|
MultiSource/Benchmarks/MiBench/automotive-bitcount/automotive-bitcount
Profile
|
38.54% |
0.071 |
0.099 |
0.000 |
-0.07% |
0.000 |
|
MultiSource/Benchmarks/Trimaran/enc-pc1/enc-pc1
Profile
|
37.71% |
0.462 |
0.636 |
0.000 |
11.26% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIND_FIRST_MIN_LAMBDA/5001
|
33.29% |
10.732 |
14.305 |
0.000 |
16.85% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIND_FIRST_MIN_LAMBDA/171
|
32.06% |
0.375 |
0.495 |
0.006 |
32.06% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint8_t>/999
|
27.30% |
1704.632 |
2169.950 |
4.828 |
28.04% |
4.828 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint8_t>/999
|
27.11% |
866.997 |
1102.042 |
0.037 |
27.53% |
0.037 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC1
|
26.56% |
5.083 |
6.433 |
0.000 |
12.50% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint8_t>/256
|
23.96% |
465.305 |
576.774 |
0.023 |
26.68% |
0.023 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint8_t>/51
|
23.64% |
105.787 |
130.793 |
0.001 |
22.81% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint8_t>/51
|
23.32% |
64.329 |
79.333 |
0.001 |
24.70% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIRST_DIFF_RAW/171
|
23.30% |
0.303 |
0.373 |
0.003 |
-0.19% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint8_t>/256
|
23.27% |
248.728 |
306.613 |
0.009 |
24.69% |
0.009 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<1, EqZero, First>
|
22.87% |
11918.340 |
14644.174 |
0.598 |
23.08% |
0.598 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint8_t>/28
|
21.87% |
45.745 |
55.747 |
0.002 |
21.86% |
0.002 |
|
External/SPEC/CINT2017rate/525.x264_r/525.x264_r
Profile
|
21.47% |
102.286 |
124.242 |
0.038 |
1.35% |
0.038 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC2
|
20.00% |
7.148 |
8.577 |
0.000 |
19.81% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC2
|
19.99% |
7.147 |
8.576 |
0.000 |
19.93% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint8_t>/28
|
19.99% |
67.903 |
81.475 |
0.003 |
19.98% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint16_t_To_uint8_t_
|
19.95% |
11929.092 |
14308.741 |
2.626 |
19.93% |
2.626 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint16_t_To_uint8_t_
|
19.92% |
11933.902 |
14311.280 |
1.535 |
19.97% |
1.535 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopFrom_uint8_t_To_uint32_t_
|
19.90% |
11928.327 |
14301.978 |
0.224 |
19.84% |
0.224 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint16_t_To_uint32_t_
|
19.90% |
11928.581 |
14301.835 |
5.972 |
19.84% |
5.972 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopFrom_uint16_t_To_uint32_t_
|
19.89% |
11928.390 |
14301.453 |
0.308 |
19.78% |
0.308 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopFrom_uint16_t_To_uint8_t_
|
19.66% |
11951.825 |
14301.706 |
4.688 |
19.87% |
4.688 |
|
SingleSource/Benchmarks/Shootout-C++/Shootout-C++-matrix
Profile
|
18.50% |
5.561 |
6.589 |
0.100 |
-0.01% |
0.100 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_cond_load_autovec_int64_t_
|
17.77% |
678554.801 |
799131.429 |
1537.956 |
0.03% |
1537.956 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_only_autovec_int64_t_
|
16.87% |
678765.504 |
793300.795 |
1209.602 |
-0.04% |
1209.602 |
|
MicroBenchmarks/ImageProcessing/Blur/blur.test:BENCHMARK_boxBlurKernel/512
|
16.86% |
17250.050 |
20158.657 |
21.967 |
-0.03% |
21.967 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint16_t>/65
|
16.44% |
82.913 |
96.541 |
0.627 |
16.43% |
0.627 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint8_t>/16
|
16.41% |
47.889 |
55.747 |
0.002 |
16.40% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint32_t>/16
|
16.27% |
30.734 |
35.735 |
0.001 |
13.63% |
0.001 |
|
MicroBenchmarks/ImageProcessing/Blur/blur.test:BENCHMARK_boxBlurKernel/128
|
16.22% |
927.238 |
1077.593 |
0.094 |
-0.06% |
0.094 |
|
MicroBenchmarks/ImageProcessing/Blur/blur.test:BENCHMARK_boxBlurKernel/256
