|
MultiSource/Benchmarks/DOE-ProxyApps-C/miniGMG/miniGMG
Profile
|
-50.32% |
9.187 |
4.564 |
0.373 |
-50.34% |
0.373 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint64_t_To_uint32_t_
|
-48.85% |
35246.326 |
18028.210 |
1227.017 |
-48.95% |
1227.017 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint64_t_To_uint16_t_
|
-48.81% |
35792.213 |
18322.426 |
627.060 |
-48.65% |
627.060 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint64_t_To_uint8_t_
|
-48.65% |
37027.647 |
19012.172 |
41.015 |
-48.70% |
41.015 |
|
SingleSource/Benchmarks/Polybench/stencils/seidel-2d/seidel-2d
Profile
|
-47.44% |
230.508 |
121.150 |
0.262 |
0.05% |
0.262 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_DIFF_PREDICT_RAW/44217
|
-44.69% |
24439.711 |
13517.143 |
296.201 |
-41.99% |
296.201 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint16_t_To_uint64_t_
|
-43.97% |
18639.654 |
10443.911 |
3.371 |
-44.08% |
3.371 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_DIFF_PREDICT_LAMBDA/44217
|
-41.62% |
23106.077 |
13488.931 |
337.854 |
-41.61% |
337.854 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint8_t_To_uint64_t_
|
-41.25% |
17859.080 |
10492.718 |
21.195 |
-41.05% |
21.195 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_DIFF_PREDICT_LAMBDA/5001
|
-40.96% |
2559.975 |
1511.466 |
36.709 |
-39.77% |
36.709 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint64_t_To_uint32_t_
|
-40.76% |
38275.289 |
22674.594 |
63.974 |
-40.57% |
63.974 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_DIFF_PREDICT_RAW/5001
|
-40.11% |
2532.671 |
1516.699 |
42.745 |
-41.09% |
42.745 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIRST_DIFF_RAW/44217
|
-39.10% |
167.129 |
101.785 |
0.993 |
-28.57% |
0.993 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint32_t_To_uint64_t_
|
-36.88% |
22572.826 |
14246.844 |
291.820 |
-37.31% |
291.820 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/32
|
-36.69% |
1396.194 |
883.918 |
0.102 |
-36.69% |
0.102 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/64
|
-36.67% |
6181.751 |
3914.829 |
0.661 |
-36.68% |
0.661 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/16
|
-36.64% |
279.503 |
177.092 |
0.014 |
-36.63% |
0.014 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/256
|
-36.15% |
107099.327 |
68384.658 |
6.585 |
-36.18% |
6.585 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/128
|
-36.12% |
26265.460 |
16779.005 |
10.235 |
-36.13% |
10.235 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_HYDRO_2D_LAMBDA/44217
|
-34.83% |
88865.479 |
57911.012 |
795.878 |
-36.31% |
795.878 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIRST_DIFF_LAMBDA/44217
|
-34.24% |
153.367 |
100.851 |
1.102 |
-30.36% |
1.102 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint64_t_To_uint8_t_
|
-34.19% |
30186.058 |
19865.891 |
56.878 |
-34.02% |
56.878 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint64_t_To_uint16_t_
|
-34.13% |
28935.744 |
19060.830 |
46.263 |
-34.16% |
46.263 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_PIC_2D_RAW/5001
|
-33.12% |
1187.796 |
794.377 |
69.297 |
-26.34% |
69.297 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, EqZero, None>
|
-31.24% |
20511.532 |
14104.223 |
0.597 |
-31.24% |
0.597 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_HYDRO_2D_LAMBDA/5001
|
-30.92% |
9272.607 |
6405.919 |
113.021 |
-29.71% |
113.021 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_INT_PREDICT_RAW/44217
|
-28.67% |
11156.553 |
7957.960 |
115.246 |
-12.06% |
115.246 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint64_t_To_uint16_t_
|
-28.59% |
25914.085 |
18505.817 |
45.678 |
-28.54% |
45.678 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint32_t_To_uint8_t_
|
-28.09% |
13507.676 |
9713.599 |
31.511 |
-27.88% |
31.511 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC128
|
-27.66% |
1293.880 |
935.936 |
4.731 |
-27.61% |
4.731 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC64
|
-27.02% |
654.263 |
477.462 |
0.092 |
-26.95% |
0.092 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC128
|
-27.01% |
558.653 |
407.745 |
0.028 |
-26.87% |
0.028 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC32
|
-26.89% |
334.562 |
244.587 |
0.170 |
-26.76% |
0.170 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC16
|
-26.30% |
174.401 |
128.525 |
0.176 |
-26.04% |
0.176 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC64
|
-25.63% |
292.096 |
217.228 |
0.079 |
-25.56% |
0.079 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint64_t_To_uint8_t_
|
-24.28% |
27258.384 |
20640.337 |
99.299 |
-24.18% |
99.299 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, EqZero, None>
|
-23.99% |
16024.376 |
12180.820 |
0.563 |
-23.98% |
0.563 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIRST_SUM_RAW/44217
|
-23.50% |
177.435 |
135.735 |
0.470 |
-18.40% |
0.470 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC128
|
-23.21% |
603.901 |
463.763 |
0.035 |
-23.21% |
0.035 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC32
|
-23.16% |
158.793 |
122.021 |
0.081 |
-23.20% |
0.081 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC128
|
-23.10% |
603.915 |
464.414 |
0.009 |
-23.10% |
0.009 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_PIC_2D_LAMBDA/44217
|
-23.02% |
11202.662 |
8624.222 |
75.662 |
-21.33% |
75.662 |
|
MicroBenchmarks/ImageProcessing/Blur/blur.test:BENCHMARK_boxBlurKernel/1024
|
-22.60% |
30084.147 |
23285.689 |
71.057 |
-22.76% |
71.057 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC64
|
-22.35% |
313.514 |
243.434 |
0.002 |
-22.35% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC127
|
-22.17% |
615.182 |
478.813 |
0.010 |
-22.17% |
0.010 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC64
|
-22.16% |
313.508 |
244.043 |
0.017 |
-22.16% |
0.017 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC127
|
-21.98% |
615.246 |
480.029 |
0.042 |
-21.97% |
0.042 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint16_t_To_uint32_t_
|
-21.76% |
7116.911 |
5568.209 |
3.263 |
-21.59% |
3.263 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint16_t_To_uint64_t_
|
-21.76% |
13244.797 |
10362.837 |
0.782 |
-21.54% |
0.782 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint8_t_To_uint32_t_
|
-21.52% |
6587.215 |
5169.702 |
0.658 |
-21.46% |
0.658 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_only_autovec_uint8_t_
|
-21.36% |
182395.230 |
143434.498 |
25.264 |
-21.34% |
25.264 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIND_FIRST_MIN_LAMBDA/171
|
-21.30% |
1.501 |
