|
SingleSource/Benchmarks/Shootout/Shootout-ary3
Profile
|
44.46% |
0.522 |
0.754 |
0.000 |
-23.46% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_single_load<uint8_t>/16
|
42.07% |
7.513 |
10.674 |
0.016 |
6.01% |
0.016 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_single_load<uint8_t>/10
|
41.77% |
7.509 |
10.645 |
0.058 |
6.94% |
0.058 |
|
SingleSource/Benchmarks/Misc-C++/stepanov_v1p2
Profile
|
33.25% |
12.256 |
16.331 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint64_t>/256
|
29.51% |
1628.805 |
2109.387 |
0.149 |
-0.03% |
0.149 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint64_t>/256
|
29.22% |
831.519 |
1074.488 |
0.105 |
0.06% |
0.105 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint64_t>/28
|
27.83% |
193.346 |
247.147 |
0.009 |
0.00% |
0.009 |
|
MultiSource/Benchmarks/TSVC/Packing-flt/Packing-flt
Profile
|
27.51% |
25.939 |
33.075 |
0.498 |
-1.64% |
0.498 |
|
SingleSource/Benchmarks/Adobe-C++/simple_types_constant_folding
Profile
|
26.48% |
1.720 |
2.175 |
0.001 |
-8.10% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint64_t>/16
|
26.45% |
118.261 |
149.539 |
0.003 |
-0.00% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint64_t>/28
|
26.24% |
112.010 |
141.405 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint64_t>/10
|
24.59% |
76.338 |
95.107 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint64_t>/16
|
24.36% |
74.459 |
92.599 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint64_t>/10
|
21.95% |
51.308 |
62.570 |
0.001 |
-0.01% |
0.001 |
|
SingleSource/Benchmarks/Misc/fp-convert
Profile
|
21.87% |
5.867 |
7.151 |
0.000 |
45.76% |
0.000 |
|
SingleSource/Benchmarks/Shootout/Shootout-random
Profile
|
21.70% |
5.762 |
7.013 |
0.000 |
-0.00% |
0.000 |
|
SingleSource/Benchmarks/Shootout-C++/Shootout-C++-random
Profile
|
21.68% |
5.767 |
7.017 |
0.000 |
-0.00% |
0.000 |
|
MultiSource/Benchmarks/TSVC/Packing-dbl/Packing-dbl
Profile
|
21.51% |
29.327 |
35.634 |
0.255 |
0.18% |
0.255 |
|
SingleSource/Benchmarks/Adobe-C++/loop_unroll
Profile
|
18.94% |
22.973 |
27.324 |
0.003 |
0.00% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_csa_with_cond_arith_autovec_int32_t_
|
18.91% |
479058.394 |
569635.380 |
2289.467 |
0.19% |
2289.467 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_csa_with_cond_arith_novec_int32_t_
|
18.64% |
479035.363 |
568319.487 |
2929.128 |
-0.59% |
2929.128 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint32_t_To_uint16_t_
|
18.13% |
10873.925 |
12845.278 |
60.448 |
-0.49% |
60.448 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC4
|
18.10% |
9.386 |
11.085 |
0.038 |
6.51% |
0.038 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint32_t_To_uint16_t_
|
18.03% |
10873.764 |
12833.992 |
59.455 |
-0.60% |
59.455 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint32_t_To_uint16_t_
|
17.98% |
10867.842 |
12821.435 |
61.875 |
-0.76% |
61.875 |
|
MultiSource/Benchmarks/MiBench/telecomm-gsm/telecomm-gsm
Profile
|
17.96% |
0.583 |
0.688 |
0.000 |
-0.67% |
0.000 |
|
MicroBenchmarks/ImageProcessing/Blur/blur.test:BENCHMARK_GAUSSIAN_BLUR/128
|
17.68% |
3768.739 |
4435.064 |
0.300 |
-0.01% |
0.300 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint32_t>/10
|
17.67% |
64.874 |
76.335 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint32_t>/10
|
17.14% |
43.801 |
51.308 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/ImageProcessing/Blur/blur.test:BENCHMARK_GAUSSIAN_BLUR/512
|
16.54% |
70114.358 |
81711.824 |
58.887 |
-0.09% |
58.887 |
|
MultiSource/Benchmarks/mediabench/gsm/toast/toast
Profile
|
16.20% |
0.076 |
0.089 |
0.000 |
-0.89% |
0.000 |
|
MicroBenchmarks/ImageProcessing/Blur/blur.test:BENCHMARK_GAUSSIAN_BLUR/256
|
15.12% |
16872.768 |
19423.108 |
68.081 |
-0.54% |
68.081 |
|
SingleSource/Benchmarks/Adobe-C++/simple_types_loop_invariant
Profile
|
14.68% |
2.674 |
3.066 |
0.005 |
26.96% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint16_t>/10
|
14.52% |
34.419 |
39.418 |
0.005 |
10.52% |
0.005 |
|
SingleSource/Benchmarks/Stanford/Bubblesort
Profile
|
14.12% |
0.079 |
0.090 |
0.000 |
-0.21% |
0.000 |
|
SingleSource/Benchmarks/Polybench/stencils/seidel-2d/seidel-2d
Profile
|
14.03% |
103.920 |
118.500 |
0.236 |
0.05% |
0.236 |
|
MultiSource/Benchmarks/TSVC/Expansion-flt/Expansion-flt
Profile
|
13.80% |
10.830 |
12.324 |
0.075 |
-0.84% |
0.075 |
|
SingleSource/Benchmarks/Shootout/Shootout-matrix
Profile
|
13.51% |
4.067 |
4.617 |
0.000 |
-1.61% |
0.000 |
|
MultiSource/Benchmarks/TSVC/StatementReordering-dbl/StatementReordering-dbl
Profile
|
13.49% |
21.245 |
24.111 |
0.538 |
-2.31% |
0.538 |
|
MultiSource/Benchmarks/TSVC/StatementReordering-flt/StatementReordering-flt
Profile
|
13.21% |
13.712 |
15.523 |
0.050 |
0.07% |
0.050 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint64_t>/28
|
12.82% |
24.403 |
27.531 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint64_t>/16
|
12.82% |
24.402 |
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 |
27.530 |
0.000 |
-0.00% |
0.000 |
|
External/SPEC/CFP2017rate/526.blender_r/526.blender_r
Profile
|
12.81% |
781.895 |
882.028 |
2.830 |
-0.12% |
2.830 |
|
MultiSource/Benchmarks/McCat/18-imp/imp
Profile
|
12.50% |
0.188 |
0.212 |
0.000 |
-0.32% |
0.000 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C/miniAMR/miniAMR
Profile
|
12.49% |
3.459 |
3.891 |
0.070 |
1.84% |
0.070 |
|
SingleSource/Benchmarks/Misc/flops-4
Profile
|
12.47% |
3.916 |
4.404 |
0.000 |
-0.01% |
0.000 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/16
|
12.22% |
173.424 |
194.610 |
0.016 |
-0.01% |
0.016 |
|
MultiSource/Benchmarks/TSVC/Expansion-dbl/Expansion-dbl
Profile
|
12.00% |
19.135 |
21.431 |
0.047 |
0.81% |
0.047 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/32
|
11.98% |
866.606 |
970.442 |
0.054 |
-0.00% |
0.054 |
|
SingleSource/Benchmarks/Misc/flops-3
Profile
|
11.89% |
8.218 |
9.195 |
0.000 |
-0.00% |
0.000 |
|
External/SPEC/CFP2017rate/538.imagick_r/538.imagick_r
Profile
|
11.79% |
244.143 |
272.939 |
0.313 |
0.04% |
0.313 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/64
|
11.65% |
3846.732 |
4295.042 |
1.249 |
-0.03% |
1.249 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint8_t_To_uint32_t_
|
11.59% |
11239.121 |
12541.359 |
54.280 |
-0.18% |
54.280 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/256
|
11.24% |
67501.946 |
75089.592 |
8.316 |
-0.01% |
8.316 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint8_t>/16
