|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_HYDRO_2D_LAMBDA/44217
|
-65.16% |
92115.411 |
32088.884 |
7911.467 |
-64.71% |
7911.467 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_HYDRO_2D_LAMBDA/5001
|
-58.88% |
9017.487 |
3708.295 |
863.710 |
-59.31% |
863.710 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_DISC_ORD_LAMBDA/44217
|
-55.25% |
14494.665 |
6486.120 |
1570.654 |
-53.85% |
1570.654 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_INT_PREDICT_LAMBDA/44217
|
-51.12% |
16363.509 |
7998.410 |
86.693 |
-4.07% |
86.693 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_HYDRO_2D_RAW/44217
|
-49.94% |
91439.718 |
45774.219 |
17580.229 |
-45.93% |
17580.229 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint64_t_To_uint32_t_
|
-49.86% |
35341.147 |
17720.067 |
125.209 |
-49.82% |
125.209 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint64_t_To_uint16_t_
|
-48.81% |
35745.539 |
18299.925 |
1578.281 |
-48.71% |
1578.281 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint64_t_To_uint8_t_
|
-48.56% |
36947.056 |
19005.713 |
40.425 |
-48.72% |
40.425 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C/miniGMG/miniGMG
Profile
|
-46.83% |
8.732 |
4.642 |
0.140 |
-49.49% |
0.140 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_DIFF_PREDICT_LAMBDA/44217
|
-44.83% |
24492.444 |
13511.358 |
336.625 |
-41.52% |
336.625 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint16_t_To_uint64_t_
|
-44.03% |
18653.759 |
10440.845 |
5.075 |
-44.09% |
5.075 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_HYDRO_2D_RAW/5001
|
-43.09% |
9221.987 |
5248.565 |
1417.475 |
-40.33% |
1417.475 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_DIFF_PREDICT_RAW/44217
|
-41.98% |
23257.867 |
13493.940 |
300.506 |
-42.09% |
300.506 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIRST_DIFF_LAMBDA/44217
|
-41.73% |
175.579 |
102.309 |
0.629 |
-29.35% |
0.629 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_PIC_1D_LAMBDA/44217
|
-41.49% |
13615.965 |
7966.579 |
1461.841 |
-40.83% |
1461.841 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint64_t_To_uint32_t_
|
-40.89% |
38322.185 |
22651.253 |
55.995 |
-40.63% |
55.995 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint8_t_To_uint64_t_
|
-40.75% |
17775.677 |
10531.907 |
2.007 |
-40.83% |
2.007 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_DIFF_PREDICT_LAMBDA/5001
|
-40.70% |
2551.262 |
1513.011 |
29.724 |
-39.71% |
29.724 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_DIFF_PREDICT_RAW/5001
|
-40.69% |
2560.918 |
1518.826 |
43.402 |
-41.01% |
43.402 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint32_t_To_uint64_t_
|
-36.79% |
22806.876 |
14415.433 |
289.965 |
-36.57% |
289.965 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/32
|
-36.70% |
1396.197 |
883.786 |
0.111 |
-36.70% |
0.111 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/64
|
-36.67% |
6181.103 |
3914.653 |
0.610 |
-36.68% |
0.610 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/16
|
-36.62% |
279.456 |
177.120 |
0.009 |
-36.62% |
0.009 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/256
|
-36.23% |
107130.315 |
68316.162 |
33.040 |
-36.24% |
33.040 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/128
|
-36.15% |
26263.197 |
16770.362 |
14.386 |
-36.17% |
14.386 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint64_t_To_uint16_t_
|
-34.27% |
28996.228 |
19058.671 |
41.939 |
-34.17% |
41.939 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint64_t_To_uint8_t_
|
-34.10% |
30142.085 |
19864.982 |
3.943 |
-34.03% |
3.943 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIRST_DIFF_RAW/44217
|
-32.40% |
148.673 |
100.502 |
0.369 |
-29.47% |
0.369 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, EqZero, None>
|
-31.23% |
20509.731 |
14104.814 |
0.481 |
-31.23% |
0.481 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint64_t_To_uint16_t_
|
-28.76% |
25907.118 |
18456.045 |
34.566 |
-28.73% |
34.566 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint32_t_To_uint8_t_
|
-27.78% |
13418.957 |
9690.951 |
13.169 |
-28.05% |
13.169 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC128
|
-27.53% |
1291.941 |
936.238 |
11.065 |
-27.58% |
11.065 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_PIC_2D_LAMBDA/44217
|
-27.31% |
11837.956 |
8605.470 |
54.019 |
-21.51% |
54.019 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC64
|
-26.98% |
654.582 |
477.961 |
5.499 |
-26.87% |
5.499 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC32
|
-26.79% |
334.122 |
244.596 |
2.623 |
-26.75% |
2.623 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC128
|
-26.65% |
555.926 |
407.798 |
0.015 |
-26.86% |
0.015 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC16
|
-26.17% |
173.809 |
128.330 |
1.119 |
-26.16% |
1.119 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIRST_SUM_LAMBDA/44217
|
-25.64% |
181.645 |
135.080 |
0.447 |
-19.16% |
0.447 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC64
|
-25.23% |
290.495 |
217.204 |
0.010 |
-25.57% |
0.010 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint64_t_To_uint8_t_
|
-24.36% |
27223.992 |
20591.012 |
2.280 |
-24.36% |
2.280 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, EqZero, None>
|
-23.98% |
16023.164 |
12181.588 |
1.112 |
-23.98% |
1.112 |
|
MicroBenchmarks/ImageProcessing/Dilate/Dilate.test:BENCHMARK_DILATE/128
|
-23.97% |
245.977 |
187.004 |
11.728 |
-17.97% |
11.728 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_PIC_2D_RAW/44217
|
-23.85% |
11344.658 |
8639.071 |
113.765 |
-22.98% |
113.765 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC128
|
-23.20% |
603.924 |
463.806 |
0.003 |
-23.21% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC128
|
-23.10% |
603.971 |
464.458 |
0.007 |
-23.10% |
0.007 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC32
|
-23.02% |
158.527 |
122.027 |
0.017 |
-23.19% |
0.017 |
|
MicroBenchmarks/ImageProcessing/Blur/blur.test:BENCHMARK_boxBlurKernel/1024
|
-22.60% |
30078.313 |
23280.304 |
65.290 |
-22.78% |
65.290 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC64
|
-22.35% |
313.505 |
243.429 |
0.017 |
-22.35% |
0.017 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC127
|
-22.17% |
615.239 |
478.809 |
0.007 |
-22.17% |
0.007 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC64
|
-22.15% |
313.515 |
244.067 |
0.012 |
-22.15% |
0.012 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC127
|
-21.96% |
615.208 |
480.108 |
0.021 |
-21.96% |
0.021 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint16_t_To_uint64_t_
|
-21.91% |
