|
MultiSource/Benchmarks/MiBench/automotive-bitcount/automotive-bitcount
Profile
|
-28.96% |
0.099 |
0.070 |
0.000 |
-29.01% |
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 |
0.001 |
-11.92% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIND_FIRST_MIN_LAMBDA/171
|
-24.28% |
0.495 |
0.375 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint8_t>/999
|
-21.61% |
2169.950 |
1701.116 |
0.859 |
0.37% |
0.859 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint8_t>/999
|
-21.46% |
1102.042 |
865.587 |
0.656 |
0.16% |
0.656 |
|
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
|
-19.95% |
576.774 |
461.728 |
0.886 |
1.41% |
0.886 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIRST_DIFF_RAW/171
|
-19.84% |
0.373 |
0.299 |
0.001 |
-20.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint8_t>/256
|
-19.35% |
306.613 |
247.299 |
0.673 |
0.57% |
0.673 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint8_t>/51
|
-19.12% |
130.793 |
105.783 |
0.001 |
-0.67% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint8_t>/51
|
-18.92% |
79.333 |
64.325 |
0.001 |
1.11% |
0.001 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<1, EqZero, First>
|
-18.85% |
14644.174 |
11884.399 |
15.933 |
-0.02% |
15.933 |
|
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
|
-17.77% |
124.242 |
102.164 |
0.045 |
-16.53% |
0.045 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint16_t_To_uint8_t_
|
-16.71% |
14311.280 |
11919.779 |
6.480 |
-0.07% |
6.480 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC2
|
-16.66% |
8.577 |
7.147 |
0.000 |
-0.01% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC2
|
-16.66% |
8.576 |
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 |
67.900 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint16_t_To_uint8_t_
|
-16.63% |
14308.741 |
11928.526 |
0.224 |
-0.01% |
0.224 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopFrom_uint8_t_To_uint32_t_
|
-16.60% |
14301.978 |
11927.561 |
0.390 |
-0.05% |
0.390 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint16_t_To_uint32_t_
|
-16.60% |
14301.835 |
11927.935 |
6.038 |
-0.04% |
6.038 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopFrom_uint16_t_To_uint32_t_
|
-16.60% |
14301.453 |
11928.055 |
0.150 |
-0.05% |
0.150 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopFrom_uint16_t_To_uint8_t_
|
-16.53% |
14301.706 |
11938.244 |
0.041 |
0.06% |
0.041 |
|
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_
|
-15.11% |
799131.429 |
678381.183 |
1072.440 |
-15.09% |
1072.440 |
|
MicroBenchmarks/ImageProcessing/Blur/blur.test:BENCHMARK_boxBlurKernel/512
|
-15.08% |
20158.657 |
17119.463 |
76.858 |
-15.11% |
76.858 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_only_autovec_int64_t_
|
-14.59% |
793300.795 |
677534.884 |
312.027 |
-14.62% |
312.027 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint16_t>/65
|
-14.12% |
96.541 |
82.910 |
0.002 |
0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint8_t>/16
|
-14.10% |
55.747 |
47.887 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/ImageProcessing/Blur/blur.test:BENCHMARK_boxBlurKernel/128
|
-14.07% |
1077.593 |
926.029 |
0.660 |
-14.12% |
0.660 |
|
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
|
-13.79% |
4579.882 |
3948.198 |
9.494 |
-13.83% |
9.494 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint8_t>/16
|
-13.33% |
42.883 |
37.166 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC64
|
-12.79% |
73.520 |
64.117 |
0.001 |
-0.32% |
0.001 |
|
