|
MultiSource/Benchmarks/MiBench/automotive-bitcount/automotive-bitcount
Profile
|
-29.20% |
0.099 |
0.070 |
0.000 |
-29.23% |
0.000 |
|
MultiSource/Benchmarks/Trimaran/enc-pc1/enc-pc1
Profile
|
-27.44% |
0.636 |
0.461 |
0.000 |
-18.96% |
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
|
-24.80% |
0.498 |
0.375 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint8_t>/999
|
-21.60% |
2169.819 |
1701.094 |
2.596 |
0.37% |
2.596 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint8_t>/999
|
-21.51% |
1102.055 |
864.960 |
0.859 |
0.09% |
0.859 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC1
|
-20.99% |
6.433 |
5.082 |
0.000 |
-11.08% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIRST_DIFF_RAW/171
|
-20.12% |
0.373 |
0.298 |
0.004 |
-20.28% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint8_t>/256
|
-19.95% |
576.790 |
461.743 |
2.267 |
1.41% |
2.267 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint8_t>/256
|
-19.57% |
306.601 |
246.585 |
0.337 |
0.28% |
0.337 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint8_t>/51
|
-19.13% |
130.793 |
105.776 |
0.003 |
-0.67% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint8_t>/51
|
-18.91% |
79.331 |
64.327 |
0.001 |
1.12% |
0.001 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<1, EqZero, First>
|
-18.85% |
14644.455 |
11883.970 |
1.255 |
-0.02% |
1.255 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint8_t>/28
|
-17.95% |
55.749 |
45.742 |
0.000 |
-0.00% |
0.000 |
|
External/SPEC/CINT2017rate/525.x264_r/525.x264_r
Profile
|
-17.77% |
124.256 |
102.173 |
0.027 |
-16.52% |
0.027 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint8_t>/28
|
-16.67% |
81.478 |
67.897 |
0.002 |
-0.01% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC2
|
-16.67% |
8.577 |
7.147 |
0.000 |
-0.01% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC2
|
-16.66% |
8.577 |
7.147 |
0.000 |
-0.01% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint16_t_To_uint8_t_
|
-16.66% |
14301.825 |
11919.288 |
6.392 |
-0.07% |
6.392 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint16_t_To_uint8_t_
|
-16.65% |
14311.572 |
11928.329 |
0.216 |
-0.02% |
0.216 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopFrom_uint16_t_To_uint8_t_
|
-16.65% |
14311.011 |
11928.770 |
4.603 |
-0.01% |
4.603 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopFrom_uint8_t_To_uint32_t_
|
-16.60% |
14301.766 |
11927.800 |
0.106 |
-0.05% |
0.106 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint16_t_To_uint32_t_
|
-16.60% |
14302.243 |
11928.254 |
0.126 |
-0.04% |
0.126 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopFrom_uint16_t_To_uint32_t_
|
-16.59% |
14301.551 |
11928.295 |
0.099 |
-0.05% |
0.099 |
|
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
|
-15.37% |
20177.657 |
17076.439 |
66.072 |
-15.32% |
66.072 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_cond_load_autovec_int64_t_
|
-15.25% |
800160.367 |
678133.981 |
538.511 |
-15.12% |
538.511 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_only_autovec_int64_t_
|
-14.69% |
793734.091 |
677169.409 |
294.402 |
-14.67% |
294.402 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint8_t>/16
|
-14.10% |
55.746 |
47.886 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint32_t>/16
|
-14.00% |
35.736 |
30.733 |
0.001 |
-2.27% |
0.001 |
|
MicroBenchmarks/ImageProcessing/Blur/blur.test:BENCHMARK_boxBlurKernel/128
|
-13.87% |
1074.860 |
925.826 |
0.274 |
-14.14% |
0.274 |
|
MicroBenchmarks/ImageProcessing/Blur/blur.test:BENCHMARK_boxBlurKernel/256