13268.954 |
10362.333 |
18.662 |
-21.55% |
18.662 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint16_t_To_uint32_t_
|
-21.67% |
7109.300 |
5568.770 |
3.673 |
-21.58% |
3.673 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint8_t_To_uint32_t_
|
-21.61% |
6587.116 |
5163.424 |
9.652 |
-21.56% |
9.652 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_only_autovec_uint8_t_
|
-21.35% |
182343.866 |
143420.551 |
233.689 |
-21.35% |
233.689 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIND_FIRST_MIN_LAMBDA/171
|
-21.30% |
1.501 |
1.181 |
0.000 |
-21.28% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIND_FIRST_MIN_LAMBDA/44217
|
-21.21% |
389.516 |
306.884 |
0.330 |
-21.23% |
0.330 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC32
|
-20.82% |
168.326 |
133.288 |
0.007 |
-20.82% |
0.007 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIND_FIRST_MIN_LAMBDA/5001
|
-20.54% |
45.193 |
35.911 |
0.151 |
-20.65% |
0.151 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC127
|
-20.50% |
275.215 |
218.792 |
1.188 |
-20.57% |
1.188 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC32
|
-20.44% |
168.311 |
133.901 |
0.007 |
-20.45% |
0.007 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC63
|
-20.41% |
324.746 |
258.457 |
0.008 |
-20.42% |
0.008 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_PIC_2D_RAW/5001
|
-20.37% |
1142.003 |
909.390 |
33.716 |
-15.67% |
33.716 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC63
|
-20.33% |
151.821 |
120.955 |
0.556 |
-19.32% |
0.556 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC128
|
-20.24% |
274.580 |
219.012 |
0.207 |
-20.28% |
0.207 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC63
|
-20.04% |
324.785 |
259.693 |
0.009 |
-20.04% |
0.009 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC64
|
-19.90% |
149.705 |
119.917 |
0.405 |
-19.32% |
0.405 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC127
|
-19.53% |
639.747 |
514.803 |
0.260 |
-19.62% |
0.260 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC16
|
-19.29% |
92.264 |
74.465 |
0.009 |
-19.31% |
0.009 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint16_t_To_uint8_t_
|
-19.10% |
3818.372 |
3089.225 |
0.227 |
-19.09% |
0.227 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_INT_PREDICT_LAMBDA/5001
|
-19.04% |
1129.832 |
914.705 |
4.874 |
1.10% |
4.874 |
|
SingleSource/Benchmarks/Adobe-C++/loop_unroll
Profile
|
-18.92% |
2.983 |
2.418 |
0.003 |
-22.16% |
0.003 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_VOL3D_CALC_LAMBDA/2
|
-18.80% |
8.757 |
7.110 |
0.000 |
-18.81% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_VOL3D_CALC_RAW/2
|
-18.78% |
8.756 |
7.112 |
0.000 |
-18.78% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint32_t_To_uint16_t_
|
-18.74% |
10740.149 |
8727.269 |
252.217 |
-11.89% |
252.217 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_PIC_2D_LAMBDA/5001
|
-18.73% |
1148.570 |
933.395 |
26.883 |
-15.57% |
26.883 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint32_t_To_uint8_t_
|
-18.65% |
13885.925 |
11295.916 |
25.959 |
-18.74% |
25.959 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint64_t_To_uint32_t_
|
-18.58% |
27097.903 |
22062.164 |
13.160 |
-18.44% |
13.160 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint32_t_To_uint16_t_
|
-18.50% |
13800.603 |
11247.765 |
4.042 |
-18.54% |
4.042 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC16
|
-18.30% |
95.733 |
78.214 |
0.004 |
-18.31% |
0.004 |
|
MultiSource/Benchmarks/MiBench/automotive-bitcount/automotive-bitcount
Profile
|
-18.18% |
0.124 |
0.102 |
0.001 |
-17.88% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC32
|
-18.18% |
86.638 |
70.891 |
0.238 |
-16.92% |
0.238 |
|
MultiSource/Benchmarks/Trimaran/enc-pc1/enc-pc1
Profile
|
-18.15% |
1.105 |
0.904 |
0.000 |
-18.12% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIRST_SUM_RAW/44217
|
-18.12% |
163.681 |
134.030 |
0.661 |
-19.42% |
0.661 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC128
|
-18.04% |
570.657 |
467.725 |
2.084 |
-18.03% |
2.084 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_with_cond_arith_novec_uint8_t_
|
-17.86% |
746115.570 |
612832.419 |
514.618 |
-17.82% |
514.618 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC16
|
-17.65% |
95.739 |
78.841 |
0.003 |
-17.65% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC31
|
-17.42% |
179.578 |
148.294 |
0.011 |
-17.42% |
0.011 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC4
|
-17.39% |
17.522 |
14.475 |
0.024 |
-17.38% |
0.024 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_with_cond_arith_novec_int32_t_
|
-17.35% |
739994.228 |
611581.619 |
453.145 |
-17.38% |
453.145 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C/miniAMR/miniAMR
Profile
|
-17.23% |
3.429 |
2.839 |
0.128 |
-12.64% |
0.128 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint8_t_To_uint64_t_
|
-16.99% |
13151.998 |
10917.850 |
7.833 |
-16.43% |
7.833 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC64
|
-16.95% |
296.591 |
246.332 |
0.242 |
-17.26% |
0.242 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC31
|
-16.72% |
179.583 |
149.560 |
0.007 |
-16.72% |
0.007 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC32
|
-16.54% |
160.644 |
134.075 |
0.085 |
-16.93% |
0.085 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_VOL3D_CALC_RAW/0
|
-16.25% |
1268.925 |
1062.698 |
0.708 |
-16.01% |
0.708 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC16
|
-16.24% |
92.997 |
77.895 |
0.004 |
-16.35% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC31
|
-16.23% |
86.694 |
72.619 |
0.762 |
-15.67% |
0.762 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_VOL3D_CALC_LAMBDA/0
|
-16.16% |
1266.384 |
1061.698 |
1.193 |
-16.24% |
1.193 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_HYDRO_1D_LAMBDA/171
|
-16.13% |
0.443 |
0.372 |
0.000 |
-15.87% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_VOL3D_CALC_LAMBDA/1
|
-16.07% |
260.097 |
218.306 |
0.374 |
-16.09% |
0.374 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_HYDRO_1D_RAW/171
|
-16.06% |
0.443 |
0.372 |
0.000 |
-15.83% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_VOL3D_CALC_RAW/1
|
-16.05% |
259.923 |
218.212 |
0.112 |
-16.11% |
0.112 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint16_t_To_uint32_t_
|
-15.68% |
7463.240 |
6293.337 |
1.288 |
-15.66% |
1.288 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC8
|
-15.44% |
58.742 |
49.671 |
0.034 |
-15.47% |
0.034 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, EqZero, First>
|
-15.40% |
16670.896 |
14104.312 |
0.795 |
-15.40% |
