|
SingleSource/Benchmarks/Shootout/Shootout-ary3
Profile
|
44.38% |
0.522 |
0.753 |
0.000 |
-23.50% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_single_load<uint8_t>/16
|
42.82% |
7.513 |
10.731 |
0.189 |
6.57% |
0.189 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_single_load<uint8_t>/10
|
40.97% |
7.509 |
10.585 |
0.285 |
6.34% |
0.285 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_multiply_accumulate_runtime_checks_fail<3, double>
|
33.33% |
11.263 |
15.017 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_multiply_accumulate_runtime_checks_pass<3, double>
|
33.32% |
11.264 |
15.016 |
0.000 |
-0.00% |
0.000 |
|
SingleSource/Benchmarks/Misc-C++/stepanov_v1p2
Profile
|
33.24% |
12.256 |
16.330 |
0.001 |
-0.00% |
0.001 |
|
MultiSource/Benchmarks/TSVC/Packing-flt/Packing-flt
Profile
|
30.71% |
25.939 |
33.905 |
0.790 |
-0.78% |
0.790 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint64_t>/256
|
29.51% |
1628.805 |
2109.476 |
0.112 |
-0.03% |
0.112 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint64_t>/256
|
29.21% |
831.519 |
1074.441 |
0.425 |
0.06% |
0.425 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_TRIDIAG_ELIM_RAW/171
|
28.10% |
0.755 |
0.967 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_TRIDIAG_ELIM_LAMBDA/171
|
28.10% |
0.755 |
0.967 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint64_t>/28
|
27.83% |
193.346 |
247.154 |
0.029 |
0.00% |
0.029 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_xor_no_runtime_checks_needed<4, int>
|
27.27% |
6.883 |
8.760 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint64_t>/16
|
26.45% |
118.261 |
149.544 |
0.002 |
0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint64_t>/28
|
26.25% |
112.010 |
141.410 |
0.001 |
0.00% |
0.001 |
|
SingleSource/Benchmarks/Adobe-C++/simple_types_constant_folding
Profile
|
25.60% |
1.720 |
2.160 |
0.002 |
-8.73% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint64_t>/10
|
24.59% |
76.338 |
95.110 |
0.003 |
-0.00% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint64_t>/16
|
24.37% |
74.459 |
92.602 |
0.003 |
-0.01% |
0.003 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_TRIDIAG_ELIM_LAMBDA/44217
|
23.47% |
203.888 |
251.733 |
0.609 |
-0.28% |
0.609 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_TRIDIAG_ELIM_RAW/44217
|
23.21% |
204.617 |
252.114 |
0.320 |
-0.10% |
0.320 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_TRIDIAG_ELIM_LAMBDA/5001
|
22.15% |
23.312 |
28.475 |
0.007 |
0.04% |
0.007 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint64_t>/10
|
21.95% |
51.308 |
62.571 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_TRIDIAG_ELIM_RAW/5001
|
21.95% |
23.329 |
28.450 |
0.009 |
-0.01% |
0.009 |
|
SingleSource/Benchmarks/Misc/fp-convert
Profile
|
21.86% |
5.867 |
7.150 |
0.000 |
45.75% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_GEN_LIN_RECUR_RAW/44217
|
21.76% |
1088.579 |
1325.447 |
46.428 |
-1.60% |
46.428 |
|
SingleSource/Benchmarks/Shootout/Shootout-random
Profile
|
21.71% |
5.762 |
7.013 |
0.000 |
-0.00% |
0.000 |
|
SingleSource/Benchmarks/Shootout-C++/Shootout-C++-random
Profile
|
21.71% |
5.767 |
7.018 |
0.000 |
0.01% |
0.000 |
|
MultiSource/Benchmarks/TSVC/Packing-dbl/Packing-dbl
Profile
|
21.65% |
29.327 |
35.677 |
0.191 |
0.30% |
0.191 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_multiply_accumulate_runtime_checks_pass<2, double>
|
21.42% |
8.760 |
10.637 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_csa_with_cond_arith_novec_int32_t_
|
19.15% |
479035.363 |
570756.151 |
4913.390 |
-0.17% |
4913.390 |
|
SingleSource/Benchmarks/Adobe-C++/loop_unroll
Profile
|
18.92% |
22.973 |
27.320 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint32_t_To_uint16_t_
|
18.39% |
10867.842 |
12866.214 |
36.809 |
-0.41% |
36.809 |
|
MultiSource/Benchmarks/MiBench/telecomm-gsm/telecomm-gsm
Profile
|
18.34% |
0.583 |
0.690 |
0.000 |
-0.34% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint32_t_To_uint16_t_
|
18.12% |
10873.925 |
12843.947 |
56.694 |
-0.50% |
56.694 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint32_t_To_uint16_t_
|
18.08% |
10873.764 |
12839.482 |
46.695 |
-0.56% |
46.695 |
|
MicroBenchmarks/ImageProcessing/Blur/blur.test:BENCHMARK_GAUSSIAN_BLUR/128
|
17.70% |
3768.739 |
4435.727 |
0.400 |
0.00% |
0.400 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint32_t>/10
|
17.67% |
64.874 |
76.338 |
0.003 |
0.00% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_csa_with_cond_arith_autovec_int32_t_
|
17.64% |
479058.394 |
563566.699 |
5073.907 |
-0.88% |
5073.907 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint32_t>/10
|
17.14% |
43.801 |
51.309 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_multiply_accumulate_runtime_checks_fail<2, double>
|
16.65% |
11.265 |
13.140 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/ImageProcessing/Blur/blur.test:BENCHMARK_GAUSSIAN_BLUR/512
|
16.51% |
70114.358 |
81692.926 |
58.218 |
-0.11% |
58.218 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC4
|
16.39% |
9.386 |
10.924 |
0.009 |
4.96% |
0.009 |
|
MultiSource/Benchmarks/TSVC/StatementReordering-dbl/StatementReordering-dbl
Profile
|
16.33% |
21.245 |
24.714 |
0.141 |
0.13% |
0.141 |
|
MicroBenchmarks/ImageProcessing/Blur/blur.test:BENCHMARK_GAUSSIAN_BLUR/256
|
15.92% |
16872.768 |
19558.258 |
73.538 |
0.09% |
73.538 |
|
MultiSource/Benchmarks/mediabench/gsm/toast/toast
Profile
|
15.49% |
0.076 |
0.088 |
0.000 |
-1.49% |
0.000 |
|
SingleSource/Benchmarks/Adobe-C++/simple_types_loop_invariant
Profile
|
14.85% |
2.674 |
3.071 |
0.002 |
27.15% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint16_t>/10
|
14.64% |
34.419 |
39.457 |
0.019 |
10.63% |
0.019 |
|
MultiSource/Benchmarks/TSVC/Expansion-flt/Expansion-flt
Profile
|
14.55% |
10.830 |
12.405 |
0.080 |
-0.19% |
0.080 |
|
SingleSource/Benchmarks/Stanford/Bubblesort
Profile
|
14.40% |
0.079 |
0.090 |
0.000 |
-0.02% |
0.000 |
|
MultiSource/Benchmarks/TSVC/StatementReordering-flt/StatementReordering-flt
Profile
|
14.16% |
13.712 |
15.654 |
0.055 |
0.07% |
0.055 |
|
SingleSource/Benchmarks/Polybench/stencils/seidel-2d/seidel-2d
Profile
|
14.02% |
103.920 |
118.487 |
0.255 |
0.04% |
0.255 |
|
SingleSource/Benchmarks/Shootout/Shootout-matrix
Profile
|
13.52% |
4.067 |
4.617 |
0.000 |
-1.60% |
0.000 |
|
External/SPEC/CFP2017rate/526.blender_r/526.blender_r
Profile
|
12.84% |
781.895 |
882.316 |
1.187 |
-0.09% |
1.187 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint64_t>/16
|
12.82% |
24.402 |
27.532 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint64_t>/28
|
12.82% |
24.403 |
27.530 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint64_t>/256
|
12.81% |
24.404 |
27.531 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/16
|
12.56% |
98.581 |
110.966 |
0.010 |
2.02% |
0.010 |
|
SingleSource/Benchmarks/Misc/flops-4
Profile
|
12.48% |
3.916 |
4.404 |
0.000 |
-0.01% |
0.000 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/32
|
12.47% |
403.836 |
454.175 |
0.011 |
2.17% |
0.011 |
|
MultiSource/Benchmarks/McCat/18-imp/imp
Profile
|
12.42% |
0.188 |
0.212 |
0.000 |
-0.40% |
0.000 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/16
|
12.22% |
173.424 |
194.612 |
0.005 |
-0.01% |
0.005 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/32
|
11.99% |
866.606 |
970.547 |
0.054 |
0.00% |
0.054 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/256
|
11.95% |
26946.014 |
30164.830 |
19.839 |
2.12% |
19.839 |
|
SingleSource/Benchmarks/Misc/flops-3
Profile
|
11.89% |
8.218 |
9.195 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/128
|
11.86% |
6774.191 |
7577.749 |
3.430 |
2.13% |
3.430 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/64
|
11.66% |
3846.732 |
4295.235 |
1.992 |
-0.03% |
1.992 |
|
MultiSource/Benchmarks/TSVC/Expansion-dbl/Expansion-dbl
