|
MultiSource/Benchmarks/MiBench/automotive-bitcount/automotive-bitcount
Profile
|
-29.14% |
0.099 |
0.070 |
0.000 |
-29.19% |
0.000 |
|
MultiSource/Benchmarks/Trimaran/enc-pc1/enc-pc1
Profile
|
-27.43% |
0.636 |
0.461 |
0.000 |
-18.96% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIND_FIRST_MIN_LAMBDA/5001
|
-24.99% |
14.305 |
10.731 |
0.000 |
-11.92% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIND_FIRST_MIN_LAMBDA/171
|
-24.43% |
0.495 |
0.374 |
0.000 |
-0.20% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint8_t>/999
|
-21.53% |
1102.042 |
864.826 |
1.005 |
0.08% |
1.005 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIRST_DIFF_LAMBDA/171
|
-21.52% |
0.373 |
0.293 |
0.004 |
-21.53% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint8_t>/999
|
-21.51% |
2169.950 |
1703.109 |
1.026 |
0.49% |
1.026 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC1
|
-20.99% |
6.433 |
5.082 |
0.000 |
-11.08% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint8_t>/256
|
-19.58% |
306.613 |
246.572 |
1.007 |
0.28% |
1.007 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint8_t>/256
|
-19.58% |
576.774 |
463.854 |
1.011 |
1.88% |
1.011 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint8_t>/51
|
-19.13% |
130.793 |
105.775 |
0.001 |
-0.68% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint8_t>/51
|
-18.92% |
79.333 |
64.323 |
0.001 |
1.11% |
0.001 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<1, EqZero, First>
|
-18.85% |
14644.174 |
11884.179 |
10.888 |
-0.02% |
10.888 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint8_t>/28
|
-17.95% |
55.747 |
45.740 |
0.001 |
-0.01% |
0.001 |
|
External/SPEC/CINT2017rate/525.x264_r/525.x264_r
Profile
|
-17.73% |
124.242 |
102.212 |
0.061 |
-16.49% |
0.061 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint16_t_To_uint8_t_
|
-16.71% |
14311.280 |
11919.337 |
5.298 |
-0.07% |
5.298 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC2
|
-16.67% |
8.577 |
7.147 |
0.000 |
-0.01% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint8_t>/28
|
-16.66% |
81.475 |
67.898 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC2
|
-16.66% |
8.576 |
7.147 |
0.000 |
-0.01% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint16_t_To_uint8_t_
|
-16.63% |
14308.741 |
11928.753 |
0.212 |
-0.01% |
0.212 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopFrom_uint8_t_To_uint32_t_
|
-16.60% |
14301.978 |
11927.835 |
0.139 |
-0.05% |
0.139 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint16_t_To_uint32_t_
|
-16.60% |
14301.835 |
11928.277 |
5.906 |
-0.04% |
5.906 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopFrom_uint16_t_To_uint32_t_
|
-16.59% |
14301.453 |
11928.422 |
0.169 |
-0.05% |
0.169 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopFrom_uint16_t_To_uint8_t_
|
-16.59% |
14301.706 |
11928.968 |
4.617 |
-0.00% |
4.617 |
|
SingleSource/Benchmarks/Shootout-C++/Shootout-C++-matrix
Profile
|
-15.62% |
6.589 |
5.560 |
0.003 |
-15.62% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_cond_load_autovec_int64_t_
|
-15.21% |
799131.429 |
677552.427 |
238.752 |
-15.19% |
238.752 |
|
MicroBenchmarks/ImageProcessing/Blur/blur.test:BENCHMARK_boxBlurKernel/512
|
-15.02% |
20158.657 |
17131.125 |
26.713 |
-15.05% |
26.713 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_only_autovec_int64_t_
|
-14.71% |
793300.795 |
676612.186 |
365.320 |
-14.74% |
365.320 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint16_t>/65
|
-14.12% |
96.541 |
82.907 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint8_t>/16
|
-14.10% |
55.747 |
47.886 |
0.000 |
-0.01% |
0.000 |
|
MicroBenchmarks/ImageProcessing/Blur/blur.test:BENCHMARK_boxBlurKernel/128
|
-14.05% |
1077.593 |
926.171 |
0.172 |
-14.10% |
0.172 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint32_t>/16
|
-14.00% |
35.735 |
30.732 |
0.001 |
-2.27% |
0.001 |
|
MicroBenchmarks/ImageProcessing/Blur/blur.test:BENCHMARK_boxBlurKernel/256
|
-13.82% |
4579.882 |
3946.768 |
0.899 |
-13.86% |
0.899 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_cond_load_novec_int32_t_
|
-13.59% |