|
-13.79% |
4581.686 |
3949.684 |
2.641 |
-13.80% |
2.641 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint16_t>/65
|
-13.38% |
95.712 |
82.907 |
0.003 |
-0.00% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint8_t>/16
|
-13.33% |
42.884 |
37.166 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/ImageProcessing/Blur/blur.test:BENCHMARK_boxBlurKernel/1024
|
-12.85% |
84666.625 |
73785.000 |
3.951 |
-12.93% |
3.951 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC64
|
-12.60% |
73.357 |
64.117 |
0.001 |
-0.32% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_csa_with_cond_arith_novec_int64_t_
|
-11.67% |
783473.684 |
692053.412 |
849.648 |
0.17% |
849.648 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint8_t>/10
|
-11.66% |
42.882 |
37.880 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIND_FIRST_MIN_LAMBDA/44217
|
-11.56% |
132.265 |
116.969 |
0.610 |
-5.40% |
0.610 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_cond_load_novec_int32_t_
|
-11.36% |
590443.692 |
523352.155 |
2130.884 |
-6.15% |
2130.884 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint32_t>/28
|
-11.29% |
44.312 |
39.309 |
0.001 |
-1.79% |
0.001 |
|
MultiSource/Benchmarks/Trimaran/enc-md5/enc-md5
Profile
|
-10.79% |
3.008 |
2.684 |
0.000 |
-10.80% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchAutoVec<uint16_t>/65
|
-10.67% |
160.817 |
143.663 |
0.006 |
-0.49% |
0.006 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_FLOYD_DITHER/512
|
-10.34% |
4437.734 |
3978.831 |
16.574 |
-10.27% |
16.574 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_FLOYD_DITHER/256
|
-10.22% |
1105.431 |
992.495 |
0.436 |
-10.11% |
0.436 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchAutoVec<uint16_t>/127
|
-9.81% |
298.762 |
269.454 |
0.003 |
-0.26% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint8_t>/10
|
-9.80% |
36.451 |
32.878 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_FLOYD_DITHER/128
|
-9.30% |
274.129 |
248.627 |
0.170 |
-9.10% |
0.170 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC2
|
-9.09% |
7.862 |
7.147 |
0.000 |
-16.66% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_PRESSURE_CALC_RAW/171
|
-8.81% |
1.357 |
1.237 |
0.000 |
-0.06% |
0.000 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<31, LessThanZero, First>
|
-8.75% |
2499.327 |
2280.722 |
0.210 |
-0.53% |
0.210 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint32_t>/51
|
-8.34% |
60.038 |
55.032 |
0.002 |
-1.28% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC4
|
-8.34% |
8.577 |
7.862 |
0.000 |
-26.66% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC4
|
-8.33% |
8.577 |
7.862 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC4
|
-8.33% |
8.577 |
7.862 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_HYDRO_1D_LAMBDA/171
|
-8.07% |
0.496 |
0.456 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1LoopWithReductionTC3
|
-8.03% |
8.548 |
7.862 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIRST_DIFF_RAW/5001
|
-7.98% |
10.872 |
10.004 |
0.003 |
-7.97% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_cond_load_novec_int64_t_
|
-7.86% |
864289.246 |
796339.408 |
1208.492 |
-0.54% |
1208.492 |
|
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 |
|
External/SPEC/CFP2017rate/508.namd_r/508.namd_r
Profile
|
-7.58% |
83.751 |
77.405 |
0.238 |
-7.87% |
0.238 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1LoopWithReductionTC4
|
-7.50% |
9.272 |
8.576 |
0.000 |
-0.01% |
0.000 |
|
