-19.63% |
1.005 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIND_FIRST_MIN_LAMBDA/171
|
-21.30% |
1.501 |
1.181 |
0.000 |
-21.28% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIND_FIRST_MIN_LAMBDA/44217
|
-21.21% |
389.133 |
306.613 |
0.224 |
-21.30% |
0.224 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIND_FIRST_MIN_LAMBDA/5001
|
-20.98% |
45.234 |
35.744 |
0.289 |
-21.02% |
0.289 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC64
|
-20.73% |
151.010 |
119.713 |
4.735 |
-19.46% |
4.735 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC128
|
-20.64% |
274.396 |
217.751 |
1.021 |
-20.74% |
1.021 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC127
|
-20.64% |
274.145 |
217.568 |
1.435 |
-21.01% |
1.435 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC32
|
-20.45% |
168.327 |
133.906 |
0.022 |
-20.45% |
0.022 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC32
|
-20.45% |
168.334 |
133.913 |
0.005 |
-20.45% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC7
|
-20.14% |
29.004 |
23.163 |
0.133 |
-19.18% |
0.133 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC63
|
-20.05% |
324.805 |
259.684 |
0.017 |
-20.04% |
0.017 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC63
|
-20.04% |
324.754 |
259.689 |
0.016 |
-20.05% |
0.016 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC127
|
-19.69% |
641.009 |
514.784 |
0.062 |
-19.63% |
0.062 |
|
SingleSource/Benchmarks/Adobe-C++/loop_unroll
Profile
|
-19.68% |
2.981 |
2.395 |
0.003 |
-22.92% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC63
|
-19.54% |
150.561 |
121.144 |
7.696 |
-19.19% |
7.696 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint32_t_To_uint8_t_
|
-19.44% |
13947.476 |
11235.750 |
66.018 |
-19.17% |
66.018 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC16
|
-19.24% |
92.288 |
74.535 |
0.026 |
-19.23% |
0.026 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint16_t_To_uint8_t_
|
-19.11% |
3818.808 |
3089.077 |
0.889 |
-19.09% |
0.889 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_VOL3D_CALC_RAW/2
|
-18.81% |
8.758 |
7.111 |
0.000 |
-18.80% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_VOL3D_CALC_LAMBDA/2
|
-18.81% |
8.757 |
7.110 |
0.001 |
-18.81% |
0.001 |
|
MultiSource/Benchmarks/MiBench/automotive-bitcount/automotive-bitcount
Profile
|
-18.79% |
0.125 |
0.101 |
0.000 |
-18.00% |
0.000 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, EqZero, None>
|
-18.75% |
20511.532 |
16665.792 |
0.590 |
-18.75% |
0.590 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint32_t_To_uint16_t_
|
-18.70% |
13803.403 |
11221.631 |
22.382 |
-18.73% |
22.382 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC128
|
-18.69% |
570.701 |
464.049 |
3.477 |
-18.67% |
3.477 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint64_t_To_uint32_t_
|
-18.57% |
27088.581 |
22057.215 |
25.154 |
-18.46% |
25.154 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint32_t_To_uint16_t_
|
-18.40% |
10565.558 |
8621.942 |
182.063 |
-12.95% |
182.063 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC32
|
-18.25% |
85.487 |
69.882 |
2.760 |
-18.10% |
2.760 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, EqZero, Last>
|
-18.18% |
14104.255 |
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_
|
-17.93% |
746578.264 |
612708.768 |
469.814 |
-17.84% |
469.814 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_INT_PREDICT_LAMBDA/5001
|
-17.93% |
1103.934 |
906.015 |
8.632 |
0.14% |
8.632 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC31
|
-17.87% |
87.110 |
71.543 |
2.035 |
-16.92% |
2.035 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint8_t_To_uint64_t_
|
-17.74% |
13275.726 |
10920.298 |
10.701 |
-16.42% |
10.701 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC8
|
-17.67% |
23.153 |
19.062 |
0.079 |
-17.67% |
0.079 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC16
|
-17.65% |
95.745 |
78.844 |
0.003 |
-17.65% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC16
|
-17.65% |
95.744 |
78.846 |
0.003 |
-17.65% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_with_cond_arith_novec_int32_t_
|
-17.48% |
740923.740 |
611373.248 |
1245.914 |
-17.40% |
1245.914 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC64
|
-17.34% |
297.866 |
246.220 |
0.019 |
-17.30% |
0.019 |
|
MultiSource/Benchmarks/MiBench/security-rijndael/security-rijndael
Profile
|
-17.28% |
0.335 |
0.277 |
0.000 |
-17.22% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC32
|
-17.27% |
161.449 |
133.574 |
0.011 |
-17.24% |
0.011 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC16
|
-17.11% |
93.233 |
77.279 |
0.015 |
-17.02% |
0.015 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC8
|
-16.80% |
58.820 |
48.938 |
0.084 |
-16.72% |
0.084 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC31
|
-16.73% |
179.596 |
149.549 |
0.008 |
-16.73% |
0.008 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC31
|
-16.73% |
179.593 |
149.548 |
0.007 |
-16.72% |
0.007 |
|
MicroBenchmarks/ImageProcessing/Dilate/Dilate.test:BENCHMARK_DILATE/1024
|
-16.69% |
7450.028 |
6206.265 |
276.877 |
-12.72% |
276.877 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_HYDRO_1D_RAW/171
|
-16.40% |
0.445 |
0.372 |
0.000 |
-15.84% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_HYDRO_1D_LAMBDA/171
|
-16.25% |
0.444 |
0.372 |
0.000 |
-15.88% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_VOL3D_CALC_RAW/0
|
-16.21% |
1269.446 |
1063.726 |
0.761 |
-15.92% |
0.761 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_VOL3D_CALC_RAW/1