596262.887 |
515233.962 |
7927.266 |
-7.61% |
7927.266 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint8_t>/16
|
-13.34% |
42.883 |
37.164 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIND_FIRST_MIN_RAW/5001
|
-12.92% |
12.323 |
10.730 |
0.000 |
-12.99% |
0.000 |
|
MicroBenchmarks/ImageProcessing/Blur/blur.test:BENCHMARK_boxBlurKernel/1024
|
-12.83% |
84629.250 |
73769.667 |
13.114 |
-12.95% |
13.114 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC64
|
-12.79% |
73.520 |
64.115 |
0.001 |
-0.32% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_csa_with_cond_arith_novec_int64_t_
|
-11.85% |
783393.498 |
690599.802 |
945.272 |
-0.04% |
945.272 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint8_t>/10
|
-11.67% |
42.884 |
37.880 |
0.000 |
-0.01% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIND_FIRST_MIN_LAMBDA/44217
|
-11.31% |
131.927 |
117.003 |
1.170 |
-5.37% |
1.170 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint32_t>/28
|
-11.29% |
44.313 |
39.309 |
0.001 |
-1.79% |
0.001 |
|
MultiSource/Benchmarks/Trimaran/enc-md5/enc-md5
Profile
|
-10.79% |
3.009 |
2.684 |
0.001 |
-10.80% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchAutoVec<uint16_t>/65
|
-10.67% |
160.817 |
143.662 |
0.002 |
-0.50% |
0.002 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_FLOYD_DITHER/256
|
-10.25% |
1105.583 |
992.261 |
0.308 |
-10.13% |
0.308 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_FLOYD_DITHER/512
|
-10.22% |
4425.120 |
3972.841 |
8.120 |
-10.41% |
8.120 |
|
SingleSource/Benchmarks/Polybench/linear-algebra/blas/gemver/gemver
Profile
|
-9.97% |
0.317 |
0.285 |
0.007 |
-4.88% |
0.007 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchAutoVec<uint16_t>/127
|
-9.81% |
298.778 |
269.455 |
0.009 |
-0.26% |
0.009 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint8_t>/10
|
-9.80% |
36.450 |
32.876 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIND_FIRST_MIN_RAW/171
|
-9.60% |
0.413 |
0.373 |
0.001 |
-9.60% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC2
|
-9.09% |
7.862 |
7.147 |
0.000 |
-16.66% |
0.000 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_FLOYD_DITHER/128
|
-9.02% |
273.867 |
249.161 |
0.447 |
-8.91% |
0.447 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_ENERGY_CALC_RAW/44217
|
-8.86% |
2290.595 |
2087.595 |
39.043 |
-6.77% |
39.043 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<31, LessThanZero, First>
|
-8.76% |
2499.450 |
2280.602 |
1.987 |
-0.53% |
1.987 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC4
|
-8.34% |
8.577 |
7.862 |
0.000 |
-26.66% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC4
|
-8.33% |
8.577 |
7.862 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC4
|
-8.33% |
8.577 |
7.862 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint32_t>/51
|
-8.33% |
60.036 |
55.033 |
0.000 |
-1.28% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_HYDRO_1D_LAMBDA/171
|
-8.07% |
0.496 |
0.456 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<15, GreaterThanZero, First>
|
-8.02% |
4887.583 |
4495.539 |
5.137 |
-0.04% |
5.137 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIRST_DIFF_LAMBDA/5001
|
-7.95% |
10.874 |
10.010 |
0.000 |
-7.95% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint32_t>/10
|
-7.84% |
36.451 |
33.592 |
0.000 |
-2.09% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_cond_load_novec_int64_t_
|
-7.82% |
862734.568 |
795258.797 |
1301.904 |
-0.67% |
1301.904 |
|
External/SPEC/CFP2017rate/508.namd_r/508.namd_r
Profile
|
-7.43% |
83.778 |
77.550 |
0.062 |
-7.69% |
0.062 |
|
SingleSource/Benchmarks/Shootout/Shootout-lists
Profile
|
-7.27% |
10.331 |
9.580 |
0.002 |
-7.31% |
0.002 |
|
SingleSource/Benchmarks/McGill/misr
Profile
|
-7.21% |
0.442 |
0.410 |
0.000 |
-7.21% |
0.000 |
|
MicroBenchmarks/ImageProcessing/Blur/blur.test:BENCHMARK_GAUSSIAN_BLUR/128
|
-7.07% |
3593.077 |
3338.881 |
1.171 |
-7.10% |
1.171 |
|
MicroBenchmarks/ImageProcessing/Blur/blur.test:BENCHMARK_GAUSSIAN_BLUR/256
|
-7.04% |
15344.891 |
14264.531 |
10.360 |
-7.07% |
10.360 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint32_t>/10