Profile
|
11.53% |
19.135 |
21.342 |
0.077 |
0.39% |
0.077 |
|
External/SPEC/CFP2017rate/538.imagick_r/538.imagick_r
Profile
|
11.51% |
244.143 |
272.234 |
0.422 |
0.00% |
0.422 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint8_t>/16
|
11.23% |
111.380 |
123.889 |
0.002 |
-0.50% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint8_t_To_uint32_t_
|
11.23% |
11262.019 |
12526.729 |
44.917 |
-0.28% |
44.917 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint16_t_To_uint32_t_
|
11.19% |
12036.540 |
13383.386 |
57.340 |
-0.37% |
57.340 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/256
|
11.12% |
67501.946 |
75006.930 |
50.091 |
-0.03% |
50.091 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint16_t_To_uint32_t_
|
11.11% |
12035.403 |
13373.107 |
68.035 |
-0.80% |
68.035 |
|
SingleSource/Benchmarks/Adobe-C++/stepanov_abstraction
Profile
|
11.07% |
11.475 |
12.746 |
0.000 |
0.38% |
0.000 |
|
MultiSource/Benchmarks/TSVC/CrossingThresholds-flt/CrossingThresholds-flt
Profile
|
11.07% |
10.011 |
11.119 |
0.058 |
-0.02% |
0.058 |
|
SingleSource/Benchmarks/Stanford/FloatMM
Profile
|
11.06% |
0.448 |
0.498 |
0.000 |
-0.07% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint16_t_To_uint32_t_
|
11.05% |
12040.011 |
13370.755 |
66.196 |
-0.75% |
66.196 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint16_t>/16
|
11.03% |
47.558 |
52.802 |
0.064 |
5.58% |
0.064 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint8_t>/16
|
11.01% |
68.201 |
75.711 |
0.002 |
0.83% |
0.002 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/64
|
10.99% |
1653.259 |
1834.918 |
5.574 |
2.04% |
5.574 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_GEN_LIN_RECUR_LAMBDA/171
|
10.98% |
1.944 |
2.157 |
0.000 |
-0.03% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_GEN_LIN_RECUR_RAW/171
|
10.97% |
1.942 |
2.155 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/128
|
10.95% |
16564.211 |
18377.683 |
6.646 |
-0.08% |
6.646 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint8_t>/10
|
10.92% |
74.462 |
82.593 |
0.006 |
-0.75% |
0.006 |
|
SingleSource/Benchmarks/Misc/matmul_f64_4x4
Profile
|
10.88% |
4.574 |
5.071 |
0.001 |
0.27% |
0.001 |
|
MultiSource/Benchmarks/ASC_Sequoia/CrystalMk/CrystalMk
Profile
|
10.87% |
13.091 |
14.514 |
0.000 |
0.22% |
0.000 |
|
MultiSource/Benchmarks/Rodinia/pathfinder/pathfinder
Profile
|
10.86% |
1.238 |
1.372 |
0.011 |
-0.02% |
0.011 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint8_t_To_uint32_t_
|
10.50% |
11261.769 |
12443.887 |
76.876 |
-0.55% |
76.876 |
|
MicroBenchmarks/ImageProcessing/Blur/blur.test:BENCHMARK_GAUSSIAN_BLUR/1024
|
10.40% |
390716.352 |
431352.290 |
140.456 |
0.03% |
140.456 |
|
MultiSource/Benchmarks/TSVC/Searching-flt/Searching-flt
Profile
|
10.19% |
15.492 |
17.071 |
0.002 |
-0.01% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint8_t_To_uint32_t_
|
10.19% |
11239.121 |
12384.007 |
80.525 |
-1.43% |
80.525 |
|
SingleSource/Benchmarks/Shootout-C++/Shootout-C++-methcall
Profile
|
10.16% |
12.316 |
13.568 |
0.002 |
0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint8_t>/10
|
10.00% |
50.055 |
55.061 |
0.002 |
1.14% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchAutoVec<uint16_t>/127
|
9.89% |
63.201 |
69.454 |
0.005 |
-0.00% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchAutoVec<uint16_t>/65
|
9.86% |
44.427 |
48.805 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_FIR_RAW/171
|
9.85% |
2.221 |
2.440 |
0.000 |
-0.01% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_FIR_LAMBDA/171
|
9.83% |
2.221 |
2.439 |
0.000 |
-0.06% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchAutoVec<uint8_t>/127
|
9.83% |
38.174 |
41.925 |
0.000 |
0.01% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchAutoVec<uint8_t>/65
|
9.77% |
31.921 |
35.039 |
0.001 |
-0.01% |
0.001 |
|
SingleSource/Benchmarks/BenchmarkGame/Large/fasta
Profile
|
9.75% |
1.990 |
2.184 |
0.005 |
-0.04% |
0.005 |
|
MultiSource/Benchmarks/TSVC/NodeSplitting-flt/NodeSplitting-flt
Profile
|
9.46% |
15.994 |
17.507 |
0.049 |
-0.38% |
0.049 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_FIR_LAMBDA/5001
|
9.45% |
73.856 |
80.834 |
0.017 |
-0.02% |
0.017 |
|
MultiSource/Benchmarks/mafft/pairlocalalign
Profile
|
9.45% |
77.366 |
84.673 |
0.346 |
5.66% |
0.346 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_FIR_RAW/5001
|
9.41% |
73.904 |
80.860 |
0.017 |
-0.01% |
0.017 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint64_t>/10
|
9.37% |
20.024 |
21.900 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint16_t>/28
|
9.20% |
108.877 |
118.899 |
0.019 |
1.04% |
0.019 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint32_t>/256
|
9.02% |
940.226 |
1025.074 |
0.216 |
0.47% |
0.216 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchAutoVec<uint32_t>/65
|
8.92% |
70.084 |
76.337 |
0.003 |
0.00% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint16_t>/999
|
8.81% |
1782.157 |
1939.116 |
0.103 |
0.08% |
0.103 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint16_t>/999
|
8.79% |
3540.972 |
3852.397 |
0.433 |
-0.03% |
0.433 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint32_t>/999
|
8.75% |
3614.655 |
3930.839 |
0.118 |
0.11% |
0.118 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint16_t>/256
|
8.74% |
471.261 |
512.450 |
0.027 |
0.12% |
0.027 |
|
MultiSource/Benchmarks/TSVC/Searching-dbl/Searching-dbl
Profile
|
8.74% |
17.716 |
19.264 |
0.012 |
-0.02% |
0.012 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchAutoVec<uint32_t>/127
|
8.73% |
114.520 |
124.523 |
0.004 |
-0.00% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint16_t>/256
|
8.61% |
923.552 |
1003.073 |
0.267 |
-0.24% |
0.267 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint32_t>/51
|
8.53% |
196.777 |
213.568 |
0.155 |
1.48% |
0.155 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint16_t_To_uint64_t_
|
8.52% |
21948.747 |
23818.028 |
9.502 |
0.08% |
9.502 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint32_t>/999
|
8.49% |
1821.728 |
1976.400 |
0.257 |
-0.09% |
0.257 |
|
SingleSource/Benchmarks/Adobe-C++/stepanov_vector
Profile
|
8.49% |
7.235 |
7.849 |
0.000 |
0.71% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint16_t_To_uint64_t_
|
8.47% |
21949.183 |
23807.623 |
18.707 |
-0.12% |
18.707 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint32_t>/256
|
8.45% |
44.425 |
48.180 |
0.003 |
-4.35% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint32_t>/16
|
8.45% |
44.424 |
48.178 |
0.003 |
-4.35% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint32_t>/28
|
8.45% |
44.426 |
48.179 |
0.001 |
-4.35% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint32_t>/51
|
8.45% |
44.425 |
48.178 |
0.005 |
-4.35% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint32_t>/999
|
8.43% |
44.432 |
48.178 |
0.001 |
-4.35% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint16_t_To_uint64_t_
|
8.40% |
21967.841 |
23814.011 |
23.190 |
-0.01% |
23.190 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint16_t>/51
|
8.38% |
193.974 |
210.236 |
0.003 |
0.07% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint16_t>/51
|
8.24% |
106.369 |
115.130 |
0.006 |
0.49% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint16_t>/28
|
8.22% |
45.677 |
49.431 |
0.001 |
-5.39% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint16_t>/10
|
8.22% |
45.676 |
49.429 |
0.001 |
-5.39% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint16_t>/51
|
8.22% |
45.677 |
49.430 |
0.001 |
-5.39% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint16_t>/999
|
8.22% |
45.677 |
49.430 |
0.001 |
-5.39% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint16_t>/16
|
8.21% |
45.677 |
49.429 |
0.001 |
-5.39% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint16_t>/256
|
8.21% |
