|
MultiSource/Benchmarks/Trimaran/enc-md5/enc-md5
Profile
|
-76.67% |
12.643 |
2.950 |
0.000 |
0.01% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_INT_PREDICT_RAW/5001
|
-50.42% |
1902.919 |
943.556 |
253.443 |
-39.18% |
253.443 |
|
SingleSource/Benchmarks/Shootout/Shootout-ary3
Profile
|
-47.19% |
0.985 |
0.520 |
0.001 |
-0.20% |
0.001 |
|
MultiSource/Benchmarks/Ptrdist/yacr2/yacr2
Profile
|
-29.17% |
2.836 |
2.009 |
0.001 |
-0.06% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_with_cond_arith_autovec_int64_t_
|
-27.56% |
1044878.546 |
756928.943 |
1175.242 |
0.15% |
1175.242 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_with_cond_arith_novec_int64_t_
|
-27.47% |
1044463.436 |
757505.768 |
924.311 |
-0.17% |
924.311 |
|
SingleSource/Benchmarks/Adobe-C++/simple_types_constant_folding
Profile
|
-27.42% |
2.366 |
1.718 |
0.001 |
0.02% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_with_cond_arith_autovec_int32_t_
|
-27.13% |
515728.518 |
375822.635 |
559.653 |
-0.48% |
559.653 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_with_cond_arith_novec_int32_t_
|
-26.96% |
515829.116 |
376757.609 |
810.708 |
-0.11% |
810.708 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_with_cond_arith_autovec_uint8_t_
|
-25.22% |
124920.394 |
93412.472 |
58.823 |
-0.12% |
58.823 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_with_cond_arith_novec_uint8_t_
|
-25.21% |
124916.399 |
93430.420 |
69.355 |
-0.10% |
69.355 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_multiply_accumulate_runtime_checks_pass<3, double>
|
-25.00% |
15.017 |
11.262 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_multiply_accumulate_runtime_checks_fail<3, double>
|
-25.00% |
15.016 |
11.262 |
0.001 |
0.00% |
0.001 |
|
SingleSource/Benchmarks/Misc-C++/stepanov_v1p2
Profile
|
-24.95% |
16.330 |
12.255 |
0.000 |
0.00% |
0.000 |
|
MultiSource/Benchmarks/TSVC/Packing-flt/Packing-flt
Profile
|
-23.54% |
33.627 |
25.711 |
0.126 |
-0.74% |
0.126 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_TRIDIAG_ELIM_LAMBDA/171
|
-21.95% |
0.967 |
0.755 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_TRIDIAG_ELIM_RAW/171
|
-21.95% |
0.967 |
0.755 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_xor_no_runtime_checks_needed<4, int>
|
-21.43% |
8.760 |
6.883 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_TRIDIAG_ELIM_LAMBDA/44217
|
-19.85% |
252.442 |
202.343 |
1.028 |
0.47% |
1.028 |
|
MultiSource/Benchmarks/SciMark2-C/scimark2
Profile
|
-19.81% |
166.680 |
133.658 |
0.041 |
0.01% |
0.041 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint32_t_To_uint16_t_
|
-19.51% |
12919.660 |
10398.607 |
232.475 |
-1.63% |
232.475 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint32_t_To_uint16_t_
|
-19.47% |
12911.816 |
10397.902 |
225.705 |
-1.47% |
225.705 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_TRIDIAG_ELIM_RAW/44217
|
-19.32% |
251.350 |
202.789 |
0.730 |
-0.26% |
0.730 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint32_t_To_uint16_t_
|
-19.25% |
12907.981 |
10423.119 |
215.261 |
-1.34% |
215.261 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_GEN_LIN_RECUR_RAW/44217
|
-18.56% |
1300.488 |
1059.071 |
12.737 |
1.46% |
12.737 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_GEN_LIN_RECUR_LAMBDA/5001
|
-18.51% |
87.236 |
71.091 |
5.455 |
-7.12% |
5.455 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint16_t>/28
|
-18.38% |
104.498 |
85.290 |
0.046 |
-0.57% |
0.046 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_TRIDIAG_ELIM_LAMBDA/5001
|
-18.30% |
28.463 |
23.256 |
0.049 |
-0.10% |
0.049 |
|
MultiSource/Benchmarks/TSVC/Packing-dbl/Packing-dbl
Profile
|
-18.04% |
35.572 |
29.155 |
0.177 |
-0.24% |
0.177 |
|
MultiSource/Benchmarks/Olden/em3d/em3d
Profile
|
-17.94% |
18.304 |
15.020 |
0.004 |
0.04% |
0.004 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_TRIDIAG_ELIM_RAW/5001
|
-17.87% |
28.452 |
23.367 |
0.015 |
0.16% |
0.015 |
|
SingleSource/Benchmarks/Shootout/Shootout-random
Profile
|
-17.84% |
7.013 |
5.762 |
0.000 |
-0.01% |
0.000 |
|
SingleSource/Benchmarks/Shootout-C++/Shootout-C++-random
Profile
|
-17.82% |
7.017 |
5.766 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_multiply_accumulate_runtime_checks_pass<2, double>
|
-17.65% |
10.637 |
8.760 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint16_t>/16
|
-17.48% |
66.954 |
55.252 |
0.046 |
-1.22% |
0.046 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint64_t>/10
|
-17.42% |
38.640 |
31.910 |
0.000 |
-6.13% |
0.000 |
|
External/SPEC/CFP2017rate/510.parest_r/510.parest_r
Profile
|
-17.06% |
419.440 |
347.877 |
0.534 |
0.20% |
0.534 |
|
MultiSource/Benchmarks/TSVC/StatementReordering-dbl/StatementReordering-dbl
Profile
|
-16.92% |
24.683 |
20.507 |
0.109 |
0.32% |
0.109 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint16_t>/10
|
-16.40% |
48.181 |
40.281 |
0.032 |
-1.35% |
0.032 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_csa_with_cond_arith_novec_int32_t_
|
-16.27% |
571704.349 |
478676.149 |
492.856 |
-0.07% |
492.856 |
|
SingleSource/Benchmarks/Adobe-C++/loop_unroll
Profile
|
-15.93% |
27.321 |
22.969 |
0.002 |
0.02% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_csa_with_cond_arith_autovec_int32_t_
|
-15.84% |
568560.244 |
478522.353 |
748.086 |
-0.05% |
748.086 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_single_load<uint8_t>/16
|
-15.81% |
9.632 |
8.110 |
0.511 |
7.94% |
0.511 |
|
MultiSource/Benchmarks/MiBench/telecomm-gsm/telecomm-gsm
Profile
|
-15.79% |
0.692 |
0.583 |
0.000 |
0.00% |
0.000 |
|
MultiSource/Benchmarks/TSVC/Expansion-flt/Expansion-flt
Profile
|
-15.63% |
12.429 |
10.486 |
0.041 |
-1.18% |
0.041 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint64_t>/16
|
-15.34% |
53.215 |
45.049 |
0.005 |
-3.14% |
0.005 |
|
MicroBenchmarks/ImageProcessing/Blur/blur.test:BENCHMARK_GAUSSIAN_BLUR/128
|
-15.03% |
4435.341 |
3768.519 |
0.563 |
-0.00% |
0.563 |
|
MultiSource/Benchmarks/mediabench/gsm/toast/toast
Profile
|
-14.87% |
0.090 |
0.076 |
0.000 |
0.08% |
0.000 |
|
MicroBenchmarks/ImageProcessing/Blur/blur.test:BENCHMARK_GAUSSIAN_BLUR/512
|
-14.47% |
81786.722 |
69950.612 |
41.091 |
-0.02% |
41.091 |
|
MicroBenchmarks/ImageProcessing/Blur/blur.test:BENCHMARK_GAUSSIAN_BLUR/256
|
-14.40% |
19528.547 |
16716.775 |
75.433 |
-0.77% |
75.433 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_multiply_accumulate_runtime_checks_fail<2, double>
|
-14.29% |
13.140 |
11.262 |
0.000 |
-0.00% |
0.000 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C++/HPCCG/HPCCG
Profile
|
-14.09% |
4.652 |
3.996 |
0.043 |
0.08% |
0.043 |
|
SingleSource/Benchmarks/Shootout/Shootout-matrix
Profile
|
-13.33% |
4.693 |
4.067 |
0.000 |
-0.00% |
0.000 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C/miniAMR/miniAMR
Profile
|
-13.31% |
3.696 |
3.204 |
0.114 |
0.39% |
0.114 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint64_t>/16
|
-12.72% |
32.544 |
28.406 |
0.077 |
-1.31% |
0.077 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint64_t>/10
|
-12.67% |
24.373 |
21.285 |
0.014 |
-5.50% |
0.014 |
|
SingleSource/Benchmarks/Polybench/stencils/seidel-2d/seidel-2d
Profile
|
-12.66% |
118.438 |
103.442 |
0.204 |
-0.02% |
0.204 |
|
SingleSource/Benchmarks/Stanford/Bubblesort
Profile
|
-12.55% |
0.090 |
0.079 |
0.000 |
0.01% |
0.000 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C++/miniFE/miniFE
Profile
|
-12.41% |
17.849 |
15.634 |
0.068 |
-0.08% |
0.068 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_single_load<uint8_t>/10
|
-12.16% |
9.669 |
8.493 |
0.085 |
13.11% |
0.085 |
|
External/SPEC/CFP2017rate/526.blender_r/526.blender_r
Profile
|
-12.06% |
879.226 |
773.156 |
0.979 |
-0.56% |
0.979 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint16_t>/16
|
-11.88% |
100.115 |
88.224 |
0.095 |
-0.00% |
0.095 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint16_t>/10
|
-11.88% |
81.654 |
71.955 |
0.010 |
0.00% |
0.010 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint16_t>/28
|
-11.88% |
155.494 |
137.027 |
0.075 |
-0.00% |
0.075 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint16_t>/51
|
-11.87% |
266.237 |
234.627 |
0.076 |
-0.00% |
0.076 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint16_t>/256
|
-11.87% |
1207.632 |
1064.300 |
0.210 |
-0.00% |
0.210 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint16_t_To_uint32_t_
|
-11.85% |
13480.798 |
11883.971 |
69.326 |
0.07% |
69.326 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint16_t_To_uint32_t_
|
-11.82% |
13471.944 |
11879.025 |
67.750 |
-0.01% |
67.750 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint16_t>/999
|
-11.82% |
2365.086 |
2085.523 |
0.302 |
0.05% |
0.302 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint16_t>/999
|
-11.82% |
4647.048 |
4097.891 |
