|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint64_t_To_uint32_t_
|
-49.85% |
35313.629 |
17708.620 |
371.948 |
3.32% |
371.948 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint64_t_To_uint8_t_
|
-48.73% |
37062.972 |
19000.562 |
24.276 |
0.06% |
24.276 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint64_t_To_uint16_t_
|
-48.40% |
35680.148 |
18409.812 |
179.933 |
-0.72% |
179.933 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C/miniGMG/miniGMG
Profile
|
-47.99% |
9.190 |
4.780 |
0.452 |
1.76% |
0.452 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint16_t_To_uint64_t_
|
-44.05% |
18675.093 |
10448.170 |
3.007 |
0.01% |
3.007 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_DIFF_PREDICT_RAW/44217
|
-42.05% |
23299.816 |
13501.273 |
381.325 |
-0.21% |
381.325 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_DIFF_PREDICT_LAMBDA/44217
|
-41.58% |
23102.783 |
13495.856 |
377.892 |
0.09% |
377.892 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_DIFF_PREDICT_RAW/5001
|
-41.32% |
2574.764 |
1510.986 |
102.681 |
-0.36% |
102.681 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint8_t_To_uint64_t_
|
-41.07% |
17799.596 |
10489.416 |
36.683 |
-0.40% |
36.683 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint64_t_To_uint32_t_
|
-40.59% |
38155.754 |
22668.417 |
33.366 |
0.14% |
33.366 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_DIFF_PREDICT_LAMBDA/5001
|
-39.58% |
2509.400 |
1516.243 |
32.005 |
0.58% |
32.005 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/32
|
-36.70% |
1396.116 |
883.795 |
0.047 |
-0.01% |
0.047 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/64
|
-36.68% |
6182.288 |
3914.760 |
0.549 |
-0.01% |
0.549 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/16
|
-36.63% |
279.469 |
177.105 |
0.004 |
0.00% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint32_t_To_uint64_t_
|
-36.60% |
22724.955 |
14407.410 |
754.263 |
-1.48% |
754.263 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/256
|
-36.20% |
107153.285 |
68361.100 |
26.490 |
-0.10% |
26.490 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/128
|
-36.16% |
26271.873 |
16773.144 |
9.807 |
-0.06% |
9.807 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint64_t_To_uint16_t_
|
-34.10% |
28949.218 |
19076.518 |
37.516 |
-0.03% |
37.516 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint64_t_To_uint8_t_
|
-34.04% |
30110.831 |
19861.143 |
10.577 |
0.04% |
10.577 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, EqZero, None>
|
-31.24% |
20511.394 |
14103.602 |
0.502 |
-0.01% |
0.502 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_PIC_2D_RAW/5001
|
-30.28% |
1078.372 |
751.867 |
75.585 |
-18.11% |
75.585 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIRST_DIFF_LAMBDA/44217
|
-29.67% |
144.820 |
101.847 |
1.512 |
0.25% |
1.512 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIRST_DIFF_RAW/44217
|
-29.28% |
142.491 |
100.763 |
0.791 |
-0.38% |
0.791 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint64_t_To_uint16_t_
|
-28.85% |
25897.435 |
18425.326 |
49.849 |
0.06% |
49.849 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC128
|
-27.99% |
1292.822 |
930.965 |
4.050 |
-0.54% |
4.050 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint32_t_To_uint8_t_
|
-27.95% |
13469.278 |
9704.281 |
19.388 |
-0.21% |
19.388 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC64
|
-27.35% |
653.610 |
474.837 |
1.329 |
-0.17% |
1.329 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC32
|
-27.07% |
333.930 |
243.542 |
0.501 |
0.11% |
0.501 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC128
|
-26.86% |
557.537 |
407.771 |
0.035 |
-0.01% |
0.035 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC16
|
-26.53% |
173.787 |
127.688 |
0.349 |
-0.02% |
0.349 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_HYDRO_2D_RAW/44217
|
-25.72% |
84652.625 |
62884.193 |
8286.074 |
6.57% |
8286.074 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC64
|
-25.59% |
291.827 |
217.159 |
0.026 |
-0.00% |
0.026 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint64_t_To_uint8_t_
|
-24.30% |
27222.887 |
20607.478 |
34.659 |
0.06% |
34.659 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, EqZero, None>
|
-23.98% |
16023.286 |
12181.234 |
0.880 |
-0.00% |
0.880 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC128
|
-23.21% |
603.966 |
463.785 |
0.013 |
-0.00% |
0.013 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC32
|
-23.19% |
158.873 |
122.038 |
0.044 |
0.00% |
0.044 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC128
|
-23.11% |
603.957 |
464.392 |
0.024 |
-0.01% |
0.024 |
|
MicroBenchmarks/ImageProcessing/Blur/blur.test:BENCHMARK_boxBlurKernel/1024
|
-22.73% |
30148.993 |
23295.529 |
43.778 |
-0.49% |
43.778 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC64
|
-22.35% |
313.505 |
243.439 |
0.006 |
-0.00% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC127
|
-22.17% |
615.213 |
478.801 |
0.015 |
-0.00% |
0.015 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC64
|
-22.15% |
313.505 |
244.052 |
0.012 |
0.00% |
0.012 |
|
SingleSource/Benchmarks/Adobe-C++/loop_unroll
Profile
|
-22.06% |
3.107 |
2.422 |
0.002 |
-0.07% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC127
|
-21.97% |
615.198 |
480.054 |
0.017 |
-0.00% |
0.017 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_HYDRO_2D_RAW/5001
|
-21.65% |
8796.368 |
6891.855 |
633.483 |
6.49% |
633.483 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint8_t_To_uint32_t_
|
-21.65% |
6582.228 |
5157.125 |
4.374 |
-0.34% |
4.374 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_PIC_2D_LAMBDA/44217
|
-21.57% |
10963.150 |
8598.188 |
614.768 |
-0.24% |
614.768 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint16_t_To_uint32_t_
|
-21.55% |
7100.968 |
5570.605 |
1.899 |
0.03% |
1.899 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint16_t_To_uint64_t_
|
-21.55% |
13208.286 |
10362.223 |
12.189 |
-0.00% |
12.189 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_only_autovec_uint8_t_
|
-21.36% |
182351.670 |
143398.048 |
89.092 |
0.01% |
89.092 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIND_FIRST_MIN_LAMBDA/171
|
-21.28% |
1.501 |
1.182 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIND_FIRST_MIN_LAMBDA/44217
|
-21.25% |
389.578 |
306.783 |
0.214 |
0.00% |
0.214 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC127
|
-20.94% |
275.455 |
217.787 |
1.657 |
-0.43% |
1.657 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC32
