|
MultiSource/Benchmarks/MiBench/automotive-bitcount/automotive-bitcount
Profile
|
-28.85% |
0.099 |
0.070 |
0.000 |
-28.90% |
0.000 |
|
MultiSource/Benchmarks/Trimaran/enc-pc1/enc-pc1
Profile
|
-27.43% |
0.636 |
0.461 |
0.000 |
-18.97% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIND_FIRST_MIN_LAMBDA/5001
|
-24.98% |
14.305 |
10.731 |
0.000 |
-11.92% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIND_FIRST_MIN_LAMBDA/171
|
-24.28% |
0.495 |
0.375 |
0.000 |
-0.01% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint8_t>/999
|
-21.53% |
1102.042 |
864.789 |
1.037 |
0.07% |
1.037 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint8_t>/999
|
-21.51% |
2169.950 |
1703.288 |
0.549 |
0.50% |
0.549 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC1
|
-20.99% |
6.433 |
5.083 |
0.000 |
-11.08% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIRST_DIFF_RAW/171
|
-20.60% |
0.373 |
0.296 |
0.003 |
-20.75% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint8_t>/256
|
-19.58% |
306.613 |
246.575 |
1.014 |
0.28% |
1.014 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint8_t>/256
|
-19.57% |
576.774 |
463.880 |
0.582 |
1.88% |
0.582 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint8_t>/51
|
-19.13% |
130.793 |
105.779 |
0.003 |
-0.67% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint8_t>/51
|
-18.92% |
79.333 |
64.327 |
0.001 |
1.12% |
0.001 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<1, EqZero, First>
|
-18.85% |
14644.174 |
11883.934 |
16.118 |
-0.02% |
16.118 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint8_t>/28
|
-17.95% |
55.747 |
45.742 |
0.001 |
-0.00% |
0.001 |
|
External/SPEC/CINT2017rate/525.x264_r/525.x264_r
Profile
|
-17.77% |
124.242 |
102.166 |
0.052 |
-16.53% |
0.052 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint16_t_To_uint8_t_
|
-16.68% |
14311.280 |
11924.235 |
4.452 |
-0.03% |
4.452 |
|
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
|
-16.67% |
81.475 |
67.897 |
0.002 |
-0.01% |
0.002 |
|
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 |
11928.668 |
0.177 |
-0.01% |
0.177 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopFrom_uint8_t_To_uint32_t_
|
-16.60% |
14301.978 |
11927.801 |
0.240 |
-0.05% |
0.240 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopFrom_uint16_t_To_uint32_t_
|
-16.60% |
14301.453 |
11928.108 |
0.123 |
-0.05% |
0.123 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint16_t_To_uint32_t_
|
-16.59% |
14301.835 |
11928.464 |
0.052 |
-0.04% |
0.052 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopFrom_uint16_t_To_uint8_t_
|
-16.53% |
14301.706 |
11938.190 |
6.010 |
0.06% |
6.010 |
|
SingleSource/Benchmarks/Shootout-C++/Shootout-C++-matrix
Profile
|
-15.61% |
6.589 |
5.560 |
0.000 |
-15.62% |
0.000 |
|
MicroBenchmarks/ImageProcessing/Blur/blur.test:BENCHMARK_boxBlurKernel/512
|
-15.24% |
20158.657 |
17085.707 |
75.524 |
-15.27% |
75.524 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_cond_load_autovec_int64_t_
|
-15.16% |
799131.429 |
677972.842 |
248.325 |
-15.14% |
248.325 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_only_autovec_int64_t_
|
-14.79% |
793300.795 |
675983.543 |
1138.336 |
-14.82% |
1138.336 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint16_t>/65
|
-14.12% |
96.541 |
82.908 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint8_t>/16
|
-14.10% |
55.747 |
47.885 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/ImageProcessing/Blur/blur.test:BENCHMARK_boxBlurKernel/128
|
-14.01% |
1077.593 |
926.605 |
0.285 |
-14.06% |
0.285 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint32_t>/16
|
-14.00% |
35.735 |
30.733 |
0.001 |
-2.27% |
0.001 |
|
MicroBenchmarks/ImageProcessing/Blur/blur.test:BENCHMARK_boxBlurKernel/256
|
-13.81% |