0.484 |
-0.04% |
0.484 |
|
MultiSource/Benchmarks/McCat/18-imp/imp
Profile
|
-11.75% |
0.212 |
0.187 |
0.000 |
-0.25% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint16_t>/256
|
-11.73% |
642.905 |
567.494 |
0.126 |
0.20% |
0.126 |
|
MultiSource/Benchmarks/ASC_Sequoia/AMGmk/AMGmk
Profile
|
-11.72% |
43.459 |
38.368 |
0.036 |
0.02% |
0.036 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint16_t_To_uint32_t_
|
-11.47% |
13432.632 |
11891.421 |
64.121 |
0.14% |
64.121 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint16_t>/28
|
-11.46% |
120.135 |
106.366 |
0.009 |
1.19% |
0.009 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint8_t>/999
|
-11.44% |
4805.013 |
4255.279 |
0.183 |
0.01% |
0.183 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint8_t>/256
|
-11.39% |
662.339 |
586.889 |
0.026 |
-0.01% |
0.026 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint8_t>/999
|
-11.39% |
2443.259 |
2164.948 |
0.226 |
-0.00% |
0.226 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint8_t>/256
|
-11.39% |
1245.804 |
1103.916 |
0.136 |
0.00% |
0.136 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint16_t>/51
|
-11.27% |
169.256 |
150.177 |
0.003 |
0.82% |
0.003 |
|
MultiSource/Benchmarks/Rodinia/pathfinder/pathfinder
Profile
|
-11.15% |
1.372 |
1.219 |
0.009 |
0.09% |
0.009 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint8_t>/51
|
-11.13% |
272.488 |
242.153 |
0.033 |
-0.00% |
0.033 |
|
SingleSource/Benchmarks/Misc/flops-4
Profile
|
-11.11% |
4.405 |
3.916 |
0.000 |
-0.01% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint16_t>/999
|
-11.07% |
2848.455 |
2533.266 |
0.197 |
-0.07% |
0.197 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint8_t>/999
|
-11.01% |
2847.792 |
2534.265 |
0.171 |
0.01% |
0.171 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint32_t>/256
|
-11.01% |
745.255 |
663.228 |
0.031 |
-0.00% |
0.031 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint16_t>/256
|
-11.00% |
745.223 |
663.212 |
0.029 |
-0.00% |
0.029 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint8_t>/51
|
-10.99% |
172.925 |
153.921 |
0.006 |
-0.00% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint32_t>/999
|
-10.99% |
2846.931 |
2534.083 |
0.561 |
0.00% |
0.561 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint32_t>/999
|
-10.94% |
1453.725 |
1294.661 |
0.017 |
0.02% |
0.017 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/16
|
-10.90% |
194.627 |
173.412 |
0.004 |
0.00% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint16_t>/16
|
-10.88% |
89.163 |
79.461 |
0.004 |
1.59% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint16_t>/999
|
-10.88% |
1451.132 |
1293.275 |
0.095 |
-0.05% |
0.095 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint8_t>/28
|
-10.88% |
157.975 |
140.795 |
0.014 |
0.00% |
0.014 |
|
MultiSource/Benchmarks/TSVC/CrossingThresholds-flt/CrossingThresholds-flt
Profile
|
-10.87% |
11.078 |
9.874 |
0.105 |
-0.09% |
0.105 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint8_t_To_uint32_t_
|
-10.87% |
12562.136 |
11197.158 |
18.246 |
-0.10% |
18.246 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint8_t>/256
|
-10.84% |
744.568 |
663.857 |
0.021 |
-0.00% |
0.021 |
|
MultiSource/Benchmarks/TSVC/Expansion-dbl/Expansion-dbl
Profile
|
-10.81% |
21.122 |
18.839 |
0.108 |
-0.47% |
0.108 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint8_t>/999
|
-10.81% |
1450.661 |
1293.916 |
0.063 |
-0.09% |
0.063 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint8_t_To_uint32_t_
|
-10.80% |
12563.526 |
11206.782 |
18.261 |
-0.05% |
18.261 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint8_t>/256
|
-10.80% |
399.822 |
356.650 |
0.007 |
-0.00% |
0.007 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint32_t>/256
|
-10.80% |
400.495 |
357.259 |
0.008 |
-0.00% |
0.008 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint16_t>/256
|
-10.78% |
400.440 |
357.261 |
0.017 |
0.00% |
0.017 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchAutoVec<uint8_t>/65
|
-10.72% |
35.041 |
31.286 |
0.003 |
-1.96% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint8_t>/28
|
-10.72% |
122.638 |
109.497 |
0.007 |
-0.00% |
0.007 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/32
|
-10.71% |
970.450 |
866.499 |
0.055 |
0.00% |
0.055 |
|
External/SPEC/CFP2017rate/538.imagick_r/538.imagick_r
Profile
|
-10.68% |
272.224 |
243.144 |
0.479 |
0.02% |
0.479 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/64
|
-10.66% |
4296.328 |
3838.372 |
0.427 |
-0.01% |
0.427 |
|
SingleSource/Benchmarks/Misc/flops-3
Profile
|
-10.64% |
9.195 |
8.217 |
0.000 |
-0.01% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint16_t>/51
|
-10.63% |
170.824 |
152.666 |
0.006 |
-0.00% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint32_t>/51
|
-10.62% |
170.815 |
152.666 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint16_t>/10
|
-10.57% |
76.960 |
68.826 |
0.002 |
1.85% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint8_t>/16
|
-10.56% |
124.514 |
111.369 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint8_t>/10
|
-10.53% |
83.221 |
74.456 |
0.002 |
0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint8_t_To_uint32_t_
|
-10.47% |
12512.676 |
11202.514 |
17.243 |
-0.08% |
17.243 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchAutoVec<uint8_t>/127
|
-10.45% |
41.923 |
37.543 |
0.002 |
-1.64% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint8_t>/999
|
-10.31% |
51.627 |
46.302 |
0.006 |
0.00% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint8_t>/256
|
-10.30% |
51.617 |
46.301 |
0.003 |
-0.00% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint8_t>/28
|
-10.27% |
51.601 |
46.303 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchAutoVec<uint16_t>/65
|
-10.25% |
48.805 |
43.800 |
0.002 |
-1.40% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint8_t>/51
|
-10.23% |
51.577 |
46.300 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint16_t>/51
|
-10.19% |
52.248 |
46.926 |
0.004 |
2.73% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint16_t>/28
|
-10.18% |
52.247 |
46.927 |
0.006 |
2.74% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint16_t>/999
|
-10.18% |
52.248 |
46.928 |
0.009 |
2.74% |
0.009 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint16_t>/256
|
-10.18% |
52.246 |
46.927 |
0.001 |
2.73% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint16_t>/16
|
-10.18% |
52.246 |
46.927 |
0.001 |
2.74% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint16_t>/10
|
-10.18% |
52.248 |
46.929 |
0.008 |
2.74% |
0.008 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/256
|
-10.17% |
75030.662 |
67402.450 |
68.556 |
-0.01% |
68.556 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint32_t>/16
|
-10.14% |
92.607 |
83.216 |
0.003 |
-0.00% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint32_t>/28
|
-10.03% |
112.632 |
101.334 |
0.017 |
1.85% |
0.017 |
|
SingleSource/Benchmarks/Stanford/FloatMM
Profile
|
-10.02% |
0.498 |
0.448 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_GEN_LIN_RECUR_LAMBDA/171
|
-9.95% |
2.158 |
1.943 |
0.000 |
-0.02% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint8_t>/51
|
-9.93% |
170.196 |
153.291 |
0.006 |
-0.00% |
0.006 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_GEN_LIN_RECUR_RAW/171
|
-9.93% |
2.155 |
1.941 |
0.000 |
-0.03% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchAutoVec<uint16_t>/127
|
-9.91% |
69.457 |
62.573 |
0.003 |
-0.99% |
0.003 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/128
|
-9.90% |
18337.432 |
16522.378 |
5.015 |
0.00% |
5.015 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint32_t>/28
|
-9.90% |
142.352 |
128.265 |
0.003 |
-0.00% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint64_t>/51
|
-9.89% |
56.940 |
51.307 |
0.002 |
0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint64_t>/999
|
-9.89% |
56.939 |
51.309 |
0.003 |
-0.00% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_only_novec_int64_t_
|
-9.87% |
1045645.924 |
942492.744 |
663.087 |
-0.05% |
663.087 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint32_t>/51
|
-9.83% |
156.117 |
140.778 |
0.006 |
0.88% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_only_autovec_int64_t_
|
-9.82% |
1046245.511 |
943501.626 |
395.791 |
-0.10% |
395.791 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint32_t>/999
|
-9.74% |
4194.518 |
3786.113 |
0.141 |
-0.03% |
0.141 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint32_t>/51
|
-9.70% |
241.837 |
218.367 |
0.006 |
-0.00% |
0.006 |
|
SingleSource/Benchmarks/Adobe-C++/stepanov_abstraction
Profile
|
-9.66% |
12.696 |
11.469 |
0.001 |
-0.05% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint8_t>/51
|
-9.60% |
110.746 |
100.111 |
0.001 |
-0.00% |
0.001 |
|
