|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint64_t_To_uint32_t_
|
-48.86% |
35255.300 |
18028.210 |
1227.017 |
-48.95% |
1227.017 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint64_t_To_uint16_t_
|
-48.73% |
35734.938 |
18322.426 |
627.060 |
-48.65% |
627.060 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint64_t_To_uint8_t_
|
-48.70% |
37061.196 |
19012.172 |
41.015 |
-48.70% |
41.015 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C/miniGMG/miniGMG
Profile
|
-48.33% |
8.833 |
4.564 |
0.373 |
-50.34% |
0.373 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint16_t_To_uint64_t_
|
-44.07% |
18673.809 |
10443.911 |
3.371 |
-44.08% |
3.371 |
|
MultiSource/Benchmarks/MiBench/automotive-bitcount/automotive-bitcount
Profile
|
-43.40% |
0.178 |
0.101 |
0.003 |
-18.55% |
0.003 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_DIFF_PREDICT_LAMBDA/44217
|
-42.10% |
23298.567 |
13488.931 |
337.854 |
-41.61% |
337.854 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_DIFF_PREDICT_RAW/44217
|
-41.78% |
23219.137 |
13517.143 |
296.201 |
-41.99% |
296.201 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_DIFF_PREDICT_LAMBDA/5001
|
-41.19% |
2570.135 |
1511.466 |
36.709 |
-39.77% |
36.709 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint8_t_To_uint64_t_
|
-41.04% |
17797.286 |
10492.718 |
21.195 |
-41.05% |
21.195 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint64_t_To_uint32_t_
|
-40.56% |
38145.684 |
22674.594 |
63.974 |
-40.57% |
63.974 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_DIFF_PREDICT_RAW/5001
|
-40.51% |
2549.290 |
1516.699 |
42.745 |
-41.09% |
42.745 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint32_t_To_uint64_t_
|
-37.06% |
22635.472 |
14246.844 |
291.820 |
-37.31% |
291.820 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/32
|
-36.69% |
1396.103 |
883.918 |
0.102 |
-36.69% |
0.102 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/64
|
-36.66% |
6181.037 |
3914.829 |
0.661 |
-36.68% |
0.661 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/16
|
-36.63% |
279.456 |
177.092 |
0.014 |
-36.63% |
0.014 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/256
|
-36.17% |
107133.928 |
68384.658 |
6.585 |
-36.18% |
6.585 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIRST_DIFF_LAMBDA/44217
|
-36.12% |
157.878 |
100.851 |
1.102 |
-30.36% |
1.102 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/128
|
-36.10% |
26258.568 |
16779.005 |
10.235 |
-36.13% |
10.235 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint64_t_To_uint8_t_
|
-34.42% |
30294.547 |
19865.891 |
56.878 |
-34.02% |
56.878 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint64_t_To_uint16_t_
|
-34.21% |
28971.213 |
19060.830 |
46.263 |
-34.16% |
46.263 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIRST_DIFF_RAW/44217
|
-32.06% |
149.817 |
101.785 |
0.993 |
-28.57% |
0.993 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_HYDRO_2D_LAMBDA/44217
|
-31.37% |
84378.312 |
57911.012 |
795.878 |
-36.31% |
795.878 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, EqZero, None>
|
-31.23% |
20509.485 |
14104.223 |
0.597 |
-31.24% |
0.597 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_HYDRO_2D_LAMBDA/5001
|
-29.64% |
9105.060 |
6405.919 |
113.021 |
-29.71% |
113.021 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint64_t_To_uint16_t_
|
-28.60% |
25917.742 |
18505.817 |
45.678 |
-28.54% |
45.678 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint32_t_To_uint8_t_
|
-28.13% |
13514.641 |
9713.599 |
31.511 |
-27.88% |
31.511 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_PIC_2D_RAW/5001
|
-27.85% |
1100.935 |
794.377 |
69.297 |
-26.34% |
69.297 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_PIC_2D_LAMBDA/44217
|
-27.82% |
11947.523 |
8624.222 |
75.662 |
-21.33% |
75.662 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC128
|
-27.59% |
1292.552 |
935.936 |
4.731 |
-27.61% |
4.731 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC128
|
-27.14% |
559.663 |
407.745 |
0.028 |
-26.87% |
0.028 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC64
|
-27.01% |
654.139 |
477.462 |
0.092 |
-26.95% |
0.092 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC32
|
-26.93% |
334.734 |
244.587 |
0.170 |
-26.76% |
0.170 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC16
|
-26.51% |
174.888 |
128.525 |
0.176 |
-26.04% |
0.176 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC64
|
-26.01% |
293.598 |
217.228 |
0.079 |
-25.56% |
0.079 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint64_t_To_uint8_t_
|
-24.33% |
27275.120 |
20640.337 |
99.299 |
-24.18% |
99.299 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, EqZero, None>
|
-23.99% |
16025.023 |
12180.820 |
0.563 |
-23.98% |
0.563 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC32
|
-23.89% |
160.321 |
122.021 |
0.081 |
-23.20% |
0.081 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC128
|
-23.05% |
602.670 |
463.763 |
0.035 |
-23.21% |
0.035 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC128
|
-22.94% |
602.656 |
464.414 |
0.009 |
-23.10% |
0.009 |
|
MicroBenchmarks/ImageProcessing/Blur/blur.test:BENCHMARK_boxBlurKernel/1024
|
-22.75% |
30144.127 |
23285.689 |
71.057 |
-22.76% |
71.057 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_PIC_2D_LAMBDA/5001
|
-22.55% |
1203.136 |
931.862 |
27.161 |
-15.71% |
27.161 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC127
|
-22.09% |
614.584 |
478.813 |
0.010 |
-22.17% |
0.010 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC64
|
-22.03% |
312.230 |
243.434 |
0.002 |
-22.35% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint8_t_To_uint32_t_
|
-21.96% |
6624.731 |
5169.702 |
0.658 |
-21.46% |
0.658 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC127
|
-21.89% |
614.593 |
480.029 |
0.042 |
-21.97% |
0.042 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint16_t_To_uint64_t_
|
-21.88% |
13265.720 |
10362.837 |
0.782 |
-21.54% |
0.782 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC64
|
-21.85% |
312.268 |
244.043 |
0.017 |
-22.16% |
0.017 |
|
SingleSource/Benchmarks/Adobe-C++/loop_unroll
Profile
|
-21.73% |
3.095 |
2.422 |
0.002 |
-22.04% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint16_t_To_uint32_t_
|
-21.70% |
7111.438 |
5568.209 |
3.263 |
-21.59% |
3.263 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_only_autovec_uint8_t_
|
-21.36% |
182386.073 |
143434.498 |
25.264 |
-21.34% |
25.264 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIND_FIRST_MIN_LAMBDA/44217
|
-21.31% |
389.460 |