|
-6.82% |
31.448 |
29.302 |
0.001 |
2.49% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC7
|
-6.67% |
10.721 |
10.006 |
0.000 |
-0.01% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC7
|
-6.67% |
10.721 |
10.006 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/ImageProcessing/Blur/blur.test:BENCHMARK_GAUSSIAN_BLUR/512
|
-6.64% |
63468.364 |
59252.000 |
57.766 |
-6.68% |
57.766 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIND_FIRST_MIN_RAW/44217
|
-6.45% |
126.610 |
118.450 |
0.038 |
-6.97% |
0.038 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC1
|
-6.29% |
5.718 |
5.358 |
0.001 |
-6.28% |
0.001 |
|
MultiSource/Applications/JM/lencod/lencod
Profile
|
-6.27% |
14.621 |
13.704 |
0.006 |
-5.27% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC1
|
-6.25% |
5.718 |
5.360 |
0.000 |
-6.25% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC1
|
-6.25% |
5.718 |
5.361 |
0.000 |
-6.25% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC32
|
-6.23% |
163.676 |
153.475 |
0.184 |
0.11% |
0.184 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC31
|
-6.16% |
158.669 |
148.893 |
0.004 |
-0.55% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC2
|
-6.12% |
5.389 |
5.060 |
0.025 |
-41.01% |
0.025 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC127
|
-6.05% |
648.265 |
609.043 |
1.461 |
-0.75% |
1.461 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1LoopWithReductionTC2
|
-6.04% |
5.403 |
5.077 |
0.023 |
-5.98% |
0.023 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC4
|
-5.89% |
12.151 |
11.436 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_ICCG_LAMBDA/44217
|
-5.81% |
297.734 |
280.443 |
4.523 |
-4.65% |
4.523 |
|
SingleSource/Benchmarks/Adobe-C++/loop_unroll
Profile
|
-5.73% |
1.715 |
1.617 |
0.001 |
-5.70% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC2
|
-5.72% |
5.435 |
5.124 |
0.034 |
-4.69% |
0.034 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC128
|
-5.72% |
651.829 |
614.571 |
0.019 |
-0.65% |
0.019 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC64
|
-5.62% |
323.777 |
305.576 |
0.012 |
-0.52% |
0.012 |
|
MultiSource/Benchmarks/Trimaran/enc-rc4/enc-rc4
Profile
|
-5.54% |
1.933 |
1.826 |
0.000 |
-5.64% |
0.000 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_no_runtime_checks_needed<16, int>
|
-5.45% |
39.308 |
37.166 |
0.000 |
-5.45% |
0.000 |
|
MicroBenchmarks/LoopInterchange/LoopInterchange.test:BENCHMARK_LI1
|
-5.42% |
2563.655 |
2424.828 |
46.637 |
-22.78% |
46.637 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<5, LessThanZero, None>
|
-5.41% |
21668.431 |
20495.520 |
18.779 |
-2.77% |
18.779 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC2
|
-5.37% |
5.397 |
5.107 |
0.015 |
-5.87% |
0.015 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC2
|
-5.37% |
5.415 |
5.125 |
0.042 |
-5.48% |
0.042 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIRST_DIFF_LAMBDA/44217
|
-5.18% |
96.080 |
91.106 |
0.017 |
-5.17% |
0.017 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_xor_no_runtime_checks_needed<16, int>
|
-5.13% |
27.874 |
26.443 |
0.001 |
-5.13% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopTC15
|
-5.13% |
143.890 |
136.515 |
0.002 |
-3.24% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_only_autovec_int32_t_
|
-5.07% |
569204.397 |
540364.760 |
9355.201 |
-2.35% |
9355.201 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopTC31
|
-5.03% |
288.541 |
274.021 |
0.017 |
-4.94% |
0.017 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC31
|
-5.00% |
288.460 |
274.024 |
0.023 |
-4.91% |
0.023 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC31
|
-4.98% |
288.355 |
273.993 |
0.039 |
-4.96% |
0.039 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC8
|
-4.92% |
43.599 |
41.453 |
0.047 |
-0.04% |
0.047 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC128
|
-4.90% |
1189.757 |
1131.413 |
0.392 |
-4.91% |
0.392 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopTC128
|
-4.90% |
1189.811 |
1131.471 |
0.072 |
-5.08% |
0.072 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC64