1.181 |
0.000 |
-21.29% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIND_FIRST_MIN_LAMBDA/44217
|
-21.24% |
389.133 |
306.464 |
0.319 |
-21.33% |
0.319 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIND_FIRST_MIN_LAMBDA/5001
|
-20.83% |
45.234 |
35.811 |
0.228 |
-20.87% |
0.228 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC32
|
-20.82% |
168.327 |
133.285 |
0.003 |
-20.82% |
0.003 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIRST_SUM_LAMBDA/44217
|
-20.79% |
170.663 |
135.189 |
0.262 |
-19.09% |
0.262 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint32_t_To_uint16_t_
|
-20.65% |
10565.558 |
8384.262 |
532.019 |
-15.35% |
532.019 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC32
|
-20.45% |
168.334 |
133.909 |
0.001 |
-20.45% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC63
|
-20.43% |
324.805 |
258.455 |
0.015 |
-20.42% |
0.015 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC64
|
-20.29% |
151.010 |
120.377 |
3.608 |
-19.01% |
3.608 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_HYDRO_1D_LAMBDA/5001
|
-20.11% |
19.128 |
15.281 |
0.752 |
-11.02% |
0.752 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC128
|
-20.05% |
274.396 |
219.384 |
1.745 |
-20.15% |
1.745 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC63
|
-20.03% |
324.754 |
259.701 |
0.014 |
-20.04% |
0.014 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC63
|
-19.96% |
150.561 |
120.506 |
4.514 |
-19.62% |
4.514 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_DISC_ORD_LAMBDA/44217
|
-19.92% |
14169.502 |
11347.087 |
67.956 |
-19.26% |
67.956 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC127
|
-19.87% |
274.145 |
219.673 |
0.299 |
-20.25% |
0.299 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC127
|
-19.74% |
641.009 |
514.488 |
0.119 |
-19.67% |
0.119 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint32_t_To_uint8_t_
|
-19.64% |
13947.476 |
11208.421 |
63.240 |
-19.37% |
63.240 |
|
MultiSource/Benchmarks/MiBench/automotive-bitcount/automotive-bitcount
Profile
|
-19.33% |
0.125 |
0.101 |
0.003 |
-18.55% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC16
|
-19.31% |
92.288 |
74.466 |
0.027 |
-19.30% |
0.027 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint16_t_To_uint8_t_
|
-19.10% |
3818.808 |
3089.539 |
0.152 |
-19.08% |
0.152 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_PIC_1D_LAMBDA/44217
|
-18.87% |
13509.061 |
10959.808 |
41.329 |
-18.60% |
41.329 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_VOL3D_CALC_RAW/2
|
-18.81% |
8.758 |
7.110 |
0.000 |
-18.80% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_VOL3D_CALC_LAMBDA/2
|
-18.80% |
8.757 |
7.111 |
0.001 |
-18.80% |
0.001 |
|
SingleSource/Benchmarks/Adobe-C++/loop_unroll
Profile
|
-18.76% |
2.981 |
2.422 |
0.002 |
-22.04% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint32_t_To_uint16_t_
|
-18.46% |
13803.403 |
11255.054 |
9.391 |
-18.48% |
9.391 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint64_t_To_uint32_t_
|
-18.41% |
27088.581 |
22101.810 |
35.445 |
-18.30% |
35.445 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC16
|
-18.31% |
95.744 |
78.216 |
0.001 |
-18.30% |
0.001 |
|
MultiSource/Benchmarks/Trimaran/enc-pc1/enc-pc1
Profile
|
-18.10% |
1.105 |
0.905 |
0.000 |
-18.09% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_with_cond_arith_novec_uint8_t_
|
-17.93% |
746578.264 |
612708.331 |
287.932 |
-17.84% |
287.932 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint8_t_To_uint64_t_
|
-17.79% |
13275.726 |
10914.142 |
8.509 |
-16.46% |
8.509 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC16
|
-17.65% |
95.745 |
78.843 |
0.004 |
-17.65% |
0.004 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_INT_PREDICT_LAMBDA/5001
|
-17.50% |
1103.934 |
910.704 |
7.281 |
0.66% |
7.281 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_with_cond_arith_novec_int32_t_
|
-17.47% |
740923.740 |
611515.408 |
817.780 |
-17.38% |
817.780 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC31
|
-17.43% |
179.596 |
148.296 |
0.008 |
-17.42% |
0.008 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC4
|
-17.35% |
17.520 |
14.480 |
0.011 |
-17.35% |
0.011 |
|
MultiSource/Benchmarks/MiBench/security-rijndael/security-rijndael
Profile
|
-17.32% |
0.335 |
0.277 |
0.000 |
-17.25% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC128
|
-17.26% |
570.701 |
472.208 |
0.019 |
-17.24% |
0.019 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC64
|
-17.12% |
297.866 |
246.869 |
0.017 |
-17.08% |
0.017 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC32
|
-16.86% |
161.449 |
134.227 |
0.012 |
-16.83% |
0.012 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC31
|
-16.72% |
179.593 |
149.557 |
0.003 |
-16.72% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC16
|
-16.48% |
93.233 |
77.870 |
0.028 |
-16.38% |
0.028 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_HYDRO_1D_RAW/171
|
-16.39% |
0.445 |
0.372 |
0.000 |
-15.83% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_VOL3D_CALC_RAW/0
|
-16.37% |
1269.446 |
1061.627 |
1.397 |
-16.09% |
1.397 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_VOL3D_CALC_LAMBDA/0
|
-16.34% |
1267.043 |
1059.956 |
1.835 |
-16.38% |
1.835 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_HYDRO_1D_LAMBDA/171
|
-16.24% |
0.444 |
0.372 |
0.000 |
-15.87% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC31
|
-16.16% |
87.110 |
73.029 |
1.560 |
-15.20% |
1.560 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC32
|
-16.15% |
85.487 |
71.685 |
2.175 |
-15.99% |
2.175 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_VOL3D_CALC_LAMBDA/1
|
-16.08% |
260.165 |
218.320 |
0.040 |
-16.09% |
0.040 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_VOL3D_CALC_RAW/1
|
-16.07% |
260.097 |
218.296 |
0.136 |
-16.08% |
0.136 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint16_t_To_uint32_t_
|
-15.67% |
7463.534 |
6293.927 |
0.977 |
-15.66% |
0.977 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint32_t_To_uint8_t_
|
-15.49% |
10638.847 |
8990.857 |
32.167 |
-15.14% |
32.167 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC8
|
-15.43% |
58.820 |
49.743 |
0.001 |
-15.35% |
0.001 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, EqZero, First>
|
-15.39% |
16670.038 |
14103.735 |
0.421 |
-15.40% |
0.421 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_no_runtime_checks_needed<16, int>
|
-15.39% |
24.403 |
20.649 |
0.001 |
-15.39% |
0.001 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, EqZero, Mid>
|
-15.38% |
16666.942 |