|
11.23% |
111.380 |
123.883 |
0.005 |
-0.51% |
0.005 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/128
|
11.06% |
16564.211 |
18395.612 |
3.525 |
0.01% |
3.525 |
|
SingleSource/Benchmarks/Stanford/FloatMM
Profile
|
11.03% |
0.448 |
0.498 |
0.000 |
-0.09% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint8_t>/16
|
11.01% |
68.201 |
75.707 |
0.001 |
0.82% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint8_t_To_uint32_t_
|
10.98% |
11261.769 |
12498.428 |
55.261 |
-0.11% |
55.261 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint8_t_To_uint32_t_
|
10.98% |
11262.019 |
12498.310 |
59.451 |
-0.51% |
59.451 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint8_t>/10
|
10.92% |
74.462 |
82.590 |
0.003 |
-0.76% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint16_t>/16
|
10.90% |
47.558 |
52.740 |
0.016 |
5.46% |
0.016 |
|
SingleSource/Benchmarks/Misc/matmul_f64_4x4
Profile
|
10.89% |
4.574 |
5.072 |
0.001 |
0.28% |
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
|
10.87% |
1.238 |
1.372 |
0.011 |
-0.02% |
0.011 |
|
SingleSource/Benchmarks/Adobe-C++/stepanov_abstraction
Profile
|
10.64% |
11.475 |
12.696 |
0.000 |
-0.00% |
0.000 |
|
MultiSource/Benchmarks/TSVC/CrossingThresholds-flt/CrossingThresholds-flt
Profile
|
10.40% |
10.011 |
11.052 |
0.054 |
-0.23% |
0.054 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint16_t_To_uint32_t_
|
10.33% |
12035.403 |
13278.975 |
86.236 |
-1.50% |
86.236 |
|
MicroBenchmarks/ImageProcessing/Blur/blur.test:BENCHMARK_GAUSSIAN_BLUR/1024
|
10.33% |
390716.352 |
431071.561 |
116.523 |
-0.02% |
116.523 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/16
|
10.26% |
98.581 |
108.700 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint16_t_To_uint32_t_
|
10.22% |
12040.011 |
13270.270 |
78.205 |
-1.50% |
78.205 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint16_t_To_uint32_t_
|
10.20% |
12036.540 |
13264.183 |
95.436 |
-1.25% |
95.436 |
|
MultiSource/Benchmarks/TSVC/Searching-flt/Searching-flt
Profile
|
10.19% |
15.492 |
17.071 |
0.005 |
-0.01% |
0.005 |
|
SingleSource/Benchmarks/Shootout-C++/Shootout-C++-methcall
Profile
|
10.15% |
12.316 |
13.566 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/32
|
10.06% |
403.836 |
444.460 |
0.022 |
0.00% |
0.022 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint8_t>/10
|
10.00% |
50.055 |
55.062 |
0.002 |
1.14% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchAutoVec<uint16_t>/127
|
9.89% |
63.201 |
69.453 |
0.002 |
-0.01% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchAutoVec<uint16_t>/65
|
9.86% |
44.427 |
48.806 |
0.003 |
0.00% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchAutoVec<uint8_t>/127
|
9.82% |
38.174 |
41.922 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchAutoVec<uint8_t>/65
|
9.79% |
31.921 |
35.045 |
0.005 |
0.01% |
0.005 |
|
SingleSource/Benchmarks/BenchmarkGame/Large/fasta
Profile
|
9.65% |
1.990 |
2.182 |
0.004 |
0.11% |
0.004 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/256
|
9.47% |
26946.014 |
29498.345 |
2.785 |
-0.03% |
2.785 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/128
|
9.39% |
6774.191 |
7410.174 |
5.942 |
-0.08% |
5.942 |
|
MultiSource/Benchmarks/TSVC/NodeSplitting-flt/NodeSplitting-flt
Profile
|
9.37% |
15.994 |
17.493 |
0.048 |
0.41% |
0.048 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint64_t>/10
|
9.37% |
20.024 |
21.901 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint16_t>/28
|
9.19% |
108.877 |
118.881 |
0.109 |
1.02% |
0.109 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint16_t>/51
|
9.19% |
106.369 |
116.142 |
0.083 |
1.38% |
0.083 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint32_t>/256
|
9.01% |
940.226 |
1024.955 |
0.136 |
0.46% |
0.136 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchAutoVec<uint32_t>/65
|
8.92% |
70.084 |
76.339 |
0.002 |
0.00% |
0.002 |
|
MultiSource/Applications/ALAC/encode/alacconvert-encode
Profile
|
8.83% |
0.123 |
0.134 |
0.001 |
0.55% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint16_t>/999
|
8.80% |
1782.157 |
1938.990 |
0.441 |
0.08% |
0.441 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint16_t>/999
|
8.78% |
3540.972 |
3851.862 |
0.487 |
-0.05% |
0.487 |
|
MultiSource/Benchmarks/TSVC/Searching-dbl/Searching-dbl
Profile
|
8.78% |
17.716 |
19.271 |
0.006 |
0.01% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchAutoVec<uint32_t>/127
|
8.73% |
114.520 |
124.523 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint16_t_To_uint64_t_
|
8.72% |
21948.747 |
23862.526 |
26.386 |
-0.23% |
26.386 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint32_t>/999
|
8.71% |
3614.655 |
3929.326 |
0.480 |
0.07% |
0.480 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint16_t>/256
|
8.71% |
471.261 |
512.285 |
0.074 |
0.08% |
0.074 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint16_t_To_uint64_t_
|
8.66% |
21949.183 |
23849.442 |
21.425 |
0.06% |
21.425 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint16_t>/256
|
8.61% |
923.552 |
1003.046 |
0.219 |
-0.24% |
0.219 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/64
|
8.57% |
1653.259 |
1794.926 |
1.794 |
-0.03% |
1.794 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint32_t>/999
|
8.49% |
1821.728 |
1976.315 |
0.104 |
-0.09% |
0.104 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint32_t>/28
|
8.45% |
44.426 |
48.178 |
0.004 |
-4.35% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint32_t>/16
|
8.45% |
44.424 |
48.176 |
0.003 |
-4.36% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint32_t>/51
|
8.45% |
44.425 |
48.177 |
0.001 |
-4.36% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint32_t>/256
|
8.44% |
44.425 |
48.177 |
0.001 |
-4.36% |
0.001 |
|
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:autovec_no_early_exit_single_load<uint16_t>/51
|
8.38% |
193.974 |
210.234 |
0.026 |
0.07% |
0.026 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint16_t_To_uint64_t_
|
8.35% |
21967.841 |
23802.264 |
38.270 |
-0.06% |
38.270 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_single_load<uint8_t>/256
|
8.32% |
22.526 |
24.401 |
0.001 |
11.40% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint16_t>/28
|
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>/10
|
8.21% |
45.676 |
49.428 |
0.001 |
-5.40% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint16_t>/51
|