306.464 |
0.319 |
-21.33% |
0.319 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIND_FIRST_MIN_LAMBDA/171
|
-21.27% |
1.501 |
1.181 |
0.000 |
-21.29% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIND_FIRST_MIN_LAMBDA/5001
|
-20.69% |
45.152 |
35.811 |
0.228 |
-20.87% |
0.228 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC16
|
-20.38% |
93.528 |
74.466 |
0.027 |
-19.30% |
0.027 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC63
|
-20.27% |
324.154 |
258.455 |
0.015 |
-20.42% |
0.015 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC32
|
-20.22% |
167.068 |
133.285 |
0.003 |
-20.82% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC127
|
-20.05% |
274.773 |
219.673 |
0.299 |
-20.25% |
0.299 |
|
MultiSource/Benchmarks/Trimaran/enc-pc1/enc-pc1
Profile
|
-19.92% |
1.130 |
0.905 |
0.000 |
-18.09% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC63
|
-19.88% |
324.140 |
259.701 |
0.014 |
-20.04% |
0.014 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC16
|
-19.87% |
97.607 |
78.216 |
0.001 |
-18.30% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC127
|
-19.86% |
642.016 |
514.488 |
0.119 |
-19.67% |
0.119 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC128
|
-19.86% |
273.753 |
219.384 |
1.745 |
-20.15% |
1.745 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC32
|
-19.85% |
167.066 |
133.909 |
0.001 |
-20.45% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIRST_SUM_RAW/44217
|
-19.61% |
168.845 |
135.735 |
0.470 |
-18.40% |
0.470 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC63
|
-19.43% |
149.563 |
120.506 |
4.514 |
-19.62% |
4.514 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint32_t_To_uint8_t_
|
-19.39% |
13904.962 |
11208.421 |
63.240 |
-19.37% |
63.240 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_PIC_1D_LAMBDA/44217
|
-19.31% |
13582.457 |
10959.808 |
41.329 |
-18.60% |
41.329 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC64
|
-19.08% |
148.752 |
120.377 |
3.608 |
-19.01% |
3.608 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint16_t_To_uint8_t_
|
-19.04% |
3815.998 |
3089.539 |
0.152 |
-19.08% |
0.152 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_VOL3D_CALC_RAW/2
|
-18.80% |
8.757 |
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 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIRST_SUM_LAMBDA/44217
|
-18.58% |
166.035 |
135.189 |
0.262 |
-19.09% |
0.262 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint64_t_To_uint32_t_
|
-18.47% |
27108.870 |
22101.810 |
35.445 |
-18.30% |
35.445 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint32_t_To_uint16_t_
|
-18.42% |
13796.574 |
11255.054 |
9.391 |
-18.48% |
9.391 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_with_cond_arith_novec_uint8_t_
|
-17.89% |
746208.375 |
612708.331 |
287.932 |
-17.84% |
287.932 |
|
MultiSource/Benchmarks/MiBench/security-rijndael/security-rijndael
Profile
|
-17.45% |
0.335 |
0.277 |
0.000 |
-17.25% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_with_cond_arith_novec_int32_t_
|
-17.37% |
740096.793 |
611515.408 |
817.780 |
-17.38% |
817.780 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC4
|
-17.35% |
17.519 |
14.480 |
0.011 |
-17.35% |
0.011 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC31
|
-17.13% |
178.955 |
148.296 |
0.008 |
-17.42% |
0.008 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC128
|
-17.08% |
569.490 |
472.208 |
0.019 |
-17.24% |
0.019 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC64
|
-16.76% |
296.587 |
246.869 |
0.017 |
-17.08% |
0.017 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC16
|
-16.55% |
94.480 |
78.843 |
0.004 |
-17.65% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC31
|
-16.46% |
179.016 |
149.557 |
0.003 |
-16.72% |
0.003 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_VOL3D_CALC_LAMBDA/0
|
-16.40% |
1267.873 |
1059.956 |
1.835 |
-16.38% |
1.835 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_VOL3D_CALC_RAW/0
|
-16.30% |
1268.353 |
1061.627 |
1.397 |
-16.09% |
1.397 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint8_t_To_uint64_t_
|
-16.26% |
13034.139 |
10914.142 |
8.509 |
-16.46% |
8.509 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC32
|
-16.20% |
160.183 |
134.227 |
0.012 |
-16.83% |
0.012 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_VOL3D_CALC_RAW/1
|
-16.09% |
260.167 |
218.296 |
0.136 |
-16.08% |
0.136 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_VOL3D_CALC_LAMBDA/1
|
-16.06% |
260.086 |
218.320 |
0.040 |
-16.09% |
0.040 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_HYDRO_1D_LAMBDA/171
|
-16.06% |
0.443 |
0.372 |
0.000 |
-15.87% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC32
|
-15.99% |
85.330 |
71.685 |
2.175 |
-15.99% |
2.175 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_HYDRO_1D_RAW/171
|
-15.86% |
0.442 |
0.372 |
0.000 |
-15.83% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint16_t_To_uint32_t_
|
-15.66% |
7462.164 |
6293.927 |
0.977 |
-15.66% |
0.977 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint32_t_To_uint8_t_
|
-15.43% |
10631.770 |
8990.857 |
32.167 |
-15.14% |
32.167 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_no_runtime_checks_needed<16, int>
|
-15.38% |
24.402 |
20.649 |
0.001 |
-15.39% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC31
|
-15.38% |
86.300 |
73.029 |
1.560 |
-15.20% |
1.560 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, EqZero, First>
|
-15.38% |
16666.714 |
14103.735 |
0.421 |
-15.40% |
0.421 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, EqZero, Mid>
|
-15.38% |
16666.983 |
14104.287 |
0.455 |
-15.37% |
0.455 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, EqZero, Last>
|
-15.36% |
16670.418 |
14109.292 |
0.309 |
-15.35% |
0.309 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC16
|
-15.35% |
91.995 |
77.870 |
0.028 |
-16.38% |
0.028 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint32_t_To_uint16_t_
|
-15.03% |
9867.360 |
8384.262 |
532.019 |
-15.35% |
532.019 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC127
|
-14.79% |
605.208 |
515.724 |
0.143 |
-14.86% |
0.143 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_DISC_ORD_LAMBDA/44217
|
-14.68% |
13298.880 |
11347.087 |
67.956 |
-19.26% |
67.956 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC128
|
-14.47% |
1102.067 |
942.624 |
0.009 |
-14.56% |
0.009 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC127
|
-14.46% |
1094.621 |
936.336 |
0.057 |
-14.51% |
0.057 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint8_t_To_uint16_t_
|