45.679 |
49.430 |
0.001 |
-5.39% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint16_t_To_uint8_t_
|
8.19% |
4363.809 |
4721.192 |
0.636 |
-0.00% |
0.636 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint16_t_To_uint8_t_
|
8.18% |
4364.015 |
4720.966 |
0.340 |
-0.00% |
0.340 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint32_t>/28
|
8.17% |
99.495 |
107.624 |
0.002 |
-4.45% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint32_t>/256
|
8.16% |
482.435 |
521.821 |
0.016 |
-0.01% |
0.016 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint16_t_To_uint8_t_
|
8.15% |
4364.680 |
4720.506 |
0.504 |
-0.01% |
0.504 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint16_t>/28
|
8.04% |
70.079 |
75.710 |
0.007 |
0.83% |
0.007 |
|
SingleSource/Benchmarks/Linpack/linpack-pc
Profile
|
8.03% |
8.850 |
9.561 |
0.002 |
-0.12% |
0.002 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_GEN_LIN_RECUR_LAMBDA/44217
|
7.87% |
1199.057 |
1293.433 |
16.435 |
-3.10% |
16.435 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_csa_with_cond_arith_novec_uint8_t_
|
7.86% |
495432.381 |
534389.566 |
51.297 |
0.00% |
51.297 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_csa_with_cond_arith_autovec_uint8_t_
|
7.84% |
495554.551 |
534384.795 |
57.027 |
0.00% |
57.027 |
|
MultiSource/Benchmarks/Ptrdist/ks/ks
Profile
|
7.79% |
2.747 |
2.961 |
0.000 |
6.52% |
0.000 |
|
SingleSource/Benchmarks/Misc-C++/Large/sphereflake
Profile
|
7.75% |
18.104 |
19.508 |
0.003 |
-0.30% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC128
|
7.72% |
104.936 |
113.034 |
0.073 |
0.06% |
0.073 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_no_runtime_checks_needed<4, int>
|
7.69% |
8.135 |
8.760 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC127
|
7.67% |
104.977 |
113.024 |
0.107 |
0.13% |
0.107 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC127
|
7.62% |
104.947 |
112.947 |
0.119 |
-0.11% |
0.119 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC127
|
7.60% |
104.979 |
112.959 |
0.066 |
-0.07% |
0.066 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_ADI_LAMBDA/44217
|
7.60% |
14161.935 |
15237.591 |
155.016 |
0.05% |
155.016 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC128
|
7.57% |
104.939 |
112.880 |
0.137 |
-0.10% |
0.137 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC127
|
7.54% |
105.127 |
113.055 |
0.055 |
-0.03% |
0.055 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC128
|
7.53% |
104.985 |
112.893 |
0.150 |
-0.12% |
0.150 |
|
MultiSource/Benchmarks/Bullet/bullet
Profile
|
7.48% |
28.487 |
30.618 |
0.153 |
4.81% |
0.153 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC127
|
7.47% |
105.124 |
112.975 |
0.014 |
-0.08% |
0.014 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC128
|
7.45% |
105.090 |
112.917 |
0.116 |
-0.03% |
0.116 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC128
|
7.42% |
105.083 |
112.884 |
0.149 |
-0.19% |
0.149 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint16_t>/10
|
7.41% |
67.574 |
72.581 |
0.001 |
-5.69% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint64_t>/51
|
7.32% |
51.308 |
55.062 |
0.002 |
-3.30% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint64_t>/999
|
7.31% |
51.311 |
55.063 |
0.002 |
-3.29% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint16_t>/28
|
7.14% |
105.120 |
112.629 |
0.001 |
-6.25% |
0.001 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_FLOYD_DITHER/256
|
7.14% |
1491.759 |
1598.300 |
1.537 |
1.11% |
1.537 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C/CoMD/CoMD
Profile
|
7.08% |
9.393 |
10.058 |
0.010 |
0.04% |
0.010 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC64
|
6.98% |
53.814 |
57.570 |
0.004 |
-0.00% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC63
|
6.98% |
53.817 |
57.571 |
0.002 |
0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC63
|
6.97% |
53.815 |
57.567 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC64
|
6.97% |
53.816 |
57.567 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC64
|
6.97% |
53.815 |
57.564 |
0.123 |
0.00% |
0.123 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC64
|
6.97% |
53.817 |
57.566 |
0.004 |
-0.00% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC63
|
6.96% |
53.821 |
57.568 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC64
|
6.96% |
53.821 |
57.569 |
0.002 |
0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC63
|
6.95% |
53.824 |
57.564 |
0.003 |
-0.01% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC63
|
6.92% |
53.841 |
57.566 |
0.002 |
0.00% |
0.002 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_FLOYD_DITHER/128
|
6.90% |
381.633 |
407.975 |
0.308 |
0.56% |
0.308 |
|
MultiSource/Benchmarks/Trimaran/enc-rc4/enc-rc4
Profile
|
6.86% |
2.728 |
2.915 |
0.000 |
0.05% |
0.000 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_xor_runtime_checks_pass<16, int>
|
6.79% |
27.538 |
29.409 |
0.001 |
0.01% |
0.001 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_runtime_checks_pass<16, int>
|
6.77% |
36.921 |
39.420 |
0.002 |
0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint32_t>/16
|
6.72% |
74.462 |
79.465 |
0.003 |
-4.87% |
0.003 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_FLOYD_DITHER/512
|
6.71% |
5794.734 |
6183.782 |
16.931 |
0.48% |
16.931 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC32
|
6.67% |
28.157 |
30.036 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC31
|
6.67% |
28.157 |
30.035 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC31
|
6.67% |
28.158 |
30.035 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC31
|
6.67% |
28.159 |
30.036 |
0.002 |
0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC32
|
6.67% |
28.158 |
30.035 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC32
|
6.66% |
28.158 |
30.035 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint32_t>/10
|
6.66% |
18.772 |
20.022 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC32
|
6.66% |
28.157 |
30.033 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC32
|
6.66% |
28.158 |
30.033 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC31
|
6.66% |
28.159 |
30.035 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC31
|
6.66% |
28.160 |
30.035 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint8_t>/999
|
6.53% |
4745.714 |
5055.698 |
0.235 |
-0.03% |
0.235 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint16_t>/10
|
6.52% |
20.650 |
21.996 |
0.325 |
-1.12% |
0.325 |
|
SingleSource/Benchmarks/Shootout-C++/Shootout-C++-fibo
Profile
|
6.50% |
5.114 |
5.446 |
0.001 |
-0.00% |
0.001 |
|
MultiSource/Benchmarks/TSVC/InductionVariable-dbl/InductionVariable-dbl
Profile
|
6.49% |
17.805 |
18.960 |
0.061 |
-0.64% |
0.061 |
|
SingleSource/Benchmarks/Shootout/Shootout-fib2
Profile
|
6.49% |
5.095 |
5.426 |
0.001 |
0.16% |
0.001 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C++/miniFE/miniFE
Profile
|
6.48% |
15.757 |
16.778 |
0.062 |
-6.00% |
0.062 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint8_t>/16
|
6.45% |
19.397 |
20.648 |
0.000 |
3.12% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint8_t>/10
|
6.45% |
19.397 |
20.648 |
0.001 |
3.11% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint16_t>/16
|
6.40% |
78.217 |
83.219 |
0.001 |
-6.67% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint8_t>/256
|
6.37% |
628.251 |
668.252 |
0.011 |
0.10% |
0.011 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint64_t>/10
|
6.36% |
28.170 |
29.961 |
0.090 |
-2.29% |
0.090 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_runtime_checks_fail<16, int>
|
6.35% |
39.420 |
41.922 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint32_t_To_uint8_t_
|
6.33% |
13274.566 |
14115.504 |
46.369 |
-0.63% |
46.369 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint8_t>/256