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>/999
|
8.21% |
45.677 |
49.429 |
0.001 |
-5.40% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint16_t>/16
|
8.21% |
45.677 |
49.428 |
0.002 |
-5.39% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint16_t>/256
|
8.21% |
45.679 |
49.429 |
0.002 |
-5.39% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint16_t_To_uint8_t_
|
8.17% |
4363.809 |
4720.406 |
0.645 |
-0.02% |
0.645 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint32_t>/256
|
8.17% |
482.435 |
521.835 |
0.005 |
-0.01% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint32_t>/28
|
8.17% |
99.495 |
107.619 |
0.007 |
-4.45% |
0.007 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint16_t_To_uint8_t_
|
8.16% |
4364.015 |
4720.284 |
0.574 |
-0.02% |
0.574 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint16_t_To_uint8_t_
|
8.16% |
4364.680 |
4720.718 |
0.359 |
-0.01% |
0.359 |
|
SingleSource/Benchmarks/Misc-C++/Large/sphereflake
Profile
|
8.12% |
18.104 |
19.575 |
0.002 |
0.04% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint32_t>/51
|
8.11% |
196.777 |
212.740 |
0.008 |
1.09% |
0.008 |
|
SingleSource/Benchmarks/Linpack/linpack-pc
Profile
|
8.08% |
8.850 |
9.565 |
0.004 |
-0.08% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_single_load<uint8_t>/51
|
8.02% |
22.526 |
24.332 |
0.030 |
11.08% |
0.030 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_single_load<uint8_t>/999
|
7.95% |
22.529 |
24.321 |
0.038 |
11.03% |
0.038 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint16_t>/28
|
7.90% |
70.079 |
75.612 |
0.045 |
0.70% |
0.045 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_csa_with_cond_arith_novec_uint8_t_
|
7.88% |
495432.381 |
534486.820 |
49.495 |
-0.00% |
49.495 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_csa_with_cond_arith_autovec_uint8_t_
|
7.85% |
495554.551 |
534437.100 |
35.139 |
0.01% |
35.139 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_single_load<uint8_t>/28
|
7.82% |
22.526 |
24.287 |
0.051 |
10.87% |
0.051 |
|
SingleSource/Benchmarks/Adobe-C++/stepanov_vector
Profile
|
7.80% |
7.235 |
7.799 |
0.000 |
0.07% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC127
|
7.74% |
104.979 |
113.103 |
0.042 |
-0.04% |
0.042 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC128
|
7.67% |
104.985 |
113.042 |
0.009 |
0.01% |
0.009 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC127
|
7.67% |
104.977 |
113.031 |
0.041 |
0.13% |
0.041 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC128
|
7.65% |
104.939 |
112.965 |
0.015 |
-0.03% |
0.015 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC127
|
7.62% |
104.947 |
112.943 |
0.102 |
-0.11% |
0.102 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC128
|
7.61% |
104.936 |
112.922 |
0.061 |
-0.04% |
0.061 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC128
|
7.52% |
105.090 |
112.996 |
0.068 |
0.04% |
0.068 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC127
|
7.52% |
105.127 |
113.031 |
0.045 |
-0.05% |
0.045 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC128
|
7.51% |
105.083 |
112.970 |
0.043 |
-0.11% |
0.043 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC127
|
7.44% |
105.124 |
112.947 |
0.032 |
-0.11% |
0.032 |
|
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/ImageProcessing/Dither/Dither.test:BENCHMARK_FLOYD_DITHER/512
|
7.40% |
5794.734 |
6223.712 |
20.544 |
1.13% |
20.544 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint64_t>/51
|
7.31% |
51.308 |
55.060 |
0.002 |
-3.30% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint64_t>/999
|
7.31% |
51.311 |
55.061 |
0.001 |
-3.30% |
0.001 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C/CoMD/CoMD
Profile
|
7.16% |
9.393 |
10.065 |
0.008 |
0.11% |
0.008 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint16_t>/28
|
7.14% |
105.120 |
112.622 |
0.005 |
-6.25% |
0.005 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_FLOYD_DITHER/256
|
7.11% |
1491.759 |
1597.806 |
1.048 |
1.08% |
1.048 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC64
|
6.97% |
53.815 |
57.567 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC64
|
6.97% |
53.816 |
57.567 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC64
|
6.97% |
53.814 |
57.564 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC63
|
6.97% |
53.815 |
57.564 |
0.004 |
-0.01% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC63
|
6.97% |
53.817 |
57.566 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC64
|
6.97% |
53.817 |
57.565 |
0.002 |
0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC64
|
6.96% |
53.821 |
57.567 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC63
|
6.96% |
53.821 |
57.566 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC63
|
6.95% |
53.824 |
57.566 |
0.003 |
-0.00% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC63
|
6.91% |
53.841 |
57.563 |
0.001 |
-0.00% |
0.001 |
|
MultiSource/Benchmarks/Trimaran/enc-rc4/enc-rc4
Profile
|
6.85% |
2.728 |
2.915 |
0.000 |
0.04% |
0.000 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_FLOYD_DITHER/128
|
6.76% |
381.633 |
407.419 |
1.307 |
0.42% |
1.307 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint32_t_To_uint8_t_
|
6.72% |
9779.214 |
10436.460 |
29.711 |
-0.00% |
29.711 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint32_t>/16
|
6.72% |
74.462 |
79.464 |
0.000 |
-4.87% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC32
|
6.66% |
28.157 |
30.033 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC32
|
6.66% |
28.157 |
30.033 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC31
|
6.66% |
28.158 |
30.034 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC31
|
6.66% |
28.157 |
30.033 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC32
|
6.66% |
28.158 |
30.033 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC32
|
6.66% |
28.158 |
30.033 |
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 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC32
|
6.66% |
28.158 |
30.033 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC31
|
6.66% |
28.159 |
30.033 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC31
|
6.65% |
28.159 |
30.033 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC31
|
6.65% |
28.160 |
30.033 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint32_t_To_uint8_t_
|
6.60% |
9750.891 |
10394.459 |
60.459 |
-0.35% |
