|
MultiSource/Benchmarks/Trimaran/enc-md5/enc-md5
Profile
|
-76.67% |
12.643 |
2.950 |
0.000 |
0.00% |
0.000 |
|
SingleSource/Benchmarks/Shootout/Shootout-ary3
Profile
|
-47.09% |
0.985 |
0.521 |
0.000 |
0.00% |
0.000 |
|
MultiSource/Benchmarks/Ptrdist/yacr2/yacr2
Profile
|
-29.12% |
2.836 |
2.010 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_with_cond_arith_autovec_int64_t_
|
-27.66% |
1044878.546 |
755813.971 |
1864.275 |
0.00% |
1864.275 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_with_cond_arith_novec_int64_t_
|
-27.61% |
1044463.436 |
756054.322 |
1282.986 |
0.00% |
1282.986 |
|
SingleSource/Benchmarks/Adobe-C++/simple_types_constant_folding
Profile
|
-27.48% |
2.366 |
1.716 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_with_cond_arith_novec_int32_t_
|
-27.06% |
515829.116 |
376246.299 |
460.657 |
0.00% |
460.657 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_with_cond_arith_autovec_int32_t_
|
-26.77% |
515728.518 |
377649.078 |
71.960 |
0.00% |
71.960 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_with_cond_arith_novec_uint8_t_
|
-25.48% |
124916.399 |
93086.337 |
264.154 |
0.00% |
264.154 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_with_cond_arith_autovec_uint8_t_
|
-25.48% |
124920.394 |
93092.152 |
261.239 |
0.00% |
261.239 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_multiply_accumulate_runtime_checks_pass<3, double>
|
-25.00% |
15.017 |
11.263 |
0.000 |
0.00% |
0.000 |
|
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
|
-24.46% |
33.627 |
25.401 |
0.246 |
0.00% |
0.246 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint64_t>/256
|
-22.86% |
2110.073 |
1627.762 |
0.461 |
0.00% |
0.461 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint64_t>/256
|
-22.57% |
1073.749 |
831.455 |
0.027 |
0.00% |
0.027 |
|
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 |
0.002 |
0.00% |
0.002 |
|
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
|
-21.95% |
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 |
193.336 |
0.004 |
0.00% |
0.004 |
|
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 |
32.538 |
0.064 |
0.00% |
0.064 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint64_t>/16
|
-20.92% |
149.541 |
118.258 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint8_t>/16
|
-20.87% |
60.094 |
47.553 |
0.003 |
0.00% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint64_t>/28
|
-20.80% |
141.410 |
112.000 |
0.004 |
0.00% |
0.004 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_TRIDIAG_ELIM_LAMBDA/44217
|
-20.22% |
252.442 |
201.407 |
1.147 |
0.00% |
1.147 |
|
MultiSource/Benchmarks/SciMark2-C/scimark2
Profile
|
-19.84% |
166.680 |
133.617 |
0.032 |
0.00% |
0.032 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint64_t>/10
|
-19.74% |
95.109 |
76.334 |
0.002 |
0.00% |
0.002 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_GEN_LIN_RECUR_RAW/44217
|
-19.73% |
1300.488 |
1043.864 |
20.422 |
0.00% |
20.422 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint64_t>/16
|
-19.60% |
92.608 |
74.458 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_TRIDIAG_ELIM_RAW/44217
|
-19.11% |
251.350 |
203.327 |
0.549 |
0.00% |
0.549 |
|
MultiSource/Benchmarks/TSVC/Packing-dbl/Packing-dbl
Profile
|
-18.62% |
35.572 |
28.949 |
0.160 |
0.00% |
0.160 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_INT_PREDICT_RAW/5001
|
-18.48% |
1902.919 |
1551.303 |
119.386 |
0.00% |
119.386 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_TRIDIAG_ELIM_RAW/5001
|
-18.43% |
28.452 |
23.208 |
0.053 |
0.00% |
0.053 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_TRIDIAG_ELIM_LAMBDA/5001
|
-18.40% |
28.463 |
23.225 |
0.036 |
0.00% |
0.036 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint32_t_To_uint16_t_
|
-18.27% |
12911.816 |
10552.915 |
131.535 |
0.00% |
131.535 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint32_t_To_uint16_t_
|
-18.18% |
12919.660 |
10571.262 |
122.168 |
0.00% |
122.168 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint32_t_To_uint16_t_
|
-18.15% |
12907.981 |
10564.979 |
129.018 |
0.00% |
129.018 |
|
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
|
-17.97% |
18.304 |
15.014 |
0.008 |
0.00% |
0.008 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint16_t>/28
|
-17.92% |
104.498 |
85.776 |
0.016 |
0.00% |
0.016 |
|
SingleSource/Benchmarks/Shootout/Shootout-random
Profile
|
-17.85% |
7.013 |
5.761 |
0.000 |
0.00% |
0.000 |
|
SingleSource/Benchmarks/Shootout-C++/Shootout-C++-random
Profile
|
-17.82% |
7.017 |
5.767 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_multiply_accumulate_runtime_checks_pass<2, double>
|
-17.65% |
10.637 |
8.759 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint8_t>/16
|
-17.43% |
33.992 |
28.068 |
0.007 |
0.00% |
0.007 |
|
External/SPEC/CFP2017rate/510.parest_r/510.parest_r
Profile
|
-17.23% |
419.440 |
347.178 |
1.303 |
0.00% |
1.303 |
|
MultiSource/Benchmarks/TSVC/StatementReordering-dbl/StatementReordering-dbl
Profile
|
-17.18% |
24.683 |
20.442 |
0.328 |
0.00% |
0.328 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_csa_with_cond_arith_novec_int32_t_
|
-16.96% |
571704.349 |
474723.144 |
1821.860 |
0.00% |
1821.860 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_csa_with_cond_arith_autovec_int32_t_
|
-16.55% |
568560.244 |
474463.143 |
2096.048 |
0.00% |
2096.048 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint16_t>/16
|
-16.46% |
66.954 |
55.937 |
0.069 |
0.00% |
0.069 |
|
SingleSource/Benchmarks/Adobe-C++/loop_unroll
Profile
|
-15.94% |
27.321 |
22.965 |
0.004 |
0.00% |
0.004 |
|
MultiSource/Benchmarks/MiBench/telecomm-gsm/telecomm-gsm
Profile
|
-15.93% |
0.692 |
0.582 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint32_t>/10
|
-15.75% |
76.336 |
64.310 |
0.264 |
0.00% |
0.264 |
|
MicroBenchmarks/ImageProcessing/Blur/blur.test:BENCHMARK_GAUSSIAN_BLUR/256
|
-15.48% |
19528.547 |
16505.719 |
167.261 |
0.00% |
167.261 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint16_t>/10
|
-15.26% |
48.181 |
40.831 |
0.074 |
0.00% |
0.074 |
|
MultiSource/Benchmarks/mediabench/gsm/toast/toast
Profile
|
-15.07% |
0.090 |
0.076 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/ImageProcessing/Blur/blur.test:BENCHMARK_GAUSSIAN_BLUR/128
|
-15.03% |
4435.341 |
3768.551 |
0.077 |
0.00% |
0.077 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint32_t>/10
|
-14.64% |
51.308 |
43.798 |
0.001 |
0.00% |
0.001 |
|
MultiSource/Benchmarks/TSVC/Expansion-flt/Expansion-flt
Profile
|
-14.63% |
12.429 |
10.611 |
0.095 |
0.00% |
0.095 |
|
MicroBenchmarks/ImageProcessing/Blur/blur.test:BENCHMARK_GAUSSIAN_BLUR/512
|
-14.46% |
81786.722 |
69961.912 |
69.227 |
0.00% |
69.227 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C++/HPCCG/HPCCG
Profile
|
-14.32% |
4.652 |
3.986 |
0.043 |
0.00% |
0.043 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_multiply_accumulate_runtime_checks_fail<2, double>
|
-14.29% |
13.140 |
11.262 |
0.001 |
0.00% |
0.001 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C/miniAMR/miniAMR
Profile
|
-13.65% |
3.696 |
3.191 |
0.111 |
0.00% |
0.111 |
|
SingleSource/Benchmarks/Shootout/Shootout-matrix
Profile
|
-13.33% |
4.693 |
4.067 |
0.000 |
0.00% |
0.000 |
|
SingleSource/Benchmarks/Stanford/Bubblesort
Profile
|
-12.77% |
0.090 |
0.079 |
0.000 |
0.00% |
0.000 |
|
SingleSource/Benchmarks/Polybench/stencils/seidel-2d/seidel-2d
Profile
|
-12.65% |
118.438 |
103.458 |
0.212 |
0.00% |
0.212 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint64_t>/16
|
-12.60% |
53.215 |
46.509 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint16_t>/10
|
-12.58% |
52.248 |
45.674 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint16_t>/28
|
-12.58% |
52.247 |
45.674 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint16_t>/51
|
-12.58% |
52.248 |
45.675 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint16_t>/999
|
-12.58% |
52.248 |
45.675 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint16_t>/16
|
-12.58% |
52.246 |
45.674 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint16_t>/256
|
-12.58% |
52.246 |
45.675 |
0.002 |
0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint16_t>/28
|
-12.51% |
120.135 |
105.112 |
0.003 |
0.00% |
0.003 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C++/miniFE/miniFE
Profile
|
-12.34% |
17.849 |
15.646 |
0.046 |
0.00% |