|
-4.89% |
595.872 |
566.734 |
0.020 |
-4.85% |
0.020 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopTC64
|
-4.88% |
595.811 |
566.756 |
0.011 |
-4.85% |
0.011 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_DEL_DOT_VEC_2D_RAW/1
|
-4.86% |
199.404 |
189.711 |
0.554 |
-3.09% |
0.554 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC128
|
-4.86% |
1189.823 |
1132.012 |
0.040 |
-4.81% |
0.040 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC15
|
-4.86% |
143.478 |
136.512 |
0.005 |
-4.43% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint32_t>/16
|
-4.84% |
44.314 |
42.168 |
0.001 |
-1.67% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopTC63
|
-4.84% |
587.762 |
559.332 |
0.008 |
-4.75% |
0.008 |
|
MultiSource/Benchmarks/VersaBench/ecbdes/ecbdes
Profile
|
-4.84% |
4.023 |
3.829 |
0.000 |
-4.86% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC63
|
-4.80% |
587.571 |
559.342 |
0.005 |
-4.82% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopTC127
|
-4.80% |
1181.779 |
1125.044 |
0.065 |
-4.95% |
0.065 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC127
|
-4.80% |
1181.728 |
1125.057 |
0.035 |
-4.80% |
0.035 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC64
|
-4.79% |
595.924 |
567.351 |
0.007 |
-4.72% |
0.007 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC127
|
-4.79% |
1181.723 |
1125.070 |
0.028 |
-4.68% |
0.028 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC63
|
-4.79% |
587.477 |
559.314 |
0.022 |
-5.33% |
0.022 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<8, LessThanZero, Last>
|
-4.75% |
15377.892 |
14647.408 |
7.752 |
-4.75% |
7.752 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<15, LessThanZero, Mid>
|
-4.74% |
8203.141 |
7814.188 |
4.976 |
-4.76% |
4.976 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<8, LessThanZero, None>
|
-4.65% |
15744.518 |
15011.988 |
8.341 |
-2.39% |
8.341 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopTC3
|
-4.61% |
28.754 |
27.429 |
0.003 |
-3.72% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint32_t>/28
|
-4.60% |
62.182 |
59.321 |
0.001 |
-1.20% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC7
|
-4.54% |
15.724 |
15.009 |
0.000 |
39.98% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopTC8
|
-4.46% |
73.877 |
70.582 |
0.003 |
-4.14% |
0.003 |
|
SingleSource/Benchmarks/Misc/salsa20
Profile
|
-4.34% |
10.905 |
10.432 |
0.000 |
-4.97% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC7
|
-4.33% |
38.597 |
36.926 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC63
|
-4.31% |
319.468 |
305.715 |
0.112 |
1.10% |
0.112 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint64_t>/51
|
-4.29% |
135.907 |
130.077 |
0.003 |
1.10% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC8
|
-4.29% |
73.724 |
70.561 |
0.001 |
-4.40% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC8
|
-4.22% |
73.669 |
70.560 |
0.002 |
-4.00% |
0.002 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<8, GreaterThanZero, First>
|
-4.16% |
8791.578 |
8425.878 |
8.087 |
-0.00% |
8.087 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopTC16
|
-4.16% |
152.684 |
146.335 |
0.005 |
-4.08% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC16
|
-4.15% |
152.682 |
146.340 |
0.002 |
-4.06% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC16
|
-4.15% |
152.673 |
146.345 |
0.001 |
-4.12% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint16_t_To_uint32_t_
|
-4.14% |
21452.392 |
20564.290 |
1.806 |
-4.13% |
1.806 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_DEL_DOT_VEC_2D_LAMBDA/1
|
-4.04% |
198.302 |
190.294 |
0.412 |
-3.60% |
0.412 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC4
|
-3.93% |
24.300 |
23.346 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC15
|
-3.88% |
142.032 |
136.515 |
0.003 |
-5.90% |
0.003 |
|
MultiSource/Applications/siod/siod
Profile
|
-3.86% |
5.676 |
5.457 |
0.003 |
0.07% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC15
|
-3.82% |
78.623 |
75.615 |
0.003 |
-0.03% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC3
|
-3.77% |
