|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_INT_PREDICT_RAW/44217
|
-59.19% |
19498.200 |
7957.960 |
115.246 |
-12.06% |
115.246 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint64_t_To_uint32_t_
|
-49.03% |
35370.805 |
18028.210 |
1227.017 |
-48.95% |
1227.017 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint64_t_To_uint8_t_
|
-48.99% |
37268.712 |
19012.172 |
41.015 |
-48.70% |
41.015 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint64_t_To_uint16_t_
|
-48.94% |
35885.805 |
18322.426 |
627.060 |
-48.65% |
627.060 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_DIFF_PREDICT_RAW/44217
|
-44.06% |
24163.937 |
13517.143 |
296.201 |
-41.99% |
296.201 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint16_t_To_uint64_t_
|
-43.96% |
18636.547 |
10443.911 |
3.371 |
-44.08% |
3.371 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C/miniGMG/miniGMG
Profile
|
-43.91% |
8.138 |
4.564 |
0.373 |
-50.34% |
0.373 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIRST_DIFF_RAW/44217
|
-43.50% |
180.150 |
101.785 |
0.993 |
-28.57% |
0.993 |
|
MultiSource/Benchmarks/MiBench/automotive-bitcount/automotive-bitcount
Profile
|
-43.38% |
0.178 |
0.101 |
0.003 |
-18.55% |
0.003 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_DIFF_PREDICT_LAMBDA/44217
|
-42.22% |
23344.556 |
13488.931 |
337.854 |
-41.61% |
337.854 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint8_t_To_uint64_t_
|
-41.20% |
17844.864 |
10492.718 |
21.195 |
-41.05% |
21.195 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_DIFF_PREDICT_LAMBDA/5001
|
-41.15% |
2568.225 |
1511.466 |
36.709 |
-39.77% |
36.709 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_DIFF_PREDICT_RAW/5001
|
-40.67% |
2556.339 |
1516.699 |
42.745 |
-41.09% |
42.745 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint64_t_To_uint32_t_
|
-40.64% |
38198.606 |
22674.594 |
63.974 |
-40.57% |
63.974 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint32_t_To_uint64_t_
|
-37.19% |
22680.753 |
14246.844 |
291.820 |
-37.31% |
291.820 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/32
|
-36.69% |
1396.250 |
883.918 |
0.102 |
-36.69% |
0.102 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/64
|
-36.68% |
6183.016 |
3914.829 |
0.661 |
-36.68% |
0.661 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/16
|
-36.65% |
279.542 |
177.092 |
0.014 |
-36.63% |
0.014 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/256
|
-36.16% |
107114.208 |
68384.658 |
6.585 |
-36.18% |
6.585 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/128
|
-36.12% |
26265.253 |
16779.005 |
10.235 |
-36.13% |
10.235 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint64_t_To_uint16_t_
|
-35.05% |
29347.015 |
19060.830 |
46.263 |
-34.16% |
46.263 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint64_t_To_uint8_t_
|
-34.32% |
30245.862 |
19865.891 |
56.878 |
-34.02% |
56.878 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_PIC_2D_RAW/5001
|
-33.30% |
1190.909 |
794.377 |
69.297 |
-26.34% |
69.297 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, EqZero, None>
|
-31.24% |
20512.115 |
14104.223 |
0.597 |
-31.24% |
0.597 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_HYDRO_2D_LAMBDA/44217
|
-30.99% |
83913.203 |
57911.012 |
795.878 |
-36.31% |
795.878 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIRST_DIFF_LAMBDA/44217
|
-29.68% |
143.413 |
100.851 |
1.102 |
-30.36% |
1.102 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_HYDRO_2D_LAMBDA/5001
|
-29.20% |
9047.544 |
6405.919 |
113.021 |
-29.71% |
113.021 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint64_t_To_uint16_t_
|
-28.58% |
25912.810 |
18505.817 |
45.678 |
-28.54% |
45.678 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint32_t_To_uint8_t_
|
-28.09% |
13507.526 |
9713.599 |
31.511 |
-27.88% |
31.511 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_PIC_2D_LAMBDA/44217
|
-27.88% |
11957.547 |
8624.222 |
75.662 |
-21.33% |
75.662 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC128
|
-27.81% |
1296.455 |
935.936 |
4.731 |
-27.61% |
4.731 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC64
|
-27.24% |
656.177 |
477.462 |
0.092 |
-26.95% |
0.092 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC128
|
-27.22% |
560.255 |
407.745 |
0.028 |
-26.87% |
0.028 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC32
|
-27.08% |
335.428 |
244.587 |
0.170 |
-26.76% |
0.170 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC16
|
-26.51% |
174.887 |
128.525 |
0.176 |
-26.04% |
0.176 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC64
|
-26.01% |
293.603 |
217.228 |
0.079 |
-25.56% |
0.079 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIRST_SUM_RAW/44217
|
-25.38% |
181.902 |
135.735 |
0.470 |
-18.40% |
0.470 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint64_t_To_uint8_t_
|
-24.03% |
27167.649 |
20640.337 |
99.299 |
-24.18% |
99.299 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, EqZero, None>
|
-24.00% |
16026.418 |
12180.820 |
0.563 |
-23.98% |
0.563 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC32
|
-23.90% |
160.334 |
122.021 |
0.081 |
-23.20% |
0.081 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC128
|
-23.05% |
602.671 |
463.763 |
0.035 |
-23.21% |
0.035 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC128
|
-22.95% |
602.720 |
464.414 |
0.009 |
-23.10% |
0.009 |
|
MicroBenchmarks/ImageProcessing/Blur/blur.test:BENCHMARK_boxBlurKernel/1024
|
-22.61% |
30089.516 |
23285.689 |
71.057 |
-22.76% |
71.057 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint16_t_To_uint64_t_
|
-22.43% |
13358.486 |
10362.837 |
0.782 |
-21.54% |
0.782 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC127
|
-22.09% |
614.588 |
478.813 |
0.010 |
-22.17% |
0.010 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC64
|
-22.04% |
312.264 |
243.434 |
0.002 |
-22.35% |
0.002 |
|
SingleSource/Benchmarks/Adobe-C++/loop_unroll
Profile
|
-21.99% |
3.105 |
2.422 |
0.002 |
-22.04% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC127
|
-21.89% |
614.581 |
480.029 |
0.042 |
-21.97% |
0.042 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC64
|
-21.84% |
312.232 |
244.043 |
0.017 |
-22.16% |
0.017 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint8_t_To_uint32_t_
|
-21.71% |
6603.217 |
5169.702 |
0.658 |
-21.46% |
0.658 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint16_t_To_uint32_t_
|
-21.66% |
7107.647 |
5568.209 |
3.263 |
-21.59% |
3.263 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_only_autovec_uint8_t_
|
-21.34% |
182340.283 |
143434.498 |
25.264 |
-21.34% |
25.264 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIND_FIRST_MIN_LAMBDA/44217