|
15.96% |
3949.627 |
4579.882 |
7.009 |
-0.05% |
7.009 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint8_t>/16
|
15.38% |
37.168 |
42.883 |
0.001 |
15.27% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC64
|
14.66% |
64.119 |
73.520 |
0.774 |
14.28% |
0.774 |
|
MicroBenchmarks/ImageProcessing/Blur/blur.test:BENCHMARK_boxBlurKernel/1024
|
14.65% |
73815.778 |
84629.250 |
100.925 |
-0.14% |
100.925 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint8_t>/10
|
13.20% |
37.882 |
42.884 |
0.001 |
13.19% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_csa_with_cond_arith_novec_int64_t_
|
12.89% |
693968.254 |
783393.498 |
1312.453 |
13.39% |
1312.453 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint32_t>/28
|
12.72% |
39.312 |
44.313 |
0.002 |
10.70% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_cond_load_novec_int32_t_
|
12.59% |
529570.336 |
596262.887 |
1806.670 |
5.71% |
1806.670 |
|
MultiSource/Benchmarks/Trimaran/enc-md5/enc-md5
Profile
|
12.05% |
2.685 |
3.009 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchAutoVec<uint16_t>/65
|
11.94% |
143.668 |
160.817 |
0.003 |
11.38% |
0.003 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_FLOYD_DITHER/256
|
11.34% |
993.000 |
1105.583 |
0.174 |
-0.01% |
0.174 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchAutoVec<uint16_t>/127
|
10.88% |
269.470 |
298.778 |
8.289 |
10.57% |
8.289 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint8_t>/10
|
10.86% |
32.878 |
36.450 |
0.001 |
10.86% |
0.001 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_FLOYD_DITHER/512
|
10.73% |
3996.360 |
4425.120 |
17.958 |
-0.21% |
17.958 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIND_FIRST_MIN_LAMBDA/44217
|
10.24% |
119.669 |
131.927 |
0.551 |
6.42% |
0.551 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC2
|
10.00% |
7.147 |
7.862 |
0.000 |
-8.33% |
0.000 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_FLOYD_DITHER/128
|
9.73% |
249.592 |
273.867 |
0.374 |
0.04% |
0.374 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_PRESSURE_CALC_RAW/171
|
9.64% |
1.237 |
1.357 |
0.000 |
9.57% |
0.000 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<31, LessThanZero, First>
|
9.38% |
2285.003 |
2499.450 |
0.013 |
9.00% |
0.013 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC4
|
9.09% |
7.862 |
8.577 |
0.000 |
9.09% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC4
|
9.09% |
7.862 |
8.577 |
0.000 |
-20.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC4
|
9.09% |
7.862 |
8.577 |
0.000 |
9.08% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint32_t>/51
|
9.08% |
55.037 |
60.036 |
0.002 |
7.69% |
0.002 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_HYDRO_1D_LAMBDA/171
|
8.77% |
0.456 |
0.496 |
0.000 |
8.77% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIRST_DIFF_RAW/5001
|
8.62% |
10.011 |
10.874 |
0.000 |
0.01% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint32_t>/10
|
8.50% |
33.595 |
36.451 |
0.001 |
6.24% |
0.001 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<15, GreaterThanZero, First>
|
8.45% |
4506.588 |
4887.583 |
6.088 |
8.68% |
6.088 |
|
External/SPEC/CFP2017rate/508.namd_r/508.namd_r
Profile
|
7.89% |
77.654 |
83.778 |
0.075 |
-0.28% |
0.075 |
|
SingleSource/Benchmarks/McGill/misr
Profile
|
7.68% |
0.411 |
0.442 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_cond_load_novec_int64_t_
|
7.60% |
801826.682 |
862734.568 |
1266.558 |
7.54% |
1266.558 |
|
SingleSource/Benchmarks/Shootout/Shootout-lists
Profile
|
7.47% |
9.613 |
10.331 |
0.004 |
-0.04% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint32_t>/10
|
7.31% |
29.305 |
31.448 |
0.001 |
9.99% |
0.001 |
|
MicroBenchmarks/ImageProcessing/Blur/blur.test:BENCHMARK_GAUSSIAN_BLUR/128
|
7.25% |
3350.172 |
3593.077 |
0.393 |
-0.03% |
0.393 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC7
|
7.14% |
10.006 |
10.721 |
0.000 |