14104.287 |
0.455 |
-15.37% |
0.455 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, EqZero, Last>
|
-15.35% |
16667.741 |
14109.292 |
0.309 |
-15.35% |
0.309 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_DISC_ORD_RAW/5001
|
-15.33% |
715.829 |
606.095 |
14.776 |
-8.82% |
14.776 |
|
MicroBenchmarks/ImageProcessing/Dilate/Dilate.test:BENCHMARK_DILATE/1024
|
-15.23% |
7450.028 |
6315.049 |
233.978 |
-11.19% |
233.978 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC127
|
-14.87% |
605.837 |
515.724 |
0.143 |
-14.86% |
0.143 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC8
|
-14.74% |
59.443 |
50.683 |
0.003 |
-14.75% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC128
|
-14.57% |
1103.385 |
942.624 |
0.009 |
-14.56% |
0.009 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC127
|
-14.54% |
1095.639 |
936.336 |
0.057 |
-14.51% |
0.057 |
|
MicroBenchmarks/ImageProcessing/Dilate/Dilate.test:BENCHMARK_DILATE/128
|
-14.42% |
229.004 |
195.983 |
5.298 |
-14.03% |
5.298 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC64
|
-14.34% |
562.524 |
481.858 |
0.028 |
-14.31% |
0.028 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint8_t_To_uint16_t_
|
-14.28% |
3757.145 |
3220.629 |
7.490 |
-14.27% |
7.490 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC63
|
-14.25% |
554.657 |
475.605 |
0.013 |
-14.27% |
0.013 |
|
SingleSource/Benchmarks/Misc/salsa20
Profile
|
-14.14% |
15.387 |
13.211 |
0.000 |
-14.12% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_with_cond_arith_novec_int64_t_
|
-14.02% |
793070.939 |
681883.438 |
584.817 |
-13.47% |
584.817 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint32_t_To_uint16_t_
|
-13.95% |
12879.645 |
11083.391 |
16.618 |
-13.66% |
16.618 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC32
|
-13.93% |
292.249 |
251.548 |
0.011 |
-13.85% |
0.011 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_with_cond_arith_autovec_int64_t_
|
-13.91% |
792316.285 |
682104.082 |
1661.169 |
-13.83% |
1661.169 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC8
|
-13.86% |
51.939 |
44.738 |
0.005 |
-13.86% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC4
|
-13.86% |
51.936 |
44.738 |
0.001 |
-13.86% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC7
|
-13.86% |
51.934 |
44.737 |
0.003 |
-13.86% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC2
|
-13.86% |
51.936 |
44.739 |
0.002 |
-13.85% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC1
|
-13.86% |
51.936 |
44.740 |
0.004 |
-13.85% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC3
|
-13.86% |
51.938 |
44.741 |
0.002 |
-13.85% |
0.002 |
|
External/SPEC/CFP2017rate/508.namd_r/508.namd_r
Profile
|
-13.82% |
224.272 |
193.271 |
0.098 |
-13.56% |
0.098 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_INT_PREDICT_LAMBDA/44217
|
-13.78% |
9323.917 |
8039.227 |
69.817 |
-3.58% |
69.817 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC8
|
-13.68% |
59.444 |
51.310 |
0.002 |
-13.69% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC31
|
-13.67% |
284.143 |
245.292 |
0.009 |
-13.66% |
0.009 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC4
|
-13.64% |
112.093 |
96.799 |
0.239 |
-14.40% |
0.239 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, EqZero, Mid>
|
-13.63% |
14103.566 |
12181.753 |
0.818 |
-13.62% |
0.818 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, EqZero, Last>
|
-13.63% |
14104.255 |
12182.407 |
0.151 |
-13.63% |
0.151 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, EqZero, First>
|
-13.62% |
14103.023 |
12182.221 |
0.123 |
-13.62% |
0.123 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC8
|
-13.54% |
23.153 |
20.017 |
0.003 |
-13.54% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint64_t_To_uint8_t_
|
-13.52% |
22080.923 |
19095.917 |
104.898 |
-13.39% |
104.898 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC63
|
-13.44% |
374.518 |
324.174 |
0.031 |
-13.42% |
0.031 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIRST_SUM_RAW/5001
|
-13.40% |
20.590 |
17.832 |
0.574 |
2.80% |
0.574 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint32_t_To_uint8_t_
|
-13.38% |
11038.829 |
9562.004 |
55.776 |
-14.08% |
55.776 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC8
|
-13.16% |
23.779 |
20.649 |
0.001 |
-13.16% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC16
|
-13.15% |
157.066 |
136.408 |
0.006 |
-13.10% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC128
|
-13.09% |
81.350 |
70.704 |
0.003 |
-13.08% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC16
|
-13.03% |
51.941 |
45.170 |
0.388 |
-13.04% |
0.388 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint8_t_To_uint16_t_
|
-12.96% |
4542.335 |
3953.709 |
0.491 |
-12.95% |
0.491 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC15
|
-12.87% |
107.007 |
93.232 |
0.003 |
-12.87% |
0.003 |
|
SingleSource/Benchmarks/Shootout-C++/Shootout-C++-matrix
Profile
|
-12.73% |
2.509 |
2.190 |
0.000 |
-12.71% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC63
|
-12.69% |
332.935 |
290.680 |
0.005 |
-12.66% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC15
|
-12.61% |
148.926 |
130.147 |
0.015 |
-12.54% |
0.015 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint16_t_To_uint8_t_
|
-12.40% |
4743.110 |
4154.865 |
0.317 |
-12.40% |
0.317 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_PIC_2D_LAMBDA/5001
|
-12.38% |
1063.512 |
931.862 |
27.161 |
-15.71% |
27.161 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC8
|
-11.89% |
89.479 |
78.837 |
0.005 |
-11.82% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC2
|
-11.76% |
21.274 |
18.772 |
0.001 |
-11.77% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC15
|
-11.69% |
107.000 |
94.489 |
0.002 |
-11.70% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC16
|
-11.45% |
33.164 |
29.366 |
0.020 |
-11.45% |
0.020 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC15
|
-11.45% |
51.936 |
45.992 |
0.001 |
-11.45% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC4
|
-11.11% |
22.526 |
20.022 |
0.002 |
-11.12% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC4
|
-11.11% |
22.527 |
20.023 |
0.001 |
-11.11% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC3
|
-11.10% |
22.525 |
20.024 |
0.000 |
-11.11% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint32_t_To_uint64_t_
|
-11.10% |
17092.447 |
15194.984 |
200.923 |
-11.64% |
200.923 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint8_t>/51
|
-11.00% |
123.896 |
110.263 |
0.306 |
19.20% |
0.306 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC7