|
6.30% |
1229.527 |
1306.986 |
0.298 |
-0.06% |
0.298 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint8_t>/999
|
6.29% |
2391.161 |
2541.672 |
0.213 |
-0.05% |
0.213 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint32_t>/51
|
6.26% |
139.557 |
148.292 |
0.002 |
-5.01% |
0.002 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_xor_runtime_checks_fail<16, int>
|
6.25% |
30.034 |
31.911 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint32_t>/256
|
6.22% |
663.291 |
704.528 |
0.021 |
-5.46% |
0.021 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint32_t>/999
|
6.21% |
2533.984 |
2691.362 |
0.092 |
-5.46% |
0.092 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint32_t_To_uint8_t_
|
6.20% |
13278.186 |
14101.968 |
69.177 |
-0.78% |
69.177 |
|
MultiSource/Benchmarks/PAQ8p/paq8p
Profile
|
6.20% |
192.776 |
204.725 |
0.385 |
1.74% |
0.385 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint16_t>/999
|
6.12% |
2535.284 |
2690.569 |
0.327 |
-5.54% |
0.327 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint32_t>/256
|
6.12% |
357.290 |
379.158 |
0.015 |
-5.33% |
0.015 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint16_t>/999
|
6.12% |
1294.188 |
1373.392 |
0.089 |
-5.36% |
0.089 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint16_t>/256
|
6.12% |
663.318 |
703.906 |
0.017 |
-5.54% |
0.017 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint8_t>/999
|
6.10% |
2535.360 |
2690.002 |
0.054 |
-5.54% |
0.054 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint32_t>/51
|
6.08% |
152.674 |
161.951 |
0.046 |
-5.19% |
0.046 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint32_t>/28
|
6.07% |
113.254 |
120.133 |
0.003 |
-0.16% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_single_load<uint16_t>/51
|
6.06% |
20.649 |
21.900 |
0.001 |
2.94% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_single_load<uint16_t>/999
|
6.06% |
20.650 |
21.901 |
0.000 |
2.94% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_single_load<uint16_t>/256
|
6.06% |
20.649 |
21.899 |
0.000 |
2.93% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_single_load<uint16_t>/28
|
6.05% |
20.650 |
21.899 |
0.001 |
2.94% |
0.001 |
|
MultiSource/Benchmarks/SciMark2-C/scimark2
Profile
|
5.99% |
133.694 |
141.699 |
0.060 |
-14.99% |
0.060 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint32_t_To_uint8_t_
|
5.97% |
13286.370 |
14079.784 |
111.117 |
-0.89% |
111.117 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint32_t>/999
|
5.96% |
1294.375 |
1371.584 |
0.040 |
-5.65% |
0.040 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint8_t>/256
|
5.96% |
356.667 |
377.933 |
0.004 |
-5.47% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint16_t>/256
|
5.95% |
357.284 |
378.544 |
0.005 |
-5.47% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint8_t>/256
|
5.94% |
663.909 |
703.315 |
0.001 |
-5.54% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint8_t>/999
|
5.87% |
1296.685 |
1372.772 |
0.559 |
-5.37% |
0.559 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint8_t>/51
|
5.78% |
251.810 |
266.377 |
0.093 |
-0.15% |
0.093 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint8_t>/28
|
5.78% |
142.040 |
150.251 |
0.569 |
0.25% |
0.569 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint32_t_To_uint8_t_
|
5.78% |
9750.891 |
10314.335 |
65.182 |
-1.12% |
65.182 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint8_t>/51
|
5.78% |
138.289 |
146.278 |
0.034 |
0.85% |
0.034 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint16_t>/51
|
5.73% |
152.688 |
161.432 |
0.001 |
-5.50% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint32_t>/51
|
5.69% |
110.118 |
116.382 |
0.002 |
-0.04% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint32_t_To_uint8_t_
|
5.68% |
9779.214 |
10334.697 |
53.371 |
-0.98% |
53.371 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint32_t>/51
|
5.64% |
99.491 |
105.105 |
0.005 |
-4.57% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_single_load<uint8_t>/28
|
5.55% |
22.526 |
23.776 |
0.001 |
8.54% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_single_load<uint8_t>/256
|
5.55% |
22.526 |
23.776 |
0.001 |
8.54% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_single_load<uint8_t>/51
|
5.55% |
22.526 |
23.776 |
0.001 |
8.54% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_single_load<uint8_t>/999
|
5.54% |
22.529 |
23.777 |
0.001 |
8.54% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_PRESSURE_CALC_RAW/171
|
5.52% |
1.460 |
1.540 |
0.000 |
-0.02% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_PRESSURE_CALC_LAMBDA/171
|
5.51% |
1.460 |
1.541 |
0.000 |
-0.00% |
0.000 |
|
SingleSource/Benchmarks/Misc-C++/Large/ray
Profile
|
5.51% |
9.302 |
9.814 |
0.001 |
-0.23% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint16_t>/51
|
5.44% |
148.953 |
157.061 |
0.003 |
-7.20% |
0.003 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_GEN_LIN_RECUR_LAMBDA/5001
|
5.34% |
83.000 |
87.433 |
0.327 |
-0.09% |
0.327 |
|
MultiSource/Benchmarks/MallocBench/cfrac/cfrac
Profile
|
5.30% |
2.645 |
2.785 |
0.001 |
0.02% |
0.001 |
|
SingleSource/Benchmarks/Misc/flops
Profile
|
5.29% |
13.433 |
14.143 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint16_t>/16
|
5.27% |
27.532 |
28.983 |
0.497 |
-2.16% |
0.497 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint32_t>/16
|
5.26% |
83.225 |
87.600 |
0.003 |
-5.41% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopFrom_uint32_t_To_uint8_t_
|
5.23% |
9822.431 |
10335.935 |
59.352 |
-1.09% |
59.352 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint16_t>/10
|
5.22% |
71.959 |
75.716 |
0.003 |
-7.27% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint32_t>/10
|
5.19% |
32.119 |
33.788 |
0.000 |
21.31% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint32_t>/28
|
5.18% |
72.579 |
76.339 |
0.003 |
0.00% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint64_t_To_uint32_t_
|
5.13% |
20961.845 |
22037.545 |
41.439 |
-0.18% |
41.439 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_FIR_LAMBDA/44217
|
5.09% |
737.163 |
774.689 |
8.373 |
-0.71% |
8.373 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_GEN_LIN_RECUR_RAW/5001
|
5.09% |
82.939 |
87.160 |
0.257 |
0.30% |
0.257 |
|
MultiSource/Benchmarks/TSVC/InductionVariable-flt/InductionVariable-flt
Profile
|
5.09% |
9.474 |
9.956 |
0.066 |
-0.79% |
0.066 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint64_t_To_uint32_t_
|
5.01% |
20967.213 |
22016.810 |
44.739 |
-0.21% |
44.739 |
|
SingleSource/Benchmarks/Misc/ReedSolomon
Profile
|
5.01% |
21.005 |
22.056 |
0.002 |
-0.01% |
0.002 |
|
SingleSource/Benchmarks/McGill/queens
Profile
|
4.98% |
2.771 |
2.909 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint8_t>/51
|
4.98% |
100.130 |
105.118 |
0.003 |
-5.08% |
0.003 |
|
External/SPEC/CFP2017rate/544.nab_r/544.nab_r
Profile
|
4.97% |
436.808 |
458.523 |
0.110 |
0.71% |
0.110 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint16_t>/16
|
4.96% |
88.225 |
92.605 |
0.002 |
-7.50% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint64_t>/16
|
4.96% |
35.678 |
37.448 |
0.072 |
-1.55% |
0.072 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint64_t_To_uint32_t_
|
4.92% |
20968.657 |
22001.066 |
53.330 |
-0.19% |
53.330 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint8_t>/51
|
4.89% |
153.302 |
160.806 |
0.008 |
-5.52% |
0.008 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint8_t>/28
|
4.89% |
89.477 |
93.854 |
0.003 |
1.00% |
0.003 |
|
MultiSource/Benchmarks/sim/sim
Profile
|
4.89% |
17.527 |
18.384 |
0.009 |
131.88% |
0.009 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint32_t>/28
|
4.87% |
128.277 |
134.526 |
0.001 |
-5.50% |
0.001 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C++/HPCCG/HPCCG
