|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopWithReductionTC31
|
-34.28% |
50.029 |
32.878 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopWithReductionTC32
|
-34.26% |
51.460 |
33.832 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint64_t_To_uint8_t_
|
-33.52% |
28597.075 |
19012.358 |
1.784 |
0.01% |
1.784 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopWithReductionTC15
|
-33.33% |
26.445 |
17.630 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopWithReductionTC8
|
-33.33% |
16.439 |
10.959 |
0.000 |
-9.80% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopWithReductionTC64
|
-33.33% |
96.485 |
64.326 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopWithReductionTC16
|
-33.33% |
27.874 |
18.584 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopWithReductionTC63
|
-33.33% |
95.054 |
63.374 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC3
|
-32.05% |
27.874 |
18.940 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopWithReductionTC2
|
-31.27% |
7.862 |
5.403 |
0.087 |
-0.97% |
0.087 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopWithReductionTC128
|
-30.37% |
192.972 |
134.368 |
0.002 |
-12.36% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopWithReductionTC3
|
-28.57% |
10.006 |
7.147 |
0.000 |
-16.67% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopWithReductionTC7
|
-28.57% |
15.009 |
10.721 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopWithReductionTC4
|
-26.67% |
10.721 |
7.862 |
0.000 |
-8.33% |
0.000 |
|
SingleSource/Benchmarks/Shootout-C++/Shootout-C++-ary3
Profile
|
-25.98% |
6.200 |
4.590 |
0.062 |
0.00% |
0.062 |
|
SingleSource/Benchmarks/BenchmarkGame/puzzle
Profile
|
-23.77% |
1.120 |
0.854 |
0.002 |
-0.09% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_nested_cond_load_autovec_int64_t_
|
-22.73% |
1295048.148 |
1000710.602 |
1805.745 |
-22.35% |
1805.745 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_nested_cond_load_novec_int64_t_
|
-22.43% |
1294703.704 |
1004252.874 |
1493.031 |
-1.05% |
1493.031 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint8_t_To_uint16_t_
|
-22.20% |
21449.266 |
16687.180 |
0.293 |
-22.20% |
0.293 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_only_novec_int64_t_
|
-22.11% |
864105.198 |
673069.364 |
564.492 |
-0.49% |
564.492 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint32_t>/999
|
-21.97% |
2169.881 |
1693.179 |
0.032 |
-21.97% |
0.032 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint32_t>/999
|
-21.55% |
1101.400 |
864.069 |
0.044 |
-21.55% |
0.044 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint32_t>/256
|
-21.32% |
576.787 |
453.844 |
0.018 |
-21.32% |
0.018 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint16_t>/999
|
-21.22% |
2169.101 |
1708.897 |
3.257 |
0.10% |
3.257 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint16_t>/999
|
-20.65% |
1100.678 |
873.416 |
1.873 |
0.74% |
1.873 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint32_t>/256
|
-19.86% |
305.912 |
245.149 |
0.008 |
-19.86% |
0.008 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint16_t>/51
|
-19.56% |
131.508 |
105.779 |
0.004 |
0.00% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint16_t>/51
|
-19.27% |
77.905 |
62.895 |
0.002 |
-0.01% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint16_t>/256
|
-18.48% |
576.053 |
469.596 |
2.660 |
2.02% |
2.660 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint16_t>/28
|
-18.26% |
82.193 |
67.185 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopWithReductionTC127
|
-18.21% |
192.251 |
157.244 |
0.002 |
4.94% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint32_t>/51
|
-17.78% |
128.656 |
105.778 |
0.001 |
-18.69% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_nested_cond_load_autovec_uint8_t_
|
-17.30% |
579062.552 |
478884.377 |
1602.840 |
-11.25% |
1602.840 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint16_t>/28
|
-17.10% |
54.320 |
45.029 |
0.001 |
1.60% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC2
|
-16.63% |