-14.26% |
3756.366 |
3220.629 |
7.490 |
-14.27% |
7.490 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC64
|
-14.16% |
561.313 |
481.858 |
0.028 |
-14.31% |
0.028 |
|
SingleSource/Benchmarks/Misc/salsa20
Profile
|
-14.14% |
15.386 |
13.211 |
0.000 |
-14.12% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC63
|
-14.13% |
553.838 |
475.605 |
0.013 |
-14.27% |
0.013 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC4
|
-14.06% |
112.641 |
96.799 |
0.239 |
-14.40% |
0.239 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_INT_PREDICT_RAW/5001
|
-14.01% |
1036.614 |
891.358 |
10.201 |
-2.42% |
10.201 |
|
MicroBenchmarks/ImageProcessing/Dilate/Dilate.test:BENCHMARK_DILATE/1024
|
-13.95% |
7338.539 |
6315.049 |
233.978 |
-11.19% |
233.978 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint64_t_To_uint8_t_
|
-13.93% |
22187.678 |
19095.917 |
104.898 |
-13.39% |
104.898 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC7
|
-13.86% |
51.935 |
44.737 |
0.003 |
-13.86% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC2
|
-13.86% |
51.937 |
44.739 |
0.002 |
-13.85% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC1
|
-13.86% |
51.937 |
44.740 |
0.004 |
-13.85% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC8
|
-13.86% |
51.935 |
44.738 |
0.005 |
-13.86% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC4
|
-13.86% |
51.934 |
44.738 |
0.001 |
-13.86% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC3
|
-13.85% |
51.933 |
44.741 |
0.002 |
-13.85% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC63
|
-13.78% |
375.977 |
324.174 |
0.031 |
-13.42% |
0.031 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_with_cond_arith_novec_int64_t_
|
-13.76% |
790685.703 |
681883.438 |
584.817 |
-13.47% |
584.817 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, EqZero, Mid>
|
-13.62% |
14102.635 |
12181.753 |
0.818 |
-13.62% |
0.818 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, EqZero, First>
|
-13.62% |
14103.054 |
12182.221 |
0.123 |
-13.62% |
0.123 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, EqZero, Last>
|
-13.61% |
14102.365 |
12182.407 |
0.151 |
-13.63% |
0.151 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC8
|
-13.61% |
57.581 |
49.743 |
0.001 |
-15.35% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_with_cond_arith_autovec_int64_t_
|
-13.56% |
789147.825 |
682104.082 |
1661.169 |
-13.83% |
1661.169 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint32_t_To_uint8_t_
|
-13.56% |
11062.107 |
9562.004 |
55.776 |
-14.08% |
55.776 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC32
|
-13.55% |
290.965 |
251.548 |
0.011 |
-13.85% |
0.011 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC8
|
-13.53% |
23.150 |
20.017 |
0.003 |
-13.54% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC31
|
-13.46% |
283.454 |
245.292 |
0.009 |
-13.66% |
0.009 |
|
External/SPEC/CFP2017rate/508.namd_r/508.namd_r
Profile
|
-13.42% |
223.220 |
193.271 |
0.098 |
-13.56% |
0.098 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint32_t_To_uint16_t_
|
-13.30% |
12783.511 |
11083.391 |
16.618 |
-13.66% |
16.618 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC8
|
-13.15% |
23.775 |
20.649 |
0.001 |
-13.16% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC128
|
-13.08% |
81.345 |
70.704 |
0.003 |
-13.08% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC16
|
-13.03% |
51.936 |
45.170 |
0.388 |
-13.04% |
0.388 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_INT_PREDICT_RAW/44217
|
-12.97% |
9143.957 |
7957.960 |
115.246 |
-12.06% |
115.246 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint8_t_To_uint16_t_
|
-12.94% |
4541.578 |
3953.709 |
0.491 |
-12.95% |
0.491 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC8
|
-12.91% |
58.194 |
50.683 |
0.003 |
-14.75% |
0.003 |
|
SingleSource/Benchmarks/Shootout-C++/Shootout-C++-matrix
Profile
|
-12.74% |
2.509 |
2.190 |
0.000 |
-12.71% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC63
|
-12.52% |
332.271 |
290.680 |
0.005 |
-12.66% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC16
|
-12.45% |
155.808 |
136.408 |
0.006 |
-13.10% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint16_t_To_uint8_t_
|
-12.42% |
4743.998 |
4154.865 |
0.317 |
-12.40% |
0.317 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC15
|
-12.36% |
106.376 |
93.232 |
0.003 |
-12.87% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC15
|
-12.23% |
148.286 |
130.147 |
0.015 |
-12.54% |
0.015 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC8
|
-11.83% |
58.192 |
51.310 |
0.002 |
-13.69% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC2
|
-11.77% |
21.275 |
18.772 |
0.001 |
-11.77% |
0.001 |
|
MicroBenchmarks/ImageProcessing/Dilate/Dilate.test:BENCHMARK_DILATE/128
|
-11.66% |
221.856 |
195.983 |
5.298 |
-14.03% |
5.298 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC16
|
-11.45% |
33.164 |
29.366 |
0.020 |
-11.45% |
0.020 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC15
|
-11.45% |
51.937 |
45.992 |
0.001 |
-11.45% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC15
|
-11.18% |
106.379 |
94.489 |
0.002 |
-11.70% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint32_t_To_uint64_t_
|
-11.17% |
17106.518 |
15194.984 |
200.923 |
-11.64% |
200.923 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC4
|
-11.11% |
22.526 |
20.023 |
0.001 |
-11.11% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC4
|
-11.11% |
22.525 |
20.022 |
0.002 |
-11.12% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC3
|
-11.10% |
22.525 |
20.024 |
0.000 |
-11.11% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint8_t>/51
|
-10.82% |
123.645 |
110.263 |
0.306 |
19.20% |
0.306 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC8
|
-10.64% |
88.223 |
78.837 |
0.005 |
-11.82% |
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
|
-10.60% |
0.384 |
0.343 |
0.000 |
-6.33% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC4
|
-10.53% |
23.777 |
21.274 |
0.001 |
-10.54% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC64
|
-10.47% |
53.814 |
48.181 |
0.002 |
-10.47% |
0.002 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/16
|
-10.19% |
115.465 |
103.704 |
0.025 |
-10.19% |
0.025 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint8_t_To_uint16_t_
|
-10.14% |
5848.923 |
5255.731 |
22.257 |
-10.16% |
22.257 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC7
|
-10.09% |
80.722 |
72.578 |
0.005 |
-10.74% |
0.005 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/64
|
-10.05% |
1913.693 |
1721.421 |
0.901 |
-10.03% |