|
-16.17% |
260.097 |
218.044 |
0.127 |
-16.18% |
0.127 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_VOL3D_CALC_LAMBDA/1
|
-16.10% |
260.165 |
218.287 |
0.188 |
-16.10% |
0.188 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_VOL3D_CALC_LAMBDA/0
|
-16.03% |
1267.043 |
1063.891 |
1.733 |
-16.07% |
1.733 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC8
|
-15.79% |
23.779 |
20.024 |
0.001 |
-15.79% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint16_t_To_uint32_t_
|
-15.63% |
7463.534 |
6296.745 |
0.535 |
-15.62% |
0.535 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint64_t_To_uint8_t_
|
-15.47% |
22080.923 |
18665.524 |
15.567 |
-15.34% |
15.567 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_no_runtime_checks_needed<16, int>
|
-15.39% |
24.403 |
20.648 |
0.001 |
-15.39% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC16
|
-15.10% |
33.164 |
28.157 |
0.572 |
-15.10% |
0.572 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC127
|
-14.98% |
605.837 |
515.078 |
0.169 |
-14.97% |
0.169 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint32_t_To_uint8_t_
|
-14.93% |
10638.847 |
9049.961 |
7.336 |
-14.59% |
7.336 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC15
|
-14.77% |
44.784 |
38.169 |
0.007 |
-14.09% |
0.007 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_HYDRO_1D_LAMBDA/5001
|
-14.76% |
19.128 |
16.304 |
0.142 |
-5.06% |
0.142 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint32_t_To_uint16_t_
|
-14.64% |
12879.645 |
10994.245 |
25.886 |
-14.36% |
25.886 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC128
|
-14.52% |
1103.385 |
943.164 |
0.032 |
-14.51% |
0.032 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC127
|
-14.44% |
1095.639 |
937.478 |
0.043 |
-14.41% |
0.043 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC64
|
-14.23% |
562.524 |
482.451 |
0.027 |
-14.20% |
0.027 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint8_t_To_uint16_t_
|
-14.15% |
3757.145 |
3225.384 |
2.332 |
-14.14% |
2.332 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_INT_PREDICT_LAMBDA/44217
|
-14.14% |
9323.917 |
8005.586 |
79.085 |
-3.98% |
79.085 |
|
SingleSource/Benchmarks/Misc/salsa20
Profile
|
-14.14% |
15.387 |
13.212 |
0.001 |
-14.12% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_with_cond_arith_novec_int64_t_
|
-14.08% |
793070.939 |
681370.540 |
875.500 |
-13.54% |
875.500 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_with_cond_arith_autovec_int64_t_
|
-14.04% |
792316.285 |
681050.486 |
1087.049 |
-13.97% |
1087.049 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC63
|
-14.03% |
554.657 |
476.817 |
0.022 |
-14.05% |
0.022 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC3
|
-13.86% |
51.938 |
44.737 |
0.003 |
-13.86% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC8
|
-13.86% |
51.939 |
44.738 |
0.004 |
-13.86% |
0.004 |
|
External/SPEC/CFP2017rate/508.namd_r/508.namd_r
Profile
|
-13.86% |
224.272 |
193.191 |
0.312 |
-13.59% |
0.312 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC7
|
-13.86% |
51.934 |
44.737 |
0.002 |
-13.86% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC1
|
-13.86% |
51.936 |
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/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC2
|
-13.85% |
51.936 |
44.740 |
0.002 |
-13.85% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint32_t_To_uint8_t_
|
-13.85% |
11038.829 |
9509.660 |
17.611 |
-14.55% |
17.611 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC32
|
-13.72% |
292.249 |
252.144 |
0.025 |
-13.65% |
0.025 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC8
|
-13.69% |
59.444 |
51.308 |
0.001 |
-13.69% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC8
|
-13.68% |
59.443 |
51.312 |
0.001 |
-13.69% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC4
|
-13.67% |
112.093 |
96.776 |
2.394 |
-14.42% |
2.394 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint32_t_To_uint16_t_
|
-13.63% |
10771.128 |
9303.143 |
542.716 |
-13.36% |
542.716 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIRST_SUM_RAW/5001
|
-13.61% |
20.590 |
17.788 |
0.626 |
2.55% |
0.626 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC63
|
-13.38% |
374.518 |
324.411 |
0.011 |
-13.36% |
0.011 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC31
|
-13.24% |
284.143 |
246.510 |
0.017 |
-13.23% |
0.017 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC16
|
-13.15% |
51.941 |
45.108 |
0.403 |
-13.16% |
0.403 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC128
|
-13.08% |
81.350 |
70.710 |
0.002 |
-13.07% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC63
|
-12.97% |
332.935 |
289.766 |
0.141 |
-12.94% |
0.141 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint8_t_To_uint16_t_
|
-12.96% |
4542.335 |
3953.764 |
0.300 |
-12.95% |
0.300 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC16
|
-12.76% |
157.066 |
137.032 |
0.005 |
-12.70% |
0.005 |
|
SingleSource/Benchmarks/Shootout-C++/Shootout-C++-matrix
Profile
|
-12.72% |
2.509 |
2.190 |
0.000 |
-12.70% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint16_t_To_uint8_t_
|
-12.41% |
4743.110 |
4154.438 |
0.270 |
-12.40% |
0.270 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, EqZero, None>
|
-11.99% |
16024.376 |
14102.404 |
0.900 |
-11.99% |
0.900 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC15
|
-11.77% |
148.926 |
131.403 |
0.019 |
-11.70% |
0.019 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC2
|
-11.76% |