|
-10.78% |
81.347 |
72.578 |
0.005 |
-10.74% |
0.005 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_BAND_LIN_EQ_RAW/171
|
-10.61% |
0.384 |
0.343 |
0.000 |
-6.33% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_BAND_LIN_EQ_LAMBDA/171
|
-10.61% |
0.384 |
0.343 |
0.000 |
-6.33% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC4
|
-10.60% |
41.296 |
36.918 |
0.002 |
-10.61% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC4
|
-10.54% |
23.779 |
21.274 |
0.001 |
-10.54% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC64
|
-10.47% |
53.817 |
48.181 |
0.002 |
-10.47% |
0.002 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/16
|
-10.18% |
115.462 |
103.704 |
0.025 |
-10.19% |
0.025 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC4
|
-10.11% |
55.691 |
50.060 |
0.002 |
-10.07% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint8_t_To_uint16_t_
|
-10.11% |
5846.955 |
5255.731 |
22.257 |
-10.16% |
22.257 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC8
|
-10.10% |
27.144 |
24.402 |
0.001 |
-9.33% |
0.001 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/64
|
-10.01% |
1912.802 |
1721.421 |
0.901 |
-10.03% |
0.901 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/32
|
-9.99% |
473.033 |
425.791 |
0.020 |
-9.98% |
0.020 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/256
|
-9.94% |
31441.424 |
28317.352 |
7.628 |
-9.96% |
7.628 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC127
|
-9.80% |
101.971 |
91.980 |
0.004 |
-9.72% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC15
|
-9.79% |
44.784 |
40.399 |
1.605 |
-9.07% |
1.605 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC8
|
-9.77% |
25.657 |
23.151 |
0.001 |
-9.76% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC8
|
-9.77% |
25.657 |
23.151 |
0.002 |
-9.77% |
0.002 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/128
|
-9.75% |
7913.452 |
7141.999 |
1.376 |
-9.79% |
1.376 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_DIFF_PREDICT_RAW/171
|
-9.69% |
12.302 |
11.110 |
0.046 |
-6.89% |
0.046 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_only_autovec_int64_t_
|
-9.65% |
332665.675 |
300547.807 |
564.057 |
-9.82% |
564.057 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC7
|
-9.61% |
32.537 |
29.409 |
0.001 |
-9.62% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC7
|
-9.52% |
26.280 |
23.777 |
0.006 |
-9.53% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC7
|
-9.52% |
26.279 |
23.778 |
0.001 |
-9.53% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC32
|
-9.43% |
53.186 |
48.169 |
0.007 |
-9.45% |
0.007 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC31
|
-9.42% |
196.488 |
177.974 |
0.022 |
-9.41% |
0.022 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_DEL_DOT_VEC_2D_LAMBDA/1
|
-9.23% |
287.289 |
260.762 |
0.034 |
-9.18% |
0.034 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_DEL_DOT_VEC_2D_RAW/1
|
-9.21% |
287.133 |
260.685 |
0.049 |
-9.17% |
0.049 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC4
|
-9.08% |
41.296 |
37.544 |
0.002 |
-9.09% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC7
|
-8.89% |
28.158 |
25.655 |
0.002 |
-8.90% |
0.002 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_runtime_checks_pass<4, int>
|
-8.89% |
16.825 |
15.329 |
0.002 |
-8.25% |
0.002 |
|
MultiSource/Benchmarks/FreeBench/pifft/pifft
Profile
|
-8.79% |
0.359 |
0.327 |
0.000 |
-8.74% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_DEL_DOT_VEC_2D_RAW/2
|
-8.72% |
3.510 |
3.204 |
0.000 |
-8.71% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_DEL_DOT_VEC_2D_LAMBDA/2
|
-8.71% |
3.510 |
3.204 |
0.000 |
-8.70% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC16
|
-8.62% |
36.293 |
33.165 |
0.000 |
-8.62% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC8
|
-8.51% |
29.411 |
26.907 |
0.000 |
-8.51% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint16_t_To_uint8_t_
|
-8.51% |
6809.945 |
6230.224 |
24.577 |
-8.59% |
24.577 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint8_t_To_uint32_t_
|
-8.24% |
12804.180 |
11748.875 |
27.538 |
-8.06% |
27.538 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC2
|
-8.20% |
38.170 |
35.040 |
0.002 |
-8.20% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC64
|
-8.06% |
93.231 |
85.720 |
0.003 |
-8.07% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint16_t_To_uint64_t_
|
-8.03% |
20339.252 |
18707.024 |
31.078 |
-7.13% |
31.078 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC3
|
-7.90% |
47.554 |
43.800 |
0.003 |
-7.90% |
0.003 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_PRESSURE_CALC_LAMBDA/5001
|
-7.89% |
45.000 |
41.452 |
0.180 |
-5.74% |
0.180 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC16
|
-7.85% |
31.912 |
29.408 |
0.001 |
-7.85% |
0.001 |
|
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 |
36.917 |
0.002 |
-7.82% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC15
|
-7.70% |
32.540 |
30.035 |
0.001 |
-7.69% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC15
|
-7.69% |
32.538 |
30.035 |
0.001 |
-7.70% |
0.001 |
|
MultiSource/Benchmarks/VersaBench/beamformer/beamformer
Profile
|
-7.61% |
5.200 |
4.805 |
0.001 |
-7.62% |
0.001 |
|
MultiSource/Benchmarks/Trimaran/enc-md5/enc-md5
Profile
|
-7.54% |
3.507 |
3.243 |
0.000 |
-7.50% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_DEL_DOT_VEC_2D_LAMBDA/0
|
-7.50% |
1795.007 |
1660.392 |
3.560 |
-7.34% |
3.560 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_xor_no_runtime_checks_needed<16, int>
|
-7.41% |
16.895 |
15.642 |
0.001 |
-7.42% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint16_t_To_uint64_t_
|
-7.39% |
25100.903 |
23246.667 |
46.876 |
-6.96% |
46.876 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_DEL_DOT_VEC_2D_RAW/0
|
-7.37% |
1791.896 |
1659.882 |
5.516 |
-7.83% |
5.516 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint8_t>/28
|
-7.35% |
82.605 |
76.534 |
0.610 |
13.23% |
0.610 |
|
MultiSource/Applications/lambda-0.1.3/lambda
Profile
|
-7.31% |
15.874 |
14.714 |
0.006 |
-7.28% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC7
|
-7.27% |
349.608 |
324.189 |
0.515 |
-8.60% |
0.515 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIND_FIRST_MIN_RAW/171
|
-7.23% |
1.497 |
1.389 |
0.000 |
-7.19% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC128
|
-7.23% |
173.345 |
160.817 |
0.006 |
-7.22% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint8_t>/127
|
-7.21% |
138.922 |
128.904 |
0.005 |
-7.21% |
0.005 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_BAND_LIN_EQ_RAW/5001
|
-7.14% |
