|
MultiSource/Benchmarks/Trimaran/enc-md5/enc-md5
Profile
|
-76.67% |
12.643 |
2.949 |
0.000 |
-0.01% |
0.000 |
|
SingleSource/Benchmarks/Shootout/Shootout-ary3
Profile
|
-47.14% |
0.985 |
0.521 |
0.001 |
-0.10% |
0.001 |
|
MultiSource/Benchmarks/Ptrdist/yacr2/yacr2
Profile
|
-28.49% |
2.836 |
2.028 |
0.001 |
0.85% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_with_cond_arith_autovec_int64_t_
|
-27.54% |
1044878.546 |
757158.656 |
496.590 |
0.18% |
496.590 |
|
SingleSource/Benchmarks/Adobe-C++/simple_types_constant_folding
Profile
|
-27.50% |
2.366 |
1.716 |
0.001 |
-0.02% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_with_cond_arith_novec_int64_t_
|
-27.46% |
1044463.436 |
757681.246 |
449.218 |
-0.15% |
449.218 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_with_cond_arith_autovec_int32_t_
|
-27.01% |
515728.518 |
376442.150 |
654.065 |
-0.32% |
654.065 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_with_cond_arith_novec_int32_t_
|
-26.95% |
515829.116 |
376803.997 |
385.080 |
-0.10% |
385.080 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_with_cond_arith_autovec_uint8_t_
|
-25.52% |
124920.394 |
93042.121 |
352.467 |
-0.05% |
352.467 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_with_cond_arith_novec_uint8_t_
|
-25.48% |
124916.399 |
93083.022 |
325.033 |
-0.00% |
325.033 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_multiply_accumulate_runtime_checks_pass<3, double>
|
-25.00% |
15.017 |
11.262 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_multiply_accumulate_runtime_checks_fail<3, double>
|
-25.00% |
15.016 |
11.262 |
0.000 |
0.00% |
0.000 |
|
SingleSource/Benchmarks/Misc-C++/stepanov_v1p2
Profile
|
-24.96% |
16.330 |
12.254 |
0.001 |
0.00% |
0.001 |
|
MultiSource/Benchmarks/TSVC/Packing-flt/Packing-flt
Profile
|
-24.59% |
33.627 |
25.358 |
0.389 |
-0.17% |
0.389 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint64_t>/256
|
-22.85% |
2110.073 |
1627.849 |
0.218 |
0.01% |
0.218 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint64_t>/256
|
-22.57% |
1073.749 |
831.434 |
0.028 |
-0.00% |
0.028 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_single_load<uint8_t>/10
|
-22.35% |
9.669 |
7.508 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_single_load<uint8_t>/16
|
-22.05% |
9.632 |
7.508 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_TRIDIAG_ELIM_LAMBDA/171
|
-21.95% |
0.967 |
0.755 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_TRIDIAG_ELIM_RAW/171
|
-21.94% |
0.967 |
0.755 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint64_t>/28
|
-21.77% |
247.146 |
193.348 |
0.003 |
0.00% |
0.003 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_GEN_LIN_RECUR_LAMBDA/44217
|
-21.54% |
1334.856 |
1047.284 |
21.694 |
-5.32% |
21.694 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_xor_no_runtime_checks_needed<4, int>
|
-21.43% |
8.760 |
6.883 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint8_t>/10
|
-21.22% |
41.303 |
32.540 |
0.004 |
0.00% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint64_t>/16
|
-20.92% |
149.541 |
118.255 |
0.004 |
-0.00% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint8_t>/16
|
-20.87% |
60.094 |
47.554 |
0.032 |
0.00% |
0.032 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint64_t>/28
|
-20.79% |
141.410 |
112.004 |
0.004 |
-0.00% |
0.004 |
|
MultiSource/Benchmarks/SciMark2-C/scimark2
Profile
|
-19.80% |
166.680 |
133.684 |
0.091 |
-0.01% |
0.091 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint64_t>/10
|
-19.74% |
95.109 |
76.334 |
0.003 |
0.00% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint64_t>/16
|
-19.60% |
92.608 |
74.460 |
0.004 |
0.00% |
0.004 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_TRIDIAG_ELIM_LAMBDA/44217
|
-19.32% |
252.442 |
203.671 |
0.637 |
-0.06% |
0.637 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_TRIDIAG_ELIM_RAW/44217
|
-18.84% |
251.350 |
203.984 |
0.701 |
0.17% |
0.701 |
|
MultiSource/Benchmarks/TSVC/Packing-dbl/Packing-dbl
Profile
|
-18.81% |
35.572 |
28.881 |
0.251 |
-0.24% |
0.251 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_TRIDIAG_ELIM_LAMBDA/5001
|
-18.24% |
28.463 |
23.271 |
0.040 |
-0.03% |
0.040 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_GEN_LIN_RECUR_RAW/44217
|
-18.23% |
1300.488 |
1063.396 |
19.416 |
1.87% |
19.416 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_TRIDIAG_ELIM_RAW/5001
|
-18.16% |
28.452 |
23.285 |
0.084 |
-0.10% |
0.084 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint64_t>/10
|
-18.01% |
62.575 |
51.306 |
0.001 |
-0.00% |
0.001 |
|
MultiSource/Benchmarks/Olden/em3d/em3d
Profile
|
-17.95% |
18.304 |
15.019 |
0.004 |
0.03% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint16_t>/28
|
-17.90% |
104.498 |
85.796 |
0.242 |
0.02% |
0.242 |
|
SingleSource/Benchmarks/Shootout/Shootout-random
Profile
|
-17.84% |
7.013 |
5.761 |
0.000 |
0.00% |
0.000 |
|
SingleSource/Benchmarks/Shootout-C++/Shootout-C++-random
Profile
|
-17.82% |
7.017 |
5.766 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_multiply_accumulate_runtime_checks_pass<2, double>
|
-17.65% |
10.637 |
8.759 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint32_t_To_uint16_t_
|
-17.49% |
12919.660 |
10660.032 |
125.786 |
0.84% |
125.786 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint32_t_To_uint16_t_
|
-17.41% |
12911.816 |
10663.373 |
133.932 |
-0.70% |
133.932 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint8_t>/16
|
-17.40% |
33.992 |
28.076 |
0.012 |
0.02% |
0.012 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint32_t_To_uint16_t_
|
-17.38% |
12907.981 |
10664.590 |
133.307 |
0.94% |
133.307 |
|
External/SPEC/CFP2017rate/510.parest_r/510.parest_r
Profile
|
-17.16% |
419.440 |
347.447 |
1.014 |
0.08% |
1.014 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C/miniAMR/miniAMR
Profile
|
-16.40% |
3.696 |
3.089 |
0.135 |
-3.19% |
0.135 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_csa_with_cond_arith_novec_int32_t_
|
-16.37% |
571704.349 |
478127.932 |
1057.002 |
0.05% |
1057.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint16_t>/16
|
-16.36% |
66.954 |
56.000 |
0.053 |
0.10% |
0.053 |
|
SingleSource/Benchmarks/Adobe-C++/loop_unroll
Profile
|
-15.94% |
27.321 |
22.967 |
0.002 |
0.01% |
0.002 |
|
MultiSource/Benchmarks/TSVC/StatementReordering-dbl/StatementReordering-dbl
Profile
|
-15.92% |
24.683 |
20.754 |
0.361 |
-0.33% |
0.361 |
|
MultiSource/Benchmarks/MiBench/telecomm-gsm/telecomm-gsm
Profile
|
-15.87% |
0.692 |
0.583 |
0.000 |
-0.04% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint32_t>/10
|
-15.87% |
76.336 |
64.221 |
0.035 |
-0.14% |
0.035 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_csa_with_cond_arith_autovec_int32_t_
|
-15.80% |
568560.244 |
478724.241 |
861.358 |
-0.00% |
861.358 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint16_t>/10
|
-15.22% |
48.181 |
40.849 |
0.110 |
0.02% |
0.110 |
|
MicroBenchmarks/ImageProcessing/Blur/blur.test:BENCHMARK_GAUSSIAN_BLUR/128
|
-15.04% |
4435.341 |
3768.242 |
0.576 |
-0.01% |
0.576 |
|
MultiSource/Benchmarks/mediabench/gsm/toast/toast
Profile
|
-14.95% |
0.090 |
0.076 |
0.000 |
-0.01% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint32_t>/10
|
-14.63% |
51.308 |
43.799 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/ImageProcessing/Blur/blur.test:BENCHMARK_GAUSSIAN_BLUR/256
|
-14.41% |
19528.547 |
16714.762 |
22.005 |
-0.78% |
22.005 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C++/HPCCG/HPCCG
Profile
|
-14.39% |
4.652 |
3.983 |
0.045 |
-0.08% |
0.045 |
|
MicroBenchmarks/ImageProcessing/Blur/blur.test:BENCHMARK_GAUSSIAN_BLUR/512
|
-14.38% |
81786.722 |
70029.262 |
20.902 |
0.10% |
20.902 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_multiply_accumulate_runtime_checks_fail<2, double>
|
-14.29% |
13.140 |
11.262 |
0.000 |
-0.00% |
0.000 |
|
MultiSource/Benchmarks/TSVC/Expansion-flt/Expansion-flt
Profile
|
-13.75% |
12.429 |
10.720 |
0.245 |
-0.61% |
0.245 |
|
SingleSource/Benchmarks/Shootout/Shootout-matrix
Profile
|
-13.33% |
4.693 |
4.067 |
0.000 |
0.00% |
0.000 |
|
SingleSource/Benchmarks/Polybench/stencils/seidel-2d/seidel-2d
Profile
|
-12.65% |
118.438 |
103.455 |
0.212 |
-0.00% |
0.212 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint64_t>/16
|
-12.60% |
53.215 |
46.510 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint16_t>/999
|
-12.58% |
52.248 |
45.674 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint16_t>/28
|
-12.58% |
52.247 |
45.675 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint16_t>/10
|
-12.58% |
52.248 |
45.676 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint16_t>/256
|
-12.57% |
52.246 |
45.676 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint16_t>/51
|
-12.57% |
52.248 |
45.678 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint16_t>/16
|
-12.57% |
52.246 |
45.677 |
0.000 |
0.00% |
0.000 |
|
SingleSource/Benchmarks/Stanford/Bubblesort
Profile
|
-12.57% |
0.090 |
0.079 |
0.000 |
-0.01% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint16_t>/28