28.459 |
27.386 |
0.014 |
-4.28% |
0.014 |
|
MultiSource/Benchmarks/sim/sim
Profile
|
-3.71% |
6.606 |
6.361 |
0.003 |
-5.20% |
0.003 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<3, LessThanZero, Mid>
|
-3.71% |
26351.380 |
25374.257 |
20.985 |
-3.70% |
20.985 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC16
|
-3.71% |
83.625 |
80.524 |
0.003 |
-0.14% |
0.003 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, LessThanZero, Last>
|
-3.70% |
39531.737 |
38067.105 |
32.043 |
-3.72% |
32.043 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC3
|
-3.70% |
28.476 |
27.422 |
0.002 |
-3.62% |
0.002 |
|
MultiSource/Benchmarks/mafft/pairlocalalign
Profile
|
-3.68% |
47.903 |
46.140 |
0.007 |
-2.87% |
0.007 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC32
|
-3.57% |
293.323 |
282.840 |
0.006 |
-3.37% |
0.006 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_VOL3D_CALC_RAW/2
|
-3.54% |
7.764 |
7.490 |
0.003 |
-3.54% |
0.003 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_VOL3D_CALC_LAMBDA/2
|
-3.53% |
7.764 |
7.490 |
0.000 |
-3.54% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopTC32
|
-3.51% |
293.212 |
282.925 |
0.010 |
-3.39% |
0.010 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC32
|
-3.48% |
293.033 |
282.843 |
0.044 |
-3.44% |
0.044 |
|
MultiSource/Benchmarks/Fhourstones/fhourstones
Profile
|
-3.43% |
2.384 |
2.302 |
0.011 |
-0.13% |
0.011 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, LessThanZero, None>
|
-3.34% |
43922.884 |
42457.661 |
30.367 |
-6.45% |
30.367 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<3, LessThanZero, Last>
|
-3.30% |
30274.020 |
29276.233 |
25.775 |
-3.22% |
25.775 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<3, EqZero, Last>
|
-3.26% |
30262.696 |
29275.461 |
29.537 |
-0.00% |
29.537 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<5, GreaterThanZero, Mid>
|
-3.26% |
18160.148 |
17568.905 |
17.273 |
0.00% |
17.273 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_two_loads<uint32_t>/51
|
-3.23% |
22.157 |
21.442 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_two_loads<uint32_t>/16
|
-3.23% |
22.157 |
21.441 |
0.000 |
-0.01% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_two_loads<uint32_t>/10
|
-3.23% |
22.157 |
21.442 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_two_loads<uint32_t>/999
|
-3.23% |
22.156 |
21.441 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_two_loads<uint32_t>/28
|
-3.23% |
22.157 |
21.442 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_two_loads<uint32_t>/256
|
-3.22% |
22.156 |
21.441 |
0.000 |
0.00% |
0.000 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C++/miniFE/miniFE
Profile
|
-3.19% |
22.898 |
22.167 |
0.080 |
-2.95% |
0.080 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, LessThanZero, Mid>
|
-3.16% |
23436.289 |
22695.253 |
21.598 |
-0.00% |
21.598 |
|
MultiSource/Benchmarks/PAQ8p/paq8p
Profile
|
-3.15% |
135.747 |
131.477 |
0.151 |
0.00% |
0.151 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_two_loads<uint8_t>/28
|
-3.13% |
22.872 |
22.156 |
0.000 |
-3.12% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_two_loads<uint8_t>/16
|
-3.13% |
22.871 |
22.156 |
0.000 |
-3.13% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_two_loads<uint8_t>/256
|
-3.13% |
22.871 |
22.155 |
0.000 |
-3.13% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_two_loads<uint8_t>/10
|
-3.13% |
22.871 |
22.156 |
0.000 |
-3.13% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_two_loads<uint8_t>/999
|
-3.13% |
22.871 |
22.156 |
0.000 |
-3.13% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint32_t>/256
|
-3.13% |
22.871 |
22.155 |
0.001 |
-3.13% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint32_t>/999
|
-3.13% |
22.871 |
22.156 |
0.001 |
-3.13% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint16_t>/999
|
-3.13% |
22.872 |
22.156 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint16_t>/16
|
-3.13% |
22.871 |
22.156 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint16_t>/10
|
-3.13% |
22.870 |