0.795 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_no_runtime_checks_needed<16, int>
|
-15.39% |
24.404 |
20.648 |
0.002 |
-15.39% |
0.002 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, EqZero, Mid>
|
-15.36% |
16666.332 |
14105.677 |
0.231 |
-15.36% |
0.231 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, EqZero, Last>
|
-15.34% |
16667.075 |
14110.110 |
0.399 |
-15.34% |
0.399 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint32_t_To_uint16_t_
|
-15.18% |
11354.159 |
9631.109 |
230.635 |
-10.30% |
230.635 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC127
|
-14.91% |
605.660 |
515.361 |
0.318 |
-14.92% |
0.318 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint32_t_To_uint8_t_
|
-14.76% |
10542.530 |
8986.486 |
28.455 |
-15.18% |
28.455 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC8
|
-14.74% |
59.446 |
50.687 |
0.001 |
-14.74% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint32_t_To_uint8_t_
|
-14.66% |
11096.632 |
9470.108 |
30.890 |
-14.91% |
30.890 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC128
|
-14.55% |
1103.057 |
942.582 |
0.068 |
-14.57% |
0.068 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC127
|
-14.52% |
1095.379 |
936.364 |
0.008 |
-14.51% |
0.008 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint8_t_To_uint16_t_
|
-14.26% |
3757.145 |
3221.261 |
7.086 |
-14.25% |
7.086 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_with_cond_arith_novec_int64_t_
|
-14.24% |
790771.116 |
678195.454 |
2407.904 |
-13.94% |
2407.904 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint64_t_To_uint8_t_
|
-14.21% |
22109.029 |
18967.224 |
49.440 |
-13.97% |
49.440 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIRST_SUM_LAMBDA/5001
|
-14.19% |
20.394 |
17.499 |
0.442 |
-0.62% |
0.442 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC64
|
-14.16% |
561.340 |
481.844 |
0.015 |
-14.31% |
0.015 |
|
SingleSource/Benchmarks/Misc/salsa20
Profile
|
-14.14% |
15.387 |
13.211 |
0.001 |
-14.12% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC63
|
-14.08% |
553.533 |
475.615 |
0.021 |
-14.26% |
0.021 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_with_cond_arith_autovec_int64_t_
|
-13.95% |
791084.789 |
680758.031 |
1509.973 |
-14.00% |
1509.973 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC1
|
-13.86% |
51.938 |
44.740 |
0.002 |
-13.85% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC4
|
-13.86% |
51.937 |
44.740 |
0.002 |
-13.85% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC7
|
-13.86% |
51.940 |
44.743 |
0.004 |
-13.85% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC2
|
-13.86% |
51.938 |
44.741 |
0.001 |
-13.85% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC3
|
-13.85% |
51.934 |
44.741 |
0.003 |
-13.85% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC8
|
-13.85% |
51.933 |
44.743 |
0.002 |
-13.85% |
0.002 |
|
External/SPEC/CFP2017rate/508.namd_r/508.namd_r
Profile
|
-13.77% |
224.110 |
193.247 |
0.874 |
-13.57% |
0.874 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC8
|
-13.68% |
59.444 |
51.310 |
0.002 |
-13.69% |
0.002 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, EqZero, Mid>
|
-13.62% |
14102.733 |
12182.093 |
0.784 |
-13.62% |
0.784 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, EqZero, Last>
|
-13.62% |
14102.477 |
12182.036 |
0.575 |
-13.63% |
0.575 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, EqZero, First>
|
-13.62% |
14102.604 |
12182.305 |
0.594 |
-13.62% |
0.594 |
|
MultiSource/Benchmarks/McCat/12-IOtest/iotest
Profile
|
-13.56% |
1.862 |
1.610 |
0.041 |
-11.79% |
0.041 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC8
|
-13.55% |
23.152 |
20.016 |
0.003 |
-13.55% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC32
|
-13.36% |
290.358 |
251.557 |
0.032 |
-13.85% |
0.032 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC63
|
-13.36% |
374.221 |
324.227 |
0.029 |
-13.41% |
0.029 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC4
|
-13.33% |
112.830 |
97.791 |
2.474 |
-13.53% |
2.474 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint32_t_To_uint16_t_
|
-13.20% |
12794.879 |
11105.388 |
14.976 |
-13.49% |
14.976 |
|
MicroBenchmarks/ImageProcessing/Dilate/Dilate.test:BENCHMARK_DILATE/1024
|
-13.20% |
7319.840 |
6353.664 |
206.827 |
-10.64% |
206.827 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC8
|
-13.16% |
23.778 |
20.649 |
0.001 |
-13.16% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC128
|
-13.08% |
81.344 |
70.707 |
0.003 |
-13.08% |
0.003 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_PIC_1D_LAMBDA/5001
|
-13.07% |
348.060 |
302.556 |
17.589 |
-14.28% |
17.589 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC31
|
-13.06% |
282.171 |
245.315 |
0.010 |
-13.65% |
0.010 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint8_t_To_uint16_t_
|
-12.94% |
4541.799 |
3953.969 |
0.211 |
-12.94% |
0.211 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_HYDRO_1D_RAW/5001
|
-12.94% |
17.596 |
15.319 |
0.390 |
-8.19% |
0.390 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC15
|
-12.86% |
106.995 |
93.235 |
0.002 |
-12.87% |
0.002 |
|
SingleSource/Benchmarks/Shootout-C++/Shootout-C++-matrix
Profile
|
-12.74% |
2.509 |
2.189 |
0.000 |
-12.72% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC16
|
-12.70% |
51.937 |
45.343 |
0.041 |
-12.70% |
0.041 |
|
MultiSource/Benchmarks/MiBench/security-rijndael/security-rijndael
Profile
|
-12.69% |
0.334 |
0.292 |
0.001 |
-12.75% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC16
|
-12.68% |
156.222 |
136.409 |
0.006 |
-13.10% |
0.006 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_PRESSURE_CALC_RAW/5001
|
-12.49% |
46.139 |
40.379 |
0.577 |
-9.47% |
0.577 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC63
|
-12.48% |
332.128 |
290.687 |
0.025 |
-12.66% |
0.025 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint16_t_To_uint8_t_
|
-12.42% |
4743.206 |
4154.219 |
0.512 |
-12.41% |
0.512 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC15
|
-12.36% |
148.500 |
130.152 |
0.009 |
-12.54% |
0.009 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC2
|
-11.78% |
21.277 |
18.771 |
0.001 |
-11.77% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC15
|
-11.70% |
107.004 |
94.485 |
0.001 |
-11.70% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC15
|
-11.47% |
51.938 |
45.983 |
0.014 |
-11.47% |
0.014 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC16
|
-11.39% |
33.169 |
29.393 |
0.007 |
-11.37% |
0.007 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC8
|
-11.32% |
88.909 |
78.844 |
0.001 |