7.14% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC7
|
7.14% |
10.006 |
10.721 |
0.000 |
7.14% |
0.000 |
|
MicroBenchmarks/ImageProcessing/Blur/blur.test:BENCHMARK_GAUSSIAN_BLUR/256
|
7.06% |
14333.082 |
15344.891 |
1.938 |
-0.03% |
1.938 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC1
|
6.67% |
5.361 |
5.718 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC1
|
6.66% |
5.361 |
5.718 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC1
|
6.66% |
5.361 |
5.718 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/ImageProcessing/Blur/blur.test:BENCHMARK_GAUSSIAN_BLUR/512
|
6.62% |
59527.917 |
63468.364 |
88.896 |
-0.03% |
88.896 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC31
|
6.56% |
148.905 |
158.669 |
0.003 |
5.97% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC32
|
6.32% |
153.943 |
163.676 |
0.002 |
6.76% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC4
|
6.25% |
11.436 |
12.151 |
0.000 |
6.24% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1LoopWithReductionTC2
|
6.07% |
5.094 |
5.403 |
0.059 |
-0.01% |
0.059 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC128
|
6.03% |
614.749 |
651.829 |
0.042 |
5.36% |
0.042 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC64
|
5.95% |
305.605 |
323.777 |
0.002 |
5.40% |
0.002 |
|
SingleSource/Benchmarks/Adobe-C++/loop_unroll
Profile
|
5.87% |
1.620 |
1.715 |
0.001 |
0.03% |
0.001 |
|
MultiSource/Benchmarks/Trimaran/enc-rc4/enc-rc4
Profile
|
5.82% |
1.827 |
1.933 |
0.003 |
-0.10% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC127
|
5.78% |
612.826 |
648.265 |
0.020 |
5.37% |
0.020 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_no_runtime_checks_needed<16, int>
|
5.76% |
37.168 |
39.308 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<5, LessThanZero, None>
|
5.52% |
20535.679 |
21668.431 |
15.231 |
2.78% |
15.231 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_xor_no_runtime_checks_needed<16, int>
|
5.40% |
26.445 |
27.874 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopTC31
|
5.29% |
274.050 |
288.541 |
0.018 |
0.09% |
0.018 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC31
|
5.27% |
274.018 |
288.460 |
0.041 |
0.10% |
0.041 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC31
|
5.22% |
274.058 |
288.355 |
0.012 |
0.01% |
0.012 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC2
|
5.18% |
5.149 |
5.415 |
0.062 |
-0.12% |
0.062 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopTC128
|
5.15% |
1131.531 |
1189.811 |
0.013 |
-0.19% |
0.013 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC64
|
5.14% |
566.762 |
595.872 |
0.087 |
0.03% |
0.087 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC8
|
5.14% |
41.469 |
43.599 |
0.001 |
5.05% |
0.001 |
|
MultiSource/Applications/JM/lencod/lencod
Profile
|
5.13% |
13.907 |
14.621 |
0.019 |
0.77% |
0.019 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopTC64
|
5.12% |
566.772 |
595.811 |
0.048 |
0.01% |
0.048 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC128
|
5.10% |
1132.085 |
1189.823 |
0.209 |
0.05% |
0.209 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC15
|
5.09% |
136.528 |
143.478 |
0.046 |
0.33% |
0.046 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopTC63
|
5.08% |
559.361 |
587.762 |
0.023 |
0.08% |
0.023 |
|
MultiSource/Benchmarks/VersaBench/ecbdes/ecbdes
Profile
|
5.08% |
3.829 |
4.023 |
0.000 |
-0.02% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC63
|
5.04% |
559.372 |
587.571 |
0.051 |
-0.02% |
0.051 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint32_t>/16
|
5.04% |
42.189 |
44.314 |
0.001 |
3.33% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC127
|
5.03% |
1125.082 |
1181.728 |
0.026 |
-0.00% |
0.026 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC64
|
5.03% |
567.374 |
595.924 |
0.016 |
0.06% |
0.016 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC63
|
5.03% |
559.345 |
587.477 |
0.088 |
-0.56% |