22.155 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_two_loads<uint8_t>/51
|
-3.13% |
22.871 |
22.156 |
0.000 |
-3.12% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint32_t>/51
|
-3.12% |
22.871 |
22.156 |
0.000 |
-3.13% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint32_t>/10
|
-3.12% |
22.871 |
22.156 |
0.001 |
-3.13% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint16_t>/256
|
-3.12% |
22.870 |
22.156 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint16_t>/28
|
-3.12% |
22.871 |
22.156 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint32_t>/28
|
-3.12% |
22.871 |
22.156 |
0.000 |
-3.13% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint16_t>/51
|
-3.12% |
22.871 |
22.157 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<3, LessThanZero, None>
|
-3.12% |
31226.812 |
30251.912 |
22.434 |
-3.12% |
22.434 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint32_t>/16
|
-3.12% |
22.870 |
22.156 |
0.000 |
-3.13% |
0.000 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<16, EqZero, First>
|
-3.11% |
5862.960 |
5680.560 |
0.205 |
-0.01% |
0.205 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<7, EqZero, Mid>
|
-3.06% |
13812.332 |
13389.843 |
9.262 |
-0.00% |
9.262 |
|
MicroBenchmarks/ImageProcessing/Blur/blur.test:BENCHMARK_GAUSSIAN_BLUR/1024
|
-3.05% |
261704.667 |
253723.000 |
208.754 |
-3.03% |
208.754 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, LessThanZero, None>
|
-2.94% |
24893.208 |
24160.558 |
21.598 |
-2.93% |
21.598 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint8_t>/127
|
-2.92% |
171.534 |
166.524 |
0.004 |
-2.11% |
0.004 |
|
MicroBenchmarks/Builtins/Int128/Builtins.test:BM_DivideIntrinsic128UniformDivisor<__uint128_t>
|
-2.91% |
38.500 |
37.378 |
0.073 |
0.03% |
0.073 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_PRESSURE_CALC_RAW/171
|
-2.90% |
1.357 |
1.317 |
0.000 |
6.40% |
0.000 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<5, EqZero, Last>
|
-2.88% |
20502.460 |
19912.528 |
14.579 |
-0.00% |
14.579 |
|
External/SPEC/CINT2017rate/505.mcf_r/505.mcf_r
Profile
|
-2.87% |
157.460 |
152.945 |
0.976 |
-2.15% |
0.976 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<8, GreaterThanZero, Mid>
|
-2.86% |
12816.349 |
12450.413 |
8.125 |
-0.01% |
8.125 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<32, EqZero, Mid>
|
-2.83% |
3210.647 |
3119.736 |
2.011 |
-0.00% |
2.011 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<5, LessThanZero, Last>
|
-2.78% |
21081.255 |
20494.847 |
9.179 |
-0.01% |
9.179 |
|
MultiSource/Benchmarks/MiBench/consumer-typeset/consumer-typeset
Profile
|
-2.71% |
0.369 |
0.359 |
0.001 |
0.42% |
0.001 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<6, GreaterThanZero, Last>
|
-2.65% |
18044.302 |
17565.620 |
6.985 |
0.04% |
6.985 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<6, LessThanZero, None>
|
-2.64% |
18531.371 |
18042.975 |
14.613 |
-2.64% |
14.613 |
|
MultiSource/Applications/aha/aha
Profile
|
-2.63% |
3.875 |
3.773 |
0.000 |
-3.06% |
0.000 |
|
External/SPEC/CINT2017rate/500.perlbench_r/500.perlbench_r
Profile
|
-2.63% |
103.399 |
100.683 |
0.263 |
-0.12% |
0.263 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC2
|
-2.62% |
20.534 |
19.996 |
0.003 |
-4.02% |
0.003 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_ICCG_RAW/44217
|
-2.62% |
296.436 |
288.673 |
2.180 |
-0.20% |
2.180 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_DEL_DOT_VEC_2D_LAMBDA/2
|
-2.58% |
2.408 |
2.346 |
0.000 |
0.02% |
0.000 |
|
SingleSource/Benchmarks/Misc/revertBits
Profile
|
-2.53% |
0.411 |
0.401 |
0.000 |
-2.50% |
0.000 |
|
External/SPEC/CINT2017rate/523.xalancbmk_r/523.xalancbmk_r
Profile
|
-2.49% |
213.795 |
208.475 |
0.976 |
-2.40% |
0.976 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC128
|
-2.47% |
159.390 |
155.452 |
0.223 |
-19.45% |
0.223 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint64_t>/10
|
-2.44% |
29.303 |
28.589 |
0.000 |
-2.44% |
0.000 |
|
MultiSource/Applications/hexxagon/hexxagon
Profile
|
-2.34% |
9.231 |
9.014 |
0.009 |
-5.92% |
0.009 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC2