|
-12.50% |
120.135 |
105.119 |
0.002 |
-0.00% |
0.002 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C++/miniFE/miniFE
Profile
|
-12.38% |
17.849 |
15.639 |
0.065 |
-0.05% |
0.065 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint16_t>/16
|
-12.28% |
89.163 |
78.215 |
0.005 |
-0.00% |
0.005 |
|
External/SPEC/CFP2017rate/526.blender_r/526.blender_r
Profile
|
-12.20% |
879.226 |
771.947 |
2.138 |
-0.71% |
2.138 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint16_t>/10
|
-12.19% |
76.960 |
67.577 |
0.006 |
0.00% |
0.006 |
|
MultiSource/Benchmarks/TSVC/Expansion-dbl/Expansion-dbl
Profile
|
-12.09% |
21.122 |
18.569 |
0.212 |
-1.90% |
0.212 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint64_t>/10
|
-12.02% |
38.640 |
33.997 |
0.002 |
0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint16_t>/51
|
-12.02% |
169.256 |
148.918 |
0.004 |
-0.00% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint16_t>/256
|
-11.92% |
642.905 |
566.282 |
0.004 |
-0.00% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint16_t>/16
|
-11.88% |
100.115 |
88.222 |
0.003 |
-0.00% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint16_t>/10
|
-11.88% |
81.654 |
71.956 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint16_t>/28
|
-11.87% |
155.494 |
137.032 |
0.012 |
-0.00% |
0.012 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint16_t>/51
|
-11.87% |
266.237 |
234.635 |
0.005 |
-0.00% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint16_t>/999
|
-11.87% |
2365.086 |
2084.407 |
0.097 |
-0.00% |
0.097 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint16_t>/256
|
-11.86% |
1207.632 |
1064.365 |
0.035 |
-0.00% |
0.035 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint32_t>/256
|
-11.80% |
50.371 |
44.425 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint32_t>/16
|
-11.80% |
50.371 |
44.425 |
0.002 |
0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint32_t>/51
|
-11.80% |
50.371 |
44.425 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint32_t>/28
|
-11.80% |
50.370 |
44.426 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint32_t>/999
|
-11.80% |
50.370 |
44.428 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint16_t>/999
|
-11.79% |
4647.048 |
4099.250 |
0.373 |
-0.00% |
0.373 |
|
MultiSource/Benchmarks/ASC_Sequoia/AMGmk/AMGmk
Profile
|
-11.75% |
43.459 |
38.352 |
0.023 |
-0.02% |
0.023 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint32_t>/28
|
-11.67% |
112.632 |
99.486 |
0.002 |
0.00% |
0.002 |
|
MultiSource/Benchmarks/McCat/18-imp/imp
Profile
|
-11.63% |
0.212 |
0.188 |
0.000 |
-0.12% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint16_t_To_uint32_t_
|
-11.59% |
13480.798 |
11918.891 |
29.029 |
0.37% |
29.029 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint64_t>/16
|
-11.56% |
32.544 |
28.783 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint16_t_To_uint32_t_
|
-11.49% |
13471.944 |
11924.115 |
32.639 |
0.37% |
32.639 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint8_t>/999
|
-11.46% |
4805.013 |
4254.199 |
0.141 |
-0.00% |
0.141 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint8_t>/256
|
-11.39% |
1245.804 |
1103.881 |
0.077 |
-0.00% |
0.077 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint8_t>/999
|
-11.39% |
2443.259 |
2165.048 |
0.069 |
0.00% |
0.069 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint8_t>/256
|
-11.38% |
662.339 |
586.980 |
0.045 |
0.00% |
0.045 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint64_t>/256
|
-11.36% |
27.530 |
24.402 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint64_t>/28
|
-11.36% |
27.530 |
24.403 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint64_t>/16
|
-11.36% |
27.530 |
24.403 |
0.002 |
0.00% |
0.002 |
|
MultiSource/Benchmarks/Rodinia/pathfinder/pathfinder
Profile
|
-11.35% |
1.372 |
1.216 |
0.010 |
-0.13% |
0.010 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint16_t_To_uint32_t_
|
-11.25% |
13432.632 |
11921.841 |
28.596 |
0.40% |
28.596 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint8_t>/51
|
-11.12% |
272.488 |
242.175 |
0.047 |
-0.00% |
0.047 |
|
SingleSource/Benchmarks/Misc/flops-4
Profile
|
-11.11% |
4.405 |
3.915 |
0.000 |
-0.01% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint8_t>/999
|
-11.04% |
2847.792 |
2533.414 |
0.865 |
-0.02% |
0.865 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint32_t>/256
|
-11.01% |
745.255 |
663.231 |
0.017 |
-0.00% |
0.017 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint32_t>/999
|
-11.01% |
2846.931 |
2533.602 |
0.434 |
-0.00% |
0.434 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint16_t>/256
|
-11.00% |
745.223 |
663.251 |
0.010 |
0.00% |
0.010 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint16_t>/999
|
-11.00% |
2848.455 |
2535.145 |
0.196 |
0.00% |
0.196 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint32_t>/999
|
-10.99% |
1453.725 |
1293.939 |
0.154 |
-0.01% |
0.154 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint8_t>/51
|
-10.99% |
172.925 |
153.925 |
0.008 |
-0.00% |
0.008 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/16
|
-10.91% |
194.627 |
173.390 |
0.009 |
0.00% |
0.009 |
|
MultiSource/Benchmarks/TSVC/StatementReordering-flt/StatementReordering-flt
Profile
|
-10.88% |
15.512 |
13.824 |
0.037 |
0.81% |
0.037 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint8_t>/28
|
-10.87% |
157.975 |
140.799 |
0.017 |
-0.00% |
0.017 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint8_t>/10
|
-10.87% |
24.538 |
21.871 |
0.424 |
0.12% |
0.424 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint16_t>/999
|
-10.86% |
1451.132 |
1293.547 |
0.336 |
-0.03% |
0.336 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint32_t>/16
|
-10.86% |
83.532 |
74.462 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint8_t>/256
|
-10.83% |
744.568 |
663.897 |
0.008 |
0.00% |
0.008 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint8_t>/256
|
-10.80% |
399.822 |
356.647 |
0.011 |
0.00% |
0.011 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint32_t>/256
|
-10.79% |
400.495 |
357.262 |
0.015 |
-0.00% |
0.015 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint16_t>/256
|
-10.78% |
400.440 |
357.267 |
0.011 |
-0.00% |
0.011 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint8_t>/999
|
-10.76% |
1450.661 |
1294.618 |
0.605 |
-0.03% |
0.605 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/32
|
-10.72% |
970.450 |
866.385 |
0.135 |
-0.01% |
0.135 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint8_t>/28
|
-10.71% |
122.638 |
109.504 |
0.013 |
0.00% |
0.013 |
|
SingleSource/Benchmarks/Misc/flops-3
Profile
|
-10.63% |
9.195 |
8.217 |
0.000 |
-0.00% |
0.000 |
|
External/SPEC/CFP2017rate/538.imagick_r/538.imagick_r
Profile
|
-10.63% |
272.224 |
243.289 |
0.385 |
0.08% |
0.385 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint16_t>/51
|
-10.63% |
170.824 |
152.669 |
0.004 |
-0.00% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint32_t>/51
|
-10.63% |
170.815 |
152.665 |
0.004 |
-0.00% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint32_t>/51
|
-10.62% |
156.117 |
139.531 |
0.003 |
0.00% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint8_t_To_uint32_t_
|
-10.62% |
12562.136 |
11228.303 |
11.838 |
-0.10% |
11.838 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/64
|
-10.62% |
4296.328 |
3840.209 |
6.833 |
0.03% |
6.833 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint8_t_To_uint32_t_
|
-10.59% |
12563.526 |
11232.879 |
8.391 |
-0.06% |
8.391 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint8_t>/16
|
-10.56% |
124.514 |
111.368 |
0.004 |
-0.00% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint8_t>/10
|
-10.53% |
83.221 |
74.456 |
0.003 |
-0.00% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint8_t>/999
|
-10.31% |
51.627 |
46.302 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint8_t>/256
|
-10.30% |
51.617 |
46.301 |
0.004 |
-0.00% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint8_t>/28
|
-10.27% |
51.601 |
46.302 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint8_t>/51
|
-10.23% |
51.577 |
46.301 |
0.003 |
0.00% |
0.003 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/256
|
-10.18% |
75030.662 |
67390.904 |
33.320 |
-0.02% |
33.320 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint8_t_To_uint32_t_
|
-10.17% |
12512.676 |
11240.109 |
9.400 |
-0.00% |
9.400 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint32_t>/16
|
-10.14% |
92.607 |
83.220 |
0.003 |
0.00% |
0.003 |
|
MultiSource/Benchmarks/TSVC/CrossingThresholds-flt/CrossingThresholds-flt
Profile
|
-10.09% |
11.078 |
9.960 |
0.013 |
-0.22% |
0.013 |
|
SingleSource/Benchmarks/Stanford/FloatMM
Profile
|
-10.07% |
0.498 |
0.448 |
0.000 |
-0.02% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_only_autovec_int64_t_
|
-10.00% |
1046245.511 |
941607.307 |
1144.993 |
-0.07% |
1144.993 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint8_t>/51
|
-9.93% |
170.196 |
153.298 |
0.007 |
-0.00% |