0.088 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC127
|
5.03% |
1125.159 |
1181.723 |
0.047 |
0.11% |
0.047 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopTC127
|
4.97% |
1125.815 |
1181.779 |
0.017 |
-0.16% |
0.017 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIRST_DIFF_RAW/44217
|
4.94% |
91.585 |
96.106 |
0.188 |
0.04% |
0.188 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC128
|
4.94% |
1133.794 |
1189.757 |
0.025 |
-0.01% |
0.025 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC2
|
4.90% |
5.138 |
5.389 |
0.067 |
-37.16% |
0.067 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<8, LessThanZero, Last>
|
4.86% |
14664.572 |
15377.892 |
5.457 |
-0.00% |
5.457 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<15, LessThanZero, Mid>
|
4.83% |
7825.068 |
8203.141 |
4.401 |
-0.02% |
4.401 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC2
|
4.83% |
5.184 |
5.435 |
0.038 |
-0.03% |
0.038 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint32_t>/28
|
4.81% |
59.326 |
62.182 |
0.001 |
3.56% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopTC3
|
4.80% |
27.436 |
28.754 |
0.002 |
0.92% |
0.002 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<8, LessThanZero, None>
|
4.76% |
15029.650 |
15744.518 |
7.401 |
2.37% |
7.401 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC7
|
4.76% |
15.010 |
15.724 |
0.000 |
46.64% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_DEL_DOT_VEC_2D_RAW/1
|
4.66% |
190.522 |
199.404 |
0.880 |
0.06% |
0.880 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopTC8
|
4.66% |
70.590 |
73.877 |
0.002 |
0.33% |
0.002 |
|
SingleSource/Benchmarks/Misc/salsa20
Profile
|
4.53% |
10.432 |
10.905 |
0.000 |
-0.66% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC8
|
4.48% |
70.564 |
73.724 |
0.025 |
-0.11% |
0.025 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint64_t>/51
|
4.47% |
130.089 |
135.907 |
0.136 |
5.63% |
0.136 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC63
|
4.45% |
305.850 |
319.468 |
0.013 |
5.65% |
0.013 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC2
|
4.44% |
5.168 |
5.397 |
0.075 |
-0.53% |
0.075 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC8
|
4.40% |
70.563 |
73.669 |
0.052 |
0.22% |
0.052 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopTC16
|
4.33% |
146.345 |
152.684 |
0.002 |
0.08% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC16
|
4.33% |
146.346 |
152.682 |
0.003 |
0.09% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC16
|
4.33% |
146.344 |
152.673 |
0.004 |
0.02% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint16_t_To_uint32_t_
|
4.29% |
20570.513 |
21452.392 |
9.539 |
-0.00% |
9.539 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopTC15
|
4.19% |
138.102 |
143.890 |
0.181 |
1.90% |
0.181 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<8, GreaterThanZero, First>
|
4.12% |
8443.520 |
8791.578 |
11.527 |
4.24% |
11.527 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC4
|
4.08% |
23.349 |
24.300 |
0.001 |
4.08% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC15
|
4.04% |
136.522 |
142.032 |
0.117 |
-2.10% |
0.117 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC15
|
3.96% |
75.628 |
78.623 |
0.001 |
3.94% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC16
|
3.84% |
80.530 |
83.625 |
0.001 |
3.70% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC3
|
3.82% |
27.429 |
28.476 |
0.053 |
0.09% |
0.053 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC3
|
3.76% |
27.429 |
28.459 |
0.035 |
-0.53% |
0.035 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC32
|
3.70% |
282.859 |
293.323 |
0.003 |
0.11% |
0.003 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_VOL3D_CALC_LAMBDA/2
|
3.66% |
7.490 |
7.764 |
0.001 |
-0.02% |
0.001 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<3, LessThanZero, Mid>
|
3.66% |
25422.112 |
26351.380 |
19.665 |
0.01% |