0.901 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/256
|
-9.97% |
31454.203 |
28317.352 |
7.628 |
-9.96% |
7.628 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/32
|
-9.97% |
472.945 |
425.791 |
0.020 |
-9.98% |
0.020 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_only_autovec_int64_t_
|
-9.95% |
333746.265 |
300547.807 |
564.057 |
-9.82% |
564.057 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/128
|
-9.76% |
7914.754 |
7141.999 |
1.376 |
-9.79% |
1.376 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC8
|
-9.76% |
25.654 |
23.151 |
0.002 |
-9.77% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC8
|
-9.75% |
25.653 |
23.151 |
0.001 |
-9.76% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_BAND_LIN_EQ_LAMBDA/44217
|
-9.63% |
175.234 |
158.365 |
3.950 |
-1.99% |
3.950 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC7
|
-9.62% |
32.540 |
29.409 |
0.001 |
-9.62% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC1
|
-9.52% |
13.141 |
11.889 |
0.001 |
-0.00% |
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% |
26.280 |
23.778 |
0.001 |
-9.53% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC32
|
-9.44% |
53.187 |
48.169 |
0.007 |
-9.45% |
0.007 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_INT_PREDICT_LAMBDA/44217
|
-9.29% |
8862.644 |
8039.227 |
69.817 |
-3.58% |
69.817 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC127
|
-9.26% |
101.372 |
91.980 |
0.004 |
-9.72% |
0.004 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_DEL_DOT_VEC_2D_LAMBDA/1
|
-9.20% |
287.196 |
260.762 |
0.034 |
-9.18% |
0.034 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_DEL_DOT_VEC_2D_RAW/1
|
-9.20% |
287.091 |
260.685 |
0.049 |
-9.17% |
0.049 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC31
|
-9.13% |
195.854 |
177.974 |
0.022 |
-9.41% |
0.022 |
|
MultiSource/Benchmarks/FreeBench/pifft/pifft
Profile
|
-9.12% |
0.360 |
0.327 |
0.000 |
-8.74% |
0.000 |
|
SingleSource/Benchmarks/Stanford/Puzzle
Profile
|
-8.92% |
0.248 |
0.226 |
0.005 |
-6.53% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC7
|
-8.88% |
28.156 |
25.655 |
0.002 |
-8.90% |
0.002 |
|
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/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint16_t_To_uint8_t_
|
-8.55% |
6812.674 |
6230.224 |
24.577 |
-8.59% |
24.577 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC8
|
-8.50% |
29.408 |
26.907 |
0.000 |
-8.51% |
0.000 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_runtime_checks_fail<4, int>
|
-8.49% |
16.754 |
15.330 |
0.000 |
-3.63% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC64
|
-8.06% |
93.237 |
85.720 |
0.003 |
-8.07% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC4
|
-8.04% |
54.438 |
50.060 |
0.002 |
-10.07% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint16_t_To_uint64_t_
|
-7.98% |
20329.875 |
18707.024 |
31.078 |
-7.13% |
31.078 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint8_t_To_uint32_t_
|
-7.91% |
12757.745 |
11748.875 |
27.538 |
-8.06% |
27.538 |
|
MultiSource/Applications/lambda-0.1.3/lambda
Profile
|
-7.88% |
15.973 |
14.714 |
0.006 |
-7.28% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC16
|
-7.84% |
31.911 |
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:benchForIC1VW4BigLoopWithReductionTC4
|
-7.82% |
40.048 |
36.918 |
0.002 |
-10.61% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC32
|
-7.81% |
40.046 |
36.917 |
0.002 |
-7.82% |
0.002 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_HYDRO_2D_LAMBDA/171
|
-7.76% |
88.995 |
82.090 |
0.639 |
-7.41% |
0.639 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_DEL_DOT_VEC_2D_LAMBDA/0
|
-7.74% |
1799.693 |
1660.392 |
3.560 |
-7.34% |
3.560 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC15
|
-7.69% |
32.538 |
30.035 |
0.001 |
-7.70% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC15
|
-7.69% |
32.537 |
30.035 |
0.001 |
-7.69% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_DEL_DOT_VEC_2D_RAW/0
|
-7.68% |
1798.008 |
1659.882 |
5.516 |
-7.83% |
5.516 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_PRESSURE_CALC_LAMBDA/5001
|
-7.64% |
44.883 |
41.452 |
0.180 |
-5.74% |
0.180 |
|
MultiSource/Benchmarks/VersaBench/beamformer/beamformer
Profile
|
-7.64% |
5.202 |
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 |
|
SingleSource/Benchmarks/Misc/richards_benchmark
Profile
|
-7.53% |
2.201 |
2.036 |
0.001 |
4.21% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_DIFF_PREDICT_LAMBDA/171
|
-7.53% |
12.010 |
11.106 |
0.016 |
-7.34% |
0.016 |
|
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/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC2
|
-7.32% |
16.896 |
15.658 |
0.132 |
0.04% |
0.132 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint16_t_To_uint64_t_
|
-7.29% |
25074.366 |
23246.667 |
46.876 |
-6.96% |
46.876 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_DIFF_PREDICT_RAW/171
|
-7.28% |
11.982 |
11.110 |
0.046 |
-6.89% |
0.046 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC128
|
-7.21% |
173.321 |
160.817 |
0.006 |
-7.22% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint8_t>/127
|
-7.21% |
138.924 |
128.904 |
0.005 |
-7.21% |
0.005 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIND_FIRST_MIN_RAW/171
|
-7.20% |
1.497 |
1.389 |
0.000 |
-7.19% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_HYDRO_2D_RAW/171
|
-7.16% |
88.867 |
82.508 |
0.291 |
-6.90% |
0.291 |
|
SingleSource/Benchmarks/Misc/oourafft
Profile
|
-7.10% |
15.457 |
14.361 |
0.070 |
-4.85% |
0.070 |
|
SingleSource/Benchmarks/Misc/pi
Profile
|
-7.03% |
1.782 |
1.657 |
0.000 |
-7.02% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC15
|
-6.95% |
45.055 |
41.923 |
0.024 |
-6.95% |
0.024 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC8
|
-6.93% |
26.220 |
24.402 |
0.001 |
-9.33% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC15
|
-6.89% |
54.439 |
50.686 |
0.003 |
-6.90% |
0.003 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_runtime_checks_pass<4, int>
|
-6.85% |
16.457 |
15.329 |
0.002 |
-8.25% |
0.002 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C++/miniFE/miniFE
Profile
|
-6.78% |
16.035 |
14.948 |
0.074 |
-6.39% |
0.074 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC7
|
-6.77% |
347.713 |
324.189 |
0.515 |
-8.60% |
0.515 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC31
|
-6.73% |
74.465 |
69.451 |
0.006 |
-6.73% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC3
|
-6.66% |
46.926 |
43.800 |
0.003 |
-7.90% |
0.003 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_BAND_LIN_EQ_RAW/5001