4579.882 |
3947.588 |
0.837 |
-13.85% |
0.837 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint8_t>/16
|
-13.33% |
42.883 |
37.165 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/ImageProcessing/Blur/blur.test:BENCHMARK_boxBlurKernel/1024
|
-12.84% |
84629.250 |
73764.222 |
21.677 |
-12.96% |
21.677 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC64
|
-12.79% |
73.520 |
64.115 |
0.002 |
-0.32% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint8_t>/10
|
-11.67% |
42.884 |
37.879 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_cond_load_novec_int32_t_
|
-11.66% |
596262.887 |
526715.679 |
1336.902 |
-5.55% |
1336.902 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_csa_with_cond_arith_novec_int64_t_
|
-11.52% |
783393.498 |
693154.609 |
360.569 |
0.33% |
360.569 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint32_t>/28
|
-11.29% |
44.313 |
39.310 |
0.001 |
-1.79% |
0.001 |
|
MultiSource/Benchmarks/Trimaran/enc-md5/enc-md5
Profile
|
-10.78% |
3.009 |
2.684 |
0.000 |
-10.80% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchAutoVec<uint16_t>/65
|
-10.67% |
160.817 |
143.660 |
0.004 |
-0.50% |
0.004 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIND_FIRST_MIN_LAMBDA/44217
|
-10.52% |
131.927 |
118.048 |
0.663 |
-4.53% |
0.663 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_ENERGY_CALC_RAW/44217
|
-10.39% |
2290.595 |
2052.655 |
64.639 |
-8.33% |
64.639 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_FLOYD_DITHER/256
|
-10.24% |
1105.583 |
992.394 |
0.281 |
-10.12% |
0.281 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_FLOYD_DITHER/512
|
-9.82% |
4425.120 |
3990.420 |
2.541 |
-10.01% |
2.541 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchAutoVec<uint16_t>/127
|
-9.81% |
298.778 |
269.463 |
0.003 |
-0.26% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint8_t>/10
|
-9.80% |
36.450 |
32.877 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_FLOYD_DITHER/128
|
-9.09% |
273.867 |
248.960 |
0.284 |
-8.98% |
0.284 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC2
|
-9.09% |
7.862 |
7.147 |
0.000 |
-16.66% |
0.000 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<31, LessThanZero, First>
|
-8.75% |
2499.450 |
2280.643 |
2.050 |
-0.53% |
2.050 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC4
|
-8.34% |
8.577 |
7.862 |
0.000 |
-26.66% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC4
|
-8.33% |
8.577 |
7.862 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC4
|
-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 |
55.034 |
0.001 |
-1.28% |
0.001 |
|
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 |
4495.665 |
5.141 |
-0.04% |
5.141 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIRST_DIFF_RAW/5001
|
-7.94% |
10.874 |
10.010 |
0.000 |
-7.92% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint32_t>/10
|
-7.84% |
36.451 |
33.592 |
0.001 |
-2.09% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_cond_load_novec_int64_t_
|
-7.71% |
862734.568 |
796182.131 |
2329.962 |
-0.56% |
2329.962 |
|
External/SPEC/CFP2017rate/508.namd_r/508.namd_r
Profile
|
-7.41% |
83.778 |
77.568 |
0.036 |
-7.67% |
0.036 |
|
SingleSource/Benchmarks/Shootout/Shootout-lists
Profile
|
-7.28% |
10.331 |
9.579 |
0.014 |
-7.33% |
0.014 |
|
SingleSource/Benchmarks/McGill/misr
Profile
|
-7.19% |
0.442 |
0.410 |
0.000 |
-7.19% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint32_t>/10
|
-6.82% |
31.448 |
29.303 |
0.001 |
2.50% |
0.001 |
|
MicroBenchmarks/ImageProcessing/Blur/blur.test:BENCHMARK_GAUSSIAN_BLUR/256
|
-6.78% |
15344.891 |
14304.061 |
12.097 |
-6.82% |
12.097 |
|
MicroBenchmarks/ImageProcessing/Blur/blur.test:BENCHMARK_GAUSSIAN_BLUR/128
|
-6.78% |
3593.077 |
3349.483 |
0.281 |
-6.81% |
0.281 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC7