0.007 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_GEN_LIN_RECUR_LAMBDA/171
|
-9.93% |
2.158 |
1.944 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_GEN_LIN_RECUR_RAW/171
|
-9.90% |
2.155 |
1.942 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint64_t>/51
|
-9.89% |
56.940 |
51.307 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint32_t>/28
|
-9.89% |
142.352 |
128.274 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint64_t>/999
|
-9.89% |
56.939 |
51.308 |
0.003 |
0.00% |
0.003 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/128
|
-9.88% |
18337.432 |
16525.636 |
11.521 |
0.02% |
11.521 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_only_novec_int64_t_
|
-9.88% |
1045645.924 |
942332.825 |
385.843 |
-0.06% |
385.843 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint32_t>/999
|
-9.71% |
4194.518 |
3787.365 |
0.343 |
0.00% |
0.343 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint32_t>/51
|
-9.70% |
241.837 |
218.368 |
0.007 |
-0.00% |
0.007 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint32_t>/51
|
-9.67% |
110.143 |
99.489 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint32_t>/256
|
-9.64% |
581.001 |
524.983 |
0.058 |
-0.00% |
0.058 |
|
SingleSource/Benchmarks/Adobe-C++/stepanov_abstraction
Profile
|
-9.63% |
12.696 |
11.474 |
0.000 |
-0.01% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint8_t>/51
|
-9.60% |
110.746 |
100.110 |
0.001 |
-0.00% |
0.001 |
|
MultiSource/Benchmarks/ASC_Sequoia/CrystalMk/CrystalMk
Profile
|
-9.60% |
14.480 |
13.090 |
0.000 |
0.00% |
0.000 |
|
SingleSource/Benchmarks/Misc/matmul_f64_4x4
Profile
|
-9.58% |
5.057 |
4.573 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/ImageProcessing/Blur/blur.test:BENCHMARK_GAUSSIAN_BLUR/1024
|
-9.56% |
431140.727 |
389929.165 |
46.892 |
-0.06% |
46.892 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint32_t>/256
|
-9.50% |
1087.542 |
984.237 |
0.030 |
-0.01% |
0.030 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint32_t>/999
|
-9.39% |
2131.884 |
1931.623 |
0.046 |
-0.01% |
0.046 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC4
|
-9.36% |
10.354 |
9.386 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/16
|
-9.32% |
108.696 |
98.567 |
0.005 |
-0.01% |
0.005 |
|
MultiSource/Benchmarks/TSVC/Searching-flt/Searching-flt
Profile
|
-9.27% |
17.074 |
15.490 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_ADI_LAMBDA/5001
|
-9.24% |
1701.071 |
1543.814 |
30.947 |
-3.33% |
30.947 |
|
SingleSource/Benchmarks/Shootout-C++/Shootout-C++-methcall
Profile
|
-9.22% |
13.567 |
12.316 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint8_t>/16
|
-9.17% |
75.084 |
68.201 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/32
|
-9.15% |
444.450 |
403.764 |
0.007 |
-0.00% |
0.007 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/64
|
-9.11% |
1795.486 |
1631.900 |
8.001 |
-0.00% |
8.001 |
|
SingleSource/Benchmarks/BenchmarkGame/Large/fasta
Profile
|
-9.07% |
2.180 |
1.982 |
0.004 |
-0.28% |
0.004 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_FIR_LAMBDA/171
|
-9.03% |
2.440 |
2.220 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchAutoVec<uint16_t>/127
|
-9.01% |
69.457 |
63.198 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_FIR_RAW/171
|
-8.99% |
2.440 |
2.220 |
0.000 |
-0.01% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchAutoVec<uint16_t>/65
|
-8.98% |
48.805 |
44.425 |
0.002 |
0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchAutoVec<uint8_t>/127
|
-8.95% |
41.923 |
38.170 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchAutoVec<uint8_t>/65
|
-8.93% |
35.041 |
31.912 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/256
|
-8.83% |
29481.368 |
26879.397 |
24.751 |
-0.14% |
24.751 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_FIR_RAW/5001
|
-8.72% |
80.865 |
73.812 |
0.035 |
-0.06% |
0.035 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/128
|
-8.71% |
7415.789 |
6769.703 |
4.245 |
-0.06% |
4.245 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_only_novec_int32_t_
|
-8.67% |
515135.584 |
470456.708 |
306.362 |
-0.03% |
306.362 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_FIR_LAMBDA/5001
|
-8.64% |
80.851 |
73.863 |
0.014 |
0.01% |
0.014 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_only_autovec_int32_t_
|
-8.61% |
515323.384 |
470958.808 |
296.023 |
0.04% |
296.023 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint64_t>/10
|
-8.57% |
21.899 |
20.023 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint16_t>/51
|
-8.55% |
109.500 |
100.144 |
0.138 |
-0.27% |
0.138 |
|
MultiSource/Benchmarks/TSVC/NodeSplitting-flt/NodeSplitting-flt
Profile
|
-8.54% |
17.421 |
15.934 |
0.080 |
-0.09% |
0.080 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint16_t_To_uint64_t_
|
-8.34% |
23815.476 |
21828.869 |
57.408 |
-0.36% |
57.408 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint16_t_To_uint64_t_
|
-8.20% |
23779.783 |
21828.896 |
57.231 |
-0.28% |
57.231 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchAutoVec<uint32_t>/65
|
-8.19% |
76.337 |
70.083 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint16_t>/999
|
-8.15% |
3853.707 |
3539.657 |
0.072 |
0.00% |
0.072 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint16_t>/256
|
-8.15% |
1005.482 |
923.545 |
0.019 |
-0.00% |
0.019 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint64_t>/10
|
-8.12% |
30.662 |
28.171 |
0.033 |
0.00% |
0.033 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint16_t_To_uint64_t_
|
-8.12% |
23755.880 |
21826.073 |
58.364 |
-0.30% |
58.364 |
|
MultiSource/Benchmarks/TSVC/Searching-dbl/Searching-dbl
Profile
|
-8.06% |
19.268 |
17.715 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint8_t>/10
|
-8.05% |
54.437 |
50.057 |
0.002 |
0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchAutoVec<uint32_t>/127
|
-8.03% |
124.514 |
114.511 |
0.007 |
0.01% |
0.007 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC127
|
-8.02% |
113.042 |
103.976 |
0.462 |
-0.19% |
0.462 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint16_t>/999
|
-8.02% |
1937.310 |
1781.960 |
0.089 |
0.00% |
0.089 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint32_t>/999
|
-7.95% |
3925.745 |
3613.737 |
0.598 |
0.00% |
0.598 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint16_t>/256
|
-7.95% |
511.823 |
471.147 |
0.011 |
0.00% |
0.011 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint32_t>/999
|
-7.92% |
1978.157 |
1821.526 |
0.122 |
0.00% |
0.122 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC127
|
-7.83% |
113.073 |
104.216 |
0.277 |
-0.25% |
0.277 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint32_t>/256
|
-7.79% |
1019.579 |
940.155 |
0.027 |
-0.00% |
0.027 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC128
|
-7.72% |
112.971 |
104.253 |
0.145 |
-0.17% |
0.145 |
|
SingleSource/Benchmarks/Linpack/linpack-pc
Profile
|
-7.65% |
9.573 |
8.841 |
0.005 |
0.03% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint64_t>/51
|
-7.64% |
196.478 |
181.460 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC128
|
-7.64% |
112.996 |
104.365 |
0.244 |
-0.46% |
0.244 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC128
|
-7.62% |
113.028 |
104.412 |
0.214 |
-0.33% |
0.214 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC128
|
-7.62% |
113.095 |
104.478 |
0.233 |
-0.01% |
0.233 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint16_t_To_uint8_t_
|
-7.60% |
4721.120 |
4362.160 |
0.683 |
0.01% |
0.683 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint16_t_To_uint8_t_
|
-7.59% |
4721.142 |
4362.580 |
0.642 |
0.01% |
0.642 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint16_t_To_uint8_t_
|
-7.59% |
4721.231 |
4363.098 |
0.089 |
-0.02% |
0.089 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_ADI_LAMBDA/44217
|
-7.57% |
14964.056 |
13831.369 |
36.418 |
-0.82% |
36.418 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC127
|
-7.56% |
112.882 |
104.342 |
0.239 |
-0.14% |
0.239 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC127
|
-7.56% |
113.069 |
104.521 |
0.133 |
0.15% |
0.133 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIND_FIRST_MIN_RAW/171
|
-7.56% |
1.390 |
1.285 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint32_t>/256
|
-7.56% |
521.863 |
482.418 |
0.012 |
-0.00% |
0.012 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_FIR_LAMBDA/44217
|
-7.56% |
780.201 |
721.243 |
5.232 |
-1.62% |
5.232 |
|
SingleSource/Benchmarks/Misc-C++/Large/sphereflake
Profile
|
-7.52% |
19.566 |
18.095 |
0.003 |
-0.01% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC128
|
-7.49% |
112.956 |
104.499 |
0.162 |
-0.03% |
0.162 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint16_t>/51
|
-7.47% |
209.623 |
193.960 |
0.008 |
-0.00% |
0.008 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint16_t>/28
|
-7.46% |
117.653 |
108.875 |
0.003 |
0.00% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopFrom_uint32_t_To_uint8_t_
|
-7.46% |
10449.467 |
9670.146 |
18.841 |
-0.18% |
18.841 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC127