|
-6.62% |
21.428 |
20.009 |
0.174 |
-2.97% |
0.174 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC63
|
-6.54% |
114.504 |
107.015 |
0.211 |
-6.55% |
0.211 |
|
SingleSource/Benchmarks/Misc/flops-6
Profile
|
-6.52% |
1.312 |
1.226 |
0.001 |
-6.55% |
0.001 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_xor_runtime_checks_pass<16, int>
|
-6.52% |
28.782 |
26.905 |
0.001 |
-6.52% |
0.001 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_xor_runtime_checks_fail<16, int>
|
-6.51% |
28.783 |
26.908 |
0.001 |
-6.51% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint64_t_To_uint16_t_
|
-6.45% |
19345.108 |
18097.262 |
469.630 |
-4.67% |
469.630 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_DISC_ORD_RAW/5001
|
-6.42% |
647.649 |
606.095 |
14.776 |
-8.82% |
14.776 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_only_autovec_int32_t_
|
-6.41% |
180977.392 |
169377.059 |
525.958 |
-6.48% |
525.958 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC127
|
-6.40% |
194.601 |
182.142 |
0.343 |
-6.41% |
0.343 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC15
|
-6.35% |
39.421 |
36.917 |
0.010 |
-6.35% |
0.010 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint16_t>/127
|
-6.30% |
138.913 |
130.158 |
0.001 |
-6.30% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC7
|
-6.25% |
70.081 |
65.702 |
0.001 |
-7.09% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC4
|
-6.25% |
40.046 |
37.544 |
0.002 |
-9.09% |
0.002 |
|
SingleSource/Benchmarks/Misc-C++/Large/sphereflake
Profile
|
-6.22% |
20.012 |
18.768 |
0.004 |
-6.17% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC127
|
-6.21% |
2384.349 |
2236.362 |
8.883 |
-7.84% |
8.883 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC16
|
-6.14% |
40.670 |
38.171 |
0.002 |
-6.15% |
0.002 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIND_FIRST_MIN_RAW/5001
|
-6.14% |
45.384 |
42.596 |
0.078 |
-6.05% |
0.078 |
|
MultiSource/Benchmarks/MiBench/telecomm-gsm/telecomm-gsm
Profile
|
-6.00% |
0.663 |
0.624 |
0.000 |
-5.97% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint8_t>/65
|
-5.93% |
95.117 |
89.481 |
0.004 |
-5.92% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC63
|
-5.92% |
73.830 |
69.458 |
0.002 |
-6.42% |
0.002 |
|
External/SPEC/CFP2017rate/538.imagick_r/538.imagick_r
Profile
|
-5.88% |
292.027 |
274.850 |
0.195 |
-5.90% |
0.195 |
|
MultiSource/Benchmarks/Rodinia/hotspot/hotspot
Profile
|
-5.87% |
2.038 |
1.918 |
0.003 |
-5.80% |
0.003 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_BAND_LIN_EQ_LAMBDA/5001
|
-5.84% |
21.326 |
20.080 |
0.147 |
-3.46% |
0.147 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC3
|
-5.83% |
21.274 |
20.033 |
0.055 |
0.04% |
0.055 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC16
|
-5.75% |
31.932 |
30.095 |
0.051 |
-3.82% |
0.051 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC16
|
-5.66% |
33.162 |
31.287 |
0.001 |
-5.66% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC32
|
-5.64% |
44.425 |
41.920 |
0.004 |
-5.64% |
0.004 |
|
MultiSource/Benchmarks/McCat/12-IOtest/iotest
Profile
|
-5.64% |
1.819 |
1.717 |
0.032 |
-5.92% |
0.032 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC32
|
-5.63% |
44.426 |
41.924 |
0.003 |
-5.64% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1LoopWithReductionTC4
|
-5.61% |
15.247 |
14.391 |
0.001 |
2.26% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint32_t_To_uint64_t_
|
-5.61% |
21497.512 |
20291.587 |
24.646 |
-5.40% |
24.646 |
|
MultiSource/Benchmarks/SciMark2-C/scimark2
Profile
|
-5.57% |
107.707 |
101.703 |
0.081 |
-5.51% |
0.081 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC31
|
-5.56% |
45.052 |
42.547 |
0.003 |
-5.59% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC128
|
-5.56% |
68.207 |
64.416 |
0.011 |
-6.38% |
0.011 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC31
|
-5.56% |
242.502 |
229.022 |
0.019 |
-5.06% |
0.019 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC31
|
-5.56% |
45.051 |
42.548 |
0.003 |
-5.56% |
0.003 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_PIC_2D_LAMBDA/171
|
-5.55% |
13.515 |
12.764 |
0.063 |
-5.44% |
0.063 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC127
|
-5.52% |
68.201 |
64.437 |
0.014 |
-5.64% |
0.014 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint8_t_To_uint16_t_
|
-5.48% |
3626.353 |
3427.696 |
34.366 |
-5.66% |
34.366 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint32_t>/127
|
-5.45% |
137.654 |
130.151 |
0.007 |
-5.88% |
0.007 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint32_t>/999
|
-5.38% |
696.450 |
658.997 |
0.023 |
-5.39% |
0.023 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC1
|
-5.26% |
11.889 |
11.263 |
0.002 |
0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC1
|
-5.26% |
11.888 |
11.263 |
0.001 |
-0.01% |
0.001 |
|
MultiSource/Applications/siod/siod
Profile
|
-5.24% |
8.322 |
7.886 |
0.016 |
-0.93% |
0.016 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIND_FIRST_MIN_RAW/44217
|
-5.24% |
389.614 |
369.213 |
0.523 |
-5.23% |
0.523 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint32_t>/999
|
-5.22% |
1364.996 |
1293.683 |
0.069 |
-5.23% |
0.069 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC32
|
-5.20% |
61.323 |
58.136 |
0.028 |
-5.19% |
0.028 |
|
MultiSource/Applications/aha/aha
Profile
|
-5.17% |
5.004 |
4.745 |
0.003 |
0.17% |
0.003 |
|
SingleSource/Benchmarks/Polybench/stencils/jacobi-2d/jacobi-2d
Profile
|
-5.13% |
31.941 |
30.301 |
0.101 |
-5.97% |
0.101 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint8_t>/28
|
-5.13% |
80.674 |
76.534 |
0.610 |
13.23% |
0.610 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC2
|
-5.08% |
36.915 |
35.040 |
0.002 |
-8.20% |
0.002 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_PIC_2D_RAW/171
|
-5.03% |
13.522 |
12.841 |
0.052 |
-5.15% |
0.052 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC1
|
-4.97% |
88.025 |
83.649 |
0.269 |
-6.00% |
0.269 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC4
|
-4.88% |
25.656 |
24.403 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_ENERGY_CALC_LAMBDA/5001
|
-4.80% |
441.350 |
420.144 |
7.581 |
-4.09% |
7.581 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint32_t>/256
|
-4.80% |
364.164 |
346.672 |
0.007 |
-4.80% |
0.007 |
|
External/SPEC/CINT2017rate/531.deepsjeng_r/531.deepsjeng_r
Profile
|
-4.74% |
267.314 |
254.643 |
0.495 |
-2.10% |
0.495 |
|
SingleSource/Benchmarks/Misc/revertBits
Profile
|
-4.67% |
0.641 |
0.611 |
0.000 |
-4.68% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC15