|
-6.67% |
10.721 |
10.006 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC7
|
-6.67% |
10.721 |
10.006 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/ImageProcessing/Blur/blur.test:BENCHMARK_GAUSSIAN_BLUR/512
|
-6.60% |
63468.364 |
59277.167 |
113.124 |
-6.64% |
113.124 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC1
|
-6.25% |
5.718 |
5.360 |
0.000 |
-6.25% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC1
|
-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:benchForIC4VW1LoopWithReductionTC2
|
-6.22% |
5.389 |
5.054 |
0.034 |
-41.07% |
0.034 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC31
|
-6.16% |
158.669 |
148.887 |
0.008 |
-0.56% |
0.008 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1LoopWithReductionTC2
|
-6.05% |
5.403 |
5.076 |
0.008 |
-5.99% |
0.008 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC32
|
-6.05% |
163.676 |
153.773 |
0.070 |
0.30% |
0.070 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC127
|
-5.99% |
648.265 |
609.422 |
1.424 |
-0.69% |
1.424 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC4
|
-5.89% |
12.151 |
11.435 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC128
|
-5.74% |
651.829 |
614.441 |
0.126 |
-0.67% |
0.126 |
|
SingleSource/Benchmarks/Adobe-C++/loop_unroll
Profile
|
-5.65% |
1.715 |
1.618 |
0.001 |
-5.62% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC64
|
-5.63% |
323.777 |
305.551 |
0.024 |
-0.53% |
0.024 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC2
|
-5.62% |
5.435 |
5.129 |
0.024 |
-4.59% |
0.024 |
|
MultiSource/Benchmarks/Trimaran/enc-rc4/enc-rc4
Profile
|
-5.60% |
1.933 |
1.825 |
0.001 |
-5.70% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_ENERGY_CALC_LAMBDA/44217
|
-5.48% |
2133.028 |
2016.226 |
12.919 |
-2.47% |
12.919 |
|
MultiSource/Applications/JM/lencod/lencod
Profile
|
-5.46% |
14.621 |
13.822 |
0.035 |
-4.46% |
0.035 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_no_runtime_checks_needed<16, int>
|
-5.45% |
39.308 |
37.165 |
0.001 |
-5.45% |
0.001 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<5, LessThanZero, None>
|
-5.41% |
21668.431 |
20495.842 |
18.643 |
-2.77% |
18.643 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC2
|
-5.32% |
5.397 |
5.110 |
0.025 |
-5.82% |
0.025 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIRST_DIFF_RAW/44217
|
-5.20% |
96.106 |
91.110 |
0.220 |
-5.16% |
0.220 |
|
MultiSource/Benchmarks/TSVC/GlobalDataFlow-dbl/GlobalDataFlow-dbl
Profile
|
-5.16% |
11.646 |
11.045 |
0.181 |
5.37% |
0.181 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_DEL_DOT_VEC_2D_RAW/1
|
-5.14% |
199.404 |
189.152 |
0.615 |
-3.37% |
0.615 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_xor_no_runtime_checks_needed<16, int>
|
-5.13% |
27.874 |
26.444 |
0.001 |
-5.13% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopTC15
|
-5.12% |
143.890 |
136.521 |
0.735 |
-3.23% |
0.735 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopTC31
|
-5.02% |
288.541 |
274.048 |
0.001 |
-4.93% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC31
|
-5.01% |
288.460 |
274.000 |
0.008 |
-4.92% |
0.008 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC31
|
-4.96% |
288.355 |
274.041 |
0.007 |
-4.95% |
0.007 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC2
|
-4.94% |
5.415 |
5.148 |
0.000 |
-5.05% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC8
|
-4.92% |
43.599 |
41.455 |
0.006 |
-0.04% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopTC128
|
-4.90% |
1189.811 |
1131.492 |
0.016 |
-5.08% |
0.016 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC64
|
-4.89% |
595.872 |
566.727 |
0.016 |
-4.85% |
0.016 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopTC64
|
-4.88% |
595.811 |
566.732 |
