|
MultiSource/Benchmarks/MiBench/automotive-bitcount/automotive-bitcount
Profile
|
-28.93% |
0.099 |
0.070 |
0.000 |
-28.99% |
0.000 |
|
MultiSource/Benchmarks/Trimaran/enc-pc1/enc-pc1
Profile
|
-27.41% |
0.636 |
0.461 |
0.000 |
-18.95% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIND_FIRST_MIN_LAMBDA/5001
|
-24.98% |
14.305 |
10.732 |
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 |
-0.00% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIRST_DIFF_RAW/171
|
-21.65% |
0.373 |
0.292 |
0.000 |
-21.80% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint8_t>/999
|
-21.61% |
2169.950 |
1701.042 |
2.643 |
0.37% |
2.643 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint8_t>/999
|
-21.52% |
1102.042 |
864.829 |
0.899 |
0.08% |
0.899 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC1
|
-20.99% |
6.433 |
5.082 |
0.000 |
-11.09% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint8_t>/256
|
-20.85% |
576.774 |
456.524 |
4.745 |
0.27% |
4.745 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint8_t>/256
|
-19.58% |
306.613 |
246.575 |
0.991 |
0.28% |
0.991 |
|
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 |
64.326 |
0.001 |
1.11% |
0.001 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<1, EqZero, First>
|
-18.85% |
14644.174 |
11883.745 |
0.133 |
-0.02% |
0.133 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint8_t>/28
|
-17.95% |
55.747 |
45.741 |
0.001 |
-0.00% |
0.001 |
|
External/SPEC/CINT2017rate/525.x264_r/525.x264_r
Profile
|
-17.71% |
124.242 |
102.236 |
0.047 |
-16.47% |
0.047 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint16_t_To_uint8_t_
|
-16.71% |
14311.280 |
11919.526 |
5.900 |
-0.07% |
5.900 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_PRESSURE_CALC_LAMBDA/5001
|
-16.69% |
47.515 |
39.585 |
2.134 |
0.01% |
2.134 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC2
|
-16.67% |
8.577 |
7.147 |
0.000 |
-0.01% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC2
|
-16.67% |
8.576 |
7.147 |
0.000 |
-0.02% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint8_t>/28
|
-16.66% |
81.475 |
67.899 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint16_t_To_uint8_t_
|
-16.63% |
14308.741 |
11928.668 |
0.320 |
-0.01% |
0.320 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopFrom_uint8_t_To_uint32_t_
|
-16.60% |
14301.978 |
11927.517 |
0.395 |
0.05% |
0.395 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint16_t_To_uint32_t_
|
-16.60% |
14301.835 |
11928.412 |
5.434 |
-0.04% |
5.434 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopFrom_uint16_t_To_uint32_t_
|
-16.59% |
14301.453 |
11928.195 |
1.159 |
-0.05% |
1.159 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopFrom_uint16_t_To_uint8_t_
|
-16.52% |
14301.706 |
11938.585 |
1.691 |
0.07% |
1.691 |
|
SingleSource/Benchmarks/Shootout-C++/Shootout-C++-matrix
Profile
|
-15.62% |
6.589 |
5.560 |
0.000 |
-15.62% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_cond_load_autovec_int64_t_
|
-15.20% |
799131.429 |
677640.777 |
690.244 |
-15.18% |
690.244 |
|
MicroBenchmarks/ImageProcessing/Blur/blur.test:BENCHMARK_boxBlurKernel/512
|
-15.18% |
20158.657 |
17098.829 |
41.313 |
-15.21% |
41.313 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_only_autovec_int64_t_
|
-14.61% |
793300.795 |
677365.924 |
524.612 |
-14.64% |
524.612 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint16_t>/65
|
-14.12% |
96.541 |
82.906 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint8_t>/16
|
-14.10% |
55.747 |
47.886 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint32_t>/16
|
-14.00% |
35.735 |
30.734 |
0.000 |
-2.27% |
0.000 |
|
MicroBenchmarks/ImageProcessing/Blur/blur.test:BENCHMARK_boxBlurKernel/128
|
-13.99% |
1077.593 |
926.834 |
0.545 |
-14.04% |