SingleSource/Benchmarks/Misc/matmul_f64_4x4
Profile
|
-9.58% |
5.057 |
4.573 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint32_t>/999
|
-9.51% |
2131.884 |
1929.237 |
0.064 |
-0.13% |
0.064 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint32_t>/256
|
-9.50% |
1087.542 |
984.270 |
0.006 |
-0.01% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint32_t>/256
|
-9.42% |
581.001 |
526.242 |
0.018 |
0.22% |
0.018 |
|
MicroBenchmarks/ImageProcessing/Blur/blur.test:BENCHMARK_GAUSSIAN_BLUR/1024
|
-9.41% |
431140.727 |
390552.519 |
279.495 |
-0.01% |
279.495 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint32_t>/16
|
-9.36% |
83.532 |
75.710 |
0.001 |
1.68% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC4
|
-9.36% |
10.354 |
9.385 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint32_t>/256
|
-9.32% |
50.371 |
45.674 |
0.001 |
2.81% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_FIR_LAMBDA/44217
|
-9.32% |
780.201 |
707.457 |
15.184 |
0.37% |
15.184 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint32_t>/16
|
-9.32% |
50.371 |
45.676 |
0.000 |
2.82% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint32_t>/51
|
-9.32% |
50.371 |
45.676 |
0.001 |
2.82% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint32_t>/999
|
-9.32% |
50.370 |
45.676 |
0.001 |
2.80% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint32_t>/28
|
-9.32% |
50.370 |
45.678 |
0.002 |
2.82% |
0.002 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/16
|
-9.31% |
108.696 |
98.578 |
0.007 |
0.00% |
0.007 |
|
MultiSource/Benchmarks/TSVC/Searching-flt/Searching-flt
Profile
|
-9.27% |
17.074 |
15.491 |
0.001 |
-0.01% |
0.001 |
|
SingleSource/Benchmarks/Shootout-C++/Shootout-C++-methcall
Profile
|
-9.22% |
13.567 |
12.316 |
0.000 |
-0.00% |
0.000 |
|
MultiSource/Benchmarks/TSVC/StatementReordering-flt/StatementReordering-flt
Profile
|
-9.20% |
15.512 |
14.085 |
0.054 |
2.72% |
0.054 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_FIR_RAW/171
|
-9.18% |
2.440 |
2.216 |
0.002 |
-0.17% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint8_t>/16
|
-9.17% |
75.084 |
68.200 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_FIR_RAW/44217
|
-9.16% |
760.807 |
691.141 |
22.431 |
-0.96% |
22.431 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/32
|
-9.15% |
444.450 |
403.782 |
0.028 |
0.00% |
0.028 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/64
|
-9.14% |
1795.486 |
1631.358 |
0.509 |
-0.04% |
0.509 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint32_t>/51
|
-9.14% |
110.143 |
100.079 |
0.005 |
0.59% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchAutoVec<uint32_t>/65
|
-9.10% |
76.337 |
69.389 |
0.031 |
-0.99% |
0.031 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_FIR_LAMBDA/171
|
-9.07% |
2.440 |
2.219 |
0.001 |
-0.04% |
0.001 |
|
SingleSource/Benchmarks/BenchmarkGame/Large/fasta
Profile
|
-8.80% |
2.180 |
1.988 |
0.002 |
0.03% |
0.002 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/256
|
-8.78% |
29481.368 |
26891.737 |
19.292 |
-0.10% |
19.292 |
|
MultiSource/Benchmarks/TSVC/NodeSplitting-flt/NodeSplitting-flt
Profile
|
-8.77% |
17.421 |
15.893 |
0.048 |
0.24% |
0.048 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_FIR_RAW/5001
|
-8.74% |
80.865 |
73.795 |
0.027 |
-0.08% |
0.027 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_FIR_LAMBDA/5001
|
-8.74% |
80.851 |
73.783 |
0.028 |
-0.08% |
0.028 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_single_load<uint32_t>/10
|
-8.74% |
8.338 |
7.610 |
0.025 |
-24.37% |
0.025 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_only_autovec_int32_t_
|
-8.73% |
515323.384 |
470322.080 |
597.576 |
-0.06% |
597.576 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/128
|
-8.70% |
7415.789 |
6770.566 |
4.148 |
-0.05% |
4.148 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchAutoVec<uint32_t>/127
|
-8.65% |
124.514 |
113.744 |
0.056 |
-0.48% |
0.056 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_only_novec_int32_t_
|
-8.61% |
515135.584 |
470799.240 |
302.258 |
0.03% |
302.258 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint16_t>/256
|
-8.59% |
1005.482 |
919.100 |
0.226 |
-0.48% |
0.226 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint16_t>/51
|
-8.58% |
109.500 |
100.108 |
0.003 |
-0.30% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_single_load<uint32_t>/16
|
-8.49% |
8.262 |
7.561 |
0.062 |
-24.66% |
0.062 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC128
|
-8.30% |
113.028 |
103.644 |
0.402 |
-1.07% |
0.402 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint16_t>/999
|
-8.29% |
3853.707 |
3534.205 |
0.098 |
-0.15% |
0.098 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint16_t>/51
|
-8.17% |
209.623 |
192.496 |
0.094 |
-0.76% |
0.094 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint16_t_To_uint64_t_
|
-8.09% |
23815.476 |
21889.846 |
15.393 |
-0.08% |
15.393 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC127
|
-8.08% |
113.073 |
103.935 |
0.270 |
-0.52% |
0.270 |
|
MultiSource/Benchmarks/TSVC/Searching-dbl/Searching-dbl
Profile
|
-8.07% |
19.268 |
17.714 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint8_t>/10
|
-8.05% |
54.437 |
50.054 |
0.002 |
0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC127
|
-8.04% |
113.069 |
103.982 |
0.242 |
-0.37% |
0.242 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC128
|
-8.01% |
113.095 |
104.034 |
0.147 |
-0.43% |
0.147 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint32_t>/999
|
-8.01% |
1978.157 |
1819.691 |
0.279 |
-0.09% |
0.279 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC128
|
-8.00% |
112.956 |
103.916 |
0.261 |
-0.58% |
0.261 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint16_t>/999
|
-7.99% |
1937.310 |
1782.598 |
0.265 |
0.02% |
0.265 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC128
|
-7.97% |
112.971 |
103.966 |
0.246 |
-0.44% |
0.246 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint16_t_To_uint64_t_
|
-7.94% |
23779.783 |
21891.956 |
14.870 |
0.01% |
14.870 |
|
MultiSource/Benchmarks/TSVC/InductionVariable-dbl/InductionVariable-dbl
Profile
|
-7.90% |
19.083 |
17.575 |
0.288 |
0.21% |
0.288 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC127
|
-7.90% |
112.967 |
104.043 |
0.186 |
-0.19% |
0.186 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint16_t_To_uint64_t_
|
-7.85% |
23755.880 |
21891.306 |
10.494 |
-0.00% |
10.494 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint32_t>/999
|
-7.85% |
3925.745 |
3617.628 |
0.271 |
0.08% |
0.271 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint16_t>/256
|
-7.83% |
511.823 |
471.747 |
0.018 |
0.10% |
0.018 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC128
|
-7.81% |
112.996 |
104.172 |
0.155 |
-0.65% |
0.155 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC127
|
-7.80% |
113.042 |
104.221 |
0.109 |
0.05% |
0.109 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint32_t>/256
|
-7.80% |
521.863 |
481.166 |
0.008 |
-0.26% |
0.008 |
|
SingleSource/Benchmarks/Linpack/linpack-pc
Profile
|
-7.75% |
9.573 |
8.832 |
0.004 |
-0.07% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint64_t>/256
|
-7.74% |
2110.073 |
1946.718 |
0.016 |
19.52% |
0.016 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC127
|
-7.73% |
112.882 |
104.152 |
0.061 |
-0.32% |
0.061 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint64_t>/10
|
-7.69% |
30.662 |
28.305 |
0.166 |
0.48% |
0.166 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopFrom_uint32_t_To_uint8_t_
|
-7.68% |
10449.467 |
9647.052 |
139.304 |
-0.42% |
139.304 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint64_t_To_uint32_t_
|
-7.67% |
22078.253 |
20385.824 |
198.126 |
-1.21% |
198.126 |
|
MultiSource/Benchmarks/TSVC/NodeSplitting-dbl/NodeSplitting-dbl
Profile
|
-7.65% |
23.405 |
21.614 |
0.357 |
-0.72% |
0.357 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint16_t_To_uint8_t_
|
-7.60% |
4721.120 |
4362.084 |
0.605 |
0.01% |
0.605 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint16_t_To_uint8_t_
|
-7.60% |
4721.142 |
4362.212 |
0.768 |
0.00% |
0.768 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint16_t_To_uint8_t_
|
-7.60% |
4721.231 |
4362.431 |
0.565 |
0.00% |
0.565 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint64_t>/51
|
-7.59% |
196.478 |
181.555 |
0.043 |
0.05% |
0.043 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint64_t>/28
|
-7.59% |
247.146 |
228.375 |
0.012 |
18.12% |
0.012 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint64_t>/256
|
-7.55% |
1073.749 |
992.687 |
0.008 |
19.38% |
0.008 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint64_t_To_uint32_t_
|
-7.53% |
22063.599 |
20401.417 |
192.183 |
-1.33% |
192.183 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint64_t>/16