0.018 |
-4.86% |
0.018 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC128
|
-4.86% |
1189.823 |
1132.037 |
0.021 |
-4.80% |
0.021 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC15
|
-4.85% |
143.478 |
136.516 |
0.005 |
-4.43% |
0.005 |
|
MultiSource/Benchmarks/VersaBench/ecbdes/ecbdes
Profile
|
-4.85% |
4.023 |
3.828 |
0.000 |
-4.87% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint32_t>/16
|
-4.84% |
44.314 |
42.167 |
0.009 |
-1.67% |
0.009 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC128
|
-4.84% |
1189.757 |
1132.158 |
0.733 |
-4.85% |
0.733 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopTC63
|
-4.84% |
587.762 |
559.341 |
0.009 |
-4.75% |
0.009 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC63
|
-4.81% |
587.571 |
559.333 |
0.016 |
-4.82% |
0.016 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopTC127
|
-4.80% |
1181.779 |
1125.073 |
0.347 |
-4.95% |
0.347 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC64
|
-4.80% |
595.924 |
567.332 |
0.018 |
-4.73% |
0.018 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC127
|
-4.80% |
1181.728 |
1125.060 |
0.010 |
-4.80% |
0.010 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC127
|
-4.79% |
1181.723 |
1125.077 |
0.036 |
-4.68% |
0.036 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC63
|
-4.79% |
587.477 |
559.326 |
0.008 |
-5.33% |
0.008 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<8, LessThanZero, Last>
|
-4.75% |
15377.892 |
14647.597 |
7.934 |
-4.75% |
7.934 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<15, LessThanZero, Mid>
|
-4.74% |
8203.141 |
7814.279 |
5.010 |
-4.76% |
5.010 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_ADI_RAW/171
|
-4.70% |
9.784 |
9.324 |
0.020 |
2.56% |
0.020 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<8, LessThanZero, None>
|
-4.65% |
15744.518 |
15012.417 |
8.098 |
-2.38% |
8.098 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint32_t>/28
|
-4.60% |
62.182 |
59.323 |
0.001 |
-1.19% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopTC3
|
-4.59% |
28.754 |
27.433 |
0.002 |
-3.70% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC7
|
-4.55% |
15.724 |
15.009 |
0.000 |
39.98% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC3
|
-4.53% |
28.476 |
27.187 |
0.112 |
-4.44% |
0.112 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopTC8
|
-4.46% |
73.877 |
70.581 |
0.004 |
-4.14% |
0.004 |
|
SingleSource/Benchmarks/Misc/salsa20
Profile
|
-4.34% |
10.905 |
10.431 |
0.000 |
-4.98% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC7
|
-4.33% |
38.597 |
36.927 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC63
|
-4.33% |
319.468 |
305.648 |
0.083 |
1.08% |
0.083 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC8
|
-4.29% |
73.724 |
70.560 |
0.002 |
-4.40% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint64_t>/51
|
-4.29% |
135.907 |
130.079 |
0.004 |
1.10% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC8
|
-4.22% |
73.669 |
70.558 |
0.002 |
-4.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopTC16
|
-4.16% |
152.684 |
146.334 |
0.005 |
-4.08% |
0.005 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<8, GreaterThanZero, First>
|
-4.16% |
8791.578 |
8426.116 |
7.232 |
-0.00% |
7.232 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC16
|
-4.15% |
152.682 |
146.343 |
0.001 |
-4.06% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC16
|
-4.15% |
152.673 |
146.340 |
0.001 |
-4.12% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint16_t_To_uint32_t_
|
-4.13% |
21452.392 |
20566.970 |
1.464 |
-4.12% |
1.464 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_DEL_DOT_VEC_2D_LAMBDA/1
|
-4.09% |
198.302 |
190.198 |
0.494 |
-3.65% |
0.494 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC4