|
-20.82% |
168.326 |
133.275 |
0.011 |
-0.01% |
0.011 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIND_FIRST_MIN_LAMBDA/5001
|
-20.71% |
45.257 |
35.886 |
0.234 |
0.28% |
0.234 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC128
|
-20.63% |
274.741 |
218.058 |
1.329 |
-0.97% |
1.329 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC32
|
-20.45% |
168.333 |
133.910 |
0.010 |
-0.00% |
0.010 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC63
|
-20.42% |
324.785 |
258.453 |
0.019 |
0.00% |
0.019 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC63
|
-20.04% |
324.799 |
259.703 |
0.012 |
0.00% |
0.012 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC63
|
-19.89% |
149.912 |
120.097 |
4.039 |
-0.97% |
4.039 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC127
|
-19.67% |
640.493 |
514.528 |
0.083 |
-0.04% |
0.083 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC16
|
-19.30% |
92.280 |
74.474 |
0.035 |
-0.01% |
0.035 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint16_t_To_uint8_t_
|
-19.09% |
3818.115 |
3089.306 |
0.196 |
-0.00% |
0.196 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC64
|
-19.00% |
148.631 |
120.389 |
2.860 |
-0.12% |
2.860 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint32_t_To_uint8_t_
|
-18.98% |
13900.786 |
11262.733 |
68.611 |
-0.80% |
68.611 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_csa_with_cond_arith_autovec_uint8_t_
|
-18.89% |
210082.683 |
170403.984 |
20.689 |
-0.01% |
20.689 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_VOL3D_CALC_LAMBDA/2
|
-18.80% |
8.757 |
7.111 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_VOL3D_CALC_RAW/2
|
-18.79% |
8.757 |
7.111 |
0.000 |
0.01% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIRST_SUM_LAMBDA/44217
|
-18.61% |
167.087 |
135.994 |
0.106 |
-0.01% |
0.106 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIRST_SUM_RAW/44217
|
-18.61% |
166.336 |
135.384 |
0.356 |
-0.25% |
0.356 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint32_t_To_uint16_t_
|
-18.49% |
13807.248 |
11254.158 |
9.858 |
0.08% |
9.858 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint64_t_To_uint32_t_
|
-18.47% |
27051.416 |
22055.496 |
31.505 |
-0.11% |
31.505 |
|
MultiSource/Benchmarks/MiBench/automotive-bitcount/automotive-bitcount
Profile
|
-18.35% |
0.124 |
0.101 |
0.000 |
0.03% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC16
|
-18.30% |
95.740 |
78.215 |
0.003 |
-0.00% |
0.003 |
|
MultiSource/Benchmarks/Trimaran/enc-pc1/enc-pc1
Profile
|
-18.11% |
1.104 |
0.904 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_with_cond_arith_novec_uint8_t_
|
-17.85% |
745760.891 |
612679.164 |
221.544 |
0.00% |
221.544 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_PIC_2D_LAMBDA/5001
|
-17.74% |
1105.490 |
909.357 |
39.971 |
0.11% |
39.971 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC16
|
-17.64% |
95.739 |
78.846 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC31
|
-17.42% |
179.585 |
148.306 |
0.007 |
0.00% |
0.007 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC31
|
-17.40% |
86.114 |
71.129 |
2.388 |
-2.51% |
2.388 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_with_cond_arith_novec_int32_t_
|
-17.40% |
740190.367 |
611389.412 |
471.267 |
-0.17% |
471.267 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC32
|
-17.33% |
85.325 |
70.542 |
2.530 |
-0.83% |
2.530 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC4
|
-17.29% |
17.520 |
14.491 |
0.010 |
0.03% |
0.010 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC128
|
-17.24% |
570.579 |
472.185 |
0.031 |
-0.01% |
0.031 |
|
MultiSource/Benchmarks/MiBench/security-rijndael/security-rijndael
Profile
|
-17.16% |
0.335 |
0.277 |
0.000 |
0.23% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC64
|
-17.08% |
297.710 |
246.849 |
0.021 |
-0.01% |
0.021 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC32
|
-16.83% |
161.394 |
134.227 |
0.014 |
0.01% |
0.014 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC31
|
-16.72% |
179.581 |
149.563 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint8_t_To_uint64_t_
|
-16.52% |
13065.090 |
10907.291 |
69.430 |
-0.12% |
69.430 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC16
|
-16.36% |
93.125 |
77.891 |
0.012 |
-0.02% |
0.012 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_VOL3D_CALC_LAMBDA/0
|
-16.29% |
1267.594 |
1061.157 |
1.194 |
0.01% |
1.194 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_VOL3D_CALC_LAMBDA/1
|
-16.18% |
260.168 |
218.079 |
0.044 |
-0.04% |
0.044 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_VOL3D_CALC_RAW/1
|
-16.15% |
260.130 |
218.131 |
0.136 |
0.01% |
0.136 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_VOL3D_CALC_RAW/0
|
-16.01% |
1265.194 |
1062.622 |
0.888 |
0.13% |
0.888 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_HYDRO_1D_LAMBDA/171
|
-15.87% |
0.442 |
0.372 |
0.000 |
0.01% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_HYDRO_1D_RAW/171
|
-15.83% |
0.442 |
0.372 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint16_t_To_uint32_t_
|
-15.66% |
7462.263 |
6293.520 |
0.788 |
-0.01% |
0.788 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, EqZero, First>
|
-15.40% |
16670.947 |
14104.174 |
0.356 |
-0.00% |
0.356 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_no_runtime_checks_needed<16, int>
|
-15.39% |
24.403 |
20.648 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, EqZero, Mid>
|
-15.37% |
16666.201 |
14105.016 |
0.458 |
0.00% |
0.458 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, EqZero, Last>
|
-15.35% |
16667.200 |
14109.067 |
0.960 |
-0.00% |
0.960 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC8
|
-15.35% |
58.764 |
49.745 |
0.002 |
0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC4
|
-15.08% |
113.088 |
96.035 |
0.489 |
-0.55% |
0.489 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint32_t_To_uint8_t_
|
-14.94% |
10595.349 |
9012.077 |
25.404 |
0.01% |
25.404 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC127
|
-14.81% |
605.768 |
516.074 |
0.011 |
0.00% |
0.011 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC8
|
-14.74% |
59.450 |
50.685 |
0.005 |
0.00% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC128
|
-14.57% |
1103.306 |
942.609 |
0.845 |
-0.00% |
0.845 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC127
|
-14.51% |
1095.285 |
936.328 |
0.148 |
-0.00% |
0.148 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint8_t_To_uint16_t_
|
-14.47% |
3756.543 |