60.459 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint8_t>/999
|
6.54% |
4745.714 |
5055.978 |
0.647 |
-0.02% |
0.647 |
|
MultiSource/Benchmarks/PAQ8p/paq8p
Profile
|
6.47% |
192.776 |
205.241 |
0.167 |
1.99% |
0.167 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint8_t>/999
|
6.46% |
2391.161 |
2545.572 |
0.056 |
0.09% |
0.056 |
|
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:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint32_t_To_uint8_t_
|
6.44% |
13274.566 |
14129.851 |
70.499 |
-0.53% |
70.499 |
|
SingleSource/Benchmarks/Shootout-C++/Shootout-C++-fibo
Profile
|
6.41% |
5.114 |
5.441 |
0.002 |
-0.07% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint8_t>/256
|
6.40% |
628.251 |
668.440 |
0.101 |
0.13% |
0.101 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint16_t>/16
|
6.40% |
78.217 |
83.220 |
0.003 |
-6.66% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint32_t_To_uint8_t_
|
6.36% |
13286.370 |
14131.198 |
28.775 |
-0.53% |
28.775 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint32_t_To_uint8_t_
|
6.32% |
13278.186 |
14116.937 |
55.725 |
-0.67% |
55.725 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint8_t>/256
|
6.28% |
1229.527 |
1306.784 |
0.334 |
-0.07% |
0.334 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint32_t>/51
|
6.26% |
139.557 |
148.286 |
0.018 |
-5.02% |
0.018 |
|
SingleSource/Benchmarks/Shootout/Shootout-fib2
Profile
|
6.25% |
5.095 |
5.414 |
0.007 |
-0.02% |
0.007 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint32_t>/999
|
6.20% |
2533.984 |
2691.190 |
0.178 |
-5.47% |
0.178 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint32_t>/256
|
6.13% |
663.291 |
703.945 |
0.021 |
-5.54% |
0.021 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint16_t>/999
|
6.13% |
2535.284 |
2690.618 |
0.104 |
-5.54% |
0.104 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint16_t>/256
|
6.12% |
663.318 |
703.931 |
0.015 |
-5.54% |
0.015 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopFrom_uint32_t_To_uint8_t_
|
6.11% |
9822.431 |
10422.455 |
45.466 |
-0.26% |
45.466 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint8_t>/999
|
6.09% |
2535.360 |
2689.844 |
0.236 |
-5.55% |
0.236 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint32_t>/28
|
6.07% |
113.254 |
120.131 |
0.033 |
-0.17% |
0.033 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint16_t>/999
|
6.07% |
1294.188 |
1372.760 |
0.150 |
-5.40% |
0.150 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_single_load<uint16_t>/51
|
6.06% |
20.649 |
21.899 |
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 |
0.001 |
2.93% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint16_t>/10
|
6.05% |
20.650 |
21.899 |
0.000 |
-1.55% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_single_load<uint16_t>/28
|
6.05% |
20.650 |
21.899 |
0.000 |
2.94% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_single_load<uint16_t>/999
|
6.05% |
20.650 |
21.899 |
0.001 |
2.93% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint32_t>/10
|
6.05% |
32.119 |
34.062 |
0.122 |
22.29% |
0.122 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint64_t>/10
|
6.00% |
28.170 |
29.861 |
0.023 |
-2.61% |
0.023 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint8_t>/256
|
5.96% |
356.667 |
377.909 |
0.010 |
-5.48% |
0.010 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint32_t>/256
|
5.95% |
357.290 |
378.541 |
0.005 |
-5.48% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint16_t>/256
|
5.95% |
357.284 |
378.531 |
0.020 |
-5.47% |
0.020 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint8_t>/256
|
5.93% |
663.909 |
703.267 |
0.011 |
-5.55% |
0.011 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint32_t>/999
|
5.92% |
1294.375 |
1370.956 |
0.184 |
-5.69% |
0.184 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint8_t>/999
|
5.87% |
1296.685 |
1372.756 |
0.094 |
-5.37% |
0.094 |
|
MultiSource/Benchmarks/SciMark2-C/scimark2
Profile
|
5.86% |
133.694 |
141.529 |
0.083 |
-15.09% |
0.083 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint8_t>/51
|
5.85% |
251.810 |
266.542 |
0.208 |
-0.09% |
0.208 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint8_t>/28
|
5.83% |
142.040 |
150.325 |
0.212 |
0.30% |
0.212 |
|
MultiSource/Benchmarks/TSVC/InductionVariable-flt/InductionVariable-flt
Profile
|
5.83% |
9.474 |
10.026 |
0.134 |
-0.09% |
0.134 |
|
MultiSource/Benchmarks/Bullet/bullet
Profile
|
5.83% |
28.487 |
30.147 |
0.364 |
3.20% |
0.364 |
|
SingleSource/Benchmarks/Misc-C++/Large/ray
Profile
|
5.82% |
9.302 |
9.844 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint32_t>/51
|
5.73% |
152.674 |
161.430 |
0.032 |
-5.49% |
0.032 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint16_t>/51
|
5.73% |
152.688 |
161.429 |
0.004 |
-5.50% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint8_t>/51
|
5.71% |
138.289 |
146.187 |
0.307 |
0.79% |
0.307 |
|
SingleSource/Benchmarks/Shootout-C++/EH/Shootout-C++-except
Profile
|
5.68% |
1.060 |
1.120 |
0.002 |
-0.03% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint32_t>/51
|
5.68% |
110.118 |
116.376 |
0.004 |
-0.05% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint64_t_To_uint32_t_
|
5.47% |
20961.845 |
22109.445 |
25.568 |
-0.06% |
25.568 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint64_t_To_uint32_t_
|
5.46% |
20967.213 |
22111.587 |
32.036 |
-0.03% |
32.036 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint64_t_To_uint32_t_
|
5.46% |
20968.657 |
22112.700 |
17.622 |
-0.02% |
17.622 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint16_t>/51
|
5.44% |
148.953 |
157.050 |
0.011 |
-7.21% |
0.011 |
|
SingleSource/Benchmarks/Misc/flops
Profile
|
5.29% |
13.433 |
14.144 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint32_t>/16
|
5.25% |
83.225 |
87.595 |
0.001 |
-5.41% |
0.001 |
|
MultiSource/Benchmarks/TSVC/InductionVariable-dbl/InductionVariable-dbl
Profile
|
5.25% |
17.805 |
18.739 |
0.185 |
-1.80% |
0.185 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C++/miniFE/miniFE
Profile
|
5.23% |
15.757 |
16.582 |
0.075 |
-7.10% |
0.075 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint16_t>/10
|
5.21% |
71.959 |
75.709 |
0.001 |
-7.28% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint32_t>/28
|
5.18% |
72.579 |
76.337 |
0.002 |
-0.00% |
0.002 |
|
MultiSource/Benchmarks/MallocBench/cfrac/cfrac
Profile
|
5.15% |
2.645 |
2.781 |
0.001 |