0.046 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint16_t>/16
|
-12.28% |
89.163 |
78.213 |
0.002 |
0.00% |
0.002 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_GEN_LIN_RECUR_LAMBDA/5001
|
-12.26% |
87.236 |
76.541 |
2.936 |
0.00% |
2.936 |
|
MultiSource/Benchmarks/TSVC/StatementReordering-flt/StatementReordering-flt
Profile
|
-12.22% |
15.512 |
13.617 |
0.039 |
0.00% |
0.039 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint16_t>/10
|
-12.20% |
76.960 |
67.572 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint64_t>/10
|
-12.02% |
38.640 |
33.995 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint16_t>/51
|
-12.01% |
169.256 |
148.920 |
0.015 |
0.00% |
0.015 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint16_t>/256
|
-11.92% |
642.905 |
566.266 |
0.039 |
0.00% |
0.039 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint16_t_To_uint32_t_
|
-11.91% |
13480.798 |
11875.475 |
65.837 |
0.00% |
65.837 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint16_t>/16
|
-11.88% |
100.115 |
88.223 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint16_t>/10
|
-11.88% |
81.654 |
71.955 |
0.002 |
0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint16_t>/999
|
-11.87% |
2365.086 |
2084.233 |
0.082 |
0.00% |
0.082 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint16_t>/28
|
-11.87% |
155.494 |
137.033 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint16_t>/51
|
-11.87% |
266.237 |
234.631 |
0.005 |
0.00% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint16_t>/256
|
-11.86% |
1207.632 |
1064.348 |
0.010 |
0.00% |
0.010 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint16_t_To_uint32_t_
|
-11.81% |
13471.944 |
11880.622 |
65.168 |
0.00% |
65.168 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint32_t>/16
|
-11.81% |
50.371 |
44.423 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint32_t>/51
|
-11.81% |
50.371 |
44.423 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint32_t>/256
|
-11.81% |
50.371 |
44.424 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint32_t>/28
|
-11.81% |
50.370 |
44.423 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint32_t>/999
|
-11.81% |
50.370 |
44.424 |
0.004 |
0.00% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint16_t>/999
|
-11.78% |
4647.048 |
4099.423 |
0.130 |
0.00% |
0.130 |
|
MultiSource/Benchmarks/ASC_Sequoia/AMGmk/AMGmk
Profile
|
-11.73% |
43.459 |
38.360 |
0.017 |
0.00% |
0.017 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint32_t>/28
|
-11.67% |
112.632 |
99.485 |
0.004 |
0.00% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint16_t_To_uint32_t_
|
-11.60% |
13432.632 |
11874.527 |
66.574 |
0.00% |
66.574 |
|
External/SPEC/CFP2017rate/526.blender_r/526.blender_r
Profile
|
-11.57% |
879.226 |
777.487 |
2.026 |
0.00% |
2.026 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint64_t>/16
|
-11.56% |
32.544 |
28.781 |
0.000 |
0.00% |
0.000 |
|
MultiSource/Benchmarks/McCat/18-imp/imp
Profile
|
-11.53% |
0.212 |
0.188 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint8_t>/999
|
-11.47% |
4805.013 |
4254.060 |
0.378 |
0.00% |
0.378 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint8_t>/256
|
-11.39% |
1245.804 |
1103.911 |
0.004 |
0.00% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint8_t>/999
|
-11.39% |
2443.259 |
2165.024 |
0.066 |
0.00% |
0.066 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint8_t>/256
|
-11.38% |
662.339 |
586.959 |
0.009 |
0.00% |
0.009 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint64_t>/28
|
-11.37% |
27.530 |
24.401 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint64_t>/256
|
-11.37% |
27.530 |
24.401 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint64_t>/16
|
-11.36% |
27.530 |
24.402 |
0.000 |
0.00% |
0.000 |
|
MultiSource/Benchmarks/Rodinia/pathfinder/pathfinder
Profile
|
-11.23% |
1.372 |
1.218 |
0.009 |
0.00% |
0.009 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint8_t>/51
|
-11.13% |
272.488 |
242.165 |
0.028 |
0.00% |
0.028 |
|
SingleSource/Benchmarks/Misc/flops-4
Profile
|
-11.10% |
4.405 |
3.916 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint8_t>/999
|
-11.02% |
2847.792 |
2533.915 |
0.599 |
0.00% |
0.599 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint32_t>/256
|
-11.01% |
745.255 |
663.240 |
0.021 |
0.00% |
0.021 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint32_t>/999
|
-11.00% |
2846.931 |
2533.643 |
0.140 |
0.00% |
0.140 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint16_t>/256
|
-11.00% |
745.223 |
663.237 |
0.037 |
0.00% |
0.037 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint16_t>/999
|
-11.00% |
2848.455 |
2535.133 |
0.065 |
0.00% |
0.065 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint8_t>/51
|
-10.99% |
172.925 |
153.926 |
0.004 |
0.00% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint32_t>/999
|
-10.98% |
1453.725 |
1294.066 |
0.136 |
0.00% |
0.136 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/16
|
-10.92% |
194.627 |
173.383 |
0.017 |
0.00% |
0.017 |
|
External/SPEC/CFP2017rate/538.imagick_r/538.imagick_r
Profile
|
-10.90% |
272.224 |
242.550 |
0.661 |
0.00% |
0.661 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint8_t>/28
|
-10.88% |
157.975 |
140.794 |
0.008 |
0.00% |
0.008 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint32_t>/16
|
-10.86% |
83.532 |
74.457 |
0.002 |
0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint8_t>/256
|
-10.84% |
744.568 |
663.871 |
0.015 |
0.00% |
0.015 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint16_t>/999
|
-10.83% |
1451.132 |
1293.926 |
0.107 |
0.00% |
0.107 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint8_t>/256
|
-10.80% |
399.822 |
356.638 |
0.013 |
0.00% |
0.013 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint32_t>/256
|
-10.79% |
400.495 |
357.269 |
0.009 |
0.00% |
0.009 |
|
MultiSource/Benchmarks/TSVC/CrossingThresholds-flt/CrossingThresholds-flt
Profile
|
-10.79% |
11.078 |
9.883 |
0.055 |
0.00% |
0.055 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint16_t>/256
|
-10.78% |
400.440 |
357.256 |
0.011 |
0.00% |
0.011 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint8_t_To_uint32_t_
|
-10.78% |
12562.136 |
11208.427 |
21.964 |
0.00% |
21.964 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint8_t_To_uint32_t_
|
-10.76% |
12563.526 |
11212.052 |
11.065 |
0.00% |
11.065 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint8_t>/999
|
-10.73% |
1450.661 |
1295.051 |
0.696 |
0.00% |
0.696 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint8_t>/28
|
-10.71% |
122.638 |
109.498 |
0.026 |
0.00% |
0.026 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/32
|
-10.71% |
970.450 |
866.469 |
0.061 |
0.00% |
0.061 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/64
|
-10.65% |
4296.328 |
3838.565 |
3.761 |
0.00% |
3.761 |
|
SingleSource/Benchmarks/Misc/flops-3
Profile
|
-10.63% |
9.195 |
8.217 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint16_t>/51
|
-10.63% |
170.824 |
152.670 |
0.008 |
0.00% |
0.008 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint32_t>/51
|
-10.62% |
156.117 |
139.530 |
0.012 |
0.00% |
0.012 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint32_t>/51
|
-10.62% |
170.815 |
152.669 |
0.002 |
0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint8_t>/16
|
-10.55% |
124.514 |
111.372 |
0.003 |
0.00% |
0.003 |
|
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:benchForTruncOrZextVecWithAddInLoopFrom_uint8_t_To_uint32_t_
|
-10.40% |
12512.676 |
11211.195 |
20.730 |
0.00% |
20.730 |
|
MultiSource/Benchmarks/TSVC/Expansion-dbl/Expansion-dbl
Profile
|
-10.38% |
21.122 |
18.929 |
0.093 |
0.00% |
0.093 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint8_t>/999
|
-10.32% |
51.627 |
46.300 |
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 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint8_t>/28
|
-10.27% |
51.601 |
46.301 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint8_t>/51
|
-10.23% |
51.577 |
46.300 |
0.004 |
0.00% |
0.004 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/256
|
-10.16% |
75030.662 |
67407.662 |
39.389 |
0.00% |
39.389 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint32_t>/16
|
-10.14% |
92.607 |
83.217 |
0.004 |
0.00% |
0.004 |
|
SingleSource/Benchmarks/Stanford/FloatMM
Profile
|
-10.04% |
0.498 |