MicroBenchmarks/ImageProcessing/Blur/blur.test:BENCHMARK_boxBlurKernel/1024
|
-12.78% |
84629.250 |
73812.667 |
38.033 |
-12.90% |
38.033 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_cond_load_novec_int32_t_
|
-12.72% |
596262.887 |
520399.110 |
1015.799 |
-6.68% |
1015.799 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_csa_with_cond_arith_novec_int64_t_
|
-11.82% |
783393.498 |
690786.772 |
1140.718 |
-0.02% |
1140.718 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint8_t>/10
|
-11.67% |
42.884 |
37.880 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint32_t>/28
|
-11.29% |
44.313 |
39.310 |
0.002 |
-1.79% |
0.002 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIND_FIRST_MIN_LAMBDA/44217
|
-10.87% |
131.927 |
117.587 |
0.407 |
-4.90% |
0.407 |
|
MultiSource/Benchmarks/Trimaran/enc-md5/enc-md5
Profile
|
-10.78% |
3.009 |
2.684 |
0.000 |
-10.79% |
0.000 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_FLOYD_DITHER/512
|
-10.67% |
4425.120 |
3952.813 |
19.462 |
-10.86% |
19.462 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchAutoVec<uint16_t>/65
|
-10.67% |
160.817 |
143.660 |
0.002 |
-0.50% |
0.002 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_FLOYD_DITHER/256
|
-10.20% |
1105.583 |
992.767 |
0.131 |
-10.09% |
0.131 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchAutoVec<uint16_t>/127
|
-9.82% |
298.778 |
269.450 |
0.005 |
-0.26% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint8_t>/10
|
-9.81% |
36.450 |
32.876 |
0.001 |
-0.01% |
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
|
-9.08% |
273.867 |
249.011 |
0.593 |
-8.96% |
0.593 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<31, LessThanZero, First>
|
-8.75% |
2499.450 |
2280.628 |
2.040 |
-0.53% |
2.040 |
|
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 |
55.035 |
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 |
4495.559 |
5.089 |
-0.04% |
5.089 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIRST_DIFF_RAW/5001
|
-7.94% |
10.874 |
10.010 |
0.047 |
-7.92% |
0.047 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC128
|
-7.89% |
153.670 |
141.543 |
0.016 |
-6.14% |
0.016 |
|
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 |
|
External/SPEC/CFP2017rate/508.namd_r/508.namd_r
Profile
|
-7.51% |
83.778 |
77.488 |
0.055 |
-7.77% |
0.055 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_cond_load_novec_int64_t_
|
-7.50% |
862734.568 |
798035.510 |
285.092 |
-0.33% |
285.092 |
|
SingleSource/Benchmarks/Shootout/Shootout-lists
Profile
|
-7.29% |
10.331 |
9.578 |
0.013 |
-7.33% |
0.013 |
|
SingleSource/Benchmarks/McGill/misr
Profile
|
-7.23% |
0.442 |
0.410 |
0.000 |
-7.24% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_ENERGY_CALC_RAW/44217
|
-7.00% |
2290.595 |
2130.309 |
26.652 |
-4.86% |
26.652 |
|
MicroBenchmarks/ImageProcessing/Blur/blur.test:BENCHMARK_GAUSSIAN_BLUR/256
|
-6.82% |
15344.891 |
14298.388 |
21.413 |
-6.85% |
21.413 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint32_t>/10
|
-6.82% |
31.448 |
29.304 |
0.001 |
2.50% |
0.001 |
|
MicroBenchmarks/ImageProcessing/Blur/blur.test:BENCHMARK_GAUSSIAN_BLUR/128
|
-6.78% |
3593.077 |
3349.416 |
0.457 |
-6.81% |
0.457 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_ADI_RAW/171
|
-6.76% |
9.784 |
9.123 |
0.065 |
0.35% |
0.065 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC7
|
-6.67% |
10.721 |
10.006 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC7
|
-6.66% |
10.721 |
10.006 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/ImageProcessing/Blur/blur.test:BENCHMARK_GAUSSIAN_BLUR/512