SingleSource/Benchmarks/McGill/misr
Profile
|
-7.37% |
0.442 |
0.409 |
0.001 |
-7.40% |
0.001 |
|
SingleSource/Benchmarks/Shootout/Shootout-lists
Profile
|
-7.37% |
10.337 |
9.576 |
0.007 |
-7.36% |
0.007 |
|
MultiSource/Benchmarks/TSVC/Symbolics-flt/Symbolics-flt
Profile
|
-7.25% |
8.143 |
7.552 |
0.150 |
-1.28% |
0.150 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint32_t>/10
|
-6.82% |
31.448 |
29.304 |
0.000 |
2.50% |
0.000 |
|
MicroBenchmarks/ImageProcessing/Blur/blur.test:BENCHMARK_GAUSSIAN_BLUR/256
|
-6.81% |
15345.978 |
14301.224 |
11.105 |
-6.83% |
11.105 |
|
MicroBenchmarks/ImageProcessing/Blur/blur.test:BENCHMARK_GAUSSIAN_BLUR/128
|
-6.74% |
3593.118 |
3351.057 |
1.436 |
-6.76% |
1.436 |
|
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 |
-0.01% |
0.000 |
|
MicroBenchmarks/ImageProcessing/Blur/blur.test:BENCHMARK_GAUSSIAN_BLUR/512
|
-6.44% |
63448.455 |
59360.417 |
19.023 |
-6.50% |
19.023 |
|
MultiSource/Applications/JM/lencod/lencod
Profile
|
-6.44% |
14.630 |
13.689 |
0.007 |
-5.37% |
0.007 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC1
|
-6.28% |
5.718 |
5.359 |
0.001 |
-6.27% |
0.001 |
|
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/LCALS/SubsetARawLoops/lcalsARaw.test:BM_ENERGY_CALC_RAW/44217
|
-6.22% |
2253.807 |
2113.598 |
7.391 |
-5.61% |
7.391 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC31
|
-6.16% |
158.668 |
148.898 |
0.004 |
-0.55% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC127
|
-6.02% |
648.272 |
609.276 |
1.085 |
-0.72% |
1.085 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC32
|
-6.01% |
163.671 |
153.832 |
0.024 |
0.34% |
0.024 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC4
|
-5.88% |
12.150 |
11.436 |
0.000 |
-0.00% |
0.000 |
|
MultiSource/Benchmarks/Trimaran/enc-rc4/enc-rc4
Profile
|
-5.83% |
1.936 |
1.823 |
0.002 |
-5.79% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC128
|
-5.74% |
651.861 |
614.437 |
0.040 |
-0.68% |
0.040 |
|
SingleSource/Benchmarks/Adobe-C++/loop_unroll
Profile
|
-5.64% |
1.713 |
1.617 |
0.001 |
-5.70% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC64
|
-5.62% |
323.777 |
305.569 |
0.009 |
-0.52% |
0.009 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_no_runtime_checks_needed<16, int>
|
-5.46% |
39.309 |
37.164 |
0.002 |
-5.46% |
0.002 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<5, LessThanZero, None>
|
-5.40% |
21665.831 |
20495.871 |
0.111 |
-2.77% |
0.111 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIRST_DIFF_RAW/44217
|
-5.27% |
96.134 |
91.068 |
0.127 |
-5.21% |
0.127 |
|
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/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_HYDRO_2D_LAMBDA/5001
|
-5.04% |
2269.695 |
2155.306 |
28.933 |
-3.51% |
28.933 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC31
|
-5.04% |
288.528 |
273.995 |
0.030 |
-4.92% |
0.030 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopTC31
|
-5.03% |
288.548 |
274.035 |
0.014 |
-4.94% |
0.014 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC31
|
-4.98% |
288.363 |
273.997 |
0.023 |
-4.96% |
0.023 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC8
|
-4.92% |
43.597 |
41.454 |
0.001 |
-0.04% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC128
|
-4.91% |
1189.802 |
1131.430 |
0.634 |
-4.91% |
0.634 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopTC128
|
-4.90% |
1189.694 |
1131.396 |
0.035 |
-5.09% |
0.035 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC64
|
-4.89% |
595.873 |
566.751 |
0.014 |