-0.05% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint32_t>/51
|
5.02% |
99.491 |
104.490 |
0.003 |
-5.13% |
0.003 |
|
SingleSource/Benchmarks/Misc/ReedSolomon
Profile
|
4.99% |
21.005 |
22.052 |
0.003 |
-0.03% |
0.003 |
|
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 |
105.116 |
0.003 |
-5.08% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint16_t>/16
|
4.96% |
88.225 |
92.603 |
0.001 |
-7.50% |
0.001 |
|
MultiSource/Benchmarks/TSVC/NodeSplitting-dbl/NodeSplitting-dbl
Profile
|
4.95% |
22.109 |
23.203 |
0.093 |
-0.86% |
0.093 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint8_t>/28
|
4.91% |
89.477 |
93.866 |
0.188 |
1.01% |
0.188 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint8_t>/51
|
4.90% |
153.302 |
160.809 |
0.002 |
-5.52% |
0.002 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C++/HPCCG/HPCCG
Profile
|
4.90% |
4.081 |
4.281 |
0.043 |
-7.98% |
0.043 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint32_t>/10
|
4.88% |
39.740 |
41.677 |
0.049 |
0.92% |
0.049 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint32_t>/28
|
4.87% |
128.277 |
134.526 |
0.002 |
-5.50% |
0.002 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_ORDERED_DITHER/512/3
|
4.84% |
34937.635 |
36628.890 |
9.622 |
0.00% |
9.622 |
|
SingleSource/Benchmarks/BenchmarkGame/spectral-norm
Profile
|
4.84% |
1.540 |
1.615 |
0.000 |
-0.02% |
0.000 |
|
SingleSource/Benchmarks/Misc/flops-1
Profile
|
4.64% |
8.414 |
8.804 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_ORDERED_DITHER/256/3
|
4.60% |
8925.437 |
9336.271 |
9.181 |
0.07% |
9.181 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint16_t>/51
|
4.58% |
100.508 |
105.114 |
0.001 |
-4.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint32_t>/51
|
4.58% |
218.389 |
228.381 |
0.004 |
-5.56% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint16_t>/28
|
4.56% |
137.035 |
143.283 |
0.003 |
-7.85% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint64_t>/16
|
4.53% |
35.678 |
37.293 |
0.023 |
-1.96% |
0.023 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint8_t>/28
|
4.51% |
109.555 |
114.500 |
0.008 |
-6.64% |
0.008 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint32_t>/256
|
4.51% |
525.066 |
548.726 |
0.037 |
-5.56% |
0.037 |
|
MultiSource/Benchmarks/FreeBench/fourinarow/fourinarow
Profile
|
4.40% |
0.647 |
0.675 |
0.000 |
-0.25% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint16_t>/10
|
4.39% |
40.992 |
42.790 |
0.016 |
-11.19% |
0.016 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_ORDERED_DITHER/512/4
|
4.37% |
33283.083 |
34737.312 |
22.635 |
-0.00% |
22.635 |
|
SingleSource/Benchmarks/Misc/dt
Profile
|
4.33% |
3.869 |
4.037 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint16_t>/51
|
4.27% |
234.643 |
244.652 |
0.021 |
-8.11% |
0.021 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint32_t>/256
|
4.25% |
984.365 |
1026.172 |
0.035 |
-5.64% |
0.035 |
|
SingleSource/Benchmarks/Polybench/stencils/jacobi-2d/jacobi-2d
Profile
|
4.23% |
40.810 |
42.535 |
0.052 |
0.43% |
0.052 |
|
External/SPEC/CFP2017rate/544.nab_r/544.nab_r
Profile
|
4.21% |
436.808 |
455.192 |
0.128 |
-0.02% |
0.128 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint32_t>/999
|
4.20% |
1931.906 |
2013.002 |
0.123 |
-5.58% |
0.123 |
|
MicroBenchmarks/ImageProcessing/AnisotropicDiffusion/AnisotropicDiffusion.test:BENCHMARK_ANISTROPIC_DIFFUSION/64
|
4.18% |
8827.889 |
9197.334 |
0.339 |
-0.01% |
0.339 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint16_t>/256
|
4.18% |
566.358 |
590.032 |
0.017 |
-8.22% |
0.017 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_ORDERED_DITHER/512/8
|
4.18% |
33349.565 |
34743.148 |
12.709 |
-0.07% |
12.709 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint8_t_To_uint64_t_
|
4.15% |
21809.840 |
22715.844 |
34.806 |
-0.01% |
34.806 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint32_t>/999
|
4.11% |
3787.931 |
3943.648 |
0.379 |
-5.98% |
0.379 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_ORDERED_DITHER/256/4
|
4.11% |
8525.345 |
8875.619 |
12.558 |
0.10% |
12.558 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_ORDERED_DITHER/128/3
|
4.11% |
2194.033 |
2284.120 |
5.270 |
-0.36% |
5.270 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint8_t_To_uint64_t_
|
4.10% |
21818.944 |
22714.268 |
41.909 |
-0.04% |
41.909 |
|
MicroBenchmarks/ImageProcessing/AnisotropicDiffusion/AnisotropicDiffusion.test:BENCHMARK_ANISTROPIC_DIFFUSION/32
|
4.09% |
1935.689 |
2014.826 |
0.438 |
0.01% |
0.438 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint32_t>/16
|
4.08% |
44.641 |
46.463 |
0.217 |
17.50% |
0.217 |
|
MultiSource/Benchmarks/ASC_Sequoia/AMGmk/AMGmk
Profile
|
4.08% |
38.397 |
39.962 |
0.055 |
-8.05% |
0.055 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint16_t>/999
|
4.07% |
2084.424 |
2169.296 |
0.085 |
-8.28% |
0.085 |
|
MicroBenchmarks/ImageProcessing/AnisotropicDiffusion/AnisotropicDiffusion.test:BENCHMARK_ANISTROPIC_DIFFUSION/256
|
4.06% |
165055.635 |
171748.937 |
174.715 |
-0.08% |
174.715 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint8_t>/51
|
4.05% |
153.935 |
160.174 |
0.004 |
-7.37% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint8_t>/256
|
4.05% |
46.303 |
48.179 |
0.002 |
-6.66% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint8_t>/28
|
4.05% |
46.302 |
48.177 |
0.001 |
-6.64% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint8_t>/999
|
4.05% |
46.303 |
48.177 |
0.001 |
-6.68% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint8_t>/51
|
4.03% |
46.309 |
48.177 |
0.002 |
-6.59% |
0.002 |
|
MultiSource/Benchmarks/sim/sim
Profile
|
4.01% |
17.527 |
18.230 |
0.005 |
129.94% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC15
|
4.00% |
15.643 |
16.269 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC15
|
3.99% |
15.643 |
16.268 |
0.000 |
-0.01% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC16
|
3.99% |
15.643 |
16.268 |
0.000 |
-0.01% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC15
|
3.99% |
15.643 |
16.268 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC15
|
3.99% |
15.643 |
16.268 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC16
|
3.99% |
15.644 |
16.268 |
0.000 |
-0.01% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC16
|
3.99% |
15.644 |
16.268 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC16
|
3.99% |
15.645 |
16.268 |
0.000 |
-0.01% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC16