3213.147 |
9.429 |
-0.55% |
9.429 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC64
|
-14.31% |
562.307 |
481.848 |
0.018 |
0.00% |
0.018 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC63
|
-14.27% |
554.742 |
475.596 |
0.029 |
0.00% |
0.029 |
|
SingleSource/Benchmarks/Misc/salsa20
Profile
|
-14.12% |
15.384 |
13.212 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_with_cond_arith_autovec_int64_t_
|
-14.01% |
791606.520 |
680736.838 |
2143.966 |
0.09% |
2143.966 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_csa_with_cond_arith_autovec_int32_t_
|
-13.92% |
396356.005 |
341174.542 |
1114.172 |
-0.12% |
1114.172 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint32_t_To_uint8_t_
|
-13.88% |
11129.319 |
9584.542 |
47.100 |
0.14% |
47.100 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC8
|
-13.86% |
51.939 |
44.741 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC1
|
-13.85% |
51.934 |
44.739 |
0.003 |
-0.00% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC7
|
-13.85% |
51.935 |
44.741 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC2
|
-13.85% |
51.934 |
44.742 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC32
|
-13.85% |
291.986 |
251.552 |
0.037 |
0.00% |
0.037 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC4
|
-13.85% |
51.934 |
44.742 |
0.002 |
0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC3
|
-13.85% |
51.935 |
44.743 |
0.001 |
0.00% |
0.001 |
|
External/SPEC/CFP2017rate/508.namd_r/508.namd_r
Profile
|
-13.73% |
223.577 |
192.883 |
0.228 |
-0.04% |
0.228 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC8
|
-13.69% |
59.450 |
51.310 |
0.002 |
0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC31
|
-13.66% |
284.084 |
245.285 |
0.015 |
-0.01% |
0.015 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, EqZero, Last>
|
-13.63% |
14104.915 |
12181.934 |
0.281 |
0.00% |
0.281 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, EqZero, First>
|
-13.63% |
14103.013 |
12181.072 |
0.675 |
-0.01% |
0.675 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, EqZero, Mid>
|
-13.62% |
14103.223 |
12181.830 |
0.632 |
-0.01% |
0.632 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint64_t_To_uint8_t_
|
-13.59% |
22047.281 |
19050.786 |
10.646 |
0.16% |
10.646 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC8
|
-13.52% |
23.153 |
20.022 |
0.001 |
0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint32_t_To_uint16_t_
|
-13.46% |
12837.101 |
11108.943 |
15.256 |
-0.00% |
15.256 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_with_cond_arith_novec_int64_t_
|
-13.44% |
788035.947 |
682090.763 |
537.433 |
-0.09% |
537.433 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC63
|
-13.42% |
374.427 |
324.185 |
0.125 |
-0.01% |
0.125 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC16
|
-13.23% |
51.941 |
45.067 |
0.402 |
-0.47% |
0.402 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC8
|
-13.17% |
23.778 |
20.648 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC16
|
-13.10% |
156.964 |
136.409 |
0.008 |
-0.01% |
0.008 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC128
|
-13.07% |
81.345 |
70.710 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint8_t_To_uint16_t_
|
-12.95% |
4541.860 |
3953.560 |
0.276 |
-0.01% |
0.276 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC15
|
-12.87% |
107.003 |
93.237 |
0.003 |
-0.00% |
0.003 |
|
SingleSource/Benchmarks/Shootout-C++/Shootout-C++-matrix
Profile
|
-12.71% |
2.508 |
2.190 |
0.000 |
0.01% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC63
|
-12.66% |
332.823 |
290.678 |
0.013 |
-0.01% |
0.013 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC15
|
-12.54% |
148.810 |
130.154 |
0.008 |
-0.01% |
0.008 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint16_t_To_uint8_t_
|
-12.40% |
4742.772 |
4154.632 |
0.222 |
0.00% |
0.222 |
|
MicroBenchmarks/ImageProcessing/Dilate/Dilate.test:BENCHMARK_DILATE/1024
|
-12.02% |
7110.540 |
6256.131 |
203.397 |
-4.10% |
203.397 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC8
|
-11.81% |
89.401 |
78.845 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC2
|
-11.77% |
21.276 |
18.771 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC15
|
-11.71% |
107.009 |
94.481 |
0.010 |
-0.01% |
0.010 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint32_t_To_uint16_t_
|
-11.67% |
9904.984 |
8749.314 |
97.933 |
1.12% |
97.933 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC15
|
-11.45% |
51.939 |
45.992 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC16
|
-11.39% |
33.164 |
29.386 |
0.011 |
-0.03% |
0.011 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC4
|
-11.12% |
22.527 |
20.022 |
0.002 |
-0.01% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC4
|
-11.12% |
22.527 |
20.022 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC3
|
-11.11% |
22.526 |
20.023 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_with_cond_arith_autovec_uint8_t_
|
-10.96% |
295250.544 |
262890.031 |
100.133 |
-0.01% |
100.133 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC7
|
-10.73% |
81.312 |
72.590 |
0.004 |
-0.00% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC4
|
-10.61% |
41.302 |
36.918 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC4
|
-10.53% |
23.779 |
21.274 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC64
|
-10.47% |
53.816 |
48.182 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/16
|
-10.18% |
115.465 |
103.716 |
0.013 |
-0.00% |
0.013 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_INT_PREDICT_RAW/44217
|
-10.16% |
9049.170 |
8129.827 |
35.770 |
-0.56% |
35.770 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint8_t_To_uint16_t_
|
-10.14% |
5850.367 |
5257.090 |
0.242 |
0.01% |
0.242 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_only_autovec_int64_t_
|
-10.14% |
333280.792 |
299484.232 |
689.075 |
-0.56% |
689.075 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/64
|
-10.08% |
1913.314 |
1720.378 |
2.009 |
-0.04% |
2.009 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC4
|
-10.07% |
55.663 |
50.060 |
0.003 |
0.00% |
0.003 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/32
|
-9.99% |
473.003 |
425.771 |
0.027 |
0.00% |
0.027 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/256
|
-9.94% |
31449.377 |
28324.828 |
18.100 |
0.03% |
18.100 |
|
SingleSource/Benchmarks/Misc-C++/oopack_v1p8
Profile
|
-9.93% |
0.519 |
0.467 |
0.000 |
0.06% |
0.000 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/128
|
-9.82% |