8.576 |
7.150 |
0.002 |
-23.05% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint16_t_To_uint32_t_
|
-16.60% |
14302.160 |
11928.509 |
0.276 |
-16.59% |
0.276 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint16_t_To_uint64_t_
|
-16.58% |
14302.364 |
11930.675 |
0.302 |
-0.05% |
0.302 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint8_t_To_uint32_t_
|
-16.58% |
14301.236 |
11930.055 |
0.392 |
-16.59% |
0.392 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint16_t>/16
|
-16.46% |
56.461 |
47.170 |
0.002 |
-0.01% |
0.002 |
|
SingleSource/Benchmarks/CoyoteBench/huffbench
Profile
|
-16.43% |
38.313 |
32.020 |
0.022 |
-0.04% |
0.022 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIND_FIRST_MIN_RAW/171
|
-16.36% |
0.494 |
0.413 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint16_t>/256
|
-16.24% |
305.191 |
255.643 |
1.319 |
3.07% |
1.319 |
|
SingleSource/Benchmarks/Shootout/Shootout-sieve
Profile
|
-15.64% |
8.388 |
7.076 |
0.031 |
-1.46% |
0.031 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_nested_cond_load_novec_uint8_t_
|
-15.57% |
579204.184 |
489015.320 |
1159.900 |
-8.53% |
1159.900 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint32_t>/51
|
-15.39% |
74.334 |
62.895 |
0.001 |
-15.38% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint16_t>/10
|
-14.75% |
43.597 |
37.165 |
0.002 |
-0.01% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint32_t>/28
|
-14.42% |
79.337 |
67.899 |
0.002 |
-15.93% |
0.002 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIND_FIRST_MIN_RAW/5001
|
-13.85% |
14.304 |
12.323 |
0.000 |
-0.08% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1LoopWithReductionTC64
|
-13.46% |
74.331 |
64.328 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_cond_load_autovec_int32_t_
|
-13.39% |
595576.661 |
515822.402 |
2892.282 |
-5.30% |
2892.282 |
|
MicroBenchmarks/LCALS/SubsetBRawLoops/lcalsBRaw.test:BM_INIT3_RAW/171
|
-13.06% |
0.618 |
0.537 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_DIFF_PREDICT_RAW/171
|
-12.66% |
4.214 |
3.681 |
0.001 |
-0.05% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_DIFF_PREDICT_LAMBDA/171
|
-12.64% |
4.213 |
3.681 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint16_t>/16
|
-12.07% |
41.455 |
36.452 |
0.001 |
1.99% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_csa_with_cond_arith_autovec_int64_t_
|
-11.98% |
781518.436 |
687882.874 |
167.694 |
-0.03% |
167.694 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC127
|
-11.43% |
150.094 |
132.939 |
0.081 |
-30.60% |
0.081 |
|
MultiSource/Benchmarks/TSVC/Searching-flt/Searching-flt
Profile
|
-11.17% |
11.675 |
10.371 |
0.044 |
-11.19% |
0.044 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC1
|
-11.11% |
6.433 |
5.718 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC128
|
-11.00% |
286.692 |
255.162 |
0.007 |
-10.75% |
0.007 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC64
|
-10.98% |
140.802 |
125.347 |
0.120 |
-10.52% |
0.120 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC128
|
-10.75% |
285.887 |
255.161 |
1.937 |
-10.75% |
1.937 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint32_t>/16
|
-10.67% |
53.603 |
47.885 |
0.002 |
-12.99% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC64
|
-10.63% |
140.085 |
125.200 |
0.175 |
-11.08% |
0.175 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC63
|
-10.53% |
137.943 |
123.413 |
0.001 |
-10.53% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC63
|
-10.53% |
137.938 |
123.409 |
0.004 |
-10.53% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC127
|
-10.36% |
283.045 |
253.727 |
0.004 |
-10.36% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC31
|
-10.19% |
69.329 |
62.266 |
0.220 |
-10.18% |
0.220 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC16
|
-10.11% |
37.880 |
34.049 |
0.047 |
-8.38% |
0.047 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC127
|
-10.10% |
283.030 |
254.450 |
0.091 |
-10.09% |
0.091 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC32
|
-10.00% |
71.474 |