Profile
|
4.86% |
4.081 |
4.280 |
0.050 |
-8.01% |
0.050 |
|
SingleSource/Benchmarks/BenchmarkGame/spectral-norm
Profile
|
4.82% |
1.540 |
1.614 |
0.000 |
-0.04% |
0.000 |
|
SingleSource/Benchmarks/Misc-C++/bigfib
Profile
|
4.77% |
1.253 |
1.312 |
0.006 |
1.32% |
0.006 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_ADI_LAMBDA/171
|
4.76% |
30.991 |
32.465 |
0.042 |
-0.20% |
0.042 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, GreaterThanZero, Last>
|
4.70% |
33967.718 |
35562.795 |
97.943 |
4.68% |
97.943 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_ORDERED_DITHER/512/3
|
4.69% |
34937.635 |
36576.300 |
36.160 |
0.02% |
36.160 |
|
SingleSource/Benchmarks/Misc/flops-1
Profile
|
4.64% |
8.414 |
8.804 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint32_t>/51
|
4.58% |
218.389 |
228.386 |
0.016 |
-5.56% |
0.016 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint16_t>/51
|
4.58% |
100.508 |
105.107 |
0.006 |
-4.01% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint16_t>/28
|
4.56% |
137.035 |
143.287 |
0.003 |
-7.85% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint8_t>/28
|
4.52% |
109.555 |
114.503 |
0.004 |
-6.63% |
0.004 |
|
MultiSource/Benchmarks/TSVC/NodeSplitting-dbl/NodeSplitting-dbl
Profile
|
4.51% |
22.109 |
23.106 |
0.118 |
-1.28% |
0.118 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint32_t>/256
|
4.51% |
525.066 |
548.731 |
0.041 |
-5.55% |
0.041 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_ORDERED_DITHER/256/3
|
4.50% |
8925.437 |
9326.679 |
7.816 |
-0.04% |
7.816 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint32_t>/10
|
4.37% |
39.740 |
41.476 |
0.004 |
0.43% |
0.004 |
|
MultiSource/Benchmarks/FreeBench/fourinarow/fourinarow
Profile
|
4.36% |
0.647 |
0.675 |
0.000 |
-0.29% |
0.000 |
|
MicroBenchmarks/ImageProcessing/AnisotropicDiffusion/AnisotropicDiffusion.test:BENCHMARK_ANISTROPIC_DIFFUSION/64
|
4.34% |
8827.889 |
9210.626 |
0.268 |
0.12% |
0.268 |
|
SingleSource/Benchmarks/Misc/dt
Profile
|
4.34% |
3.869 |
4.037 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/ImageProcessing/AnisotropicDiffusion/AnisotropicDiffusion.test:BENCHMARK_ANISTROPIC_DIFFUSION/32
|
4.33% |
1935.689 |
2019.548 |
0.361 |
0.19% |
0.361 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_ORDERED_DITHER/128/3
|
4.30% |
2194.033 |
2288.453 |
21.018 |
-0.17% |
21.018 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_ORDERED_DITHER/512/4
|
4.27% |
33283.083 |
34703.481 |
9.420 |
0.08% |
9.420 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint16_t>/51
|
4.27% |
234.643 |
244.655 |
0.004 |
-8.11% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint32_t>/256
|
4.25% |
984.365 |
1026.190 |
0.007 |
-5.64% |
0.007 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_ADI_LAMBDA/5001
|
4.20% |
1667.223 |
1737.232 |
21.941 |
1.29% |
21.941 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint32_t>/999
|
4.20% |
1931.906 |
2013.001 |
0.123 |
-5.58% |
0.123 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_ORDERED_DITHER/512/8
|
4.18% |
33349.565 |
34745.231 |
26.128 |
-0.07% |
26.128 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint16_t>/256
|
4.18% |
566.358 |
590.048 |
0.036 |
-8.22% |
0.036 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint32_t>/999
|
4.12% |
3787.931 |
3944.062 |
0.363 |
-5.97% |
0.363 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint16_t>/999
|
4.07% |
2084.424 |
2169.357 |
0.020 |
-8.28% |
0.020 |
|
SingleSource/Benchmarks/Polybench/stencils/jacobi-2d/jacobi-2d
Profile
|
4.06% |
40.810 |
42.468 |
0.094 |
0.28% |
0.094 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint8_t>/51
|
4.06% |
153.935 |
160.179 |
0.009 |
-7.37% |
0.009 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint8_t>/28
|
4.05% |
46.302 |
48.179 |
0.000 |
-6.63% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint8_t>/999
|
4.05% |
46.303 |
48.179 |
0.000 |
-6.68% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint8_t>/256
|
4.05% |
46.303 |
48.178 |
0.001 |
-6.66% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint8_t>/51
|
4.04% |
46.309 |
48.179 |
0.002 |
-6.59% |
0.002 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_ORDERED_DITHER/256/8
|
4.04% |
8533.329 |
8877.763 |
12.605 |
0.16% |
12.605 |
|
MultiSource/Benchmarks/ASC_Sequoia/AMGmk/AMGmk
Profile
|
4.02% |
38.397 |
39.942 |
0.041 |
-8.09% |
0.041 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint8_t_To_uint64_t_
|
4.02% |
21809.840 |
22686.975 |
22.900 |
-0.13% |
22.900 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC16
|
4.00% |
15.643 |
16.269 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC16
|
4.00% |
15.644 |
16.270 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC15
|
4.00% |
15.643 |
16.269 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC15
|
4.00% |
15.643 |
16.269 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC15
|
4.00% |
15.643 |
16.269 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC15
|
4.00% |
15.643 |
16.268 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC16
|
4.00% |
15.644 |
16.269 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC16
|
3.99% |
15.645 |
16.269 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC16
|
3.99% |
15.645 |
16.269 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC15
|
3.98% |
15.645 |
16.268 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint8_t_To_uint64_t_
|
3.98% |
21818.944 |
22687.458 |
26.487 |
-0.16% |
26.487 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_DEL_DOT_VEC_2D_LAMBDA/2
|
3.97% |
2.669 |
2.775 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_ORDERED_DITHER/256/4
|
3.96% |
8525.345 |
8862.690 |
12.604 |
-0.04% |
12.604 |
|
SingleSource/Benchmarks/SmallPT/smallpt
Profile
|
3.95% |
27.373 |
28.455 |
0.003 |
0.01% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint16_t>/256
|
3.94% |
1064.371 |
1106.283 |
0.006 |
-8.39% |
0.006 |
|
MicroBenchmarks/LoopInterchange/LoopInterchange.test:BENCHMARK_LI1
|
3.90% |
1567.856 |
1628.937 |
0.693 |
0.20% |
0.693 |
|
MultiSource/Benchmarks/FreeBench/distray/distray
Profile
|
3.88% |
0.408 |
0.424 |
0.000 |
0.03% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint64_t_To_uint8_t_
|
3.88% |
31139.216 |
32347.170 |
29.852 |
0.04% |
29.852 |
|
MicroBenchmarks/ImageProcessing/BilateralFiltering/BilateralFilter.test:BENCHMARK_BILATERAL_FILTER/16/2
|
3.87% |
124.547 |
129.368 |
0.027 |
-0.00% |
0.027 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_DISC_ORD_RAW/44217
|
3.86% |
14159.515 |
14706.304 |
82.793 |
-0.21% |
82.793 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint64_t_To_uint8_t_
|
3.86% |
31140.731 |
32343.041 |
30.346 |
-0.00% |
30.346 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint64_t_To_uint8_t_
|
3.85% |
31140.645 |
32339.045 |
32.693 |
0.01% |
32.693 |
|
SingleSource/Benchmarks/Misc/flops-8
Profile
|
3.83% |
1.900 |
1.973 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint16_t>/999
|
3.82% |
4099.728 |
4256.196 |
0.598 |
-8.41% |
0.598 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint16_t>/10
|
3.79% |
40.992 |
42.547 |
0.008 |
-11.69% |
0.008 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_DEL_DOT_VEC_2D_LAMBDA/1
|
3.78% |
219.064 |
227.335 |
0.078 |
-0.04% |
0.078 |
|
MicroBenchmarks/ImageProcessing/BilateralFiltering/BilateralFilter.test:BENCHMARK_BILATERAL_FILTER/32/2
|
3.76% |
571.715 |
593.215 |
0.051 |
-0.00% |
0.051 |
|
MultiSource/Benchmarks/TSVC/Reductions-flt/Reductions-flt
Profile
|
3.76% |
2.726 |
2.828 |
0.022 |
-0.07% |
0.022 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_COUPLE_RAW/2
|
3.76% |
7.790 |
8.083 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC1
|
3.76% |
33.169 |
34.415 |
0.001 |
1.85% |
0.001 |
|
SingleSource/Benchmarks/BenchmarkGame/n-body
Profile