0.448 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_only_autovec_int64_t_
|
-9.94% |
1046245.511 |
942284.240 |
1425.708 |
0.00% |
1425.708 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint8_t>/51
|
-9.93% |
170.196 |
153.293 |
0.004 |
0.00% |
0.004 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_GEN_LIN_RECUR_LAMBDA/171
|
-9.93% |
2.158 |
1.943 |
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/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/128
|
-9.90% |
18337.432 |
16522.164 |
17.637 |
0.00% |
17.637 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint32_t>/28
|
-9.89% |
142.352 |
128.267 |
0.004 |
0.00% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint64_t>/999
|
-9.89% |
56.939 |
51.305 |
0.002 |
0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint64_t>/51
|
-9.89% |
56.940 |
51.307 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_only_novec_int64_t_
|
-9.82% |
1045645.924 |
942923.186 |
1110.525 |
0.00% |
1110.525 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint32_t>/999
|
-9.71% |
4194.518 |
3787.260 |
0.299 |
0.00% |
0.299 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint32_t>/51
|
-9.70% |
241.837 |
218.371 |
0.008 |
0.00% |
0.008 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint32_t>/51
|
-9.68% |
110.143 |
99.484 |
0.003 |
0.00% |
0.003 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_FIR_LAMBDA/44217
|
-9.66% |
780.201 |
704.846 |
14.381 |
0.00% |
14.381 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint32_t>/256
|
-9.64% |
581.001 |
524.992 |
0.032 |
0.00% |
0.032 |
|
SingleSource/Benchmarks/Adobe-C++/stepanov_abstraction
Profile
|
-9.62% |
12.696 |
11.475 |
0.000 |
0.00% |
0.000 |
|
MultiSource/Benchmarks/ASC_Sequoia/CrystalMk/CrystalMk
Profile
|
-9.60% |
14.480 |
13.090 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint8_t>/51
|
-9.60% |
110.746 |
100.114 |
0.006 |
0.00% |
0.006 |
|
SingleSource/Benchmarks/Misc/matmul_f64_4x4
Profile
|
-9.57% |
5.057 |
4.573 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/ImageProcessing/Blur/blur.test:BENCHMARK_GAUSSIAN_BLUR/1024
|
-9.51% |
431140.727 |
390150.394 |
242.835 |
0.00% |
242.835 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint32_t>/256
|
-9.49% |
1087.542 |
984.323 |
0.017 |
0.00% |
0.017 |
|
SingleSource/Benchmarks/BenchmarkGame/Large/fasta
Profile
|
-9.44% |
2.180 |
1.974 |
0.007 |
0.00% |
0.007 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint32_t>/999
|
-9.39% |
2131.884 |
1931.782 |
0.053 |
0.00% |
0.053 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC4
|
-9.36% |
10.354 |
9.385 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/16
|
-9.31% |
108.696 |
98.575 |
0.003 |
0.00% |
0.003 |
|
MultiSource/Benchmarks/TSVC/Searching-flt/Searching-flt
Profile
|
-9.26% |
17.074 |
15.492 |
0.000 |
0.00% |
0.000 |
|
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 |
68.198 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/32
|
-9.15% |
444.450 |
403.781 |
0.023 |
0.00% |
0.023 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/64
|
-9.11% |
1795.486 |
1631.937 |
9.968 |
0.00% |
9.968 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_FIR_LAMBDA/171
|
-9.04% |
2.440 |
2.220 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_FIR_RAW/171
|
-9.02% |
2.440 |
2.220 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchAutoVec<uint16_t>/127
|
-9.01% |
69.457 |
63.197 |
0.002 |
0.00% |
0.002 |
|
MultiSource/Benchmarks/TSVC/NodeSplitting-flt/NodeSplitting-flt
Profile
|
-8.99% |
17.421 |
15.855 |
0.058 |
0.00% |
0.058 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchAutoVec<uint16_t>/65
|
-8.98% |
48.805 |
44.424 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchAutoVec<uint8_t>/127
|
-8.96% |
41.923 |
38.168 |
0.002 |
0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchAutoVec<uint8_t>/65
|
-8.93% |
35.041 |
31.912 |
0.004 |
0.00% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_only_novec_int32_t_
|
-8.77% |
515135.584 |
469961.752 |
316.713 |
0.00% |
316.713 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/256
|
-8.70% |
29481.368 |
26917.312 |
12.204 |
0.00% |
12.204 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_only_autovec_int32_t_
|
-8.68% |
515323.384 |
470599.719 |
254.943 |
0.00% |
254.943 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_FIR_RAW/5001
|
-8.67% |
80.865 |
73.854 |
0.022 |
0.00% |
0.022 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_FIR_LAMBDA/5001
|
-8.67% |
80.851 |
73.845 |
0.005 |
0.00% |
0.005 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/128
|
-8.66% |
7415.789 |
6773.674 |
0.241 |
0.00% |
0.241 |
|
MultiSource/Benchmarks/TSVC/InductionVariable-dbl/InductionVariable-dbl
Profile
|
-8.60% |
19.083 |
17.441 |
0.154 |
0.00% |
0.154 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint64_t>/10
|
-8.57% |
21.899 |
20.022 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint16_t>/51
|
-8.30% |
109.500 |
100.414 |
0.044 |
0.00% |
0.044 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_FIR_RAW/44217
|
-8.27% |
760.807 |
697.853 |
16.110 |
0.00% |
16.110 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchAutoVec<uint32_t>/127
|
-8.21% |
124.514 |
114.297 |
0.101 |
0.00% |
0.101 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchAutoVec<uint32_t>/65
|
-8.20% |
76.337 |
70.079 |
0.002 |
0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint16_t>/256
|
-8.15% |
1005.482 |
923.515 |
0.016 |
0.00% |
0.016 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint64_t>/10
|
-8.15% |
30.662 |
28.163 |
0.003 |
0.00% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint16_t>/999
|
-8.15% |
3853.707 |
3539.638 |
0.599 |
0.00% |
0.599 |
|
MultiSource/Benchmarks/TSVC/Searching-dbl/Searching-dbl
Profile
|
-8.06% |
19.268 |
17.715 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint8_t>/10
|
-8.05% |
54.437 |
50.053 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint16_t>/999
|
-8.02% |
1937.310 |
1781.932 |
0.101 |
0.00% |
0.101 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint16_t_To_uint64_t_
|
-8.01% |
23815.476 |
21906.950 |
25.609 |
0.00% |
25.609 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint16_t>/256
|
-7.95% |
511.823 |
471.137 |
0.058 |
0.00% |
0.058 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint16_t_To_uint64_t_
|
-7.95% |
23779.783 |
21889.524 |
24.216 |
0.00% |
24.216 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint32_t>/999
|
-7.95% |
3925.745 |
3613.705 |
0.429 |
0.00% |
0.429 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint32_t>/999
|
-7.92% |
1978.157 |
1821.395 |
0.141 |
0.00% |
0.141 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint16_t_To_uint64_t_
|
-7.85% |
23755.880 |
21892.134 |
23.308 |
0.00% |
23.308 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC127
|
-7.84% |
113.042 |
104.174 |
0.364 |
0.00% |
0.364 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint32_t>/256
|
-7.79% |
1019.579 |
940.120 |
0.043 |
0.00% |
0.043 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC127
|
-7.72% |
112.967 |
104.243 |
0.385 |
0.00% |
0.385 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC127
|
-7.70% |
113.069 |
104.364 |
0.327 |
0.00% |
0.327 |
|
SingleSource/Benchmarks/Linpack/linpack-pc
Profile
|
-7.68% |
9.573 |
8.838 |
0.005 |
0.00% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint64_t>/51
|
-7.64% |
196.478 |
181.458 |
0.003 |
0.00% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint16_t_To_uint8_t_
|
-7.62% |
4721.120 |
4361.600 |
1.258 |
0.00% |
1.258 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC128
|
-7.61% |
113.095 |
104.488 |
0.246 |
0.00% |
0.246 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC127
|
-7.61% |
113.073 |
104.473 |
0.205 |
0.00% |
0.205 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint16_t_To_uint8_t_
|
-7.60% |
4721.142 |
4362.162 |
0.764 |
0.00% |
0.764 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint16_t_To_uint8_t_
|
-7.60% |
4721.231 |
4362.303 |
0.704 |
0.00% |
0.704 |
|
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 |
482.407 |
0.011 |
0.00% |
0.011 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC128
|
-7.56% |
112.971 |
104.430 |
0.231 |
0.00% |
0.231 |
|
SingleSource/Benchmarks/Misc-C++/Large/sphereflake
Profile
|
-7.50% |
19.566 |
18.098 |
0.003 |
0.00% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint16_t>/51