|
-7.43% |
112.967 |
104.572 |
0.222 |
0.32% |
0.222 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint32_t_To_uint8_t_
|
-7.42% |
10436.688 |
9661.978 |
22.827 |
-0.88% |
22.827 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint32_t_To_uint8_t_
|
-7.38% |
10430.646 |
9661.239 |
25.090 |
-0.53% |
25.090 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint32_t_To_uint8_t_
|
-7.32% |
14212.545 |
13172.063 |
15.562 |
-0.38% |
15.562 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_csa_with_cond_arith_autovec_uint8_t_
|
-7.29% |
534382.568 |
495424.745 |
37.285 |
0.00% |
37.285 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_csa_with_cond_arith_novec_uint8_t_
|
-7.29% |
534365.099 |
495434.741 |
8.063 |
0.00% |
8.063 |
|
MultiSource/Benchmarks/TSVC/InductionVariable-dbl/InductionVariable-dbl
Profile
|
-7.25% |
19.083 |
17.699 |
0.212 |
-0.59% |
0.212 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint16_t>/10
|
-7.18% |
22.245 |
20.647 |
0.031 |
-0.00% |
0.031 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint32_t_To_uint8_t_
|
-7.15% |
14205.854 |
13190.352 |
3.802 |
-0.26% |
3.802 |
|
SingleSource/Benchmarks/Adobe-C++/stepanov_vector
Profile
|
-7.15% |
7.791 |
7.235 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_no_runtime_checks_needed<4, int>
|
-7.15% |
8.760 |
8.134 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint16_t>/51
|
-7.14% |
114.546 |
106.370 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint32_t_To_uint8_t_
|
-7.11% |
14205.288 |
13195.673 |
5.467 |
-0.19% |
5.467 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint16_t>/16
|
-7.06% |
29.623 |
27.531 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint64_t>/10
|
-6.99% |
24.373 |
22.670 |
0.538 |
0.64% |
0.538 |
|
MultiSource/Benchmarks/TSVC/InductionVariable-flt/InductionVariable-flt
Profile
|
-6.78% |
10.035 |
9.355 |
0.058 |
0.32% |
0.058 |
|
MultiSource/Benchmarks/TSVC/NodeSplitting-dbl/NodeSplitting-dbl
Profile
|
-6.72% |
23.405 |
21.833 |
0.091 |
0.29% |
0.091 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint16_t>/28
|
-6.67% |
75.082 |
70.077 |
0.004 |
-0.00% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC64
|
-6.64% |
57.566 |
53.742 |
0.033 |
-0.13% |
0.033 |
|
MicroBenchmarks/harris/harris.test:BENCHMARK_HARRIS/2048/2048
|
-6.62% |
225384.680 |
210467.624 |
2090.566 |
0.41% |
2090.566 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C/CoMD/CoMD
Profile
|
-6.62% |
10.055 |
9.389 |
0.012 |
-0.04% |
0.012 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC63
|
-6.52% |
57.567 |
53.812 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC63
|
-6.52% |
57.568 |
53.815 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC63
|
-6.52% |
57.567 |
53.814 |
0.003 |
-0.00% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC63
|
-6.52% |
57.565 |
53.812 |
0.003 |
0.00% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC64
|
-6.52% |
57.564 |
53.812 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC64
|
-6.52% |
57.564 |
53.813 |
0.005 |
-0.00% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC64
|
-6.52% |
57.564 |
53.813 |
0.002 |
0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC64
|
-6.52% |
57.563 |
53.812 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC63
|
-6.51% |
57.564 |
53.814 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint32_t>/51
|
-6.43% |
210.202 |
196.692 |
0.178 |
0.01% |
0.178 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_xor_runtime_checks_pass<16, int>
|
-6.38% |
29.407 |
27.532 |
0.002 |
-0.01% |
0.002 |
|
MultiSource/Benchmarks/Trimaran/enc-rc4/enc-rc4
Profile
|
-6.37% |
2.913 |
2.728 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_runtime_checks_pass<16, int>
|
-6.35% |
39.419 |
36.917 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC32
|
-6.25% |
30.034 |
28.156 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC31
|
-6.25% |
30.034 |
28.157 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC32
|
-6.25% |
30.034 |
28.156 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC32
|
-6.25% |
30.035 |
28.157 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC31
|
-6.25% |
30.034 |
28.156 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC31
|
-6.25% |
30.035 |
28.157 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC32
|
-6.25% |
30.034 |
28.157 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC32
|
-6.25% |
30.034 |
28.157 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC31
|
-6.25% |
30.033 |
28.156 |
0.003 |
0.00% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC31
|
-6.25% |
30.033 |
28.157 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint32_t>/10
|
-6.25% |
20.022 |
18.772 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint64_t>/16
|
-6.24% |
38.037 |
35.663 |
0.005 |
-0.01% |
0.005 |
|
SingleSource/Benchmarks/Shootout-C++/Shootout-C++-fibo
Profile
|
-6.20% |
5.445 |
5.107 |
0.002 |
-0.01% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint8_t>/999
|
-6.17% |
5056.997 |
4744.975 |
0.278 |
0.00% |
0.278 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint64_t>/51
|
-6.05% |
310.351 |
291.583 |
0.007 |
0.00% |
0.007 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint8_t>/256
|
-6.04% |
1307.724 |
1228.689 |
0.208 |
0.01% |
0.208 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_FLOYD_DITHER/512
|
-6.04% |
6092.953 |
5724.957 |
53.122 |
-0.76% |
53.122 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint64_t_To_uint32_t_
|
-5.98% |
22063.599 |
20743.712 |
111.615 |
0.33% |
111.615 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint8_t>/999
|
-5.98% |
2542.862 |
2390.904 |
0.091 |
0.00% |
0.091 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_runtime_checks_fail<16, int>
|
-5.97% |
41.922 |
39.419 |
0.003 |
0.00% |
0.003 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIND_FIRST_MIN_RAW/5001
|
-5.97% |
42.137 |
39.623 |
0.034 |
-0.86% |
0.034 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint64_t>/999
|
-5.94% |
2804.568 |
2637.996 |
0.140 |
0.00% |
0.140 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_ADI_LAMBDA/171
|
-5.94% |
32.530 |
30.598 |
0.183 |
-0.66% |
0.183 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint8_t>/51
|
-5.91% |
266.770 |
250.992 |
0.276 |
-0.24% |
0.276 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint64_t_To_uint32_t_
|
-5.91% |
22078.253 |
20773.268 |
92.870 |
-0.60% |
92.870 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint64_t_To_uint32_t_
|
-5.90% |
22042.110 |
20740.571 |
108.799 |
0.24% |
108.799 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint8_t>/256
|
-5.90% |
667.586 |
628.222 |
0.011 |
-0.00% |
0.011 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint32_t>/28
|
-5.89% |
120.330 |
113.245 |
0.004 |
-0.00% |
0.004 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_xor_runtime_checks_fail<16, int>
|
-5.88% |
31.910 |
30.034 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC15
|
-5.80% |
273.341 |
257.484 |
2.552 |
-1.62% |
2.552 |
|
SingleSource/Benchmarks/Shootout/Shootout-fib2
Profile
|
-5.80% |
5.409 |
5.095 |
0.009 |
0.01% |
0.009 |
|
External/SPEC/CINT2017rate/525.x264_r/525.x264_r
Profile
|
-5.78% |
142.176 |
133.957 |
0.136 |
-0.66% |
0.136 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_FLOYD_DITHER/256
|
-5.78% |
1579.312 |
1488.088 |
6.115 |
-0.09% |
6.115 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint64_t>/999
|
-5.73% |
5517.621 |
5201.293 |
0.542 |
0.00% |
0.542 |
|
SingleSource/Benchmarks/Misc-C++/bigfib
Profile
|
-5.50% |
1.295 |
1.224 |
0.014 |
-0.32% |
0.014 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_FIR_RAW/44217
|
-5.48% |
760.807 |
719.122 |
10.148 |
-1.15% |
10.148 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC15
|
-5.47% |
272.396 |
257.490 |
2.540 |
-1.66% |
2.540 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_GEN_LIN_RECUR_LAMBDA/5001
|
-5.47% |
87.236 |
82.466 |
0.127 |
-0.06% |
0.127 |
|
SingleSource/Benchmarks/Misc-C++/Large/ray
Profile
|
-5.46% |
9.837 |
9.300 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_FLOYD_DITHER/128
|
-5.42% |
402.074 |
380.269 |
1.522 |
0.05% |
1.522 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint32_t>/51
|
-5.42% |
116.433 |
110.125 |
0.002 |
0.01% |
0.002 |
|
MultiSource/Benchmarks/MiBench/consumer-lame/consumer-lame
Profile
|
-5.36% |
0.682 |
0.645 |
0.001 |
-0.07% |
0.001 |
|
SingleSource/Benchmarks/Shootout-C++/EH/Shootout-C++-except
Profile
|
-5.34% |
1.115 |
1.056 |
0.003 |
0.13% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopTC15
|
-5.31% |
271.926 |
257.487 |
2.524 |
-1.75% |
2.524 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIND_FIRST_MIN_RAW/44217
|
-5.30% |
361.165 |
342.037 |
0.373 |
-0.22% |
0.373 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_PRESSURE_CALC_RAW/171
|
-5.26% |
1.540 |
1.459 |
0.000 |
-0.00% |
0.000 |
|
MultiSource/Benchmarks/MallocBench/cfrac/cfrac
Profile
|
-5.24% |
2.783 |
2.637 |
0.003 |
-0.19% |
0.003 |
|