|
3.73% |
3.096 |
3.212 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint32_t>/16
|
3.72% |
44.641 |
46.302 |
0.007 |
17.10% |
0.007 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint8_t>/256
|
3.72% |
586.980 |
608.813 |
0.042 |
-8.08% |
0.042 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint8_t>/999
|
3.72% |
2165.181 |
2245.646 |
0.074 |
-8.09% |
0.074 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C/SimpleMOC/SimpleMOC
Profile
|
3.68% |
7.200 |
7.465 |
0.045 |
-0.32% |
0.045 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_ORDERED_DITHER/128/8
|
3.68% |
2095.596 |
2172.618 |
19.896 |
-0.05% |
19.896 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint8_t>/999
|
3.64% |
4254.956 |
4409.980 |
0.212 |
-8.22% |
0.212 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint8_t>/10
|
3.64% |
47.969 |
49.715 |
0.009 |
0.76% |
0.009 |
|
MicroBenchmarks/ImageProcessing/AnisotropicDiffusion/AnisotropicDiffusion.test:BENCHMARK_ANISTROPIC_DIFFUSION/256
|
3.63% |
165055.635 |
171053.666 |
359.731 |
-0.48% |
359.731 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_ORDERED_DITHER/128/4
|
3.62% |
2091.751 |
2167.417 |
21.823 |
-0.15% |
21.823 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_EOS_LAMBDA/5001
|
3.59% |
39.465 |
40.882 |
0.237 |
-0.30% |
0.237 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC16
|
3.58% |
51.313 |
53.152 |
0.010 |
2.33% |
0.010 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC15
|
3.56% |
51.311 |
53.138 |
0.023 |
2.30% |
0.023 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint8_t>/256
|
3.55% |
1103.922 |
1143.164 |
0.106 |
-8.24% |
0.106 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC15
|
3.55% |
51.313 |
53.136 |
0.006 |
2.30% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC16
|
3.52% |
51.312 |
53.117 |
0.024 |
2.26% |
0.024 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_COUPLE_RAW/0
|
3.49% |
5939.969 |
6146.988 |
2.793 |
0.01% |
2.793 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC16
|
3.45% |
51.312 |
53.080 |
0.025 |
2.20% |
0.025 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_DEL_DOT_VEC_2D_RAW/2
|
3.42% |
2.668 |
2.760 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetBLambdaLoops/lcalsBLambda.test:BM_IF_QUAD_LAMBDA/171
|
3.37% |
4.105 |
4.243 |
0.000 |
-0.01% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_DEL_DOT_VEC_2D_RAW/1
|
3.36% |
219.256 |
226.630 |
0.076 |
0.01% |
0.076 |
|
MicroBenchmarks/ImageProcessing/BilateralFiltering/BilateralFilter.test:BENCHMARK_BILATERAL_FILTER/64/2
|
3.33% |
2455.815 |
2537.704 |
0.070 |
-0.54% |
0.070 |
|
SingleSource/Benchmarks/Dhrystone/fldry
Profile
|
3.30% |
0.944 |
0.975 |
0.000 |
-0.03% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint8_t_To_uint64_t_
|
3.24% |
21976.959 |
22689.299 |
20.542 |
-0.19% |
20.542 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint64_t>/28
|
3.22% |
50.692 |
52.326 |
0.077 |
-1.38% |
0.077 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_MAT_X_MAT_RAW/171
|
3.14% |
2396.124 |
2471.327 |
6.934 |
-0.33% |
6.934 |
|
MicroBenchmarks/harris/harris.test:BENCHMARK_HARRIS/2048/2048
|
3.12% |
215391.527 |
222104.388 |
1858.440 |
-1.46% |
1858.440 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint64_t>/51
|
3.10% |
181.465 |
187.084 |
0.007 |
-4.78% |
0.007 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint32_t>/16
|
3.07% |
54.762 |
56.445 |
0.019 |
0.23% |
0.019 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint8_t>/51
|
3.06% |
242.232 |
249.654 |
0.004 |
-8.38% |
0.004 |
|
SingleSource/Benchmarks/Misc/pi
Profile
|
3.06% |
1.808 |
1.863 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_COUPLE_LAMBDA/2
|
3.01% |
7.821 |
8.057 |
0.000 |
-0.02% |
0.000 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_ORDERED_DITHER/256/2
|
2.99% |
8494.707 |
8748.699 |
27.079 |
-0.05% |
27.079 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC16
|
2.97% |
20.661 |
21.274 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint64_t_To_uint16_t_
|
2.96% |
25952.367 |
26720.372 |
83.801 |
0.01% |
83.801 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint64_t_To_uint16_t_
|
2.96% |
25952.946 |
26720.194 |
86.122 |
-0.02% |
86.122 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_ORDERED_DITHER/512/2
|
2.92% |
33274.702 |
34247.856 |
68.054 |
-0.09% |
68.054 |
|
External/SPEC/CFP2017rate/511.povray_r/511.povray_r
Profile
|
2.92% |
27.560 |
28.364 |
0.025 |
-0.94% |
0.025 |
|
SingleSource/Benchmarks/Misc/mandel
Profile
|
2.92% |
3.206 |
3.300 |
0.000 |
-0.00% |
0.000 |
|
SingleSource/Benchmarks/Misc/perlin
Profile
|
2.91% |
8.174 |
8.412 |
0.000 |
-0.01% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint64_t_To_uint16_t_
|
2.89% |
25978.573 |
26730.048 |
80.192 |
0.00% |
80.192 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC31
|
2.84% |
88.233 |
90.741 |
0.001 |
1.38% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC31
|
2.84% |
88.229 |
90.731 |
0.006 |
1.37% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC32
|
2.83% |
88.238 |
90.733 |
0.004 |
1.35% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1BigLoopWithReductionTC31
|
2.81% |
88.231 |
90.713 |
0.012 |
1.36% |
0.012 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC32
|
2.81% |
88.233 |
90.712 |
0.012 |
1.35% |
0.012 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC31
|
2.81% |
88.233 |
90.711 |
0.013 |
1.35% |
0.013 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC32
|
2.81% |
88.230 |
90.706 |
0.024 |
1.35% |
0.024 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC31
|
2.81% |
88.240 |
90.716 |
0.010 |
1.13% |
0.010 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC32
|
2.80% |
88.239 |
90.713 |
0.011 |
1.34% |
0.011 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC31
|
2.80% |
88.232 |
90.705 |
0.016 |
1.31% |
0.016 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1BigLoopWithReductionTC32
|
2.78% |
88.231 |
90.683 |
0.024 |
1.22% |
0.024 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC32
|
2.78% |
88.230 |
90.681 |
0.026 |
1.32% |
0.026 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC31
|
2.77% |
88.232 |
90.678 |
0.027 |
1.26% |
0.027 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC32
|
2.77% |
88.233 |
90.677 |
0.032 |
1.26% |
0.032 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint8_t>/16
|
2.76% |
67.276 |
69.132 |
0.004 |
0.58% |
0.004 |
|
MicroBenchmarks/LCALS/SubsetBLambdaLoops/lcalsBLambda.test:BM_IF_QUAD_LAMBDA/5001
|
2.74% |
127.783 |
131.287 |
0.178 |
-0.04% |
0.178 |
|
MicroBenchmarks/LCALS/SubsetBRawLoops/lcalsBRaw.test:BM_IF_QUAD_RAW/171
|
2.71% |
4.105 |
4.216 |
0.000 |
-0.01% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_COUPLE_LAMBDA/0
|
2.71% |
5961.175 |
6122.706 |
7.090 |
0.03% |
7.090 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_PIC_2D_RAW/171
|
2.70% |
13.295 |
13.655 |
0.064 |
-0.07% |
0.064 |
|
SingleSource/Benchmarks/Misc/flops-6
Profile
|
2.69% |
1.802 |
1.850 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/ImageProcessing/AnisotropicDiffusion/AnisotropicDiffusion.test:BENCHMARK_ANISTROPIC_DIFFUSION/128
|
2.66% |
38498.426 |
39522.940 |
8.334 |
0.08% |
8.334 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint8_t>/28
|
2.64% |
140.814 |
144.538 |
0.001 |
-8.51% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint16_t>/16
|
2.64% |
56.087 |
57.566 |
0.003 |
-14.02% |
0.003 |
|
External/SPEC/CFP2017rate/508.namd_r/508.namd_r
Profile
|
2.59% |
181.704 |
186.408 |
0.681 |
-0.51% |
0.681 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_IMP_HYDRO_2D_RAW/5001
|
2.51% |
1635.496 |
1676.590 |
4.285 |
-0.04% |
4.285 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, EqZero, First>
|
2.48% |
3211.035 |
3290.736 |
4.566 |
2.48% |