|
-4.65% |
127.638 |
121.696 |
0.003 |
-5.12% |
0.003 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_runtime_checks_pass<16, int>
|
-4.60% |
54.438 |
51.933 |
0.002 |
-4.60% |
0.002 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_runtime_checks_fail<16, int>
|
-4.60% |
54.435 |
51.931 |
0.004 |
-4.61% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint16_t>/65
|
-4.60% |
95.108 |
90.733 |
0.001 |
-4.61% |
0.001 |
|
External/SPEC/CINT2017rate/500.perlbench_r/500.perlbench_r
Profile
|
-4.57% |
153.168 |
146.163 |
0.544 |
-0.37% |
0.544 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC2
|
-4.55% |
13.765 |
13.140 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC4
|
-4.47% |
358.146 |
342.127 |
2.658 |
-2.07% |
2.658 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC7
|
-4.47% |
70.083 |
66.951 |
0.003 |
-5.33% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint8_t_To_uint64_t_
|
-4.46% |
23539.698 |
22488.729 |
27.676 |
-4.24% |
27.676 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC31
|
-4.46% |
70.079 |
66.955 |
0.002 |
-4.46% |
0.002 |
|
MicroBenchmarks/ImageProcessing/Blur/blur.test:BENCHMARK_boxBlurKernel/128
|
-4.37% |
437.345 |
418.219 |
7.160 |
-3.70% |
7.160 |
|
MultiSource/Applications/JM/lencod/lencod
Profile
|
-4.33% |
33.053 |
31.622 |
0.014 |
-2.82% |
0.014 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint32_t_To_uint16_t_
|
-4.32% |
9882.214 |
9455.125 |
48.053 |
-4.30% |
48.053 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_PRESSURE_CALC_RAW/44217
|
-4.27% |
500.746 |
479.373 |
2.258 |
-4.54% |
2.258 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint64_t>/999
|
-4.25% |
1811.441 |
1734.499 |
0.102 |
-4.24% |
0.102 |
|
SingleSource/Benchmarks/Misc/flops-5
Profile
|
-4.23% |
2.022 |
1.936 |
0.001 |
-4.19% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_ENERGY_CALC_RAW/171
|
-4.18% |
14.217 |
13.624 |
0.019 |
-4.33% |
0.019 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint64_t>/999
|
-4.17% |
3595.458 |
3445.643 |
0.095 |
-4.15% |
0.095 |
|
MultiSource/Benchmarks/Rodinia/pathfinder/pathfinder
Profile
|
-4.15% |
1.279 |
1.226 |
0.007 |
-2.53% |
0.007 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_ENERGY_CALC_LAMBDA/171
|
-4.14% |
14.214 |
13.625 |
0.018 |
-4.37% |
0.018 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint64_t>/256
|
-4.08% |
935.558 |
897.361 |
0.093 |
-4.09% |
0.093 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC31
|
-4.03% |
61.943 |
59.445 |
0.000 |
-4.04% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC3
|
-4.01% |
15.644 |
15.017 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_only_autovec_uint8_t_
|
-3.96% |
96166.597 |
92353.971 |
17.751 |
-3.96% |
17.751 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC32
|
-3.96% |
63.194 |
60.694 |
0.004 |
-3.96% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint32_t>/256
|
-3.95% |
221.508 |
212.760 |
0.013 |
-3.95% |
0.013 |
|
External/SPEC/CFP2017rate/519.lbm_r/519.lbm_r
Profile
|
-3.83% |
199.905 |
192.251 |
1.382 |
-4.20% |
1.382 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC31
|
-3.79% |
94.344 |
90.766 |
0.220 |
-3.29% |
0.220 |
|
MultiSource/Benchmarks/MiBench/consumer-typeset/consumer-typeset
Profile
|
-3.71% |
0.742 |
0.714 |
0.004 |
-0.46% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC2
|
-3.70% |
16.895 |
16.270 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<64, GreaterThanZero, None>
|
-3.70% |
3050.979 |
2938.105 |
6.938 |
0.83% |
6.938 |
|
SingleSource/Benchmarks/Shootout/Shootout-matrix
Profile
|
-3.70% |
3.864 |
3.721 |
0.000 |
-3.69% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC2
|
-3.70% |
16.894 |
16.269 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint64_t_To_uint32_t_
|
-3.65% |
19376.477 |
18668.524 |
47.198 |
-3.23% |
47.198 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint64_t>/256
|
-3.64% |
514.354 |
495.650 |
0.022 |
-3.64% |
0.022 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint16_t_To_uint8_t_
|
-3.63% |
2874.686 |
2770.350 |
23.990 |
-3.75% |
23.990 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC64
|
-3.61% |
69.454 |
66.950 |
0.003 |
-3.61% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC64
|
-3.61% |
69.457 |
66.953 |
0.002 |
-3.61% |
0.002 |
|
SingleSource/Benchmarks/BenchmarkGame/n-body
Profile
|
-3.58% |
2.731 |
2.634 |
0.000 |
21.70% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC63
|
-3.57% |
70.084 |
67.580 |
0.001 |
-3.57% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC63
|
-3.57% |
70.077 |
67.576 |
0.004 |
-3.59% |
0.004 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_FLOYD_DITHER/256
|
-3.53% |
1794.171 |
1730.763 |
8.328 |
-0.16% |
8.328 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint8_t>/16
|
-3.43% |
59.472 |
57.431 |
0.449 |
6.71% |
0.449 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC63
|
-3.42% |
43.175 |
41.699 |
0.041 |
-3.68% |
0.041 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC64
|
-3.35% |
43.177 |
41.730 |
0.018 |
-3.35% |
0.018 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint32_t>/65
|
-3.33% |
93.851 |
90.726 |
0.003 |
-3.98% |
0.003 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_PRESSURE_CALC_LAMBDA/44217
|
-3.28% |
495.751 |
479.487 |
2.813 |
-3.82% |
2.813 |
|
MultiSource/Benchmarks/Olden/health/health
Profile
|
-3.27% |
1.607 |
1.554 |
0.003 |
-2.34% |
0.003 |
|
MultiSource/Benchmarks/nbench/nbench
Profile
|
-3.27% |
6.105 |
5.906 |
0.002 |
-3.61% |
0.002 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_ENERGY_CALC_RAW/5001
|
-3.26% |
440.052 |
425.702 |
1.085 |
-0.71% |
1.085 |
|
MultiSource/Benchmarks/Fhourstones-3.1/fhourstones3.1
Profile
|
-3.19% |
4.030 |
3.902 |
0.021 |
-1.76% |
0.021 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint16_t_To_uint8_t_
|
-3.17% |
4513.055 |
4370.037 |
20.927 |
-3.26% |
20.927 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint16_t>/999
|
-3.16% |
515.006 |
498.733 |
0.018 |
-3.16% |
0.018 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC31
|
-3.14% |
60.074 |
58.189 |
0.006 |
-3.46% |
0.006 |
|
SingleSource/Benchmarks/Shootout/Shootout-lists
Profile
|
-3.13% |
11.316 |
10.962 |
0.012 |
-3.09% |
0.012 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC7
|
-3.12% |
37.542 |
36.370 |
0.076 |
0.20% |
0.076 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1BigLoopWithReductionTC1
|
-3.12% |
20.023 |
19.398 |
0.002 |
-3.13% |
0.002 |
|
MicroBenchmarks/ImageProcessing/Dilate/Dilate.test:BENCHMARK_DILATE/256
|
-3.11% |
1054.152 |