-4.84% |
0.014 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopTC64
|
-4.88% |
595.840 |
566.748 |
0.008 |
-4.85% |
0.008 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC128
|
-4.86% |
1189.838 |
1132.021 |
0.028 |
-4.81% |
0.028 |
|
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% |
4.024 |
3.829 |
0.000 |
-4.85% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC15
|
-4.83% |
143.443 |
136.513 |
0.003 |
-4.43% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopTC63
|
-4.82% |
587.690 |
559.338 |
0.007 |
-4.75% |
0.007 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC63
|
-4.81% |
587.577 |
559.338 |
0.014 |
-4.82% |
0.014 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC127
|
-4.80% |
1181.779 |
1125.013 |
0.056 |
-4.80% |
0.056 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopTC127
|
-4.80% |
1181.805 |
1125.094 |
0.711 |
-4.95% |
0.711 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC64
|
-4.80% |
595.927 |
567.348 |
0.006 |
-4.72% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC127
|
-4.79% |
1181.717 |
1125.090 |
0.008 |
-4.68% |
0.008 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC63
|
-4.79% |
587.449 |
559.328 |
0.009 |
-5.33% |
0.009 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<8, LessThanZero, Last>
|
-4.75% |
15377.422 |
14647.653 |
282.533 |
-4.75% |
282.533 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<8, LessThanZero, None>
|
-4.64% |
15742.752 |
15011.969 |
4.666 |
-2.39% |
4.666 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint32_t>/28
|
-4.59% |
62.179 |
59.323 |
0.002 |
-1.19% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopTC3
|
-4.58% |
28.748 |
27.430 |
0.003 |
-3.72% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC7
|
-4.54% |
15.724 |
15.009 |
0.000 |
39.98% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC7
|
-4.48% |
38.659 |
36.927 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopTC8
|
-4.46% |
73.873 |
70.578 |
0.003 |
-4.15% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC8
|
-4.36% |
73.779 |
70.562 |
0.000 |
-3.99% |
0.000 |
|
SingleSource/Benchmarks/Misc/salsa20
Profile
|
-4.34% |
10.905 |
10.431 |
0.000 |
-4.98% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC63
|
-4.31% |
319.478 |
305.724 |
0.036 |
1.10% |
0.036 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC8
|
-4.29% |
73.722 |
70.563 |
0.000 |
-4.40% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint64_t>/51
|
-4.28% |
135.890 |
130.076 |
0.004 |
1.10% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint16_t_To_uint32_t_
|
-4.20% |
21464.798 |
20562.528 |
2.751 |
-4.14% |
2.751 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC16
|
-4.15% |
152.680 |
146.337 |
0.005 |
-4.07% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopTC16
|
-4.15% |
152.685 |
146.343 |
0.001 |
-4.07% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC16
|
-4.15% |
152.673 |
146.341 |
0.002 |
-4.12% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopTC15
|
-4.11% |
142.369 |
136.514 |
0.735 |
-3.24% |
0.735 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_DEL_DOT_VEC_2D_LAMBDA/1
|
-4.00% |
198.211 |
190.277 |
0.511 |
-3.61% |
0.511 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC4
|
-3.92% |
24.301 |
23.347 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC15
|
-3.85% |
141.988 |
136.517 |
0.002 |
-5.90% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC15
|
-3.82% |
78.619 |
75.619 |
0.001 |
-0.02% |
0.001 |
|
MultiSource/Benchmarks/sim/sim
Profile