|
-6.60% |
63468.364 |
59280.917 |
111.535 |
-6.63% |
111.535 |
|
MultiSource/Applications/JM/lencod/lencod
Profile
|
-6.56% |
14.621 |
13.662 |
0.010 |
-5.56% |
0.010 |
|
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 |
5.360 |
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 |
148.893 |
0.004 |
-0.55% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC32
|
-6.02% |
163.676 |
153.819 |
0.026 |
0.33% |
0.026 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC127
|
-6.02% |
648.265 |
609.251 |
1.336 |
-0.72% |
1.336 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC4
|
-5.89% |
12.151 |
11.435 |
0.000 |
0.00% |
0.000 |
|
SingleSource/Benchmarks/Adobe-C++/loop_unroll
Profile
|
-5.74% |
1.715 |
1.616 |
0.000 |
-5.72% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC128
|
-5.74% |
651.829 |
614.444 |
0.020 |
-0.67% |
0.020 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC64
|
-5.61% |
323.777 |
305.597 |
0.002 |
-0.51% |
0.002 |
|
MultiSource/Benchmarks/Trimaran/enc-rc4/enc-rc4
Profile
|
-5.59% |
1.933 |
1.825 |
0.001 |
-5.69% |
0.001 |
|
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/MemFunctions/MemFunctions.test:BM_MemCmp<5, LessThanZero, None>
|
-5.41% |
21668.431 |
20496.252 |
18.826 |
-2.77% |
18.826 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIRST_DIFF_RAW/44217
|
-5.17% |
96.106 |
91.136 |
0.218 |
-5.13% |
0.218 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_xor_no_runtime_checks_needed<16, int>
|
-5.13% |
27.874 |
26.445 |
0.000 |
-5.13% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1LoopWithReductionTC2
|
-5.10% |
5.403 |
5.128 |
0.056 |
-5.04% |
0.056 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopTC31
|
-5.03% |
288.541 |
274.034 |
0.006 |
-4.94% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC31
|
-5.02% |
288.460 |
273.988 |
0.027 |
-4.92% |
0.027 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC31
|
-4.97% |
288.355 |
274.014 |
0.025 |
-4.95% |
0.025 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC8
|
-4.92% |
43.599 |
41.455 |
0.003 |
-0.04% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopTC128
|
-4.91% |
1189.811 |
1131.416 |
0.022 |
-5.09% |
0.022 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC128
|
-4.90% |
1189.757 |
1131.501 |
0.368 |
-4.90% |
0.368 |
|
SingleSource/Benchmarks/Polybench/linear-algebra/blas/gemver/gemver
Profile
|
-4.89% |
0.317 |
0.301 |
0.006 |
0.48% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC64
|
-4.89% |
595.872 |
566.720 |
0.022 |
-4.85% |
0.022 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopTC64
|
-4.88% |
595.811 |
566.750 |
0.005 |
-4.85% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC128
|
-4.86% |
1189.823 |
1132.037 |
0.011 |
-4.80% |
0.011 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC15
|
-4.85% |
143.478 |
136.518 |
0.004 |
-4.42% |
0.004 |
|
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 |
42.168 |
0.002 |
-1.67% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopTC63
|
-4.83% |
587.762 |
559.346 |
0.002 |
-4.75% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC63
|
-4.81% |
587.571 |
559.308 |
0.013 |
-4.83% |
0.013 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopTC127
|
-4.80% |
1181.779 |
1125.026 |
0.371 |
-4.95% |
0.371 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC64
|
-4.80% |
595.924 |
567.342 |
0.013 |
-4.72% |
0.013 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC127
|
-4.80% |
1181.723 |
1125.056 |
0.025 |
-4.69% |