|
-7.47% |
209.623 |
193.967 |
0.003 |
0.00% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint16_t>/28
|
-7.46% |
117.653 |
108.870 |
0.003 |
0.00% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC128
|
-7.46% |
112.956 |
104.527 |
0.246 |
0.00% |
0.246 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC127
|
-7.44% |
112.882 |
104.485 |
0.204 |
0.00% |
0.204 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC128
|
-7.31% |
113.028 |
104.762 |
0.097 |
0.00% |
0.097 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_csa_with_cond_arith_autovec_uint8_t_
|
-7.29% |
534382.568 |
495410.325 |
63.604 |
0.00% |
63.604 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopFrom_uint32_t_To_uint8_t_
|
-7.29% |
10449.467 |
9687.467 |
56.340 |
0.00% |
56.340 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_csa_with_cond_arith_novec_uint8_t_
|
-7.29% |
534365.099 |
495407.553 |
10.346 |
0.00% |
10.346 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC128
|
-7.21% |
112.996 |
104.848 |
0.039 |
0.00% |
0.039 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint16_t>/10
|
-7.18% |
22.245 |
20.648 |
0.001 |
0.00% |
0.001 |
|
SingleSource/Benchmarks/Adobe-C++/stepanov_vector
Profile
|
-7.15% |
7.791 |
7.234 |
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 |
106.365 |
0.002 |
0.00% |
0.002 |
|
MultiSource/Benchmarks/TSVC/InductionVariable-flt/InductionVariable-flt
Profile
|
-7.13% |
10.035 |
9.319 |
0.071 |
0.00% |
0.071 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint16_t>/16
|
-7.07% |
29.623 |
27.530 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/harris/harris.test:BENCHMARK_HARRIS/2048/2048
|
-7.00% |
225384.680 |
209598.916 |
2606.885 |
0.00% |
2606.885 |
|
MultiSource/Benchmarks/TSVC/NodeSplitting-dbl/NodeSplitting-dbl
Profile
|
-6.98% |
23.405 |
21.770 |
0.140 |
0.00% |
0.140 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint32_t_To_uint8_t_
|
-6.96% |
14212.545 |
13222.785 |
22.639 |
0.00% |
22.639 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint32_t_To_uint8_t_
|
-6.93% |
14205.288 |
13220.669 |
22.030 |
0.00% |
22.030 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint32_t_To_uint8_t_
|
-6.90% |
14205.854 |
13225.278 |
24.974 |
0.00% |
24.974 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint32_t_To_uint8_t_
|
-6.88% |
10430.646 |
9712.805 |
15.787 |
0.00% |
15.787 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_ADI_LAMBDA/44217
|
-6.80% |
14964.056 |
13946.383 |
91.190 |
0.00% |
91.190 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C/CoMD/CoMD
Profile
|
-6.75% |
10.055 |
9.376 |
0.007 |
0.00% |
0.007 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint16_t>/28
|
-6.67% |
75.082 |
70.076 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint32_t_To_uint8_t_
|
-6.60% |
10436.688 |
9747.460 |
14.398 |
0.00% |
14.398 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint64_t_To_uint32_t_
|
-6.53% |
22078.253 |
20636.545 |
140.872 |
0.00% |
140.872 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC63
|
-6.52% |
57.568 |
53.813 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC63
|
-6.52% |
57.567 |
53.812 |
0.002 |
0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC63
|
-6.52% |
57.565 |
53.811 |
0.004 |
0.00% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC64
|
-6.52% |
57.566 |
53.812 |
0.002 |
0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC64
|
-6.52% |
57.563 |
53.810 |
0.003 |
0.00% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC63
|
-6.52% |
57.567 |
53.814 |
0.005 |
0.00% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC64
|
-6.52% |
57.564 |
53.811 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC63
|
-6.52% |
57.564 |
53.812 |
0.012 |
0.00% |
0.012 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC64
|
-6.52% |
57.564 |
53.813 |
0.004 |
0.00% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC64
|
-6.52% |
57.564 |
53.813 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint32_t>/51
|
-6.47% |
210.202 |
196.608 |
0.070 |
0.00% |
0.070 |
|
MultiSource/Benchmarks/Trimaran/enc-rc4/enc-rc4
Profile
|
-6.38% |
2.913 |
2.727 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_xor_runtime_checks_pass<16, int>
|
-6.37% |
29.407 |
27.533 |
0.002 |
0.00% |
0.002 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_runtime_checks_pass<16, int>
|
-6.35% |
39.419 |
36.916 |
0.002 |
0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint64_t_To_uint32_t_
|
-6.29% |
22063.599 |
20676.276 |
127.948 |
0.00% |
127.948 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC32
|
-6.25% |
30.034 |
28.156 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC32
|
-6.25% |
30.034 |
28.156 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC31
|
-6.25% |
30.035 |
28.156 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC32
|
-6.25% |
30.034 |
28.156 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint32_t>/10
|
-6.25% |
20.022 |
18.770 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC31
|
-6.25% |
30.034 |
28.156 |
0.002 |
0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC32
|
-6.25% |
30.035 |
28.157 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC32
|
-6.25% |
30.034 |
28.156 |
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:benchForIC4VW4LoopTC31
|
-6.25% |
30.033 |
28.156 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC31
|
-6.25% |
30.033 |
28.156 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint64_t>/16
|
-6.23% |
38.037 |
35.666 |
0.005 |
0.00% |
0.005 |
|
SingleSource/Benchmarks/Shootout-C++/Shootout-C++-fibo
Profile
|
-6.19% |
5.445 |
5.108 |
0.002 |
0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint8_t>/999
|
-6.17% |
5056.997 |
4744.857 |
0.350 |
0.00% |
0.350 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint64_t_To_uint32_t_
|
-6.13% |
22042.110 |
20691.094 |
114.388 |
0.00% |
114.388 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_ADI_LAMBDA/5001
|
-6.12% |
1701.071 |
1597.009 |
28.714 |
0.00% |
28.714 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint8_t>/256
|
-6.05% |
1307.724 |
1228.544 |
0.408 |
0.00% |
0.408 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint64_t>/51
|
-6.05% |
310.351 |
291.569 |
0.009 |
0.00% |
0.009 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint8_t>/999
|
-5.98% |
2542.862 |
2390.817 |
0.150 |
0.00% |
0.150 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_runtime_checks_fail<16, int>
|
-5.97% |
41.922 |
39.418 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint64_t>/999
|
-5.95% |
2804.568 |
2637.612 |
0.208 |
0.00% |
0.208 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint8_t>/256
|
-5.90% |
667.586 |
628.187 |
0.026 |
0.00% |
0.026 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint32_t>/28
|
-5.89% |
120.330 |
113.248 |
0.002 |
0.00% |
0.002 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_xor_runtime_checks_fail<16, int>
|
-5.88% |
31.910 |
30.033 |
0.000 |
0.00% |
0.000 |
|
SingleSource/Benchmarks/Shootout/Shootout-fib2
Profile
|
-5.81% |
5.409 |
5.094 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint64_t>/999
|
-5.73% |
5517.621 |
5201.286 |
0.420 |
0.00% |
0.420 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_FLOYD_DITHER/256
|
-5.69% |
1579.312 |
1489.419 |
1.083 |
0.00% |
1.083 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint8_t>/51
|
-5.68% |
266.770 |
251.607 |
0.083 |
0.00% |
0.083 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_FLOYD_DITHER/128
|
-5.47% |
402.074 |
380.071 |
0.638 |
0.00% |
0.638 |
|
SingleSource/Benchmarks/Shootout-C++/EH/Shootout-C++-except
Profile
|
-5.47% |
1.115 |
1.054 |
0.002 |
0.00% |
0.002 |
|
SingleSource/Benchmarks/Misc-C++/Large/ray
Profile
|
-5.46% |
9.837 |
9.300 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_GEN_LIN_RECUR_RAW/5001
|
-5.43% |
86.903 |
82.183 |
0.319 |
0.00% |
0.319 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint32_t>/51
|
-5.43% |
116.433 |
110.112 |
0.002 |
0.00% |
0.002 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_FLOYD_DITHER/512
|
-5.32% |
6092.953 |
5768.657 |
10.738 |
0.00% |
10.738 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_ADI_LAMBDA/171
|
-5.31% |
32.530 |
30.803 |
0.082 |
0.00% |
0.082 |
|
MultiSource/Benchmarks/MiBench/consumer-lame/consumer-lame
Profile
|
-5.29% |
0.682 |