MultiSource/Benchmarks/TSVC/IndirectAddressing-flt/IndirectAddressing-flt
Profile
|
-5.24% |
15.747 |
14.922 |
0.045 |
-0.49% |
0.045 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_PRESSURE_CALC_LAMBDA/171
|
-5.23% |
1.541 |
1.460 |
0.000 |
-0.00% |
0.000 |
|
MultiSource/Benchmarks/TSVC/Reductions-flt/Reductions-flt
Profile
|
-5.22% |
2.830 |
2.683 |
0.037 |
-0.27% |
0.037 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint64_t>/999
|
-5.21% |
3006.073 |
2849.522 |
0.150 |
-0.00% |
0.150 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint64_t>/999
|
-5.15% |
1529.178 |
1450.468 |
0.144 |
0.02% |
0.144 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_ORDERED_DITHER/128/3
|
-5.15% |
2292.263 |
2174.315 |
20.318 |
-0.54% |
20.318 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_GEN_LIN_RECUR_RAW/5001
|
-5.14% |
86.903 |
82.438 |
0.086 |
0.06% |
0.086 |
|
MicroBenchmarks/ImageProcessing/Dilate/Dilate.test:BENCHMARK_DILATE/128
|
-5.06% |
324.721 |
308.298 |
4.855 |
-2.45% |
4.855 |
|
SingleSource/Benchmarks/Misc/flops
Profile
|
-5.03% |
14.144 |
13.432 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint8_t>/28
|
-5.03% |
149.558 |
142.035 |
0.006 |
-0.00% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint64_t>/51
|
-4.95% |
113.886 |
108.250 |
0.002 |
0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint32_t>/28
|
-4.94% |
76.337 |
72.566 |
0.008 |
-0.01% |
0.008 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC7
|
-4.92% |
161.315 |
153.371 |
2.835 |
-1.31% |
2.835 |
|
SingleSource/Benchmarks/Misc/ReedSolomon
Profile
|
-4.80% |
22.059 |
21.000 |
0.000 |
0.01% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint16_t>/16
|
-4.80% |
49.949 |
47.554 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopTC7
|
-4.79% |
160.984 |
153.270 |
2.667 |
-1.09% |
2.667 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_two_loads<uint8_t>/51
|
-4.77% |
39.420 |
37.541 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_two_loads<uint8_t>/999
|
-4.76% |
39.419 |
37.541 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_two_loads<uint8_t>/256
|
-4.76% |
39.419 |
37.542 |
0.002 |
-0.00% |
0.002 |
|
SingleSource/Benchmarks/McGill/queens
Profile
|
-4.75% |
2.908 |
2.770 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_ORDERED_DITHER/512/3
|
-4.73% |
36570.164 |
34842.060 |
28.323 |
-0.03% |
28.323 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_two_loads<uint16_t>/999
|
-4.69% |
40.046 |
38.167 |
0.002 |
0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_two_loads<uint16_t>/51
|
-4.69% |
40.046 |
38.167 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_two_loads<uint32_t>/256
|
-4.69% |
40.046 |
38.167 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_two_loads<uint32_t>/51
|
-4.69% |
40.046 |
38.168 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_two_loads<uint16_t>/256
|
-4.69% |
40.045 |
38.167 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_two_loads<uint32_t>/999
|
-4.69% |
40.046 |
38.168 |
0.001 |
-0.00% |
0.001 |
|
MultiSource/Benchmarks/FreeBench/fourinarow/fourinarow
Profile
|
-4.67% |
0.677 |
0.645 |
0.001 |
-0.07% |
0.001 |
|
SingleSource/Benchmarks/BenchmarkGame/spectral-norm
Profile
|
-4.66% |
1.615 |
1.540 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_ORDERED_DITHER/256/3
|
-4.65% |
9301.952 |
8869.470 |
28.177 |
-0.16% |
28.177 |
|
MultiSource/Benchmarks/PAQ8p/paq8p
Profile
|
-4.64% |
200.309 |
191.019 |
0.358 |
-0.22% |
0.358 |
|
MultiSource/Benchmarks/TSVC/LoopRerolling-dbl/LoopRerolling-dbl
Profile
|
-4.60% |
10.090 |
9.626 |
0.169 |
-3.01% |
0.169 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC7
|
-4.59% |
160.668 |
153.291 |
2.734 |
-1.07% |
2.734 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint64_t>/51
|
-4.56% |
178.325 |
170.187 |
0.004 |
-0.00% |
0.004 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_ORDERED_DITHER/128/8
|
-4.56% |
2173.775 |
2074.734 |
20.728 |
-0.59% |
20.728 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_ORDERED_DITHER/128/4
|
-4.51% |
2170.766 |
2072.793 |
19.788 |
-0.52% |
19.788 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint8_t>/51
|
-4.47% |
144.758 |
138.281 |
0.003 |
-0.00% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint64_t>/28
|
-4.46% |
53.057 |
50.688 |
0.002 |
-0.01% |
0.002 |
|
MicroBenchmarks/LCALS/SubsetBLambdaLoops/lcalsBLambda.test:BM_INIT3_LAMBDA/171
|
-4.46% |
0.711 |
0.679 |
0.003 |
-0.81% |
0.003 |
|
SingleSource/Benchmarks/Misc/flops-1
Profile
|
-4.44% |
8.804 |
8.413 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/ImageProcessing/BilateralFiltering/BilateralFilter.test:BENCHMARK_BILATERAL_FILTER/64/2
|
-4.43% |
2551.510 |
2438.393 |
0.139 |
-0.01% |
0.139 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_ORDERED_DITHER/512/8
|
-4.37% |
34768.085 |
33247.446 |
8.757 |
0.03% |
8.757 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C/SimpleMOC/SimpleMOC
Profile
|
-4.35% |
7.415 |
7.092 |
0.029 |
-0.38% |
0.029 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_MAT_X_MAT_RAW/171
|
-4.34% |
2479.442 |
2371.775 |
36.912 |
-0.01% |
36.912 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint8_t_To_uint64_t_
|
-4.33% |
22732.946 |
21749.275 |
56.156 |
0.01% |
56.156 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint8_t_To_uint64_t_
|
-4.29% |
22724.322 |
21750.256 |
46.173 |
-0.03% |
46.173 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint8_t_To_uint64_t_
|
-4.27% |
22717.333 |
21747.864 |
46.583 |
0.00% |
46.583 |
|
MicroBenchmarks/LCALS/SubsetBRawLoops/lcalsBRaw.test:BM_INIT3_RAW/171
|
-4.26% |
0.711 |
0.681 |
0.002 |
-0.43% |
0.002 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_ORDERED_DITHER/512/4
|
-4.20% |
34674.256 |
33216.248 |
20.741 |
-0.03% |
20.741 |
|
SingleSource/Benchmarks/Misc/dt
Profile
|
-4.16% |
4.037 |
3.869 |
0.000 |
-0.01% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_EOS_LAMBDA/5001
|
-4.10% |
41.005 |
39.324 |
0.131 |
-0.28% |
0.131 |
|
MicroBenchmarks/ImageProcessing/AnisotropicDiffusion/AnisotropicDiffusion.test:BENCHMARK_ANISTROPIC_DIFFUSION/64
|
-4.08% |
9198.691 |
8823.525 |
1.149 |
-0.01% |
1.149 |
|
MicroBenchmarks/ImageProcessing/AnisotropicDiffusion/AnisotropicDiffusion.test:BENCHMARK_ANISTROPIC_DIFFUSION/128
|
-4.05% |
39484.789 |
37884.558 |
38.445 |
0.07% |
38.445 |
|
MultiSource/Benchmarks/Rodinia/hotspot/hotspot
Profile
|
-4.01% |
2.312 |
2.219 |
0.013 |
0.03% |
0.013 |
|
MicroBenchmarks/ImageProcessing/AnisotropicDiffusion/AnisotropicDiffusion.test:BENCHMARK_ANISTROPIC_DIFFUSION/256
|
-4.00% |
171882.749 |
165006.520 |
85.735 |
-0.03% |
85.735 |
|
External/SPEC/CFP2017rate/544.nab_r/544.nab_r
Profile
|
-3.99% |
454.804 |
436.675 |
0.218 |
-0.01% |
0.218 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_ORDERED_DITHER/256/4
|
-3.97% |
8849.763 |
8498.477 |
0.961 |
-0.02% |
0.961 |
|
MicroBenchmarks/ImageProcessing/AnisotropicDiffusion/AnisotropicDiffusion.test:BENCHMARK_ANISTROPIC_DIFFUSION/32
|
-3.97% |
2014.654 |
1934.712 |
0.584 |
0.00% |
0.584 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_ORDERED_DITHER/256/8
|
-3.93% |
8861.897 |
8513.580 |
7.038 |
0.04% |
7.038 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_PIC_2D_RAW/171
|
-3.88% |
13.665 |
13.135 |
0.063 |
-0.08% |
0.063 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint64_t_To_uint8_t_
|
-3.86% |
32336.834 |
31087.719 |
49.123 |
-0.03% |
49.123 |
|
MicroBenchmarks/ImageProcessing/BilateralFiltering/BilateralFilter.test:BENCHMARK_BILATERAL_FILTER/32/2
|
-3.86% |
593.241 |
570.347 |
3.752 |
-0.00% |
3.752 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint64_t_To_uint8_t_
|
-3.85% |
32343.677 |
31097.161 |
45.071 |
0.00% |
45.071 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC16
|
-3.85% |
16.269 |
15.643 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC16
|
-3.85% |
16.269 |
15.642 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC16
|
-3.85% |
16.269 |
15.643 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint64_t_To_uint8_t_
|
-3.85% |
32335.807 |
31091.146 |
48.611 |
-0.02% |
48.611 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC15
|
-3.85% |
16.269 |
15.643 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC15
|
-3.85% |
16.269 |
15.643 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC15
|
-3.85% |
16.269 |
15.643 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC16
|
-3.85% |
16.269 |
15.643 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC15
|
-3.84% |
16.268 |
15.643 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC16
|
-3.84% |
16.268 |
15.643 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC15
|
-3.84% |
16.268 |
15.643 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_DEL_DOT_VEC_2D_LAMBDA/2
|
-3.83% |
2.775 |
2.669 |
0.000 |
-0.00% |
0.000 |
|
SingleSource/Benchmarks/SmallPT/smallpt
Profile
|
-3.82% |
28.454 |
27.366 |
0.002 |
-0.01% |
0.002 |
|
MultiSource/Benchmarks/FreeBench/distray/distray
Profile
|
-3.81% |
0.424 |