64.326 |
0.002 |
-10.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC32
|
-10.00% |
71.474 |
64.327 |
0.000 |
-10.00% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_IMP_HYDRO_2D_RAW/44217
|
-9.99% |
7531.871 |
6779.631 |
236.197 |
-5.69% |
236.197 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint32_t>/28
|
-9.86% |
50.747 |
45.744 |
0.001 |
-9.86% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1LoopWithReductionTC8
|
-9.80% |
12.150 |
10.959 |
0.000 |
-4.17% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC31
|
-9.52% |
69.327 |
62.730 |
0.016 |
-9.52% |
0.016 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_with_cond_arith_autovec_int32_t_
|
-9.26% |
439454.602 |
398742.156 |
1009.414 |
-0.07% |
1009.414 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC16
|
-9.22% |
37.165 |
33.737 |
0.109 |
-9.23% |
0.109 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_DIFF_PREDICT_RAW/5001
|
-9.16% |
207.558 |
188.550 |
3.824 |
0.26% |
3.824 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC3
|
-9.09% |
7.862 |
7.147 |
0.000 |
-9.09% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1LoopWithReductionTC3
|
-9.09% |
7.862 |
7.147 |
0.000 |
-9.09% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_with_cond_arith_autovec_uint8_t_
|
-9.03% |
439924.576 |
400216.695 |
1739.810 |
0.56% |
1739.810 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_PRESSURE_CALC_LAMBDA/171
|
-9.00% |
1.359 |
1.237 |
0.000 |
-6.18% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC15
|
-8.85% |
35.022 |
31.924 |
0.001 |
-8.84% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC15
|
-8.84% |
35.022 |
31.925 |
0.001 |
-10.67% |
0.001 |
|
SingleSource/Benchmarks/Shootout/Shootout-matrix
Profile
|
-8.51% |
4.822 |
4.411 |
0.015 |
-0.16% |
0.015 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1LoopWithReductionTC4
|
-8.33% |
8.576 |
7.862 |
0.000 |
-8.34% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchVecWithRuntimeChecks4PointersDEqualsA/1000
|
-8.25% |
2868176.230 |
2631560.150 |
44.305 |
0.05% |
44.305 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchVecWithRuntimeChecks4PointersDAfterA/1000
|
-8.25% |
2868184.426 |
2631593.985 |
63.081 |
0.04% |
63.081 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchVecWithRuntimeChecks4PointersAllDisjointIncreasing/1000
|
-8.24% |
2868106.557 |
2631631.579 |
27.283 |
0.05% |
27.283 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchVecWithRuntimeChecks4PointersAllDisjointDecreasing/1000
|
-8.24% |
2868118.852 |
2631691.729 |
30.127 |
0.05% |
30.127 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchVecWithRuntimeChecks4PointersDBeforeA/1000
|
-8.23% |
2868352.459 |
2632172.932 |
21.777 |
0.05% |
21.777 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint32_t>/999
|
-8.18% |
2883.145 |
2647.359 |
0.013 |
0.00% |
0.013 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint16_t>/10
|
-8.16% |
35.022 |
32.163 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint32_t>/999
|
-8.07% |
1460.849 |
1342.887 |
0.054 |
-0.05% |
0.054 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<7, EqZero, First>
|
-7.98% |
10461.750 |
9626.554 |
12.436 |
0.02% |
12.436 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint32_t>/256
|
-7.81% |
759.008 |
699.709 |
0.005 |
-0.10% |
0.005 |
|
MultiSource/Benchmarks/ASC_Sequoia/AMGmk/AMGmk
Profile
|
-7.78% |
38.525 |
35.528 |
0.495 |
-4.01% |
0.495 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC7
|
-7.77% |
17.868 |
16.479 |
0.093 |
-7.77% |
0.093 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC2
|
-7.69% |
9.291 |
8.577 |
0.000 |
19.92% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchVecWithRuntimeChecks4PointersDEqualsA/32
|
-7.58% |
94376.483 |
87224.078 |
2.665 |
0.00% |
2.665 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchVecWithRuntimeChecks4PointersAllDisjointIncreasing/32
|
-7.58% |
94378.859 |
87227.318 |
2.806 |
-0.01% |
2.806 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchVecWithRuntimeChecks4PointersDAfterA/32