0.646 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_PRESSURE_CALC_RAW/171
|
-5.26% |
1.540 |
1.459 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_PRESSURE_CALC_LAMBDA/171
|
-5.24% |
1.541 |
1.460 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint64_t>/999
|
-5.21% |
3006.073 |
2849.581 |
0.097 |
0.00% |
0.097 |
|
SingleSource/Benchmarks/Misc-C++/bigfib
Profile
|
-5.19% |
1.295 |
1.228 |
0.011 |
0.00% |
0.011 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint64_t>/999
|
-5.17% |
1529.178 |
1450.069 |
0.063 |
0.00% |
0.063 |
|
External/SPEC/CINT2017rate/525.x264_r/525.x264_r
Profile
|
-5.16% |
142.176 |
134.843 |
0.210 |
0.00% |
0.210 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIND_FIRST_MIN_RAW/5001
|
-5.15% |
42.137 |
39.967 |
0.009 |
0.00% |
0.009 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIND_FIRST_MIN_RAW/44217
|
-5.09% |
361.165 |
342.797 |
0.393 |
0.00% |
0.393 |
|
MultiSource/Benchmarks/MallocBench/cfrac/cfrac
Profile
|
-5.07% |
2.783 |
2.642 |
0.001 |
0.00% |
0.001 |
|
SingleSource/Benchmarks/Misc/flops
Profile
|
-5.03% |
14.144 |
13.432 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint8_t>/28
|
-5.03% |
149.558 |
142.035 |
0.002 |
0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint32_t>/28
|
-5.02% |
76.337 |
72.503 |
0.034 |
0.00% |
0.034 |
|
MultiSource/Benchmarks/TSVC/Reductions-flt/Reductions-flt
Profile
|
-4.96% |
2.830 |
2.690 |
0.015 |
0.00% |
0.015 |
|
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 |
|
MultiSource/Benchmarks/FreeBench/fourinarow/fourinarow
Profile
|
-4.85% |
0.677 |
0.644 |
0.001 |
0.00% |
0.001 |
|
SingleSource/Benchmarks/Misc/ReedSolomon
Profile
|
-4.81% |
22.059 |
20.999 |
0.003 |
0.00% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint16_t>/16
|
-4.80% |
49.949 |
47.553 |
0.002 |
0.00% |
0.002 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_ORDERED_DITHER/512/3
|
-4.79% |
36570.164 |
34819.262 |
49.750 |
0.00% |
49.750 |
|
MultiSource/Benchmarks/TSVC/IndirectAddressing-flt/IndirectAddressing-flt
Profile
|
-4.77% |
15.747 |
14.995 |
0.024 |
0.00% |
0.024 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_two_loads<uint8_t>/51
|
-4.77% |
39.420 |
37.541 |
0.002 |
0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_two_loads<uint8_t>/256
|
-4.77% |
39.419 |
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 |
|
SingleSource/Benchmarks/McGill/queens
Profile
|
-4.75% |
2.908 |
2.770 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_MAT_X_MAT_LAMBDA/171
|
-4.73% |
2483.986 |
2366.502 |
36.646 |
0.00% |
36.646 |
|
SingleSource/Benchmarks/BenchmarkGame/spectral-norm
Profile
|
-4.71% |
1.615 |
1.539 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_two_loads<uint32_t>/51
|
-4.70% |
40.046 |
38.166 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_two_loads<uint32_t>/256
|
-4.69% |
40.046 |
38.166 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_two_loads<uint16_t>/999
|
-4.69% |
40.046 |
38.167 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_two_loads<uint16_t>/256
|
-4.69% |
40.045 |
38.166 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_two_loads<uint16_t>/51
|
-4.69% |
40.046 |
38.166 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_two_loads<uint32_t>/999
|
-4.69% |
40.046 |
38.167 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_ORDERED_DITHER/128/3
|
-4.63% |
2292.263 |
2186.036 |
3.373 |
0.00% |
3.373 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint64_t>/51
|
-4.56% |
178.325 |
170.193 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_ORDERED_DITHER/256/3
|
-4.49% |
9301.952 |
8883.882 |
16.966 |
0.00% |
16.966 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint8_t>/51
|
-4.48% |
144.758 |
138.273 |
0.007 |
0.00% |
0.007 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_EOS_LAMBDA/5001
|
-4.47% |
41.005 |
39.174 |
0.130 |
0.00% |
0.130 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint64_t>/28
|
-4.46% |
53.057 |
50.691 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/ImageProcessing/BilateralFiltering/BilateralFilter.test:BENCHMARK_BILATERAL_FILTER/64/2
|
-4.44% |
2551.510 |
2438.136 |
8.236 |
0.00% |
8.236 |
|
SingleSource/Benchmarks/Misc/flops-1
Profile
|
-4.44% |
8.804 |
8.413 |
0.000 |
0.00% |
0.000 |
|
MultiSource/Benchmarks/PAQ8p/paq8p
Profile
|
-4.43% |
200.309 |
191.443 |
0.625 |
0.00% |
0.625 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_ORDERED_DITHER/512/8
|
-4.41% |
34768.085 |
33234.252 |
53.610 |
0.00% |
53.610 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_MAT_X_MAT_RAW/171
|
-4.34% |
2479.442 |
2371.920 |
10.063 |
0.00% |
10.063 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint8_t_To_uint64_t_
|
-4.34% |
22732.946 |
21747.170 |
103.088 |
0.00% |
103.088 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint8_t_To_uint64_t_
|
-4.27% |
22717.333 |
21747.481 |
28.081 |
0.00% |
28.081 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint8_t_To_uint64_t_
|
-4.26% |
22724.322 |
21756.660 |
26.194 |
0.00% |
26.194 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_ORDERED_DITHER/512/4
|
-4.26% |
34674.256 |
33198.174 |
35.474 |
0.00% |
35.474 |
|
MicroBenchmarks/ImageProcessing/AnisotropicDiffusion/AnisotropicDiffusion.test:BENCHMARK_ANISTROPIC_DIFFUSION/256
|
-4.25% |
171882.749 |
164583.895 |
207.204 |
0.00% |
207.204 |
|
SingleSource/Benchmarks/Misc/dt
Profile
|
-4.16% |
4.037 |
3.869 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/ImageProcessing/AnisotropicDiffusion/AnisotropicDiffusion.test:BENCHMARK_ANISTROPIC_DIFFUSION/128
|
-4.12% |
39484.789 |
37859.532 |
267.680 |
0.00% |
267.680 |
|
External/SPEC/CFP2017rate/511.povray_r/511.povray_r
Profile
|
-4.10% |
28.635 |
27.460 |
0.047 |
0.00% |
0.047 |
|
MicroBenchmarks/ImageProcessing/AnisotropicDiffusion/AnisotropicDiffusion.test:BENCHMARK_ANISTROPIC_DIFFUSION/64
|
-4.07% |
9198.691 |
8824.413 |
1.623 |
0.00% |
1.623 |
|
MultiSource/Benchmarks/Rodinia/hotspot/hotspot
Profile
|
-4.03% |
2.312 |
2.218 |
0.008 |
0.00% |
0.008 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_ORDERED_DITHER/128/4
|
-4.01% |
2170.766 |
2083.630 |
3.626 |
0.00% |
3.626 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint64_t_To_uint8_t_
|
-4.01% |
32343.677 |
31045.581 |
38.869 |
0.00% |
38.869 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint64_t_To_uint8_t_
|
-3.99% |
32335.807 |
31044.596 |
38.757 |
0.00% |
38.757 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C/SimpleMOC/SimpleMOC
Profile
|
-3.99% |
7.415 |
7.119 |
0.036 |
0.00% |
0.036 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_ORDERED_DITHER/128/8
|
-3.99% |
2173.775 |
2087.031 |
3.860 |
0.00% |
3.860 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint64_t_To_uint8_t_
|
-3.99% |
32336.834 |
31047.704 |
37.975 |
0.00% |
37.975 |
|
External/SPEC/CFP2017rate/544.nab_r/544.nab_r
Profile
|
-3.98% |
454.804 |
436.719 |
0.041 |
0.00% |
0.041 |
|
MicroBenchmarks/ImageProcessing/AnisotropicDiffusion/AnisotropicDiffusion.test:BENCHMARK_ANISTROPIC_DIFFUSION/32
|
-3.97% |
2014.654 |
1934.627 |
0.488 |
0.00% |
0.488 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_ORDERED_DITHER/256/8
|
-3.97% |
8861.897 |
8510.344 |
9.672 |
0.00% |
9.672 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_ORDERED_DITHER/256/4
|
-3.95% |
8849.763 |
8500.506 |
11.142 |
0.00% |
11.142 |
|
MicroBenchmarks/ImageProcessing/BilateralFiltering/BilateralFilter.test:BENCHMARK_BILATERAL_FILTER/32/2
|
-3.87% |
593.241 |
570.298 |
0.651 |
0.00% |
0.651 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC15
|
-3.85% |
16.269 |
15.642 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC15
|
-3.85% |
16.269 |
15.642 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC15
|
-3.85% |
16.268 |
15.642 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC15
|
-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/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC15
|
-3.85% |
16.268 |
15.642 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetBRawLoops/lcalsBRaw.test:BM_INIT3_RAW/171
|
-3.85% |
0.711 |
0.684 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC16
|
-3.85% |
16.269 |
15.643 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC16
|
-3.85% |
16.269 |
15.643 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC16
|
-3.84% |
16.269 |