|
-21.31% |
389.462 |
306.464 |
0.319 |
-21.33% |
0.319 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIND_FIRST_MIN_LAMBDA/171
|
-21.28% |
1.501 |
1.181 |
0.000 |
-21.29% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIND_FIRST_MIN_LAMBDA/5001
|
-20.78% |
45.207 |
35.811 |
0.228 |
-20.87% |
0.228 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC16
|
-20.49% |
93.661 |
74.466 |
0.027 |
-19.30% |
0.027 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC63
|
-20.27% |
324.159 |
258.455 |
0.015 |
-20.42% |
0.015 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC32
|
-20.22% |
167.076 |
133.285 |
0.003 |
-20.82% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC127
|
-20.14% |
275.058 |
219.673 |
0.299 |
-20.25% |
0.299 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC128
|
-20.13% |
274.691 |
219.384 |
1.745 |
-20.15% |
1.745 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC16
|
-19.99% |
97.759 |
78.216 |
0.001 |
-18.30% |
0.001 |
|
MultiSource/Benchmarks/Trimaran/enc-pc1/enc-pc1
Profile
|
-19.93% |
1.130 |
0.905 |
0.000 |
-18.09% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC127
|
-19.90% |
642.314 |
514.488 |
0.119 |
-19.67% |
0.119 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC63
|
-19.88% |
324.151 |
259.701 |
0.014 |
-20.04% |
0.014 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC32
|
-19.85% |
167.083 |
133.909 |
0.001 |
-20.45% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC63
|
-19.72% |
150.116 |
120.506 |
4.514 |
-19.62% |
4.514 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint8_t_To_uint64_t_
|
-19.69% |
13589.395 |
10914.142 |
8.509 |
-16.46% |
8.509 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint32_t_To_uint8_t_
|
-19.39% |
13904.868 |
11208.421 |
63.240 |
-19.37% |
63.240 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_INT_PREDICT_RAW/5001
|
-19.08% |
1101.576 |
891.358 |
10.201 |
-2.42% |
10.201 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC64
|
-19.08% |
148.762 |
120.377 |
3.608 |
-19.01% |
3.608 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint16_t_To_uint8_t_
|
-19.06% |
3817.037 |
3089.539 |
0.152 |
-19.08% |
0.152 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_VOL3D_CALC_RAW/2
|
-18.81% |
8.757 |
7.110 |
0.000 |
-18.80% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_VOL3D_CALC_LAMBDA/2
|
-18.80% |
8.757 |
7.111 |
0.001 |
-18.80% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint32_t_To_uint16_t_
|
-18.46% |
13803.567 |
11255.054 |
9.391 |
-18.48% |
9.391 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint64_t_To_uint32_t_
|
-18.44% |
27099.460 |
22101.810 |
35.445 |
-18.30% |
35.445 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_PIC_1D_LAMBDA/44217
|
-18.41% |
13431.994 |
10959.808 |
41.329 |
-18.60% |
41.329 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_with_cond_arith_novec_uint8_t_
|
-17.87% |
746047.260 |
612708.331 |
287.932 |
-17.84% |
287.932 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIRST_SUM_LAMBDA/44217
|
-17.48% |
163.820 |
135.189 |
0.262 |
-19.09% |
0.262 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_with_cond_arith_novec_int32_t_
|
-17.43% |
740626.275 |
611515.408 |
817.780 |
-17.38% |
817.780 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC4
|
-17.35% |
17.521 |
14.480 |
0.011 |
-17.35% |
0.011 |
|
MultiSource/Benchmarks/MiBench/security-rijndael/security-rijndael
Profile
|
-17.33% |
0.335 |
0.277 |
0.000 |
-17.25% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC31
|
-17.13% |
178.953 |
148.296 |
0.008 |
-17.42% |
0.008 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC128
|
-17.08% |
569.500 |
472.208 |
0.019 |
-17.24% |
0.019 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_PIC_2D_LAMBDA/5001
|
-17.05% |
1123.433 |
931.862 |
27.161 |
-15.71% |
27.161 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC64
|
-16.77% |
296.619 |
246.869 |
0.017 |
-17.08% |
0.017 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC16
|
-16.55% |
94.481 |
78.843 |
0.004 |
-17.65% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC31
|
-16.47% |
179.037 |
149.557 |
0.003 |
-16.72% |
0.003 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_VOL3D_CALC_LAMBDA/0
|
-16.40% |
1267.830 |
1059.956 |
1.835 |
-16.38% |
1.835 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_VOL3D_CALC_RAW/0
|
-16.38% |
1269.511 |
1061.627 |
1.397 |
-16.09% |
1.397 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC31
|
-16.24% |
87.188 |
73.029 |
1.560 |
-15.20% |
1.560 |
|
MicroBenchmarks/ImageProcessing/Dilate/Dilate.test:BENCHMARK_DILATE/1024
|
-16.23% |
7538.515 |
6315.049 |
233.978 |
-11.19% |
233.978 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC32
|
-16.21% |
160.190 |
134.227 |
0.012 |
-16.83% |
0.012 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_HYDRO_1D_RAW/171
|
-16.19% |
0.444 |
0.372 |
0.000 |
-15.83% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_VOL3D_CALC_LAMBDA/1
|
-16.11% |
260.235 |
218.320 |
0.040 |
-16.09% |
0.040 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_VOL3D_CALC_RAW/1
|
-16.06% |
260.058 |
218.296 |
0.136 |
-16.08% |
0.136 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC32
|
-15.94% |
85.281 |
71.685 |
2.175 |
-15.99% |
2.175 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_HYDRO_1D_LAMBDA/171
|
-15.77% |
0.441 |
0.372 |
0.000 |
-15.87% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint16_t_To_uint32_t_
|
-15.67% |
7463.468 |
6293.927 |
0.977 |
-15.66% |
0.977 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint32_t_To_uint8_t_
|
-15.50% |
10639.533 |
8990.857 |
32.167 |
-15.14% |
32.167 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_no_runtime_checks_needed<16, int>
|
-15.39% |
24.405 |
20.649 |
0.001 |
-15.39% |
0.001 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, EqZero, First>
|
-15.39% |
16668.177 |
14103.735 |
0.421 |
-15.40% |
0.421 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, EqZero, Mid>
|
-15.38% |
16668.089 |
14104.287 |
0.455 |
-15.37% |
0.455 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, EqZero, Last>
|
-15.37% |
16671.829 |
14109.292 |
0.309 |
-15.35% |
0.309 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC16
|
-15.35% |
91.987 |
77.870 |
0.028 |
-16.38% |
0.028 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC127
|
-14.78% |
605.137 |
515.724 |
0.143 |
-14.86% |
0.143 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC128
|
-14.47% |
1102.119 |
942.624 |
0.009 |
-14.56% |
0.009 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC127
|
-14.45% |
1094.448 |
936.336 |
0.057 |
-14.51% |
0.057 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC4
|
-14.30% |