|
-7.58% |
94378.455 |
87227.290 |
3.379 |
-0.01% |
3.379 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchVecWithRuntimeChecks4PointersDBeforeA/32
|
-7.58% |
94378.101 |
87226.972 |
1.539 |
-0.00% |
1.539 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchVecWithRuntimeChecks4PointersAllDisjointDecreasing/32
|
-7.57% |
94374.949 |
87228.938 |
1.542 |
-0.00% |
1.542 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC8
|
-7.14% |
20.012 |
18.583 |
0.000 |
-7.14% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC8
|
-7.14% |
20.012 |
18.583 |
0.000 |
-7.14% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint32_t>/10
|
-7.02% |
40.739 |
37.880 |
0.002 |
-10.18% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint32_t>/256
|
-6.96% |
400.242 |
372.378 |
0.007 |
0.19% |
0.007 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint32_t>/51
|
-6.87% |
166.530 |
155.091 |
0.005 |
-0.01% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint32_t>/51
|
-6.82% |
94.343 |
87.911 |
0.002 |
-0.80% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC7
|
-6.67% |
10.721 |
10.006 |
0.000 |
-6.66% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC7
|
-6.66% |
10.721 |
10.007 |
0.000 |
-36.36% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1LoopWithReductionTC7
|
-6.66% |
10.721 |
10.006 |
0.000 |
-12.49% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_INT_PREDICT_LAMBDA/5001
|
-6.41% |
120.107 |
112.413 |
0.728 |
-0.39% |
0.728 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint32_t>/28
|
-6.39% |
100.776 |
94.340 |
0.006 |
-0.76% |
0.006 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_INT_PREDICT_RAW/5001
|
-6.32% |
119.938 |
112.354 |
0.692 |
-0.00% |
0.692 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopTC7
|
-6.29% |
62.338 |
58.417 |
0.043 |
-4.40% |
0.043 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint32_t>/16
|
-6.25% |
45.743 |
42.883 |
0.001 |
-1.64% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC4
|
-6.25% |
11.435 |
10.721 |
0.000 |
24.99% |
0.000 |
|
MultiSource/Benchmarks/SciMark2-C/scimark2
Profile
|
-6.18% |
55.519 |
52.088 |
0.016 |
-0.01% |
0.016 |
|
SingleSource/Benchmarks/BenchmarkGame/n-body
Profile
|
-6.05% |
2.631 |
2.472 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_DIFF_PREDICT_LAMBDA/44217
|
-5.99% |
5399.600 |
5076.159 |
6.465 |
-0.35% |
6.465 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC4
|
-5.88% |
12.150 |
11.436 |
0.000 |
-5.88% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC4
|
-5.88% |
12.150 |
11.436 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<6, GreaterThanZero, Mid>
|
-5.86% |
16580.722 |
15609.268 |
10.951 |
-0.00% |
10.951 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_DIFF_PREDICT_RAW/44217
|
-5.84% |
5404.411 |
5088.606 |
19.531 |
-0.10% |
19.531 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint32_t>/28
|
-5.68% |
62.896 |
59.324 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC7
|
-5.52% |
17.868 |
16.882 |
0.018 |
-5.52% |
0.018 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/128
|
-5.41% |
2920.775 |
2762.625 |
0.390 |
-0.02% |
0.390 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint32_t>/16
|
-5.38% |
66.470 |
62.896 |
0.001 |
-0.01% |
0.001 |
|
MultiSource/Benchmarks/Olden/tsp/tsp
Profile
|
-5.18% |
3.268 |
3.099 |
0.007 |
0.05% |
0.007 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_INT_PREDICT_LAMBDA/44217
|
-5.09% |
3721.729 |
3532.215 |
8.765 |
-0.59% |
8.765 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC7
|
-5.03% |
61.477 |
58.385 |
0.099 |
-2.61% |
0.099 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/64
|
-4.86% |
725.207 |
689.944 |
0.147 |
-0.05% |
0.147 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/32
|
-4.71% |
179.122 |
170.685 |
0.106 |
-0.00% |
0.106 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_INT_PREDICT_RAW/44217
|
-4.70% |
3701.979 |
3527.817 |
16.228 |
-0.44% |
16.228 |
|
SingleSource/Benchmarks/McGill/queens
Profile
|
-4.58% |
3.395 |
3.240 |
0.000 |