|
-3.92% |
24.300 |
23.348 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC15
|
-3.88% |
142.032 |
136.518 |
0.002 |
-5.90% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC15
|
-3.82% |
78.623 |
75.617 |
0.004 |
-0.02% |
0.004 |
|
MultiSource/Benchmarks/sim/sim
Profile
|
-3.75% |
6.606 |
6.359 |
0.007 |
-5.23% |
0.007 |
|
MultiSource/Applications/siod/siod
Profile
|
-3.74% |
5.676 |
5.464 |
0.007 |
0.04% |
0.007 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<3, LessThanZero, Mid>
|
-3.71% |
26351.380 |
25374.148 |
22.418 |
-3.70% |
22.418 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC16
|
-3.71% |
83.625 |
80.525 |
0.002 |
-0.14% |
0.002 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, LessThanZero, Last>
|
-3.71% |
39531.737 |
38067.055 |
33.547 |
-3.72% |
33.547 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC3
|
-3.68% |
28.459 |
27.411 |
0.007 |
-4.19% |
0.007 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC32
|
-3.57% |
293.323 |
282.850 |
0.004 |
-3.37% |
0.004 |
|
MultiSource/Benchmarks/mafft/pairlocalalign
Profile
|
-3.56% |
47.903 |
46.199 |
0.011 |
-2.74% |
0.011 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_VOL3D_CALC_LAMBDA/2
|
-3.53% |
7.764 |
7.490 |
0.000 |
-3.55% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopTC32
|
-3.51% |
293.212 |
282.928 |
0.006 |
-3.39% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC32
|
-3.48% |
293.033 |
282.848 |
0.003 |
-3.44% |
0.003 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_VOL3D_CALC_RAW/2
|
-3.46% |
7.764 |
7.496 |
0.000 |
-3.46% |
0.000 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, LessThanZero, None>
|
-3.33% |
43922.884 |
42458.179 |
32.862 |
-6.45% |
32.862 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<3, LessThanZero, Last>
|
-3.29% |
30274.020 |
29276.495 |
27.411 |
-3.22% |
27.411 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<5, GreaterThanZero, Mid>
|
-3.26% |
18160.148 |
17567.886 |
17.607 |
-0.00% |
17.607 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<3, EqZero, Last>
|
-3.26% |
30262.696 |
29276.381 |
30.056 |
0.00% |
30.056 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_DEL_DOT_VEC_2D_LAMBDA/2
|
-3.25% |
2.408 |
2.330 |
0.007 |
-0.66% |
0.007 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_two_loads<uint32_t>/51
|
-3.23% |
22.157 |
21.441 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_two_loads<uint32_t>/16
|
-3.23% |
22.157 |
21.441 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_two_loads<uint32_t>/28
|
-3.23% |
22.157 |
21.442 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_two_loads<uint32_t>/10
|
-3.22% |
22.157 |
21.442 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_two_loads<uint32_t>/999
|
-3.22% |
22.156 |
21.442 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_two_loads<uint32_t>/256
|
-3.22% |
22.156 |
21.442 |
0.001 |
-0.00% |
0.001 |
|
MultiSource/Benchmarks/PAQ8p/paq8p
Profile
|
-3.22% |
135.747 |
131.375 |
0.088 |
-0.04% |
0.088 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, LessThanZero, Mid>
|
-3.16% |
23436.289 |
22695.707 |
21.824 |
0.00% |
21.824 |
|
MultiSource/Benchmarks/nbench/nbench
Profile
|
-3.14% |
3.870 |
3.748 |
0.002 |
-0.73% |
0.002 |
|
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>/28
|
-3.13% |
22.872 |
22.156 |
0.001 |
-3.12% |
0.001 |
|
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_three_loads<uint32_t>/10
|
-3.13% |
22.871 |
22.156 |
0.001 |
-3.13% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_two_loads<uint8_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<uint32_t>/28
|
-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
|
-3.12% |
22.872 |
22.157 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint32_t>/51
|
-3.12% |