21.274 |
18.772 |
0.001 |
-11.77% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC15
|
-11.70% |
107.007 |
94.482 |
0.031 |
-11.70% |
0.031 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC15
|
-11.70% |
107.000 |
94.485 |
0.007 |
-11.70% |
0.007 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC15
|
-11.46% |
51.936 |
45.985 |
0.004 |
-11.46% |
0.004 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_PIC_2D_LAMBDA/5001
|
-11.38% |
1063.512 |
942.470 |
15.624 |
-14.75% |
15.624 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC4
|
-11.11% |
22.526 |
20.023 |
0.000 |
-11.12% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC4
|
-11.11% |
22.527 |
20.023 |
0.002 |
-11.11% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC3
|
-11.11% |
22.525 |
20.022 |
0.001 |
-11.12% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint8_t>/51
|
-11.10% |
123.896 |
110.144 |
0.035 |
19.07% |
0.035 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint32_t_To_uint64_t_
|
-10.65% |
17092.447 |
15272.052 |
408.980 |
-11.19% |
408.980 |
|
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
|
-10.61% |
0.384 |
0.343 |
0.000 |
-6.33% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint64_t_To_uint16_t_
|
-10.55% |
19229.574 |
17200.887 |
240.704 |
-9.39% |
240.704 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC4
|
-10.53% |
23.779 |
21.275 |
0.001 |
-10.53% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC8
|
-10.49% |
89.479 |
80.095 |
0.003 |
-10.41% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC64
|
-10.47% |
53.817 |
48.182 |
0.000 |
-10.47% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC16
|
-10.35% |
36.293 |
32.538 |
0.000 |
-10.35% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint64_t_To_uint32_t_
|
-10.32% |
18285.722 |
16397.912 |
206.023 |
-7.95% |
206.023 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/16
|
-10.17% |
115.462 |
103.719 |
0.010 |
-10.17% |
0.010 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/32
|
-10.00% |
473.033 |
425.727 |
0.019 |
-9.99% |
0.019 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/64
|
-10.00% |
1912.802 |
1721.532 |
0.306 |
-10.02% |
0.306 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint8_t_To_uint16_t_
|
-9.97% |
5846.955 |
5263.836 |
8.427 |
-10.03% |
8.427 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/256
|
-9.95% |
31441.424 |
28313.467 |
25.521 |
-9.97% |
25.521 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC127
|
-9.79% |
101.971 |
91.987 |
0.003 |
-9.71% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC8
|
-9.77% |
25.657 |
23.151 |
0.001 |
-9.76% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC8
|
-9.76% |
25.657 |
23.152 |
0.000 |
-9.76% |
0.000 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/128
|
-9.75% |
7913.452 |
7141.790 |
2.300 |
-9.80% |
2.300 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC31
|
-9.74% |
196.488 |
177.343 |
0.034 |
-9.74% |
0.034 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_DIFF_PREDICT_RAW/171
|
-9.70% |
12.302 |
11.109 |
0.116 |
-6.90% |
0.116 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC7
|
-9.61% |
32.537 |
29.409 |
0.000 |
-9.62% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC16
|
-9.61% |
31.842 |
28.782 |
0.001 |
-8.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC7
|
-9.52% |
26.280 |
23.777 |
0.001 |
-9.53% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_only_autovec_int64_t_
|
-9.41% |
332665.675 |
301345.582 |
473.609 |
-9.58% |
473.609 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC7
|
-9.39% |
26.279 |
23.812 |
0.032 |
-9.40% |
0.032 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_DEL_DOT_VEC_2D_RAW/1
|
-9.27% |
287.133 |
260.518 |
0.156 |
-9.22% |
0.156 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_DEL_DOT_VEC_2D_LAMBDA/1
|
-9.27% |
287.289 |
260.662 |
0.149 |
-9.21% |
0.149 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC7
|
-9.24% |
81.347 |
73.834 |
0.004 |
-9.20% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC4
|
-9.09% |
41.296 |
37.543 |
0.002 |
-9.10% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC4
|
-9.08% |
41.296 |
37.545 |
0.002 |
-9.09% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC32
|
-9.01% |
53.186 |
48.393 |
0.013 |
-9.02% |
0.013 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC4
|
-8.99% |
55.691 |
50.683 |
0.003 |
-8.95% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC7
|
-8.89% |
28.158 |
25.654 |
0.001 |
-8.90% |
0.001 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_runtime_checks_pass<4, int>
|
-8.89% |
16.825 |
15.330 |
0.001 |
-8.25% |
0.001 |
|
MultiSource/Benchmarks/FreeBench/pifft/pifft
Profile
|
-8.81% |
0.359 |
0.327 |
0.001 |
-8.75% |
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
|
-8.71% |
3.510 |
3.204 |
0.000 |
-8.70% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC16
|
-8.70% |
14.393 |
13.140 |
0.001 |
-8.71% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC4
|
-8.70% |
14.392 |
13.140 |
0.001 |
-8.71% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC1
|
-8.70% |
14.392 |
13.140 |
0.000 |
-8.70% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC1
|
-8.70% |
14.394 |
13.142 |
0.001 |
-8.70% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC8
|
-8.70% |
14.392 |
13.140 |
0.000 |
-8.70% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC7
|
-8.70% |
14.392 |
13.140 |
0.000 |
-8.70% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC15
|
-8.70% |
14.392 |
13.140 |
0.000 |