|
-3.78% |
6.609 |
6.359 |
0.005 |
-5.22% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC16
|
-3.71% |
83.623 |
80.524 |
0.001 |
-0.14% |
0.001 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, LessThanZero, Last>
|
-3.70% |
39528.150 |
38064.665 |
1.556 |
-3.73% |
1.556 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC3
|
-3.66% |
28.458 |
27.415 |
0.004 |
-3.64% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC3
|
-3.66% |
28.445 |
27.405 |
0.006 |
-4.21% |
0.006 |
|
MultiSource/Benchmarks/mafft/pairlocalalign
Profile
|
-3.61% |
47.916 |
46.185 |
0.014 |
-2.77% |
0.014 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC32
|
-3.57% |
293.318 |
282.857 |
0.007 |
-3.37% |
0.007 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_VOL3D_CALC_RAW/2
|
-3.53% |
7.764 |
7.490 |
0.011 |
-3.54% |
0.011 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopTC32
|
-3.51% |
293.212 |
282.920 |
0.008 |
-3.39% |
0.008 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC32
|
-3.47% |
293.019 |
282.847 |
0.004 |
-3.44% |
0.004 |
|
MultiSource/Applications/siod/siod
Profile
|
-3.35% |
5.661 |
5.472 |
0.006 |
0.17% |
0.006 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, LessThanZero, None>
|
-3.33% |
43920.630 |
42457.143 |
0.718 |
-6.45% |
0.718 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_two_loads<uint32_t>/28
|
-3.23% |
22.157 |
21.442 |
0.000 |
-0.01% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_two_loads<uint32_t>/16
|
-3.23% |
22.156 |
21.441 |
0.000 |
-0.01% |
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 |
|
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>/256
|
-3.22% |
22.156 |
21.442 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_two_loads<uint32_t>/51
|
-3.22% |
22.156 |
21.442 |
0.000 |
0.00% |
0.000 |
|
MultiSource/Benchmarks/nbench/nbench
Profile
|
-3.16% |
3.867 |
3.745 |
0.002 |
-0.83% |
0.002 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_BAND_LIN_EQ_LAMBDA/44217
|
-3.16% |
85.174 |
82.485 |
0.680 |
0.32% |
0.680 |
|
MultiSource/Benchmarks/PAQ8p/paq8p
Profile
|
-3.14% |
135.792 |
131.522 |
0.069 |
0.04% |
0.069 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_two_loads<uint8_t>/999
|
-3.13% |
22.872 |
22.156 |
0.001 |
-3.13% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_two_loads<uint8_t>/256
|
-3.13% |
22.872 |
22.156 |
0.001 |
-3.12% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint32_t>/999
|
-3.13% |
22.872 |
22.156 |
0.000 |
-3.13% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint32_t>/16
|
-3.13% |
22.872 |
22.156 |
0.000 |
-3.13% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint16_t>/256
|
-3.13% |
22.872 |
22.157 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint32_t>/28
|
-3.13% |
22.871 |
22.156 |
0.000 |
-3.13% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint16_t>/28
|
-3.13% |
22.871 |
22.156 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint16_t>/51
|
-3.13% |
22.872 |
22.157 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint32_t>/51
|
-3.13% |
22.871 |
22.156 |
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<uint32_t>/10
|
-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>/16
|
-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>/10
|
-3.12% |
22.871 |
22.156 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_two_loads<uint8_t>/28
|
-3.12% |
22.871 |
22.156 |
0.000 |
-3.12% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_two_loads<uint8_t>/10
|
-3.12% |
22.871 |
22.156 |
0.000 |