0.025 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC127
|
-4.79% |
1181.728 |
1125.068 |
0.033 |
-4.80% |
0.033 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC63
|
-4.79% |
587.477 |
559.321 |
0.010 |
-5.33% |
0.010 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<8, LessThanZero, Last>
|
-4.75% |
15377.892 |
14647.130 |
8.162 |
-4.75% |
8.162 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<15, LessThanZero, Mid>
|
-4.74% |
8203.141 |
7814.110 |
4.917 |
-4.76% |
4.917 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<8, LessThanZero, None>
|
-4.65% |
15744.518 |
15012.032 |
7.039 |
-2.39% |
7.039 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopTC3
|
-4.63% |
28.754 |
27.422 |
0.007 |
-3.74% |
0.007 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint32_t>/28
|
-4.60% |
62.182 |
59.322 |
0.002 |
-1.20% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC7
|
-4.55% |
15.724 |
15.009 |
0.000 |
39.98% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_DEL_DOT_VEC_2D_RAW/1
|
-4.48% |
199.404 |
190.473 |
0.554 |
-2.70% |
0.554 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopTC8
|
-4.46% |
73.877 |
70.583 |
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
|
-4.30% |
319.468 |
305.740 |
0.028 |
1.11% |
0.028 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC8
|
-4.29% |
73.724 |
70.561 |
0.002 |
-4.40% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint64_t>/51
|
-4.28% |
135.907 |
130.083 |
0.001 |
1.10% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC8
|
-4.22% |
73.669 |
70.559 |
0.002 |
-4.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopTC16
|
-4.16% |
152.684 |
146.337 |
0.003 |
-4.08% |
0.003 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<8, GreaterThanZero, First>
|
-4.16% |
8791.578 |
8426.236 |
6.758 |
0.00% |
6.758 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC16
|
-4.15% |
152.682 |
146.341 |
0.002 |
-4.06% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC16
|
-4.15% |
152.673 |
146.337 |
0.002 |
-4.12% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint16_t_To_uint32_t_
|
-4.14% |
21452.392 |
20565.335 |
29.602 |
-4.13% |
29.602 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopTC15
|
-4.10% |
143.890 |
137.985 |
0.062 |
-2.20% |
0.062 |
|
MultiSource/Benchmarks/MiBench/telecomm-CRC32/telecomm-CRC32
Profile
|
-3.99% |
0.597 |
0.573 |
0.002 |
-4.35% |
0.002 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_DEL_DOT_VEC_2D_LAMBDA/1
|
-3.98% |
198.302 |
190.411 |
0.536 |
-3.54% |
0.536 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC4
|
-3.92% |
24.300 |
23.348 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC15
|
-3.89% |
142.032 |
136.510 |
0.004 |
-5.91% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC15
|
-3.82% |
78.623 |
75.620 |
0.001 |
-0.02% |
0.001 |
|
MultiSource/Applications/siod/siod
Profile
|
-3.79% |
5.676 |
5.461 |
0.010 |
-0.02% |
0.010 |
|
MultiSource/Benchmarks/sim/sim
Profile
|
-3.74% |
6.606 |
6.359 |
0.006 |
-5.23% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC3
|
-3.74% |
28.459 |
27.395 |
0.010 |
-4.25% |
0.010 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC3
|
-3.72% |
28.476 |
27.416 |
0.006 |
-3.63% |
0.006 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<3, LessThanZero, Mid>
|
-3.71% |
26351.380 |
25375.032 |
22.101 |
-3.69% |
22.101 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC16
|
-3.70% |
83.625 |
80.527 |
0.001 |
-0.14% |
0.001 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, LessThanZero, Last>