21.547 |
20.009 |
0.174 |
-2.97% |
0.174 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_DIFF_PREDICT_LAMBDA/171
|
-7.09% |
11.953 |
11.106 |
0.016 |
-7.34% |
0.016 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC7
|
-7.08% |
70.710 |
65.702 |
0.001 |
-7.09% |
0.001 |
|
SingleSource/Benchmarks/Misc/pi
Profile
|
-7.02% |
1.782 |
1.657 |
0.000 |
-7.02% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC15
|
-6.94% |
45.051 |
41.923 |
0.024 |
-6.95% |
0.024 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC15
|
-6.90% |
54.443 |
50.686 |
0.003 |
-6.90% |
0.003 |
|
SingleSource/Benchmarks/Misc/oourafft
Profile
|
-6.90% |
15.425 |
14.361 |
0.070 |
-4.85% |
0.070 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_HYDRO_2D_LAMBDA/171
|
-6.88% |
88.160 |
82.090 |
0.639 |
-7.41% |
0.639 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_HYDRO_2D_RAW/171
|
-6.85% |
88.574 |
82.508 |
0.291 |
-6.90% |
0.291 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC31
|
-6.73% |
74.461 |
69.451 |
0.006 |
-6.73% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_only_autovec_int32_t_
|
-6.56% |
181271.654 |
169377.059 |
525.958 |
-6.48% |
525.958 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC63
|
-6.55% |
114.516 |
107.015 |
0.211 |
-6.55% |
0.211 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_xor_runtime_checks_pass<16, int>
|
-6.52% |
28.782 |
26.905 |
0.001 |
-6.52% |
0.001 |
|
SingleSource/Benchmarks/Stanford/Puzzle
Profile
|
-6.52% |
0.241 |
0.226 |
0.005 |
-6.53% |
0.005 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_xor_runtime_checks_fail<16, int>
|
-6.51% |
28.783 |
26.908 |
0.001 |
-6.51% |
0.001 |
|
SingleSource/Benchmarks/Misc/flops-6
Profile
|
-6.46% |
1.311 |
1.226 |
0.001 |
-6.55% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC128
|
-6.41% |
68.829 |
64.416 |
0.011 |
-6.38% |
0.011 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC127
|
-6.41% |
194.617 |
182.142 |
0.343 |
-6.41% |
0.343 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_INT_PREDICT_RAW/5001
|
-6.39% |
952.216 |
891.358 |
10.201 |
-2.42% |
10.201 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC127
|
-6.38% |
68.827 |
64.437 |
0.014 |
-5.64% |
0.014 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC15
|
-6.35% |
39.420 |
36.917 |
0.010 |
-6.35% |
0.010 |
|
MultiSource/Benchmarks/McCat/12-IOtest/iotest
Profile
|
-6.34% |
1.833 |
1.717 |
0.032 |
-5.92% |
0.032 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_BAND_LIN_EQ_LAMBDA/5001
|
-6.30% |
21.431 |
20.080 |
0.147 |
-3.46% |
0.147 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint16_t>/127
|
-6.30% |
138.909 |
130.158 |
0.001 |
-6.30% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC63
|
-6.26% |
74.096 |
69.458 |
0.002 |
-6.42% |
0.002 |
|
SingleSource/Benchmarks/Misc-C++/Large/sphereflake
Profile
|
-6.23% |
20.014 |
18.768 |
0.004 |
-6.17% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC127
|
-6.21% |
2384.361 |
2236.362 |
8.883 |
-7.84% |
8.883 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC16
|
-6.15% |
40.671 |
38.171 |
0.002 |
-6.15% |
0.002 |
|
External/SPEC/CFP2017rate/538.imagick_r/538.imagick_r
Profile
|
-6.14% |
292.828 |
274.850 |
0.195 |
-5.90% |
0.195 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIND_FIRST_MIN_RAW/5001
|
-6.00% |
45.314 |
42.596 |
0.078 |
-6.05% |
0.078 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint8_t>/65
|
-5.92% |
95.112 |
89.481 |
0.004 |
-5.92% |
0.004 |
|
MultiSource/Benchmarks/MiBench/telecomm-gsm/telecomm-gsm
Profile
|
-5.89% |
0.663 |
0.624 |
0.000 |
-5.97% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint32_t>/127
|
-5.88% |
138.276 |
130.151 |
0.007 |
-5.88% |
0.007 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint32_t_To_uint64_t_
|
-5.87% |
21557.973 |
20291.587 |
24.646 |
-5.40% |
24.646 |
|
MultiSource/Benchmarks/Rodinia/hotspot/hotspot
Profile
|
-5.77% |
2.035 |
1.918 |
0.003 |
-5.80% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC16
|
-5.66% |
33.162 |
31.287 |
0.001 |
-5.66% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC32
|
-5.65% |
44.429 |
41.920 |
0.004 |
-5.64% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC32
|
-5.64% |
44.430 |
41.924 |
0.003 |
-5.64% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC31
|
-5.59% |
45.065 |
42.547 |
0.003 |
-5.59% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint8_t_To_uint16_t_
|
-5.58% |
3630.226 |
3427.696 |
34.366 |
-5.66% |
34.366 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC31
|
-5.56% |
45.054 |
42.548 |
0.003 |
-5.56% |
0.003 |
|
MultiSource/Benchmarks/SciMark2-C/scimark2
Profile
|
-5.56% |
107.686 |
101.703 |
0.081 |
-5.51% |
0.081 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC16
|
-5.49% |
31.842 |
30.095 |
0.051 |
-3.82% |
0.051 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C++/miniFE/miniFE
Profile
|
-5.43% |
15.806 |
14.948 |
0.074 |
-6.39% |
0.074 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint32_t>/999
|
-5.38% |
696.493 |
658.997 |
0.023 |
-5.39% |
0.023 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_PIC_2D_LAMBDA/171
|
-5.32% |
13.482 |
12.764 |
0.063 |
-5.44% |
0.063 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC7
|
-5.32% |
70.712 |
66.951 |
0.003 |
-5.33% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopWithReductionTC1
|
-5.27% |
11.889 |
11.263 |
0.000 |
-5.26% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint32_t>/999
|
-5.23% |
1365.038 |
1293.683 |
0.069 |
-5.23% |
0.069 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIND_FIRST_MIN_RAW/44217
|
-5.22% |
389.538 |
369.213 |
0.523 |
-5.23% |
0.523 |
|
SingleSource/Benchmarks/Polybench/stencils/jacobi-2d/jacobi-2d
Profile
|
-5.21% |
31.967 |
30.301 |
0.101 |
-5.97% |
0.101 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC32
|
-5.19% |
61.320 |
58.136 |
0.028 |
-5.19% |
0.028 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC31
|
-5.14% |
24.404 |
23.151 |
0.001 |
-5.13% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC31
|
-5.13% |
24.405 |
23.152 |
0.001 |
-5.13% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC32
|
-5.13% |
24.405 |
23.153 |
0.002 |
-5.13% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC32
|
-5.13% |
24.404 |
23.153 |
0.001 |
-5.12% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC15
|
-5.13% |
128.275 |
121.696 |
0.003 |
-5.12% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC31
|
-5.07% |
241.260 |
229.022 |
0.019 |
-5.06% |
0.019 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC1
|
-5.05% |
88.093 |
83.649 |
0.269 |
-6.00% |