7917.293 |
7140.066 |
3.480 |
-0.10% |
3.480 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC8
|
-9.77% |
25.657 |
23.152 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC8
|
-9.76% |
25.656 |
23.152 |
0.003 |
-0.00% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC127
|
-9.71% |
101.879 |
91.982 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC7
|
-9.61% |
32.539 |
29.411 |
0.001 |
0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC7
|
-9.53% |
26.282 |
23.777 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC7
|
-9.53% |
26.282 |
23.778 |
0.000 |
-0.01% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_with_cond_arith_autovec_int32_t_
|
-9.52% |
940875.108 |
851320.355 |
60.317 |
-0.00% |
60.317 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC32
|
-9.42% |
53.193 |
48.181 |
0.001 |
0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC31
|
-9.40% |
196.470 |
177.998 |
0.018 |
-0.01% |
0.018 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC8
|
-9.32% |
26.912 |
24.404 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_HYDRO_1D_RAW/5001
|
-9.24% |
16.686 |
15.144 |
0.446 |
-8.61% |
0.446 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_DEL_DOT_VEC_2D_LAMBDA/1
|
-9.19% |
287.120 |
260.734 |
0.116 |
-0.02% |
0.116 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_DEL_DOT_VEC_2D_RAW/1
|
-9.16% |
286.991 |
260.701 |
0.028 |
-0.03% |
0.028 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC4
|
-9.09% |
41.299 |
37.543 |
0.002 |
-0.00% |
0.002 |
|
MultiSource/Benchmarks/FreeBench/pifft/pifft
Profile
|
-9.02% |
0.359 |
0.326 |
0.000 |
-0.63% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC7
|
-8.89% |
28.160 |
25.655 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC7
|
-8.78% |
354.707 |
323.549 |
1.340 |
-0.05% |
1.340 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_DEL_DOT_VEC_2D_RAW/2
|
-8.71% |
3.510 |
3.204 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_DEL_DOT_VEC_2D_LAMBDA/2
|
-8.70% |
3.510 |
3.204 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC16
|
-8.62% |
36.293 |
33.166 |
0.002 |
0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint16_t_To_uint64_t_
|
-8.62% |
20143.016 |
18407.497 |
172.359 |
-0.67% |
172.359 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint64_t_To_uint16_t_
|
-8.61% |
18983.917 |
17349.830 |
349.283 |
-4.52% |
349.283 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint16_t_To_uint8_t_
|
-8.61% |
6815.821 |
6229.144 |
0.996 |
-0.03% |
0.996 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC8
|
-8.52% |
29.411 |
26.907 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_runtime_checks_pass<4, int>
|
-8.25% |
16.708 |
15.330 |
0.002 |
0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC2
|
-8.20% |
38.171 |
35.040 |
0.004 |
-0.01% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC64
|
-8.08% |
93.242 |
85.709 |
0.008 |
-0.01% |
0.008 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint8_t_To_uint32_t_
|
-7.96% |
12778.752 |
11761.285 |
28.340 |
-0.15% |
28.340 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC3
|
-7.90% |
47.558 |
43.802 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC16
|
-7.84% |
31.913 |
29.409 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC16
|
-7.84% |
31.911 |
29.410 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC32
|
-7.82% |
40.050 |
36.918 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_DEL_DOT_VEC_2D_RAW/0
|
-7.78% |
1800.857 |
1660.676 |
3.396 |
0.00% |
3.396 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC127
|
-7.76% |
2426.612 |
2238.359 |
9.029 |
1.06% |
9.029 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC15
|
-7.70% |
32.539 |
30.035 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC15
|
-7.69% |
32.538 |
30.037 |
0.001 |
0.00% |
0.001 |
|
MultiSource/Benchmarks/VersaBench/beamformer/beamformer
Profile
|
-7.61% |
5.201 |
4.805 |
0.002 |
0.00% |
0.002 |
|
MultiSource/Benchmarks/McCat/12-IOtest/iotest
Profile
|
-7.61% |
1.825 |
1.686 |
0.027 |
-0.09% |
0.027 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_DEL_DOT_VEC_2D_LAMBDA/0
|
-7.51% |
1791.999 |
1657.334 |
4.128 |
0.01% |
4.128 |
|
MultiSource/Benchmarks/Trimaran/enc-md5/enc-md5
Profile
|
-7.49% |
3.506 |
3.243 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_xor_no_runtime_checks_needed<16, int>
|
-7.42% |
16.896 |
15.643 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint16_t_To_uint64_t_
|
-7.41% |
24986.152 |
23134.896 |
76.745 |
-0.16% |
76.745 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_DIFF_PREDICT_LAMBDA/171
|
-7.28% |
11.986 |
11.113 |
0.111 |
-0.01% |
0.111 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint32_t_To_uint64_t_
|
-7.26% |
17196.059 |
15946.984 |
59.819 |
0.35% |
59.819 |
|
MultiSource/Applications/lambda-0.1.3/lambda
Profile
|
-7.24% |
15.870 |
14.721 |
0.010 |
-0.02% |
0.010 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC128
|
-7.22% |
173.330 |
160.823 |
0.008 |
-0.01% |
0.008 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint8_t>/127
|
-7.20% |
138.913 |
128.905 |
0.009 |
-0.00% |
0.009 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIND_FIRST_MIN_RAW/171
|
-7.19% |
1.497 |
1.389 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_HYDRO_2D_RAW/171
|
-7.14% |
88.626 |
82.296 |
0.487 |
0.34% |
0.487 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_PRESSURE_CALC_RAW/5001
|
-7.14% |
44.600 |
41.416 |
0.815 |
0.52% |
0.815 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC7
|
-7.09% |
70.713 |
65.698 |
0.004 |
-0.00% |
0.004 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_PRESSURE_CALC_LAMBDA/5001
|
-7.07% |
43.974 |
40.864 |
0.834 |
-5.16% |
0.834 |
|
SingleSource/Benchmarks/Misc/pi
Profile
|
-7.02% |
1.782 |
1.657 |
0.000 |
-0.01% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_HYDRO_2D_LAMBDA/171
|
-7.01% |
88.658 |
82.446 |
0.250 |
0.16% |
0.250 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC15
|
-6.94% |
45.051 |
41.927 |
0.003 |
0.00% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC15
|
-6.91% |
54.442 |
50.682 |
0.004 |
-0.01% |
0.004 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_DIFF_PREDICT_RAW/171
|
-6.84% |
11.933 |
11.116 |
0.033 |
0.02% |
0.033 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC1
|
-6.79% |
88.984 |
82.946 |
0.530 |
-0.43% |
0.530 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC31
|
-6.72% |
74.464 |
69.460 |
0.013 |
0.01% |
0.013 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC63
|