-8.70% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC2
|
-8.70% |
14.392 |
13.141 |
0.000 |
-8.69% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC3
|
-8.70% |
14.391 |
13.140 |
0.001 |
-8.70% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC2
|
-8.69% |
14.392 |
13.140 |
0.000 |
-8.69% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC15
|
-8.69% |
14.392 |
13.141 |
0.000 |
-8.70% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC3
|
-8.69% |
14.392 |
13.140 |
0.001 |
-8.70% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC16
|
-8.69% |
14.392 |
13.140 |
0.002 |
-8.69% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC7
|
-8.69% |
14.392 |
13.141 |
0.001 |
-8.69% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC4
|
-8.69% |
14.391 |
13.140 |
0.000 |
-8.70% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC8
|
-8.69% |
14.391 |
13.141 |
0.000 |
-8.70% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopFrom_uint32_t_To_uint16_t_
|
-8.52% |
7957.508 |
7279.466 |
198.667 |
-2.30% |
198.667 |
|
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% |
6809.945 |
6230.482 |
12.294 |
-8.59% |
12.294 |
|
MicroBenchmarks/ImageProcessing/Dilate/Dilate.test:BENCHMARK_DILATE/128
|
-8.49% |
229.004 |
209.556 |
6.226 |
-8.08% |
6.226 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint8_t_To_uint32_t_
|
-8.38% |
12804.180 |
11731.537 |
20.630 |
-8.19% |
20.630 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint16_t_To_uint64_t_
|
-8.35% |
20339.252 |
18639.951 |
93.870 |
-7.46% |
93.870 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint8_t>/28
|
-8.26% |
82.605 |
75.785 |
0.027 |
12.13% |
0.027 |
|
MultiSource/Benchmarks/McCat/12-IOtest/iotest
Profile
|
-8.23% |
1.833 |
1.682 |
0.015 |
-7.83% |
0.015 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC64
|
-8.06% |
93.231 |
85.719 |
0.004 |
-8.07% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC16
|
-7.84% |
31.912 |
29.409 |
0.002 |
-7.85% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC16
|
-7.84% |
31.912 |
29.409 |
0.001 |
-7.84% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC32
|
-7.81% |
40.046 |
36.919 |
0.001 |
-7.82% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC8
|
-7.79% |
27.144 |
25.029 |
0.001 |
-7.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC15
|
-7.70% |
32.540 |
30.035 |
0.001 |
-7.69% |
0.001 |
|
MultiSource/Benchmarks/VersaBench/beamformer/beamformer
Profile
|
-7.66% |
5.200 |
4.802 |
0.003 |
-7.67% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC15
|
-7.65% |
54.443 |
50.277 |
0.016 |
-7.65% |
0.016 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint16_t_To_uint64_t_
|
-7.58% |
25100.903 |
23199.290 |
46.308 |
-7.15% |
46.308 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC31
|
-7.55% |
74.461 |
68.843 |
0.013 |
-7.55% |
0.013 |
|
MultiSource/Benchmarks/Trimaran/enc-md5/enc-md5
Profile
|
-7.54% |
3.507 |
3.243 |
0.000 |
-7.49% |
0.000 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_xor_no_runtime_checks_needed<16, int>
|
-7.41% |
16.895 |
15.643 |
0.001 |
-7.42% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_PIC_1D_RAW/5001
|
-7.38% |
362.938 |
336.151 |
4.401 |
-2.57% |
4.401 |
|
MultiSource/Applications/lambda-0.1.3/lambda
Profile
|
-7.29% |
15.874 |
14.717 |
0.007 |
-7.27% |
0.007 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_DEL_DOT_VEC_2D_LAMBDA/0
|
-7.29% |
1795.007 |
1664.229 |
5.530 |
-7.13% |
5.530 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC128
|
-7.27% |
68.829 |
63.823 |
0.002 |
-7.24% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC127
|
-7.27% |
68.827 |
63.824 |
0.001 |
-6.54% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_HYDRO_2D_RAW/171
|
-7.22% |
88.574 |
82.178 |
0.522 |
-7.28% |
0.522 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint8_t>/127
|
-7.22% |
138.922 |
128.894 |
0.019 |
-7.21% |
0.019 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC128
|
-7.22% |
173.345 |
160.833 |
0.004 |
-7.21% |
0.004 |
|
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/SubsetCLambdaLoops/lcalsCLambda.test:BM_DIFF_PREDICT_LAMBDA/171
|
-7.06% |
11.953 |
11.109 |
0.086 |
-7.31% |
0.086 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_BAND_LIN_EQ_RAW/5001
|
-7.05% |
21.547 |
20.029 |
0.277 |
-2.88% |
0.277 |
|
SingleSource/Benchmarks/Misc/pi
Profile
|
-7.02% |
1.782 |
1.657 |
0.000 |
-7.02% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC63
|
-6.97% |
114.516 |
106.539 |
0.070 |
-6.96% |
0.070 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC15
|
-6.94% |
45.051 |
41.924 |
0.002 |
-6.94% |
0.002 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_DEL_DOT_VEC_2D_RAW/0
|
-6.92% |
1791.896 |
1667.923 |
1.024 |
-7.38% |
1.024 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_HYDRO_2D_LAMBDA/171
|
-6.85% |
88.160 |
82.122 |
0.510 |
-7.37% |
0.510 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_only_autovec_int32_t_
|
-6.62% |
181271.654 |
169279.532 |
163.032 |
-6.54% |
163.032 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC127
|
-6.61% |
194.617 |
181.750 |
0.111 |
-6.61% |
0.111 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC2
|
-6.56% |
38.170 |
35.668 |
0.001 |
-6.56% |
0.001 |
|
SingleSource/Benchmarks/Misc/flops-6
Profile
|
-6.53% |
1.311 |
1.225 |
0.001 |
-6.63% |
0.001 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_xor_runtime_checks_fail<16, int>
|
-6.52% |
28.783 |
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 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C++/miniFE/miniFE