|
-7.53% |
149.541 |
138.275 |
0.004 |
16.92% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint64_t>/28
|
-7.52% |
141.410 |
130.774 |
0.003 |
16.75% |
0.003 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIND_FIRST_MIN_RAW/171
|
-7.51% |
1.390 |
1.285 |
0.000 |
0.04% |
0.000 |
|
SingleSource/Benchmarks/Misc-C++/Large/sphereflake
Profile
|
-7.50% |
19.566 |
18.098 |
0.002 |
0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint64_t_To_uint32_t_
|
-7.50% |
22042.110 |
20389.359 |
186.690 |
-1.46% |
186.690 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint32_t>/256
|
-7.46% |
1019.579 |
943.554 |
0.196 |
0.35% |
0.196 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint32_t>/28
|
-7.45% |
120.330 |
111.372 |
0.004 |
-1.66% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint64_t>/16
|
-7.44% |
92.608 |
85.720 |
0.002 |
15.12% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint32_t_To_uint8_t_
|
-7.39% |
10430.646 |
9659.779 |
153.968 |
-0.55% |
153.968 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_FLOYD_DITHER/512
|
-7.34% |
6092.953 |
5645.639 |
7.434 |
-2.13% |
7.434 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint32_t_To_uint8_t_
|
-7.34% |
10436.688 |
9670.987 |
121.557 |
-0.78% |
121.557 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_ADI_LAMBDA/44217
|
-7.29% |
14964.056 |
13873.789 |
140.695 |
-0.52% |
140.695 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_csa_with_cond_arith_autovec_uint8_t_
|
-7.28% |
534382.568 |
495482.187 |
49.168 |
-0.01% |
49.168 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_csa_with_cond_arith_novec_uint8_t_
|
-7.28% |
534365.099 |
495479.740 |
12.708 |
0.01% |
12.708 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_FLOYD_DITHER/256
|
-7.24% |
1579.312 |
1464.954 |
2.273 |
-1.64% |
2.273 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint32_t_To_uint8_t_
|
-7.17% |
14205.854 |
13187.516 |
6.438 |
-0.29% |
6.438 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_no_runtime_checks_needed<4, int>
|
-7.14% |
8.760 |
8.134 |
0.000 |
0.00% |
0.000 |
|
SingleSource/Benchmarks/Adobe-C++/stepanov_vector
Profile
|
-7.14% |
7.791 |
7.235 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint32_t_To_uint8_t_
|
-7.11% |
14205.288 |
13194.996 |
4.250 |
-0.19% |
4.250 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_FLOYD_DITHER/128
|
-7.07% |
402.074 |
373.633 |
0.934 |
-1.69% |
0.934 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint32_t_To_uint8_t_
|
-7.07% |
14212.545 |
13207.519 |
5.960 |
-0.12% |
5.960 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint32_t>/51
|
-7.03% |
116.433 |
108.242 |
0.004 |
-1.70% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint16_t>/28
|
-6.89% |
117.653 |
109.541 |
0.046 |
0.61% |
0.046 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint64_t>/256
|
-6.82% |
27.530 |
25.653 |
0.000 |
5.12% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint64_t>/28
|
-6.82% |
27.530 |
25.654 |
0.001 |
5.13% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint64_t>/16
|
-6.81% |
27.530 |
25.654 |
0.001 |
5.13% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC64
|
-6.81% |
57.564 |
53.644 |
0.080 |
-0.31% |
0.080 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC64
|
-6.80% |
57.564 |
53.650 |
0.077 |
-0.30% |
0.077 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C/CoMD/CoMD
Profile
|
-6.72% |
10.055 |
9.379 |
0.008 |
0.03% |
0.008 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC64
|
-6.70% |
57.566 |
53.712 |
0.048 |
-0.19% |
0.048 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC64
|
-6.67% |
57.563 |
53.725 |
0.042 |
-0.16% |
0.042 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC63
|
-6.62% |
57.568 |
53.758 |
0.028 |
-0.10% |
0.028 |
|
MicroBenchmarks/harris/harris.test:BENCHMARK_HARRIS/2048/2048
|
-6.61% |
225384.680 |
210496.180 |
1908.696 |
0.43% |
1908.696 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint16_t>/51
|
-6.59% |
114.546 |
106.992 |
0.001 |
0.59% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint64_t>/10
|
-6.58% |
95.109 |
88.850 |
0.001 |
16.39% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC64
|
-6.58% |
57.564 |
53.779 |
0.019 |
-0.06% |
0.019 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint32_t>/28
|
-6.56% |
76.337 |
71.328 |
0.002 |
-1.62% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC63
|
-6.56% |
57.564 |
53.789 |
0.012 |
-0.04% |
0.012 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC63
|
-6.54% |
57.567 |
53.801 |
0.007 |
-0.02% |
0.007 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC63
|
-6.53% |
57.565 |
53.806 |
0.004 |
-0.01% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC63
|
-6.52% |
57.567 |
53.811 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_single_load<uint64_t>/16
|
-6.42% |
10.020 |
9.377 |
0.003 |
-6.33% |
0.003 |
|
SingleSource/Benchmarks/Shootout-C++/Shootout-C++-fibo
Profile
|
-6.41% |
5.445 |
5.096 |
0.009 |
-0.23% |
0.009 |
|
MultiSource/Benchmarks/TSVC/IndirectAddressing-flt/IndirectAddressing-flt
Profile
|
-6.41% |
15.747 |
14.738 |
0.034 |
-1.72% |
0.034 |
|
MultiSource/Benchmarks/Trimaran/enc-rc4/enc-rc4
Profile
|
-6.38% |
2.913 |
2.727 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_xor_runtime_checks_pass<16, int>
|
-6.37% |
29.407 |
27.533 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_runtime_checks_pass<16, int>
|
-6.35% |
39.419 |
36.916 |
0.001 |
0.00% |
0.001 |
|
MultiSource/Benchmarks/MiBench/consumer-lame/consumer-lame
Profile
|
-6.35% |
0.682 |
0.639 |
0.001 |
-1.12% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_single_load<uint64_t>/10
|
-6.33% |
10.012 |
9.378 |
0.003 |
-6.32% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC31
|
-6.25% |
30.035 |
28.156 |
0.002 |
0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC32
|
-6.25% |
30.034 |
28.156 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC32
|
-6.25% |
30.035 |
28.157 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC32
|
-6.25% |
30.034 |
28.156 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC31
|
-6.25% |
30.034 |
28.156 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC32
|
-6.25% |
30.034 |
28.157 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC32
|
-6.25% |
30.034 |
28.157 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC31
|
-6.25% |
30.033 |
28.157 |
0.002 |
0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC31
|
-6.25% |
30.034 |
28.158 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC31
|
-6.25% |
30.033 |
28.157 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint8_t>/999
|
-6.20% |
5056.997 |
4743.266 |
0.866 |
-0.03% |
0.866 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint8_t>/256
|
-6.09% |
667.586 |
626.955 |
0.013 |
-0.20% |
0.013 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint8_t>/256
|
-6.08% |
1307.724 |
1228.256 |
0.132 |
-0.02% |
0.132 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint8_t>/999
|
-6.05% |
2542.862 |
2388.979 |
0.238 |
-0.08% |
0.238 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint64_t>/51
|
-6.02% |
310.351 |
291.665 |
0.103 |
0.03% |
0.103 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint64_t>/10
|
-6.01% |
62.575 |
58.815 |
0.001 |
14.63% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint64_t>/16
|
-5.98% |
38.037 |
35.761 |
0.042 |
0.23% |
0.042 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_runtime_checks_fail<16, int>
|
-5.98% |
41.922 |
39.417 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint32_t>/51
|
-5.94% |
210.202 |
197.716 |
0.021 |
0.48% |
0.021 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_xor_runtime_checks_fail<16, int>
|
-5.88% |
31.910 |
30.033 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_ADI_LAMBDA/171
|
-5.84% |
32.530 |
30.631 |
0.115 |
-0.56% |
0.115 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint16_t>/28
|
-5.83% |
75.082 |
70.703 |
0.000 |
0.89% |
0.000 |
|
SingleSource/Benchmarks/Shootout/Shootout-fib2
Profile
|
-5.83% |
5.409 |
5.093 |
0.003 |
-0.02% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint64_t>/999
|
-5.75% |
2804.568 |
2643.327 |
0.327 |
0.20% |
0.327 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint64_t>/999
|
-5.73% |
5517.621 |
5201.726 |
1.187 |
-0.01% |
1.187 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_single_load<uint64_t>/256
|
-5.72% |
21.900 |
20.647 |
0.000 |
-5.72% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_single_load<uint64_t>/28
|
-5.72% |
21.901 |
20.648 |
0.003 |
-5.71% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_single_load<uint64_t>/51
|
-5.72% |
21.900 |
20.648 |
0.001 |
-5.71% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint8_t>/51
|
-5.71% |
266.770 |
251.536 |
0.011 |
-0.03% |