1021.367 |
4.060 |
-4.30% |
4.060 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC127
|
-3.09% |
3082.737 |
2987.339 |
21.955 |
-4.52% |
21.955 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchVecWithRuntimeChecks4PointersDBeforeA/1000
|
-3.09% |
5020941.532 |
4865574.917 |
205.225 |
-3.07% |
205.225 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_PIC_1D_LAMBDA/5001
|
-3.09% |
346.457 |
335.752 |
2.822 |
-4.87% |
2.822 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC128
|
-3.09% |
2932.099 |
2841.632 |
20.725 |
-4.46% |
20.725 |
|
MultiSource/Benchmarks/FreeBench/fourinarow/fourinarow
Profile
|
-3.08% |
0.654 |
0.634 |
0.001 |
-2.58% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1LoopWithReductionTC7
|
-3.03% |
20.649 |
20.023 |
0.000 |
3.20% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_ENERGY_CALC_LAMBDA/44217
|
-3.01% |
4365.741 |
4234.481 |
16.214 |
-2.08% |
16.214 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC8
|
-2.99% |
41.926 |
40.670 |
0.002 |
-0.01% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC32
|
-2.89% |
741.881 |
720.437 |
6.480 |
-4.03% |
6.480 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint16_t>/999
|
-2.84% |
1013.736 |
984.901 |
0.057 |
-2.86% |
0.057 |
|
External/SPEC/CFP2017rate/511.povray_r/511.povray_r
Profile
|
-2.83% |
34.486 |
33.511 |
0.081 |
-0.82% |
0.081 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC64
|
-2.80% |
111.375 |
108.255 |
0.008 |
-2.81% |
0.008 |
|
MultiSource/Benchmarks/FreeBench/mason/mason
Profile
|
-2.79% |
0.553 |
0.537 |
0.001 |
-2.84% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC1
|
-2.78% |
22.527 |
21.900 |
0.001 |
-2.77% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1LoopWithReductionTC8
|
-2.78% |
22.525 |
21.899 |
0.001 |
2.93% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC1
|
-2.78% |
22.526 |
21.901 |
0.001 |
-2.78% |
0.001 |
|
MultiSource/Benchmarks/TSVC/NodeSplitting-dbl/NodeSplitting-dbl
Profile
|
-2.78% |
26.880 |
26.134 |
0.125 |
-1.06% |
0.125 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC32
|
-2.71% |
50.183 |
48.822 |
0.212 |
-2.46% |
0.212 |
|
MultiSource/Applications/ClamAV/clamscan
Profile
|
-2.71% |
0.496 |
0.482 |
0.001 |
-1.42% |
0.001 |
|
SingleSource/Benchmarks/Misc-C++/oopack_v1p8
Profile
|
-2.65% |
0.480 |
0.467 |
0.000 |
-9.98% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC31
|
-2.64% |
891.432 |
867.935 |
4.127 |
-5.35% |
4.127 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC31
|
-2.63% |
23.776 |
23.151 |
0.001 |
-5.13% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC31
|
-2.63% |
23.777 |
23.152 |
0.001 |
-5.13% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC32
|
-2.62% |
23.777 |
23.153 |
0.002 |
-5.13% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC32
|
-2.62% |
23.775 |
23.153 |
0.001 |
-5.12% |
0.001 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C/CoMD/CoMD
Profile
|
-2.60% |
9.899 |
9.641 |
0.007 |
-2.61% |
0.007 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<64, GreaterThanZero, Mid>
|
-2.59% |
2741.160 |
2670.162 |
16.159 |
-2.75% |
16.159 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC63
|
-2.59% |
120.131 |
117.021 |
0.004 |
-2.60% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint64_t_To_uint8_t_
|
-2.58% |
19761.399 |
19251.415 |
53.298 |
-2.97% |
53.298 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint8_t>/10
|
-2.56% |
48.804 |
47.553 |
0.010 |
2.46% |
0.010 |
|
MultiSource/Benchmarks/sim/sim
Profile
|
-2.55% |
9.685 |
9.438 |
0.032 |
-2.71% |
0.032 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC15
|
-2.54% |
532.485 |
518.956 |
1.286 |
-1.22% |
1.286 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint8_t_To_uint32_t_
|
-2.53% |
7076.549 |
6897.583 |
1.707 |
-2.54% |
1.707 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<63, GreaterThanZero, None>
|
-2.51% |
4742.608 |
4623.469 |
5.542 |
-0.10% |
5.542 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchVecWithRuntimeChecks4PointersDBeforeA/32
|
-2.44% |
166192.169 |
162133.577 |
5.083 |
-2.45% |
5.083 |
|
External/SPEC/CFP2017rate/544.nab_r/544.nab_r
Profile
|
-2.40% |
472.028 |
460.686 |
0.118 |
-3.60% |
0.118 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<63, LessThanZero, First>
|
-2.39% |
1641.561 |
1602.259 |
0.330 |
0.01% |
0.330 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint64_t>/10
|
-2.38% |
56.411 |
55.067 |
0.047 |
-0.06% |
0.047 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_only_autovec_int64_t_
|
-2.36% |
1449289.503 |
1415092.182 |
494.289 |
-2.20% |
494.289 |
|
MultiSource/Benchmarks/mafft/pairlocalalign
Profile
|
-2.35% |
93.837 |
91.634 |
0.377 |
-2.58% |
0.377 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC63
|
-2.34% |
107.000 |
104.497 |
0.001 |
-2.34% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint32_t_To_uint64_t_
|
-2.34% |
26412.691 |
25795.530 |
25.322 |
-1.85% |
25.322 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC64
|
-2.32% |
108.252 |
105.744 |
0.006 |
-2.31% |
0.006 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_FLOYD_DITHER/512
|
-2.29% |
6648.488 |
6496.509 |
10.539 |
-2.24% |
10.539 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC63
|
-2.24% |
1714.046 |
1675.570 |
6.972 |
-3.54% |
6.972 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint16_t_To_uint32_t_
|
-2.18% |
11296.010 |
11049.761 |
58.714 |
-2.58% |
58.714 |
|
SingleSource/Benchmarks/Misc/flops-1
Profile
|
-2.17% |
9.002 |
8.806 |
0.000 |
-2.15% |
0.000 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C/SimpleMOC/SimpleMOC
Profile
|
-2.16% |
10.437 |
10.211 |
0.020 |
-1.86% |
0.020 |
|
SingleSource/Benchmarks/Misc-C++/Large/ray
Profile
|
-2.14% |
12.108 |
11.850 |
0.002 |
-2.08% |
0.002 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_FLOYD_DITHER/128
|
-2.13% |
436.987 |
427.678 |
2.758 |
-2.68% |
2.758 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC128
|
-2.09% |
119.515 |
117.012 |
0.005 |
-2.10% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC128
|
-2.09% |
119.515 |
117.012 |
0.005 |
-2.10% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC127
|
-2.08% |
120.130 |
117.633 |
0.006 |
-2.09% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC127
|
-2.08% |
120.137 |
117.639 |
0.006 |
-2.09% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_nested_cond_load_novec_int32_t_
|
-2.01% |
634604.563 |
621824.641 |
614.099 |
-3.62% |
614.099 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC63
|
-2.01% |
1618.915 |
1586.444 |
10.147 |
-3.48% |
10.147 |
|