-11.81% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC3
|
-11.12% |
22.528 |
20.024 |
0.001 |
-11.11% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC4
|
-11.11% |
22.527 |
20.024 |
0.000 |
-11.11% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC4
|
-11.11% |
22.525 |
20.023 |
0.001 |
-11.12% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint8_t>/51
|
-11.09% |
123.888 |
110.152 |
0.341 |
19.08% |
0.341 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_HYDRO_1D_LAMBDA/5001
|
-10.71% |
17.309 |
15.455 |
0.310 |
-10.00% |
0.310 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_BAND_LIN_EQ_RAW/171
|
-10.61% |
0.384 |
0.343 |
0.000 |
-6.33% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC4
|
-10.61% |
41.299 |
36.919 |
0.001 |
-10.61% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_BAND_LIN_EQ_LAMBDA/171
|
-10.59% |
0.384 |
0.343 |
0.000 |
-6.32% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC7
|
-10.58% |
81.171 |
72.586 |
0.001 |
-10.73% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint32_t_To_uint64_t_
|
-10.53% |
17422.525 |
15587.850 |
301.062 |
-9.35% |
301.062 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC4
|
-10.52% |
23.778 |
21.275 |
0.000 |
-10.53% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC64
|
-10.46% |
53.810 |
48.180 |
0.001 |
-10.47% |
0.001 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/16
|
-10.17% |
115.469 |
103.732 |
0.004 |
-10.16% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint8_t_To_uint16_t_
|
-10.08% |
5846.603 |
5257.215 |
4.744 |
-10.14% |
4.744 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC127
|
-10.07% |
102.284 |
91.988 |
0.004 |
-9.71% |
0.004 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/64
|
-10.03% |
1912.612 |
1720.870 |
0.918 |
-10.06% |
0.918 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/32
|
-9.99% |
473.005 |
425.767 |
0.010 |
-9.99% |
0.010 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/128
|
-9.90% |
7922.133 |
7137.625 |
4.628 |
-9.85% |
4.628 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_INT_PREDICT_RAW/44217
|
-9.86% |
8847.463 |
7975.073 |
104.430 |
-11.87% |
104.430 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/256
|
-9.85% |
31433.869 |
28338.638 |
8.419 |
-9.89% |
8.419 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC4
|
-9.81% |
55.506 |
50.060 |
0.002 |
-10.07% |
0.002 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_DIFF_PREDICT_LAMBDA/171
|
-9.79% |
12.316 |
11.110 |
0.045 |
-7.31% |
0.045 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_only_autovec_int64_t_
|
-9.79% |
333607.752 |
300954.085 |
571.003 |
-9.70% |
571.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC8
|
-9.76% |
25.655 |
23.150 |
0.002 |
-9.77% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC8
|
-9.75% |
25.654 |
23.153 |
0.001 |
-9.76% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC7
|
-9.62% |
32.541 |
29.410 |
0.001 |
-9.61% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC7
|
-9.53% |
26.282 |
23.777 |
0.001 |
-9.53% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC7
|
-9.52% |
26.281 |
23.778 |
0.002 |
-9.53% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC8
|
-9.49% |
26.964 |
24.405 |
0.003 |
-9.32% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC32
|
-9.43% |
53.188 |
48.170 |
0.007 |
-9.44% |
0.007 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_DEL_DOT_VEC_2D_RAW/1
|
-9.25% |
287.116 |
260.545 |
0.042 |
-9.22% |
0.042 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_DEL_DOT_VEC_2D_LAMBDA/1
|
-9.18% |
286.983 |
260.631 |
0.083 |
-9.23% |
0.083 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC31
|
-9.14% |
195.923 |
178.021 |
0.011 |
-9.39% |
0.011 |
|
MultiSource/Benchmarks/FreeBench/pifft/pifft
Profile
|
-9.10% |
0.359 |
0.326 |
0.002 |
-9.03% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC4
|
-9.09% |
41.300 |
37.544 |
0.003 |
-9.09% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC7
|
-8.90% |
28.159 |
25.653 |
0.001 |
-8.90% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_INT_PREDICT_RAW/5001
|
-8.74% |
997.076 |
909.915 |
5.021 |
-0.38% |
5.021 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_DEL_DOT_VEC_2D_LAMBDA/2
|
-8.70% |
3.510 |
3.205 |
0.000 |
-8.69% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_DEL_DOT_VEC_2D_RAW/2
|
-8.70% |
3.510 |
3.204 |
0.000 |
-8.71% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC16
|
-8.62% |
36.293 |
33.165 |
0.002 |
-8.62% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC8
|
-8.52% |
29.410 |
26.906 |
0.001 |
-8.52% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint16_t_To_uint8_t_
|
-8.50% |
6808.830 |
6230.159 |
3.615 |
-8.59% |
3.615 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_runtime_checks_pass<4, int>
|
-8.47% |
16.750 |
15.331 |
0.001 |
-8.24% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_DISC_ORD_RAW/5001
|
-8.25% |
655.960 |
601.821 |
16.017 |
-9.47% |
16.017 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC2
|
-8.20% |
38.169 |
35.040 |
0.002 |
-8.20% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint16_t_To_uint64_t_
|
-8.10% |
20217.751 |
18580.391 |
62.691 |
-7.76% |
62.691 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC64
|
-8.09% |
93.239 |
85.696 |
0.015 |
-8.09% |
0.015 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint8_t>/28
|
-8.06% |
82.589 |
75.934 |
0.152 |
12.35% |
0.152 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_HYDRO_2D_LAMBDA/171
|
-7.95% |
88.784 |
81.726 |
1.229 |
-7.82% |
1.229 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC7
|
-7.91% |
354.352 |
326.321 |
7.202 |
-8.00% |
7.202 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC3
|
-7.90% |
47.558 |
43.803 |
0.001 |
-7.89% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC16
|
-7.85% |
31.914 |
29.408 |
0.001 |
-7.85% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC16
|
-7.84% |
31.913 |
29.411 |
0.001 |
-7.84% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIRST_DIFF_LAMBDA/5001
|
-7.83% |
12.850 |
11.843 |
0.050 |
-2.85% |
0.050 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC32
|
-7.82% |
40.050 |
36.916 |
0.002 |
-7.82% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint8_t_To_uint32_t_
|
-7.82% |
12777.009 |
11778.268 |
11.605 |
-7.83% |
11.605 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_DEL_DOT_VEC_2D_LAMBDA/0
|
-7.72% |
1798.238 |
1659.369 |
6.477 |
-7.40% |
6.477 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_DEL_DOT_VEC_2D_RAW/0
|
-7.72% |
1798.190 |
1659.374 |
2.556 |
-7.86% |
2.556 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC15