112.945 |
96.799 |
0.239 |
-14.40% |
0.239 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint8_t_To_uint16_t_
|
-14.28% |
3757.063 |
3220.629 |
7.490 |
-14.27% |
7.490 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_DISC_ORD_LAMBDA/44217
|
-14.25% |
13232.131 |
11347.087 |
67.956 |
-19.26% |
67.956 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC64
|
-14.15% |
561.280 |
481.858 |
0.028 |
-14.31% |
0.028 |
|
SingleSource/Benchmarks/Misc/salsa20
Profile
|
-14.14% |
15.387 |
13.211 |
0.000 |
-14.12% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC63
|
-14.12% |
553.822 |
475.605 |
0.013 |
-14.27% |
0.013 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC8
|
-13.86% |
51.937 |
44.738 |
0.005 |
-13.86% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC7
|
-13.86% |
51.932 |
44.737 |
0.003 |
-13.86% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC4
|
-13.86% |
51.934 |
44.738 |
0.001 |
-13.86% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC1
|
-13.85% |
51.935 |
44.740 |
0.004 |
-13.85% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC3
|
-13.85% |
51.936 |
44.741 |
0.002 |
-13.85% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC2
|
-13.85% |
51.934 |
44.739 |
0.002 |
-13.85% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC63
|
-13.78% |
376.003 |
324.174 |
0.031 |
-13.42% |
0.031 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_with_cond_arith_autovec_int64_t_
|
-13.73% |
790680.850 |
682104.082 |
1661.169 |
-13.83% |
1661.169 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_with_cond_arith_novec_int64_t_
|
-13.68% |
789940.427 |
681883.438 |
584.817 |
-13.47% |
584.817 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, EqZero, Mid>
|
-13.62% |
14102.938 |
12181.753 |
0.818 |
-13.62% |
0.818 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, EqZero, First>
|
-13.62% |
14103.424 |
12182.221 |
0.123 |
-13.62% |
0.123 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, EqZero, Last>
|
-13.62% |
14102.855 |
12182.407 |
0.151 |
-13.63% |
0.151 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC8
|
-13.60% |
57.572 |
49.743 |
0.001 |
-15.35% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC32
|
-13.55% |
290.965 |
251.548 |
0.011 |
-13.85% |
0.011 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC8
|
-13.54% |
23.151 |
20.017 |
0.003 |
-13.54% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint64_t_To_uint8_t_
|
-13.50% |
22075.327 |
19095.917 |
104.898 |
-13.39% |
104.898 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint32_t_To_uint16_t_
|
-13.48% |
12809.477 |
11083.391 |
16.618 |
-13.66% |
16.618 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC31
|
-13.46% |
283.450 |
245.292 |
0.009 |
-13.66% |
0.009 |
|
External/SPEC/CFP2017rate/508.namd_r/508.namd_r
Profile
|
-13.43% |
223.259 |
193.271 |
0.098 |
-13.56% |
0.098 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint32_t_To_uint8_t_
|
-13.38% |
11038.766 |
9562.004 |
55.776 |
-14.08% |
55.776 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC8
|
-13.16% |
23.778 |
20.649 |
0.001 |
-13.16% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC128
|
-13.08% |
81.348 |
70.704 |
0.003 |
-13.08% |
0.003 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_INT_PREDICT_LAMBDA/44217
|
-13.04% |
9244.557 |
8039.227 |
69.817 |
-3.58% |
69.817 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC16
|
-13.02% |
51.934 |
45.170 |
0.388 |
-13.04% |
0.388 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint8_t_To_uint16_t_
|
-12.94% |
4541.556 |
3953.709 |
0.491 |
-12.95% |
0.491 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC8
|
-12.91% |
58.194 |
50.683 |
0.003 |
-14.75% |
0.003 |
|
SingleSource/Benchmarks/Shootout-C++/Shootout-C++-matrix
Profile
|
-12.74% |
2.509 |
2.190 |
0.000 |
-12.71% |
0.000 |
|
MicroBenchmarks/ImageProcessing/Dilate/Dilate.test:BENCHMARK_DILATE/128
|
-12.54% |
224.086 |
195.983 |
5.298 |
-14.03% |
5.298 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC63
|
-12.52% |
332.272 |
290.680 |
0.005 |
-12.66% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC16
|
-12.45% |
155.810 |
136.408 |
0.006 |
-13.10% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint16_t_To_uint8_t_
|
-12.42% |
4744.065 |
4154.865 |
0.317 |
-12.40% |
0.317 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC15
|
-12.35% |
106.370 |
93.232 |
0.003 |
-12.87% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC15
|
-12.24% |
148.293 |
130.147 |
0.015 |
-12.54% |
0.015 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIRST_SUM_RAW/5001
|
-12.03% |
20.270 |
17.832 |
0.574 |
2.80% |
0.574 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC8
|
-11.82% |
58.190 |
51.310 |
0.002 |
-13.69% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC2
|
-11.77% |
21.275 |
18.772 |
0.001 |
-11.77% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC16
|
-11.45% |
33.163 |
29.366 |
0.020 |
-11.45% |
0.020 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC15
|
-11.44% |
51.936 |
45.992 |
0.001 |
-11.45% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC15
|
-11.17% |
106.372 |
94.489 |
0.002 |
-11.70% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC4
|
-11.12% |
22.526 |
20.022 |
0.002 |
-11.12% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC4
|
-11.11% |
22.526 |
20.023 |
0.001 |
-11.11% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC3
|
-11.11% |
22.526 |
20.024 |
0.000 |
-11.11% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint8_t>/51
|
-11.00% |
123.886 |
110.263 |
0.306 |
19.20% |
0.306 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint32_t_To_uint64_t_
|
-10.77% |
17028.100 |
15194.984 |
200.923 |
-11.64% |
200.923 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC8
|
-10.65% |
88.230 |
78.837 |
0.005 |
-11.82% |
0.005 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_BAND_LIN_EQ_RAW/171
|
-10.61% |
0.384 |
0.343 |
0.000 |
-6.33% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_BAND_LIN_EQ_LAMBDA/171
|
-10.60% |
0.384 |
0.343 |
0.000 |
-6.33% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC4
|
-10.53% |
23.777 |
21.274 |
0.001 |
-10.54% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC64
|
-10.47% |
53.813 |
48.181 |
0.002 |
-10.47% |
0.002 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/16
|
-10.19% |
115.466 |
103.704 |
0.025 |
-10.19% |
0.025 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint8_t_To_uint16_t_
|
-10.10% |
5846.300 |
5255.731 |
22.257 |
-10.16% |
22.257 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/64
|
-10.09% |
1914.575 |
1721.421 |
0.901 |
-10.03% |
0.901 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC7
|
-10.09% |
80.720 |