-6.56% |
114.514 |
107.000 |
0.005 |
0.00% |
0.005 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_xor_runtime_checks_pass<16, int>
|
-6.52% |
28.783 |
26.906 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_xor_runtime_checks_fail<16, int>
|
-6.52% |
28.783 |
26.907 |
0.002 |
-0.00% |
0.002 |
|
SingleSource/Benchmarks/Misc/flops-6
Profile
|
-6.46% |
1.312 |
1.228 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC127
|
-6.43% |
194.608 |
182.095 |
0.366 |
-0.01% |
0.366 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC63
|
-6.43% |
74.223 |
69.454 |
0.002 |
-0.01% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_only_autovec_int32_t_
|
-6.42% |
181119.283 |
169487.369 |
447.379 |
-0.09% |
447.379 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIND_FIRST_MIN_RAW/5001
|
-6.42% |
45.339 |
42.429 |
0.126 |
-0.37% |
0.126 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C++/miniFE/miniFE
Profile
|
-6.42% |
15.969 |
14.944 |
0.064 |
-0.02% |
0.064 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC128
|
-6.38% |
68.804 |
64.416 |
0.015 |
-0.01% |
0.015 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC15
|
-6.35% |
39.422 |
36.917 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint32_t_To_uint64_t_
|
-6.35% |
21450.888 |
20088.999 |
67.616 |
-0.01% |
67.616 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_BAND_LIN_EQ_LAMBDA/171
|
-6.33% |
0.366 |
0.343 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_BAND_LIN_EQ_RAW/171
|
-6.32% |
0.366 |
0.343 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint16_t>/127
|
-6.30% |
138.912 |
130.158 |
0.003 |
0.01% |
0.003 |
|
SingleSource/Benchmarks/Misc-C++/Large/sphereflake
Profile
|
-6.19% |
20.002 |
18.764 |
0.005 |
-0.04% |
0.005 |
|
External/SPEC/CFP2017rate/538.imagick_r/538.imagick_r
Profile
|
-6.19% |
292.080 |
274.010 |
0.702 |
-0.18% |
0.702 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC16
|
-6.17% |
40.674 |
38.167 |
0.002 |
-0.01% |
0.002 |
|
MultiSource/Benchmarks/MiBench/telecomm-gsm/telecomm-gsm
Profile
|
-6.04% |
0.663 |
0.623 |
0.000 |
-0.11% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint8_t>/65
|
-5.92% |
95.111 |
89.485 |
0.006 |
0.00% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint32_t>/127
|
-5.88% |
138.286 |
130.160 |
0.003 |
0.00% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC127
|
-5.68% |
68.292 |
64.411 |
0.018 |
-0.05% |
0.018 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC15
|
-5.68% |
44.431 |
41.906 |
0.849 |
-1.66% |
0.849 |
|
MultiSource/Benchmarks/Rodinia/hotspot/hotspot
Profile
|
-5.67% |
2.036 |
1.921 |
0.006 |
-0.04% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC16
|
-5.66% |
33.163 |
31.286 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC32
|
-5.64% |
44.429 |
41.923 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC32
|
-5.64% |
44.427 |
41.923 |
0.002 |
0.00% |
0.002 |
|
SingleSource/Benchmarks/Polybench/stencils/jacobi-2d/jacobi-2d
Profile
|
-5.63% |
32.224 |
30.409 |
0.078 |
0.32% |
0.078 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint8_t_To_uint16_t_
|
-5.62% |
3633.347 |
3429.150 |
0.053 |
0.02% |
0.053 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC31
|
-5.58% |
45.064 |
42.550 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC31
|
-5.56% |
45.052 |
42.548 |
0.002 |
-0.00% |
0.002 |
|
MultiSource/Benchmarks/SciMark2-C/scimark2
Profile
|
-5.51% |
107.639 |
101.705 |
0.025 |
-0.00% |
0.025 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC31
|
-5.47% |
916.985 |
866.852 |
6.173 |
0.22% |
6.173 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint32_t>/999
|
-5.39% |
696.521 |
658.948 |
0.045 |
-0.00% |
0.045 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIND_FIRST_MIN_RAW/44217
|
-5.39% |
389.585 |
368.595 |
0.246 |
-0.01% |
0.246 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC7
|
-5.32% |
70.719 |
66.953 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopWithReductionTC1
|
-5.26% |
11.888 |
11.263 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_PIC_2D_LAMBDA/171
|
-5.23% |
13.498 |
12.792 |
0.042 |
0.10% |
0.042 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint32_t>/999
|
-5.23% |
1365.037 |
1293.652 |
0.016 |
-0.00% |
0.016 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC32
|
-5.14% |
24.405 |
23.151 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC31
|
-5.13% |
24.404 |
23.151 |
0.015 |
-0.01% |
0.015 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC32
|
-5.12% |
24.402 |
23.152 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC31
|
-5.12% |
24.403 |
23.153 |
0.014 |
0.01% |
0.014 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC32
|
-5.11% |
61.321 |
58.187 |
0.006 |
0.00% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC15
|
-5.10% |
128.256 |
121.711 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC31
|
-5.06% |
241.230 |
229.027 |
0.021 |
-0.01% |
0.021 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_PIC_2D_RAW/171
|
-4.98% |
13.539 |
12.864 |
0.047 |
-0.03% |
0.047 |
|
SingleSource/Benchmarks/Stanford/Puzzle
Profile
|
-4.85% |
0.241 |
0.230 |
0.000 |
0.68% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint32_t>/256
|
-4.82% |
364.169 |
346.627 |
0.027 |
-0.00% |
0.027 |
|
SingleSource/Benchmarks/Misc/oourafft
Profile
|
-4.71% |
15.093 |
14.382 |
0.056 |
-0.82% |
0.056 |
|
MultiSource/Benchmarks/TSVC/Recurrences-dbl/Recurrences-dbl
Profile
|
-4.67% |
10.357 |
9.874 |
0.091 |
1.35% |
0.091 |
|
SingleSource/Benchmarks/Misc/revertBits
Profile
|
-4.66% |
0.641 |
0.611 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_ENERGY_CALC_LAMBDA/5001
|
-4.63% |
438.042 |
417.772 |
5.825 |
-1.28% |
5.825 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_runtime_checks_fail<16, int>
|
-4.60% |
54.439 |
51.933 |
0.002 |
-0.01% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint16_t>/65
|
-4.60% |
95.115 |
90.738 |
0.006 |
-0.00% |
0.006 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_runtime_checks_pass<16, int>
|
-4.59% |
54.438 |
51.936 |
0.002 |
0.00% |
0.002 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_ENERGY_CALC_LAMBDA/171
|
-4.53% |
14.248 |
13.602 |
0.016 |
-0.02% |
0.016 |
|
MicroBenchmarks/ImageProcessing/Dilate/Dilate.test:BENCHMARK_DILATE/256
|
-4.52% |
1067.252 |
1018.997 |
3.862 |
-0.38% |
3.862 |
|
External/SPEC/CFP2017rate/519.lbm_r/519.lbm_r
Profile
|
-4.49% |
200.678 |
191.668 |
1.688 |
-0.26% |
1.688 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC31
|
-4.47% |
70.083 |
66.951 |
0.006 |