0.011 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_single_load<uint64_t>/999
|
-5.71% |
21.900 |
20.649 |
0.001 |
-5.70% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint16_t>/10
|
-5.59% |
35.652 |
33.658 |
0.013 |
-2.20% |
0.013 |
|
External/SPEC/CINT2017rate/525.x264_r/525.x264_r
Profile
|
-5.58% |
142.176 |
134.239 |
0.120 |
-0.45% |
0.120 |
|
SingleSource/Benchmarks/Shootout-C++/EH/Shootout-C++-except
Profile
|
-5.52% |
1.115 |
1.054 |
0.004 |
-0.05% |
0.004 |
|
SingleSource/Benchmarks/Misc-C++/Large/ray
Profile
|
-5.46% |
9.837 |
9.300 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint8_t>/28
|
-5.45% |
149.558 |
141.404 |
0.005 |
-0.44% |
0.005 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIND_FIRST_MIN_RAW/5001
|
-5.41% |
42.137 |
39.856 |
0.097 |
-0.28% |
0.097 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_HYDRO_2D_RAW/5001
|
-5.40% |
15872.412 |
15014.571 |
247.747 |
-1.56% |
247.747 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_ADI_LAMBDA/5001
|
-5.39% |
1701.071 |
1609.446 |
14.078 |
0.78% |
14.078 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_GEN_LIN_RECUR_RAW/5001
|
-5.35% |
86.903 |
82.251 |
0.235 |
0.08% |
0.235 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint8_t>/51
|
-5.34% |
144.758 |
137.024 |
0.003 |
-0.90% |
0.003 |
|
MultiSource/Benchmarks/TSVC/InductionVariable-flt/InductionVariable-flt
Profile
|
-5.27% |
10.035 |
9.507 |
0.030 |
0.35% |
0.030 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_PRESSURE_CALC_RAW/171
|
-5.25% |
1.540 |
1.460 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_PRESSURE_CALC_LAMBDA/171
|
-5.24% |
1.541 |
1.460 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint64_t>/999
|
-5.23% |
3006.073 |
2848.873 |
0.249 |
-0.02% |
0.249 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIND_FIRST_MIN_RAW/44217
|
-5.15% |
361.165 |
342.549 |
0.479 |
-0.07% |
0.479 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint64_t>/999
|
-5.13% |
1529.178 |
1450.675 |
0.143 |
0.03% |
0.143 |
|
MultiSource/Benchmarks/MallocBench/cfrac/cfrac
Profile
|
-5.11% |
2.783 |
2.641 |
0.001 |
-0.05% |
0.001 |
|
SingleSource/Benchmarks/Misc/flops
Profile
|
-5.03% |
14.144 |
13.433 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint64_t>/51
|
-4.95% |
113.886 |
108.249 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_ORDERED_DITHER/512/3
|
-4.94% |
36570.164 |
34761.912 |
33.720 |
-0.16% |
33.720 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_HYDRO_2D_RAW/44217
|
-4.91% |
145175.633 |
138053.916 |
2249.733 |
0.10% |
2249.733 |
|
MultiSource/Benchmarks/TSVC/Reductions-flt/Reductions-flt
Profile
|
-4.84% |
2.830 |
2.693 |
0.017 |
0.12% |
0.017 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint8_t>/28
|
-4.79% |
92.661 |
88.220 |
0.003 |
-1.40% |
0.003 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_ORDERED_DITHER/128/3
|
-4.77% |
2292.263 |
2182.883 |
13.775 |
-0.14% |
13.775 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_two_loads<uint8_t>/51
|
-4.77% |
39.420 |
37.540 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_two_loads<uint8_t>/999
|
-4.77% |
39.419 |
37.540 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_two_loads<uint8_t>/256
|
-4.77% |
39.419 |
37.541 |
0.001 |
-0.00% |
0.001 |
|
MultiSource/Benchmarks/PAQ8p/paq8p
Profile
|
-4.74% |
200.309 |
190.821 |
0.481 |
-0.32% |
0.481 |
|
SingleSource/Benchmarks/McGill/queens
Profile
|
-4.73% |
2.908 |
2.771 |
0.000 |
0.01% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_two_loads<uint32_t>/51
|
-4.69% |
40.046 |
38.166 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_two_loads<uint16_t>/51
|
-4.69% |
40.046 |
38.166 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_two_loads<uint32_t>/256
|
-4.69% |
40.046 |
38.166 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_two_loads<uint32_t>/999
|
-4.69% |
40.046 |
38.167 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_two_loads<uint16_t>/256
|
-4.69% |
40.045 |
38.166 |
0.002 |
0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_two_loads<uint16_t>/999
|
-4.69% |
40.046 |
38.168 |
0.001 |
-0.00% |
0.001 |
|
SingleSource/Benchmarks/BenchmarkGame/spectral-norm
Profile
|
-4.69% |
1.615 |
1.539 |
0.001 |
0.02% |
0.001 |
|
MultiSource/Benchmarks/FreeBench/fourinarow/fourinarow
Profile
|
-4.68% |
0.677 |
0.645 |
0.000 |
-0.08% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint64_t>/51
|
-4.56% |
178.325 |
170.189 |
0.005 |
-0.00% |
0.005 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_ORDERED_DITHER/256/3
|
-4.55% |
9301.952 |
8878.644 |
25.855 |
-0.06% |
25.855 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_EOS_LAMBDA/5001
|
-4.50% |
41.005 |
39.160 |
0.049 |
-0.04% |
0.049 |
|
SingleSource/Benchmarks/Misc/ReedSolomon
Profile
|
-4.50% |
22.059 |
21.067 |
0.006 |
0.29% |
0.006 |
|
SingleSource/Benchmarks/Misc/flops-1
Profile
|
-4.44% |
8.804 |
8.413 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/ImageProcessing/BilateralFiltering/BilateralFilter.test:BENCHMARK_BILATERAL_FILTER/64/2
|
-4.43% |
2551.510 |
2438.462 |
12.342 |
-0.00% |
12.342 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint8_t_To_uint64_t_
|
-4.37% |
22732.946 |
21738.801 |
19.250 |
-0.04% |
19.250 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_ORDERED_DITHER/512/8
|
-4.34% |
34768.085 |
33257.417 |
51.002 |
0.06% |
51.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint8_t_To_uint64_t_
|
-4.33% |
22724.322 |
21739.289 |
27.514 |
-0.08% |
27.514 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C/SimpleMOC/SimpleMOC
Profile
|
-4.33% |
7.415 |
7.094 |
0.008 |
-0.35% |
0.008 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_ORDERED_DITHER/512/4
|
-4.33% |
34674.256 |
33174.387 |
41.563 |
-0.07% |
41.563 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_ORDERED_DITHER/128/4
|
-4.32% |
2170.766 |
2076.927 |
15.061 |
-0.32% |
15.061 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_ORDERED_DITHER/128/8
|
-4.28% |
2173.775 |
2080.719 |
13.871 |
-0.30% |
13.871 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint8_t_To_uint64_t_
|
-4.27% |
22717.333 |
21747.868 |
36.424 |
0.00% |
36.424 |
|
MultiSource/Benchmarks/McCat/12-IOtest/iotest
Profile
|
-4.26% |
2.027 |
1.941 |
0.032 |
0.69% |
0.032 |
|
MicroBenchmarks/ImageProcessing/AnisotropicDiffusion/AnisotropicDiffusion.test:BENCHMARK_ANISTROPIC_DIFFUSION/256
|
-4.22% |
171882.749 |
164634.187 |
162.971 |
-0.01% |
162.971 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_ORDERED_DITHER/256/4
|
-4.17% |
8849.763 |
8480.406 |
20.166 |
-0.24% |
20.166 |
|
SingleSource/Benchmarks/Misc/dt
Profile
|
-4.16% |
4.037 |
3.869 |
0.000 |
-0.01% |
0.000 |
|
MultiSource/Benchmarks/ASC_Sequoia/CrystalMk/CrystalMk
Profile
|
-4.14% |
14.480 |
13.880 |
0.000 |
6.03% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint64_t>/28
|
-4.12% |
53.057 |
50.869 |
0.025 |
0.35% |
0.025 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_PIC_2D_RAW/171
|
-4.09% |
13.665 |
13.105 |
0.109 |
-0.30% |
0.109 |
|
MicroBenchmarks/ImageProcessing/AnisotropicDiffusion/AnisotropicDiffusion.test:BENCHMARK_ANISTROPIC_DIFFUSION/128
|
-4.09% |
39484.789 |
37871.261 |
31.452 |
0.03% |
31.452 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_ORDERED_DITHER/256/8
|
-4.06% |
8861.897 |
8502.092 |
20.372 |
-0.10% |
20.372 |
|
MicroBenchmarks/ImageProcessing/AnisotropicDiffusion/AnisotropicDiffusion.test:BENCHMARK_ANISTROPIC_DIFFUSION/64
|
-4.06% |
9198.691 |
8825.327 |
1.906 |
0.01% |
1.906 |
|
MicroBenchmarks/ImageProcessing/AnisotropicDiffusion/AnisotropicDiffusion.test:BENCHMARK_ANISTROPIC_DIFFUSION/32
|
-3.93% |
2014.654 |
1935.379 |
0.287 |
-0.01% |
0.287 |
|
External/SPEC/CFP2017rate/544.nab_r/544.nab_r
Profile
|
-3.90% |
454.804 |
437.051 |
0.065 |
0.06% |
0.065 |
|
MicroBenchmarks/LCALS/SubsetBRawLoops/lcalsBRaw.test:BM_INIT3_RAW/171
|
-3.89% |
0.711 |
0.684 |
0.000 |
-0.04% |
0.000 |
|
SingleSource/Benchmarks/Misc-C++/bigfib
Profile
|
-3.86% |
1.295 |
1.245 |
0.004 |
-0.49% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint64_t_To_uint8_t_
|
-3.86% |
32343.677 |
31096.291 |
8.025 |
0.00% |
8.025 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC16
|
-3.85% |
16.269 |
15.643 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetBLambdaLoops/lcalsBLambda.test:BM_INIT3_LAMBDA/171
|
-3.85% |
0.711 |
0.683 |
0.001 |
-0.17% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC15
|
-3.85% |
16.269 |
15.643 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC16
|
-3.85% |
16.269 |
15.643 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC16
|
-3.85% |
16.269 |
15.643 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC15
|
-3.85% |
16.269 |
15.643 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC15
|
-3.85% |
16.269 |