19.665 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, LessThanZero, Last>
|
3.65% |
38138.218 |
39531.737 |
27.317 |
-0.01% |
27.317 |
|
MultiSource/Benchmarks/mafft/pairlocalalign
Profile
|
3.63% |
46.224 |
47.903 |
0.009 |
0.74% |
0.009 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopTC32
|
3.63% |
282.944 |
293.212 |
0.035 |
0.06% |
0.035 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_ENERGY_CALC_RAW/44217
|
3.61% |
2210.700 |
2290.595 |
27.696 |
0.08% |
27.696 |
|
MultiSource/Benchmarks/sim/sim
Profile
|
3.61% |
6.376 |
6.606 |
0.006 |
-1.54% |
0.006 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_DEL_DOT_VEC_2D_LAMBDA/1
|
3.60% |
191.404 |
198.302 |
1.287 |
-0.05% |
1.287 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC32
|
3.60% |
282.856 |
293.033 |
0.012 |
0.00% |
0.012 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_VOL3D_CALC_RAW/2
|
3.58% |
7.496 |
7.764 |
0.002 |
-0.00% |
0.002 |
|
MultiSource/Applications/siod/siod
Profile
|
3.54% |
5.482 |
5.676 |
0.009 |
3.92% |
0.009 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_two_loads<uint32_t>/10
|
3.33% |
21.443 |
22.157 |
0.001 |
3.32% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_two_loads<uint32_t>/16
|
3.33% |
21.443 |
22.157 |
0.001 |
3.32% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_two_loads<uint32_t>/51
|
3.33% |
21.444 |
22.157 |
0.000 |
3.33% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_two_loads<uint32_t>/28
|
3.32% |
21.444 |
22.157 |
0.000 |
3.32% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_two_loads<uint32_t>/999
|
3.32% |
21.443 |
22.156 |
0.000 |
3.33% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_two_loads<uint32_t>/256
|
3.32% |
21.443 |
22.156 |
0.001 |
3.32% |
0.001 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, LessThanZero, None>
|
3.28% |
42527.921 |
43922.884 |
31.783 |
-3.22% |
31.783 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_two_loads<uint8_t>/10
|
3.23% |
22.156 |
22.871 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_two_loads<uint8_t>/16
|
3.22% |
22.157 |
22.871 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_two_loads<uint8_t>/28
|
3.22% |
22.158 |
22.872 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint16_t>/999
|
3.22% |
22.158 |
22.872 |
0.001 |
3.22% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_two_loads<uint8_t>/51
|
3.22% |
22.157 |
22.871 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_two_loads<uint8_t>/256
|
3.22% |
22.157 |
22.871 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint32_t>/10
|
3.22% |
22.158 |
22.871 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_two_loads<uint8_t>/999
|
3.22% |
22.157 |
22.871 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint16_t>/51
|
3.22% |
22.157 |
22.871 |
0.001 |
3.21% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint16_t>/256
|
3.22% |
22.157 |
22.870 |
0.001 |
3.21% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint16_t>/16
|
3.22% |
22.158 |
22.871 |
0.001 |
3.22% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint32_t>/999
|
3.22% |
22.158 |
22.871 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint32_t>/256
|
3.21% |
22.158 |
22.871 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint32_t>/28
|
3.21% |
22.158 |
22.871 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint16_t>/28
|
3.21% |
22.158 |
22.871 |
0.000 |
3.21% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint16_t>/10
|
3.21% |
22.158 |
22.870 |
0.001 |
3.22% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint32_t>/16
|
3.20% |
22.162 |
22.870 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<3, LessThanZero, Last>
|
3.19% |
29338.978 |
30274.020 |
12.187 |
0.07% |
12.187 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint32_t>/51
|
3.18% |
22.166 |
22.871 |
0.001 |
-0.00% |
0.001 |
|
MultiSource/Benchmarks/PAQ8p/paq8p
Profile
|
3.17% |
131.575 |
135.747 |
0.041 |
3.25% |