72.578 |
0.005 |
-10.74% |
0.005 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/32
|
-9.98% |
473.015 |
425.791 |
0.020 |
-9.98% |
0.020 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/256
|
-9.96% |
31449.398 |
28317.352 |
7.628 |
-9.96% |
7.628 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_only_autovec_int64_t_
|
-9.90% |
333574.887 |
300547.807 |
564.057 |
-9.82% |
564.057 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC8
|
-9.76% |
25.656 |
23.151 |
0.001 |
-9.76% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC8
|
-9.76% |
25.654 |
23.151 |
0.002 |
-9.77% |
0.002 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/128
|
-9.68% |
7907.678 |
7141.999 |
1.376 |
-9.79% |
1.376 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC7
|
-9.62% |
32.538 |
29.409 |
0.001 |
-9.62% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC7
|
-9.53% |
26.281 |
23.777 |
0.006 |
-9.53% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC1
|
-9.52% |
13.140 |
11.889 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC7
|
-9.52% |
26.279 |
23.778 |
0.001 |
-9.53% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC32
|
-9.44% |
53.188 |
48.169 |
0.007 |
-9.45% |
0.007 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_DIFF_PREDICT_RAW/171
|
-9.43% |
12.266 |
11.110 |
0.046 |
-6.89% |
0.046 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC127
|
-9.26% |
101.367 |
91.980 |
0.004 |
-9.72% |
0.004 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_DEL_DOT_VEC_2D_RAW/1
|
-9.20% |
287.091 |
260.685 |
0.049 |
-9.17% |
0.049 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_DEL_DOT_VEC_2D_LAMBDA/1
|
-9.15% |
287.025 |
260.762 |
0.034 |
-9.18% |
0.034 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC31
|
-9.14% |
195.877 |
177.974 |
0.022 |
-9.41% |
0.022 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_INT_PREDICT_LAMBDA/5001
|
-9.02% |
1001.036 |
910.704 |
7.281 |
0.66% |
7.281 |
|
MultiSource/Benchmarks/FreeBench/pifft/pifft
Profile
|
-8.95% |
0.359 |
0.327 |
0.000 |
-8.74% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC7
|
-8.88% |
28.156 |
25.655 |
0.002 |
-8.90% |
0.002 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_runtime_checks_fail<4, int>
|
-8.87% |
16.823 |
15.330 |
0.000 |
-3.63% |
0.000 |
|
SingleSource/Benchmarks/Stanford/Puzzle
Profile
|
-8.83% |
0.247 |
0.226 |
0.005 |
-6.53% |
0.005 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_DEL_DOT_VEC_2D_RAW/2
|
-8.72% |
3.510 |
3.204 |
0.000 |
-8.71% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_DEL_DOT_VEC_2D_LAMBDA/2
|
-8.70% |
3.510 |
3.204 |
0.000 |
-8.70% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC16
|
-8.62% |
36.293 |
33.165 |
0.000 |
-8.62% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint16_t_To_uint8_t_
|
-8.53% |
6811.513 |
6230.224 |
24.577 |
-8.59% |
24.577 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC8
|
-8.51% |
29.410 |
26.907 |
0.000 |
-8.51% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC64
|
-8.06% |
93.231 |
85.720 |
0.003 |
-8.07% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint8_t_To_uint32_t_
|
-8.05% |
12777.773 |
11748.875 |
27.538 |
-8.06% |
27.538 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC4
|
-8.01% |
54.419 |
50.060 |
0.002 |
-10.07% |
0.002 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_DEL_DOT_VEC_2D_RAW/0
|
-7.89% |
1802.090 |
1659.882 |
5.516 |
-7.83% |
5.516 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC16
|
-7.85% |
31.912 |
29.408 |
0.001 |
-7.85% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC16
|
-7.85% |
31.913 |
29.409 |
0.001 |
-7.84% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC4
|
-7.81% |
40.044 |
36.918 |
0.002 |
-10.61% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC32
|
-7.81% |
40.044 |
36.917 |
0.002 |
-7.82% |
0.002 |
|
MultiSource/Applications/lambda-0.1.3/lambda
Profile
|
-7.74% |
15.948 |
14.714 |
0.006 |
-7.28% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC15
|
-7.69% |
32.537 |
30.035 |
0.001 |
-7.69% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC15
|
-7.69% |
32.536 |
30.035 |
0.001 |
-7.70% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_HYDRO_2D_LAMBDA/171
|
-7.66% |
88.902 |
82.090 |
0.639 |
-7.41% |
0.639 |
|
MultiSource/Benchmarks/VersaBench/beamformer/beamformer
Profile
|
-7.65% |
5.202 |
4.805 |
0.001 |
-7.62% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC7
|
-7.62% |
350.947 |
324.189 |
0.515 |
-8.60% |
0.515 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_DIFF_PREDICT_LAMBDA/171
|
-7.54% |
12.011 |
11.106 |
0.016 |
-7.34% |
0.016 |
|
MultiSource/Benchmarks/Trimaran/enc-md5/enc-md5
Profile
|
-7.54% |
3.507 |
3.243 |
0.000 |
-7.50% |
0.000 |
|
SingleSource/Benchmarks/Misc/richards_benchmark
Profile
|
-7.51% |
2.201 |
2.036 |
0.001 |
4.21% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_DEL_DOT_VEC_2D_LAMBDA/0
|
-7.49% |
1794.868 |
1660.392 |
3.560 |
-7.34% |
3.560 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint16_t_To_uint64_t_
|
-7.48% |
20219.236 |
18707.024 |
31.078 |
-7.13% |
31.078 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_xor_no_runtime_checks_needed<16, int>
|
-7.41% |
16.895 |
15.642 |
0.001 |
-7.42% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC2
|
-7.32% |
16.895 |
15.658 |
0.132 |
0.04% |
0.132 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint16_t_To_uint64_t_
|
-7.28% |
25071.673 |
23246.667 |
46.876 |
-6.96% |
46.876 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIRST_SUM_LAMBDA/5001
|
-7.22% |
18.890 |
17.525 |
0.334 |
-0.47% |
0.334 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC128
|
-7.22% |
173.334 |
160.817 |
0.006 |
-7.22% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint8_t>/127
|
-7.20% |
138.908 |
128.904 |
0.005 |
-7.21% |
0.005 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIND_FIRST_MIN_RAW/171
|
-7.19% |
1.497 |
1.389 |
0.000 |
-7.19% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_HYDRO_2D_RAW/171
|
-7.05% |
88.771 |
82.508 |
0.291 |
-6.90% |
0.291 |
|
SingleSource/Benchmarks/Misc/pi
Profile
|
-7.04% |
1.783 |
1.657 |
0.000 |
-7.02% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC15
|
-6.94% |
45.051 |
41.923 |
0.024 |
-6.95% |
0.024 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC127
|
-6.94% |
2403.087 |
2236.362 |
8.883 |
-7.84% |
8.883 |
|
MultiSource/Benchmarks/McCat/12-IOtest/iotest
Profile
|
-6.90% |
1.844 |
1.717 |
0.032 |
-5.92% |
0.032 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC15
|
-6.90% |
54.441 |
50.686 |
0.003 |
-6.90% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC8
|
-6.89% |
26.208 |
24.402 |
0.001 |
-9.33% |