-3.13% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_two_loads<uint8_t>/16
|
-3.12% |
22.871 |
22.156 |
0.000 |
-3.13% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint16_t>/999
|
-3.12% |
22.871 |
22.157 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint32_t>/256
|
-3.12% |
22.871 |
22.157 |
0.000 |
-3.13% |
0.000 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<3, LessThanZero, None>
|
-3.12% |
31226.346 |
30251.577 |
0.377 |
-3.12% |
0.377 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<16, EqZero, First>
|
-3.11% |
5862.988 |
5680.658 |
0.157 |
-0.01% |
0.157 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_VOL3D_CALC_RAW/1
|
-3.11% |
211.138 |
204.581 |
2.450 |
-2.22% |
2.450 |
|
MicroBenchmarks/ImageProcessing/Blur/blur.test:BENCHMARK_GAUSSIAN_BLUR/1024
|
-3.06% |
261709.667 |
253689.333 |
1534.900 |
-3.05% |
1534.900 |
|
MultiSource/Benchmarks/Fhourstones/fhourstones
Profile
|
-2.96% |
2.388 |
2.317 |
0.003 |
0.09% |
0.003 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, LessThanZero, None>
|
-2.95% |
24892.038 |
24158.918 |
0.653 |
-2.94% |
0.653 |
|
MultiSource/Benchmarks/MiBench/consumer-typeset/consumer-typeset
Profile
|
-2.93% |
0.369 |
0.358 |
0.000 |
0.03% |
0.000 |
|
MicroBenchmarks/Builtins/Int128/Builtins.test:BM_DivideIntrinsic128UniformDivisor<__uint128_t>
|
-2.86% |
38.472 |
37.370 |
0.046 |
0.01% |
0.046 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<32, EqZero, Mid>
|
-2.82% |
3210.043 |
3119.679 |
0.088 |
-0.01% |
0.088 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<5, LessThanZero, Last>
|
-2.77% |
21079.958 |
20495.886 |
226.494 |
-0.00% |
226.494 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_DEL_DOT_VEC_2D_RAW/1
|
-2.74% |
195.378 |
190.020 |
0.647 |
-2.93% |
0.647 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint8_t>/127
|
-2.71% |
171.172 |
166.535 |
0.022 |
-2.11% |
0.022 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_ENERGY_CALC_LAMBDA/5001
|
-2.69% |
226.946 |
220.839 |
2.010 |
-3.31% |
2.010 |
|
MultiSource/Applications/aha/aha
Profile
|
-2.67% |
3.876 |
3.772 |
0.001 |
-3.09% |
0.001 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<6, LessThanZero, None>
|
-2.63% |
18529.438 |
18042.841 |
0.382 |
-2.64% |
0.382 |
|
External/SPEC/CINT2017rate/523.xalancbmk_r/523.xalancbmk_r
Profile
|
-2.56% |
214.297 |
208.801 |
0.920 |
-2.25% |
0.920 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_ADI_RAW/171
|
-2.56% |
9.215 |
8.979 |
0.089 |
-1.24% |
0.089 |
|
SingleSource/Benchmarks/Misc/revertBits
Profile
|
-2.56% |
0.411 |
0.401 |
0.000 |
-2.52% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC2
|
-2.53% |
20.515 |
19.995 |
0.001 |
-4.02% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_DEL_DOT_VEC_2D_LAMBDA/2
|
-2.53% |
2.373 |
2.313 |
0.015 |
-1.37% |
0.015 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<7, EqZero, None>
|
-2.50% |
16732.443 |
16314.619 |
0.120 |
0.00% |
0.120 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint64_t>/10
|
-2.44% |
29.304 |
28.589 |
0.000 |
-2.44% |
0.000 |
|
MultiSource/Applications/SPASS/SPASS
Profile
|
-2.42% |
26.127 |
25.495 |
0.017 |
-0.13% |
0.017 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC128
|
-2.37% |
161.729 |
157.890 |
0.025 |
2.70% |
0.025 |
|
MultiSource/Applications/hexxagon/hexxagon
Profile
|
-2.37% |
9.228 |
9.010 |
0.002 |
-5.96% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC2
|
-2.30% |
20.470 |
20.000 |
0.019 |
-3.02% |
0.019 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint32_t>/51