Profile
|
-6.47% |
15.806 |
14.783 |
0.099 |
-7.43% |
0.099 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_BAND_LIN_EQ_LAMBDA/5001
|
-6.47% |
21.431 |
20.045 |
0.056 |
-3.63% |
0.056 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC15
|
-6.34% |
39.420 |
36.920 |
0.000 |
-6.35% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIND_FIRST_MIN_RAW/5001
|
-6.33% |
45.314 |
42.444 |
0.010 |
-6.39% |
0.010 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint16_t>/127
|
-6.30% |
138.909 |
130.154 |
0.005 |
-6.30% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC63
|
-6.26% |
74.096 |
69.456 |
0.006 |
-6.42% |
0.006 |
|
SingleSource/Benchmarks/Misc/oourafft
Profile
|
-6.26% |
15.425 |
14.459 |
0.049 |
-4.20% |
0.049 |
|
SingleSource/Benchmarks/Misc-C++/Large/sphereflake
Profile
|
-6.24% |
20.014 |
18.766 |
0.003 |
-6.18% |
0.003 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_PRESSURE_CALC_LAMBDA/5001
|
-6.16% |
45.000 |
42.229 |
0.984 |
-3.97% |
0.984 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC16
|
-6.15% |
40.671 |
38.168 |
0.003 |
-6.16% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC32
|
-6.12% |
61.320 |
57.568 |
0.003 |
-6.12% |
0.003 |
|
SingleSource/Benchmarks/Misc/perlin
Profile
|
-5.98% |
6.599 |
6.204 |
0.000 |
-5.97% |
0.000 |
|
External/SPEC/CFP2017rate/538.imagick_r/538.imagick_r
Profile
|
-5.97% |
292.828 |
275.358 |
0.315 |
-5.73% |
0.315 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint32_t_To_uint64_t_
|
-5.95% |
21557.973 |
20274.224 |
69.716 |
-5.49% |
69.716 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint8_t>/65
|
-5.92% |
95.112 |
89.484 |
0.004 |
-5.92% |
0.004 |
|
MultiSource/Benchmarks/MiBench/telecomm-gsm/telecomm-gsm
Profile
|
-5.88% |
0.663 |
0.624 |
0.000 |
-5.96% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint32_t>/127
|
-5.88% |
138.276 |
130.151 |
0.005 |
-5.88% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC32
|
-5.80% |
24.404 |
22.989 |
0.338 |
-5.79% |
0.338 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC16
|
-5.65% |
33.162 |
31.287 |
0.000 |
-5.66% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC32
|
-5.64% |
44.429 |
41.921 |
0.003 |
-5.64% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC32
|
-5.64% |
44.430 |
41.925 |
0.001 |
-5.64% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC15
|
-5.60% |
128.275 |
121.086 |
0.017 |
-5.59% |
0.017 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC31
|
-5.58% |
45.065 |
42.549 |
0.001 |
-5.58% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC31
|
-5.56% |
45.054 |
42.549 |
0.003 |
-5.56% |
0.003 |
|
MultiSource/Benchmarks/SciMark2-C/scimark2
Profile
|
-5.54% |
107.686 |
101.720 |
0.069 |
-5.50% |
0.069 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC64
|
-5.52% |
43.710 |
41.297 |
0.001 |
-4.35% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint8_t_To_uint16_t_
|
-5.51% |
3630.226 |
3430.274 |
5.415 |
-5.59% |
5.415 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIND_FIRST_MIN_RAW/44217
|
-5.43% |
389.538 |
368.370 |
0.256 |
-5.45% |
0.256 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint32_t>/999
|
-5.39% |
696.493 |
658.955 |
0.041 |
-5.39% |
0.041 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC127
|
-5.37% |
2384.361 |
2256.416 |
34.489 |
-7.01% |
34.489 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_PIC_2D_LAMBDA/171
|
-5.36% |
13.482 |
12.760 |
0.055 |
-5.47% |
0.055 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC7
|
-5.32% |
70.712 |
66.951 |
0.002 |
-5.33% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC7
|
-5.32% |
70.710 |
66.951 |
0.004 |
-5.32% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC3
|
-5.27% |
47.554 |
45.049 |
0.002 |
-5.27% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC1
|
-5.27% |
11.889 |
11.263 |
0.001 |
-5.27% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint32_t>/999
|
-5.22% |
1365.038 |
1293.844 |
0.090 |
-5.22% |
0.090 |
|
MultiSource/Benchmarks/Rodinia/hotspot/hotspot
Profile
|
-5.11% |
2.035 |
1.931 |
0.003 |
-5.14% |
0.003 |
|
SingleSource/Benchmarks/Polybench/stencils/jacobi-2d/jacobi-2d
Profile
|
-5.11% |
31.967 |
30.334 |
0.087 |
-5.86% |
0.087 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_PIC_2D_RAW/171
|
-5.10% |
13.520 |
12.831 |
0.057 |
-5.23% |
0.057 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC31
|
-5.00% |
241.260 |
229.209 |
0.027 |
-4.98% |
0.027 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC32
|
-4.84% |
49.976 |
47.558 |
0.035 |
-4.98% |
0.035 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint32_t>/256
|
-4.81% |
364.163 |
346.650 |
0.012 |
-4.81% |
0.012 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC15
|
-4.81% |
32.538 |
30.974 |
0.001 |
-4.81% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC32
|
-4.73% |
24.405 |
23.251 |
0.259 |
-4.73% |
0.259 |
|
SingleSource/Benchmarks/Misc/revertBits
Profile
|
-4.67% |
0.641 |
0.611 |
0.000 |
-4.69% |
0.000 |
|
MultiSource/Benchmarks/TSVC/Expansion-flt/Expansion-flt
Profile
|
-4.61% |
11.756 |
11.214 |
0.157 |
-0.93% |
0.157 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint16_t>/65
|
-4.61% |
95.117 |
90.732 |
0.005 |
-4.61% |
0.005 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_PRESSURE_CALC_RAW/44217
|
-4.61% |
504.117 |
480.887 |
1.245 |
-4.24% |
1.245 |
|
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% |
54.434 |
51.936 |
0.001 |
-4.59% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC31
|
-4.58% |
93.779 |
89.487 |
0.119 |
-4.65% |