|
-7.70% |
32.540 |
30.033 |
0.002 |
-7.70% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC15
|
-7.70% |
32.539 |
30.033 |
0.002 |
-7.70% |
0.002 |
|
MultiSource/Benchmarks/VersaBench/beamformer/beamformer
Profile
|
-7.69% |
5.203 |
4.803 |
0.001 |
-7.65% |
0.001 |
|
MultiSource/Benchmarks/Trimaran/enc-md5/enc-md5
Profile
|
-7.54% |
3.508 |
3.243 |
0.000 |
-7.49% |
0.000 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_xor_no_runtime_checks_needed<16, int>
|
-7.40% |
16.894 |
15.644 |
0.000 |
-7.41% |
0.000 |
|
MultiSource/Applications/lambda-0.1.3/lambda
Profile
|
-7.33% |
15.887 |
14.723 |
0.005 |
-7.23% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC128
|
-7.23% |
173.337 |
160.801 |
0.012 |
-7.23% |
0.012 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIND_FIRST_MIN_RAW/171
|
-7.23% |
1.497 |
1.389 |
0.000 |
-7.19% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint8_t>/127
|
-7.20% |
138.900 |
128.893 |
0.011 |
-7.21% |
0.011 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint16_t_To_uint64_t_
|
-7.15% |
24998.763 |
23211.874 |
46.357 |
-7.10% |
46.357 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_HYDRO_2D_RAW/171
|
-7.13% |
88.901 |
82.564 |
0.376 |
-6.84% |
0.376 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC7
|
-7.08% |
70.708 |
65.701 |
0.004 |
-7.09% |
0.004 |
|
SingleSource/Benchmarks/Misc/pi
Profile
|
-7.02% |
1.783 |
1.657 |
0.000 |
-7.01% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_PRESSURE_CALC_LAMBDA/5001
|
-6.95% |
44.865 |
41.747 |
1.042 |
-5.06% |
1.042 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC15
|
-6.95% |
45.054 |
41.924 |
0.002 |
-6.94% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC15
|
-6.88% |
54.436 |
50.690 |
0.012 |
-6.89% |
0.012 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC31
|
-6.72% |
74.466 |
69.462 |
0.014 |
-6.72% |
0.014 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC63
|
-6.56% |
114.513 |
106.999 |
0.172 |
-6.56% |
0.172 |
|
SingleSource/Benchmarks/Misc/flops-6
Profile
|
-6.55% |
1.312 |
1.226 |
0.001 |
-6.59% |
0.001 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_xor_runtime_checks_pass<16, int>
|
-6.52% |
28.783 |
26.906 |
0.001 |
-6.52% |
0.001 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_xor_runtime_checks_fail<16, int>
|
-6.52% |
28.784 |
26.907 |
0.001 |
-6.52% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC63
|
-6.50% |
74.279 |
69.451 |
0.003 |
-6.43% |
0.003 |
|
SingleSource/Benchmarks/Misc/oourafft
Profile
|
-6.44% |
15.370 |
14.380 |
0.107 |
-4.73% |
0.107 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_only_autovec_int32_t_
|
-6.40% |
181103.021 |
169503.970 |
388.774 |
-6.41% |
388.774 |
|
SingleSource/Benchmarks/Polybench/stencils/jacobi-2d/jacobi-2d
Profile
|
-6.39% |
32.274 |
30.210 |
0.194 |
-6.25% |
0.194 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIND_FIRST_MIN_RAW/5001
|
-6.38% |
45.292 |
42.400 |
0.156 |
-6.48% |
0.156 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC127
|
-6.38% |
68.833 |
64.439 |
0.006 |
-5.64% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC128
|
-6.36% |
68.828 |
64.449 |
0.003 |
-6.33% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC15
|
-6.36% |
39.422 |
36.917 |
0.002 |
-6.36% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC127
|
-6.34% |
194.599 |
182.257 |
0.267 |
-6.35% |
0.267 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint16_t>/127
|
-6.30% |
138.907 |
130.153 |
0.005 |
-6.31% |
0.005 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_DIFF_PREDICT_RAW/171
|
-6.29% |
11.856 |
11.111 |
0.065 |
-6.89% |
0.065 |
|
SingleSource/Benchmarks/Misc-C++/Large/sphereflake
Profile
|
-6.22% |
20.009 |
18.766 |
0.005 |
-6.18% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC16
|
-6.16% |
40.674 |
38.168 |
0.003 |
-6.16% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC127
|
-6.07% |
2410.412 |
2264.018 |
40.437 |
-6.70% |
40.437 |
|
MultiSource/Benchmarks/MiBench/telecomm-gsm/telecomm-gsm
Profile
|
-5.98% |
0.663 |
0.624 |
0.000 |
-5.94% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint8_t>/65
|
-5.91% |
95.104 |
89.480 |
0.007 |
-5.92% |
0.007 |
|
External/SPEC/CFP2017rate/538.imagick_r/538.imagick_r
Profile
|
-5.88% |
291.524 |
274.393 |
0.811 |
-6.06% |
0.811 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint32_t>/127
|
-5.87% |
138.279 |
130.164 |
0.001 |
-5.87% |
0.001 |
|
MultiSource/Benchmarks/Rodinia/hotspot/hotspot
Profile
|
-5.79% |
2.035 |
1.917 |
0.021 |
-5.84% |
0.021 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint32_t_To_uint64_t_
|
-5.67% |
21535.118 |
20314.751 |
15.040 |
-5.30% |
15.040 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC16
|
-5.65% |
33.162 |
31.287 |
0.000 |
-5.66% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC32
|
-5.64% |
44.429 |
41.924 |
0.002 |
-5.64% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC32
|
-5.63% |
44.424 |
41.922 |
0.002 |
-5.64% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC31
|
-5.59% |
45.069 |
42.551 |
0.001 |
-5.58% |
0.001 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C++/miniFE/miniFE
Profile
|
-5.58% |
15.815 |
14.932 |
0.076 |
-6.49% |
0.076 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC31
|
-5.55% |
45.050 |
42.547 |
0.002 |
-5.56% |
0.002 |
|
MultiSource/Benchmarks/SciMark2-C/scimark2
Profile
|
-5.54% |
107.701 |
101.733 |
0.036 |
-5.49% |
0.036 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint8_t_To_uint16_t_
|
-5.49% |
3627.021 |
3427.976 |
5.857 |
-5.65% |
5.857 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_BAND_LIN_EQ_RAW/5001
|
-5.48% |
21.297 |
20.131 |
0.083 |
-2.38% |
0.083 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_PIC_1D_RAW/5001
|
-5.47% |
355.178 |
335.736 |
4.283 |
-2.69% |
4.283 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint32_t>/999
|
-5.39% |
696.456 |
658.908 |
0.053 |
-5.40% |
0.053 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC32
|
-5.35% |
61.323 |
58.041 |
0.064 |
-5.35% |
0.064 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC7
|
-5.31% |
70.706 |
66.953 |
0.003 |
-5.33% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopWithReductionTC1
|
-5.27% |
11.889 |
11.263 |
0.000 |
-5.26% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC1
|
-5.27% |
88.703 |
84.033 |
1.647 |
-5.56% |
1.647 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIND_FIRST_MIN_RAW/44217
|
-5.25% |
389.229 |
368.787 |
0.187 |
-5.34% |
0.187 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint32_t>/999
|
-5.24% |
1365.086 |
1293.596 |
0.110 |
-5.23% |
0.110 |
|
MicroBenchmarks/ImageProcessing/Dilate/Dilate.test:BENCHMARK_DILATE/512