15.643 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC16
|
-3.84% |
16.268 |
15.643 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_DEL_DOT_VEC_2D_LAMBDA/2
|
-3.84% |
2.775 |
2.668 |
0.000 |
0.00% |
0.000 |
|
SingleSource/Benchmarks/SmallPT/smallpt
Profile
|
-3.81% |
28.454 |
27.369 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_PIC_2D_RAW/171
|
-3.80% |
13.665 |
13.145 |
0.062 |
0.00% |
0.062 |
|
MultiSource/Benchmarks/FreeBench/distray/distray
Profile
|
-3.80% |
0.424 |
0.408 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint32_t>/10
|
-3.78% |
41.296 |
39.733 |
0.003 |
0.00% |
0.003 |
|
SingleSource/Benchmarks/Misc-C++/oopack_v1p8
Profile
|
-3.77% |
0.479 |
0.461 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/ImageProcessing/BilateralFiltering/BilateralFilter.test:BENCHMARK_BILATERAL_FILTER/16/2
|
-3.75% |
129.369 |
124.512 |
0.014 |
0.00% |
0.014 |
|
SingleSource/Benchmarks/Shootout-C++/Shootout-C++-lists
Profile
|
-3.75% |
20.762 |
19.984 |
0.063 |
0.00% |
0.063 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_DEL_DOT_VEC_2D_LAMBDA/1
|
-3.71% |
227.416 |
218.987 |
0.031 |
0.00% |
0.031 |
|
SingleSource/Benchmarks/Misc/flops-8
Profile
|
-3.70% |
1.973 |
1.900 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetBLambdaLoops/lcalsBLambda.test:BM_INIT3_LAMBDA/171
|
-3.68% |
0.711 |
0.685 |
0.005 |
0.00% |
0.005 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_HYDRO_2D_RAW/171
|
-3.64% |
261.421 |
251.897 |
1.808 |
0.00% |
1.808 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_COUPLE_RAW/2
|
-3.64% |
8.083 |
7.789 |
0.001 |
0.00% |
0.001 |
|
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 |
979.983 |
5.930 |
0.00% |
5.930 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint16_t>/10
|
-3.47% |
35.652 |
34.414 |
0.003 |
0.00% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint8_t>/28
|
-3.44% |
92.661 |
89.471 |
0.003 |
0.00% |
0.003 |
|
MultiSource/Benchmarks/mafft/pairlocalalign
Profile
|
-3.40% |
79.380 |
76.680 |
0.319 |
0.00% |
0.319 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_COUPLE_RAW/0
|
-3.36% |
6136.421 |
5930.478 |
4.044 |
0.00% |
4.044 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_DEL_DOT_VEC_2D_RAW/2
|
-3.32% |
2.760 |
2.668 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_DEL_DOT_VEC_2D_RAW/1
|
-3.32% |
226.576 |
219.062 |
0.081 |
0.00% |
0.081 |
|
External/SPEC/CFP2017rate/508.namd_r/508.namd_r
Profile
|
-3.30% |
187.364 |
181.176 |
0.224 |
0.00% |
0.224 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_ENERGY_CALC_RAW/5001
|
-3.28% |
474.039 |
458.509 |
2.883 |
0.00% |
2.883 |
|
MicroBenchmarks/LCALS/SubsetBLambdaLoops/lcalsBLambda.test:BM_IF_QUAD_LAMBDA/171
|
-3.27% |
4.243 |
4.105 |
0.000 |
0.00% |
0.000 |
|
SingleSource/Benchmarks/Dhrystone/fldry
Profile
|
-3.23% |
0.975 |
0.943 |
0.000 |
0.00% |
0.000 |
|
External/SPEC/CFP2017rate/519.lbm_r/519.lbm_r
Profile
|
-3.19% |
211.683 |
204.927 |
1.358 |
0.00% |
1.358 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint64_t_To_uint16_t_
|
-3.16% |
26726.819 |
25882.192 |
33.202 |
0.00% |
33.202 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_PIC_2D_LAMBDA/171
|
-3.16% |
13.738 |
13.304 |
0.062 |
0.00% |
0.062 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint64_t_To_uint16_t_
|
-3.14% |
26721.359 |
25882.760 |
41.732 |
0.00% |
41.732 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint8_t>/10
|
-3.13% |
20.022 |
19.396 |
0.000 |
0.00% |
0.000 |
|
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/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint64_t_To_uint16_t_
|
-3.12% |
26718.022 |
25885.404 |
30.603 |
0.00% |
30.603 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_HYDRO_2D_LAMBDA/171
|
-3.08% |
261.306 |
253.260 |
0.997 |
0.00% |
0.997 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_ORDERED_DITHER/512/2
|
-3.08% |
34278.585 |
33223.244 |
21.500 |
0.00% |
21.500 |
|
MicroBenchmarks/LCALS/SubsetBLambdaLoops/lcalsBLambda.test:BM_IF_QUAD_LAMBDA/5001
|
-2.96% |
131.334 |
127.443 |
0.139 |
0.00% |
0.139 |
|
SingleSource/Benchmarks/Misc/pi
Profile
|
-2.95% |
1.863 |
1.808 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_COUPLE_LAMBDA/2
|
-2.95% |
8.058 |
7.821 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_single_load<uint16_t>/256
|
-2.94% |
21.274 |
20.647 |
0.001 |
0.00% |
0.001 |
|
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>/51
|
-2.94% |
21.273 |
20.647 |
0.000 |
0.00% |
0.000 |
|
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/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC15
|
-2.94% |
21.274 |
20.649 |
0.066 |
0.00% |
0.066 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_COUPLE_LAMBDA/1
|
-2.94% |
1012.956 |
983.218 |
3.507 |
0.00% |
3.507 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_PIC_1D_RAW/171
|
-2.92% |
9.067 |
8.802 |
0.003 |
0.00% |
0.003 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_ORDERED_DITHER/128/2
|
-2.89% |
2142.135 |
2080.139 |
3.485 |
0.00% |
3.485 |
|
SingleSource/Benchmarks/Polybench/stencils/jacobi-2d/jacobi-2d
Profile
|
-2.85% |
41.791 |
40.600 |
0.097 |
0.00% |
0.097 |
|
SingleSource/Benchmarks/Misc/perlin
Profile
|
-2.85% |
8.412 |
8.173 |
0.000 |
0.00% |
0.000 |
|
SingleSource/Benchmarks/Misc/mandel
Profile
|
-2.84% |
3.300 |
3.206 |
0.000 |
0.00% |
0.000 |
|
MultiSource/Benchmarks/TSVC/ControlLoops-flt/ControlLoops-flt
Profile
|
-2.84% |
4.213 |
4.093 |
0.017 |
0.00% |
0.017 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_ORDERED_DITHER/256/2
|
-2.80% |
8733.359 |
8488.710 |
2.578 |
0.00% |
2.578 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint32_t>/16
|
-2.78% |
56.315 |
54.749 |
0.005 |
0.00% |
0.005 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_EOS_RAW/5001
|
-2.75% |
40.667 |
39.550 |
0.246 |
0.00% |
0.246 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_IMP_HYDRO_2D_RAW/5001
|
-2.74% |
1677.217 |
1631.251 |
1.784 |
0.00% |
1.784 |
|
MultiSource/Benchmarks/tramp3d-v4/tramp3d-v4
Profile
|
-2.74% |
1.011 |
0.983 |
0.003 |
0.00% |
0.003 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_ADI_RAW/171
|
-2.71% |
31.912 |
31.047 |
0.133 |
0.00% |
0.133 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_IMP_HYDRO_2D_RAW/171
|
-2.69% |
54.973 |
53.497 |
0.153 |
0.00% |
0.153 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC16
|
-2.67% |
21.214 |
20.647 |
0.002 |
0.00% |
0.002 |
|
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
|
-2.65% |
1.850 |
1.801 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint64_t>/256
|
-2.63% |
355.305 |
345.957 |
0.337 |
0.00% |
0.337 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_IMP_HYDRO_2D_RAW/44217
|
-2.61% |
14979.919 |
14589.478 |
51.133 |
0.00% |
51.133 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_COUPLE_LAMBDA/0
|
-2.59% |
6103.757 |
5945.604 |
6.589 |
0.00% |
6.589 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C++/PENNANT/PENNANT
Profile
|
-2.57% |
4.607 |
4.488 |
0.017 |
0.00% |
0.017 |
|
MultiSource/Applications/JM/lencod/lencod
Profile
|
-2.51% |
35.747 |
34.848 |
0.049 |
0.00% |
0.049 |
|
MultiSource/Benchmarks/ASCI_Purple/SMG2000/smg2000
Profile
|
-2.48% |
17.924 |
17.480 |
0.018 |
0.00% |
0.018 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_DEL_DOT_VEC_2D_LAMBDA/0
|
-2.48% |
1463.348 |
1427.113 |
1.891 |
0.00% |
1.891 |
|
SingleSource/Benchmarks/Shootout-C++/Shootout-C++-lists1
Profile
|
-2.44% |
1.003 |
0.979 |
0.005 |
0.00% |
0.005 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C++/CLAMR/CLAMR
Profile
|
-2.42% |
12.121 |
11.827 |
0.037 |
0.00% |
0.037 |
|
MicroBenchmarks/ImageProcessing/BilateralFiltering/BilateralFilter.test:BENCHMARK_BILATERAL_FILTER/64/4
|
-2.38% |
9542.475 |
9315.407 |
36.844 |
0.00% |
36.844 |
|
MicroBenchmarks/LCALS/SubsetBRawLoops/lcalsBRaw.test:BM_IF_QUAD_RAW/5001
|
-2.38% |
130.491 |
127.387 |
0.135 |
0.00% |
0.135 |
|
MicroBenchmarks/ImageProcessing/BilateralFiltering/BilateralFilter.test:BENCHMARK_BILATERAL_FILTER/32/4
|
-2.38% |
2077.330 |
2027.945 |
9.269 |
0.00% |
9.269 |
|
MicroBenchmarks/ImageProcessing/BilateralFiltering/BilateralFilter.test:BENCHMARK_BILATERAL_FILTER/16/4
|
-2.35% |
381.703 |
372.729 |
0.022 |
0.00% |
0.022 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_EOS_LAMBDA/171
|
-2.34% |
1.157 |
1.130 |
0.000 |
0.00% |
0.000 |
|
MultiSource/Benchmarks/Fhourstones-3.1/fhourstones3.1