15.643 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC16
|
-3.85% |
16.269 |
15.643 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/ImageProcessing/BilateralFiltering/BilateralFilter.test:BENCHMARK_BILATERAL_FILTER/32/2
|
-3.85% |
593.241 |
570.424 |
3.696 |
0.01% |
3.696 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC16
|
-3.85% |
16.268 |
15.642 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC15
|
-3.84% |
16.268 |
15.643 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC15
|
-3.84% |
16.268 |
15.643 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint64_t_To_uint8_t_
|
-3.84% |
32336.834 |
31094.112 |
10.532 |
-0.01% |
10.532 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_MAT_X_MAT_RAW/171
|
-3.84% |
2479.442 |
2384.214 |
5.932 |
0.18% |
5.932 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint64_t_To_uint8_t_
|
-3.84% |
32335.807 |
31094.842 |
7.793 |
-0.01% |
7.793 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_DEL_DOT_VEC_2D_LAMBDA/2
|
-3.83% |
2.775 |
2.669 |
0.000 |
0.00% |
0.000 |
|
SingleSource/Benchmarks/Misc-C++/oopack_v1p8
Profile
|
-3.82% |
0.479 |
0.460 |
0.000 |
-0.05% |
0.000 |
|
SingleSource/Benchmarks/SmallPT/smallpt
Profile
|
-3.82% |
28.454 |
27.366 |
0.002 |
-0.01% |
0.002 |
|
MultiSource/Benchmarks/TSVC/Equivalencing-flt/Equivalencing-flt
Profile
|
-3.80% |
4.001 |
3.849 |
0.013 |
-0.70% |
0.013 |
|
MicroBenchmarks/ImageProcessing/BilateralFiltering/BilateralFilter.test:BENCHMARK_BILATERAL_FILTER/16/2
|
-3.75% |
129.369 |
124.514 |
0.010 |
0.00% |
0.010 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_DEL_DOT_VEC_2D_LAMBDA/1
|
-3.71% |
227.416 |
218.968 |
0.135 |
-0.01% |
0.135 |
|
SingleSource/Benchmarks/Misc/flops-8
Profile
|
-3.70% |
1.973 |
1.900 |
0.000 |
0.00% |
0.000 |
|
MultiSource/Benchmarks/FreeBench/distray/distray
Profile
|
-3.68% |
0.424 |
0.408 |
0.000 |
0.03% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_HYDRO_2D_LAMBDA/171
|
-3.66% |
261.306 |
251.743 |
0.945 |
-0.60% |
0.945 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_COUPLE_RAW/2
|
-3.64% |
8.083 |
7.789 |
0.001 |
-0.00% |
0.001 |
|
SingleSource/Benchmarks/BenchmarkGame/n-body
Profile
|
-3.58% |
3.212 |
3.096 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_COUPLE_RAW/1
|
-3.57% |
1016.220 |
979.962 |
10.414 |
-0.00% |
10.414 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C++/PENNANT/PENNANT
Profile
|
-3.56% |
4.607 |
4.443 |
0.016 |
-1.01% |
0.016 |
|
External/SPEC/CFP2017rate/511.povray_r/511.povray_r
Profile
|
-3.54% |
28.635 |
27.620 |
0.029 |
0.22% |
0.029 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_COUPLE_RAW/0
|
-3.54% |
6136.421 |
5919.147 |
13.667 |
-0.19% |
13.667 |
|
MultiSource/Benchmarks/Rodinia/hotspot/hotspot
Profile
|
-3.47% |
2.312 |
2.231 |
0.003 |
0.04% |
0.003 |
|
SingleSource/Benchmarks/Shootout-C++/Shootout-C++-lists
Profile
|
-3.39% |
20.762 |
20.059 |
0.128 |
0.30% |
0.128 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_PIC_2D_LAMBDA/171
|
-3.38% |
13.738 |
13.273 |
0.071 |
-0.23% |
0.071 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_DEL_DOT_VEC_2D_RAW/1
|
-3.34% |
226.576 |
219.015 |
0.078 |
-0.02% |
0.078 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_DEL_DOT_VEC_2D_RAW/2
|
-3.30% |
2.760 |
2.669 |
0.000 |
0.01% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetBLambdaLoops/lcalsBLambda.test:BM_IF_QUAD_LAMBDA/171
|
-3.28% |
4.243 |
4.104 |
0.000 |
-0.01% |
0.000 |
|
External/SPEC/CFP2017rate/519.lbm_r/519.lbm_r
Profile
|
-3.24% |
211.683 |
204.818 |
1.229 |
-0.05% |
1.229 |
|
SingleSource/Benchmarks/Dhrystone/fldry
Profile
|
-3.22% |
0.975 |
0.944 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_HYDRO_2D_RAW/171
|
-3.22% |
261.421 |
253.010 |
0.414 |
-0.07% |
0.414 |
|
External/SPEC/CFP2017rate/508.namd_r/508.namd_r
Profile
|
-3.21% |
187.364 |
181.342 |
0.275 |
0.09% |
0.275 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_ORDERED_DITHER/128/2
|
-3.21% |
2142.135 |
2073.473 |
15.691 |
-0.32% |
15.691 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint64_t_To_uint16_t_
|
-3.15% |
26726.819 |
25883.787 |
54.078 |
0.01% |
54.078 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint64_t_To_uint16_t_
|
-3.13% |
26721.359 |
25884.301 |
49.190 |
0.01% |
49.190 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint8_t>/10
|
-3.13% |
20.022 |
19.397 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint8_t>/16
|
-3.12% |
20.022 |
19.396 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint64_t_To_uint16_t_
|
-3.12% |
26718.022 |
25885.501 |
47.564 |
0.00% |
47.564 |
|
SingleSource/Benchmarks/Polybench/stencils/jacobi-2d/jacobi-2d
Profile
|
-3.09% |
41.791 |
40.498 |
0.146 |
-0.25% |
0.146 |
|
MultiSource/Benchmarks/mafft/pairlocalalign
Profile
|
-3.07% |
79.380 |
76.939 |
0.045 |
0.32% |
0.045 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_two_loads<uint64_t>/10
|
-3.05% |
16.894 |
16.379 |
0.012 |
-3.05% |
0.012 |
|
MicroBenchmarks/LCALS/SubsetBLambdaLoops/lcalsBLambda.test:BM_IF_QUAD_LAMBDA/5001
|
-3.04% |
131.334 |
127.335 |
0.145 |
-0.08% |
0.145 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_single_load<uint32_t>/256
|
-3.04% |
20.648 |
20.021 |
0.001 |
-8.55% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_single_load<uint32_t>/999
|
-3.03% |
20.650 |
20.023 |
0.000 |
-5.87% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_single_load<uint32_t>/51
|
-3.03% |
20.648 |
20.022 |
0.000 |
-5.88% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_two_loads<uint64_t>/16
|
-3.03% |
16.894 |
16.382 |
0.006 |
-3.03% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_single_load<uint32_t>/28
|
-3.03% |
20.648 |
20.022 |
0.000 |
-5.88% |
0.000 |
|
SingleSource/Benchmarks/Shootout-C++/Shootout-C++-lists1
Profile
|
-3.01% |
1.003 |
0.973 |
0.007 |
-0.59% |
0.007 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_ORDERED_DITHER/512/2
|
-3.01% |
34278.585 |
33247.276 |
9.140 |
-0.03% |
9.140 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_two_loads<uint64_t>/28
|
-3.00% |
16.894 |
16.387 |
0.011 |
-3.00% |
0.011 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_COUPLE_LAMBDA/2
|
-2.98% |
8.058 |
7.818 |
0.000 |
-0.03% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC32
|
-2.97% |
89.489 |
86.829 |
0.660 |
-1.58% |
0.660 |
|
SingleSource/Benchmarks/Misc/pi
Profile
|
-2.96% |
1.863 |
1.808 |
0.000 |
-0.01% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_COUPLE_LAMBDA/1
|
-2.94% |
1012.956 |
983.149 |
7.426 |
-0.01% |
7.426 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC15
|
-2.93% |
21.274 |
20.650 |
0.005 |
0.00% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC31
|
-2.91% |
89.483 |
86.882 |
0.624 |
-1.52% |
0.624 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIRST_DIFF_LAMBDA/171
|
-2.89% |
0.355 |
0.345 |
0.003 |
-1.95% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_single_load<uint8_t>/28
|
-2.88% |
21.904 |
21.273 |
0.000 |
-5.56% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_single_load<uint8_t>/51
|
-2.87% |
21.900 |
21.272 |
0.001 |
-5.56% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_IMP_HYDRO_2D_RAW/5001
|
-2.87% |
1677.217 |
1629.156 |
1.591 |
-0.13% |
1.591 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_single_load<uint8_t>/256
|
-2.86% |
21.900 |
21.273 |
0.001 |
-5.56% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_single_load<uint8_t>/999
|
-2.86% |
21.900 |
21.273 |
0.001 |
-5.55% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint64_t>/10
|
-2.86% |
21.899 |
21.273 |
0.001 |
6.24% |
0.001 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_ORDERED_DITHER/256/2
|
-2.85% |
8733.359 |
8484.749 |
8.225 |
-0.05% |
8.225 |
|
SingleSource/Benchmarks/Misc/perlin
Profile
|
-2.85% |
8.412 |
8.173 |
0.000 |
0.00% |
0.000 |
|
SingleSource/Benchmarks/Misc/mandel
Profile
|
-2.84% |
3.300 |
3.206 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_IMP_HYDRO_2D_RAW/44217
|
-2.81% |
14979.919 |
14559.222 |
57.605 |
-0.21% |
57.605 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC32
|
-2.80% |
89.488 |
86.985 |
0.592 |
-1.41% |
0.592 |
|
MultiSource/Benchmarks/tramp3d-v4/tramp3d-v4
Profile
|
-2.77% |
1.011 |
0.983 |
0.001 |
-0.03% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC16
|
-2.67% |
21.214 |
20.647 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetBRawLoops/lcalsBRaw.test:BM_IF_QUAD_RAW/171
|
-2.66% |
4.216 |
4.104 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_DEL_DOT_VEC_2D_LAMBDA/0
|
-2.65% |
1463.348 |
1424.547 |
2.107 |
-0.18% |
2.107 |
|
SingleSource/Benchmarks/Misc/flops-6
Profile
|
-2.64% |
1.850 |
1.801 |
0.000 |
0.01% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetBLambdaLoops/lcalsBLambda.test:BM_MULADDSUB_LAMBDA/5001
|
-2.62% |
58.478 |
56.948 |
0.447 |
