|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_INT_PREDICT_LAMBDA/44217
|
-57.92% |
19353.908 |
8144.202 |
15.675 |
-2.32% |
15.675 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_HYDRO_2D_LAMBDA/44217
|
-53.63% |
69087.279 |
32033.610 |
11427.877 |
-64.77% |
11427.877 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_HYDRO_2D_LAMBDA/5001
|
-53.14% |
7866.279 |
3686.270 |
1201.952 |
-59.55% |
1201.952 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint64_t_To_uint32_t_
|
-50.21% |
35243.705 |
17546.382 |
175.683 |
-50.31% |
175.683 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C/miniGMG/miniGMG
Profile
|
-50.11% |
9.247 |
4.613 |
0.214 |
-49.81% |
0.214 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint64_t_To_uint16_t_
|
-48.91% |
35645.677 |
18212.878 |
1593.393 |
-48.96% |
1593.393 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint64_t_To_uint8_t_
|
-48.84% |
37134.490 |
18998.079 |
25.996 |
-48.74% |
25.996 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_DIFF_PREDICT_LAMBDA/44217
|
-44.25% |
24245.553 |
13517.674 |
299.393 |
-41.49% |
299.393 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint16_t_To_uint64_t_
|
-44.00% |
18654.697 |
10445.869 |
2.443 |
-44.07% |
2.443 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIRST_DIFF_LAMBDA/44217
|
-42.87% |
178.039 |
101.720 |
1.712 |
-29.76% |
1.712 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_DIFF_PREDICT_RAW/44217
|
-41.55% |
23073.803 |
13485.788 |
293.196 |
-42.12% |
293.196 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_PIC_1D_LAMBDA/44217
|
-41.06% |
13587.899 |
8009.363 |
1388.927 |
-40.51% |
1388.927 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint8_t_To_uint64_t_
|
-41.05% |
17829.710 |
10510.009 |
15.171 |
-40.95% |
15.171 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_DIFF_PREDICT_RAW/5001
|
-41.04% |
2564.906 |
1512.346 |
28.289 |
-41.26% |
28.289 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_DIFF_PREDICT_LAMBDA/5001
|
-40.85% |
2569.563 |
1520.004 |
29.819 |
-39.43% |
29.819 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint64_t_To_uint32_t_
|
-40.72% |
38206.696 |
22647.568 |
19.666 |
-40.64% |
19.666 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_INT_PREDICT_LAMBDA/5001
|
-38.78% |
1479.169 |
905.620 |
6.994 |
0.10% |
6.994 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint32_t_To_uint64_t_
|
-37.19% |
22612.999 |
14204.288 |
644.111 |
-37.49% |
644.111 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/32
|
-36.70% |
1396.277 |
883.799 |
0.096 |
-36.70% |
0.096 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/64
|
-36.67% |
6181.725 |
3914.614 |
1.290 |
-36.68% |
1.290 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/16
|
-36.63% |
279.504 |
177.115 |
0.020 |
-36.62% |
0.020 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_PIC_2D_RAW/5001
|
-36.44% |
1089.717 |
692.582 |
119.397 |
-35.78% |
119.397 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/256
|
-36.19% |
107138.601 |
68364.879 |
24.389 |
-36.20% |
24.389 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/128
|
-36.14% |
26265.330 |
16771.874 |
20.169 |
-36.16% |
20.169 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint64_t_To_uint8_t_
|
-34.14% |
30069.957 |
19804.126 |
12.749 |
-34.23% |
12.749 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint64_t_To_uint16_t_
|
-34.07% |
28956.872 |
19091.069 |
15.519 |
-34.05% |
15.519 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, EqZero, None>
|
-31.24% |
20511.267 |
14104.469 |
0.592 |
-31.24% |
0.592 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIRST_DIFF_RAW/44217
|
-31.04% |
148.068 |
102.104 |
1.186 |
-28.34% |
1.186 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint64_t_To_uint16_t_
|
-28.99% |
25912.165 |
18401.126 |
54.354 |
-28.95% |
54.354 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC128
|
-28.18% |
1296.294 |
930.946 |
5.306 |
-27.99% |
5.306 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint32_t_To_uint8_t_
|
-27.94% |
13467.326 |
9704.710 |
53.763 |
-27.95% |
53.763 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_PIC_2D_LAMBDA/44217
|
-27.67% |
11917.027 |
8619.570 |
89.786 |
-21.38% |
89.786 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC64
|
-27.58% |
655.515 |
474.740 |
3.102 |
-27.37% |
3.102 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC32
|
-27.21% |
334.936 |
243.795 |
1.172 |
-26.99% |
1.172 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC16
|
-26.71% |
174.176 |
127.653 |
0.800 |
-26.55% |
0.800 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC128
|
-26.63% |
555.768 |
407.751 |
0.022 |
-26.87% |
0.022 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC64
|
-25.48% |
291.403 |
217.144 |
0.066 |
-25.59% |
0.066 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint64_t_To_uint8_t_
|
-24.29% |
27191.402 |
20587.005 |
13.022 |
-24.38% |
13.022 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, EqZero, None>
|
-23.99% |
16024.399 |
12179.877 |
0.705 |
-23.99% |
0.705 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIRST_SUM_LAMBDA/44217
|
-23.29% |
177.165 |
135.906 |
0.834 |
-18.66% |
0.834 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC128
|
-23.23% |
604.017 |
463.727 |
0.042 |
-23.22% |
0.042 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC32
|
-23.13% |
158.751 |
122.024 |
0.099 |
-23.19% |
0.099 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC128
|
-23.11% |
603.982 |
464.390 |
0.031 |
-23.11% |
0.031 |
|
MicroBenchmarks/ImageProcessing/Blur/blur.test:BENCHMARK_boxBlurKernel/1024