|
-5.16% |
3637.062 |
3449.465 |
28.952 |
-3.76% |
28.952 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_PIC_2D_LAMBDA/171
|
-5.15% |
13.455 |
12.762 |
0.064 |
-5.45% |
0.064 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC31
|
-5.13% |
24.402 |
23.150 |
0.005 |
-5.13% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC31
|
-5.13% |
24.402 |
23.151 |
0.014 |
-5.13% |
0.014 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC32
|
-5.12% |
24.402 |
23.153 |
0.001 |
-5.12% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC32
|
-5.12% |
24.402 |
23.153 |
0.001 |
-5.13% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_PIC_2D_RAW/171
|
-5.08% |
13.525 |
12.837 |
0.057 |
-5.19% |
0.057 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC15
|
-5.07% |
128.213 |
121.707 |
0.004 |
-5.11% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC31
|
-5.07% |
241.269 |
229.039 |
0.017 |
-5.05% |
0.017 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint64_t_To_uint16_t_
|
-4.98% |
18707.478 |
17774.947 |
300.910 |
-6.37% |
300.910 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint32_t>/256
|
-4.82% |
364.206 |
346.654 |
0.009 |
-4.81% |
0.009 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC64
|
-4.77% |
43.802 |
41.712 |
0.006 |
-3.39% |
0.006 |
|
MicroBenchmarks/ImageProcessing/Dilate/Dilate.test:BENCHMARK_DILATE/256
|
-4.76% |
1064.727 |
1014.028 |
6.389 |
-4.99% |
6.389 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_BAND_LIN_EQ_LAMBDA/5001
|
-4.75% |
21.197 |
20.190 |
0.064 |
-2.93% |
0.064 |
|
SingleSource/Benchmarks/Misc/revertBits
Profile
|
-4.72% |
0.641 |
0.611 |
0.000 |
-4.69% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC15
|
-4.71% |
44.705 |
42.598 |
0.526 |
-4.13% |
0.526 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_PRESSURE_CALC_LAMBDA/44217
|
-4.62% |
498.504 |
475.474 |
2.472 |
-4.63% |
2.472 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint16_t>/65
|
-4.60% |
95.110 |
90.734 |
0.005 |
-4.61% |
0.005 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_runtime_checks_pass<16, int>
|
-4.60% |
54.440 |
51.938 |
0.001 |
-4.59% |
0.001 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_runtime_checks_fail<16, int>
|
-4.59% |
54.439 |
51.939 |
0.002 |
-4.59% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC63
|
-4.56% |
43.567 |
41.581 |
0.103 |
-3.96% |
0.103 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint8_t>/16
|
-4.56% |
59.975 |
57.243 |
0.606 |
6.36% |
0.606 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopWithReductionTC2
|
-4.52% |
13.766 |
13.144 |
0.007 |
-4.52% |
0.007 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC31
|
-4.47% |
70.086 |
66.956 |
0.002 |
-4.46% |
0.002 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_PRESSURE_CALC_RAW/44217
|
-4.39% |
502.243 |
480.170 |
2.570 |
-4.39% |
2.570 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC3
|
-4.36% |
14.393 |
13.766 |
0.001 |
-4.35% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC2
|
-4.36% |
14.393 |
13.766 |
0.000 |
-4.35% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC3
|
-4.35% |
14.393 |
13.766 |
0.000 |
-4.35% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC7
|
-4.35% |
14.392 |
13.765 |
0.001 |
-4.35% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC4
|
-4.35% |
14.392 |
13.765 |
0.001 |
-4.36% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_ENERGY_CALC_RAW/171
|
-4.35% |
14.233 |
13.614 |
0.006 |
-4.40% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC8
|
-4.35% |
14.393 |
13.766 |
0.000 |
-4.35% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC16
|
-4.35% |
14.392 |
13.765 |
0.001 |
-4.35% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC2
|
-4.35% |
14.391 |
13.765 |
0.001 |
-4.36% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC4
|
-4.35% |
14.392 |
13.766 |
0.000 |
-4.35% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC8
|
-4.35% |
14.391 |
13.766 |
0.000 |
-4.35% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC15
|
-4.34% |
14.392 |
13.767 |
0.001 |
-4.35% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC7
|
-4.34% |
14.391 |
13.766 |
0.000 |
-4.35% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC1
|
-4.34% |
14.391 |
13.766 |
0.000 |
-4.35% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC15
|
-4.34% |
14.392 |
13.767 |
0.000 |
-4.34% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC1
|
-4.34% |
14.392 |
13.767 |
0.001 |
-4.35% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC16
|
-4.34% |
14.391 |
13.767 |
0.174 |
-4.35% |
0.174 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint64_t>/999
|
-4.24% |
1810.879 |
1734.065 |
0.174 |
-4.26% |
0.174 |
|
SingleSource/Benchmarks/Misc/flops-5
Profile
|
-4.21% |
2.021 |
1.936 |
0.002 |
-4.22% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint64_t>/999
|
-4.16% |
3595.245 |
3445.726 |
0.219 |
-4.14% |
0.219 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_nested_cond_load_novec_int32_t_
|
-4.16% |
649482.730 |
622496.102 |
323.695 |
-3.51% |
323.695 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint64_t>/256
|
-4.08% |
935.529 |
897.376 |
0.024 |
-4.08% |
0.024 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_ENERGY_CALC_LAMBDA/171
|
-4.07% |
14.193 |
13.616 |
0.005 |
-4.44% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC31
|
-4.04% |
61.945 |
59.442 |
0.007 |
-4.04% |
0.007 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_runtime_checks_fail<4, int>
|
-4.03% |
15.974 |
15.330 |
0.001 |
-3.63% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC16
|
-4.02% |
31.295 |
30.036 |
0.001 |
-4.00% |
0.001 |
|
External/SPEC/CFP2017rate/519.lbm_r/519.lbm_r
Profile
|
-4.02% |
199.966 |
191.936 |
1.508 |
-4.36% |
1.508 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint8_t_To_uint64_t_
|
-4.01% |
23490.313 |
22549.376 |
74.286 |
-3.98% |
74.286 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_only_autovec_uint8_t_
|
-3.98% |
96160.108 |
92330.160 |
11.623 |
-3.98% |
11.623 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint32_t>/65
|
-3.96% |
94.482 |
90.737 |
0.000 |
-3.97% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint32_t>/256
|
-3.96% |
221.523 |
212.744 |
0.014 |
-3.95% |
0.014 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC32
|
-3.96% |
63.199 |
60.698 |
0.005 |
-3.96% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC3
|
-3.85% |
16.270 |
15.643 |
0.001 |
-3.84% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint32_t_To_uint16_t_
|
-3.78% |
9877.584 |
9504.559 |
6.236 |
-3.80% |
6.236 |
|