Profile
|
-2.34% |
3.931 |
3.839 |
0.003 |
0.00% |
0.003 |
|
MicroBenchmarks/LCALS/SubsetBRawLoops/lcalsBRaw.test:BM_IF_QUAD_RAW/44217
|
-2.27% |
1336.622 |
1306.252 |
11.643 |
0.00% |
11.643 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_DEL_DOT_VEC_2D_RAW/0
|
-2.27% |
1461.622 |
1428.491 |
0.613 |
0.00% |
0.613 |
|
SingleSource/Benchmarks/Misc/whetstone
Profile
|
-2.26% |
2.955 |
2.888 |
0.000 |
0.00% |
0.000 |
|
MultiSource/Benchmarks/Olden/power/power
Profile
|
-2.19% |
3.744 |
3.662 |
0.000 |
0.00% |
0.000 |
|
SingleSource/Benchmarks/Misc/ffbench
Profile
|
-2.16% |
10.813 |
10.579 |
0.022 |
0.00% |
0.022 |
|
MultiSource/Benchmarks/7zip/7zip-benchmark
Profile
|
-2.15% |
30.569 |
29.910 |
0.045 |
0.00% |
0.045 |
|
MultiSource/Benchmarks/Rodinia/backprop/backprop
Profile
|
-2.13% |
2.316 |
2.266 |
0.016 |
0.00% |
0.016 |
|
MicroBenchmarks/LoopInterchange/LoopInterchange.test:BENCHMARK_LI1
|
-2.10% |
1598.161 |
1564.637 |
1.363 |
0.00% |
1.363 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC15
|
-2.06% |
21.081 |
20.648 |
0.006 |
0.00% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint8_t>/10
|
-2.02% |
48.905 |
47.917 |
0.023 |
0.00% |
0.023 |
|
MultiSource/Benchmarks/Bullet/bullet
Profile
|
-1.99% |
28.708 |
28.137 |
0.163 |
0.00% |
0.163 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC64
|
-1.97% |
165.326 |
162.071 |
0.004 |
0.00% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC127
|
-1.95% |
315.944 |
309.769 |
0.017 |
0.00% |
0.017 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_DISC_ORD_LAMBDA/171
|
-1.93% |
18.693 |
18.333 |
0.113 |
0.00% |
0.113 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC64
|
-1.92% |
165.245 |
162.069 |
0.011 |
0.00% |
0.011 |
|
SingleSource/Benchmarks/Misc/flops-5
Profile
|
-1.90% |
2.584 |
2.535 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1BigLoopWithReductionTC4
|
-1.86% |
33.791 |
33.162 |
0.002 |
0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC7
|
-1.86% |
33.789 |
33.161 |
0.002 |
0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC7
|
-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:benchForIC2VW4BigLoopWithReductionTC7
|
-1.86% |
33.790 |
33.162 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC7
|
-1.86% |
33.789 |
33.162 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC8
|
-1.86% |
33.789 |
33.161 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1BigLoopWithReductionTC7
|
-1.86% |
33.790 |
33.162 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC4
|
-1.86% |
33.790 |
33.163 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC4
|
-1.86% |
33.790 |
33.163 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC1
|
-1.86% |
33.789 |
33.162 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC1
|
-1.86% |
33.790 |
33.162 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC2
|
-1.86% |
33.789 |
33.162 |
0.002 |
0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC8
|
-1.86% |
33.790 |
33.163 |
0.003 |
0.00% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC7
|
-1.86% |
33.790 |
33.163 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC4
|
-1.86% |
33.788 |
33.161 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC2
|
-1.86% |
33.788 |
33.162 |
0.002 |
0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1BigLoopWithReductionTC8
|
-1.86% |
33.789 |
33.162 |
0.002 |
0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC2
|
-1.86% |
33.789 |
33.162 |
0.002 |
0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC3
|
-1.86% |
33.788 |
33.162 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC1
|
-1.85% |
33.788 |
33.161 |
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:benchForIC1VW1BigLoopWithReductionTC2
|
-1.85% |
33.788 |
33.161 |
0.003 |
0.00% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC8
|
-1.85% |
33.790 |
33.163 |
0.002 |
0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC1
|
-1.85% |
33.789 |
33.162 |
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:benchForIC2VW1BigLoopWithReductionTC4
|
-1.85% |
33.789 |
33.163 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC8
|
-1.85% |
33.789 |
33.163 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC3
|
-1.85% |
33.789 |
33.162 |
0.002 |
0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC3
|
-1.85% |
33.789 |
33.162 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1BigLoopWithReductionTC3
|
-1.85% |
33.789 |
33.163 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC4
|
-1.85% |
33.789 |
33.163 |
0.002 |
0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC2
|
-1.85% |
33.789 |
33.163 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC8
|
-1.85% |
33.789 |
33.163 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC2
|
-1.85% |
33.789 |
33.163 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC3
|
-1.85% |
33.788 |
33.162 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC4
|
-1.85% |
33.789 |
33.163 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC1
|
-1.85% |
33.788 |
33.162 |
0.010 |
0.00% |
0.010 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC2
|
-1.85% |
33.788 |
33.162 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1BigLoopWithReductionTC1
|
-1.85% |
33.788 |
33.163 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC3
|
-1.85% |
33.787 |
33.163 |
0.002 |
0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC1
|
-1.85% |
33.788 |
33.164 |
0.002 |
0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC128
|
-1.85% |
315.601 |
309.770 |
0.020 |
0.00% |
0.020 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC63
|
-1.85% |
165.117 |
162.068 |
0.007 |
0.00% |
0.007 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1BigLoopWithReductionTC63
|
-1.84% |
165.108 |
162.068 |
0.004 |
0.00% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC128
|
-1.83% |
315.552 |
309.768 |
0.015 |
0.00% |
0.015 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC63
|
-1.83% |
165.098 |
162.074 |
0.008 |
0.00% |
0.008 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC127
|
-1.83% |
315.535 |
309.764 |
0.016 |
0.00% |
0.016 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint8_t>/16
|
-1.83% |
68.382 |
67.132 |
0.059 |
0.00% |
0.059 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1BigLoopWithReductionTC64
|
-1.82% |
165.082 |
162.074 |
0.004 |
0.00% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC127
|
-1.82% |
315.514 |
309.772 |
0.013 |
0.00% |
0.013 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC128
|
-1.82% |
315.515 |
309.776 |
0.009 |
0.00% |
0.009 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC64
|
-1.82% |
165.068 |
162.067 |
0.004 |
0.00% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC64
|
-1.82% |
165.073 |
162.073 |
0.004 |
0.00% |
0.004 |
|
External/SPEC/CINT2017rate/541.leela_r/541.leela_r
Profile
|
-1.81% |
215.968 |
212.049 |
0.408 |
0.00% |
0.408 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint32_t>/28
|
-1.81% |
86.349 |
84.784 |
0.024 |
0.00% |
0.024 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_nested_cond_load_novec_int64_t_
|
-1.81% |
617130.196 |
605948.417 |
3962.666 |
0.00% |
3962.666 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1BigLoopWithReductionTC128
|
-1.80% |
315.438 |
309.769 |
0.040 |
0.00% |
0.040 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_IMP_HYDRO_2D_LAMBDA/44217
|
-1.79% |
14843.254 |
14576.885 |
52.327 |
0.00% |
52.327 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC63
|
-1.79% |
165.028 |
162.069 |
0.003 |
0.00% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC128
|
-1.79% |
315.422 |
309.773 |
0.031 |
0.00% |
0.031 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC128
|
-1.78% |
315.400 |
309.771 |
0.011 |
0.00% |
0.011 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC63
|
-1.78% |
164.999 |
162.067 |
0.007 |
0.00% |
0.007 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC127
|
-1.77% |
315.359 |
309.766 |
0.022 |
0.00% |
0.022 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC128
|
-1.77% |
315.359 |
309.769 |
0.017 |
0.00% |
0.017 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC64
|
-1.77% |
164.925 |
162.009 |
0.030 |
0.00% |
0.030 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC127
|
-1.76% |
315.353 |
309.792 |
0.009 |
0.00% |
0.009 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC127
|
-1.76% |