0.545 |
|
MicroBenchmarks/ImageProcessing/Blur/blur.test:BENCHMARK_boxBlurKernel/256
|
-13.76% |
4579.882 |
3949.650 |
0.410 |
-13.80% |
0.410 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_cond_load_novec_int32_t_
|
-13.35% |
596262.887 |
516664.419 |
3556.727 |
-7.35% |
3556.727 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint8_t>/16
|
-13.33% |
42.883 |
37.166 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/ImageProcessing/Blur/blur.test:BENCHMARK_boxBlurKernel/1024
|
-12.91% |
84629.250 |
73702.667 |
71.832 |
-13.03% |
71.832 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC64
|
-12.79% |
73.520 |
64.117 |
0.001 |
-0.32% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint8_t>/10
|
-11.67% |
42.884 |
37.881 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_csa_with_cond_arith_novec_int64_t_
|
-11.62% |
783393.498 |
692373.267 |
591.779 |
0.21% |
591.779 |
|
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 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIND_FIRST_MIN_LAMBDA/44217
|
-11.18% |
131.927 |
117.178 |
0.595 |
-5.23% |
0.595 |
|
MultiSource/Benchmarks/Trimaran/enc-md5/enc-md5
Profile
|
-10.78% |
3.009 |
2.684 |
0.000 |
-10.79% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchAutoVec<uint16_t>/65
|
-10.67% |
160.817 |
143.657 |
0.003 |
-0.50% |
0.003 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_FLOYD_DITHER/512
|
-10.65% |
4425.120 |
3953.729 |
16.815 |
-10.84% |
16.815 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_FLOYD_DITHER/256
|
-10.22% |
1105.583 |
992.549 |
0.679 |
-10.11% |
0.679 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchAutoVec<uint16_t>/127
|
-9.82% |
298.778 |
269.449 |
0.006 |
-0.27% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint8_t>/10
|
-9.80% |
36.450 |
32.877 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_FLOYD_DITHER/128
|
-9.65% |
273.867 |
247.434 |
0.600 |
-9.54% |
0.600 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_ICCG_RAW/44217
|
-9.39% |
296.436 |
268.608 |
2.348 |
-5.96% |
2.348 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC2
|
-9.09% |
7.862 |
7.147 |
0.000 |
-16.66% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint32_t>/10
|
-8.85% |
31.448 |
28.664 |
0.301 |
0.26% |
0.301 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_PRESSURE_CALC_RAW/171
|
-8.80% |
1.357 |
1.237 |
0.000 |
-0.06% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC4
|
-8.33% |
8.577 |
7.862 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC4
|
-8.33% |
8.577 |
7.862 |
0.000 |
-26.66% |
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/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC4
|
-8.33% |
8.577 |
7.862 |
0.000 |
-0.00% |
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 |
4495.620 |
2.374 |
-0.04% |
2.374 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIRST_DIFF_RAW/5001
|
-7.95% |
10.874 |
10.010 |
0.000 |
-7.92% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_HYDRO_2D_RAW/171
|
-7.90% |
72.187 |
66.485 |
2.150 |
-4.18% |
2.150 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint32_t>/10
|
-7.84% |
36.451 |
33.593 |
0.001 |
-2.09% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_cond_load_novec_int64_t_
|
-7.64% |
862734.568 |
796782.212 |
1007.015 |
-0.48% |
1007.015 |
|
External/SPEC/CFP2017rate/508.namd_r/508.namd_r
Profile
|
-7.56% |
83.778 |
77.446 |
0.108 |
-7.82% |
0.108 |
|
SingleSource/Benchmarks/Shootout/Shootout-lists
Profile
|
-7.26% |
10.331 |
9.582 |
0.003 |
-7.30% |
0.003 |
|
SingleSource/Benchmarks/McGill/misr
Profile
|
-7.22% |
0.442 |
0.410 |
0.000 |
-7.22% |
0.000 |
|
MicroBenchmarks/ImageProcessing/Blur/blur.test:BENCHMARK_GAUSSIAN_BLUR/256
|
-6.81% |
15344.891 |
14299.469 |
10.548 |
-6.85% |