SingleSource/Benchmarks/Shootout/Shootout-matrix
Profile
|
-3.70% |
3.864 |
3.721 |
0.001 |
-3.68% |
0.001 |
|
MultiSource/Benchmarks/TSVC/ControlLoops-dbl/ControlLoops-dbl
Profile
|
-3.68% |
11.079 |
10.671 |
0.115 |
-3.16% |
0.115 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint64_t>/256
|
-3.65% |
514.357 |
495.595 |
0.014 |
-3.65% |
0.014 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint16_t_To_uint8_t_
|
-3.62% |
2873.019 |
2768.950 |
4.761 |
-3.80% |
4.761 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<31, EqZero, First>
|
-3.62% |
3344.114 |
3223.218 |
0.109 |
-3.68% |
0.109 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<32, EqZero, Last>
|
-3.60% |
7070.097 |
6815.342 |
67.020 |
-3.37% |
67.020 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC64
|
-3.60% |
69.458 |
66.959 |
0.003 |
-3.60% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC63
|
-3.59% |
70.102 |
67.583 |
0.002 |
-3.58% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC64
|
-3.59% |
69.452 |
66.957 |
0.001 |
-3.61% |
0.001 |
|
SingleSource/Benchmarks/BenchmarkGame/n-body
Profile
|
-3.59% |
2.731 |
2.633 |
0.000 |
21.69% |
0.000 |
|
MultiSource/Applications/JM/lencod/lencod
Profile
|
-3.58% |
32.778 |
31.605 |
0.011 |
-2.87% |
0.011 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC63
|
-3.57% |
70.081 |
67.582 |
0.001 |
-3.57% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint64_t_To_uint32_t_
|
-3.56% |
19320.465 |
18633.273 |
6.708 |
-3.42% |
6.708 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC31
|
-3.49% |
60.298 |
58.194 |
0.001 |
-3.45% |
0.001 |
|
MultiSource/Benchmarks/nbench/nbench
Profile
|
-3.46% |
6.115 |
5.904 |
0.001 |
-3.64% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopFrom_uint32_t_To_uint16_t_
|
-3.32% |
7845.999 |
7585.711 |
33.626 |
1.81% |
33.626 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC31
|
-3.28% |
93.859 |
90.776 |
0.009 |
-3.28% |
0.009 |
|
External/SPEC/CFP2017rate/544.nab_r/544.nab_r
Profile
|
-3.27% |
476.318 |
460.747 |
0.067 |
-3.59% |
0.067 |
|
MultiSource/Benchmarks/Rodinia/pathfinder/pathfinder
Profile
|
-3.20% |
1.264 |
1.224 |
0.009 |
-2.69% |
0.009 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint16_t>/999
|
-3.16% |
514.985 |
498.714 |
0.020 |
-3.17% |
0.020 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint16_t_To_uint8_t_
|
-3.13% |
4512.743 |
4371.387 |
1.764 |
-3.23% |
1.764 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1BigLoopWithReductionTC1
|
-3.13% |
20.025 |
19.398 |
0.001 |
-3.13% |
0.001 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, LessThanZero, None>
|
-3.11% |
37659.638 |
36488.441 |
21.506 |
-2.89% |
21.506 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchVecWithRuntimeChecks4PointersDBeforeA/1000
|
-3.09% |
5020240.683 |
4865222.778 |
361.926 |
-3.08% |
361.926 |
|
SingleSource/Benchmarks/Shootout/Shootout-lists
Profile
|
-3.09% |
11.315 |
10.966 |
0.002 |
-3.06% |
0.002 |
|
MultiSource/Benchmarks/TSVC/InductionVariable-dbl/InductionVariable-dbl
Profile
|
-2.97% |
17.976 |
17.442 |
0.135 |
-1.65% |
0.135 |
|
MultiSource/Benchmarks/FreeBench/pcompress2/pcompress2
Profile
|
-2.97% |
0.405 |
0.393 |
0.001 |
-2.87% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC7
|
-2.92% |
27.109 |
26.318 |
0.110 |
-8.17% |
0.110 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC128
|
-2.90% |
86.892 |
84.373 |
0.808 |
0.22% |
0.808 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_FLOYD_DITHER/256
|
-2.88% |
1790.901 |
1739.386 |
9.700 |
0.33% |
9.700 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint16_t>/999
|
-2.84% |
1013.739 |
984.968 |
0.018 |
-2.85% |
0.018 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC64
|
-2.81% |
111.382 |
108.253 |
0.006 |
-2.81% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC1
|
-2.77% |
22.526 |
21.901 |
0.002 |
-2.77% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC1
|
-2.77% |
22.525 |
21.901 |
0.002 |
-2.77% |
0.002 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C/CoMD/CoMD
Profile
|
-2.77% |
9.908 |
9.634 |
0.007 |
-2.68% |
0.007 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_FLOYD_DITHER/128
|
-2.76% |
438.573 |
426.467 |
1.843 |
-2.96% |
1.843 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<31, GreaterThanZero, Last>
|
-2.73% |
8326.104 |
8098.920 |
7.974 |
-2.37% |
7.974 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC32
|
-2.73% |
31.283 |
30.430 |
0.035 |
-2.73% |
0.035 |
|
MultiSource/Benchmarks/FreeBench/mason/mason
Profile
|
-2.69% |
0.553 |
0.538 |
0.000 |
-2.74% |
0.000 |
|
MultiSource/Benchmarks/mafft/pairlocalalign
Profile
|
-2.68% |
94.143 |
91.616 |
0.293 |
-2.60% |
0.293 |
|
SingleSource/Benchmarks/Misc-C++/oopack_v1p8
Profile
|
-2.62% |
0.480 |
0.467 |
0.000 |
-9.98% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC63
|
-2.61% |
120.142 |
117.011 |
0.007 |
-2.61% |
0.007 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint8_t>/10
|
-2.57% |
48.808 |
47.554 |
0.008 |
2.46% |
0.008 |
|
MultiSource/Benchmarks/Bullet/bullet
Profile
|
-2.57% |
30.525 |
29.741 |
0.215 |
-2.27% |
0.215 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint8_t_To_uint32_t_
|
-2.51% |
7077.317 |
6899.880 |
0.624 |
-2.51% |
0.624 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC31
|
-2.50% |
31.266 |
30.484 |
0.006 |
-2.26% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC32
|
-2.49% |
50.057 |
48.810 |
0.030 |
-2.48% |
0.030 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchVecWithRuntimeChecks4PointersDBeforeA/32
|
-2.44% |
166181.459 |
162123.291 |
0.512 |
-2.45% |
0.512 |
|
MultiSource/Benchmarks/TSVC/ControlLoops-flt/ControlLoops-flt
Profile
|
-2.40% |
5.424 |
5.294 |
0.042 |
-2.82% |
0.042 |
|
MultiSource/Benchmarks/FreeBench/fourinarow/fourinarow
Profile
|
-2.38% |
0.651 |
0.635 |
0.001 |
-2.34% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_ENERGY_CALC_LAMBDA/44217
|
-2.35% |
4342.317 |
4240.210 |
30.008 |
-1.95% |
30.008 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_only_autovec_int64_t_
|
-2.34% |
1448411.400 |
1414464.299 |
581.634 |
-2.25% |
581.634 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC63
|
-2.34% |
106.999 |
104.494 |
0.006 |
-2.35% |
0.006 |
|
MultiSource/Benchmarks/sim/sim
Profile
|
-2.33% |
9.698 |
9.472 |
0.020 |
-2.36% |
0.020 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC64
|
-2.31% |
108.248 |
105.752 |
0.003 |
-2.31% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint64_t_To_uint8_t_
|
-2.23% |
19757.699 |
19317.166 |
13.800 |
-2.64% |
13.800 |
|
SingleSource/Benchmarks/Misc/flops-1
Profile
|
-2.17% |
9.002 |
8.806 |
0.000 |
-2.15% |