0.119 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC2
|
-4.55% |
13.767 |
13.140 |
0.000 |
-4.54% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC31
|
-4.47% |
70.084 |
66.955 |
0.005 |
-4.46% |
0.005 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_INT_PREDICT_RAW/5001
|
-4.46% |
952.216 |
909.750 |
5.137 |
-0.40% |
5.137 |
|
MicroBenchmarks/ImageProcessing/Dilate/Dilate.test:BENCHMARK_DILATE/512
|
-4.42% |
3611.836 |
3452.047 |
12.677 |
-3.68% |
12.677 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint8_t_To_uint64_t_
|
-4.41% |
23509.913 |
22473.222 |
15.132 |
-4.30% |
15.132 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint32_t_To_uint16_t_
|
-4.36% |
9834.185 |
9405.213 |
42.820 |
-4.80% |
42.820 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC63
|
-4.35% |
43.178 |
41.300 |
0.001 |
-4.61% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint16_t_To_uint8_t_
|
-4.34% |
2872.550 |
2748.024 |
7.071 |
-4.52% |
7.071 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C++/HPCCG/HPCCG
Profile
|
-4.31% |
3.915 |
3.746 |
0.042 |
-4.30% |
0.042 |
|
MicroBenchmarks/ImageProcessing/Dilate/Dilate.test:BENCHMARK_DILATE/256
|
-4.27% |
1061.946 |
1016.607 |
3.153 |
-4.75% |
3.153 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_ENERGY_CALC_LAMBDA/171
|
-4.26% |
14.205 |
13.600 |
0.018 |
-4.55% |
0.018 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_cond_load_novec_int32_t_
|
-4.25% |
418746.005 |
400938.632 |
71.649 |
-2.38% |
71.649 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint64_t>/999
|
-4.25% |
1811.585 |
1734.665 |
0.104 |
-4.23% |
0.104 |
|
External/SPEC/CFP2017rate/519.lbm_r/519.lbm_r
Profile
|
-4.21% |
200.669 |
192.218 |
1.380 |
-4.22% |
1.380 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint64_t>/999
|
-4.16% |
3595.308 |
3445.852 |
0.350 |
-4.14% |
0.350 |
|
SingleSource/Benchmarks/Misc/flops-5
Profile
|
-4.15% |
2.021 |
1.937 |
0.001 |
-4.15% |
0.001 |
|
MultiSource/Benchmarks/TSVC/NodeSplitting-dbl/NodeSplitting-dbl
Profile
|
-4.10% |
26.947 |
25.841 |
0.269 |
-2.17% |
0.269 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_PRESSURE_CALC_LAMBDA/44217
|
-4.09% |
503.035 |
482.466 |
3.842 |
-3.22% |
3.842 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint64_t>/256
|
-4.05% |
935.469 |
897.566 |
0.004 |
-4.06% |
0.004 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_ENERGY_CALC_RAW/171
|
-4.05% |
14.207 |
13.632 |
0.013 |
-4.27% |
0.013 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC31
|
-4.04% |
61.949 |
59.445 |
0.001 |
-4.04% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC32
|
-4.01% |
31.289 |
30.034 |
0.002 |
-4.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC3
|
-4.01% |
15.645 |
15.018 |
0.000 |
-4.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint64_t_To_uint32_t_
|
-4.00% |
19399.980 |
18623.180 |
37.031 |
-3.47% |
37.031 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_only_autovec_uint8_t_
|
-4.00% |
96169.271 |
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
|
-3.97% |
63.203 |
60.696 |
0.000 |
-3.96% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint32_t>/256
|
-3.96% |
221.512 |
212.739 |
0.042 |
-3.96% |
0.042 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_cond_load_autovec_int64_t_
|
-3.95% |
553407.566 |
531574.866 |
892.698 |
-3.81% |
892.698 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC31
|
-3.90% |
31.253 |
30.035 |
0.000 |
-3.70% |
0.000 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<32, EqZero, Last>
|
-3.85% |
7126.261 |
6851.640 |
24.127 |
-2.85% |
24.127 |
|
External/SPEC/CFP2017rate/544.nab_r/544.nab_r
Profile
|
-3.81% |
476.167 |
458.018 |
0.105 |
-4.16% |
0.105 |
|
MultiSource/Benchmarks/nbench/nbench
Profile
|
-3.77% |
6.119 |
5.888 |
0.003 |
-3.89% |
0.003 |
|
SingleSource/Benchmarks/Shootout/Shootout-matrix
Profile
|
-3.69% |
3.864 |
3.721 |
0.000 |
-3.68% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint64_t_To_uint8_t_
|
-3.68% |
19750.688 |
19024.562 |
40.425 |
-4.12% |
40.425 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint64_t>/256
|
-3.64% |
514.389 |
495.642 |
0.013 |
-3.65% |
0.013 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint16_t_To_uint32_t_
|
-3.64% |
11310.803 |
10898.666 |
12.483 |
-3.91% |
12.483 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<31, EqZero, First>
|
-3.64% |
3346.110 |
3224.411 |
2.562 |
-3.64% |
2.562 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_nested_cond_load_novec_int32_t_
|
-3.63% |
650220.385 |
626632.756 |
63.913 |
-2.87% |
63.913 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_runtime_checks_fail<4, int>
|
-3.62% |
15.905 |
15.329 |
0.000 |
-3.64% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC64
|
-3.61% |
69.458 |
66.953 |
0.001 |
-3.61% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC64
|
-3.61% |
69.459 |
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/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC63
|
-3.57% |
70.082 |
67.578 |
0.001 |
-3.57% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC63
|
-3.57% |
70.084 |
67.582 |
0.013 |
-3.58% |
0.013 |
|
MultiSource/Applications/JM/lencod/lencod
Profile
|
-3.53% |
32.763 |
31.607 |
0.038 |
-2.87% |
0.038 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint8_t>/16
|
-3.47% |
59.885 |
57.807 |
0.258 |
7.41% |
0.258 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC64
|
-3.37% |
111.389 |
107.631 |
0.006 |
-3.37% |
0.006 |
|
SingleSource/Benchmarks/Shootout/Shootout-lists
Profile
|
-3.15% |