4.566 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_DEL_DOT_VEC_2D_RAW/0
|
2.46% |
1429.969 |
1465.196 |
4.070 |
0.13% |
4.070 |
|
MultiSource/Benchmarks/tramp3d-v4/tramp3d-v4
Profile
|
2.45% |
0.990 |
1.014 |
0.002 |
-0.02% |
0.002 |
|
MicroBenchmarks/ImageProcessing/BilateralFiltering/BilateralFilter.test:BENCHMARK_BILATERAL_FILTER/16/4
|
2.39% |
372.781 |
381.688 |
0.021 |
-0.00% |
0.021 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_EOS_LAMBDA/171
|
2.32% |
1.131 |
1.157 |
0.000 |
-0.01% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC64
|
2.32% |
162.074 |
165.837 |
0.009 |
0.03% |
0.009 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC63
|
2.32% |
162.081 |
165.843 |
0.005 |
0.26% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC63
|
2.32% |
162.076 |
165.835 |
0.007 |
0.01% |
0.007 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC63
|
2.32% |
162.084 |
165.838 |
0.002 |
0.19% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC64
|
2.31% |
162.078 |
165.826 |
0.007 |
0.27% |
0.007 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC64
|
2.31% |
162.080 |
165.827 |
0.008 |
0.12% |
0.008 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1BigLoopWithReductionTC64
|
2.31% |
162.083 |
165.830 |
0.009 |
0.27% |
0.009 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC63
|
2.31% |
162.085 |
165.827 |
0.017 |
0.23% |
0.017 |
|
MultiSource/Benchmarks/Rodinia/hotspot/hotspot
Profile
|
2.31% |
2.238 |
2.289 |
0.013 |
-0.96% |
0.013 |
|
SingleSource/Benchmarks/Misc/whetstone
Profile
|
2.31% |
2.888 |
2.955 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC64
|
2.30% |
162.094 |
165.830 |
0.006 |
0.24% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC64
|
2.28% |
162.079 |
165.776 |
0.027 |
0.24% |
0.027 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC63
|
2.28% |
162.092 |
165.784 |
0.024 |
0.09% |
0.024 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC63
|
2.28% |
162.079 |
165.769 |
0.035 |
0.09% |
0.035 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_HYDRO_2D_LAMBDA/171
|
2.28% |
255.663 |
261.483 |
0.598 |
0.01% |
0.598 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC64
|
2.28% |
162.081 |
165.770 |
0.034 |
0.04% |
0.034 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1BigLoopWithReductionTC63
|
2.28% |
162.079 |
165.766 |
0.035 |
0.33% |
0.035 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_DEL_DOT_VEC_2D_LAMBDA/0
|
2.27% |
1431.690 |
1464.202 |
1.857 |
0.02% |
1.857 |
|
MultiSource/Benchmarks/ASCI_Purple/SMG2000/smg2000
Profile
|
2.25% |
17.522 |
17.916 |
0.013 |
-0.04% |
0.013 |
|
MultiSource/Benchmarks/Olden/power/power
Profile
|
2.20% |
3.663 |
3.744 |
0.000 |
-0.01% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint8_t>/10
|
2.17% |
32.673 |
33.382 |
0.056 |
-19.18% |
0.056 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint8_t>/10
|
2.17% |
33.466 |
34.192 |
0.226 |
2.46% |
0.226 |
|
MicroBenchmarks/LCALS/SubsetBRawLoops/lcalsBRaw.test:BM_IF_QUAD_RAW/5001
|
2.16% |
127.718 |
130.475 |
0.311 |
-0.01% |
0.311 |
|
SingleSource/Benchmarks/CoyoteBench/huffbench
Profile
|
2.13% |
49.840 |
50.902 |
0.009 |
0.52% |
0.009 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_COUPLE_LAMBDA/1
|
2.11% |
991.808 |
1012.733 |
2.507 |
-0.02% |
2.507 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint8_t>/16
|
2.11% |
47.560 |
48.563 |
0.026 |
-19.19% |
0.026 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint16_t>/28
|
2.08% |
85.811 |
87.598 |
0.015 |
-16.17% |
0.015 |
|
MicroBenchmarks/LCALS/SubsetBRawLoops/lcalsBRaw.test:BM_IF_QUAD_RAW/44217
|
2.05% |
1334.157 |
1361.545 |
5.025 |
0.84% |
5.025 |
|
External/SPEC/CFP2017rate/519.lbm_r/519.lbm_r
Profile
|
2.04% |
207.934 |
212.167 |
0.844 |
0.23% |
0.844 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1BigLoopWithReductionTC127
|
2.02% |
309.793 |
316.056 |
0.004 |
0.04% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC128
|
2.02% |
309.799 |
316.058 |
0.009 |
0.04% |
0.009 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC127
|
2.02% |
309.790 |
316.046 |
0.012 |
0.09% |
0.012 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC128
|
2.02% |
309.796 |
316.052 |
0.011 |
-0.00% |
0.011 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC127
|
2.02% |
309.810 |
316.060 |
0.039 |
0.03% |
0.039 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC127
|
2.01% |
309.804 |
316.046 |
0.010 |
0.11% |
0.010 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC128
|
2.01% |
309.804 |
316.037 |
0.010 |
0.12% |
0.010 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC127
|
2.01% |
309.803 |
316.033 |
0.022 |
0.08% |
0.022 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC127
|
2.01% |
309.821 |
316.045 |
0.017 |
0.03% |
0.017 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC127
|
2.01% |
309.814 |
316.033 |
0.027 |
0.12% |
0.027 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC128
|
2.00% |
309.847 |
316.050 |
0.015 |
0.13% |
0.015 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1BigLoopWithReductionTC128
|
2.00% |
309.856 |
316.041 |
0.012 |
0.04% |
0.012 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint8_t>/28
|
1.98% |
63.198 |
64.447 |
0.001 |
1.98% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_HYDRO_2D_RAW/171
|
1.97% |
256.211 |
261.260 |
0.933 |
-0.06% |
0.933 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC128
|
1.96% |
309.815 |
315.898 |
0.076 |
0.06% |
0.076 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC128
|
1.96% |
309.810 |
315.893 |
0.073 |
0.02% |
0.073 |
|
SingleSource/Benchmarks/Misc/flops-5
Profile
|
1.93% |
2.535 |
2.584 |
0.000 |
-0.01% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1BigLoopWithReductionTC15
|
1.90% |
51.316 |
52.292 |
0.321 |
0.68% |
0.321 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC7
|
1.89% |
33.164 |
33.792 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1BigLoopWithReductionTC7
|
1.89% |
33.165 |
33.793 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint32_t>/28
|
1.89% |
84.834 |
86.438 |
0.005 |
0.10% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC2
|
1.89% |
33.163 |
33.790 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC3
|
1.89% |
33.163 |
33.790 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC7
|
1.89% |
33.165 |
33.791 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC4
|
1.89% |
33.163 |
33.790 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC8
|
1.89% |
33.164 |
33.790 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC4
|
1.89% |
33.163 |
33.789 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC4
|
1.89% |
33.164 |
33.789 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC1
|
1.89% |
33.164 |
33.790 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC3
|
1.89% |
33.164 |
33.789 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1BigLoopWithReductionTC3
|
1.89% |
33.163 |
33.788 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC4
|
1.89% |
33.165 |
33.790 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC7
|
1.89% |
33.165 |
33.791 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC2
|
1.89% |
33.165 |
33.790 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC1
|
1.88% |
33.165 |
33.790 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC8
|
1.88% |
33.166 |
33.791 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC8
|
1.88% |
33.164 |
33.789 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC3
|
1.88% |
33.164 |
33.789 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC1
|
1.88% |
33.164 |
33.789 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC4
|
1.88% |
33.164 |
33.789 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC8
|
1.88% |
33.165 |
33.789 |
0.003 |
-0.00% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC2
|
1.88% |
33.166 |