-1.12% |
0.447 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint32_t>/10
|
-2.60% |
41.296 |
40.222 |
0.014 |
1.21% |
0.014 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_IMP_HYDRO_2D_RAW/171
|
-2.58% |
54.973 |
53.554 |
0.089 |
0.11% |
0.089 |
|
MultiSource/Benchmarks/Fhourstones-3.1/fhourstones3.1
Profile
|
-2.52% |
3.931 |
3.832 |
0.002 |
-0.19% |
0.002 |
|
MultiSource/Applications/JM/lencod/lencod
Profile
|
-2.52% |
35.747 |
34.845 |
0.047 |
-0.01% |
0.047 |
|
MultiSource/Benchmarks/ASCI_Purple/SMG2000/smg2000
Profile
|
-2.49% |
17.924 |
17.477 |
0.009 |
-0.02% |
0.009 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_DEL_DOT_VEC_2D_RAW/0
|
-2.48% |
1461.622 |
1425.445 |
1.756 |
-0.21% |
1.756 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint8_t>/16
|
-2.46% |
33.992 |
33.157 |
0.288 |
18.06% |
0.288 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint64_t>/256
|
-2.44% |
355.305 |
346.618 |
0.245 |
-0.05% |
0.245 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_DISC_ORD_LAMBDA/171
|
-2.44% |
18.693 |
18.236 |
0.138 |
-0.53% |
0.138 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC31
|
-2.42% |
89.502 |
87.338 |
0.422 |
-1.01% |
0.422 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_ADI_RAW/171
|
-2.42% |
31.912 |
31.140 |
0.110 |
-0.12% |
0.110 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint16_t>/16
|
-2.42% |
49.949 |
48.743 |
0.001 |
2.49% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC31
|
-2.39% |
89.492 |
87.354 |
0.414 |
-0.99% |
0.414 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_COUPLE_LAMBDA/0
|
-2.39% |
6103.757 |
5958.078 |
1.058 |
-0.05% |
1.058 |
|
MicroBenchmarks/ImageProcessing/BilateralFiltering/BilateralFilter.test:BENCHMARK_BILATERAL_FILTER/64/4
|
-2.38% |
9542.475 |
9314.934 |
1.104 |
-0.01% |
1.104 |
|
MicroBenchmarks/ImageProcessing/BilateralFiltering/BilateralFilter.test:BENCHMARK_BILATERAL_FILTER/32/4
|
-2.37% |
2077.330 |
2028.106 |
0.172 |
-0.00% |
0.172 |
|
MultiSource/Benchmarks/TSVC/ControlLoops-flt/ControlLoops-flt
Profile
|
-2.37% |
4.213 |
4.113 |
0.029 |
0.15% |
0.029 |
|
MicroBenchmarks/ImageProcessing/BilateralFiltering/BilateralFilter.test:BENCHMARK_BILATERAL_FILTER/16/4
|
-2.35% |
381.703 |
372.746 |
0.018 |
0.00% |
0.018 |
|
MultiSource/Benchmarks/TSVC/IndirectAddressing-dbl/IndirectAddressing-dbl
Profile
|
-2.32% |
18.523 |
18.093 |
0.070 |
-0.78% |
0.070 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_EOS_LAMBDA/171
|
-2.32% |
1.157 |
1.130 |
0.000 |
-0.02% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_EOS_RAW/5001
|
-2.30% |
40.667 |
39.732 |
0.021 |
-0.05% |
0.021 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_PIC_1D_LAMBDA/171
|
-2.30% |
8.951 |
8.746 |
0.069 |
-0.55% |
0.069 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C++/CLAMR/CLAMR
Profile
|
-2.27% |
12.121 |
11.846 |
0.051 |
0.16% |
0.051 |
|
SingleSource/Benchmarks/Misc/whetstone
Profile
|
-2.25% |
2.955 |
2.888 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC32
|
-2.25% |
89.480 |
87.465 |
0.364 |
-0.87% |
0.364 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_PRESSURE_CALC_RAW/5001
|
-2.22% |
48.017 |
46.950 |
0.322 |
-1.25% |
0.322 |
|
MultiSource/Benchmarks/7zip/7zip-benchmark
Profile
|
-2.22% |
30.569 |
29.890 |
0.076 |
-0.07% |
0.076 |
|
MultiSource/Benchmarks/Olden/power/power
Profile
|
-2.20% |
3.744 |
3.661 |
0.000 |
-0.02% |
0.000 |
|
MicroBenchmarks/LoopInterchange/LoopInterchange.test:BENCHMARK_LI1
|
-2.17% |
1598.161 |
1563.537 |
1.844 |
-0.07% |
1.844 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC64
|
-2.12% |
165.326 |
161.815 |
0.124 |
-0.16% |
0.124 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC64
|
-2.07% |
165.245 |
161.817 |
0.124 |
-0.16% |
0.124 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC64
|
-2.06% |
165.073 |
161.675 |
0.194 |
-0.25% |
0.194 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC32
|
-2.05% |
89.486 |
87.649 |
0.275 |
-0.66% |
0.275 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC63
|
-2.04% |
165.117 |
161.745 |
0.160 |
-0.20% |
0.160 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC63
|
-2.02% |
164.947 |
161.611 |
0.221 |
-0.28% |
0.221 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC32
|
-2.02% |
89.485 |
87.681 |
0.259 |
-0.62% |
0.259 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC64
|
-2.00% |
164.925 |
161.619 |
0.228 |
-0.24% |
0.228 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1BigLoopWithReductionTC31
|
-2.00% |
89.492 |
87.705 |
0.249 |
-0.59% |
0.249 |
|
MicroBenchmarks/LCALS/SubsetBRawLoops/lcalsBRaw.test:BM_IF_QUAD_RAW/5001
|
-2.00% |
130.491 |
127.885 |
0.029 |
0.13% |
0.029 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC127
|
-1.99% |
315.944 |
309.641 |
0.072 |
-0.04% |
0.072 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1BigLoopWithReductionTC63
|
-1.96% |
165.108 |
161.876 |
0.097 |
-0.12% |
0.097 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC63
|
-1.94% |
164.999 |
161.803 |
0.132 |
-0.16% |
0.132 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC64
|
-1.92% |
165.068 |
161.903 |
0.082 |
-0.10% |
0.082 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC128
|
-1.91% |
315.515 |
309.501 |
0.145 |
-0.09% |
0.145 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1BigLoopWithReductionTC64
|
-1.90% |
165.082 |
161.953 |
0.064 |
-0.07% |
0.064 |
|
SingleSource/Benchmarks/Misc/flops-5
Profile
|
-1.89% |
2.584 |
2.535 |
0.000 |
0.01% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC128
|
-1.88% |
315.601 |
309.658 |
0.068 |
-0.04% |
0.068 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC63
|
-1.88% |
165.028 |
161.930 |
0.075 |
-0.09% |
0.075 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC127
|
-1.87% |
315.535 |
309.640 |
0.076 |
-0.04% |
0.076 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC63
|
-1.87% |
165.098 |
162.016 |
0.037 |
-0.04% |
0.037 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC32
|
-1.86% |
89.451 |
87.783 |
0.211 |
-0.50% |
0.211 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC127
|
-1.86% |
315.514 |
309.638 |
0.082 |
-0.04% |
0.082 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC31
|
-1.86% |
89.485 |
87.820 |
0.199 |
-0.46% |
0.199 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC15
|
-1.86% |
21.081 |
20.689 |
0.015 |
0.13% |
0.015 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC7
|
-1.86% |
33.789 |
33.161 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC7
|
-1.86% |
33.790 |
33.162 |
0.003 |
-0.00% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1BigLoopWithReductionTC4
|
-1.86% |
33.791 |
33.163 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC8
|
-1.86% |
33.789 |
33.162 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC7
|
-1.86% |
33.790 |
33.163 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC8
|
-1.86% |
33.790 |
33.163 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC2
|
-1.86% |
33.789 |
33.162 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1BigLoopWithReductionTC7
|
-1.86% |
33.790 |
33.163 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC1
|
-1.86% |
33.790 |
33.163 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC1
|
-1.86% |
33.789 |
33.162 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC4
|
-1.86% |
33.789 |
33.162 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC4
|
-1.86% |
33.790 |
33.164 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC7
|
-1.86% |
33.789 |
33.162 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC7
|
-1.85% |
33.790 |
33.163 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC1
|
-1.85% |
33.789 |
33.163 |
0.003 |
0.00% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC4
|
-1.85% |
33.789 |
33.163 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC8
|
-1.85% |
33.790 |
33.163 |
0.004 |
-0.00% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC8
|
-1.85% |
33.789 |
33.163 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC3
|
-1.85% |
33.789 |
33.163 |
0.002 |
0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC4
|
-1.85% |
33.788 |
33.162 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1BigLoopWithReductionTC3
|
-1.85% |
33.789 |
33.163 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC2
|
-1.85% |
33.789 |
33.163 |
0.002 |
0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC4
|
-1.85% |
33.789 |
33.163 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC8
|
-1.85% |
33.788 |
33.163 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1BigLoopWithReductionTC1
|
-1.85% |
33.788 |
33.162 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC1
|
-1.85% |
33.788 |
33.162 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC1
|
-1.85% |
33.788 |
33.162 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1BigLoopWithReductionTC8