0.36% |
0.000 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/256
|
-4.50% |
11911.102 |
11374.754 |
11.783 |
-0.23% |
11.783 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_PIC_2D_LAMBDA/44217
|
-4.22% |
1603.101 |
1535.387 |
6.501 |
-0.22% |
6.501 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<8, EqZero, First>
|
-4.15% |
8791.314 |
8426.061 |
10.216 |
0.00% |
10.216 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<3, GreaterThanZero, First>
|
-4.15% |
23421.889 |
22449.857 |
20.869 |
-7.99% |
20.869 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint16_t>/256
|
-4.13% |
225.136 |
215.848 |
0.004 |
1.33% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint16_t>/256
|
-4.10% |
415.869 |
398.805 |
0.018 |
0.71% |
0.018 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint32_t>/256
|
-3.87% |
221.571 |
212.987 |
0.008 |
-8.17% |
0.008 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_PIC_2D_RAW/44217
|
-3.87% |
1595.009 |
1533.298 |
2.743 |
0.05% |
2.743 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC7
|
-3.85% |
18.583 |
17.868 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<3, EqZero, Mid>
|
-3.84% |
25376.690 |
24402.217 |
18.683 |
-0.03% |
18.683 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint8_t>/256
|
-3.78% |
415.245 |
399.534 |
0.011 |
-2.93% |
0.011 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC7
|
-3.76% |
61.482 |
59.172 |
0.008 |
-3.62% |
0.008 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC127
|
-3.68% |
159.552 |
153.681 |
0.014 |
-3.50% |
0.014 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, GreaterThanZero, Last>
|
-3.67% |
39528.631 |
38077.739 |
30.262 |
4.01% |
30.262 |
|
SingleSource/Benchmarks/Misc/mandel
Profile
|
-3.56% |
1.328 |
1.281 |
0.000 |
-0.01% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint8_t>/256
|
-3.53% |
223.001 |
215.134 |
0.007 |
-8.81% |
0.007 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint8_t>/28
|
-3.51% |
40.739 |
39.309 |
0.020 |
0.00% |
0.020 |
|
MultiSource/Applications/obsequi/Obsequi
Profile
|
-3.42% |
4.424 |
4.273 |
0.007 |
1.47% |
0.007 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint64_t>/10
|
-3.39% |
42.170 |
40.739 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_HYDRO_1D_RAW/5001
|
-3.36% |
14.501 |
14.014 |
0.064 |
-0.51% |
0.064 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_single_load<uint16_t>/256
|
-3.23% |
22.157 |
21.441 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_single_load<uint16_t>/999
|
-3.23% |
22.157 |
21.442 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_single_load<uint16_t>/51
|
-3.23% |
22.157 |
21.441 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_single_load<uint16_t>/16
|
-3.23% |
22.157 |
21.441 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_single_load<uint16_t>/10
|
-3.23% |
22.157 |
21.442 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_single_load<uint16_t>/28
|
-3.23% |
22.156 |
21.441 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/harris/harris.test:BENCHMARK_HARRIS/1024/1024
|
-3.21% |
54964.231 |
53198.769 |
162.926 |
-0.52% |
162.926 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopTC1
|
-3.07% |
13.204 |
12.799 |
0.002 |
0.20% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint64_t>/51
|
-3.03% |
23.586 |
22.870 |
0.001 |
3.22% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint64_t>/256
|
-3.03% |
23.586 |
22.870 |
0.001 |
3.21% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint64_t>/28
|
-3.03% |
23.586 |
22.871 |
0.000 |
3.22% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint64_t>/999
|
-3.03% |
23.585 |
22.871 |
0.001 |
3.21% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint64_t>/10
|
-3.03% |
23.585 |
22.871 |
0.001 |
3.22% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint64_t>/16
|
-3.03% |
23.585 |
22.871 |
0.001 |
3.22% |
0.001 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<6, EqZero, Mid>
|
-2.93% |
16580.996 |
16095.075 |
10.620 |
3.11% |