33.791 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC7
|
1.88% |
33.165 |
33.789 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC7
|
1.88% |
33.166 |
33.790 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC2
|
1.88% |
33.166 |
33.790 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC3
|
1.88% |
33.165 |
33.790 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC2
|
1.88% |
33.165 |
33.789 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC1
|
1.88% |
33.165 |
33.789 |
0.004 |
-0.00% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC2
|
1.88% |
33.164 |
33.788 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1BigLoopWithReductionTC1
|
1.88% |
33.166 |
33.790 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1BigLoopWithReductionTC8
|
1.88% |
33.165 |
33.789 |
0.002 |
0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC7
|
1.88% |
33.165 |
33.789 |
0.003 |
-0.00% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC3
|
1.88% |
33.167 |
33.790 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC8
|
1.88% |
33.168 |
33.791 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1BigLoopWithReductionTC4
|
1.88% |
33.166 |
33.789 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC4
|
1.88% |
33.167 |
33.790 |
0.002 |
0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC8
|
1.88% |
33.169 |
33.791 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC3
|
1.87% |
33.167 |
33.788 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1BigLoopWithReductionTC2
|
1.87% |
33.169 |
33.789 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_ADI_RAW/171
|
1.83% |
31.370 |
31.945 |
0.070 |
0.11% |
0.070 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC1
|
1.83% |
33.183 |
33.790 |
0.003 |
0.00% |
0.003 |
|
MultiSource/Benchmarks/MiBench/consumer-lame/consumer-lame
Profile
|
1.80% |
0.646 |
0.658 |
0.001 |
-3.54% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint8_t>/28
|
1.80% |
106.565 |
108.486 |
0.036 |
0.35% |
0.036 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<5, GreaterThanZero, None>
|
1.80% |
30713.501 |
31265.383 |
3.102 |
1.84% |
3.102 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C++/CLAMR/CLAMR
Profile
|
1.79% |
11.915 |
12.129 |
0.022 |
0.07% |
0.022 |
|
MicroBenchmarks/ImageProcessing/Dilate/Dilate.test:BENCHMARK_DILATE/512
|
1.78% |
4851.698 |
4938.247 |
28.510 |
2.37% |
28.510 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_PIC_1D_RAW/171
|
1.71% |
8.808 |
8.959 |
0.055 |
-1.19% |
0.055 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_IMP_HYDRO_2D_RAW/44217
|
1.69% |
14714.682 |
14963.718 |
67.766 |
-0.11% |
67.766 |
|
MultiSource/Benchmarks/nbench/nbench
Profile
|
1.64% |
6.166 |
6.268 |
0.002 |
2.47% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_two_loads<uint32_t>/51
|
1.61% |
38.168 |
38.783 |
0.003 |
-3.15% |
0.003 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<3, LessThanZero, None>
|
1.59% |
42016.715 |
42686.349 |
152.201 |
1.11% |
152.201 |
|
MicroBenchmarks/ImageProcessing/BilateralFiltering/BilateralFilter.test:BENCHMARK_BILATERAL_FILTER/64/4
|
1.58% |
9394.287 |
9542.301 |
54.210 |
-0.00% |
54.210 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_ENERGY_CALC_LAMBDA/5001
|
1.57% |
453.396 |
460.523 |
2.741 |
-1.11% |
2.741 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_INT_PREDICT_RAW/171
|
1.57% |
6.039 |
6.134 |
0.004 |
-0.02% |
0.004 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_PIC_2D_LAMBDA/171
|
1.56% |
13.455 |
13.665 |
0.076 |
-0.53% |
0.076 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_two_loads<uint32_t>/999
|
1.56% |
38.169 |
38.765 |
0.011 |
-3.20% |
0.011 |
|
MultiSource/Benchmarks/Fhourstones-3.1/fhourstones3.1
Profile
|
1.49% |
3.847 |
3.904 |
0.015 |
-0.69% |
0.015 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint8_t>/16
|
1.48% |
28.084 |
28.499 |
0.054 |
-16.16% |
0.054 |
|
MultiSource/Applications/JM/lencod/lencod
Profile
|
1.46% |
34.965 |
35.477 |
0.058 |
-0.75% |
0.058 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_two_loads<uint32_t>/256
|
1.45% |
38.168 |
38.722 |
0.034 |
-3.31% |
0.034 |
|
MicroBenchmarks/ImageProcessing/BilateralFiltering/BilateralFilter.test:BENCHMARK_BILATERAL_FILTER/32/4
|
1.45% |
2047.717 |
2077.309 |
0.063 |
-0.00% |
0.063 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_IMP_HYDRO_2D_RAW/171
|
1.44% |
53.854 |
54.631 |
0.198 |
-0.62% |
0.198 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_ENERGY_CALC_RAW/171
|
1.42% |
15.627 |
15.849 |
0.052 |
0.17% |
0.052 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C++/PENNANT/PENNANT
Profile
|
1.40% |
4.525 |
4.589 |
0.021 |
-0.40% |
0.021 |
|
MicroBenchmarks/LCALS/SubsetBLambdaLoops/lcalsBLambda.test:BM_TRAP_INT_LAMBDA/44217
|
1.36% |
764.351 |
774.716 |
0.009 |
0.00% |
0.009 |
|
MicroBenchmarks/LCALS/SubsetBLambdaLoops/lcalsBLambda.test:BM_TRAP_INT_LAMBDA/5001
|
1.35% |
86.500 |
87.671 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetBRawLoops/lcalsBRaw.test:BM_TRAP_INT_RAW/44217
|
1.35% |
764.387 |
774.715 |
0.012 |
-0.00% |
0.012 |
|
MicroBenchmarks/LCALS/SubsetBRawLoops/lcalsBRaw.test:BM_TRAP_INT_RAW/5001
|
1.35% |
86.501 |
87.668 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetBRawLoops/lcalsBRaw.test:BM_TRAP_INT_RAW/171
|
1.35% |
2.988 |
3.028 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetBLambdaLoops/lcalsBLambda.test:BM_TRAP_INT_LAMBDA/171
|
1.34% |
2.988 |
3.028 |
0.000 |
-0.01% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC15
|
1.33% |
51.311 |
51.992 |
0.088 |
0.10% |
0.088 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1BigLoopWithReductionTC16
|
1.32% |
51.315 |
51.991 |
0.067 |
0.10% |
0.067 |
|
SingleSource/Benchmarks/Misc/flops-7
Profile
|
1.30% |
7.533 |
7.631 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC15
|
1.30% |
51.310 |
51.975 |
0.247 |
0.07% |
0.247 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC15
|
1.28% |
51.312 |
51.969 |
0.137 |
0.05% |
0.137 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchVecWithRuntimeChecks4PointersDEqualsA/32
|
1.28% |
47848.921 |
48459.874 |
0.797 |
-0.01% |
0.797 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC16
|
1.26% |
51.317 |
51.963 |
0.196 |
0.04% |
0.196 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC16
|
1.25% |
51.310 |
51.953 |
0.097 |
0.03% |
0.097 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC15
|
1.21% |
51.313 |
51.932 |
0.003 |
-0.01% |
0.003 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_VOL3D_CALC_LAMBDA/1
|
1.19% |
168.340 |
170.336 |
0.148 |
0.80% |
0.148 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_INT_PREDICT_LAMBDA/171
|
1.17% |
6.056 |
6.127 |
0.004 |
-0.12% |
0.004 |
|
External/SPEC/CINT2017rate/541.leela_r/541.leela_r
Profile
|
1.15% |
212.969 |
215.427 |
0.589 |
-0.25% |
0.589 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<32, LessThanZero, None>
|
1.12% |
4407.055 |
4456.227 |
14.350 |
4.11% |
14.350 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC15
|
1.10% |
21.042 |
21.274 |
0.002 |
-0.01% |
0.002 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<5, GreaterThanZero, Last>
|
1.10% |
30119.193 |
30449.349 |
2.277 |
1.09% |
2.277 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_VOL3D_CALC_RAW/2
|
1.09% |
5.297 |
5.355 |
0.000 |
2.11% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_EOS_RAW/5001
|
1.08% |
40.143 |
40.578 |
0.037 |
-0.22% |
0.037 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_DISC_ORD_RAW/171
|
1.04% |
18.644 |
18.838 |
0.064 |
-0.01% |
0.064 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_IMP_HYDRO_2D_LAMBDA/5001
|
1.01% |
1641.683 |
1658.336 |
1.524 |
0.01% |
1.524 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<15, EqZero, Last>
|
1.01% |
19867.178 |
20067.644 |
1.221 |
0.95% |
1.221 |