0.001 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C++/miniFE/miniFE
Profile
|
-6.79% |
16.037 |
14.948 |
0.074 |
-6.39% |
0.074 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC31
|
-6.73% |
74.459 |
69.451 |
0.006 |
-6.73% |
0.006 |
|
SingleSource/Benchmarks/Misc/oourafft
Profile
|
-6.71% |
15.394 |
14.361 |
0.070 |
-4.85% |
0.070 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC3
|
-6.67% |
46.931 |
43.800 |
0.003 |
-7.90% |
0.003 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_runtime_checks_pass<4, int>
|
-6.66% |
16.423 |
15.329 |
0.002 |
-8.25% |
0.002 |
|
SingleSource/Benchmarks/Misc/flops-6
Profile
|
-6.55% |
1.312 |
1.226 |
0.001 |
-6.55% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC63
|
-6.55% |
114.515 |
107.015 |
0.211 |
-6.55% |
0.211 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_xor_runtime_checks_pass<16, int>
|
-6.52% |
28.783 |
26.905 |
0.001 |
-6.52% |
0.001 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_xor_runtime_checks_fail<16, int>
|
-6.52% |
28.785 |
26.908 |
0.001 |
-6.51% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_only_autovec_int32_t_
|
-6.41% |
180978.536 |
169377.059 |
525.958 |
-6.48% |
525.958 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC127
|
-6.41% |
194.614 |
182.142 |
0.343 |
-6.41% |
0.343 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_PRESSURE_CALC_LAMBDA/5001
|
-6.36% |
44.267 |
41.452 |
0.180 |
-5.74% |
0.180 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC15
|
-6.35% |
39.420 |
36.917 |
0.010 |
-6.35% |
0.010 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint16_t>/127
|
-6.31% |
138.921 |
130.158 |
0.001 |
-6.30% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC7
|
-6.25% |
70.080 |
65.702 |
0.001 |
-7.09% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC4
|
-6.25% |
40.046 |
37.544 |
0.002 |
-9.09% |
0.002 |
|
SingleSource/Benchmarks/Misc-C++/Large/sphereflake
Profile
|
-6.22% |
20.013 |
18.768 |
0.004 |
-6.17% |
0.004 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_BAND_LIN_EQ_LAMBDA/5001
|
-6.21% |
21.409 |
20.080 |
0.147 |
-3.46% |
0.147 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC16
|
-6.15% |
40.671 |
38.171 |
0.002 |
-6.15% |
0.002 |
|
External/SPEC/CFP2017rate/538.imagick_r/538.imagick_r
Profile
|
-5.95% |
292.246 |
274.850 |
0.195 |
-5.90% |
0.195 |
|
MultiSource/Benchmarks/MiBench/telecomm-gsm/telecomm-gsm
Profile
|
-5.95% |
0.663 |
0.624 |
0.000 |
-5.97% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint8_t>/65
|
-5.93% |
95.120 |
89.481 |
0.004 |
-5.92% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC63
|
-5.93% |
73.834 |
69.458 |
0.002 |
-6.42% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC1
|
-5.92% |
88.909 |
83.649 |
0.269 |
-6.00% |
0.269 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC3
|
-5.83% |
21.274 |
20.033 |
0.055 |
0.04% |
0.055 |
|
MultiSource/Benchmarks/Rodinia/hotspot/hotspot
Profile
|
-5.83% |
2.037 |
1.918 |
0.003 |
-5.80% |
0.003 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIND_FIRST_MIN_RAW/5001
|
-5.83% |
45.232 |
42.596 |
0.078 |
-6.05% |
0.078 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1LoopWithReductionTC4
|
-5.72% |
15.265 |
14.391 |
0.001 |
2.26% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint32_t_To_uint64_t_
|
-5.71% |
21519.403 |
20291.587 |
24.646 |
-5.40% |
24.646 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC16
|
-5.69% |
31.912 |
30.095 |
0.051 |
-3.82% |
0.051 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC16
|
-5.66% |
33.165 |
31.287 |
0.001 |
-5.66% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC32
|
-5.64% |
44.423 |
41.920 |
0.004 |
-5.64% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC32
|
-5.63% |
44.427 |
41.924 |
0.003 |
-5.64% |
0.003 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_PIC_2D_LAMBDA/171
|
-5.61% |
13.522 |
12.764 |
0.063 |
-5.44% |
0.063 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC31
|
-5.59% |
242.576 |
229.022 |
0.019 |
-5.06% |
0.019 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_PRESSURE_CALC_RAW/44217
|
-5.57% |
507.656 |
479.373 |
2.258 |
-4.54% |
2.258 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC31
|
-5.56% |
45.052 |
42.548 |
0.003 |
-5.56% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC31
|
-5.56% |
45.051 |
42.547 |
0.003 |
-5.59% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC128
|
-5.55% |
68.204 |
64.416 |
0.011 |
-6.38% |
0.011 |
|
MultiSource/Benchmarks/SciMark2-C/scimark2
Profile
|
-5.55% |
107.677 |
101.703 |
0.081 |
-5.51% |
0.081 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC127
|
-5.53% |
68.207 |
64.437 |
0.014 |
-5.64% |
0.014 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint8_t_To_uint16_t_
|
-5.46% |
3625.683 |
3427.696 |
34.366 |
-5.66% |
34.366 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint32_t>/127
|
-5.46% |
137.663 |
130.151 |
0.007 |
-5.88% |
0.007 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint32_t>/999
|
-5.39% |
696.521 |
658.997 |
0.023 |
-5.39% |
0.023 |
|
MultiSource/Applications/siod/siod
Profile
|
-5.36% |
8.333 |
7.886 |
0.016 |
-0.93% |
0.016 |
|
SingleSource/Benchmarks/Polybench/stencils/jacobi-2d/jacobi-2d
Profile
|
-5.31% |
32.000 |
30.301 |
0.101 |
-5.97% |
0.101 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_PIC_2D_RAW/171
|
-5.30% |
13.560 |
12.841 |
0.052 |
-5.15% |
0.052 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC1
|
-5.27% |
11.889 |
11.263 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC1
|
-5.26% |
11.888 |
11.263 |
0.002 |
0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint32_t>/999
|
-5.24% |
1365.167 |
1293.683 |
0.069 |
-5.23% |
0.069 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIND_FIRST_MIN_RAW/44217
|
-5.22% |
389.558 |
369.213 |
0.523 |
-5.23% |
0.523 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC32
|
-5.20% |
61.323 |
58.136 |
0.028 |
-5.19% |
0.028 |
|
MultiSource/Applications/aha/aha
Profile
|
-5.18% |
5.004 |
4.745 |
0.003 |
0.17% |
0.003 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_FLOYD_DITHER/256
|
-5.13% |
1824.387 |
1730.763 |
8.328 |
-0.16% |
8.328 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC2
|
-5.10% |
36.922 |
35.040 |
0.002 |
-8.20% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC4
|
-4.88% |
25.654 |
24.403 |
0.001 |
-0.01% |
0.001 |
|
External/SPEC/CINT2017rate/531.deepsjeng_r/531.deepsjeng_r
Profile
|
-4.82% |
267.534 |
254.643 |
0.495 |
-2.10% |
0.495 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint32_t>/256
|
-4.82% |
364.219 |
346.672 |
0.007 |
-4.80% |
0.007 |
|
SingleSource/Benchmarks/Misc/revertBits
Profile
|
-4.68% |
0.641 |
0.611 |
0.000 |
-4.68% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC15