11.317 |
10.960 |
0.005 |
-3.12% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint16_t>/999
|
-3.15% |
514.967 |
498.753 |
0.013 |
-3.16% |
0.013 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1BigLoopWithReductionTC1
|
-3.13% |
20.024 |
19.397 |
0.004 |
-3.14% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC31
|
-3.13% |
60.072 |
58.193 |
0.005 |
-3.46% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint16_t_To_uint8_t_
|
-3.12% |
4511.936 |
4371.324 |
10.309 |
-3.23% |
10.309 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchVecWithRuntimeChecks4PointersDBeforeA/1000
|
-3.07% |
5020476.302 |
4866129.042 |
562.436 |
-3.06% |
562.436 |
|
MultiSource/Benchmarks/Rodinia/pathfinder/pathfinder
Profile
|
-3.02% |
1.257 |
1.220 |
0.009 |
-3.04% |
0.009 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C/CoMD/CoMD
Profile
|
-2.84% |
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% |
1013.756 |
985.061 |
0.129 |
-2.84% |
0.129 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<31, GreaterThanZero, Last>
|
-2.78% |
8332.157 |
8100.508 |
18.323 |
-2.35% |
18.323 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC1
|
-2.78% |
22.527 |
21.902 |
0.001 |
-2.77% |
0.001 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_FLOYD_DITHER/128
|
-2.75% |
437.801 |
425.759 |
1.723 |
-3.12% |
1.723 |
|
MultiSource/Benchmarks/FreeBench/mason/mason
Profile
|
-2.66% |
0.553 |
0.538 |
0.000 |
-2.72% |
0.000 |
|
SingleSource/Benchmarks/Misc-C++/oopack_v1p8
Profile
|
-2.63% |
0.480 |
0.467 |
0.000 |
-10.00% |
0.000 |
|
MultiSource/Benchmarks/mafft/pairlocalalign
Profile
|
-2.62% |
94.098 |
91.629 |
0.368 |
-2.59% |
0.368 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC63
|
-2.61% |
120.150 |
117.012 |
0.008 |
-2.61% |
0.008 |
|
MultiSource/Benchmarks/sim/sim
Profile
|
-2.59% |
9.700 |
9.449 |
0.012 |
-2.60% |
0.012 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC31
|
-2.56% |
24.404 |
23.778 |
0.004 |
-2.56% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC31
|
-2.56% |
24.405 |
23.780 |
0.017 |
-2.55% |
0.017 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint8_t>/10
|
-2.55% |
48.803 |
47.560 |
0.010 |
2.47% |
0.010 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint8_t_To_uint32_t_
|
-2.54% |
7078.169 |
6898.648 |
1.425 |
-2.52% |
1.425 |
|
MultiSource/Benchmarks/TSVC/Recurrences-dbl/Recurrences-dbl
Profile
|
-2.48% |
10.345 |
10.088 |
0.056 |
-2.59% |
0.056 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchVecWithRuntimeChecks4PointersDBeforeA/32
|
-2.40% |
166174.483 |
162185.542 |
176.558 |
-2.42% |
176.558 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC63
|
-2.37% |
130.116 |
127.032 |
0.074 |
-2.41% |
0.074 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_FLOYD_DITHER/256
|
-2.36% |
1786.593 |
1744.436 |
6.088 |
0.63% |
6.088 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_FLOYD_DITHER/512
|
-2.36% |
6645.402 |
6488.801 |
36.026 |
-2.35% |
36.026 |
|
MultiSource/Benchmarks/FreeBench/fourinarow/fourinarow
Profile
|
-2.36% |
0.650 |
0.635 |
0.001 |
-2.43% |
0.001 |
|
SingleSource/Benchmarks/Misc/fbench
Profile
|
-2.35% |
5.763 |
5.627 |
0.000 |
-2.32% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC63
|
-2.33% |
106.996 |
104.500 |
0.003 |
-2.34% |
0.003 |
|
MultiSource/Applications/sgefa/sgefa
Profile
|
-2.32% |
0.580 |
0.566 |
0.001 |
-1.25% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_only_autovec_int64_t_
|
-2.27% |
1449612.921 |
1416727.769 |
1477.944 |
-2.09% |
1477.944 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_nested_cond_load_novec_uint8_t_
|
-2.21% |
504351.791 |
493208.302 |
421.857 |
-2.28% |
421.857 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint32_t_To_uint64_t_
|
-2.21% |
26352.690 |
25771.151 |
46.689 |
-1.94% |
46.689 |
|
SingleSource/Benchmarks/Misc/flops-1
Profile
|
-2.18% |
9.002 |
8.806 |
0.000 |
-2.15% |
0.000 |
|
External/SPEC/CINT2017rate/531.deepsjeng_r/531.deepsjeng_r
Profile
|
-2.15% |
259.941 |
254.340 |
0.432 |
-2.22% |
0.432 |
|
SingleSource/Benchmarks/Misc-C++/Large/ray
Profile
|
-2.11% |
12.105 |
11.849 |
0.002 |
-2.08% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC128
|
-2.10% |
119.521 |
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:benchForIC4VW1LoopWithReductionTC127
|
-2.09% |
120.148 |
117.633 |
0.009 |
-2.09% |
0.009 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC127
|
-2.09% |
120.140 |
117.635 |
0.003 |
-2.09% |
0.003 |
|
SingleSource/Benchmarks/Misc/ReedSolomon
Profile
|
-2.08% |
20.821 |
20.389 |
0.001 |
-1.96% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_ENERGY_CALC_LAMBDA/44217
|
-2.04% |
4334.275 |
4245.683 |
10.047 |
-1.82% |
10.047 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C/SimpleMOC/SimpleMOC
Profile
|
-2.04% |
10.444 |
10.232 |
0.031 |
-1.67% |
0.031 |
|
MultiSource/Benchmarks/Bullet/bullet
Profile
|
-2.03% |
30.402 |
29.784 |
0.165 |
-2.12% |
0.165 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<16, LessThanZero, Mid>
|
-2.02% |
8672.445 |
8497.531 |
4.937 |
-1.88% |
4.937 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_EOS_RAW/171
|
-2.00% |
0.873 |
0.855 |
0.001 |
-1.80% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint32_t>/10
|
-2.00% |
47.246 |
46.302 |
0.005 |
-0.00% |
0.005 |
|
MicroBenchmarks/ImageProcessing/Blur/blur.test:BENCHMARK_boxBlurKernel/512
|
-1.99% |
6652.983 |
6520.275 |
9.950 |
-1.41% |
9.950 |
|
MultiSource/Benchmarks/Olden/health/health
Profile
|
-1.97% |
1.592 |
1.560 |
0.004 |
-1.95% |