10.548 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_ENERGY_CALC_RAW/44217
|
-6.78% |
2290.595 |
2135.346 |
20.550 |
-4.64% |
20.550 |
|
MicroBenchmarks/ImageProcessing/Blur/blur.test:BENCHMARK_GAUSSIAN_BLUR/128
|
-6.76% |
3593.077 |
3350.225 |
0.214 |
-6.79% |
0.214 |
|
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 |
|
MultiSource/Applications/JM/lencod/lencod
Profile
|
-6.57% |
14.621 |
13.660 |
0.013 |
-5.57% |
0.013 |
|
MicroBenchmarks/ImageProcessing/Blur/blur.test:BENCHMARK_GAUSSIAN_BLUR/512
|
-6.47% |
63468.364 |
59358.917 |
16.537 |
-6.51% |
16.537 |
|
MultiSource/Benchmarks/TSVC/Expansion-flt/Expansion-flt
Profile
|
-6.25% |
9.619 |
9.018 |
0.038 |
-2.89% |
0.038 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC1
|
-6.25% |
5.718 |
5.360 |
0.000 |
-6.25% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC1
|
-6.25% |
5.718 |
5.361 |
0.000 |
-6.25% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC1
|
-6.25% |
5.718 |
5.361 |
0.000 |
-6.24% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC31
|
-6.16% |
158.669 |
148.889 |
0.008 |
-0.55% |
0.008 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC127
|
-6.05% |
648.265 |
609.068 |
1.489 |
-0.75% |
1.489 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC32
|
-6.02% |
163.676 |
153.819 |
0.020 |
0.33% |
0.020 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC4
|
-5.88% |
12.151 |
11.436 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC128
|
-5.73% |
651.829 |
614.462 |
0.026 |
-0.67% |
0.026 |
|
SingleSource/Benchmarks/Adobe-C++/loop_unroll
Profile
|
-5.73% |
1.715 |
1.616 |
0.001 |
-5.70% |
0.001 |
|
MultiSource/Benchmarks/Trimaran/enc-rc4/enc-rc4
Profile
|
-5.69% |
1.933 |
1.823 |
0.002 |
-5.79% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC64
|
-5.62% |
323.777 |
305.571 |
0.013 |
-0.52% |
0.013 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC2
|
-5.59% |
5.389 |
5.088 |
0.115 |
-40.68% |
0.115 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_no_runtime_checks_needed<16, int>
|
-5.45% |
39.308 |
37.166 |
0.001 |
-5.45% |
0.001 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<5, LessThanZero, None>
|
-5.41% |
21668.431 |
20495.330 |
0.417 |
-2.77% |
0.417 |
|
SingleSource/Benchmarks/Polybench/linear-algebra/blas/gemver/gemver
Profile
|
-5.33% |
0.317 |
0.300 |
0.002 |
0.02% |
0.002 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIRST_DIFF_RAW/44217
|
-5.24% |
96.106 |
91.071 |
0.046 |
-5.20% |
0.046 |
|
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 |
136.517 |
0.383 |
-3.24% |
0.383 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopTC31
|
-5.03% |
288.541 |
274.039 |
0.005 |
-4.94% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC31
|
-5.01% |
288.460 |
274.021 |
0.010 |
-4.91% |
0.010 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC31
|
-4.97% |
288.355 |
274.029 |
0.014 |
-4.95% |
0.014 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC8
|
-4.92% |
43.599 |
41.455 |
0.001 |
-0.04% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_ENERGY_CALC_LAMBDA/44217
|
-4.92% |
2133.028 |
2028.156 |
29.045 |
-1.89% |
29.045 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopTC128
|
-4.91% |
1189.811 |
1131.449 |
0.017 |
-5.08% |
0.017 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC128
|
-4.90% |
1189.757 |
1131.447 |
0.009 |
-4.91% |
0.009 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC64
|
-4.89% |
595.872 |
566.743 |
0.012 |
-4.85% |
0.012 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopTC64
|
-4.88% |
595.811 |
566.755 |
0.003 |
-4.85% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC128
|
-4.86% |
1189.823 |
1132.008 |
0.043 |
-4.81% |
0.043 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC15
|
-4.85% |
143.478 |