0.408 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint32_t>/10
|
-3.79% |
41.296 |
39.731 |
0.006 |
-0.01% |
0.006 |
|
SingleSource/Benchmarks/Misc-C++/oopack_v1p8
Profile
|
-3.75% |
0.479 |
0.461 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/ImageProcessing/BilateralFiltering/BilateralFilter.test:BENCHMARK_BILATERAL_FILTER/16/2
|
-3.75% |
129.369 |
124.518 |
0.813 |
0.00% |
0.813 |
|
SingleSource/Benchmarks/Misc/flops-8
Profile
|
-3.68% |
1.973 |
1.900 |
0.000 |
0.01% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_DEL_DOT_VEC_2D_LAMBDA/1
|
-3.67% |
227.416 |
219.074 |
0.057 |
0.00% |
0.057 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_MAT_X_MAT_LAMBDA/171
|
-3.65% |
2483.986 |
2393.347 |
10.537 |
-0.30% |
10.537 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_COUPLE_RAW/2
|
-3.64% |
8.083 |
7.789 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetBRawLoops/lcalsBRaw.test:BM_IF_QUAD_RAW/44217
|
-3.62% |
1336.622 |
1288.179 |
17.545 |
-1.38% |
17.545 |
|
MultiSource/Benchmarks/Rodinia/backprop/backprop
Profile
|
-3.60% |
2.316 |
2.232 |
0.015 |
-1.50% |
0.015 |
|
SingleSource/Benchmarks/BenchmarkGame/n-body
Profile
|
-3.59% |
3.212 |
3.096 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_COUPLE_RAW/1
|
-3.57% |
1016.220 |
979.908 |
7.658 |
-0.01% |
7.658 |
|
External/SPEC/CFP2017rate/511.povray_r/511.povray_r
Profile
|
-3.57% |
28.635 |
27.613 |
0.067 |
0.19% |
0.067 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_COUPLE_RAW/0
|
-3.53% |
6136.421 |
5919.525 |
12.813 |
-0.18% |
12.813 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC1
|
-3.49% |
108.324 |
104.542 |
1.405 |
-1.19% |
1.405 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint16_t>/10
|
-3.47% |
35.652 |
34.414 |
0.001 |
-0.00% |
0.001 |
|
SingleSource/Benchmarks/Shootout-C++/Shootout-C++-lists
Profile
|
-3.45% |
20.762 |
20.046 |
0.015 |
0.24% |
0.015 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint8_t>/28
|
-3.44% |
92.661 |
89.474 |
0.002 |
0.00% |
0.002 |
|
MultiSource/Benchmarks/mafft/pairlocalalign
Profile
|
-3.43% |
79.380 |
76.660 |
0.359 |
-0.03% |
0.359 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_BAND_LIN_EQ_RAW/44217
|
-3.39% |
187.670 |
181.302 |
2.431 |
1.31% |
2.431 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_ORDERED_DITHER/128/2
|
-3.36% |
2142.135 |
2070.053 |
19.876 |
-0.48% |
19.876 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_DEL_DOT_VEC_2D_RAW/1
|
-3.36% |
226.576 |
218.971 |
0.022 |
-0.04% |
0.022 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint64_t_To_uint16_t_
|
-3.34% |
26726.819 |
25832.884 |
47.013 |
-0.19% |
47.013 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC16
|
-3.33% |
265.793 |
256.938 |
2.202 |
-1.04% |
2.202 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_DEL_DOT_VEC_2D_RAW/2
|
-3.31% |
2.760 |
2.668 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint64_t_To_uint16_t_
|
-3.30% |
26718.022 |
25835.703 |
47.781 |
-0.19% |
47.781 |
|
MicroBenchmarks/LCALS/SubsetBLambdaLoops/lcalsBLambda.test:BM_IF_QUAD_LAMBDA/171
|
-3.28% |
4.243 |
4.104 |
0.000 |
-0.00% |
0.000 |
|
External/SPEC/CFP2017rate/508.namd_r/508.namd_r
Profile
|
-3.27% |
187.364 |
181.233 |
0.290 |
0.03% |
0.290 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint64_t_To_uint16_t_
|
-3.27% |
26721.359 |
25847.381 |
44.171 |
-0.14% |
44.171 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC16
|
-3.25% |
265.585 |
256.944 |
2.194 |
-1.14% |
2.194 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopTC16
|
-3.25% |
265.574 |
256.939 |
2.230 |
-1.13% |
2.230 |
|
SingleSource/Benchmarks/Dhrystone/fldry
Profile
|
-3.25% |
0.975 |
0.943 |
0.000 |
-0.01% |
0.000 |
|
SingleSource/Benchmarks/Misc/ffbench
Profile
|
-3.21% |
10.813 |
10.466 |
0.124 |
-1.07% |
0.124 |
|
External/SPEC/CFP2017rate/519.lbm_r/519.lbm_r
Profile
|
-3.18% |
211.683 |
204.944 |
1.663 |
0.01% |
1.663 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_ORDERED_DITHER/512/2
|
-3.18% |
34278.585 |
33188.073 |
34.084 |
-0.11% |
34.084 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_PIC_2D_LAMBDA/171
|
-3.16% |
13.738 |
13.304 |
0.080 |
0.00% |
0.080 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_HYDRO_2D_LAMBDA/171
|
-3.15% |
261.306 |
253.077 |
0.398 |
-0.07% |
0.398 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint8_t>/10
|
-3.13% |
20.022 |
19.396 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint8_t>/16
|
-3.12% |
20.022 |
19.397 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_HYDRO_2D_RAW/171
|
-3.12% |
261.421 |
253.274 |
1.633 |
0.03% |
1.633 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC1
|
-3.07% |
108.216 |
104.891 |
0.959 |
-0.40% |
0.959 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC2
|
-3.05% |
108.197 |
104.894 |
1.065 |
-1.19% |
1.065 |
|
MultiSource/Benchmarks/TSVC/ControlLoops-flt/ControlLoops-flt
Profile
|
-3.04% |
4.213 |
4.085 |
0.034 |
-0.20% |
0.034 |
|
MicroBenchmarks/LCALS/SubsetBLambdaLoops/lcalsBLambda.test:BM_IF_QUAD_LAMBDA/5001
|
-3.02% |
131.334 |
127.361 |
0.231 |
-0.06% |
0.231 |
|
MultiSource/Benchmarks/FreeBench/pifft/pifft
Profile
|
-2.98% |
0.351 |
0.340 |
0.002 |
-0.42% |
0.002 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_ADI_RAW/171
|
-2.96% |
31.912 |
30.966 |
0.124 |
-0.26% |
0.124 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC4
|
-2.96% |
107.017 |
103.851 |
1.174 |
-0.89% |
1.174 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_COUPLE_LAMBDA/2
|
-2.95% |
8.058 |
7.820 |
0.001 |
-0.01% |
0.001 |
|
SingleSource/Benchmarks/Misc/pi
Profile
|
-2.95% |
1.863 |
1.808 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_single_load<uint16_t>/28
|
-2.94% |
21.274 |
20.648 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_single_load<uint16_t>/999
|
-2.94% |
21.274 |
20.648 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_single_load<uint16_t>/256
|
-2.94% |
21.274 |
20.648 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_single_load<uint16_t>/51
|
-2.93% |
21.273 |
20.649 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_COUPLE_LAMBDA/1
|
-2.92% |
1012.956 |
983.347 |
7.956 |
0.01% |
7.956 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC15
|
-2.92% |
21.274 |
20.652 |
0.010 |
0.02% |
0.010 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_PIC_1D_RAW/171
|
-2.90% |
9.067 |
8.804 |
0.002 |
-0.01% |
0.002 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_ORDERED_DITHER/256/2
|
-2.89% |
8733.359 |
8481.012 |
9.263 |
-0.09% |
9.263 |
|
SingleSource/Benchmarks/Misc/mandel
Profile
|
-2.85% |
3.300 |
3.206 |
0.000 |
-0.00% |
0.000 |
|
SingleSource/Benchmarks/Misc/perlin
Profile
|
-2.84% |
8.412 |
8.173 |
0.000 |
0.00% |
0.000 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C++/PENNANT/PENNANT
Profile
|
-2.81% |
4.607 |
4.477 |
0.017 |
-0.24% |
0.017 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC3
|
-2.80% |
107.676 |
104.659 |
0.947 |
-1.04% |
0.947 |
|
MultiSource/Benchmarks/tramp3d-v4/tramp3d-v4
Profile
|
-2.80% |
1.011 |
0.982 |
0.002 |
-0.06% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint32_t>/16
|
-2.77% |
56.315 |
54.754 |
0.008 |
0.00% |
0.008 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopTC2
|
-2.74% |
107.546 |
104.602 |
1.140 |
-0.78% |
1.140 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopTC3
|
-2.67% |
107.884 |
104.999 |
0.974 |
-1.27% |
0.974 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC16
|
-2.67% |
21.214 |
20.648 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_IMP_HYDRO_2D_RAW/5001
|
-2.66% |
1677.217 |
1632.596 |
2.705 |
0.08% |
2.705 |
|
MicroBenchmarks/LCALS/SubsetBRawLoops/lcalsBRaw.test:BM_IF_QUAD_RAW/171
|
-2.66% |
4.216 |
4.104 |
0.000 |
0.00% |
0.000 |
|
SingleSource/Benchmarks/Misc/flops-6
Profile
|
-2.64% |
1.850 |
1.801 |
0.000 |
0.00% |
0.000 |
|
MultiSource/Benchmarks/Fhourstones-3.1/fhourstones3.1
Profile
|
-2.62% |
3.931 |
3.828 |
0.009 |
-0.28% |
0.009 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C++/CLAMR/CLAMR
Profile
|
-2.57% |
12.121 |
11.809 |
0.025 |
-0.15% |
0.025 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint64_t>/256
|
-2.54% |
355.305 |
346.282 |
0.177 |
-0.03% |
0.177 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_DEL_DOT_VEC_2D_RAW/0
|
-2.52% |
1461.622 |
1424.822 |
2.173 |
-0.26% |
2.173 |
|
SingleSource/Benchmarks/Shootout-C++/Shootout-C++-lists1
Profile
|
-2.50% |
1.003 |
0.978 |
0.004 |
-0.06% |
0.004 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_IMP_HYDRO_2D_RAW/44217
|
-2.42% |
14979.919 |
14616.700 |
33.018 |
0.19% |
33.018 |
|
SingleSource/Benchmarks/Polybench/stencils/jacobi-2d/jacobi-2d
Profile
|
-2.39% |
41.791 |
40.791 |
0.010 |
-0.04% |
0.010 |
|
MultiSource/Benchmarks/McCat/12-IOtest/iotest
Profile
|
-2.39% |
2.027 |
1.979 |
0.016 |
-0.26% |
0.016 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_COUPLE_LAMBDA/0
|
-2.39% |
6103.757 |
5958.126 |
4.358 |
-0.05% |
4.358 |
|
MicroBenchmarks/ImageProcessing/BilateralFiltering/BilateralFilter.test:BENCHMARK_BILATERAL_FILTER/64/4
|
-2.38% |
9542.475 |