0.000 |
|
SingleSource/Benchmarks/BenchmarkGame/puzzle
Profile
|
-2.16% |
0.872 |
0.853 |
0.001 |
-1.83% |
0.001 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C/SimpleMOC/SimpleMOC
Profile
|
-2.12% |
10.428 |
10.207 |
0.036 |
-1.90% |
0.036 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_EOS_LAMBDA/171
|
-2.11% |
0.874 |
0.855 |
0.002 |
-1.75% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC128
|
-2.11% |
119.526 |
117.006 |
0.006 |
-2.10% |
0.006 |
|
SingleSource/Benchmarks/Misc-C++/Large/ray
Profile
|
-2.11% |
12.104 |
11.849 |
0.000 |
-2.08% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC128
|
-2.10% |
119.524 |
117.015 |
0.005 |
-2.10% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC127
|
-2.10% |
120.154 |
117.634 |
0.003 |
-2.09% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC127
|
-2.09% |
120.146 |
117.636 |
0.003 |
-2.08% |
0.003 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<64, EqZero, Mid>
|
-2.03% |
2746.828 |
2690.993 |
11.860 |
-1.94% |
11.860 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_FLOYD_DITHER/512
|
-2.02% |
6661.906 |
6527.181 |
6.766 |
-1.78% |
6.766 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint32_t_To_uint64_t_
|
-1.99% |
26261.296 |
25738.240 |
30.196 |
-2.06% |
30.196 |
|
SingleSource/Benchmarks/Misc/ReedSolomon
Profile
|
-1.95% |
20.819 |
20.412 |
0.002 |
-1.85% |
0.002 |
|
External/SPEC/CINT2017rate/531.deepsjeng_r/531.deepsjeng_r
Profile
|
-1.93% |
260.084 |
255.066 |
0.310 |
-1.94% |
0.310 |
|
MultiSource/Benchmarks/Olden/health/health
Profile
|
-1.92% |
1.586 |
1.555 |
0.005 |
-2.27% |
0.005 |
|
MultiSource/Applications/sgefa/sgefa
Profile
|
-1.89% |
0.577 |
0.566 |
0.001 |
-1.27% |
0.001 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<64, GreaterThanZero, Mid>
|
-1.86% |
2742.142 |
2691.009 |
16.943 |
-1.99% |
16.943 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint16_t_To_uint32_t_
|
-1.83% |
11268.991 |
11062.384 |
40.716 |
-2.47% |
40.716 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint16_t>/256
|
-1.83% |
272.829 |
267.830 |
0.013 |
-1.84% |
0.013 |
|
MultiSource/Benchmarks/Fhourstones-3.1/fhourstones3.1
Profile
|
-1.83% |
3.992 |
3.919 |
0.004 |
-1.33% |
0.004 |
|
MultiSource/Applications/SPASS/SPASS
Profile
|
-1.76% |
119.179 |
117.078 |
0.692 |
-1.05% |
0.692 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_INT_PREDICT_LAMBDA/171
|
-1.71% |
6.926 |
6.808 |
0.003 |
-1.69% |
0.003 |
|
External/SPEC/CFP2017rate/511.povray_r/511.povray_r
Profile
|
-1.70% |
33.994 |
33.416 |
0.019 |
-1.09% |
0.019 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint64_t>/51
|
-1.69% |
148.297 |
145.796 |
0.004 |
-1.69% |
0.004 |
|
MultiSource/Benchmarks/VersaBench/ecbdes/ecbdes
Profile
|
-1.67% |
5.142 |
5.056 |
0.002 |
-1.62% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_nested_cond_load_novec_uint8_t_
|
-1.61% |
504472.790 |
496356.411 |
471.102 |
-1.66% |
471.102 |
|
MultiSource/Benchmarks/tramp3d-v4/tramp3d-v4
Profile
|
-1.60% |
1.075 |
1.058 |
0.002 |
-1.61% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_csa_with_in_loop_arith_novec_int64_t_
|
-1.59% |
1028068.009 |
1011727.170 |
301.147 |
-1.60% |
301.147 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_INT_PREDICT_RAW/171
|
-1.58% |
6.925 |
6.815 |
0.000 |
-1.58% |
0.000 |
|
SingleSource/Benchmarks/Misc/mandel-2
Profile
|
-1.56% |
2.536 |
2.496 |
0.000 |
-1.54% |
0.000 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<32, LessThanZero, Mid>
|
-1.53% |
4570.412 |
4500.436 |
7.857 |
-1.54% |
7.857 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_EOS_RAW/171
|
-1.51% |
0.872 |
0.859 |
0.001 |
-1.35% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint32_t>/10
|
-1.48% |
57.900 |
57.040 |
0.063 |
-0.01% |
0.063 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC128
|
-1.48% |
211.506 |
208.377 |
0.020 |
-1.48% |
0.020 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_ENERGY_CALC_RAW/44217
|
-1.42% |
4330.618 |
4269.144 |
8.931 |
-1.44% |
8.931 |
|
External/SPEC/CINT2017rate/557.xz_r/557.xz_r
Profile
|
-1.41% |
212.782 |
209.784 |
1.070 |
-0.68% |
1.070 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, LessThanZero, Mid>
|
-1.41% |
31936.416 |
31486.518 |
30.496 |
-0.93% |
30.496 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<6, LessThanZero, Mid>
|
-1.41% |
23845.365 |
23509.820 |
8.885 |
-0.24% |
8.885 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC63
|
-1.40% |
130.156 |
128.330 |
0.148 |
-1.41% |
0.148 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC127
|
-1.40% |
220.268 |
217.187 |
0.074 |
-1.40% |
0.074 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_csa_with_cond_arith_novec_int64_t_
|
-1.38% |
746050.021 |
735746.178 |
572.520 |
-1.20% |
572.520 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_csa_with_cond_arith_autovec_int64_t_
|
-1.38% |
747163.412 |
736868.084 |
240.364 |
-1.08% |
240.364 |
|
MicroBenchmarks/ImageProcessing/Blur/blur.test:BENCHMARK_boxBlurKernel/512
|
-1.37% |
6625.750 |
6534.757 |
10.128 |
-1.19% |
10.128 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint64_t>/51
|
-1.36% |
228.997 |
225.881 |
0.009 |
-1.37% |
0.009 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC128
|
-1.27% |
198.366 |
195.851 |
0.007 |
-1.27% |
0.007 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC127
|
-1.27% |
197.097 |
194.603 |
0.012 |
-1.27% |
0.012 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<16, EqZero, Mid>
|
-1.23% |
8657.812 |
8551.684 |
28.281 |
-1.22% |
28.281 |
|
MultiSource/Benchmarks/MallocBench/cfrac/cfrac
Profile
|
-1.22% |
2.778 |
2.744 |
0.000 |
-1.30% |
0.000 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<32, GreaterThanZero, Mid>
|
-1.21% |
4552.337 |
4497.466 |
11.459 |
-1.27% |
11.459 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_sinhf_novec_float_
|
-1.15% |
2242.582 |
2216.828 |
0.788 |
-1.12% |
0.788 |
|
SingleSource/Benchmarks/SmallPT/smallpt
Profile
|
-1.09% |
30.033 |
29.704 |
0.004 |
-1.08% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_sinhf_autovec_float_
|
-1.09% |
2241.819 |
2217.333 |
0.608 |
-1.13% |
0.608 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<16, LessThanZero, Last>
|
-1.08% |
13143.932 |
13002.259 |
10.170 |
-1.06% |
10.170 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C++/PENNANT/PENNANT
Profile
|
-1.04% |
4.785 |
4.736 |
0.019 |
-1.69% |
0.019 |
|
MultiSource/Benchmarks/ASC_Sequoia/AMGmk/AMGmk
Profile
|
-1.03% |
33.126 |
32.786 |
0.038 |
-0.82% |
0.038 |
|
External/SPEC/CINT2017rate/541.leela_r/541.leela_r
Profile
|
-1.01% |
228.011 |
225.712 |
0.274 |
-1.60% |
0.274 |