10.620 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, GreaterThanZero, None>
|
-2.93% |
24890.825 |
24161.426 |
20.676 |
-2.93% |
20.676 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint32_t>/10
|
-2.90% |
49.317 |
47.885 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC1
|
-2.80% |
13.161 |
12.792 |
0.003 |
-0.63% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC15
|
-2.63% |
27.159 |
26.445 |
0.000 |
49.99% |
0.000 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<6, EqZero, None>
|
-2.62% |
18530.301 |
18044.673 |
17.749 |
-2.62% |
17.749 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint64_t>/16
|
-2.60% |
55.034 |
53.603 |
0.001 |
0.00% |
0.001 |
|
MultiSource/Applications/spiff/spiff
Profile
|
-2.53% |
6.178 |
6.022 |
0.021 |
-2.14% |
0.021 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint32_t>/127
|
-2.51% |
171.555 |
167.248 |
0.520 |
-0.00% |
0.520 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<64, GreaterThanZero, Mid>
|
-2.51% |
1792.514 |
1747.603 |
1.161 |
-2.50% |
1.161 |
|
MicroBenchmarks/harris/harris.test:BENCHMARK_HARRIS/512/512
|
-2.45% |
14055.060 |
13710.706 |
113.914 |
-0.62% |
113.914 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint8_t>/10
|
-2.44% |
29.305 |
28.589 |
0.001 |
-2.44% |
0.001 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/16
|
-2.40% |
43.728 |
42.678 |
0.001 |
0.10% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_only_autovec_uint8_t_
|
-2.37% |
794113.766 |
775265.851 |
2691.073 |
-3.40% |
2691.073 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<8, GreaterThanZero, None>
|
-2.37% |
15376.881 |
15011.945 |
8.136 |
-0.00% |
8.136 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint64_t>/16
|
-2.27% |
31.448 |
30.733 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint8_t>/16
|
-2.22% |
32.162 |
31.447 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint64_t>/10
|
-2.22% |
32.162 |
31.448 |
0.001 |
-2.23% |
0.001 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, LessThanZero, Mid>
|
-2.17% |
23955.578 |
23436.289 |
1.316 |
3.25% |
1.316 |
|
MultiSource/Benchmarks/Trimaran/enc-3des/enc-3des
Profile
|
-2.16% |
3.142 |
3.074 |
0.000 |
-0.01% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIND_FIRST_MIN_RAW/44217
|
-2.13% |
129.369 |
126.610 |
0.823 |
-0.56% |
0.823 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<3, LessThanZero, Last>
|
-2.13% |
30931.991 |
30274.020 |
12.187 |
0.07% |
12.187 |
|
SingleSource/Benchmarks/CoyoteBench/lpbench
Profile
|
-2.12% |
7.761 |
7.596 |
0.007 |
-0.00% |
0.007 |
|
MultiSource/Benchmarks/TSVC/IndirectAddressing-dbl/IndirectAddressing-dbl
Profile
|
-2.09% |
11.720 |
11.475 |
0.059 |
-1.45% |
0.059 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint64_t>/10
|
-2.08% |
34.306 |
33.592 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<3, EqZero, Last>
|
-2.07% |
30903.803 |
30262.696 |
24.558 |
3.36% |
24.558 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C/CoMD/CoMD
Profile
|
-2.07% |
5.063 |
4.958 |
0.011 |
0.01% |
0.011 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<8, GreaterThanZero, Mid>
|
-2.02% |
13080.591 |
12816.349 |
7.943 |
2.93% |
7.943 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<5, GreaterThanZero, Mid>
|
-2.01% |
18531.923 |
18160.148 |
14.618 |
3.36% |
14.618 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<5, EqZero, Last>
|
-2.00% |
20921.420 |
20502.460 |
11.116 |
2.96% |
11.116 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC15
|
-2.00% |
35.735 |
35.022 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<6, GreaterThanZero, Last>
|
-1.99% |
18410.647 |
18044.302 |
7.564 |
2.77% |
7.564 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<7, EqZero, Mid>
|
-1.95% |
14087.196 |
13812.332 |
7.229 |
3.15% |
7.229 |
|
SingleSource/Benchmarks/Polybench/stencils/seidel-2d/seidel-2d
Profile
|
-1.95% |
164.286 |
161.083 |
0.080 |
0.05% |
0.080 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_csa_with_cond_arith_autovec_int32_t_
|
-1.94% |
539713.953 |
529230.651 |
2586.877 |