9315.287 |
1.609 |
-0.00% |
1.609 |
|
MultiSource/Applications/JM/lencod/lencod
Profile
|
-2.37% |
35.747 |
34.898 |
0.029 |
-0.09% |
0.029 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_DEL_DOT_VEC_2D_LAMBDA/0
|
-2.37% |
1463.348 |
1428.711 |
1.122 |
-0.01% |
1.122 |
|
MicroBenchmarks/ImageProcessing/BilateralFiltering/BilateralFilter.test:BENCHMARK_BILATERAL_FILTER/32/4
|
-2.36% |
2077.330 |
2028.236 |
0.042 |
0.00% |
0.042 |
|
MicroBenchmarks/LCALS/SubsetBRawLoops/lcalsBRaw.test:BM_IF_QUAD_RAW/5001
|
-2.36% |
130.491 |
127.413 |
0.156 |
0.02% |
0.156 |
|
MultiSource/Benchmarks/ASCI_Purple/SMG2000/smg2000
Profile
|
-2.36% |
17.924 |
17.501 |
0.020 |
-0.08% |
0.020 |
|
MicroBenchmarks/ImageProcessing/BilateralFiltering/BilateralFilter.test:BENCHMARK_BILATERAL_FILTER/16/4
|
-2.34% |
381.703 |
372.767 |
0.029 |
0.00% |
0.029 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_EOS_LAMBDA/171
|
-2.34% |
1.157 |
1.130 |
0.000 |
0.01% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint8_t>/10
|
-2.31% |
48.905 |
47.775 |
0.109 |
-0.30% |
0.109 |
|
SingleSource/Benchmarks/Misc/whetstone
Profile
|
-2.24% |
2.955 |
2.888 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_EOS_RAW/5001
|
-2.24% |
40.667 |
39.755 |
0.064 |
0.01% |
0.064 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_IMP_HYDRO_2D_RAW/171
|
-2.19% |
54.973 |
53.769 |
0.329 |
-0.01% |
0.329 |
|
MultiSource/Benchmarks/Olden/power/power
Profile
|
-2.19% |
3.744 |
3.662 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopInterchange/LoopInterchange.test:BENCHMARK_LI1
|
-2.18% |
1598.161 |
1563.382 |
5.165 |
-0.08% |
5.165 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_PRESSURE_CALC_RAW/5001
|
-2.06% |
48.017 |
47.026 |
0.381 |
-1.09% |
0.381 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC64
|
-2.04% |
165.326 |
161.950 |
0.064 |
-0.07% |
0.064 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC15
|
-2.03% |
21.081 |
20.653 |
0.011 |
0.02% |
0.011 |
|
MultiSource/Benchmarks/7zip/7zip-benchmark
Profile
|
-2.00% |
30.569 |
29.957 |
0.035 |
0.10% |
0.035 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC127
|
-1.95% |
315.944 |
309.793 |
0.011 |
0.00% |
0.011 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC64
|
-1.92% |
165.245 |
162.076 |
0.004 |
0.00% |
0.004 |
|
SingleSource/Benchmarks/Misc/flops-5
Profile
|
-1.89% |
2.584 |
2.535 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1BigLoopWithReductionTC4
|
-1.86% |
33.791 |
33.162 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC4
|
-1.86% |
33.790 |
33.162 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC7
|
-1.86% |
33.790 |
33.162 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC4
|
-1.86% |
33.790 |
33.162 |
0.003 |
-0.00% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC7
|
-1.86% |
33.790 |
33.163 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC8
|
-1.86% |
33.789 |
33.162 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC7
|
-1.86% |
33.790 |
33.163 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC8
|
-1.86% |
33.790 |
33.162 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_DISC_ORD_RAW/171
|
-1.86% |
18.778 |
18.430 |
0.032 |
-0.32% |
0.032 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC4
|
-1.86% |
33.789 |
33.162 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC4
|
-1.86% |
33.789 |
33.162 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1BigLoopWithReductionTC7
|
-1.86% |
33.790 |
33.163 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC2
|
-1.85% |
33.789 |
33.163 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1BigLoopWithReductionTC3
|
-1.85% |
33.789 |
33.162 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC1
|
-1.85% |
33.790 |
33.163 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC3
|
-1.85% |
33.789 |
33.162 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC8
|
-1.85% |
33.789 |
33.163 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC3
|
-1.85% |
33.789 |
33.163 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC8
|
-1.85% |
33.788 |
33.162 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC2
|
-1.85% |
33.789 |
33.163 |
0.002 |
0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC3
|
-1.85% |
33.788 |
33.163 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1BigLoopWithReductionTC1
|
-1.85% |
33.788 |
33.162 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC4
|
-1.85% |
33.788 |
33.163 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC8
|
-1.85% |
33.789 |
33.163 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC7
|
-1.85% |
33.789 |
33.164 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC1
|
-1.85% |
33.789 |
33.163 |
0.002 |
0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC3
|
-1.85% |
33.787 |
33.162 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC2
|
-1.85% |
33.789 |
33.163 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC7
|
-1.85% |
33.790 |
33.164 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC8
|
-1.85% |
33.790 |
33.164 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC3
|
-1.85% |
33.788 |
33.162 |
0.002 |
0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC1
|
-1.85% |
33.788 |
33.163 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC1
|
-1.85% |
33.789 |
33.164 |
0.002 |
0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC128
|
-1.85% |
315.601 |
309.761 |
0.025 |
-0.00% |
0.025 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC7
|
-1.85% |
33.789 |
33.164 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC4
|
-1.85% |
33.789 |
33.164 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC2
|
-1.85% |
33.788 |
33.163 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC2
|
-1.85% |
33.789 |
33.164 |
0.002 |
0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC2
|
-1.85% |
33.788 |
33.163 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1BigLoopWithReductionTC8
|
-1.85% |
33.789 |
33.164 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC3
|
-1.85% |
33.789 |
33.164 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC1
|
-1.85% |
33.788 |
33.163 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC1
|
-1.85% |
33.788 |
33.163 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1BigLoopWithReductionTC2
|
-1.85% |
33.788 |
33.164 |
0.000 |
0.00% |
0.000 |
|
MultiSource/Applications/sgefa/sgefa
Profile
|
-1.84% |
0.642 |
0.630 |
0.002 |
-0.13% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC63
|
-1.84% |
165.117 |
162.078 |
0.003 |
-0.00% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1BigLoopWithReductionTC63
|
-1.84% |
165.108 |
162.077 |
0.002 |
0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC63
|
-1.83% |
165.098 |
162.080 |
0.009 |
0.00% |
0.009 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC128
|
-1.83% |
315.552 |
309.789 |
0.011 |
-0.00% |
0.011 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC127
|
-1.82% |
315.535 |
309.777 |
0.011 |
-0.00% |
0.011 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC64
|
-1.82% |
165.073 |
162.072 |
0.014 |
-0.00% |
0.014 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1BigLoopWithReductionTC64
|
-1.82% |
165.082 |
162.082 |
0.003 |
-0.00% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC64
|
-1.82% |
165.068 |
162.070 |
0.006 |
0.00% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC128
|
-1.81% |
315.515 |
309.800 |
0.019 |
0.00% |
0.019 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint32_t>/28
|
-1.81% |
86.349 |
84.786 |
0.002 |
0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC127
|
-1.81% |
315.514 |
309.802 |
0.015 |
-0.00% |
0.015 |
|
MultiSource/Benchmarks/TSVC/IndirectAddressing-dbl/IndirectAddressing-dbl
Profile
|
-1.80% |
18.523 |
18.189 |
0.027 |
-0.25% |
0.027 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1BigLoopWithReductionTC128
|
-1.80% |
315.438 |
309.765 |
0.022 |
-0.00% |
0.022 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC128
|
-1.79% |
315.422 |
309.770 |
0.034 |
-0.00% |
0.034 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC63
|
-1.79% |
165.028 |
162.072 |
0.007 |
0.00% |
0.007 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC128
|
-1.78% |
315.400 |
309.775 |
0.023 |
0.00% |
0.023 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint8_t>/16
|
-1.78% |
68.382 |
67.166 |
0.017 |
-0.02% |
0.017 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC63
|
-1.77% |
164.999 |
162.074 |
0.010 |
0.00% |
0.010 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC127
|
-1.77% |
315.359 |
309.779 |
0.021 |
0.00% |
0.021 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC127
|
-1.77% |
315.353 |
309.783 |
0.013 |
-0.00% |
0.013 |
|
External/SPEC/CINT2017rate/541.leela_r/541.leela_r
Profile
|
-1.77% |
215.968 |
212.154 |
0.465 |
0.05% |
0.465 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC127
|
-1.76% |
315.335 |
309.775 |
0.018 |
-0.00% |
0.018 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC128
|
-1.76% |
315.359 |
309.806 |
0.003 |