|
-3.70% |
39531.737 |
38067.653 |
30.637 |
-3.72% |
30.637 |
|
MultiSource/Benchmarks/Fhourstones/fhourstones
Profile
|
-3.64% |
2.384 |
2.297 |
0.009 |
-0.35% |
0.009 |
|
MultiSource/Benchmarks/mafft/pairlocalalign
Profile
|
-3.58% |
47.903 |
46.188 |
0.017 |
-2.76% |
0.017 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC32
|
-3.57% |
293.323 |
282.849 |
0.003 |
-3.37% |
0.003 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_VOL3D_CALC_LAMBDA/2
|
-3.53% |
7.764 |
7.490 |
0.000 |
-3.55% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_VOL3D_CALC_RAW/2
|
-3.53% |
7.764 |
7.490 |
0.002 |
-3.53% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopTC32
|
-3.51% |
293.212 |
282.923 |
0.012 |
-3.39% |
0.012 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC32
|
-3.48% |
293.033 |
282.847 |
0.003 |
-3.44% |
0.003 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, LessThanZero, None>
|
-3.34% |
43922.884 |
42456.448 |
32.584 |
-6.45% |
32.584 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<3, LessThanZero, Last>
|
-3.30% |
30274.020 |
29276.244 |
27.330 |
-3.22% |
27.330 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<5, GreaterThanZero, Mid>
|
-3.26% |
18160.148 |
17568.721 |
17.000 |
-0.00% |
17.000 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<3, EqZero, Last>
|
-3.26% |
30262.696 |
29277.457 |
30.072 |
-0.00% |
30.072 |
|
MultiSource/Benchmarks/MiBench/consumer-typeset/consumer-typeset
Profile
|
-3.25% |
0.369 |
0.357 |
0.000 |
-0.14% |
0.000 |
|
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 |
|
MultiSource/Benchmarks/nbench/nbench
Profile
|
-3.23% |
3.870 |
3.745 |
0.001 |
-0.82% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_two_loads<uint32_t>/10
|
-3.23% |
22.157 |
21.442 |
0.001 |
-0.00% |
0.001 |
|
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>/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 |
0.001 |
-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
|
-3.15% |
135.747 |
131.468 |
0.147 |
0.00% |
0.147 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_two_loads<uint8_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>/28
|
-3.13% |
22.872 |
22.156 |
0.001 |
-3.12% |
0.001 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, LessThanZero, Mid>
|
-3.13% |
23436.289 |
22703.202 |
17.469 |
0.02% |
17.469 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_two_loads<uint8_t>/16
|
-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 |
0.001 |
-0.00% |
0.001 |
|
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<uint16_t>/256
|
-3.12% |
22.870 |
22.156 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_two_loads<uint8_t>/51
|
-3.12% |
22.871 |
22.156 |
0.001 |
-3.12% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint32_t>/28
|
-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 |
0.001 |
-3.13% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_two_loads<uint8_t>/256
|
-3.12% |
22.871 |
22.157 |
0.001 |
-3.12% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint32_t>/999
|
-3.12% |
22.871 |
22.157 |
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 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint32_t>/51
|
-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>/10
|
-3.12% |
22.870 |
22.156 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint16_t>/28
|
-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>/16
|
-3.12% |
22.871 |
22.157 |
0.004 |
-0.00% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint32_t>/16
|
-3.12% |
22.870 |