|
-1.85% |
33.789 |
33.163 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC3
|
-1.85% |
33.788 |
33.163 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC3
|
-1.85% |
33.788 |
33.162 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC4
|
-1.85% |
33.790 |
33.165 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC7
|
-1.85% |
33.790 |
33.164 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1BigLoopWithReductionTC2
|
-1.85% |
33.788 |
33.163 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC8
|
-1.85% |
33.789 |
33.164 |
0.003 |
0.00% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC2
|
-1.85% |
33.788 |
33.163 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC1
|
-1.85% |
33.788 |
33.163 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC3
|
-1.85% |
33.789 |
33.164 |
0.003 |
0.00% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC2
|
-1.85% |
33.789 |
33.164 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC2
|
-1.85% |
33.788 |
33.163 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC2
|
-1.85% |
33.789 |
33.164 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC3
|
-1.85% |
33.789 |
33.164 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC3
|
-1.85% |
33.787 |
33.164 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC16
|
-1.84% |
51.935 |
50.979 |
0.159 |
-0.64% |
0.159 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC31
|
-1.83% |
89.498 |
87.856 |
0.177 |
-0.42% |
0.177 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC128
|
-1.83% |
315.552 |
309.792 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint32_t>/16
|
-1.82% |
56.315 |
55.289 |
0.020 |
0.96% |
0.020 |
|
MicroBenchmarks/harris/harris.test:BENCHMARK_HARRIS/1024/1024
|
-1.82% |
123698.333 |
121447.222 |
196.539 |
-1.62% |
196.539 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC127
|
-1.81% |
315.353 |
309.635 |
0.082 |
-0.05% |
0.082 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC15
|
-1.81% |
51.938 |
51.000 |
0.146 |
-0.60% |
0.146 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC127
|
-1.80% |
315.335 |
309.653 |
0.069 |
-0.04% |
0.069 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC15
|
-1.80% |
51.936 |
51.000 |
0.147 |
-0.60% |
0.147 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1BigLoopWithReductionTC128
|
-1.80% |
315.438 |
309.775 |
0.014 |
0.00% |
0.014 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC128
|
-1.79% |
315.422 |
309.788 |
0.005 |
-0.00% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC63
|
-1.78% |
164.882 |
161.945 |
0.068 |
-0.07% |
0.068 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC128
|
-1.78% |
315.400 |
309.795 |
0.004 |
-0.00% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC128
|
-1.77% |
315.359 |
309.784 |
0.035 |
0.00% |
0.035 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC127
|
-1.77% |
315.359 |
309.789 |
0.018 |
-0.00% |
0.018 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, GreaterThanZero, Mid>
|
-1.74% |
30654.876 |
30121.758 |
1.024 |
0.00% |
1.024 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1BigLoopWithReductionTC127
|
-1.73% |
315.232 |
309.777 |
0.050 |
0.00% |
0.050 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_IMP_HYDRO_2D_LAMBDA/44217
|
-1.73% |
14843.254 |
14587.062 |
48.584 |
0.07% |
48.584 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1BigLoopWithReductionTC32
|
-1.70% |
89.488 |
87.963 |
0.128 |
-0.30% |
0.128 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC64
|
-1.70% |
164.812 |
162.008 |
0.034 |
-0.03% |
0.034 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_asin_novec_double_
|
-1.67% |
1184.843 |
1165.100 |
6.681 |
0.01% |
6.681 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC16
|
-1.65% |
51.934 |
51.076 |
0.111 |
-0.45% |
0.111 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC16
|
-1.64% |
51.936 |
51.083 |
0.108 |
-0.44% |
0.108 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1LoopWithReductionTC31
|
-1.64% |
28.779 |
28.307 |
0.095 |
-0.50% |
0.095 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_INT_PREDICT_RAW/171
|
-1.60% |
6.127 |
6.029 |
0.008 |
-0.00% |
0.008 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC16
|
-1.59% |
51.940 |
51.112 |
0.093 |
-0.38% |
0.093 |
|
MultiSource/Applications/sgefa/sgefa
Profile
|
-1.59% |
0.642 |
0.632 |
0.000 |
0.12% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC15
|
-1.59% |
51.937 |
51.113 |
0.093 |
-0.38% |
0.093 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_INT_PREDICT_LAMBDA/171
|
-1.57% |
6.134 |
6.038 |
0.013 |
-0.03% |
0.013 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_two_loads<uint64_t>/999
|
-1.57% |
40.048 |
39.419 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_two_loads<uint64_t>/51
|
-1.57% |
40.045 |
39.417 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_IMP_HYDRO_2D_LAMBDA/5001
|
-1.56% |
1658.243 |
1632.396 |
0.793 |
0.14% |
0.793 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC15
|
-1.55% |
51.937 |
51.134 |
0.084 |
-0.34% |
0.084 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC15
|
-1.54% |
51.938 |
51.136 |
0.085 |
-0.34% |
0.085 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1BigLoopWithReductionTC16
|
-1.46% |
51.935 |
51.177 |
0.064 |
-0.26% |
0.064 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_DISC_ORD_RAW/171
|
-1.45% |
18.778 |
18.505 |
0.051 |
0.09% |
0.051 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_csa_with_cond_arith_autovec_int64_t_
|
-1.45% |
693303.386 |
683247.679 |
451.391 |
0.02% |
451.391 |
|
MicroBenchmarks/harris/harris.test:BENCHMARK_HARRIS/512/512
|
-1.43% |
30640.493 |
30201.118 |
8.041 |
-1.24% |
8.041 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_csa_with_cond_arith_novec_int64_t_
|
-1.40% |
693019.961 |
683298.335 |
1310.234 |
-0.23% |
1310.234 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC31
|
-1.39% |
89.469 |
88.227 |
0.003 |
-0.00% |
0.003 |
|
SingleSource/Benchmarks/Shootout-C++/Shootout-C++-sieve
Profile
|
-1.36% |
7.556 |
7.453 |
0.005 |
-0.01% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint32_t>/28
|
-1.35% |
86.349 |
85.187 |
0.034 |
0.42% |
0.034 |
|
MicroBenchmarks/LCALS/SubsetBRawLoops/lcalsBRaw.test:BM_TRAP_INT_RAW/5001
|
-1.34% |
87.674 |
86.495 |
0.004 |
-0.00% |
0.004 |
|
MicroBenchmarks/LCALS/SubsetBLambdaLoops/lcalsBLambda.test:BM_TRAP_INT_LAMBDA/171
|
-1.34% |
3.029 |
2.988 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetBRawLoops/lcalsBRaw.test:BM_TRAP_INT_RAW/44217
|
-1.34% |
774.728 |
764.327 |
0.022 |
0.00% |
0.022 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC16
|
-1.34% |
51.934 |
51.237 |
0.034 |
-0.15% |
0.034 |
|
MicroBenchmarks/LCALS/SubsetBLambdaLoops/lcalsBLambda.test:BM_TRAP_INT_LAMBDA/44217
|
-1.34% |
774.715 |
764.339 |
0.030 |
0.00% |
0.030 |
|
MicroBenchmarks/LCALS/SubsetBLambdaLoops/lcalsBLambda.test:BM_TRAP_INT_LAMBDA/5001
|
-1.34% |
87.673 |
86.501 |
0.006 |
0.00% |
0.006 |
|
MicroBenchmarks/LCALS/SubsetBRawLoops/lcalsBRaw.test:BM_TRAP_INT_RAW/171
|
-1.33% |
3.028 |
2.988 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC16
|
-1.29% |
51.916 |
51.245 |
0.030 |
-0.12% |
0.030 |
|
MultiSource/Benchmarks/TSVC/ControlLoops-dbl/ControlLoops-dbl
Profile
|
-1.29% |
8.022 |
7.918 |
0.036 |
-0.92% |
0.036 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchVecWithRuntimeChecks4PointersDEqualsA/32
|
-1.28% |
48463.967 |
47843.287 |
2.565 |
-0.00% |
2.565 |
|
SingleSource/Benchmarks/Misc/flops-7
Profile
|
-1.28% |
7.631 |
7.533 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_ENERGY_CALC_RAW/171
|
-1.27% |
15.823 |
15.623 |
0.036 |
-0.03% |
0.036 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1BigLoopWithReductionTC15
|
-1.23% |
51.935 |
51.296 |
0.007 |
-0.02% |
0.007 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC15
|
-1.21% |
51.936 |
51.310 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_nested_cond_load_novec_int64_t_
|
-1.17% |
617130.196 |
609925.107 |
1745.552 |
-0.35% |
1745.552 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC31
|
-1.13% |
28.779 |
28.453 |
0.046 |
-0.13% |
0.046 |
|
SingleSource/Benchmarks/Shootout-C++/Shootout-C++-hash2
Profile
|
-1.12% |
8.512 |
8.416 |
0.028 |
-0.04% |
0.028 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC31
|
-1.08% |
28.782 |
28.472 |
0.008 |
0.16% |
0.008 |
|
SingleSource/Benchmarks/Misc/fbench
Profile
|
-1.05% |
6.131 |
6.067 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC32
|
-1.04% |
28.768 |
28.468 |
0.033 |
-0.23% |
0.033 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC32
|
-1.04% |
28.777 |
28.478 |
0.055 |
0.06% |
0.055 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1LoopWithReductionTC32
|
-1.02% |
28.783 |
28.489 |
0.034 |
0.02% |
0.034 |