|
-2.27% |
94.342 |
92.200 |
0.001 |
-1.52% |
0.001 |
|
MultiSource/Benchmarks/TSVC/ControlFlow-dbl/ControlFlow-dbl
Profile
|
-2.25% |
11.007 |
10.760 |
0.095 |
-1.69% |
0.095 |
|
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:benchForIC1VW4LoopWithReductionTC8
|
-2.17% |
10.959 |
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/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC8
|
-2.17% |
10.959 |
10.721 |
0.000 |
-2.17% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_IMP_HYDRO_2D_LAMBDA/5001
|
-2.16% |
388.161 |
379.766 |
1.385 |
-1.51% |
1.385 |
|
External/SPEC/CINT2017rate/500.perlbench_r/500.perlbench_r
Profile
|
-2.14% |
103.051 |
100.845 |
0.190 |
-0.03% |
0.190 |
|
MultiSource/Benchmarks/MiBench/telecomm-CRC32/telecomm-CRC32
Profile
|
-2.13% |
0.591 |
0.579 |
0.004 |
-3.38% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint8_t>/10
|
-2.08% |
34.306 |
33.591 |
0.001 |
-2.08% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopTC2
|
-2.07% |
20.433 |
20.009 |
0.000 |
-3.04% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1BigLoopWithReductionTC64
|
-2.04% |
311.956 |
305.596 |
0.002 |
-0.51% |
0.002 |
|
External/SPEC/CINT2017rate/505.mcf_r/505.mcf_r
Profile
|
-2.03% |
157.563 |
154.367 |
0.942 |
-1.24% |
0.942 |
|
SingleSource/Benchmarks/Stanford/FloatMM
Profile
|
-2.01% |
0.769 |
0.753 |
0.000 |
-2.00% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_MAT_X_MAT_LAMBDA/44217
|
-1.97% |
1048718.000 |
1028021.000 |
7146.756 |
-1.58% |
7146.756 |
|
SingleSource/Benchmarks/Adobe-C++/functionobjects
Profile
|
-1.95% |
6.063 |
5.945 |
0.001 |
-1.96% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint16_t>/10
|
-1.92% |
37.166 |
36.452 |
0.000 |
-0.00% |
0.000 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C++/miniFE/miniFE
Profile
|
-1.92% |
22.952 |
22.511 |
0.115 |
-1.45% |
0.115 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC128
|
-1.78% |
291.053 |
285.886 |
0.009 |
-0.00% |
0.009 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC128
|
-1.77% |
160.805 |
157.953 |
0.103 |
1.60% |
0.103 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_asinf_autovec_float_
|
-1.77% |
392.230 |
385.282 |
0.042 |
-0.02% |
0.042 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_ENERGY_CALC_RAW/5001
|
-1.71% |
232.560 |
228.585 |
0.712 |
-0.58% |
0.712 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_DEL_DOT_VEC_2D_LAMBDA/0
|
-1.70% |
1218.896 |
1198.226 |
0.826 |
-1.90% |
0.826 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint8_t>/16
|
-1.66% |
42.881 |
42.168 |
0.001 |
-1.67% |
0.001 |
|
External/SPEC/CINT2017rate/531.deepsjeng_r/531.deepsjeng_r
Profile
|
-1.65% |
138.603 |
136.312 |
0.131 |
-0.68% |
0.131 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint16_t>/16
|
-1.64% |
43.599 |
42.885 |
0.000 |
-4.76% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_expf_novec_float_
|
-1.62% |
463.433 |
455.918 |
0.247 |
0.04% |
0.247 |
|
MultiSource/Applications/minisat/minisat
Profile
|
-1.59% |
17.108 |
16.836 |
0.044 |
-1.32% |
0.044 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_PIC_2D_RAW/171
|
-1.50% |
5.115 |
5.039 |
0.018 |
-1.20% |
0.018 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint16_t>/10
|
-1.49% |
47.887 |
47.173 |
0.001 |
-1.50% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint16_t_To_uint64_t_
|
-1.48% |
22200.361 |
21871.153 |
11.093 |
-1.34% |
11.093 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint64_t>/10
|
-1.44% |
49.314 |
48.602 |
0.000 |