22.157 |
0.001 |
-3.12% |
0.001 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<16, EqZero, First>
|
-3.11% |
5862.960 |
5680.530 |
4.134 |
-0.01% |
4.134 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<7, EqZero, Mid>
|
-3.06% |
13812.332 |
13389.525 |
9.843 |
0.00% |
9.843 |
|
MicroBenchmarks/ImageProcessing/Blur/blur.test:BENCHMARK_GAUSSIAN_BLUR/1024
|
-3.05% |
261704.667 |
253715.667 |
838.272 |
-3.04% |
838.272 |
|
MicroBenchmarks/LoopInterchange/LoopInterchange.test:BENCHMARK_LI1
|
-2.95% |
2563.655 |
2487.943 |
10.366 |
-20.77% |
10.366 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, LessThanZero, None>
|
-2.95% |
24893.208 |
24159.838 |
21.663 |
-2.93% |
21.663 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint8_t>/127
|
-2.92% |
171.534 |
166.527 |
0.054 |
-2.11% |
0.054 |
|
External/SPEC/CINT2017rate/505.mcf_r/505.mcf_r
Profile
|
-2.91% |
157.460 |
152.874 |
1.077 |
-2.19% |
1.077 |
|
MicroBenchmarks/Builtins/Int128/Builtins.test:BM_DivideIntrinsic128UniformDivisor<__uint128_t>
|
-2.89% |
38.500 |
37.388 |
0.034 |
0.06% |
0.034 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<5, EqZero, Last>
|
-2.88% |
20502.460 |
19912.556 |
13.876 |
-0.00% |
13.876 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<8, GreaterThanZero, Mid>
|
-2.85% |
12816.349 |
12450.496 |
8.051 |
-0.01% |
8.051 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<32, EqZero, Mid>
|
-2.83% |
3210.647 |
3119.756 |
0.643 |
-0.00% |
0.643 |
|
SingleSource/Benchmarks/Misc/revertBits
Profile
|
-2.78% |
0.411 |
0.400 |
0.000 |
-2.75% |
0.000 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<5, LessThanZero, Last>
|
-2.78% |
21081.255 |
20495.330 |
9.514 |
-0.01% |
9.514 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<6, GreaterThanZero, Last>
|
-2.70% |
18044.302 |
17557.950 |
11.732 |
0.00% |
11.732 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<6, LessThanZero, None>
|
-2.63% |
18531.371 |
18043.130 |
16.012 |
-2.64% |
16.012 |
|
MultiSource/Applications/aha/aha
Profile
|
-2.62% |
3.875 |
3.774 |
0.000 |
-3.05% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC2
|
-2.61% |
20.534 |
19.999 |
0.004 |
-4.00% |
0.004 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_DEL_DOT_VEC_2D_LAMBDA/2
|
-2.60% |
2.408 |
2.345 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<7, EqZero, None>
|
-2.50% |
16732.734 |
16314.898 |
12.082 |
-0.00% |
12.082 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC128
|
-2.47% |
159.390 |
155.453 |
0.004 |
-19.45% |
0.004 |
|
External/SPEC/CINT2017rate/500.perlbench_r/500.perlbench_r
Profile
|
-2.44% |
103.399 |
100.872 |
0.093 |
-0.00% |
0.093 |
|
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 |
|
MultiSource/Applications/hexxagon/hexxagon
Profile
|
-2.44% |
9.231 |
9.006 |
0.005 |
-6.01% |
0.005 |
|
MultiSource/Applications/SPASS/SPASS
Profile
|
-2.39% |
26.073 |
25.449 |
0.019 |
0.31% |
0.019 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC2
|
-2.32% |
20.477 |
20.002 |
0.021 |
-3.00% |
0.021 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint32_t>/51
|
-2.27% |
94.341 |
92.199 |
0.004 |
-1.53% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopTC2
|
-2.25% |
20.470 |
20.009 |
0.001 |
-3.04% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC8
|
-2.18% |
10.960 |
10.721 |
0.000 |
-6.25% |
0.000 |
|
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 |
157.934 |
0.010 |
2.73% |
0.010 |
|
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 |
305.602 |
0.003 |