-0.01% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopWithReductionTC2
|
-4.47% |
13.766 |
13.151 |
0.000 |
0.04% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_ENERGY_CALC_RAW/171
|
-4.40% |
14.241 |
13.614 |
0.026 |
-0.01% |
0.026 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC3
|
-4.36% |
14.393 |
13.765 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC8
|
-4.36% |
14.392 |
13.765 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC4
|
-4.35% |
14.393 |
13.766 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC2
|
-4.35% |
14.392 |
13.765 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC8
|
-4.35% |
14.393 |
13.766 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC7
|
-4.35% |
14.392 |
13.766 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC4
|
-4.35% |
14.392 |
13.766 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC3
|
-4.35% |
14.392 |
13.766 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC1
|
-4.35% |
14.392 |
13.766 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC15
|
-4.35% |
14.392 |
13.767 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC2
|
-4.35% |
14.391 |
13.766 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC16
|
-4.34% |
14.392 |
13.766 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC7
|
-4.34% |
14.391 |
13.766 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC1
|
-4.34% |
14.393 |
13.768 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC15
|
-4.34% |
14.392 |
13.767 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC127
|
-4.30% |
3128.822 |
2994.157 |
19.110 |
-0.13% |
19.110 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC128
|
-4.26% |
2974.265 |
2847.496 |
17.641 |
-0.13% |
17.641 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint64_t>/999
|
-4.25% |
1811.241 |
1734.346 |
0.105 |
0.02% |
0.105 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint8_t_To_uint64_t_
|
-4.21% |
23483.830 |
22495.754 |
31.220 |
-0.03% |
31.220 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint64_t>/999
|
-4.15% |
3594.644 |
3445.315 |
0.296 |
0.00% |
0.296 |
|
SingleSource/Benchmarks/Misc/flops-5
Profile
|
-4.15% |
2.021 |
1.937 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint64_t>/256
|
-4.09% |
935.580 |
897.298 |
0.073 |
0.00% |
0.073 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC31
|
-4.03% |
61.945 |
59.451 |
0.003 |
0.00% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC16
|
-4.00% |
31.289 |
30.038 |
0.292 |
0.00% |
0.292 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_only_autovec_uint8_t_
|
-3.97% |
96157.793 |
92338.861 |
12.412 |
-0.00% |
12.412 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint32_t>/65
|
-3.97% |
94.488 |
90.736 |
0.002 |
0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC32
|
-3.96% |
63.198 |
60.695 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint32_t>/256
|
-3.95% |
221.503 |
212.757 |
0.006 |
0.00% |
0.006 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_PRESSURE_CALC_LAMBDA/44217
|
-3.93% |
498.539 |
478.927 |
0.925 |
-0.44% |
0.925 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_PRESSURE_CALC_RAW/44217
|
-3.93% |
502.197 |
482.465 |
0.576 |
-0.26% |
0.576 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint32_t_To_uint16_t_
|
-3.88% |
9879.809 |
9496.920 |
20.468 |
0.03% |
20.468 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<31, EqZero, First>
|
-3.85% |
3346.347 |
3217.627 |
2.616 |
-0.16% |
2.616 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC3
|
-3.85% |
16.269 |
15.643 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint16_t_To_uint8_t_
|
-3.75% |
2878.208 |
2770.263 |
0.238 |
0.00% |
0.238 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC63
|
-3.73% |
43.294 |
41.679 |
0.012 |
0.06% |
0.012 |
|
SingleSource/Benchmarks/Shootout/Shootout-matrix
Profile
|
-3.68% |
3.863 |
3.721 |
0.000 |
-0.00% |
0.000 |
|
MultiSource/Benchmarks/nbench/nbench
Profile
|
-3.68% |
6.127 |
5.901 |
0.004 |
-0.01% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint64_t>/256
|
-3.66% |
514.395 |
495.582 |
0.037 |
-0.00% |
0.037 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_runtime_checks_fail<4, int>
|
-3.64% |
15.908 |
15.329 |
0.001 |
-0.00% |
0.001 |
|
External/SPEC/CFP2017rate/544.nab_r/544.nab_r
Profile
|
-3.62% |
477.880 |
460.573 |
0.160 |
-0.02% |
0.160 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC64
|
-3.62% |
69.461 |
66.948 |
0.003 |
-0.01% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_nested_cond_load_novec_int32_t_
|
-3.60% |
645149.252 |
621952.134 |
861.127 |
-0.03% |
861.127 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC63
|
-3.59% |
70.092 |
67.575 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC64
|
-3.59% |
69.457 |
66.965 |
0.001 |
0.01% |
0.001 |
|
MultiSource/Benchmarks/TSVC/ControlLoops-dbl/ControlLoops-dbl
Profile
|
-3.58% |
11.019 |
10.624 |
0.116 |
-2.15% |
0.116 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC63
|
-3.58% |
70.083 |
67.576 |
0.003 |
-0.00% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC63
|
-3.54% |
1737.110 |
1675.544 |
9.997 |
0.03% |
9.997 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC63
|
-3.47% |
1643.724 |
1586.611 |
9.291 |
-0.08% |
9.291 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC64
|
-3.46% |
43.175 |
41.681 |
0.028 |
0.05% |
0.028 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC31
|
-3.46% |
60.276 |
58.192 |
0.002 |
-0.01% |
0.002 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<32, EqZero, Last>
|
-3.38% |
7052.998 |
6814.691 |
71.487 |
-0.46% |
71.487 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC32
|
-3.35% |
750.660 |
725.512 |
2.174 |
-0.22% |
2.174 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint64_t_To_uint32_t_
|
-3.32% |
19292.425 |
18651.823 |
77.278 |
-0.09% |
77.278 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC31
|
-3.31% |
93.853 |
90.750 |
0.024 |
-0.04% |
0.024 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint16_t_To_uint8_t_
|
-3.22% |
4517.211 |
4371.786 |
2.769 |
0.01% |
2.769 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC31
|
-3.18% |
1514.949 |
1466.787 |
7.963 |
1.00% |
7.963 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint16_t>/999
|
-3.17% |
515.023 |
498.720 |
0.015 |
0.00% |
0.015 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC64
|
-3.14% |
1490.531 |
1443.725 |
8.788 |
-0.18% |
8.788 |
|
MicroBenchmarks/ImageProcessing/Dilate/Dilate.test:BENCHMARK_DILATE/512
|
-3.14% |
3584.064 |
3471.651 |