3.02% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_csa_with_in_loop_arith_autovec_uint8_t_
|
-1.43% |
519841.791 |
512408.657 |
634.468 |
-1.29% |
634.468 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC31
|
-1.43% |
50.030 |
49.315 |
0.001 |
49.98% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_DEL_DOT_VEC_2D_RAW/0
|
-1.42% |
1216.047 |
1198.830 |
1.871 |
-1.30% |
1.871 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, EqZero, First>
|
-1.36% |
8437.862 |
8323.104 |
42.700 |
-1.37% |
42.700 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC15
|
-1.35% |
17.630 |
17.391 |
0.000 |
-34.23% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC15
|
-1.35% |
17.630 |
17.392 |
0.001 |
-1.35% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC15
|
-1.35% |
17.630 |
17.392 |
0.000 |
-1.35% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC15
|
-1.35% |
17.630 |
17.392 |
0.000 |
-1.36% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1LoopWithReductionTC15
|
-1.35% |
17.630 |
17.392 |
0.000 |
-1.35% |
0.000 |
|
MultiSource/Benchmarks/Ptrdist/anagram/anagram
Profile
|
-1.31% |
1.911 |
1.886 |
0.007 |
-1.25% |
0.007 |
|
MultiSource/Benchmarks/Rodinia/backprop/backprop
Profile
|
-1.30% |
2.500 |
2.467 |
0.011 |
0.94% |
0.011 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/16
|
-1.28% |
120.609 |
119.064 |
0.002 |
-1.19% |
0.002 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_MAT_X_MAT_LAMBDA/5001
|
-1.28% |
55932.417 |
55216.167 |
239.760 |
-0.25% |
239.760 |
|
MultiSource/Benchmarks/TSVC/CrossingThresholds-dbl/CrossingThresholds-dbl
Profile
|
-1.26% |
9.635 |
9.513 |
0.027 |
-3.28% |
0.027 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_ENERGY_CALC_RAW/171
|
-1.22% |
6.005 |
5.932 |
0.010 |
-1.16% |
0.010 |
|
SingleSource/Benchmarks/Misc/ReedSolomon
Profile
|
-1.20% |
9.634 |
9.518 |
0.000 |
-0.42% |
0.000 |
|
MultiSource/Benchmarks/MallocBench/espresso/espresso
Profile
|
-1.19% |
0.854 |
0.843 |
0.001 |
-0.48% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint8_t>/28
|
-1.19% |
60.037 |
59.323 |
0.001 |
-1.19% |
0.001 |
|
MultiSource/Benchmarks/Fhourstones-3.1/fhourstones3.1
Profile
|
-1.18% |
2.499 |
2.470 |
0.001 |
1.43% |
0.001 |
|
SingleSource/Benchmarks/Misc-C++/stepanov_container
Profile
|
-1.17% |
11.036 |
10.906 |
0.036 |
-0.70% |
0.036 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC127
|
-1.17% |
154.396 |
152.595 |
0.001 |
0.70% |
0.001 |
|
SingleSource/Benchmarks/BenchmarkGame/recursive
Profile
|
-1.15% |
2.338 |
2.311 |
0.009 |
-0.83% |
0.009 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_EOS_LAMBDA/44217
|
-1.12% |
401.522 |
397.007 |
0.744 |
-0.47% |
0.744 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_EOS_RAW/44217
|
-1.12% |
401.128 |
396.619 |
0.420 |
-0.61% |
0.420 |
|
External/SPEC/CFP2017rate/544.nab_r/544.nab_r
Profile
|
-1.12% |
280.191 |
277.053 |
0.031 |
-1.08% |
0.031 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/32
|
-1.08% |
599.480 |
592.976 |
0.183 |
-1.09% |
0.183 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint64_t>/16
|
-1.08% |
66.469 |
65.753 |
0.002 |
5.74% |
0.002 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_ORDERED_DITHER/512/2
|
-1.07% |
19420.444 |
19213.278 |
18.038 |
-0.71% |
18.038 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<31, GreaterThanZero, Mid>
|
-1.05% |
5003.146 |
4950.563 |
1.836 |
0.02% |
1.836 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/64
|
-1.02% |
2649.977 |
2622.981 |
0.153 |
-1.02% |
0.153 |