-0.51% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint8_t>/10
|
-2.08% |
34.306 |
33.592 |
0.001 |
-2.08% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_HYDRO_2D_RAW/44217
|
-2.03% |
29619.000 |
29017.125 |
176.813 |
-1.28% |
176.813 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_HYDRO_2D_RAW/5001
|
-2.02% |
2253.697 |
2208.228 |
14.464 |
0.20% |
14.464 |
|
SingleSource/Benchmarks/Stanford/FloatMM
Profile
|
-1.99% |
0.769 |
0.753 |
0.002 |
-1.98% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint16_t>/10
|
-1.92% |
37.166 |
36.452 |
0.002 |
-0.00% |
0.002 |
|
MultiSource/Benchmarks/TSVC/LoopRerolling-flt/LoopRerolling-flt
Profile
|
-1.90% |
10.948 |
10.739 |
0.062 |
-1.70% |
0.062 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C++/miniFE/miniFE
Profile
|
-1.89% |
22.898 |
22.465 |
0.097 |
-1.65% |
0.097 |
|
SingleSource/Benchmarks/Adobe-C++/functionobjects
Profile
|
-1.82% |
6.063 |
5.953 |
0.003 |
-1.83% |
0.003 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<31, LessThanZero, None>
|
-1.79% |
5268.222 |
5173.921 |
2.550 |
-1.75% |
2.550 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC128
|
-1.78% |
160.805 |
157.938 |
0.008 |
1.59% |
0.008 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_DEL_DOT_VEC_2D_RAW/0
|
-1.77% |
1221.866 |
1200.180 |
1.270 |
-1.19% |
1.270 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_MAT_X_MAT_LAMBDA/44217
|
-1.76% |
1044277.000 |
1025868.000 |
5372.479 |
-1.78% |
5372.479 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_only_novec_int64_t_
|
-1.72% |
1953980.447 |
1920274.725 |
5912.161 |
-0.51% |
5912.161 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint8_t>/16
|
-1.66% |
42.883 |
42.169 |
0.001 |
-1.67% |
0.001 |
|
External/SPEC/CINT2017rate/523.xalancbmk_r/523.xalancbmk_r
Profile
|
-1.65% |
213.795 |
210.258 |
0.444 |
-1.56% |
0.444 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_asinf_autovec_float_
|
-1.64% |
391.824 |
385.382 |
0.030 |
-0.00% |
0.030 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint16_t>/16
|
-1.64% |
43.598 |
42.883 |
0.001 |
-4.76% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_expf_novec_float_
|
-1.62% |
463.330 |
455.827 |
0.159 |
0.02% |
0.159 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, EqZero, Mid>
|
-1.53% |
8444.065 |
8314.684 |
32.167 |
-1.49% |
32.167 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint16_t>/10
|
-1.49% |
47.888 |
47.172 |
0.001 |
-1.50% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint64_t>/10
|
-1.45% |
49.316 |
48.601 |
0.002 |
3.02% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC31
|
-1.43% |
50.031 |
49.316 |
0.000 |
49.98% |
0.000 |
|
MicroBenchmarks/ImageProcessing/AnisotropicDiffusion/AnisotropicDiffusion.test:BENCHMARK_ANISTROPIC_DIFFUSION/32
|
-1.43% |
895.472 |
882.693 |
0.997 |
-0.88% |
0.997 |
|
External/SPEC/CINT2017rate/531.deepsjeng_r/531.deepsjeng_r
Profile
|
-1.43% |
138.574 |
136.598 |
0.008 |
-0.47% |
0.008 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_csa_with_in_loop_arith_autovec_uint8_t_
|
-1.42% |
517897.990 |
510531.045 |
493.777 |
-1.65% |
493.777 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint16_t_To_uint64_t_
|
-1.42% |
22199.772 |
21884.689 |
9.839 |
-1.28% |
9.839 |
|
MultiSource/Applications/obsequi/Obsequi
Profile
|
-1.37% |
4.273 |
4.214 |
0.007 |
0.09% |
0.007 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1LoopWithReductionTC15
|
-1.36% |
17.630 |
17.391 |
0.000 |
-1.35% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC15
|
-1.36% |
17.630 |