136.514 |
0.003 |
-4.43% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint32_t>/16
|
-4.84% |
44.314 |
42.169 |
0.001 |
-1.67% |
0.001 |
|
MultiSource/Benchmarks/VersaBench/ecbdes/ecbdes
Profile
|
-4.84% |
4.023 |
3.829 |
0.000 |
-4.86% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopTC63
|
-4.84% |
587.762 |
559.336 |
0.013 |
-4.75% |
0.013 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC63
|
-4.81% |
587.571 |
559.301 |
0.013 |
-4.83% |
0.013 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC127
|
-4.80% |
1181.728 |
1125.053 |
0.030 |
-4.80% |
0.030 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC64
|
-4.79% |
595.924 |
567.356 |
0.001 |
-4.72% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopTC127
|
-4.79% |
1181.779 |
1125.130 |
0.210 |
-4.94% |
0.210 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC127
|
-4.79% |
1181.723 |
1125.081 |
0.020 |
-4.68% |
0.020 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC63
|
-4.79% |
587.477 |
559.327 |
0.014 |
-5.33% |
0.014 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<8, LessThanZero, Last>
|
-4.75% |
15377.892 |
14646.905 |
0.274 |
-4.76% |
0.274 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<15, LessThanZero, Mid>
|
-4.74% |
8203.141 |
7814.276 |
0.064 |
-4.76% |
0.064 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<8, LessThanZero, None>
|
-4.65% |
15744.518 |
15012.439 |
4.405 |
-2.38% |
4.405 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint32_t>/28
|
-4.60% |
62.182 |
59.324 |
0.001 |
-1.19% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopTC3
|
-4.60% |
28.754 |
27.433 |
0.002 |
-3.71% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC7
|
-4.54% |
15.724 |
15.009 |
0.000 |
39.98% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_DEL_DOT_VEC_2D_RAW/1
|
-4.54% |
199.404 |
190.360 |
0.811 |
-2.76% |
0.811 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopTC8
|
-4.46% |
73.877 |
70.585 |
0.003 |
-4.14% |
0.003 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_IMP_HYDRO_2D_LAMBDA/171
|
-4.38% |
12.445 |
11.900 |
0.194 |
-4.85% |
0.194 |
|
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 |
36.927 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC63
|
-4.29% |
319.468 |
305.769 |
0.049 |
1.12% |
0.049 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC8
|
-4.29% |
73.724 |
70.562 |
0.001 |
-4.40% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint64_t>/51
|
-4.29% |
135.907 |
130.082 |
0.003 |
1.10% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC8
|
-4.22% |
73.669 |
70.558 |
0.002 |
-4.00% |
0.002 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<8, GreaterThanZero, First>
|
-4.16% |
8791.578 |
8426.057 |
3.343 |
-0.00% |
3.343 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopTC16
|
-4.16% |
152.684 |
146.336 |
0.005 |
-4.08% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC16
|
-4.15% |
152.682 |
146.338 |
0.003 |
-4.07% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC16
|
-4.15% |
152.673 |
146.336 |
0.005 |
-4.12% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint16_t_To_uint32_t_
|
-4.12% |
21452.392 |
20568.272 |
26.770 |
-4.12% |
26.770 |
|
MultiSource/Applications/siod/siod
Profile
|
-4.02% |
5.676 |
5.448 |
0.015 |
-0.10% |
0.015 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC4
|
-3.92% |
24.300 |
23.348 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_DEL_DOT_VEC_2D_LAMBDA/1
|
-3.89% |
198.302 |
190.590 |
0.304 |
-3.45% |
0.304 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC15
|
-3.88% |
142.032 |
136.515 |
0.002 |
-5.90% |
0.002 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_DEL_DOT_VEC_2D_LAMBDA/2
|
-3.88% |
2.408 |
2.314 |
0.015 |
-1.31% |
0.015 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC3