0.041 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<5, GreaterThanZero, Mid>
|
3.15% |
17605.674 |
18160.148 |
14.618 |
3.36% |
14.618 |
|
MultiSource/Benchmarks/nbench/nbench
Profile
|
3.15% |
3.752 |
3.870 |
0.003 |
2.37% |
0.003 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<3, EqZero, Last>
|
3.14% |
29340.166 |
30262.696 |
24.558 |
3.36% |
24.558 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<3, LessThanZero, None>
|
3.06% |
30299.424 |
31226.812 |
22.610 |
-0.00% |
22.610 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, LessThanZero, Mid>
|
3.05% |
22742.292 |
23436.289 |
1.316 |
3.25% |
1.316 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<7, EqZero, Mid>
|
2.99% |
13410.842 |
13812.332 |
7.229 |
3.15% |
7.229 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<32, EqZero, Mid>
|
2.86% |
3121.313 |
3210.647 |
0.904 |
2.90% |
0.904 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, LessThanZero, None>
|
2.84% |
24206.343 |
24893.208 |
15.906 |
0.01% |
15.906 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<5, EqZero, Last>
|
2.81% |
19942.360 |
20502.460 |
11.116 |
2.96% |
11.116 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<8, GreaterThanZero, Mid>
|
2.79% |
12468.178 |
12816.349 |
7.943 |
2.93% |
7.943 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<5, LessThanZero, Last>
|
2.75% |
20516.252 |
21081.255 |
18.551 |
2.81% |
18.551 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint8_t>/127
|
2.75% |
166.943 |
171.534 |
0.541 |
0.82% |
0.541 |
|
MicroBenchmarks/Builtins/Int128/Builtins.test:BM_DivideIntrinsic128UniformDivisor<__uint128_t>
|
2.71% |
37.484 |
38.500 |
0.033 |
3.03% |
0.033 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_DEL_DOT_VEC_2D_LAMBDA/2
|
2.67% |
2.345 |
2.408 |
0.019 |
2.68% |
0.019 |
|
MultiSource/Applications/aha/aha
Profile
|
2.64% |
3.776 |
3.875 |
0.001 |
-0.44% |
0.001 |
|
SingleSource/Benchmarks/Misc/revertBits
Profile
|
2.63% |
0.401 |
0.411 |
0.000 |
-0.01% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC2
|
2.62% |
20.009 |
20.534 |
0.010 |
-1.43% |
0.010 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<6, GreaterThanZero, Last>
|
2.62% |
17584.129 |
18044.302 |
7.564 |
2.77% |
7.564 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC128
|
2.51% |
155.484 |
159.390 |
0.008 |
-17.41% |
0.008 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<6, LessThanZero, None>
|
2.51% |
18078.338 |
18531.371 |
11.278 |
-0.00% |
11.278 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint64_t>/10
|
2.50% |
28.590 |
29.303 |
0.001 |
-0.01% |
0.001 |
|
MultiSource/Benchmarks/Fhourstones/fhourstones
Profile
|
2.49% |
2.326 |
2.384 |
0.014 |
2.97% |
0.014 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<7, EqZero, None>
|
2.38% |
16343.147 |
16732.734 |
10.629 |
2.56% |
10.629 |
|
MicroBenchmarks/ImageProcessing/Blur/blur.test:BENCHMARK_GAUSSIAN_BLUR/1024
|
2.31% |
255792.667 |
261704.667 |
2.514 |
0.01% |
2.514 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopTC2
|
2.29% |
20.010 |
20.470 |
0.015 |
-0.81% |
0.015 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint32_t>/51
|
2.27% |
92.250 |
94.341 |
0.003 |
0.75% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC8
|
2.22% |
10.721 |
10.960 |
0.000 |
-4.17% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC8
|
2.22% |
10.721 |
10.959 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC8
|
2.22% |
10.721 |
10.959 |
0.000 |
-33.33% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint32_t>/10
|
2.21% |
32.165 |
32.877 |
0.001 |
2.21% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC128
|
2.21% |
157.957 |
161.446 |
0.453 |
5.01% |
0.453 |
|
MultiSource/Applications/hexxagon/hexxagon
Profile
|
2.18% |
9.034 |
9.231 |
0.002 |
-3.66% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1BigLoopWithReductionTC64
|
2.17% |
305.614 |
312.246 |
0.254 |
1.64% |
0.254 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC2