|
-2.33% |
20.477 |
20.000 |
0.021 |
-3.01% |
0.021 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint32_t>/51
|
-2.27% |
94.341 |
92.195 |
0.003 |
-1.53% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopTC2
|
-2.27% |
20.470 |
20.005 |
0.002 |
-3.06% |
0.002 |
|
MultiSource/Applications/SPASS/SPASS
Profile
|
-2.24% |
26.073 |
25.489 |
0.140 |
-0.15% |
0.140 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC128
|
-2.19% |
161.446 |
157.905 |
0.020 |
2.71% |
0.020 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC8
|
-2.18% |
10.959 |
10.721 |
0.000 |
-2.17% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC8
|
-2.18% |
10.960 |
10.721 |
0.000 |
-6.25% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint32_t>/10
|
-2.18% |
32.877 |
32.162 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC8
|
-2.18% |
10.959 |
10.721 |
0.000 |
-34.78% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_VOL3D_CALC_RAW/1
|
-2.14% |
208.555 |
204.085 |
1.559 |
-2.46% |
1.559 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1BigLoopWithReductionTC64
|
-2.13% |
312.246 |
305.585 |
0.004 |
-0.52% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint8_t>/10
|
-2.08% |
34.306 |
33.591 |
0.000 |
-2.09% |
0.000 |
|
SingleSource/Benchmarks/Adobe-C++/functionobjects
Profile
|
-2.05% |
6.063 |
5.939 |
0.005 |
-2.06% |
0.005 |
|
SingleSource/Benchmarks/Stanford/FloatMM
Profile
|
-2.00% |
0.769 |
0.753 |
0.000 |
-2.00% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_DEL_DOT_VEC_2D_RAW/0
|
-1.97% |
1221.866 |
1197.817 |
1.773 |
-1.38% |
1.773 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint16_t>/10
|
-1.92% |
37.166 |
36.452 |
0.000 |
-0.00% |
0.000 |
|
MultiSource/Benchmarks/nbench/nbench
Profile
|
-1.83% |
3.870 |
3.799 |
0.001 |
0.50% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC128
|
-1.80% |
160.805 |
157.914 |
0.810 |
1.58% |
0.810 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<31, LessThanZero, None>
|
-1.78% |
5268.222 |
5174.705 |
4.083 |
-1.74% |
4.083 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_expf_novec_float_
|
-1.73% |
463.330 |
455.298 |
0.330 |
-0.01% |
0.330 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_ENERGY_CALC_LAMBDA/171
|
-1.71% |
5.775 |
5.676 |
0.024 |
-3.24% |
0.024 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint8_t>/16
|
-1.67% |
42.883 |
42.167 |
0.001 |
-1.67% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_asinf_autovec_float_
|
-1.65% |
391.824 |
385.358 |
0.023 |
-0.00% |
0.023 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint16_t>/16
|
-1.64% |
43.598 |
42.884 |
0.000 |
-4.76% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_HYDRO_2D_RAW/44217
|
-1.56% |
29619.000 |
29157.708 |
106.608 |
-0.80% |
106.608 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, EqZero, Mid>
|
-1.53% |
8444.065 |
8314.573 |
33.480 |
-1.49% |
33.480 |
|
External/SPEC/CINT2017rate/531.deepsjeng_r/531.deepsjeng_r
Profile
|
-1.53% |
138.574 |
136.460 |
0.109 |
-0.57% |
0.109 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint16_t>/10
|
-1.50% |
47.888 |
47.172 |
0.000 |
-1.50% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint64_t>/10
|
-1.45% |
49.316 |
48.600 |
0.001 |
3.02% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint16_t_To_uint64_t_
|
-1.45% |
22199.772 |
21878.065 |
5.229 |
-1.31% |
5.229 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC31
|
-1.43% |
50.031 |
49.316 |
0.000 |
49.98% |
0.000 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, EqZero, First>
|
-1.40% |
8438.465 |
8320.285 |
34.158 |
-1.41% |
34.158 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_only_novec_int32_t_
|
-1.36% |
1424953.157 |
1405522.088 |
4265.174 |
-0.74% |
4265.174 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<31, GreaterThanZero, None>
|
-1.36% |
5257.455 |
5186.028 |
3.819 |
0.02% |
3.819 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC15
|
-1.36% |
17.630 |
17.391 |
0.000 |
-1.35% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC15
|
-1.36% |
17.630 |
17.391 |
0.001 |