|
-3.86% |
28.476 |
27.377 |
0.020 |
-3.77% |
0.020 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC15
|
-3.82% |
78.623 |
75.616 |
0.004 |
-0.03% |
0.004 |
|
MultiSource/Benchmarks/sim/sim
Profile
|
-3.75% |
6.606 |
6.359 |
0.003 |
-5.23% |
0.003 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<3, LessThanZero, Mid>
|
-3.71% |
26351.380 |
25374.067 |
0.469 |
-3.70% |
0.469 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, LessThanZero, Last>
|
-3.71% |
39531.737 |
38066.565 |
1.102 |
-3.72% |
1.102 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC16
|
-3.70% |
83.625 |
80.527 |
0.001 |
-0.13% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC3
|
-3.66% |
28.459 |
27.419 |
0.004 |
-4.17% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC32
|
-3.57% |
293.323 |
282.851 |
0.003 |
-3.37% |
0.003 |
|
MultiSource/Benchmarks/mafft/pairlocalalign
Profile
|
-3.55% |
47.903 |
46.201 |
0.038 |
-2.74% |
0.038 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_VOL3D_CALC_RAW/2
|
-3.53% |
7.764 |
7.490 |
0.002 |
-3.53% |
0.002 |
|
MultiSource/Benchmarks/MiBench/consumer-typeset/consumer-typeset
Profile
|
-3.52% |
0.369 |
0.356 |
0.001 |
-0.41% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopTC32
|
-3.51% |
293.212 |
282.931 |
0.005 |
-3.39% |
0.005 |
|
MicroBenchmarks/Builtins/Int128/Builtins.test:BM_DivideIntrinsic128UniformDivisor<__uint128_t>
|
-3.49% |
38.500 |
37.154 |
0.117 |
-0.37% |
0.117 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC32
|
-3.47% |
293.033 |
282.853 |
0.004 |
-3.43% |
0.004 |
|
MultiSource/Benchmarks/Fhourstones/fhourstones
Profile
|
-3.39% |
2.384 |
2.303 |
0.007 |
-0.09% |
0.007 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, LessThanZero, None>
|
-3.34% |
43922.884 |
42457.027 |
0.473 |
-6.45% |
0.473 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<3, LessThanZero, Last>
|
-3.29% |
30274.020 |
29276.609 |
4.380 |
-3.22% |
4.380 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<5, GreaterThanZero, Mid>
|
-3.26% |
18160.148 |
17568.187 |
0.137 |
-0.00% |
0.137 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<3, EqZero, Last>
|
-3.26% |
30262.696 |
29276.400 |
0.409 |
0.00% |
0.409 |
|
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>/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>/256
|
-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>/51
|
-3.22% |
22.157 |
21.443 |
0.000 |
0.01% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_two_loads<uint32_t>/28
|
-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 |
0.000 |
0.00% |
0.000 |
|
MultiSource/Benchmarks/nbench/nbench
Profile
|
-3.22% |
3.870 |
3.745 |
0.001 |
-0.81% |
0.001 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, LessThanZero, Mid>
|
-3.16% |
23436.289 |
22696.787 |
3.345 |
0.00% |
3.345 |
|
MultiSource/Benchmarks/PAQ8p/paq8p
Profile
|
-3.14% |
135.747 |
131.479 |
0.081 |
0.01% |
0.081 |
|
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_three_loads<uint16_t>/999
|
-3.13% |
22.872 |
22.156 |
0.001 |
-0.01% |
0.001 |
|
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>/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>/999
|
-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>/256
|
-3.13% |
22.871 |
22.156 |
0.001 |
-3.12% |
0.001 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<3, LessThanZero, None>
|
-3.13% |
31226.812 |
30250.681 |
0.410 |
-3.12% |
0.410 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint32_t>/51
|
-3.12% |
22.871 |
22.156 |
0.001 |
-3.13% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint32_t>/256
|
-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>/999
|
-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 |
22.157 |
0.000 |
-3.13% |
0.000 |