-0.00% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1BigLoopWithReductionTC127
|
-1.74% |
315.232 |
309.760 |
0.056 |
-0.00% |
0.056 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, GreaterThanZero, Mid>
|
-1.73% |
30654.876 |
30124.125 |
0.981 |
-0.00% |
0.981 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC63
|
-1.73% |
164.947 |
162.092 |
0.005 |
0.01% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC64
|
-1.73% |
164.925 |
162.079 |
0.004 |
0.00% |
0.004 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<63, LessThanZero, Last>
|
-1.72% |
4764.976 |
4682.988 |
12.058 |
-0.02% |
12.058 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC63
|
-1.70% |
164.882 |
162.074 |
0.008 |
-0.00% |
0.008 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_asin_novec_double_
|
-1.68% |
1184.843 |
1164.888 |
1.285 |
-0.01% |
1.285 |
|
MicroBenchmarks/harris/harris.test:BENCHMARK_HARRIS/512/512
|
-1.67% |
30640.493 |
30128.380 |
107.116 |
1.16% |
107.116 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_nested_cond_load_novec_int64_t_
|
-1.67% |
617130.196 |
606846.479 |
2928.351 |
0.15% |
2928.351 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC64
|
-1.66% |
164.812 |
162.075 |
0.005 |
-0.00% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1LoopWithReductionTC31
|
-1.66% |
28.779 |
28.301 |
0.009 |
-0.52% |
0.009 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_IMP_HYDRO_2D_LAMBDA/44217
|
-1.65% |
14843.254 |
14597.959 |
75.201 |
-0.06% |
75.201 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_PLANCKIAN_RAW/44217
|
-1.65% |
4368.082 |
4295.970 |
25.369 |
-0.65% |
25.369 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_PIC_1D_LAMBDA/171
|
-1.65% |
8.951 |
8.804 |
0.029 |
0.03% |
0.029 |
|
MicroBenchmarks/harris/harris.test:BENCHMARK_HARRIS/1024/1024
|
-1.64% |
123698.333 |
121669.611 |
584.916 |
-1.44% |
584.916 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_INT_PREDICT_RAW/171
|
-1.60% |
6.127 |
6.029 |
0.004 |
-0.01% |
0.004 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_INT_PREDICT_LAMBDA/171
|
-1.59% |
6.134 |
6.037 |
0.007 |
-0.05% |
0.007 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_two_loads<uint64_t>/999
|
-1.57% |
40.048 |
39.418 |
0.002 |
0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_two_loads<uint64_t>/51
|
-1.57% |
40.045 |
39.418 |
0.001 |
-0.00% |
0.001 |
|
SingleSource/Benchmarks/Shootout-C++/Shootout-C++-sieve
Profile
|
-1.52% |
7.556 |
7.441 |
0.006 |
0.05% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC31
|
-1.51% |
89.498 |
88.147 |
0.041 |
-0.09% |
0.041 |
|
MicroBenchmarks/LCALS/SubsetBLambdaLoops/lcalsBLambda.test:BM_MULADDSUB_LAMBDA/5001
|
-1.49% |
58.478 |
57.604 |
0.264 |
0.02% |
0.264 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_IMP_HYDRO_2D_LAMBDA/5001
|
-1.48% |
1658.243 |
1633.712 |
3.888 |
-0.22% |
3.888 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_DISC_ORD_LAMBDA/171
|
-1.44% |
18.693 |
18.425 |
0.032 |
0.50% |
0.032 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_csa_with_in_loop_arith_autovec_int32_t_
|
-1.43% |
375998.947 |
370626.745 |
1696.693 |
-1.46% |
1696.693 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC31
|
-1.43% |
89.502 |
88.224 |
0.004 |
-0.00% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC31
|
-1.41% |
89.492 |
88.227 |
0.007 |
-0.00% |
0.007 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC32
|
-1.41% |
89.489 |
88.224 |
0.006 |
-0.00% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1BigLoopWithReductionTC31
|
-1.41% |
89.492 |
88.229 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1BigLoopWithReductionTC32
|
-1.41% |
89.488 |
88.225 |
0.010 |
-0.00% |
0.010 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC32
|
-1.41% |
89.488 |
88.227 |
0.012 |
-0.00% |
0.012 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC31
|
-1.41% |
89.483 |
88.224 |
0.005 |
-0.00% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC32
|
-1.41% |
89.486 |
88.228 |
0.003 |
-0.00% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC32
|
-1.40% |
89.485 |
88.231 |
0.002 |
0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC31
|
-1.40% |
89.485 |
88.231 |
0.003 |
-0.00% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC32
|
-1.40% |
89.480 |
88.226 |
0.004 |
-0.00% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_csa_with_cond_arith_autovec_int64_t_
|
-1.40% |
693303.386 |
683598.314 |
878.171 |
0.08% |
878.171 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC31
|
-1.38% |
89.469 |
88.231 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC32
|
-1.37% |
89.451 |
88.226 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LCALS/SubsetBLambdaLoops/lcalsBLambda.test:BM_TRAP_INT_LAMBDA/44217
|
-1.34% |
774.715 |
764.322 |
0.047 |
-0.00% |
0.047 |
|
MicroBenchmarks/LCALS/SubsetBRawLoops/lcalsBRaw.test:BM_TRAP_INT_RAW/44217
|
-1.34% |
774.728 |
764.342 |
0.008 |
0.00% |
0.008 |
|
MicroBenchmarks/LCALS/SubsetBRawLoops/lcalsBRaw.test:BM_TRAP_INT_RAW/5001
|
-1.34% |
87.674 |
86.499 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LCALS/SubsetBLambdaLoops/lcalsBLambda.test:BM_TRAP_INT_LAMBDA/171
|
-1.34% |
3.029 |
2.988 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetBLambdaLoops/lcalsBLambda.test:BM_TRAP_INT_LAMBDA/5001
|
-1.34% |
87.673 |
86.503 |
0.003 |
0.00% |
0.003 |
|
MicroBenchmarks/LCALS/SubsetBRawLoops/lcalsBRaw.test:BM_TRAP_INT_RAW/171
|
-1.33% |
3.028 |
2.988 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint8_t>/28
|
-1.33% |
107.962 |
106.529 |
0.019 |
-0.00% |
0.019 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_ENERGY_CALC_RAW/171
|
-1.32% |
15.823 |
15.614 |
0.019 |
0.05% |
0.019 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC32
|
-1.32% |
28.768 |
28.388 |
0.082 |
-0.51% |
0.082 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C/RSBench/rsbench
Profile
|
-1.32% |
1.222 |
1.206 |
0.003 |
-0.10% |
0.003 |
|
SingleSource/Benchmarks/Misc/flops-7
Profile
|
-1.28% |
7.631 |
7.533 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchVecWithRuntimeChecks4PointersDEqualsA/32
|
-1.27% |
48463.967 |
47846.223 |
1.700 |
-0.00% |
1.700 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC31
|
-1.25% |
28.782 |
28.423 |
0.066 |
-0.02% |
0.066 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC16
|
-1.23% |
51.940 |
51.303 |
0.005 |
-0.01% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_csa_with_cond_arith_novec_int64_t_
|
-1.22% |
693019.961 |
684575.055 |
554.048 |
-0.04% |
554.048 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC15
|
-1.21% |
51.938 |
51.308 |
0.003 |
-0.00% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC15
|
-1.21% |
51.938 |
51.308 |
0.002 |
0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC15
|
-1.21% |
51.937 |
51.309 |
0.018 |
-0.00% |
0.018 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1BigLoopWithReductionTC16
|
-1.21% |
51.935 |
51.307 |
0.002 |
-0.01% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC15
|
-1.21% |
51.937 |
51.309 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC15
|
-1.21% |
51.936 |
51.309 |
0.002 |
0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC15
|
-1.21% |
51.936 |
51.309 |
0.002 |
0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1BigLoopWithReductionTC15
|
-1.21% |
51.935 |
51.308 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC16
|
-1.20% |
51.936 |
51.311 |
0.003 |
0.00% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC16
|
-1.20% |
51.935 |
51.310 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC16
|
-1.20% |
51.934 |
51.310 |
0.005 |
-0.00% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC16
|
-1.20% |
51.934 |
51.311 |
0.021 |
-0.00% |
0.021 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC16
|
-1.17% |
51.916 |
51.309 |
0.002 |
0.00% |
0.002 |
|
MultiSource/Benchmarks/Bullet/bullet
Profile
|
-1.15% |
28.708 |
28.378 |
0.048 |
-0.35% |
0.048 |
|
MultiSource/Benchmarks/Ptrdist/ks/ks
Profile
|
-1.15% |
2.778 |
2.746 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopWithReductionTC32
|
-1.12% |
28.782 |
28.459 |
0.041 |
-0.03% |
0.041 |
|
MicroBenchmarks/LCALS/SubsetBLambdaLoops/lcalsBLambda.test:BM_MULADDSUB_LAMBDA/171
|
-1.11% |
1.090 |
1.078 |
0.002 |
0.17% |
0.002 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_HYDRO_1D_LAMBDA/44217
|
-1.08% |
185.387 |
183.382 |
0.643 |
-0.22% |
0.643 |
|
SingleSource/Benchmarks/Misc/richards_benchmark
Profile
|
-1.07% |
1.958 |
1.937 |
0.004 |
-0.20% |
0.004 |
|
SingleSource/Benchmarks/Misc/fbench
Profile
|
-1.05% |
6.131 |
6.067 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_BAND_LIN_EQ_RAW/5001
|
-1.03% |
22.350 |
22.119 |
0.079 |
0.02% |
0.079 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_IMP_HYDRO_2D_LAMBDA/171
|
-1.03% |
53.990 |
53.433 |
0.200 |
-0.24% |
0.200 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_ENERGY_CALC_LAMBDA/171
|
-1.02% |
15.684 |
15.524 |
0.057 |
-0.51% |
0.057 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC32
|
-1.02% |
28.777 |
28.485 |
0.055 |
0.09% |
0.055 |