0.269 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_PIC_2D_RAW/171
|
-5.02% |
13.520 |
12.841 |
0.052 |
-5.15% |
0.052 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_PRESSURE_CALC_RAW/44217
|
-4.91% |
504.117 |
479.373 |
2.258 |
-4.54% |
2.258 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint32_t>/256
|
-4.80% |
364.163 |
346.672 |
0.007 |
-4.80% |
0.007 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_PRESSURE_CALC_LAMBDA/44217
|
-4.68% |
503.035 |
479.487 |
2.813 |
-3.82% |
2.813 |
|
SingleSource/Benchmarks/Misc/revertBits
Profile
|
-4.66% |
0.641 |
0.611 |
0.000 |
-4.68% |
0.000 |
|
MultiSource/Benchmarks/TSVC/Recurrences-dbl/Recurrences-dbl
Profile
|
-4.62% |
10.345 |
9.867 |
0.136 |
-4.73% |
0.136 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint16_t>/65
|
-4.61% |
95.117 |
90.733 |
0.001 |
-4.61% |
0.001 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_runtime_checks_fail<16, int>
|
-4.61% |
54.438 |
51.931 |
0.004 |
-4.61% |
0.004 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_runtime_checks_pass<16, int>
|
-4.59% |
54.434 |
51.933 |
0.002 |
-4.60% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC64
|
-4.53% |
43.710 |
41.730 |
0.018 |
-3.35% |
0.018 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopWithReductionTC2
|
-4.52% |
13.767 |
13.144 |
0.001 |
-4.52% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC31
|
-4.47% |
70.084 |
66.955 |
0.002 |
-4.46% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_nested_cond_load_novec_int32_t_
|
-4.37% |
650220.385 |
621824.641 |
614.099 |
-3.62% |
614.099 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC7
|
-4.37% |
29.004 |
27.738 |
0.435 |
-3.22% |
0.435 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<32, EqZero, Last>
|
-4.36% |
7126.261 |
6815.208 |
40.379 |
-3.37% |
40.379 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC8
|
-4.36% |
14.392 |
13.765 |
0.001 |
-4.36% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC2
|
-4.36% |
14.392 |
13.765 |
0.001 |
-4.35% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC16
|
-4.36% |
14.393 |
13.766 |
0.000 |
-4.36% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC4
|
-4.35% |
14.392 |
13.766 |
0.001 |
-4.36% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC1
|
-4.35% |
14.394 |
13.767 |
0.000 |
-4.35% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC15
|
-4.35% |
14.392 |
13.766 |
0.001 |
-4.35% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC7
|
-4.35% |
14.392 |
13.766 |
0.000 |
-4.35% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC3
|
-4.35% |
14.391 |
13.765 |
0.001 |
-4.35% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC1
|
-4.35% |
14.392 |
13.766 |
0.000 |
-4.35% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC15
|
-4.35% |
14.392 |
13.766 |
0.000 |
-4.35% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC16
|
-4.35% |
14.392 |
13.766 |
0.000 |
-4.35% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC4
|
-4.35% |
14.391 |
13.765 |
0.001 |
-4.35% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC7
|
-4.35% |
14.392 |
13.766 |
0.000 |
-4.35% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC2
|
-4.35% |
14.392 |
13.766 |
0.000 |
-4.34% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC8
|
-4.35% |
14.391 |
13.766 |
0.000 |
-4.36% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC3
|
-4.35% |
14.392 |
13.766 |
0.000 |
-4.35% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint8_t_To_uint64_t_
|
-4.34% |
23509.913 |
22488.729 |
27.676 |
-4.24% |
27.676 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint64_t>/999
|
-4.26% |
1811.585 |
1734.499 |
0.102 |
-4.24% |
0.102 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_PIC_1D_RAW/5001
|
-4.21% |
362.938 |
347.671 |
4.784 |
0.77% |
4.784 |
|
External/SPEC/CFP2017rate/519.lbm_r/519.lbm_r
Profile
|
-4.19% |
200.669 |
192.251 |
1.382 |
-4.20% |
1.382 |
|
SingleSource/Benchmarks/Misc/flops-5
Profile
|
-4.19% |
2.021 |
1.936 |
0.001 |
-4.19% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint64_t>/999
|
-4.16% |
3595.308 |
3445.643 |
0.095 |
-4.15% |
0.095 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_ENERGY_CALC_RAW/171
|
-4.11% |
14.207 |
13.624 |
0.019 |
-4.33% |
0.019 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint8_t>/16
|
-4.10% |
59.885 |
57.431 |
0.449 |
6.71% |
0.449 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_ENERGY_CALC_LAMBDA/171
|
-4.08% |
14.205 |
13.625 |
0.018 |
-4.37% |
0.018 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint64_t>/256
|
-4.07% |
935.469 |
897.361 |
0.093 |
-4.09% |
0.093 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC31
|
-4.04% |
61.949 |
59.445 |
0.000 |
-4.04% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint32_t>/65
|
-3.98% |
94.486 |
90.726 |
0.003 |
-3.98% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC32
|
-3.97% |
63.203 |
60.694 |
0.004 |
-3.96% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_only_autovec_uint8_t_
|
-3.97% |
96169.271 |
92353.971 |
17.751 |
-3.96% |
17.751 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint32_t>/256
|
-3.95% |
221.512 |
212.760 |
0.013 |
-3.95% |
0.013 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint32_t_To_uint16_t_
|
-3.85% |
9834.185 |
9455.125 |
48.053 |
-4.30% |
48.053 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC3
|
-3.85% |
16.269 |
15.643 |
0.001 |
-3.85% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC31
|
-3.82% |
902.430 |
867.935 |
4.127 |
-5.35% |
4.127 |
|
MicroBenchmarks/ImageProcessing/Dilate/Dilate.test:BENCHMARK_DILATE/256
|
-3.82% |
1061.946 |
1021.367 |
4.060 |
-4.30% |
4.060 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint64_t_To_uint32_t_
|
-3.77% |
19399.980 |
18668.524 |
47.198 |
-3.23% |
47.198 |
|
MicroBenchmarks/ImageProcessing/Dilate/Dilate.test:BENCHMARK_DILATE/512
|
-3.72% |
3611.836 |
3477.619 |
22.869 |
-2.97% |
22.869 |
|
SingleSource/Benchmarks/Shootout/Shootout-matrix
Profile
|
-3.70% |
3.864 |
3.721 |
0.000 |
-3.69% |
0.000 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<31, EqZero, First>
|
-3.68% |
3346.110 |
3222.876 |
0.061 |
-3.69% |
0.061 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint64_t>/256
|
-3.64% |
514.389 |
495.650 |
0.022 |
-3.64% |
0.022 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_runtime_checks_fail<4, int>
|
-3.61% |
15.905 |
15.330 |
0.000 |
-3.63% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC64
|
-3.61% |
69.459 |
66.950 |
0.003 |
-3.61% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC64
|
-3.61% |
69.458 |
66.953 |
0.002 |