8.409 |
-0.68% |
8.409 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1BigLoopWithReductionTC1
|
-3.13% |
20.025 |
19.399 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchVecWithRuntimeChecks4PointersDBeforeA/1000
|
-3.09% |
5019862.993 |
4864895.819 |
600.210 |
-0.00% |
600.210 |
|
SingleSource/Benchmarks/Shootout/Shootout-lists
Profile
|
-3.06% |
11.312 |
10.966 |
0.002 |
-0.01% |
0.002 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_BAND_LIN_EQ_LAMBDA/5001
|
-3.04% |
20.799 |
20.167 |
0.232 |
0.31% |
0.232 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_FLOYD_DITHER/128
|
-3.03% |
439.467 |
426.168 |
1.237 |
0.09% |
1.237 |
|
MultiSource/Applications/JM/lencod/lencod
Profile
|
-2.98% |
32.540 |
31.570 |
0.015 |
-0.03% |
0.015 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint16_t_To_uint32_t_
|
-2.97% |
11342.699 |
11006.033 |
63.331 |
-0.63% |
63.331 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint64_t_To_uint8_t_
|
-2.94% |
19841.137 |
19257.407 |
22.957 |
0.10% |
22.957 |
|
MultiSource/Benchmarks/Rodinia/pathfinder/pathfinder
Profile
|
-2.93% |
1.258 |
1.221 |
0.009 |
-1.28% |
0.009 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_BAND_LIN_EQ_RAW/5001
|
-2.93% |
20.622 |
20.019 |
0.098 |
-0.02% |
0.098 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC32
|
-2.88% |
31.286 |
30.384 |
0.041 |
-0.12% |
0.041 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint16_t>/999
|
-2.85% |
1013.869 |
984.996 |
0.045 |
-0.00% |
0.045 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, LessThanZero, None>
|
-2.82% |
37576.235 |
36518.168 |
56.600 |
-0.03% |
56.600 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC64
|
-2.81% |
111.383 |
108.258 |
0.010 |
0.00% |
0.010 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopTC16
|
-2.78% |
276.218 |
268.532 |
1.896 |
0.36% |
1.896 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC1
|
-2.78% |
22.525 |
21.900 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC1
|
-2.77% |
22.526 |
21.902 |
0.001 |
0.00% |
0.001 |
|
SingleSource/Benchmarks/BenchmarkGame/puzzle
Profile
|
-2.68% |
0.869 |
0.845 |
0.004 |
-0.87% |
0.004 |
|
MultiSource/Benchmarks/mafft/pairlocalalign
Profile
|
-2.64% |
94.062 |
91.579 |
0.365 |
0.01% |
0.365 |
|
MultiSource/Benchmarks/FreeBench/mason/mason
Profile
|
-2.64% |
0.553 |
0.538 |
0.000 |
-0.06% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC63
|
-2.61% |
120.145 |
117.009 |
0.013 |
-0.00% |
0.013 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C/CoMD/CoMD
Profile
|
-2.59% |
9.899 |
9.642 |
0.003 |
0.02% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint8_t_To_uint32_t_
|
-2.53% |
7077.318 |
6898.261 |
0.713 |
-0.02% |
0.713 |
|
MultiSource/Benchmarks/sim/sim
Profile
|
-2.52% |
9.701 |
9.456 |
0.035 |
-0.09% |
0.035 |
|
MultiSource/Benchmarks/FreeBench/pcompress2/pcompress2
Profile
|
-2.51% |
0.404 |
0.394 |
0.001 |
0.05% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC32
|
-2.49% |
50.052 |
48.806 |
0.007 |
-0.01% |
0.007 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchVecWithRuntimeChecks4PointersDBeforeA/32
|
-2.45% |
166201.466 |
162124.826 |
8.774 |
0.00% |
8.774 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_cond_load_novec_uint8_t_
|
-2.44% |
314092.103 |
306426.998 |
1594.447 |
-0.32% |
1594.447 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<31, GreaterThanZero, Last>
|
-2.37% |
8295.600 |
8098.849 |
1.209 |
-0.00% |
1.209 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC63
|
-2.34% |
107.004 |
104.495 |
0.186 |
0.00% |
0.186 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_FLOYD_DITHER/512
|
-2.34% |
6645.158 |
6489.797 |
11.373 |
-0.13% |
11.373 |
|
MultiSource/Benchmarks/FreeBench/fourinarow/fourinarow
Profile
|
-2.33% |
0.651 |
0.635 |
0.000 |
0.06% |
0.000 |
|
SingleSource/Benchmarks/Misc/fbench
Profile
|
-2.32% |
5.761 |
5.627 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC31
|
-2.31% |
31.189 |
30.468 |
0.017 |
-0.02% |
0.017 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC64
|
-2.31% |
108.247 |
105.745 |
0.020 |
-0.01% |
0.020 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_only_autovec_int64_t_
|
-2.27% |
1446971.267 |
1414124.240 |
499.349 |
0.04% |
499.349 |
|
MultiSource/Benchmarks/Olden/health/health
Profile
|
-2.24% |
1.591 |
1.556 |
0.003 |
-0.18% |
0.003 |
|
MultiSource/Benchmarks/Bullet/bullet
Profile
|
-2.20% |
30.431 |
29.761 |
0.216 |
-0.05% |
0.216 |
|
SingleSource/Benchmarks/Misc/flops-1
Profile
|
-2.15% |
9.000 |
8.806 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_only_novec_int32_t_
|
-2.12% |
450922.862 |
441367.334 |
684.447 |
-0.26% |
684.447 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC128
|
-2.11% |
119.525 |
117.005 |
0.015 |
-0.01% |
0.015 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC128
|
-2.10% |
119.520 |
117.005 |
0.004 |
-0.01% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC127
|
-2.09% |
120.138 |
117.630 |
0.014 |
-0.01% |
0.014 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC127
|
-2.09% |
120.146 |
117.640 |
0.001 |
-0.00% |
0.001 |
|
SingleSource/Benchmarks/Misc-C++/Large/ray
Profile
|
-2.07% |
12.101 |
11.851 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_cond_load_autovec_int64_t_
|
-2.01% |
552633.768 |
541530.506 |
2913.318 |
-0.74% |
2913.318 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<64, GreaterThanZero, Mid>
|
-1.99% |
2745.767 |
2691.102 |
11.292 |
0.04% |
11.292 |
|
MultiSource/Benchmarks/tramp3d-v4/tramp3d-v4
Profile
|
-1.98% |
1.076 |
1.054 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<64, EqZero, Mid>
|
-1.96% |
2744.265 |
2690.510 |
11.283 |
0.00% |
11.283 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint32_t>/10
|
-1.95% |
61.947 |
60.737 |
0.008 |
-0.05% |
0.008 |
|
External/SPEC/CINT2017rate/531.deepsjeng_r/531.deepsjeng_r
Profile
|
-1.94% |
260.112 |
255.063 |
0.394 |
-0.09% |
0.394 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_ADI_RAW/44217
|
-1.91% |
19747.738 |
19370.393 |
143.623 |
-1.50% |
143.623 |
|
SingleSource/Benchmarks/Shootout-C++/Shootout-C++-hash2
Profile
|
-1.91% |
9.336 |
9.158 |
0.029 |
-0.12% |
0.029 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_INT_PREDICT_LAMBDA/44217
|
-1.85% |
8337.702 |
8183.366 |
15.677 |
-0.03% |
15.677 |
|
SingleSource/Benchmarks/Misc/ReedSolomon
Profile
|
-1.85% |
20.797 |
20.412 |
0.004 |
-0.00% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint16_t>/256
|
-1.85% |
272.838 |
267.800 |
0.022 |
-0.00% |