|
-4.66% |
127.647 |
121.696 |
0.003 |
-5.12% |
0.003 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_runtime_checks_fail<16, int>
|
-4.62% |
54.444 |
51.931 |
0.004 |
-4.61% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint16_t>/65
|
-4.61% |
95.117 |
90.733 |
0.001 |
-4.61% |
0.001 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_runtime_checks_pass<16, int>
|
-4.60% |
54.439 |
51.933 |
0.002 |
-4.60% |
0.002 |
|
MultiSource/Benchmarks/MiBench/consumer-typeset/consumer-typeset
Profile
|
-4.60% |
0.749 |
0.714 |
0.004 |
-0.46% |
0.004 |
|
External/SPEC/CINT2017rate/500.perlbench_r/500.perlbench_r
Profile
|
-4.59% |
153.193 |
146.163 |
0.544 |
-0.37% |
0.544 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC31
|
-4.57% |
909.544 |
867.935 |
4.127 |
-5.35% |
4.127 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC2
|
-4.55% |
13.767 |
13.140 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC7
|
-4.47% |
70.082 |
66.951 |
0.003 |
-5.33% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC31
|
-4.47% |
70.084 |
66.955 |
0.002 |
-4.46% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC127
|
-4.30% |
3121.623 |
2987.339 |
21.955 |
-4.52% |
21.955 |
|
MultiSource/Applications/JM/lencod/lencod
Profile
|
-4.29% |
33.041 |
31.622 |
0.014 |
-2.82% |
0.014 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC128
|
-4.27% |
2968.392 |
2841.632 |
20.725 |
-4.46% |
20.725 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint64_t>/999
|
-4.23% |
1811.192 |
1734.499 |
0.102 |
-4.24% |
0.102 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint64_t>/999
|
-4.16% |
3595.245 |
3445.643 |
0.095 |
-4.15% |
0.095 |
|
SingleSource/Benchmarks/Misc/flops-5
Profile
|
-4.16% |
2.020 |
1.936 |
0.001 |
-4.19% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_PRESSURE_CALC_LAMBDA/44217
|
-4.14% |
500.218 |
479.487 |
2.813 |
-3.82% |
2.813 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint64_t>/256
|
-4.09% |
935.630 |
897.361 |
0.093 |
-4.09% |
0.093 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC3
|
-4.08% |
15.656 |
15.017 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_ENERGY_CALC_RAW/171
|
-4.07% |
14.202 |
13.624 |
0.019 |
-4.33% |
0.019 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC31
|
-4.04% |
61.946 |
59.445 |
0.000 |
-4.04% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_ENERGY_CALC_LAMBDA/171
|
-4.03% |
14.197 |
13.625 |
0.018 |
-4.37% |
0.018 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_only_autovec_uint8_t_
|
-3.97% |
96175.835 |
92353.971 |
17.751 |
-3.96% |
17.751 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC32
|
-3.96% |
63.196 |
60.694 |
0.004 |
-3.96% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint32_t>/256
|
-3.96% |
221.532 |
212.760 |
0.013 |
-3.95% |
0.013 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint32_t_To_uint16_t_
|
-3.89% |
9837.354 |
9455.125 |
48.053 |
-4.30% |
48.053 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint8_t_To_uint64_t_
|
-3.82% |
23381.729 |
22488.729 |
27.676 |
-4.24% |
27.676 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC15
|
-3.78% |
539.370 |
518.956 |
1.286 |
-1.22% |
1.286 |
|
External/SPEC/CFP2017rate/519.lbm_r/519.lbm_r
Profile
|
-3.78% |
199.805 |
192.251 |
1.382 |
-4.20% |
1.382 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint64_t_To_uint32_t_
|
-3.72% |
19390.528 |
18668.524 |
47.198 |
-3.23% |
47.198 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC2
|
-3.70% |
16.895 |
16.269 |
0.001 |
0.00% |
0.001 |
|
SingleSource/Benchmarks/Shootout/Shootout-matrix
Profile
|
-3.70% |
3.864 |
3.721 |
0.000 |
-3.69% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC2
|
-3.70% |
16.894 |
16.270 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint64_t>/256
|
-3.65% |
514.413 |
495.650 |
0.022 |
-3.64% |
0.022 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIRST_DIFF_LAMBDA/5001
|
-3.64% |
12.402 |
11.951 |
0.124 |
-1.97% |
0.124 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC64
|
-3.61% |
69.458 |
66.950 |
0.003 |
-3.61% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC64
|
-3.60% |
69.453 |
66.953 |
0.002 |
-3.61% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint16_t_To_uint8_t_
|
-3.60% |
2873.718 |
2770.350 |
23.990 |
-3.75% |
23.990 |
|
MultiSource/Benchmarks/Fhourstones-3.1/fhourstones3.1
Profile
|
-3.59% |
4.047 |
3.902 |
0.021 |
-1.76% |
0.021 |
|
MicroBenchmarks/ImageProcessing/Dilate/Dilate.test:BENCHMARK_DILATE/512
|
-3.59% |
3606.986 |
3477.619 |
22.869 |
-2.97% |
22.869 |
|
SingleSource/Benchmarks/BenchmarkGame/n-body
Profile
|
-3.58% |
2.731 |
2.634 |
0.000 |
21.70% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC63
|
-3.57% |
70.079 |
67.576 |
0.004 |
-3.59% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC63
|
-3.57% |
70.084 |
67.580 |
0.001 |
-3.57% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint8_t>/16
|
-3.53% |
59.535 |
57.431 |
0.449 |
6.71% |
0.449 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<64, GreaterThanZero, None>
|
-3.49% |
3044.406 |
2938.105 |
6.938 |
0.83% |
6.938 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC31
|
-3.42% |
93.981 |
90.766 |
0.220 |
-3.29% |
0.220 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC63
|
-3.42% |
43.176 |
41.699 |
0.041 |
-3.68% |
0.041 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC64
|
-3.34% |
43.174 |
41.730 |
0.018 |
-3.35% |
0.018 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint32_t>/65
|
-3.34% |
93.858 |
90.726 |
0.003 |
-3.98% |
0.003 |
|
MultiSource/Benchmarks/nbench/nbench
Profile
|
-3.27% |
6.105 |
5.906 |
0.002 |
-3.61% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC63
|
-3.26% |
1731.977 |
1675.570 |
6.972 |
-3.54% |
6.972 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint8_t>/28
|
-3.25% |
79.102 |
76.534 |
0.610 |
13.23% |
0.610 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC63
|
-3.21% |
1638.997 |
1586.444 |
10.147 |
-3.48% |
10.147 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC32
|
-3.19% |
744.166 |
720.437 |
6.480 |
-4.03% |
6.480 |
|
MultiSource/Benchmarks/Rodinia/pathfinder/pathfinder
Profile
|
-3.17% |
1.266 |
1.226 |
0.007 |
-2.53% |
0.007 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint16_t>/999
|
-3.16% |
515.013 |
498.733 |
0.018 |
-3.16% |
0.018 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint16_t_To_uint8_t_
|
-3.15% |
4512.093 |
4370.037 |
20.927 |
-3.26% |
20.927 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC31
|
-3.13% |
60.069 |
58.189 |
0.006 |
-3.46% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC7
|
-3.13% |
37.544 |
36.370 |
0.076 |
0.20% |