|
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<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<uint16_t>/16
|
-3.12% |
22.871 |
22.157 |
0.000 |
-0.00% |
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/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_three_loads<uint32_t>/28
|
-3.12% |
22.871 |
22.157 |
0.000 |
-3.12% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint32_t>/16
|
-3.12% |
22.870 |
22.157 |
0.000 |
-3.13% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint16_t>/256
|
-3.12% |
22.870 |
22.157 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<16, EqZero, First>
|
-3.11% |
5862.960 |
5680.609 |
0.049 |
-0.01% |
0.049 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<7, EqZero, Mid>
|
-3.06% |
13812.332 |
13389.568 |
0.584 |
0.00% |
0.584 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, LessThanZero, None>
|
-2.95% |
24893.208 |
24160.086 |
1.319 |
-2.93% |
1.319 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint8_t>/127
|
-2.92% |
171.534 |
166.527 |
0.006 |
-2.11% |
0.006 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<5, EqZero, Last>
|
-2.88% |
20502.460 |
19912.236 |
0.162 |
0.00% |
0.162 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<8, GreaterThanZero, Mid>
|
-2.86% |
12816.349 |
12450.286 |
3.708 |
-0.01% |
3.708 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<32, EqZero, Mid>
|
-2.83% |
3210.647 |
3119.763 |
0.043 |
-0.00% |
0.043 |
|
MicroBenchmarks/ImageProcessing/Blur/blur.test:BENCHMARK_GAUSSIAN_BLUR/1024
|
-2.79% |
261704.667 |
254402.333 |
708.884 |
-2.77% |
708.884 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<5, LessThanZero, Last>
|
-2.78% |
21081.255 |
20495.857 |
0.297 |
-0.01% |
0.297 |
|
MultiSource/Applications/SPASS/SPASS
Profile
|
-2.74% |
26.073 |
25.358 |
0.060 |
-0.05% |
0.060 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<6, GreaterThanZero, Last>
|
-2.70% |
18044.302 |
17557.554 |
0.678 |
-0.00% |
0.678 |
|
MultiSource/Applications/aha/aha
Profile
|
-2.70% |
3.875 |
3.771 |
0.002 |
-3.12% |
0.002 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<6, LessThanZero, None>
|
-2.64% |
18531.371 |
18042.737 |
1.669 |
-2.64% |
1.669 |
|
SingleSource/Benchmarks/Misc/revertBits
Profile
|
-2.62% |
0.411 |
0.401 |
0.000 |
-2.58% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC2
|
-2.60% |
20.534 |
19.999 |
0.003 |
-4.00% |
0.003 |
|
External/SPEC/CINT2017rate/500.perlbench_r/500.perlbench_r
Profile
|
-2.51% |
103.399 |
100.803 |
0.237 |
-0.01% |
0.237 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<7, EqZero, None>
|
-2.50% |
16732.734 |
16314.126 |
0.448 |
-0.00% |
0.448 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC128
|
-2.47% |
159.390 |
155.457 |
0.014 |
-19.45% |
0.014 |
|
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 |
|
External/SPEC/CINT2017rate/505.mcf_r/505.mcf_r
Profile
|
-2.39% |
157.460 |
153.696 |
0.558 |
-1.67% |
0.558 |
|
MultiSource/Applications/hexxagon/hexxagon
Profile
|
-2.37% |
9.231 |
9.012 |
0.002 |
-5.94% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC2
|
-2.29% |
20.477 |
20.009 |
0.017 |
-2.97% |
0.017 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint32_t>/51
|
-2.27% |
94.341 |
92.202 |
0.001 |
-1.52% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopTC2
|
-2.25% |
20.470 |
20.009 |
0.001 |
-3.04% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_MAT_X_MAT_RAW/5001
|
-2.21% |
55231.583 |
54012.231 |
444.422 |
0.26% |
444.422 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC128
|
-2.18% |
161.446 |
157.922 |
0.008 |
2.72% |
0.008 |
|
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 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1BigLoopWithReductionTC64
|
-2.13% |
312.246 |
305.583 |