-3.61% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC63
|
-3.58% |
70.084 |
67.576 |
0.004 |
-3.59% |
0.004 |
|
SingleSource/Benchmarks/BenchmarkGame/n-body
Profile
|
-3.57% |
2.731 |
2.634 |
0.000 |
21.70% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC63
|
-3.57% |
70.082 |
67.580 |
0.001 |
-3.57% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint16_t_To_uint8_t_
|
-3.56% |
2872.550 |
2770.350 |
23.990 |
-3.75% |
23.990 |
|
MultiSource/Applications/JM/lencod/lencod
Profile
|
-3.48% |
32.763 |
31.622 |
0.014 |
-2.82% |
0.014 |
|
MultiSource/Benchmarks/nbench/nbench
Profile
|
-3.48% |
6.119 |
5.906 |
0.002 |
-3.61% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC63
|
-3.42% |
43.178 |
41.699 |
0.041 |
-3.68% |
0.041 |
|
External/SPEC/CFP2017rate/544.nab_r/544.nab_r
Profile
|
-3.25% |
476.167 |
460.686 |
0.118 |
-3.60% |
0.118 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC31
|
-3.21% |
93.779 |
90.766 |
0.220 |
-3.29% |
0.220 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint16_t>/999
|
-3.15% |
514.967 |
498.733 |
0.018 |
-3.16% |
0.018 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint16_t_To_uint8_t_
|
-3.14% |
4511.936 |
4370.037 |
20.927 |
-3.26% |
20.927 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC31
|
-3.13% |
60.072 |
58.189 |
0.006 |
-3.46% |
0.006 |
|
SingleSource/Benchmarks/Shootout/Shootout-lists
Profile
|
-3.13% |
11.317 |
10.962 |
0.012 |
-3.09% |
0.012 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1BigLoopWithReductionTC1
|
-3.13% |
20.024 |
19.398 |
0.002 |
-3.13% |
0.002 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_FLOYD_DITHER/256
|
-3.12% |
1786.593 |
1730.763 |
8.328 |
-0.16% |
8.328 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_PIC_1D_LAMBDA/5001
|
-3.12% |
346.555 |
335.752 |
2.822 |
-4.87% |
2.822 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchVecWithRuntimeChecks4PointersDBeforeA/1000
|
-3.09% |
5020476.302 |
4865574.917 |
205.225 |
-3.07% |
205.225 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC127
|
-3.08% |
3082.251 |
2987.339 |
21.955 |
-4.52% |
21.955 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC128
|
-3.05% |
2930.927 |
2841.632 |
20.725 |
-4.46% |
20.725 |
|
MultiSource/Benchmarks/TSVC/NodeSplitting-dbl/NodeSplitting-dbl
Profile
|
-3.01% |
26.947 |
26.134 |
0.125 |
-1.06% |
0.125 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint16_t>/999
|
-2.85% |
1013.756 |
984.901 |
0.057 |
-2.86% |
0.057 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC32
|
-2.83% |
741.414 |
720.437 |
6.480 |
-4.03% |
6.480 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC64
|
-2.81% |
111.389 |
108.255 |
0.008 |
-2.81% |
0.008 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<31, GreaterThanZero, Last>
|
-2.78% |
8332.157 |
8100.185 |
13.132 |
-2.36% |
13.132 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC1
|
-2.78% |
22.528 |
21.901 |
0.001 |
-2.78% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC1
|
-2.78% |
22.527 |
21.900 |
0.001 |
-2.77% |
0.001 |
|
MultiSource/Benchmarks/FreeBench/mason/mason
Profile
|
-2.78% |
0.553 |
0.537 |
0.001 |
-2.84% |
0.001 |
|
MultiSource/Benchmarks/sim/sim
Profile
|
-2.70% |
9.700 |
9.438 |
0.032 |
-2.71% |
0.032 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C/CoMD/CoMD
Profile
|
-2.68% |
9.907 |
9.641 |
0.007 |
-2.61% |
0.007 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC32
|
-2.68% |
31.289 |
30.450 |
0.015 |
-2.67% |
0.015 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, LessThanZero, None>
|
-2.67% |
37511.074 |
36508.635 |
21.388 |
-2.84% |
21.388 |
|
MultiSource/Applications/sgefa/sgefa
Profile
|
-2.62% |
0.580 |
0.565 |
0.002 |
-1.55% |
0.002 |
|
MultiSource/Benchmarks/mafft/pairlocalalign
Profile
|
-2.62% |
94.098 |
91.634 |
0.377 |
-2.58% |
0.377 |
|
SingleSource/Benchmarks/Misc-C++/oopack_v1p8
Profile
|
-2.61% |
0.480 |
0.467 |
0.000 |
-9.98% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC63
|
-2.60% |
120.150 |
117.021 |
0.004 |
-2.60% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint8_t>/10
|
-2.56% |
48.803 |
47.553 |
0.010 |
2.46% |
0.010 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint8_t_To_uint32_t_
|
-2.55% |
7078.169 |
6897.583 |
1.707 |
-2.54% |
1.707 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint64_t_To_uint8_t_
|
-2.53% |
19750.688 |
19251.415 |
53.298 |
-2.97% |
53.298 |
|
MultiSource/Benchmarks/Rodinia/pathfinder/pathfinder
Profile
|
-2.51% |
1.257 |
1.226 |
0.007 |
-2.53% |
0.007 |
|
MultiSource/Benchmarks/FreeBench/fourinarow/fourinarow
Profile
|
-2.50% |
0.650 |
0.634 |
0.001 |
-2.58% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC31
|
-2.44% |
31.253 |
30.491 |
0.007 |
-2.24% |
0.007 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchVecWithRuntimeChecks4PointersDBeforeA/32
|
-2.43% |
166174.483 |
162133.577 |
5.083 |
-2.45% |
5.083 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_only_autovec_int64_t_
|
-2.38% |
1449612.921 |
1415092.182 |
494.289 |
-2.20% |
494.289 |
|
MultiSource/Benchmarks/Olden/health/health
Profile
|
-2.36% |
1.592 |
1.554 |
0.003 |
-2.34% |
0.003 |
|
SingleSource/Benchmarks/Misc/fbench
Profile
|
-2.35% |
5.763 |
5.627 |
0.000 |
-2.32% |
0.000 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<64, GreaterThanZero, Mid>
|
-2.34% |
2734.275 |
2670.162 |
16.159 |
-2.75% |
16.159 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC63
|
-2.34% |
106.996 |
104.497 |
0.001 |
-2.34% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC64
|
-2.32% |
108.258 |
105.744 |
0.006 |
-2.31% |
0.006 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_FLOYD_DITHER/128
|
-2.31% |
437.801 |
427.678 |
2.758 |
-2.68% |
2.758 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC32
|
-2.31% |
49.976 |
48.822 |
0.212 |
-2.46% |
0.212 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint16_t_To_uint32_t_
|
-2.31% |
11310.803 |
11049.761 |
58.714 |
-2.58% |
58.714 |
|
MultiSource/Benchmarks/TSVC/LinearDependence-flt/LinearDependence-flt
Profile
|
-2.31% |
15.224 |
14.872 |
0.070 |
-2.25% |
0.070 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_ENERGY_CALC_LAMBDA/44217
|
-2.30% |
4334.275 |
4234.481 |
16.214 |
-2.08% |
16.214 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<16, GreaterThanZero, First>
|
-2.27% |
8615.298 |
8419.419 |
35.491 |
-0.90% |
35.491 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_FLOYD_DITHER/512
|
-2.24% |
6645.402 |
6496.509 |
10.539 |
-2.24% |
10.539 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C/SimpleMOC/SimpleMOC
Profile
|
-2.23% |
10.444 |
10.211 |