-1.97% |
2586.877 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint32_t>/10
|
-1.92% |
37.165 |
36.451 |
0.002 |
1.99% |
0.002 |
|
SingleSource/Benchmarks/Misc/perlin
Profile
|
-1.90% |
7.274 |
7.136 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint32_t>/16
|
-1.89% |
37.880 |
37.164 |
0.001 |
-1.89% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint64_t>/16
|
-1.89% |
37.880 |
37.165 |
0.002 |
-1.89% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC16
|
-1.88% |
37.880 |
37.166 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_PIC_2D_RAW/5001
|
-1.80% |
178.529 |
175.323 |
0.519 |
-0.14% |
0.519 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint64_t>/28
|
-1.79% |
40.025 |
39.311 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint64_t>/28
|
-1.77% |
80.761 |
79.334 |
0.003 |
0.00% |
0.003 |
|
SingleSource/Benchmarks/Misc/flops-8
Profile
|
-1.75% |
1.768 |
1.737 |
0.001 |
-0.03% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint64_t>/16
|
-1.66% |
42.882 |
42.168 |
0.002 |
-0.01% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_csa_with_cond_arith_autovec_uint8_t_
|
-1.66% |
280657.143 |
275988.519 |
1474.499 |
0.05% |
1474.499 |
|
MultiSource/Benchmarks/TSVC/Expansion-flt/Expansion-flt
Profile
|
-1.61% |
9.777 |
9.619 |
0.042 |
-0.93% |
0.042 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint8_t>/16
|
-1.59% |
45.028 |
44.313 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint64_t>/51
|
-1.53% |
93.631 |
92.200 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_PIC_2D_LAMBDA/5001
|
-1.48% |
178.245 |
175.611 |
0.874 |
0.07% |
0.874 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint64_t>/28
|
-1.40% |
50.744 |
50.032 |
0.001 |
-1.41% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC32
|
-1.38% |
51.459 |
50.748 |
0.002 |
50.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint16_t>/999
|
-1.36% |
756.471 |
746.150 |
0.021 |
0.37% |
0.021 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint8_t>/999
|
-1.34% |
755.626 |
745.463 |
0.025 |
-2.73% |
0.025 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<63, LessThanZero, None>
|
-1.31% |
3094.728 |
3054.103 |
2.060 |
-1.24% |
2.060 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_nested_cond_load_autovec_int32_t_
|
-1.31% |
1024223.529 |
1010801.737 |
738.318 |
-1.43% |
738.318 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_csa_with_in_loop_arith_novec_int32_t_
|
-1.31% |
766181.319 |
756181.025 |
3614.878 |
-0.97% |
3614.878 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint8_t>/51
|
-1.29% |
55.750 |
55.033 |
0.002 |
-2.53% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint64_t>/51
|
-1.28% |
55.747 |
55.034 |
0.002 |
-0.01% |
0.002 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_GEN_LIN_RECUR_RAW/44217
|
-1.26% |
512.447 |
505.986 |
0.059 |
-0.00% |
0.059 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint16_t>/28
|
-1.20% |
59.322 |
58.608 |
0.003 |
-5.75% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_nested_cond_load_novec_int32_t_
|
-1.20% |
1023879.056 |
1011590.449 |
1023.420 |
-0.87% |
1023.420 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint64_t>/28
|
-1.19% |
60.037 |
59.320 |
0.002 |
-0.00% |
0.002 |
|
MultiSource/Benchmarks/VersaBench/8b10b/8b10b
Profile
|
-1.15% |
7.409 |
7.324 |
0.021 |
-0.27% |
0.021 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint32_t>/999
|
-1.14% |
751.893 |
743.307 |
0.038 |
-2.72% |
0.038 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC4
|
-1.10% |
36.869 |
36.465 |
0.025 |
-0.67% |
0.025 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint8_t>/999
|
-1.07% |
1477.352 |
1461.558 |
0.044 |
-0.93% |
0.044 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC31
|
-1.02% |
70.041 |
69.327 |
0.002 |
-0.00% |
0.002 |
|
SingleSource/Benchmarks/Polybench/linear-algebra/blas/syr2k/syr2k
Profile
|
-1.02% |
47.907 |
47.420 |
0.184 |
0.08% |
0.184 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC64
|
-1.01% |
141.514 |
140.086 |
0.003 |
-0.51% |
0.003 |