22.871 |
22.156 |
0.004 |
-3.13% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint32_t>/16
|
-3.12% |
22.870 |
22.156 |
0.003 |
-3.13% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint16_t>/10
|
-3.12% |
22.870 |
22.156 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_two_loads<uint8_t>/256
|
-3.12% |
22.871 |
22.156 |
0.000 |
-3.12% |
0.000 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<3, LessThanZero, None>
|
-3.12% |
31226.812 |
30251.491 |
22.593 |
-3.12% |
22.593 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_two_loads<uint8_t>/51
|
-3.12% |
22.871 |
22.156 |
0.000 |
-3.12% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint32_t>/256
|
-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 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint32_t>/999
|
-3.12% |
22.871 |
22.157 |
0.001 |
-3.13% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint16_t>/28
|
-3.12% |
22.871 |
22.157 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint16_t>/16
|
-3.12% |
22.871 |
22.157 |
0.001 |
-0.00% |
0.001 |
|
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<16, EqZero, First>
|
-3.11% |
5862.960 |
5680.745 |
4.054 |
-0.01% |
4.054 |
|
MultiSource/Benchmarks/MiBench/telecomm-CRC32/telecomm-CRC32
Profile
|
-3.10% |
0.597 |
0.578 |
0.002 |
-3.46% |
0.002 |
|
MultiSource/Benchmarks/MiBench/consumer-typeset/consumer-typeset
Profile
|
-3.06% |
0.369 |
0.358 |
0.001 |
0.06% |
0.001 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<7, EqZero, Mid>
|
-3.06% |
13812.332 |
13389.525 |
10.021 |
0.00% |
10.021 |
|
MultiSource/Benchmarks/Fhourstones/fhourstones
Profile
|
-2.95% |
2.384 |
2.313 |
0.005 |
-0.07% |
0.005 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, LessThanZero, None>
|
-2.95% |
24893.208 |
24159.936 |
21.812 |
-2.93% |
21.812 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint8_t>/127
|
-2.92% |
171.534 |
166.533 |
0.192 |
-2.11% |
0.192 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<5, EqZero, Last>
|
-2.88% |
20502.460 |
19912.639 |
13.990 |
-0.00% |
13.990 |
|
MicroBenchmarks/Builtins/Int128/Builtins.test:BM_DivideIntrinsic128UniformDivisor<__uint128_t>
|
-2.87% |
38.500 |
37.394 |
0.037 |
0.07% |
0.037 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<8, GreaterThanZero, Mid>
|
-2.85% |
12816.349 |
12450.708 |
8.162 |
-0.00% |
8.162 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<32, EqZero, Mid>
|
-2.83% |
3210.647 |
3119.759 |
0.647 |
-0.00% |
0.647 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<5, LessThanZero, Last>
|
-2.78% |
21081.255 |
20496.194 |
9.442 |
-0.00% |
9.442 |
|
SingleSource/Benchmarks/Misc/revertBits
Profile
|
-2.77% |
0.411 |
0.400 |
0.000 |
-2.73% |
0.000 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<6, GreaterThanZero, Last>
|
-2.70% |
18044.302 |
17558.005 |
10.920 |
-0.00% |
10.920 |
|
External/SPEC/CINT2017rate/505.mcf_r/505.mcf_r
Profile
|
-2.64% |
157.460 |
153.306 |
0.966 |
-1.92% |
0.966 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<6, LessThanZero, None>
|
-2.63% |
18531.371 |
18043.950 |
14.727 |
-2.63% |
14.727 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC2
|
-2.62% |
20.534 |
19.995 |
0.006 |
-4.02% |
0.006 |
|
MultiSource/Applications/aha/aha
Profile
|
-2.62% |
3.875 |
3.774 |
0.001 |
-3.05% |
0.001 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<7, EqZero, None>
|
-2.50% |
16732.734 |
16314.529 |
13.483 |
0.00% |
13.483 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC128
|
-2.47% |
159.390 |
155.448 |
0.015 |
-19.45% |
0.015 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint64_t>/10
|
-2.44% |
29.303 |
28.588 |
0.001 |
-2.45% |
0.001 |
|
MicroBenchmarks/ImageProcessing/Blur/blur.test:BENCHMARK_GAUSSIAN_BLUR/1024
|
-2.39% |
261704.667 |