|
3.98% |
15.645 |
16.268 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC15
|
3.98% |
15.645 |
16.268 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_ORDERED_DITHER/256/8
|
3.98% |
8533.329 |
8872.703 |
14.831 |
0.11% |
14.831 |
|
SingleSource/Benchmarks/SmallPT/smallpt
Profile
|
3.94% |
27.373 |
28.451 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint16_t>/256
|
3.93% |
1064.371 |
1106.246 |
0.023 |
-8.40% |
0.023 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint64_t_To_uint8_t_
|
3.92% |
31140.731 |
32362.402 |
28.499 |
0.06% |
28.499 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint64_t_To_uint8_t_
|
3.92% |
31140.645 |
32362.171 |
27.341 |
0.08% |
27.341 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint64_t_To_uint8_t_
|
3.92% |
31139.216 |
32360.537 |
28.559 |
0.08% |
28.559 |
|
MicroBenchmarks/ImageProcessing/BilateralFiltering/BilateralFilter.test:BENCHMARK_BILATERAL_FILTER/16/2
|
3.86% |
124.547 |
129.351 |
0.690 |
-0.01% |
0.690 |
|
SingleSource/Benchmarks/Misc/flops-8
Profile
|
3.82% |
1.900 |
1.973 |
0.000 |
-0.01% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint16_t>/999
|
3.82% |
4099.728 |
4256.234 |
0.267 |
-8.41% |
0.267 |
|
MultiSource/Benchmarks/FreeBench/distray/distray
Profile
|
3.77% |
0.408 |
0.424 |
0.000 |
-0.07% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC1
|
3.75% |
33.169 |
34.413 |
0.002 |
1.84% |
0.002 |
|
MicroBenchmarks/ImageProcessing/BilateralFiltering/BilateralFilter.test:BENCHMARK_BILATERAL_FILTER/32/2
|
3.74% |
571.715 |
593.098 |
0.013 |
-0.02% |
0.013 |
|
SingleSource/Benchmarks/BenchmarkGame/n-body
Profile
|
3.73% |
3.096 |
3.212 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint8_t>/256
|
3.72% |
586.980 |
608.804 |
0.030 |
-8.08% |
0.030 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint8_t>/999
|
3.71% |
2165.181 |
2245.547 |
0.090 |
-8.09% |
0.090 |
|
MultiSource/Benchmarks/TSVC/Reductions-flt/Reductions-flt
Profile
|
3.69% |
2.726 |
2.826 |
0.020 |
-0.14% |
0.020 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint8_t>/10
|
3.69% |
47.969 |
49.739 |
0.003 |
0.81% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint8_t>/999
|
3.64% |
4254.956 |
4409.628 |
0.496 |
-8.23% |
0.496 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint8_t>/256
|
3.55% |
1103.922 |
1143.125 |
0.013 |
-8.24% |
0.013 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_ORDERED_DITHER/128/8
|
3.54% |
2095.596 |
2169.880 |
5.749 |
-0.18% |
5.749 |
|
MicroBenchmarks/LoopInterchange/LoopInterchange.test:BENCHMARK_LI1
|
3.54% |
1567.856 |
1623.417 |
5.374 |
-0.14% |
5.374 |
|
MultiSource/Benchmarks/Rodinia/hotspot/hotspot
Profile
|
3.47% |
2.238 |
2.315 |
0.002 |
0.17% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint32_t>/16
|
3.46% |
54.762 |
56.654 |
0.089 |
0.60% |
0.089 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_ORDERED_DITHER/128/4
|
3.45% |
2091.751 |
2163.928 |
4.928 |
-0.31% |
4.928 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint8_t_To_uint64_t_
|
3.35% |
21976.959 |
22713.964 |
37.003 |
-0.08% |
37.003 |
|
MicroBenchmarks/ImageProcessing/BilateralFiltering/BilateralFilter.test:BENCHMARK_BILATERAL_FILTER/64/2
|
3.33% |
2455.815 |
2537.507 |
0.227 |
-0.55% |
0.227 |
|
MultiSource/Benchmarks/mafft/pairlocalalign
Profile
|
3.32% |
77.366 |
79.936 |
0.303 |
-0.25% |
0.303 |
|
SingleSource/Benchmarks/Dhrystone/fldry
Profile
|
3.32% |
0.944 |
0.975 |
0.000 |
-0.01% |
0.000 |
|
SingleSource/Benchmarks/Shootout-C++/Shootout-C++-lists
Profile
|
3.13% |
20.123 |
20.754 |
0.131 |
-0.04% |
0.131 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint64_t>/51
|
3.09% |
181.465 |
187.077 |
0.007 |
-4.78% |
0.007 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint8_t>/51
|
3.06% |
242.232 |
249.643 |
0.004 |
-8.38% |
0.004 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_ORDERED_DITHER/512/2
|
3.03% |
33274.702 |
34283.617 |
28.875 |
0.01% |
28.875 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint64_t>/28
|
2.99% |
50.692 |
52.207 |
0.055 |
-1.60% |
0.055 |
|
SingleSource/Benchmarks/Misc/pi
Profile
|
2.94% |
1.808 |
1.861 |
0.001 |
-0.08% |
0.001 |
|
SingleSource/Benchmarks/Misc/mandel
Profile
|
2.92% |
3.206 |
3.300 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint16_t>/16
|
2.92% |
56.087 |
57.723 |
0.008 |
-13.79% |
0.008 |
|
SingleSource/Benchmarks/Misc/perlin
Profile
|
2.91% |
8.174 |
8.412 |
0.000 |
-0.01% |
0.000 |
|
MultiSource/Benchmarks/Trimaran/enc-md5/enc-md5
Profile
|
2.85% |
2.951 |
3.035 |
0.000 |
-75.99% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint64_t_To_uint16_t_
|
2.83% |
25952.367 |
26686.664 |
55.163 |
-0.12% |
55.163 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint64_t_To_uint16_t_
|
2.83% |
25952.946 |
26686.347 |
51.495 |
-0.15% |
51.495 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_ORDERED_DITHER/256/2
|
2.82% |
8494.707 |
8734.242 |
12.467 |
0.01% |
12.467 |
|
External/SPEC/CFP2017rate/511.povray_r/511.povray_r
Profile
|
2.70% |
27.560 |
28.304 |
0.024 |
-1.16% |
0.024 |
|
SingleSource/Benchmarks/Misc/flops-6
Profile
|
2.69% |
1.802 |
1.850 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint8_t>/16
|
2.69% |
67.276 |
69.085 |
0.027 |
0.51% |
0.027 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint64_t_To_uint16_t_
|
2.69% |
25978.573 |
26677.063 |
56.814 |
-0.17% |
56.814 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint8_t>/28
|
2.64% |
140.814 |
144.530 |
0.004 |
-8.51% |
0.004 |
|
External/SPEC/CFP2017rate/508.namd_r/508.namd_r
Profile
|
2.58% |
181.704 |
186.384 |
0.567 |
-0.52% |
0.567 |
|
MicroBenchmarks/ImageProcessing/AnisotropicDiffusion/AnisotropicDiffusion.test:BENCHMARK_ANISTROPIC_DIFFUSION/128
|
2.48% |
38498.426 |
39451.484 |
72.767 |
-0.08% |
72.767 |
|
MultiSource/Benchmarks/MiBench/consumer-lame/consumer-lame
Profile
|
2.44% |
0.646 |
0.662 |
0.000 |
-2.93% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC32
|
2.41% |
88.239 |
90.364 |
0.134 |
0.95% |
0.134 |
|
MicroBenchmarks/ImageProcessing/BilateralFiltering/BilateralFilter.test:BENCHMARK_BILATERAL_FILTER/16/4
|
2.38% |
372.781 |
381.653 |
0.034 |
-0.01% |
0.034 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C/SimpleMOC/SimpleMOC
Profile
|
2.35% |
7.200 |
7.369 |
0.029 |
-0.62% |
0.029 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_ORDERED_DITHER/128/2
|
2.32% |
2087.605 |
2135.990 |