0.020 |
-1.86% |
0.020 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC63
|
-2.22% |
1713.676 |
1675.570 |
6.972 |
-3.54% |
6.972 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_ENERGY_CALC_RAW/5001
|
-2.17% |
435.164 |
425.702 |
1.085 |
-0.71% |
1.085 |
|
SingleSource/Benchmarks/Misc/flops-1
Profile
|
-2.17% |
9.002 |
8.806 |
0.000 |
-2.15% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint32_t_To_uint64_t_
|
-2.11% |
26352.690 |
25795.530 |
25.322 |
-1.85% |
25.322 |
|
SingleSource/Benchmarks/Misc-C++/Large/ray
Profile
|
-2.11% |
12.105 |
11.850 |
0.002 |
-2.08% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC128
|
-2.10% |
119.521 |
117.012 |
0.005 |
-2.10% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC127
|
-2.09% |
120.148 |
117.633 |
0.006 |
-2.09% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC128
|
-2.09% |
119.509 |
117.012 |
0.005 |
-2.10% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC127
|
-2.08% |
120.140 |
117.639 |
0.006 |
-2.09% |
0.006 |
|
MicroBenchmarks/ImageProcessing/Blur/blur.test:BENCHMARK_boxBlurKernel/512
|
-2.07% |
6652.983 |
6515.335 |
22.841 |
-1.49% |
22.841 |
|
External/SPEC/CINT2017rate/531.deepsjeng_r/531.deepsjeng_r
Profile
|
-2.04% |
259.941 |
254.643 |
0.495 |
-2.10% |
0.495 |
|
SingleSource/Benchmarks/Shootout-C++/Shootout-C++-hash2
Profile
|
-2.00% |
9.349 |
9.162 |
0.036 |
-1.86% |
0.036 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC63
|
-1.98% |
1618.523 |
1586.444 |
10.147 |
-3.48% |
10.147 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint32_t>/10
|
-1.97% |
47.246 |
46.315 |
0.008 |
0.01% |
0.008 |
|
SingleSource/Benchmarks/Misc/ReedSolomon
Profile
|
-1.97% |
20.821 |
20.412 |
0.001 |
-1.85% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_EOS_RAW/171
|
-1.88% |
0.873 |
0.856 |
0.001 |
-1.68% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint16_t>/256
|
-1.84% |
272.812 |
267.801 |
0.015 |
-1.85% |
0.015 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopTC16
|
-1.83% |
275.889 |
270.836 |
1.263 |
-1.95% |
1.263 |
|
MultiSource/Benchmarks/Fhourstones-3.1/fhourstones3.1
Profile
|
-1.82% |
3.974 |
3.902 |
0.021 |
-1.76% |
0.021 |
|
MultiSource/Benchmarks/tramp3d-v4/tramp3d-v4
Profile
|
-1.82% |
1.074 |
1.054 |
0.004 |
-2.00% |
0.004 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<16, EqZero, Mid>
|
-1.81% |
8661.582 |
8504.661 |
31.928 |
-1.76% |
31.928 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<16, EqZero, None>
|
-1.79% |
8177.114 |
8031.114 |
29.581 |
-1.79% |
29.581 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<64, EqZero, Mid>
|
-1.78% |
2739.187 |
2690.413 |
12.559 |
-1.96% |
12.559 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_INT_PREDICT_LAMBDA/171
|
-1.77% |
6.923 |
6.800 |
0.006 |
-1.80% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_csa_with_in_loop_arith_novec_int64_t_
|
-1.71% |
1029552.953 |
1011939.155 |
1127.875 |
-1.58% |
1127.875 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint64_t>/51
|
-1.69% |
148.297 |
145.797 |
0.003 |
-1.69% |
0.003 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<32, LessThanZero, Mid>
|
-1.65% |
4570.614 |
4495.263 |
11.800 |
-1.66% |
11.800 |
|
MultiSource/Benchmarks/VersaBench/ecbdes/ecbdes
Profile
|
-1.63% |
5.142 |
5.058 |
0.001 |
-1.59% |
0.001 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<6, LessThanZero, Mid>
|
-1.61% |
23870.239 |
23487.007 |
22.393 |
-0.34% |
22.393 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_nested_cond_load_novec_uint8_t_
|
-1.57% |
504351.791 |
496413.618 |
218.680 |
-1.64% |
218.680 |
|
SingleSource/Benchmarks/Misc/mandel-2
Profile
|
-1.57% |
2.536 |
2.496 |
0.000 |
-1.55% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC128
|
-1.54% |
211.519 |
208.263 |
0.036 |
-1.54% |
0.036 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_EOS_LAMBDA/171
|
-1.50% |
0.870 |
0.857 |
0.001 |
-1.52% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_INT_PREDICT_RAW/171
|
-1.46% |
6.911 |
6.810 |
0.007 |
-1.65% |
0.007 |
|
MultiSource/Benchmarks/Bullet/bullet
Profile
|
-1.43% |
30.402 |
29.968 |
0.097 |
-1.52% |
0.097 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC127
|
-1.41% |
220.285 |
217.181 |
0.076 |
-1.40% |
0.076 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint64_t>/51
|
-1.37% |
229.007 |
225.875 |
0.013 |
-1.37% |
0.013 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<8, LessThanZero, Mid>
|
-1.35% |
19494.554 |
19230.477 |
10.623 |
-1.05% |
10.623 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC63
|
-1.34% |
130.116 |
128.371 |
0.208 |
-1.38% |
0.208 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_ENERGY_CALC_RAW/44217
|
-1.34% |
4331.305 |
4273.239 |
8.460 |
-1.34% |
8.460 |
|
External/SPEC/CINT2017rate/525.x264_r/525.x264_r
Profile
|
-1.34% |
129.153 |
127.426 |
0.330 |
-1.56% |
0.330 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<32, LessThanZero, Last>
|
-1.33% |
6910.131 |
6818.462 |
9.791 |
-0.67% |
9.791 |
|
MultiSource/Benchmarks/MallocBench/cfrac/cfrac
Profile
|
-1.31% |
2.781 |
2.744 |
0.001 |
-1.28% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC127
|
-1.28% |
197.123 |
194.596 |
0.013 |
-1.27% |
0.013 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC128
|
-1.26% |
198.355 |
195.858 |
0.003 |
-1.27% |
0.003 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<32, GreaterThanZero, Mid>
|
-1.25% |
4551.345 |
4494.258 |
5.808 |
-1.34% |
5.808 |
|
External/SPEC/CFP2017rate/511.povray_r/511.povray_r
Profile
|
-1.25% |
33.935 |
33.511 |
0.081 |
-0.82% |
0.081 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<16, LessThanZero, Last>
|
-1.20% |
13142.097 |
12985.028 |
5.080 |
-1.20% |
5.080 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, LessThanZero, Mid>
|
-1.16% |
31882.402 |
31511.278 |
135.555 |
-0.85% |
135.555 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_sinhf_novec_float_
|
-1.16% |
2243.166 |
2217.133 |
0.713 |
-1.10% |
0.713 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, LessThanZero, Mid>
|
-1.15% |
56577.111 |
55925.093 |
105.988 |
-1.07% |
105.988 |
|
SingleSource/Benchmarks/SmallPT/smallpt
Profile
|
-1.15% |
30.048 |
29.704 |
0.002 |
-1.08% |
0.002 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C++/PENNANT/PENNANT
Profile
|
-1.13% |
4.784 |
4.729 |
0.019 |
-1.82% |
0.019 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_sinhf_autovec_float_
|
-1.06% |
2241.559 |
2217.795 |
0.543 |
-1.11% |
0.543 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint8_t>/16
|
-1.06% |
85.377 |
84.474 |
0.001 |
11.81% |
0.001 |