0.010 |
-0.52% |
0.010 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C++/miniFE/miniFE
Profile
|
-2.10% |
22.898 |
22.417 |
0.127 |
-1.86% |
0.127 |
|
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 |
|
SingleSource/Benchmarks/Adobe-C++/functionobjects
Profile
|
-2.00% |
6.063 |
5.942 |
0.005 |
-2.01% |
0.005 |
|
SingleSource/Benchmarks/Stanford/FloatMM
Profile
|
-1.99% |
0.769 |
0.753 |
0.000 |
-1.99% |
0.000 |
|
MultiSource/Benchmarks/TSVC/GlobalDataFlow-dbl/GlobalDataFlow-dbl
Profile
|
-1.93% |
10.422 |
10.220 |
0.045 |
-1.59% |
0.045 |
|
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/MemFunctions/MemFunctions.test:BM_MemCmp<31, LessThanZero, None>
|
-1.89% |
5268.222 |
5168.621 |
1.085 |
-1.85% |
1.085 |
|
External/SPEC/CINT2017rate/523.xalancbmk_r/523.xalancbmk_r
Profile
|
-1.86% |
213.795 |
209.815 |
0.499 |
-1.77% |
0.499 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_only_novec_int64_t_
|
-1.84% |
1953980.447 |
1918090.411 |
10972.442 |
-0.62% |
10972.442 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_DEL_DOT_VEC_2D_RAW/0
|
-1.82% |
1221.866 |
1199.681 |
0.587 |
-1.23% |
0.587 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC128
|
-1.79% |
160.805 |
157.926 |
0.004 |
1.59% |
0.004 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_MAT_X_MAT_LAMBDA/44217
|
-1.67% |
1044277.000 |
1026854.000 |
5638.563 |
-1.69% |
5638.563 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint8_t>/16
|
-1.67% |
42.883 |
42.168 |
0.001 |
-1.67% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_asinf_autovec_float_
|
-1.66% |
391.824 |
385.339 |
0.036 |
-0.01% |
0.036 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_VOL3D_CALC_LAMBDA/1
|
-1.65% |
209.677 |
206.217 |
1.320 |
-1.19% |
1.320 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint16_t>/16
|
-1.64% |
43.598 |
42.885 |
0.001 |
-4.76% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_expf_novec_float_
|
-1.63% |
463.330 |
455.787 |
0.185 |
0.01% |
0.185 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<31, GreaterThanZero, None>
|
-1.53% |
5257.455 |
5177.266 |
2.774 |
-0.14% |
2.774 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint16_t>/10
|
-1.49% |
47.888 |
47.173 |
0.000 |
-1.50% |
0.000 |
|
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 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint16_t_To_uint64_t_
|
-1.44% |
22199.772 |
21881.023 |
8.089 |
-1.30% |
8.089 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC31
|
-1.43% |
50.031 |
49.315 |
0.001 |
49.98% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_csa_with_in_loop_arith_autovec_uint8_t_
|
-1.41% |
517897.990 |
510612.454 |
230.561 |
-1.64% |
230.561 |
|
External/SPEC/CINT2017rate/531.deepsjeng_r/531.deepsjeng_r
Profile
|
-1.40% |
138.574 |
136.636 |
0.053 |
-0.44% |
0.053 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC15
|
-1.35% |
17.630 |
17.392 |
0.001 |
-1.36% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC15
|
-1.35% |
17.630 |
17.391 |
0.000 |
-1.35% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC15
|
-1.35% |
17.630 |
17.392 |
0.000 |
-1.35% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1LoopWithReductionTC15
|
-1.35% |
17.630 |
17.392 |
0.000 |
-1.35% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC15
|
-1.35% |
17.630 |
17.392 |
0.000 |
-34.23% |
0.000 |
|
SingleSource/Benchmarks/Misc/fbench
Profile
|
-1.34% |
2.896 |
2.857 |
0.005 |
-2.55% |
0.005 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<63, GreaterThanZero, None>
|
-1.33% |
3057.698 |
3016.901 |
2.929 |
-0.09% |
2.929 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_INT_PREDICT_LAMBDA/171
|
-1.30% |
2.091 |
2.064 |
0.003 |
-1.31% |
0.003 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/16