255458.667 |
145.994 |
-2.37% |
145.994 |
|
MultiSource/Applications/hexxagon/hexxagon
Profile
|
-2.32% |
9.231 |
9.016 |
0.007 |
-5.90% |
0.007 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC2
|
-2.31% |
20.477 |
20.003 |
0.018 |
-3.00% |
0.018 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint32_t>/51
|
-2.27% |
94.341 |
92.199 |
0.023 |
-1.53% |
0.023 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_MAT_X_MAT_LAMBDA/5001
|
-2.26% |
54941.385 |
53697.692 |
469.729 |
-2.99% |
469.729 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopTC2
|
-2.25% |
20.470 |
20.008 |
0.001 |
-3.04% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC8
|
-2.18% |
10.959 |
10.721 |
0.000 |
-2.17% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC128
|
-2.18% |
161.446 |
157.930 |
0.011 |
2.73% |
0.011 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC8
|
-2.18% |
10.960 |
10.721 |
0.000 |
-6.25% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC8
|
-2.17% |
10.959 |
10.721 |
0.000 |
-34.78% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint32_t>/10
|
-2.17% |
32.877 |
32.163 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1BigLoopWithReductionTC64
|
-2.13% |
312.246 |
305.581 |
0.014 |
-0.52% |
0.014 |
|
External/SPEC/CINT2017rate/500.perlbench_r/500.perlbench_r
Profile
|
-2.13% |
103.399 |
101.199 |
0.048 |
0.08% |
0.048 |
|
SingleSource/Benchmarks/Adobe-C++/functionobjects
Profile
|
-2.08% |
6.063 |
5.937 |
0.003 |
-2.10% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint8_t>/10
|
-2.08% |
34.306 |
33.592 |
0.000 |
-2.08% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_MAT_X_MAT_LAMBDA/44217
|
-2.06% |
1044277.000 |
1022719.000 |
6279.524 |
-2.09% |
6279.524 |
|
SingleSource/Benchmarks/Stanford/FloatMM
Profile
|
-2.00% |
0.769 |
0.753 |
0.001 |
-2.00% |
0.001 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<31, LessThanZero, None>
|
-1.99% |
5268.222 |
5163.141 |
7.206 |
-1.96% |
7.206 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C++/miniFE/miniFE
Profile
|
-1.97% |
22.898 |
22.448 |
0.125 |
-1.72% |
0.125 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_VOL3D_CALC_LAMBDA/1
|
-1.95% |
209.677 |
205.592 |
0.711 |
-1.49% |
0.711 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_DEL_DOT_VEC_2D_RAW/0
|
-1.93% |
1221.866 |
1198.271 |
2.343 |
-1.34% |
2.343 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint16_t>/10
|
-1.92% |
37.166 |
36.451 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC128
|
-1.79% |
160.805 |
157.932 |
0.008 |
1.59% |
0.008 |
|
External/SPEC/CINT2017rate/523.xalancbmk_r/523.xalancbmk_r
Profile
|
-1.76% |
213.795 |
210.029 |
1.189 |
-1.67% |
1.189 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_VOL3D_CALC_RAW/1
|
-1.75% |
208.555 |
204.915 |
0.457 |
-2.06% |
0.457 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_asinf_autovec_float_
|
-1.67% |
391.824 |
385.279 |
0.063 |
-0.02% |
0.063 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint8_t>/16
|
-1.66% |
42.883 |
42.169 |
0.000 |
-1.67% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_expf_novec_float_
|
-1.65% |
463.330 |
455.666 |
1.014 |
-0.02% |
1.014 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint16_t>/16
|
-1.64% |
43.598 |
42.884 |
0.001 |
-4.76% |
0.001 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<31, GreaterThanZero, None>
|
-1.56% |
5257.455 |
5175.489 |
8.306 |
-0.18% |
8.306 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint16_t>/10
|
-1.49% |
47.888 |
47.172 |
0.002 |
-1.50% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint16_t_To_uint64_t_
|
-1.45% |
22199.772 |
21877.851 |
8.561 |
-1.31% |
8.561 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint64_t>/10
|
-1.45% |
49.316 |
48.602 |
0.002 |
3.02% |
0.002 |
|