-1.35% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC15
|
-1.35% |
17.630 |
17.391 |
0.000 |
-34.23% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1LoopWithReductionTC15
|
-1.35% |
17.630 |
17.392 |
0.000 |
-1.35% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC15
|
-1.35% |
17.630 |
17.392 |
0.000 |
-1.35% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_only_novec_int32_t_
|
-1.33% |
606792.174 |
598709.622 |
2888.105 |
4.22% |
2888.105 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_EOS_RAW/44217
|
-1.33% |
401.170 |
395.849 |
0.379 |
-0.80% |
0.379 |
|
External/SPEC/CFP2017rate/511.povray_r/511.povray_r
Profile
|
-1.30% |
17.180 |
16.957 |
0.070 |
-0.06% |
0.070 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_MAT_X_MAT_LAMBDA/44217
|
-1.29% |
1044277.000 |
1030766.000 |
2629.883 |
-1.32% |
2629.883 |
|
MicroBenchmarks/ImageProcessing/AnisotropicDiffusion/AnisotropicDiffusion.test:BENCHMARK_ANISTROPIC_DIFFUSION/32
|
-1.29% |
895.472 |
883.947 |
0.533 |
-0.74% |
0.533 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/16
|
-1.28% |
120.606 |
119.067 |
0.004 |
-1.19% |
0.004 |
|
MultiSource/Benchmarks/Ptrdist/anagram/anagram
Profile
|
-1.27% |
1.909 |
1.885 |
0.001 |
-1.31% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_csa_with_in_loop_arith_autovec_uint8_t_
|
-1.27% |
517897.990 |
511331.625 |
770.701 |
-1.50% |
770.701 |
|
External/SPEC/CFP2017rate/544.nab_r/544.nab_r
Profile
|
-1.26% |
280.156 |
276.639 |
0.117 |
-1.23% |
0.117 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<31, GreaterThanZero, Mid>
|
-1.25% |
5009.226 |
4946.817 |
2.657 |
-0.05% |
2.657 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_ADI_LAMBDA/5001
|
-1.22% |
320.415 |
316.520 |
1.106 |
0.27% |
1.106 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, EqZero, Last>
|
-1.21% |
8443.156 |
8341.241 |
16.800 |
-1.15% |
16.800 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_BAND_LIN_EQ_RAW/44217
|
-1.21% |
82.855 |
81.856 |
0.297 |
1.24% |
0.297 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint8_t>/28
|
-1.19% |
60.036 |
59.320 |
0.001 |
-1.19% |
0.001 |
|
SingleSource/Benchmarks/Misc/ReedSolomon
Profile
|
-1.17% |
9.633 |
9.520 |
0.004 |
-0.40% |
0.004 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_INT_PREDICT_LAMBDA/171
|
-1.16% |
2.091 |
2.067 |
0.000 |
-1.17% |
0.000 |
|
MicroBenchmarks/ImageProcessing/AnisotropicDiffusion/AnisotropicDiffusion.test:BENCHMARK_ANISTROPIC_DIFFUSION/128
|
-1.16% |
18305.711 |
18093.795 |
6.080 |
-0.82% |
6.080 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<63, GreaterThanZero, None>
|
-1.16% |
3057.698 |
3022.308 |
1.029 |
-0.02% |
1.029 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_INT_PREDICT_RAW/171
|
-1.16% |
2.092 |
2.067 |
0.004 |
-1.17% |
0.004 |
|
MultiSource/Benchmarks/TSVC/CrossingThresholds-flt/CrossingThresholds-flt
Profile
|
-1.13% |
8.157 |
8.065 |
0.016 |
-1.32% |
0.016 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_EOS_LAMBDA/5001
|
-1.10% |
36.037 |
35.640 |
0.123 |
-1.14% |
0.123 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_PIC_2D_LAMBDA/171
|
-1.10% |
5.109 |
5.053 |
0.013 |
-1.31% |
0.013 |
|
MicroBenchmarks/ImageProcessing/AnisotropicDiffusion/AnisotropicDiffusion.test:BENCHMARK_ANISTROPIC_DIFFUSION/256
|
-1.09% |
75832.556 |
75009.667 |
20.833 |
-0.82% |
20.833 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/32
|
-1.08% |
599.473 |
592.989 |
0.169 |
-1.09% |
0.169 |
|
SingleSource/Benchmarks/Misc/fbench
Profile
|
-1.08% |
2.896 |
2.864 |
0.005 |
-2.29% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint64_t>/16
|
-1.07% |
66.467 |
65.752 |
0.001 |
5.74% |
0.001 |
|
SingleSource/Benchmarks/Misc-C++-EH/spirit
Profile
|
-1.06% |
15.041 |
14.882 |
0.034 |
-1.53% |
0.034 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_EOS_RAW/5001
|
-1.04% |
36.102 |
35.726 |
0.096 |
-0.87% |
0.096 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_PIC_2D_RAW/171
|
-1.04% |
5.114 |
5.061 |
0.014 |
-0.76% |
0.014 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/64
|
-1.02% |
2650.125 |
2623.172 |
0.286 |
-1.01% |
0.286 |