315.335 |
309.780 |
0.004 |
0.00% |
0.004 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_PIC_1D_LAMBDA/171
|
-1.76% |
8.951 |
8.794 |
0.032 |
0.00% |
0.032 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC63
|
-1.75% |
164.947 |
162.067 |
0.006 |
0.00% |
0.006 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, GreaterThanZero, Mid>
|
-1.74% |
30654.876 |
30121.347 |
2.039 |
0.00% |
2.039 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1BigLoopWithReductionTC127
|
-1.73% |
315.232 |
309.775 |
0.007 |
0.00% |
0.007 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_asin_novec_double_
|
-1.72% |
1184.843 |
1164.406 |
0.232 |
0.00% |
0.232 |
|
MultiSource/Applications/sgefa/sgefa
Profile
|
-1.71% |
0.642 |
0.631 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC63
|
-1.71% |
164.882 |
162.065 |
0.006 |
0.00% |
0.006 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_INT_PREDICT_RAW/171
|
-1.71% |
6.127 |
6.023 |
0.007 |
0.00% |
0.007 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_csa_with_cond_arith_novec_int64_t_
|
-1.70% |
693019.961 |
681228.125 |
2094.824 |
0.00% |
2094.824 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<63, LessThanZero, Last>
|
-1.70% |
4764.976 |
4684.114 |
0.780 |
0.00% |
0.780 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_IMP_HYDRO_2D_LAMBDA/5001
|
-1.70% |
1658.243 |
1630.121 |
4.765 |
0.00% |
4.765 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC64
|
-1.67% |
164.812 |
162.062 |
0.007 |
0.00% |
0.007 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_asin_autovec_double_
|
-1.64% |
1183.407 |
1163.943 |
0.332 |
0.00% |
0.332 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_csa_with_cond_arith_autovec_int64_t_
|
-1.58% |
693303.386 |
682331.657 |
1203.913 |
0.00% |
1203.913 |
|
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 |
|
SingleSource/Benchmarks/CoyoteBench/huffbench
Profile
|
-1.57% |
50.629 |
49.832 |
0.003 |
0.00% |
0.003 |
|
SingleSource/Benchmarks/Shootout-C++/Shootout-C++-sieve
Profile
|
-1.57% |
7.556 |
7.437 |
0.007 |
0.00% |
0.007 |
|
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 |
|
MultiSource/Benchmarks/TSVC/IndirectAddressing-dbl/IndirectAddressing-dbl
Profile
|
-1.56% |
18.523 |
18.235 |
0.012 |
0.00% |
0.012 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_INT_PREDICT_LAMBDA/171
|
-1.55% |
6.134 |
6.039 |
0.008 |
0.00% |
0.008 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_DISC_ORD_RAW/171
|
-1.54% |
18.778 |
18.488 |
0.064 |
0.00% |
0.064 |
|
MicroBenchmarks/LCALS/SubsetBLambdaLoops/lcalsBLambda.test:BM_MULADDSUB_LAMBDA/5001
|
-1.52% |
58.478 |
57.592 |
0.230 |
0.00% |
0.230 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_BAND_LIN_EQ_LAMBDA/5001
|
-1.49% |
22.519 |
22.184 |
0.113 |
0.00% |
0.113 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC31
|
-1.43% |
89.502 |
88.225 |
0.003 |
0.00% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC31
|
-1.42% |
89.498 |
88.225 |
0.006 |
0.00% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC31
|
-1.42% |
89.492 |
88.226 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1BigLoopWithReductionTC31
|
-1.41% |
89.492 |
88.228 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC32
|
-1.41% |
89.488 |
88.225 |
0.003 |
0.00% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC32
|
-1.41% |
89.489 |
88.226 |
0.002 |
0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1BigLoopWithReductionTC32
|
-1.41% |
89.488 |
88.225 |
0.002 |
0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC31
|
-1.41% |
89.485 |
88.227 |
0.003 |
0.00% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC32
|
-1.41% |
89.485 |
88.227 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<64, LessThanZero, Last>
|
-1.40% |
4169.969 |
4111.394 |
13.761 |
0.00% |
13.761 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC31
|
-1.40% |
89.483 |
88.227 |
0.003 |
0.00% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC32
|
-1.40% |
89.486 |
88.232 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC32
|
-1.40% |
89.480 |
88.228 |
0.005 |
0.00% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC31
|
-1.39% |
89.469 |
88.222 |
0.004 |
0.00% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC32
|
-1.37% |
89.451 |
88.227 |
0.005 |
0.00% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint8_t>/28
|
-1.36% |
107.962 |
106.494 |
0.029 |
0.00% |
0.029 |
|
MicroBenchmarks/LCALS/SubsetBRawLoops/lcalsBRaw.test:BM_TRAP_INT_RAW/5001
|
-1.35% |
87.674 |
86.492 |
0.003 |
0.00% |
0.003 |
|
MicroBenchmarks/LCALS/SubsetBLambdaLoops/lcalsBLambda.test:BM_TRAP_INT_LAMBDA/44217
|
-1.34% |
774.715 |
764.296 |
0.023 |
0.00% |
0.023 |
|
MicroBenchmarks/LCALS/SubsetBRawLoops/lcalsBRaw.test:BM_TRAP_INT_RAW/44217
|
-1.34% |
774.728 |
764.322 |
0.029 |
0.00% |
0.029 |
|
MicroBenchmarks/LCALS/SubsetBLambdaLoops/lcalsBLambda.test:BM_TRAP_INT_LAMBDA/5001
|
-1.34% |
87.673 |
86.498 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetBLambdaLoops/lcalsBLambda.test:BM_TRAP_INT_LAMBDA/171
|
-1.34% |
3.029 |
2.988 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetBRawLoops/lcalsBRaw.test:BM_TRAP_INT_RAW/171
|
-1.34% |
3.028 |
2.988 |
0.000 |
0.00% |
0.000 |
|
SingleSource/Benchmarks/Shootout-C++/Shootout-C++-hash2
Profile
|
-1.33% |
8.512 |
8.399 |
0.019 |
0.00% |
0.019 |
|
SingleSource/Benchmarks/Misc/flops-7
Profile
|
-1.28% |
7.631 |
7.533 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchVecWithRuntimeChecks4PointersDEqualsA/32
|
-1.28% |
48463.967 |
47844.440 |
1.836 |
0.00% |
1.836 |
|
MicroBenchmarks/LCALS/SubsetBLambdaLoops/lcalsBLambda.test:BM_MULADDSUB_LAMBDA/171
|
-1.27% |
1.090 |
1.076 |
0.004 |
0.00% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC31
|
-1.23% |
28.782 |
28.428 |
0.059 |
0.00% |
0.059 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC16
|
-1.22% |
51.940 |
51.309 |
0.002 |
0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC15
|
-1.21% |
51.938 |
51.307 |
0.002 |
0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC15
|
-1.21% |
51.937 |
51.307 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC15
|
-1.21% |
51.936 |
51.307 |
0.002 |
0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC15
|
-1.21% |
51.938 |
51.310 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC15
|
-1.21% |
51.936 |
51.308 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC16
|
-1.21% |
51.936 |
51.308 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC16
|
-1.21% |
51.934 |
51.307 |
0.003 |
0.00% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC15
|
-1.21% |
51.937 |
51.309 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1BigLoopWithReductionTC15
|
-1.21% |
51.935 |
51.308 |
0.004 |
0.00% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC16
|
-1.21% |
51.935 |
51.307 |
0.004 |
0.00% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1BigLoopWithReductionTC16
|
-1.20% |
51.935 |
51.311 |
0.002 |
0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC16
|
-1.20% |
51.934 |
51.312 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC32
|
-1.20% |
28.777 |
28.433 |
0.070 |
0.00% |
0.070 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC16
|
-1.17% |
51.916 |
51.308 |
0.004 |
0.00% |
0.004 |
|
MultiSource/Benchmarks/Ptrdist/ks/ks
Profile
|
-1.15% |
2.778 |
2.746 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1LoopWithReductionTC31
|
-1.14% |
28.779 |
28.450 |
0.032 |
0.00% |
0.032 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopWithReductionTC32
|
-1.10% |
28.782 |
28.466 |
0.052 |
0.00% |
0.052 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC32
|
-1.10% |
28.771 |
28.456 |
0.024 |
0.00% |
0.024 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_BAND_LIN_EQ_RAW/5001
|
-1.06% |
22.350 |
22.114 |
0.090 |
0.00% |
0.090 |
|
SingleSource/Benchmarks/Misc/fbench
Profile
|
-1.04% |
6.131 |
6.067 |
0.000 |
0.00% |
0.000 |
|
External/SPEC/CINT2017rate/520.omnetpp_r/520.omnetpp_r
Profile
|
-1.04% |
595.651 |
589.463 |
1.374 |
0.00% |
1.374 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1LoopWithReductionTC32
|
-1.04% |
28.783 |
28.485 |
0.033 |
0.00% |
0.033 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC31
|
-1.01% |
28.779 |
28.490 |
0.030 |
0.00% |
0.030 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_PLANCKIAN_RAW/44217
|
-1.01% |
4368.082 |
4324.164 |
8.262 |
0.00% |
8.262 |