|
2.16% |
20.044 |
20.477 |
0.014 |
-0.70% |
0.014 |
|
MultiSource/Benchmarks/MiBench/telecomm-CRC32/telecomm-CRC32
Profile
|
2.15% |
0.584 |
0.597 |
0.002 |
-0.37% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint8_t>/10
|
2.12% |
33.593 |
34.306 |
0.001 |
-0.00% |
0.001 |
|
External/SPEC/CINT2017rate/500.perlbench_r/500.perlbench_r
Profile
|
2.07% |
101.306 |
103.399 |
0.120 |
2.26% |
0.120 |
|
SingleSource/Benchmarks/Adobe-C++/functionobjects
Profile
|
1.99% |
5.944 |
6.063 |
0.002 |
-0.01% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint16_t>/10
|
1.96% |
36.453 |
37.166 |
0.001 |
1.92% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC128
|
1.81% |
157.951 |
160.805 |
0.005 |
3.44% |
0.005 |
|
SingleSource/Benchmarks/Stanford/FloatMM
Profile
|
1.71% |
0.756 |
0.769 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint8_t>/16
|
1.69% |
42.170 |
42.883 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<31, LessThanZero, None>
|
1.69% |
5180.790 |
5268.222 |
2.012 |
0.03% |
2.012 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_asinf_autovec_float_
|
1.66% |
385.432 |
391.824 |
0.264 |
1.65% |
0.264 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint16_t>/16
|
1.66% |
42.888 |
43.598 |
0.000 |
-3.17% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint16_t>/10
|
1.51% |
47.176 |
47.888 |
0.000 |
-0.01% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_DEL_DOT_VEC_2D_RAW/0
|
1.49% |
1203.923 |
1221.866 |
1.207 |
0.15% |
1.207 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint64_t>/10
|
1.46% |
48.606 |
49.316 |
0.002 |
4.54% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC31
|
1.45% |
49.317 |
50.031 |
0.001 |
52.16% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint16_t_To_uint64_t_
|
1.38% |
21898.599 |
22199.772 |
1.704 |
-0.01% |
1.704 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC15
|
1.37% |
17.392 |
17.630 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC15
|
1.37% |
17.392 |
17.630 |
0.000 |
-33.33% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC15
|
1.37% |
17.392 |
17.630 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC15
|
1.37% |
17.392 |
17.630 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1LoopWithReductionTC15
|
1.37% |
17.392 |
17.630 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/16
|
1.29% |
119.070 |
120.606 |
0.002 |
0.03% |
0.002 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_VOL3D_CALC_RAW/1
|
1.24% |
206.007 |
208.555 |
0.983 |
-0.32% |
0.983 |
|
MultiSource/Benchmarks/Ptrdist/anagram/anagram
Profile
|
1.21% |
1.887 |
1.909 |
0.001 |
-0.04% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint8_t>/28
|
1.20% |
59.325 |
60.036 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<31, GreaterThanZero, None>
|
1.19% |
5195.791 |
5257.455 |
2.374 |
1.34% |
2.374 |
|
External/SPEC/CINT2017rate/531.deepsjeng_r/531.deepsjeng_r
Profile
|
1.15% |
136.994 |
138.574 |
0.098 |
0.83% |
0.098 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_expf_novec_float_
|
1.15% |
458.074 |
463.330 |
0.071 |
1.66% |
0.071 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_VOL3D_CALC_LAMBDA/1
|
1.14% |
207.312 |
209.677 |
0.723 |
0.21% |
0.723 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint64_t>/16
|
1.08% |
65.760 |
66.467 |
0.002 |
6.89% |
0.002 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<31, GreaterThanZero, Mid>
|
1.06% |
4956.689 |
5009.226 |
1.371 |
1.15% |
1.371 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<63, GreaterThanZero, None>
|
1.05% |
3025.926 |
3057.698 |
0.366 |
1.15% |
0.366 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/32
|
1.02% |
593.421 |
599.473 |
0.248 |
-0.01% |
0.248 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/64
|
1.01% |
2623.596 |
2650.125 |
0.056 |
0.00% |
0.056 |
|
External/SPEC/CFP2017rate/544.nab_r/544.nab_r
Profile
|
1.00% |
277.379 |
280.156 |
0.082 |
-0.01% |
0.082 |