0.076 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1BigLoopWithReductionTC1
|
-3.12% |
20.024 |
19.398 |
0.002 |
-3.13% |
0.002 |
|
SingleSource/Benchmarks/Shootout/Shootout-lists
Profile
|
-3.12% |
11.316 |
10.962 |
0.012 |
-3.09% |
0.012 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchVecWithRuntimeChecks4PointersDBeforeA/1000
|
-3.09% |
5020760.173 |
4865574.917 |
205.225 |
-3.07% |
205.225 |
|
MultiSource/Benchmarks/FreeBench/fourinarow/fourinarow
Profile
|
-3.06% |
0.654 |
0.634 |
0.001 |
-2.58% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1LoopWithReductionTC7
|
-3.03% |
20.649 |
20.023 |
0.000 |
3.20% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC8
|
-2.99% |
41.923 |
40.670 |
0.002 |
-0.01% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC64
|
-2.98% |
1487.143 |
1442.831 |
10.789 |
-3.20% |
10.789 |
|
MicroBenchmarks/ImageProcessing/Dilate/Dilate.test:BENCHMARK_DILATE/256
|
-2.93% |
1052.213 |
1021.367 |
4.060 |
-4.30% |
4.060 |
|
External/SPEC/CFP2017rate/511.povray_r/511.povray_r
Profile
|
-2.90% |
34.511 |
33.511 |
0.081 |
-0.82% |
0.081 |
|
MultiSource/Applications/ClamAV/clamscan
Profile
|
-2.87% |
0.497 |
0.482 |
0.001 |
-1.42% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint16_t>/999
|
-2.85% |
1013.804 |
984.901 |
0.057 |
-2.86% |
0.057 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC64
|
-2.81% |
111.388 |
108.255 |
0.008 |
-2.81% |
0.008 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC1
|
-2.81% |
22.533 |
21.900 |
0.001 |
-2.77% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_ENERGY_CALC_LAMBDA/44217
|
-2.80% |
4356.452 |
4234.481 |
16.214 |
-2.08% |
16.214 |
|
MultiSource/Benchmarks/FreeBench/mason/mason
Profile
|
-2.79% |
0.553 |
0.537 |
0.001 |
-2.84% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1LoopWithReductionTC8
|
-2.78% |
22.527 |
21.899 |
0.001 |
2.93% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_PIC_1D_LAMBDA/5001
|
-2.77% |
345.324 |
335.752 |
2.822 |
-4.87% |
2.822 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC1
|
-2.77% |
22.525 |
21.901 |
0.001 |
-2.78% |
0.001 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C/CoMD/CoMD
Profile
|
-2.69% |
9.908 |
9.641 |
0.007 |
-2.61% |
0.007 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC31
|
-2.63% |
23.778 |
23.152 |
0.001 |
-5.13% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC31
|
-2.63% |
23.777 |
23.151 |
0.001 |
-5.13% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC32
|
-2.63% |
23.777 |
23.153 |
0.001 |
-5.12% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC32
|
-2.62% |
23.777 |
23.153 |
0.002 |
-5.13% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC63
|
-2.60% |
120.142 |
117.021 |
0.004 |
-2.60% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint8_t>/10
|
-2.57% |
48.809 |
47.553 |
0.010 |
2.46% |
0.010 |
|
SingleSource/Benchmarks/Misc-C++/oopack_v1p8
Profile
|
-2.57% |
0.479 |
0.467 |
0.000 |
-9.98% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC31
|
-2.53% |
1511.989 |
1473.666 |
3.502 |
-2.72% |
3.502 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint8_t_To_uint32_t_
|
-2.53% |
7076.494 |
6897.583 |
1.707 |
-2.54% |
1.707 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopTC16
|
-2.52% |
277.843 |
270.836 |
1.263 |
-1.95% |
1.263 |
|
MultiSource/Benchmarks/Olden/health/health
Profile
|
-2.52% |
1.594 |
1.554 |
0.003 |
-2.34% |
0.003 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<63, GreaterThanZero, None>
|
-2.50% |
4742.197 |
4623.469 |
5.542 |
-0.10% |
5.542 |
|
MultiSource/Benchmarks/mafft/pairlocalalign
Profile
|
-2.48% |
93.966 |
91.634 |
0.377 |
-2.58% |
0.377 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_only_autovec_int64_t_
|
-2.48% |
1451048.664 |
1415092.182 |
494.289 |
-2.20% |
494.289 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint64_t_To_uint8_t_
|
-2.47% |
19739.800 |
19251.415 |
53.298 |
-2.97% |
53.298 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC32
|
-2.47% |
50.059 |
48.822 |
0.212 |
-2.46% |
0.212 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint64_t>/10
|
-2.45% |
56.449 |
55.067 |
0.047 |
-0.06% |
0.047 |
|
External/SPEC/CFP2017rate/544.nab_r/544.nab_r
Profile
|
-2.45% |
472.233 |
460.686 |
0.118 |
-3.60% |
0.118 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchVecWithRuntimeChecks4PointersDBeforeA/32
|
-2.44% |
166194.770 |
162133.577 |
5.083 |
-2.45% |
5.083 |
|
MultiSource/Benchmarks/sim/sim
Profile
|
-2.37% |
9.667 |
9.438 |
0.032 |
-2.71% |
0.032 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_FLOYD_DITHER/512
|
-2.35% |
6653.191 |
6496.509 |
10.539 |
-2.24% |
10.539 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_FLOYD_DITHER/128
|
-2.35% |
437.971 |
427.678 |
2.758 |
-2.68% |
2.758 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC63
|
-2.34% |
107.005 |
104.497 |
0.001 |
-2.34% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC64
|
-2.32% |
108.252 |
105.744 |
0.006 |
-2.31% |
0.006 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C/SimpleMOC/SimpleMOC
Profile
|
-2.32% |
10.453 |
10.211 |
0.020 |
-1.86% |
0.020 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<63, LessThanZero, First>
|
-2.31% |
1640.117 |
1602.259 |
0.330 |
0.01% |
0.330 |
|
SingleSource/Benchmarks/BenchmarkGame/puzzle
Profile
|
-2.24% |
0.872 |
0.852 |
0.005 |
-1.89% |
0.005 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<64, GreaterThanZero, Mid>
|
-2.23% |
2731.173 |
2670.162 |
16.159 |
-2.75% |
16.159 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<64, EqZero, None>
|
-2.23% |
2955.513 |
2889.575 |
20.519 |
-1.36% |
20.519 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_ADI_LAMBDA/5001
|
-2.22% |
2251.358 |
2201.443 |
8.999 |
-1.50% |
8.999 |
|
SingleSource/Benchmarks/Misc/flops-1
Profile
|
-2.17% |
9.002 |
8.806 |
0.000 |
-2.15% |
0.000 |
|
SingleSource/Benchmarks/Misc-C++/Large/ray
Profile
|
-2.14% |
12.108 |
11.850 |
0.002 |
-2.08% |
0.002 |
|
MultiSource/Applications/sgefa/sgefa
Profile
|
-2.12% |
0.577 |
0.565 |
0.002 |
-1.55% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC128
|
-2.10% |
119.521 |
117.012 |
0.005 |
-2.10% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC128
|
-2.09% |
119.512 |
117.012 |
0.005 |
-2.10% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC127
|
-2.09% |
120.143 |
117.633 |
0.006 |
-2.09% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC127
|
-2.08% |
120.143 |
117.639 |
0.006 |
-2.09% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_nested_cond_load_novec_int32_t_
|
-2.04% |
634788.710 |
621824.641 |
614.099 |
-3.62% |
614.099 |
|
MultiSource/Benchmarks/tramp3d-v4/tramp3d-v4
Profile
|
-2.01% |
1.076 |
1.054 |
0.004 |
-2.00% |