17.391 |
0.000 |
-1.36% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC15
|
-1.35% |
17.630 |
17.392 |
0.000 |
-1.35% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC15
|
-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 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_EOS_LAMBDA/44217
|
-1.34% |
400.264 |
394.901 |
1.134 |
-1.00% |
1.134 |
|
SingleSource/Benchmarks/Misc/fbench
Profile
|
-1.32% |
2.896 |
2.857 |
0.004 |
-2.53% |
0.004 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_INT_PREDICT_LAMBDA/171
|
-1.30% |
2.091 |
2.064 |
0.010 |
-1.31% |
0.010 |
|
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 |
119.067 |
0.003 |
-1.19% |
0.003 |
|
MultiSource/Benchmarks/TSVC/LoopRestructuring-flt/LoopRestructuring-flt
Profile
|
-1.26% |
7.597 |
7.501 |
0.023 |
-1.35% |
0.023 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_EOS_RAW/5001
|
-1.25% |
36.102 |
35.652 |
0.045 |
-1.08% |
0.045 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<63, GreaterThanZero, None>
|
-1.19% |
3057.698 |
3021.308 |
2.388 |
-0.00% |
2.388 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint8_t>/28
|
-1.19% |
60.036 |
59.323 |
0.001 |
-1.19% |
0.001 |
|
MicroBenchmarks/ImageProcessing/AnisotropicDiffusion/AnisotropicDiffusion.test:BENCHMARK_ANISTROPIC_DIFFUSION/128
|
-1.19% |
18305.711 |
18088.513 |
11.624 |
-0.85% |
11.624 |
|
SingleSource/Benchmarks/BenchmarkGame/recursive
Profile
|
-1.18% |
2.338 |
2.311 |
0.002 |
-0.84% |
0.002 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_INT_PREDICT_RAW/171
|
-1.18% |
2.092 |
2.067 |
0.000 |
-1.19% |
0.000 |
|
SingleSource/Benchmarks/Misc/ReedSolomon
Profile
|
-1.18% |
9.633 |
9.520 |
0.000 |
-0.40% |
0.000 |
|
MultiSource/Benchmarks/TSVC/CrossingThresholds-flt/CrossingThresholds-flt
Profile
|
-1.16% |
8.157 |
8.062 |
0.034 |
-1.36% |
0.034 |
|
MultiSource/Benchmarks/Ptrdist/bc/bc
Profile
|
-1.14% |
1.016 |
1.004 |
0.001 |
-0.70% |
0.001 |
|
MultiSource/Benchmarks/Fhourstones-3.1/fhourstones3.1
Profile
|
-1.13% |
2.494 |
2.466 |
0.005 |
1.29% |
0.005 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<31, GreaterThanZero, Mid>
|
-1.12% |
5009.226 |
4953.260 |
1.222 |
0.02% |
1.222 |
|
MicroBenchmarks/Builtins/Int128/Builtins.test:BM_RemainderIntrinsic128UniformDivisor<__uint128_t>
|
-1.09% |
48.769 |
48.237 |
0.079 |
-1.20% |
0.079 |
|
MicroBenchmarks/ImageProcessing/AnisotropicDiffusion/AnisotropicDiffusion.test:BENCHMARK_ANISTROPIC_DIFFUSION/256
|
-1.09% |
75832.556 |
75007.556 |
17.903 |
-0.82% |
17.903 |
|
External/SPEC/CFP2017rate/544.nab_r/544.nab_r
Profile
|
-1.08% |
280.156 |
277.120 |
0.039 |
-1.06% |
0.039 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/32
|
-1.08% |
599.473 |
592.982 |
0.214 |
-1.09% |
0.214 |
|
SingleSource/Benchmarks/Misc-C++/stepanov_container
Profile
|
-1.07% |
11.029 |
10.910 |
0.018 |
-0.66% |
0.018 |
|
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 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_EOS_RAW/44217
|
-1.07% |
401.170 |
396.874 |
0.200 |
-0.54% |
0.200 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_ORDERED_DITHER/512/2
|
-1.05% |
19404.139 |
19201.056 |
12.968 |
-0.77% |
12.968 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_only_novec_int32_t_
|
-1.02% |
1424953.157 |
1410411.290 |
3891.334 |
-0.40% |
3891.334 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/64
|
-1.02% |
2650.125 |
2623.127 |
0.052 |
-1.01% |
0.052 |
|
MultiSource/Applications/SIBsim4/SIBsim4
Profile
|
-1.01% |
8.738 |
8.649 |
0.016 |
-1.27% |
0.016 |