0.004 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_BAND_LIN_EQ_LAMBDA/44217
|
-1.93% |
176.793 |
173.378 |
0.338 |
4.54% |
0.338 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_ENERGY_CALC_RAW/44217
|
-1.91% |
4331.305 |
4248.723 |
6.174 |
-1.91% |
6.174 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<6, GreaterThanZero, None>
|
-1.89% |
29651.967 |
29092.166 |
14.041 |
-1.64% |
14.041 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<16, EqZero, Mid>
|
-1.87% |
8661.582 |
8499.283 |
0.614 |
-1.82% |
0.614 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_INT_PREDICT_LAMBDA/171
|
-1.86% |
6.923 |
6.795 |
0.009 |
-1.88% |
0.009 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint16_t>/256
|
-1.83% |
272.812 |
267.812 |
0.024 |
-1.84% |
0.024 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC128
|
-1.78% |
211.519 |
207.751 |
1.019 |
-1.78% |
1.019 |
|
SingleSource/Benchmarks/BenchmarkGame/puzzle
Profile
|
-1.75% |
0.865 |
0.849 |
0.003 |
-2.22% |
0.003 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<32, LessThanZero, Mid>
|
-1.70% |
4570.614 |
4492.995 |
6.231 |
-1.71% |
6.231 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint64_t>/51
|
-1.69% |
148.297 |
145.792 |
0.009 |
-1.70% |
0.009 |
|
MultiSource/Benchmarks/VersaBench/ecbdes/ecbdes
Profile
|
-1.67% |
5.142 |
5.056 |
0.001 |
-1.63% |
0.001 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, GreaterThanZero, None>
|
-1.65% |
37119.995 |
36506.197 |
1.428 |
-1.80% |
1.428 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_EOS_LAMBDA/171
|
-1.64% |
0.870 |
0.856 |
0.001 |
-1.65% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_csa_with_in_loop_arith_novec_int64_t_
|
-1.64% |
1029552.953 |
1012701.996 |
169.121 |
-1.50% |
169.121 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<6, LessThanZero, Mid>
|
-1.59% |
23870.239 |
23491.283 |
6.674 |
-0.32% |
6.674 |
|
SingleSource/Benchmarks/Misc/mandel-2
Profile
|
-1.57% |
2.536 |
2.496 |
0.000 |
-1.55% |
0.000 |
|
MultiSource/Benchmarks/Fhourstones-3.1/fhourstones3.1
Profile
|
-1.56% |
3.974 |
3.912 |
0.005 |
-1.50% |
0.005 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_INT_PREDICT_RAW/171
|
-1.51% |
6.911 |
6.806 |
0.011 |
-1.71% |
0.011 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<16, GreaterThanZero, First>
|
-1.48% |
8615.298 |
8487.648 |
8.049 |
-0.10% |
8.049 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, LessThanZero, Mid>
|
-1.48% |
31882.402 |
31411.052 |
26.204 |
-1.17% |
26.204 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint16_t_To_uint32_t_
|
-1.46% |
13498.614 |
13301.802 |
19.120 |
-1.35% |
19.120 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, LessThanZero, Mid>
|
-1.44% |
56577.111 |
55759.839 |
5.937 |
-1.36% |
5.937 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC64
|
-1.44% |
86.345 |
85.102 |
0.168 |
-1.45% |
0.168 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC127
|
-1.43% |
220.285 |
217.132 |
0.021 |
-1.43% |
0.021 |
|
External/SPEC/CFP2017rate/511.povray_r/511.povray_r
Profile
|
-1.42% |
33.935 |
33.454 |
0.061 |
-0.98% |
0.061 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<3, GreaterThanZero, None>
|
-1.38% |
45108.794 |
44484.717 |
146.402 |
-1.46% |
146.402 |
|
External/SPEC/CINT2017rate/523.xalancbmk_r/523.xalancbmk_r
Profile
|
-1.38% |
241.208 |
237.891 |
1.176 |
-1.27% |
1.176 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint64_t>/51
|
-1.36% |
229.007 |
225.892 |
0.014 |
-1.36% |
0.014 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<8, LessThanZero, Mid>
|
-1.33% |
19494.554 |
19235.209 |
1.545 |
-1.03% |
1.545 |
|
SingleSource/Benchmarks/Shootout-C++/Shootout-C++-hash2
Profile
|
-1.30% |
9.349 |
9.228 |
0.022 |
-1.16% |
0.022 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC127
|
-1.28% |
197.123 |
194.593 |
0.013 |
-1.27% |
0.013 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC128
|
-1.26% |
198.355 |
195.858 |
0.010 |
-1.27% |
0.010 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, LessThanZero, None>
|
-1.24% |
37511.074 |
37047.640 |
28.319 |
-1.41% |
28.319 |
|
MultiSource/Benchmarks/MallocBench/cfrac/cfrac
Profile
|
-1.23% |
2.781 |
2.747 |
0.005 |
-1.20% |
0.005 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<32, GreaterThanZero, Mid>
|
-1.22% |
4551.345 |
4495.995 |
1.135 |
-1.31% |
1.135 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopFrom_uint64_t_To_uint16_t_
|
-1.22% |
14829.139 |
14648.823 |
17.199 |
-1.26% |
17.199 |
|
MultiSource/Applications/hexxagon/hexxagon
Profile
|
-1.20% |
14.909 |
14.730 |
0.003 |
0.83% |
0.003 |
|
MultiSource/Applications/obsequi/Obsequi
Profile
|
-1.19% |
7.683 |
7.592 |
0.011 |
-0.90% |
0.011 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_sinhf_novec_float_
|
-1.17% |
2243.166 |
2216.947 |
0.587 |
-1.11% |
0.587 |
|
SingleSource/Benchmarks/SmallPT/smallpt
Profile
|
-1.14% |
30.048 |
29.705 |
0.001 |
-1.08% |
0.001 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<7, EqZero, None>
|
-1.13% |
27180.317 |
26872.709 |
11.699 |
-1.13% |
11.699 |
|
MultiSource/Benchmarks/Prolangs-C++/primes/primes
Profile
|
-1.11% |
0.981 |
0.970 |
0.004 |
0.14% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_sinhf_autovec_float_
|
-1.06% |
2241.559 |
2217.701 |
0.583 |
-1.11% |
0.583 |
|
SingleSource/Benchmarks/Adobe-C++/simple_types_loop_invariant
Profile
|
-1.03% |
1.851 |
1.832 |
0.002 |
-1.66% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_sinh_novec_double_
|
-1.02% |
2470.151 |
2445.044 |
1.878 |
-1.17% |
1.878 |