5.325 |
-0.29% |
5.325 |
|
SingleSource/Benchmarks/Misc/whetstone
Profile
|
2.31% |
2.888 |
2.955 |
0.000 |
0.00% |
0.000 |
|
MultiSource/Benchmarks/ASCI_Purple/SMG2000/smg2000
Profile
|
2.30% |
17.522 |
17.925 |
0.025 |
0.01% |
0.025 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC63
|
2.30% |
162.076 |
165.796 |
0.014 |
-0.01% |
0.014 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint16_t>/16
|
2.27% |
27.532 |
28.156 |
0.002 |
-4.95% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1BigLoopWithReductionTC63
|
2.26% |
162.079 |
165.735 |
0.036 |
0.31% |
0.036 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint16_t>/28
|
2.24% |
85.811 |
87.737 |
0.058 |
-16.04% |
0.058 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC63
|
2.24% |
162.081 |
165.710 |
0.052 |
0.18% |
0.052 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC64
|
2.21% |
162.094 |
165.678 |
0.055 |
0.15% |
0.055 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC32
|
2.20% |
88.230 |
90.169 |
0.136 |
0.75% |
0.136 |
|
MultiSource/Benchmarks/Olden/power/power
Profile
|
2.19% |
3.663 |
3.743 |
0.000 |
-0.02% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC64
|
2.17% |
162.081 |
165.595 |
0.076 |
-0.07% |
0.076 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC64
|
2.16% |
162.078 |
165.587 |
0.101 |
0.13% |
0.101 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC16
|
2.16% |
20.811 |
21.260 |
0.006 |
-0.07% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC64
|
2.13% |
162.080 |
165.530 |
0.139 |
-0.06% |
0.139 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC63
|
2.11% |
162.084 |
165.511 |
0.134 |
-0.01% |
0.134 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC63
|
2.10% |
162.085 |
165.489 |
0.155 |
0.03% |
0.155 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC63
|
2.07% |
162.079 |
165.431 |
0.160 |
0.09% |
0.160 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint32_t>/28
|
2.05% |
84.834 |
86.573 |
0.119 |
0.26% |
0.119 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1BigLoopWithReductionTC32
|
2.02% |
88.231 |
90.012 |
0.234 |
0.47% |
0.234 |
|
External/SPEC/CFP2017rate/519.lbm_r/519.lbm_r
Profile
|
2.01% |
207.934 |
212.120 |
0.735 |
0.21% |
0.735 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC127
|
2.01% |
309.821 |
316.041 |
0.021 |
0.03% |
0.021 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC128
|
1.98% |
309.796 |
315.922 |
0.064 |
-0.05% |
0.064 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC127
|
1.98% |
309.810 |
315.934 |
0.065 |
-0.00% |
0.065 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint8_t>/28
|
1.97% |
63.198 |
64.445 |
0.001 |
1.97% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1BigLoopWithReductionTC64
|
1.97% |
162.083 |
165.268 |
0.258 |
0.05% |
0.258 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC64
|
1.96% |
162.074 |
165.251 |
0.204 |
0.17% |
0.204 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC128
|
1.94% |
309.810 |
315.815 |
0.112 |
-0.01% |
0.112 |
|
SingleSource/Benchmarks/Misc/flops-5
Profile
|
1.93% |
2.535 |
2.584 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1BigLoopWithReductionTC127
|
1.92% |
309.793 |
315.727 |
0.116 |
0.00% |
0.116 |
|
MultiSource/Benchmarks/Fhourstones-3.1/fhourstones3.1
Profile
|
1.91% |
3.847 |
3.920 |
0.003 |
-0.28% |
0.003 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C++/CLAMR/CLAMR
Profile
|
1.91% |
11.915 |
12.142 |
0.021 |
0.18% |
0.021 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint8_t>/10
|
1.90% |
32.673 |
33.295 |
0.017 |
-19.39% |
0.017 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC127
|
1.89% |
309.803 |
315.651 |
0.169 |
0.03% |
0.169 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC4
|
1.88% |
33.163 |
33.788 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC4
|
1.88% |
33.163 |
33.788 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC8
|
1.88% |
33.165 |
33.789 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC8
|
1.88% |
33.164 |
33.788 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC4
|
1.88% |
33.164 |
33.788 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC4
|
1.88% |
33.164 |
33.788 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1BigLoopWithReductionTC3
|
1.88% |
33.163 |
33.787 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1BigLoopWithReductionTC7
|
1.88% |
33.165 |
33.789 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC8
|
1.88% |
33.164 |
33.788 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC1
|
1.88% |
33.164 |
33.788 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC1
|
1.88% |
33.164 |
33.788 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC2
|
1.88% |
33.164 |
33.788 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC7
|
1.88% |
33.165 |
33.788 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC2
|
1.88% |
33.163 |
33.787 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC7
|
1.88% |
33.166 |
33.789 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC1
|
1.88% |
33.165 |
33.789 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC7
|
1.88% |
33.164 |
33.788 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC3
|
1.88% |
33.163 |
33.787 |
0.002 |
-0.01% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC3
|
1.88% |
33.164 |
33.787 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1BigLoopWithReductionTC8
|
1.88% |
33.165 |
33.789 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC2
|
1.88% |
33.165 |
33.788 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC3
|
1.88% |
33.164 |
33.787 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC3
|
1.88% |
33.165 |
33.789 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC1
|
1.88% |
33.165 |
33.787 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC7
|
1.88% |
33.165 |
33.787 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC4
|
1.88% |
33.165 |
33.788 |
0.000 |
-0.01% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC7
|
1.88% |
33.165 |
33.788 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC7
|
1.88% |
33.165 |
33.788 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC2
|
1.88% |
33.165 |
33.788 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC2
|
1.88% |
33.166 |
33.788 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1BigLoopWithReductionTC1
|
1.87% |
33.166 |
33.788 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1BigLoopWithReductionTC4