0.004 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_ENERGY_CALC_RAW/5001
|
-1.86% |
433.759 |
425.702 |
1.085 |
-0.71% |
1.085 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint16_t>/256
|
-1.85% |
272.844 |
267.801 |
0.015 |
-1.85% |
0.015 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_EOS_RAW/171
|
-1.83% |
0.872 |
0.856 |
0.001 |
-1.68% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_INT_PREDICT_LAMBDA/171
|
-1.81% |
6.926 |
6.800 |
0.006 |
-1.80% |
0.006 |
|
MultiSource/Benchmarks/VersaBench/ecbdes/ecbdes
Profile
|
-1.80% |
5.150 |
5.058 |
0.001 |
-1.59% |
0.001 |
|
External/SPEC/CINT2017rate/525.x264_r/525.x264_r
Profile
|
-1.78% |
129.735 |
127.426 |
0.330 |
-1.56% |
0.330 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC15
|
-1.78% |
70.079 |
68.834 |
0.010 |
0.00% |
0.010 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<16, LessThanZero, None>
|
-1.76% |
8322.464 |
8176.011 |
2.635 |
-0.32% |
2.635 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1LoopWithReductionTC15
|
-1.75% |
35.665 |
35.042 |
0.021 |
1.81% |
0.021 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint32_t_To_uint64_t_
|
-1.71% |
26244.782 |
25795.530 |
25.322 |
-1.85% |
25.322 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint64_t>/51
|
-1.69% |
148.303 |
145.797 |
0.003 |
-1.69% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_csa_with_in_loop_arith_novec_int64_t_
|
-1.68% |
1029274.049 |
1011939.155 |
1127.875 |
-1.58% |
1127.875 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint16_t_To_uint32_t_
|
-1.68% |
11238.973 |
11049.761 |
58.714 |
-2.58% |
58.714 |
|
SingleSource/Benchmarks/Misc/ReedSolomon
Profile
|
-1.68% |
20.760 |
20.412 |
0.001 |
-1.85% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1LoopWithReductionTC16
|
-1.67% |
37.542 |
36.916 |
0.002 |
1.71% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopTC15
|
-1.65% |
740.909 |
728.660 |
3.849 |
-1.34% |
3.849 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<3, GreaterThanZero, Mid>
|
-1.65% |
37984.197 |
37356.449 |
65.721 |
-0.14% |
65.721 |
|
SingleSource/Benchmarks/Shootout-C++/Shootout-C++-heapsort
Profile
|
-1.63% |
22.297 |
21.932 |
0.102 |
-0.30% |
0.102 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_EOS_LAMBDA/171
|
-1.63% |
0.872 |
0.857 |
0.001 |
-1.52% |
0.001 |
|
MicroBenchmarks/Builtins/Int128/Builtins.test:BM_RemainderIntrinsic128SmallDivisor<__uint128_t>
|
-1.63% |
72.454 |
71.272 |
0.036 |
-0.64% |
0.036 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC63
|
-1.63% |
130.497 |
128.371 |
0.208 |
-1.38% |
0.208 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, GreaterThanZero, Mid>
|
-1.62% |
31937.240 |
31419.776 |
42.756 |
-0.01% |
42.756 |
|
MicroBenchmarks/Builtins/Int128/Builtins.test:BM_RemainderIntrinsic128UniformDivisor<__int128_t>
|
-1.62% |
66.799 |
65.718 |
0.379 |
-0.77% |
0.379 |
|
SingleSource/Benchmarks/Misc/mandel-2
Profile
|
-1.57% |
2.536 |
2.496 |
0.000 |
-1.55% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_INT_PREDICT_RAW/171
|
-1.54% |
6.916 |
6.810 |
0.007 |
-1.65% |
0.007 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC128
|
-1.53% |
211.498 |
208.263 |
0.036 |
-1.54% |
0.036 |
|
MultiSource/Applications/minisat/minisat
Profile
|
-1.52% |
61.522 |
60.586 |
0.285 |
-0.82% |
0.285 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C++/PENNANT/PENNANT
Profile
|
-1.49% |
4.801 |
4.729 |
0.019 |
-1.82% |
0.019 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<6, LessThanZero, Mid>
|
-1.48% |
23838.985 |
23487.007 |
22.393 |
-0.34% |
22.393 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, LessThanZero, None>
|
-1.45% |
37044.575 |
36508.635 |
21.388 |
-2.84% |
21.388 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC127
|
-1.40% |
220.265 |
217.181 |
0.076 |
-1.40% |
0.076 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<7, GreaterThanZero, Mid>
|
-1.37% |
20468.782 |
20187.541 |
57.067 |
0.20% |
57.067 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint64_t>/51
|
-1.37% |
229.014 |
225.875 |
0.013 |
-1.37% |
0.013 |
|
MicroBenchmarks/LCALS/SubsetBRawLoops/lcalsBRaw.test:BM_MULADDSUB_RAW/44217
|
-1.33% |
395.594 |
390.342 |
1.517 |
0.51% |
1.517 |
|
MultiSource/Benchmarks/Bullet/bullet
Profile
|
-1.30% |
30.362 |
29.968 |
0.097 |
-1.52% |
0.097 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_nested_cond_load_novec_uint8_t_
|
-1.28% |
502841.852 |
496413.618 |
218.680 |
-1.64% |
218.680 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC127
|
-1.28% |
197.109 |
194.596 |
0.013 |
-1.27% |
0.013 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC128
|
-1.26% |
198.360 |
195.858 |
0.003 |
-1.27% |
0.003 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, LessThanZero, Mid>
|
-1.21% |
31897.455 |
31511.278 |
135.555 |
-0.85% |
135.555 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, LessThanZero, Mid>
|
-1.17% |
56587.283 |
55925.093 |
105.988 |
-1.07% |
105.988 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<6, GreaterThanZero, First>
|
-1.16% |
16199.791 |
16011.390 |
0.992 |
0.01% |
0.992 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, GreaterThanZero, Last>
|
-1.16% |
35662.767 |
35249.628 |
3.938 |
-0.00% |
3.938 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<63, EqZero, Mid>
|
-1.16% |
4117.945 |
4070.285 |
3.432 |
-0.01% |
3.432 |
|
SingleSource/Benchmarks/SmallPT/smallpt
Profile
|
-1.12% |
30.039 |
29.704 |
0.002 |
-1.08% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_sinhf_novec_float_
|
-1.11% |
2242.112 |
2217.133 |
0.713 |
-1.10% |
0.713 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<32, LessThanZero, Last>
|
-1.11% |
6895.085 |
6818.462 |
9.791 |
-0.67% |
9.791 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_sinhf_autovec_float_
|
-1.10% |
2242.514 |
2217.795 |
0.543 |
-1.11% |
0.543 |
|
MultiSource/Benchmarks/Fhourstones/fhourstones
Profile
|
-1.09% |
10.921 |
10.801 |
0.036 |
0.21% |
0.036 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_csa_with_cond_arith_novec_int64_t_
|
-1.08% |
744375.706 |
736337.418 |
1360.675 |
-1.12% |
1360.675 |
|
MicroBenchmarks/ImageProcessing/Blur/blur.test:BENCHMARK_boxBlurKernel/512
|
-1.07% |
6586.011 |
6515.335 |
22.841 |
-1.49% |
22.841 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_sinh_autovec_double_
|
-1.05% |
2471.736 |
2445.695 |
9.317 |
-1.21% |
9.317 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint8_t>/16
|
-1.05% |
68.402 |
67.683 |
0.245 |
10.32% |
0.245 |
|
SingleSource/Benchmarks/Misc/fbench
Profile
|
-1.01% |
5.685 |
5.627 |
0.000 |
-2.32% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_sinh_novec_double_
|
-1.01% |
2471.424 |
2446.571 |
1.937 |
-1.10% |
1.937 |