|
-1.28% |
120.606 |
119.061 |
0.004 |
-1.19% |
0.004 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<31, GreaterThanZero, Mid>
|
-1.28% |
5009.226 |
4945.125 |
1.592 |
0.02% |
1.592 |
|
MultiSource/Benchmarks/Ptrdist/anagram/anagram
Profile
|
-1.27% |
1.909 |
1.885 |
0.001 |
-1.32% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_EOS_RAW/5001
|
-1.25% |
36.102 |
35.652 |
0.040 |
-1.08% |
0.040 |
|
MultiSource/Applications/obsequi/Obsequi
Profile
|
-1.24% |
4.273 |
4.220 |
0.004 |
0.21% |
0.004 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, EqZero, Mid>
|
-1.23% |
8444.065 |
8340.444 |
19.632 |
-1.18% |
19.632 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint8_t>/28
|
-1.19% |
60.036 |
59.321 |
0.001 |
-1.19% |
0.001 |
|
SingleSource/Benchmarks/Misc/ReedSolomon
Profile
|
-1.19% |
9.633 |
9.518 |
0.038 |
-0.42% |
0.038 |
|
SingleSource/Benchmarks/Polybench/datamining/correlation/correlation
Profile
|
-1.18% |
24.438 |
24.149 |
0.058 |
-0.97% |
0.058 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_EOS_LAMBDA/44217
|
-1.18% |
400.264 |
395.552 |
0.857 |
-0.83% |
0.857 |
|
SingleSource/Benchmarks/Misc-C++/stepanov_container
Profile
|
-1.18% |
11.029 |
10.899 |
0.021 |
-0.76% |
0.021 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_csa_with_in_loop_arith_novec_uint8_t_
|
-1.16% |
516336.538 |
510335.522 |
2239.047 |
-0.17% |
2239.047 |
|
MicroBenchmarks/ImageProcessing/AnisotropicDiffusion/AnisotropicDiffusion.test:BENCHMARK_ANISTROPIC_DIFFUSION/128
|
-1.14% |
18305.711 |
18097.692 |
6.976 |
-0.80% |
6.976 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_PIC_2D_RAW/171
|
-1.14% |
5.114 |
5.056 |
0.012 |
-0.86% |
0.012 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_EOS_RAW/44217
|
-1.11% |
401.170 |
396.722 |
0.633 |
-0.58% |
0.633 |
|
MicroBenchmarks/ImageProcessing/AnisotropicDiffusion/AnisotropicDiffusion.test:BENCHMARK_ANISTROPIC_DIFFUSION/256
|
-1.10% |
75832.556 |
74998.778 |
24.822 |
-0.83% |
24.822 |
|
MicroBenchmarks/ImageProcessing/AnisotropicDiffusion/AnisotropicDiffusion.test:BENCHMARK_ANISTROPIC_DIFFUSION/32
|
-1.10% |
895.472 |
885.628 |
0.645 |
-0.55% |
0.645 |
|
MultiSource/Benchmarks/Fhourstones-3.1/fhourstones3.1
Profile
|
-1.10% |
2.494 |
2.467 |
0.004 |
1.32% |
0.004 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_ORDERED_DITHER/512/2
|
-1.09% |
19404.139 |
19192.611 |
13.030 |
-0.82% |
13.030 |
|
External/SPEC/CFP2017rate/544.nab_r/544.nab_r
Profile
|
-1.08% |
280.156 |
277.117 |
0.072 |
-1.06% |
0.072 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/32
|
-1.08% |
599.473 |
592.980 |
0.202 |
-1.09% |
0.202 |
|
MultiSource/Benchmarks/Ptrdist/bc/bc
Profile
|
-1.08% |
1.016 |
1.005 |
0.002 |
-0.64% |
0.002 |
|
SingleSource/Benchmarks/Misc-C++-EH/spirit
Profile
|
-1.08% |
15.041 |
14.879 |
0.014 |
-1.55% |
0.014 |
|
MultiSource/Benchmarks/ASCI_Purple/SMG2000/smg2000
Profile
|
-1.08% |
7.269 |
7.191 |
0.018 |
-0.83% |
0.018 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint64_t>/16
|
-1.07% |
66.467 |
65.755 |
0.001 |
5.74% |
0.001 |
|
MultiSource/Benchmarks/TSVC/LoopRestructuring-flt/LoopRestructuring-flt
Profile
|
-1.05% |
7.597 |
7.518 |
0.027 |
-1.14% |
0.027 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/64
|
-1.02% |
2650.125 |
2623.037 |
0.189 |
-1.02% |
0.189 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_only_novec_int32_t_
|
-1.02% |
1424953.157 |
1410421.371 |
4537.533 |
-0.40% |
4537.533 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C/SimpleMOC/SimpleMOC
Profile
|
-1.02% |
8.280 |
8.196 |
0.023 |
-4.08% |
0.023 |
|
MicroBenchmarks/ImageProcessing/AnisotropicDiffusion/AnisotropicDiffusion.test:BENCHMARK_ANISTROPIC_DIFFUSION/64
|
-1.00% |
4202.729 |
4160.554 |
2.955 |
-0.59% |
2.955 |