|
1.87% |
33.166 |
33.787 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC8
|
1.87% |
33.166 |
33.787 |
0.002 |
-0.01% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC8
|
1.87% |
33.168 |
33.789 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC4
|
1.87% |
33.167 |
33.788 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC2
|
1.87% |
33.166 |
33.787 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC3
|
1.87% |
33.167 |
33.787 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC3
|
1.87% |
33.167 |
33.787 |
0.003 |
-0.00% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC8
|
1.87% |
33.169 |
33.787 |
0.002 |
-0.01% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1BigLoopWithReductionTC2
|
1.86% |
33.169 |
33.787 |
0.003 |
-0.00% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint8_t>/28
|
1.86% |
106.565 |
108.546 |
0.004 |
0.41% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC127
|
1.86% |
309.814 |
315.562 |
0.173 |
-0.01% |
0.173 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint8_t>/16
|
1.85% |
28.084 |
28.605 |
0.042 |
-15.85% |
0.042 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC127
|
1.85% |
309.804 |
315.527 |
0.197 |
-0.00% |
0.197 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC1
|
1.82% |
33.183 |
33.788 |
0.003 |
-0.00% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC32
|
1.81% |
88.238 |
89.839 |
0.336 |
0.35% |
0.336 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC63
|
1.80% |
162.092 |
165.004 |
0.330 |
-0.06% |
0.330 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC128
|
1.76% |
309.815 |
315.253 |
0.370 |
-0.11% |
0.370 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC127
|
1.74% |
309.790 |
315.193 |
0.319 |
-0.05% |
0.319 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC128
|
1.73% |
309.847 |
315.216 |
0.353 |
-0.07% |
0.353 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C++/PENNANT/PENNANT
Profile
|
1.73% |
4.525 |
4.604 |
0.026 |
-0.07% |
0.026 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1BigLoopWithReductionTC128
|
1.73% |
309.856 |
315.204 |
0.373 |
-0.07% |
0.373 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC128
|
1.71% |
309.804 |
315.087 |
0.405 |
-0.15% |
0.405 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC128
|
1.69% |
309.799 |
315.042 |
0.390 |
-0.11% |
0.390 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC64
|
1.68% |
162.079 |
164.796 |
0.411 |
-0.01% |
0.411 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint8_t>/16
|
1.60% |
47.560 |
48.320 |
0.005 |
-19.59% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC32
|
1.59% |
88.233 |
89.634 |
0.426 |
0.14% |
0.426 |
|
MultiSource/Benchmarks/nbench/nbench
Profile
|
1.53% |
6.166 |
6.261 |
0.001 |
2.36% |
0.001 |
|
SingleSource/Benchmarks/Misc/oourafft
Profile
|
1.47% |
16.753 |
16.999 |
0.019 |
11.19% |
0.019 |
|
SingleSource/Benchmarks/Shootout-C++/Shootout-C++-sieve
Profile
|
1.46% |
7.454 |
7.563 |
0.006 |
0.07% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC31
|
1.46% |
88.232 |
89.519 |
0.132 |
0.04% |
0.132 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1BigLoopWithReductionTC31
|
1.44% |
88.231 |
89.499 |
0.110 |
0.00% |
0.110 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC32
|
1.43% |
88.233 |
89.491 |
0.381 |
0.00% |
0.381 |
|
MicroBenchmarks/ImageProcessing/BilateralFiltering/BilateralFilter.test:BENCHMARK_BILATERAL_FILTER/32/4
|
1.42% |
2047.717 |
2076.894 |
0.194 |
-0.02% |
0.194 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC31
|
1.42% |
88.233 |
89.487 |
0.032 |
0.00% |
0.032 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC31
|
1.42% |
88.233 |
89.487 |
0.010 |
0.00% |
0.010 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC31
|
1.42% |
88.229 |
89.480 |
0.225 |
-0.01% |
0.225 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC31
|
1.42% |
88.240 |
89.488 |
0.005 |
-0.01% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC31
|
1.41% |
88.232 |
89.480 |
0.001 |
-0.02% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC32
|
1.37% |
88.230 |
89.442 |
0.395 |
-0.05% |
0.395 |
|
SingleSource/Benchmarks/Misc/flops-7
Profile
|
1.29% |
7.533 |
7.631 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchVecWithRuntimeChecks4PointersDEqualsA/32
|
1.27% |
47848.921 |
48458.783 |
4.360 |
-0.01% |
4.360 |
|
MultiSource/Applications/JM/lencod/lencod
Profile
|
1.22% |
34.965 |
35.393 |
0.034 |
-0.99% |
0.034 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC16
|
1.22% |
51.312 |
51.939 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC15
|
1.22% |
51.313 |
51.939 |
0.004 |
-0.00% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC16
|
1.22% |
51.310 |
51.935 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC16
|
1.22% |
51.313 |
51.937 |
0.005 |
-0.01% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC15
|
1.22% |
51.313 |
51.936 |
0.012 |
-0.00% |
0.012 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC15
|
1.21% |
51.311 |
51.935 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC15
|
1.21% |
51.311 |
51.934 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC15
|
1.21% |
51.312 |
51.934 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC16
|
1.21% |
51.312 |
51.933 |
0.003 |
-0.00% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1BigLoopWithReductionTC16
|
1.21% |
51.315 |
51.935 |
0.003 |
0.00% |
0.003 |
|
MultiSource/Benchmarks/7zip/7zip-benchmark
Profile
|
1.21% |
30.013 |
30.375 |
0.026 |
-0.63% |
0.026 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1BigLoopWithReductionTC15
|
1.20% |
51.316 |
51.934 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC15
|
1.20% |
51.310 |
51.926 |
0.018 |
-0.02% |
0.018 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC16
|
1.20% |
51.317 |
51.933 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC16
|
1.20% |
51.317 |
51.933 |
0.003 |
-0.01% |
0.003 |
|
MultiSource/Applications/obsequi/Obsequi
Profile
|
1.13% |
7.349 |
7.432 |
0.011 |
-0.09% |
0.011 |
|
MultiSource/Benchmarks/Ptrdist/ks/ks
Profile
|
1.11% |
2.747 |
2.777 |
0.001 |
-0.03% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint8_t>/10
|
1.05% |
33.466 |
33.817 |
0.023 |
1.33% |
0.023 |
|
SingleSource/Benchmarks/Misc/fbench
Profile
|
1.04% |
6.068 |
6.131 |
0.000 |
0.00% |
0.000 |
|
MultiSource/Benchmarks/Ptrdist/anagram/anagram
Profile
|
1.02% |
2.869 |
2.898 |
0.002 |
2.12% |
0.002 |