External/SPEC/CINT2017rate/531.deepsjeng_r/531.deepsjeng_r
Profile
|
-1.45% |
138.574 |
136.569 |
0.175 |
-0.49% |
0.175 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC31
|
-1.43% |
50.031 |
49.316 |
0.001 |
49.98% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC15
|
-1.36% |
17.630 |
17.391 |
0.000 |
-1.35% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1LoopWithReductionTC15
|
-1.36% |
17.630 |
17.391 |
0.001 |
-1.35% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC15
|
-1.36% |
17.630 |
17.392 |
0.000 |
-1.36% |
0.000 |
|
SingleSource/Benchmarks/BenchmarkGame/recursive
Profile
|
-1.35% |
2.338 |
2.307 |
0.009 |
-1.01% |
0.009 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC15
|
-1.35% |
17.630 |
17.392 |
0.000 |
-34.23% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC15
|
-1.35% |
17.630 |
17.392 |
0.000 |
-1.35% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_INT_PREDICT_LAMBDA/171
|
-1.30% |
2.091 |
2.064 |
0.004 |
-1.31% |
0.004 |
|
MultiSource/Benchmarks/Ptrdist/anagram/anagram
Profile
|
-1.29% |
1.909 |
1.885 |
0.001 |
-1.33% |
0.001 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/16
|
-1.28% |
120.606 |
119.064 |
0.002 |
-1.19% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_csa_with_in_loop_arith_autovec_uint8_t_
|
-1.26% |
517897.990 |
511380.220 |
1410.207 |
-1.49% |
1410.207 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<31, GreaterThanZero, Mid>
|
-1.21% |
5009.226 |
4948.687 |
3.268 |
-0.01% |
3.268 |
|
SingleSource/Benchmarks/Misc/ReedSolomon
Profile
|
-1.20% |
9.633 |
9.517 |
0.014 |
-0.43% |
0.014 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint8_t>/28
|
-1.19% |
60.036 |
59.322 |
0.001 |
-1.19% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_INT_PREDICT_RAW/171
|
-1.17% |
2.092 |
2.067 |
0.008 |
-1.18% |
0.008 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_EOS_RAW/44217
|
-1.17% |
401.170 |
396.495 |
1.001 |
-0.64% |
1.001 |
|
SingleSource/Benchmarks/Misc/fbench
Profile
|
-1.16% |
2.896 |
2.862 |
0.003 |
-2.38% |
0.003 |
|
External/SPEC/CFP2017rate/544.nab_r/544.nab_r
Profile
|
-1.14% |
280.156 |
276.963 |
0.170 |
-1.11% |
0.170 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_PIC_2D_LAMBDA/171
|
-1.12% |
5.109 |
5.052 |
0.011 |
-1.32% |
0.011 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_EOS_LAMBDA/44217
|
-1.11% |
400.264 |
395.819 |
1.015 |
-0.77% |
1.015 |
|
MultiSource/Benchmarks/Fhourstones-3.1/fhourstones3.1
Profile
|
-1.10% |
2.494 |
2.467 |
0.004 |
1.32% |
0.004 |
|
MicroBenchmarks/ImageProcessing/AnisotropicDiffusion/AnisotropicDiffusion.test:BENCHMARK_ANISTROPIC_DIFFUSION/128
|
-1.09% |
18305.711 |
18106.795 |
18.952 |
-0.75% |
18.952 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/32
|
-1.08% |
599.473 |
592.997 |
0.193 |
-1.09% |
0.193 |
|
MicroBenchmarks/ImageProcessing/AnisotropicDiffusion/AnisotropicDiffusion.test:BENCHMARK_ANISTROPIC_DIFFUSION/256
|
-1.07% |
75832.556 |
75017.667 |
36.332 |
-0.81% |
36.332 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint64_t>/16
|
-1.07% |
66.467 |
65.755 |
0.002 |
5.74% |
0.002 |
|
SingleSource/Benchmarks/Misc-C++/stepanov_container
Profile
|
-1.05% |
11.029 |
10.913 |
0.031 |
-0.64% |
0.031 |
|
MicroBenchmarks/ImageProcessing/AnisotropicDiffusion/AnisotropicDiffusion.test:BENCHMARK_ANISTROPIC_DIFFUSION/32
|
-1.04% |
895.472 |
886.157 |
2.133 |
-0.49% |
2.133 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_only_novec_int32_t_
|
-1.03% |
1424953.157 |
1410241.449 |
1941.763 |
-0.41% |
1941.763 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_ORDERED_DITHER/512/2
|
-1.03% |
19404.139 |
19205.167 |
21.359 |
-0.75% |
21.359 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/64
|
-1.02% |
2650.125 |
2623.101 |
0.213 |
-1.02% |
0.213 |