0.022 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C/SimpleMOC/SimpleMOC
Profile
|
-1.85% |
10.405 |
10.213 |
0.041 |
0.03% |
0.041 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_EOS_RAW/171
|
-1.82% |
0.871 |
0.855 |
0.000 |
-0.05% |
0.000 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<16, EqZero, None>
|
-1.78% |
8177.641 |
8032.400 |
47.150 |
0.18% |
47.150 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_INT_PREDICT_RAW/171
|
-1.76% |
6.925 |
6.803 |
0.013 |
0.03% |
0.013 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_EOS_LAMBDA/171
|
-1.75% |
0.871 |
0.855 |
0.001 |
-0.02% |
0.001 |
|
MultiSource/Benchmarks/TSVC/NodeSplitting-dbl/NodeSplitting-dbl
Profile
|
-1.75% |
26.415 |
25.954 |
0.083 |
-0.79% |
0.083 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_ENERGY_CALC_LAMBDA/44217
|
-1.73% |
4324.422 |
4249.480 |
28.969 |
-0.04% |
28.969 |
|
MultiSource/Benchmarks/TSVC/Searching-dbl/Searching-dbl
Profile
|
-1.70% |
7.666 |
7.536 |
0.033 |
-0.26% |
0.033 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint64_t>/51
|
-1.69% |
148.307 |
145.797 |
0.004 |
-0.00% |
0.004 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_INT_PREDICT_LAMBDA/171
|
-1.69% |
6.925 |
6.808 |
0.014 |
-0.04% |
0.014 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_nested_cond_load_novec_uint8_t_
|
-1.69% |
504714.718 |
496174.407 |
305.570 |
-0.07% |
305.570 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C++/PENNANT/PENNANT
Profile
|
-1.64% |
4.817 |
4.738 |
0.018 |
-0.31% |
0.018 |
|
External/SPEC/CINT2017rate/541.leela_r/541.leela_r
Profile
|
-1.64% |
229.386 |
225.635 |
0.113 |
0.11% |
0.113 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<16, EqZero, Mid>
|
-1.63% |
8657.236 |
8516.280 |
46.346 |
-0.72% |
46.346 |
|
MultiSource/Benchmarks/VersaBench/ecbdes/ecbdes
Profile
|
-1.61% |
5.139 |
5.056 |
0.001 |
-0.03% |
0.001 |
|
SingleSource/Benchmarks/Misc/ffbench
Profile
|
-1.61% |
11.084 |
10.906 |
0.015 |
-0.35% |
0.015 |
|
MultiSource/Benchmarks/ASC_Sequoia/CrystalMk/CrystalMk
Profile
|
-1.57% |
15.572 |
15.327 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint32_t>/51
|
-1.57% |
83.849 |
82.535 |
0.060 |
0.00% |
0.060 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC15
|
-1.57% |
525.355 |
517.125 |
2.683 |
-0.24% |
2.683 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<3, GreaterThanZero, None>
|
-1.56% |
45142.879 |
44437.268 |
94.903 |
-0.72% |
94.903 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_ENERGY_CALC_RAW/44217
|
-1.56% |
4331.435 |
4263.920 |
12.817 |
-0.38% |
12.817 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_csa_with_in_loop_arith_novec_int64_t_
|
-1.54% |
1028155.144 |
1012297.280 |
906.870 |
0.00% |
906.870 |
|
SingleSource/Benchmarks/Misc/mandel-2
Profile
|
-1.54% |
2.535 |
2.496 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC128
|
-1.51% |
211.515 |
208.320 |
0.027 |
-0.02% |
0.027 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopTC15
|
-1.49% |
738.556 |
727.555 |
4.230 |
-0.22% |
4.230 |
|
MultiSource/Benchmarks/Fhourstones-3.1/fhourstones3.1
Profile
|
-1.43% |
3.972 |
3.915 |
0.009 |
-0.28% |
0.009 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint32_t>/28
|
-1.43% |
82.597 |
81.414 |
0.005 |
-0.02% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC127
|
-1.43% |
220.275 |
217.136 |
0.079 |
-0.04% |
0.079 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC63
|
-1.40% |
130.166 |
128.342 |
0.251 |
-0.25% |
0.251 |
|
MicroBenchmarks/ImageProcessing/Blur/blur.test:BENCHMARK_boxBlurKernel/512
|
-1.39% |
6613.679 |
6521.500 |
18.908 |
-0.46% |
18.908 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_csa_with_cond_arith_autovec_int64_t_
|
-1.38% |
744936.248 |
734626.752 |
704.030 |
-0.02% |
704.030 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint32_t_To_uint64_t_
|
-1.38% |
26280.748 |
25918.583 |
16.919 |
-0.15% |
16.919 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<32, GreaterThanZero, Mid>
|
-1.37% |
4555.446 |
4493.036 |
3.440 |
-0.02% |
3.440 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, LessThanZero, Mid>
|
-1.36% |
56527.388 |
55758.088 |
238.099 |
-0.03% |
238.099 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint64_t>/51
|
-1.36% |
229.009 |
225.898 |
0.012 |
-0.00% |
0.012 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint8_t_To_uint32_t_
|
-1.35% |
12122.484 |
11958.241 |
4.910 |
0.14% |
4.910 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<64, EqZero, None>
|
-1.33% |
2929.347 |
2890.459 |
5.241 |
-0.47% |
5.241 |
|
SingleSource/Benchmarks/Adobe-C++/simple_types_loop_invariant
Profile
|
-1.27% |
1.863 |
1.839 |
0.003 |
0.05% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC127
|
-1.27% |
197.100 |
194.597 |
0.068 |
-0.00% |
0.068 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC128
|
-1.27% |
198.368 |
195.853 |
0.008 |
-0.00% |
0.008 |
|
MultiSource/Benchmarks/MallocBench/cfrac/cfrac
Profile
|
-1.22% |
2.780 |
2.746 |
0.001 |
0.06% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_csa_with_cond_arith_novec_int64_t_
|
-1.18% |
744710.098 |
735928.043 |
192.493 |
-0.08% |
192.493 |
|
External/SPEC/CINT2017rate/525.x264_r/525.x264_r
Profile
|
-1.16% |
129.445 |
127.941 |
0.296 |
-1.18% |
0.296 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_sinh_novec_double_
|
-1.15% |
2473.865 |
2445.379 |
2.696 |
-0.06% |
2.696 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_sinhf_autovec_float_
|
-1.15% |
2242.663 |
2216.909 |
0.722 |
0.00% |
0.722 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<3, EqZero, Mid>
|
-1.15% |
37598.714 |
37167.391 |
23.433 |
0.00% |
23.433 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<32, LessThanZero, Mid>
|
-1.12% |
4570.992 |
4519.618 |
1.577 |
0.16% |
1.577 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_sinhf_novec_float_
|
-1.11% |
2241.857 |
2217.037 |
0.274 |
-0.01% |
0.274 |
|
SingleSource/Benchmarks/SmallPT/smallpt
Profile
|
-1.09% |
30.029 |
29.703 |
0.003 |
-0.02% |
0.003 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<16, LessThanZero, Last>
|
-1.07% |
13142.214 |
13000.991 |
1.792 |
0.09% |
1.792 |
|
MultiSource/Benchmarks/TSVC/Packing-flt/Packing-flt
Profile
|
-1.06% |
34.688 |
34.320 |
0.100 |
-2.01% |
0.100 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<31, EqZero, None>
|
-1.03% |
7995.131 |
7912.537 |
10.046 |
-0.28% |
10.046 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<8, LessThanZero, Mid>
|
-1.02% |
19434.559 |
19236.287 |
5.533 |
-0.05% |
5.533 |