MicroBenchmarks/ImageProcessing/Dilate/Dilate.test:BENCHMARK_DILATE/512
|
-1.95% |
3546.762 |
3477.619 |
22.869 |
-2.97% |
22.869 |
|
MultiSource/Benchmarks/Fhourstones/fhourstones
Profile
|
-1.89% |
11.010 |
10.801 |
0.036 |
0.21% |
0.036 |
|
MultiSource/Benchmarks/tramp3d-v4/tramp3d-v4
Profile
|
-1.88% |
1.074 |
1.054 |
0.004 |
-2.00% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint16_t>/256
|
-1.84% |
272.809 |
267.801 |
0.015 |
-1.85% |
0.015 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_ENERGY_CALC_RAW/44217
|
-1.83% |
4353.007 |
4273.239 |
8.460 |
-1.34% |
8.460 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC63
|
-1.83% |
130.763 |
128.371 |
0.208 |
-1.38% |
0.208 |
|
External/SPEC/CINT2017rate/525.x264_r/525.x264_r
Profile
|
-1.82% |
129.791 |
127.426 |
0.330 |
-1.56% |
0.330 |
|
MultiSource/Benchmarks/VersaBench/ecbdes/ecbdes
Profile
|
-1.79% |
5.150 |
5.058 |
0.001 |
-1.59% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC15
|
-1.78% |
70.079 |
68.834 |
0.010 |
0.00% |
0.010 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1LoopWithReductionTC15
|
-1.75% |
35.667 |
35.042 |
0.021 |
1.81% |
0.021 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_csa_with_in_loop_arith_novec_int64_t_
|
-1.72% |
1029666.173 |
1011939.155 |
1127.875 |
-1.58% |
1127.875 |
|
SingleSource/Benchmarks/Misc/ReedSolomon
Profile
|
-1.72% |
20.768 |
20.412 |
0.001 |
-1.85% |
0.001 |
|
MicroBenchmarks/Builtins/Int128/Builtins.test:BM_RemainderIntrinsic128UniformDivisor<__int128_t>
|
-1.68% |
66.844 |
65.718 |
0.379 |
-0.77% |
0.379 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint64_t>/51
|
-1.68% |
148.292 |
145.797 |
0.003 |
-1.69% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1LoopWithReductionTC16
|
-1.67% |
37.545 |
36.916 |
0.002 |
1.71% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC31
|
-1.67% |
1498.724 |
1473.666 |
3.502 |
-2.72% |
3.502 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_INT_PREDICT_LAMBDA/171
|
-1.66% |
6.915 |
6.800 |
0.006 |
-1.80% |
0.006 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_INT_PREDICT_RAW/171
|
-1.66% |
6.925 |
6.810 |
0.007 |
-1.65% |
0.007 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_EOS_RAW/171
|
-1.65% |
0.871 |
0.856 |
0.001 |
-1.68% |
0.001 |
|
MicroBenchmarks/Builtins/Int128/Builtins.test:BM_RemainderIntrinsic128SmallDivisor<__uint128_t>
|
-1.63% |
72.453 |
71.272 |
0.036 |
-0.64% |
0.036 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_EOS_LAMBDA/171
|
-1.61% |
0.871 |
0.857 |
0.001 |
-1.52% |
0.001 |
|
SingleSource/Benchmarks/Misc/mandel-2
Profile
|
-1.56% |
2.535 |
2.496 |
0.000 |
-1.55% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint8_t>/10
|
-1.56% |
66.741 |
65.703 |
0.005 |
6.43% |
0.005 |
|
MicroBenchmarks/ImageProcessing/Blur/blur.test:BENCHMARK_boxBlurKernel/512
|
-1.55% |
6617.899 |
6515.335 |
22.841 |
-1.49% |
22.841 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC128
|
-1.53% |
211.489 |
208.263 |
0.036 |
-1.54% |
0.036 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, LessThanZero, None>
|
-1.42% |
37035.009 |
36508.635 |
21.388 |
-2.84% |
21.388 |
|
MultiSource/Benchmarks/Bullet/bullet
Profile
|
-1.42% |
30.399 |
29.968 |
0.097 |
-1.52% |
0.097 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC127
|
-1.40% |
220.276 |
217.181 |
0.076 |
-1.40% |
0.076 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint8_t>/16
|
-1.39% |
68.636 |
67.683 |
0.245 |
10.32% |
0.245 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint64_t>/51
|
-1.37% |
229.015 |
225.875 |
0.013 |
-1.37% |
0.013 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, GreaterThanZero, Last>
|
-1.34% |
35727.462 |
35249.628 |
3.938 |
-0.00% |
3.938 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_nested_cond_load_novec_uint8_t_
|
-1.30% |
502962.579 |
496413.618 |
218.680 |
-1.64% |
218.680 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C++/PENNANT/PENNANT
Profile
|
-1.27% |
4.790 |
4.729 |
0.019 |
-1.82% |
0.019 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC127
|
-1.27% |
197.096 |
194.596 |
0.013 |
-1.27% |
0.013 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_csa_with_cond_arith_novec_int64_t_
|
-1.26% |
745714.087 |
736337.418 |
1360.675 |
-1.12% |
1360.675 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC128
|
-1.26% |
198.352 |
195.858 |
0.003 |
-1.27% |
0.003 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<3, GreaterThanZero, Mid>
|
-1.22% |
37818.785 |
37356.449 |
65.721 |
-0.14% |
65.721 |
|
MicroBenchmarks/LCALS/SubsetBRawLoops/lcalsBRaw.test:BM_INIT3_RAW/44217
|
-1.22% |
392.739 |
387.943 |
1.843 |
-1.95% |
1.843 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<3, LessThanZero, None>
|
-1.20% |
45716.844 |
45166.900 |
79.347 |
-0.15% |
79.347 |
|
SingleSource/Benchmarks/SmallPT/smallpt
Profile
|
-1.13% |
30.044 |
29.704 |
0.002 |
-1.08% |
0.002 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<63, EqZero, Mid>
|
-1.13% |
4116.629 |
4070.285 |
3.432 |
-0.01% |
3.432 |
|
MicroBenchmarks/LCALS/SubsetBRawLoops/lcalsBRaw.test:BM_MULADDSUB_RAW/44217
|
-1.11% |
394.714 |
390.342 |
1.517 |
0.51% |
1.517 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<63, GreaterThanZero, First>
|
-1.11% |
1614.332 |
1596.475 |
0.087 |
-0.40% |
0.087 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_sinhf_novec_float_
|
-1.10% |
2241.744 |
2217.133 |
0.713 |
-1.10% |
0.713 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<32, LessThanZero, Last>
|
-1.08% |
6893.145 |
6818.462 |
9.791 |
-0.67% |
9.791 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<31, EqZero, None>
|
-1.08% |
8049.043 |
7962.023 |
9.421 |
-0.41% |
9.421 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_sinhf_autovec_float_
|
-1.05% |
2241.435 |
2217.795 |
0.543 |
-1.11% |
0.543 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_sinh_autovec_double_
|
-1.04% |
2471.353 |
2445.695 |
9.317 |
-1.21% |
9.317 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<5, LessThanZero, None>
|
-1.04% |
32293.845 |
31959.177 |
40.698 |
-0.40% |
40.698 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_csa_with_cond_arith_autovec_int64_t_
|
-1.02% |
745391.087 |
737792.986 |
673.074 |
-0.96% |
673.074 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC2
|
-1.02% |
169.485 |
167.762 |
0.647 |
-0.07% |
0.647 |
|
SingleSource/Benchmarks/Misc/fbench
Profile
|
-1.01% |
5.685 |
5.627 |
0.000 |
-2.32% |
0.000 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<6, GreaterThanZero, First>
|
-1.00% |
16173.305 |
16011.390 |
0.992 |
0.01% |
0.992 |