|
-22.48% |
30098.956 |
23332.276 |
74.767 |
-22.61% |
74.767 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint16_t_To_uint64_t_
|
-22.41% |
13355.555 |
10362.863 |
0.462 |
-21.54% |
0.462 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC64
|
-22.36% |
313.510 |
243.421 |
0.016 |
-22.35% |
0.016 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC127
|
-22.18% |
615.209 |
478.749 |
0.043 |
-22.18% |
0.043 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC64
|
-22.16% |
313.519 |
244.031 |
0.033 |
-22.16% |
0.033 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC127
|
-21.97% |
615.166 |
480.025 |
0.030 |
-21.97% |
0.030 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint16_t_To_uint32_t_
|
-21.67% |
7108.965 |
5568.274 |
7.900 |
-21.58% |
7.900 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint8_t_To_uint32_t_
|
-21.56% |
6583.359 |
5163.835 |
5.954 |
-21.55% |
5.954 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_only_autovec_uint8_t_
|
-21.36% |
182337.361 |
143398.320 |
76.295 |
-21.36% |
76.295 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIND_FIRST_MIN_LAMBDA/171
|
-21.31% |
1.501 |
1.181 |
0.000 |
-21.29% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIND_FIRST_MIN_LAMBDA/44217
|
-21.27% |
389.242 |
306.452 |
0.572 |
-21.34% |
0.572 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIND_FIRST_MIN_LAMBDA/5001
|
-20.83% |
45.258 |
35.829 |
0.060 |
-20.83% |
0.060 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC32
|
-20.81% |
168.321 |
133.288 |
0.003 |
-20.82% |
0.003 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_PIC_2D_LAMBDA/5001
|
-20.78% |
1180.961 |
935.543 |
22.320 |
-15.37% |
22.320 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC32
|
-20.46% |
168.336 |
133.896 |
0.014 |
-20.46% |
0.014 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC63
|
-20.43% |
324.789 |
258.422 |
0.035 |
-20.43% |
0.035 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC127
|
-20.42% |
274.682 |
218.596 |
0.637 |
-20.64% |
0.637 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC128
|
-20.15% |
274.047 |
218.835 |
0.417 |
-20.35% |
0.417 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint32_t_To_uint8_t_
|
-20.09% |
13890.049 |
11099.377 |
114.248 |
-20.15% |
114.248 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC63
|
-20.05% |
324.778 |
259.666 |
0.032 |
-20.05% |
0.032 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC127
|
-19.71% |
640.903 |
514.549 |
0.080 |
-19.66% |
0.080 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC16
|
-19.29% |
92.260 |
74.464 |
0.005 |
-19.31% |
0.005 |
|
MultiSource/Benchmarks/MiBench/automotive-bitcount/automotive-bitcount
Profile
|
-19.22% |
0.125 |
0.101 |
0.000 |
-18.39% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC64
|
-19.16% |
150.475 |
121.651 |
0.749 |
-18.15% |
0.749 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint16_t_To_uint8_t_
|
-19.07% |
3817.029 |
3089.124 |
0.803 |
-19.09% |
0.803 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIRST_SUM_RAW/44217
|
-19.02% |
166.345 |
134.712 |
0.466 |
-19.01% |
0.466 |
|
SingleSource/Benchmarks/Adobe-C++/loop_unroll
Profile
|
-18.89% |
2.982 |
2.419 |
0.003 |
-22.14% |
0.003 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_VOL3D_CALC_LAMBDA/2
|
-18.80% |
8.757 |
7.111 |
0.000 |
-18.80% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_VOL3D_CALC_RAW/2
|
-18.79% |
8.757 |
7.111 |
0.000 |
-18.79% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint64_t_To_uint32_t_
|
-18.51% |
27094.581 |
22079.673 |
6.099 |
-18.38% |
6.099 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint32_t_To_uint16_t_
|
-18.50% |
13804.338 |
11251.016 |
5.528 |
-18.51% |
5.528 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC16
|
-18.31% |
95.742 |
78.213 |
0.011 |
-18.31% |
0.011 |
|
MultiSource/Benchmarks/Trimaran/enc-pc1/enc-pc1
Profile
|
-18.11% |
1.105 |
0.905 |
0.000 |
-18.09% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_with_cond_arith_novec_uint8_t_
|
-17.85% |
745777.863 |
612626.710 |
535.888 |
-17.85% |
535.888 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC16
|
-17.65% |
95.739 |
78.839 |
0.004 |
-17.65% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_with_cond_arith_novec_int32_t_
|
-17.47% |
740166.178 |
610893.553 |
934.965 |
-17.47% |
934.965 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint32_t_To_uint16_t_
|
-17.46% |
10333.372 |
8529.535 |
370.904 |
-13.89% |
370.904 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC31
|
-17.42% |
179.591 |
148.297 |
0.005 |
-17.42% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC128
|
-17.26% |
570.726 |
472.202 |
0.060 |
-17.24% |
0.060 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC4
|
-17.25% |
17.521 |
14.499 |
0.004 |
-17.24% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC63
|
-17.21% |
150.983 |
125.006 |
1.131 |
-16.61% |
1.131 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC64
|
-17.00% |
297.364 |
246.822 |
0.035 |
-17.09% |
0.035 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_VOL3D_CALC_RAW/0
|
-16.73% |
1268.945 |
1056.696 |
3.579 |
-16.48% |
3.579 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC31
|
-16.72% |
179.580 |
149.557 |
0.005 |
-16.72% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC32
|
-16.61% |
160.888 |
134.168 |
0.021 |
-16.87% |
0.021 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC32
|
-16.41% |
87.040 |
72.758 |
1.487 |
-14.73% |
1.487 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_VOL3D_CALC_LAMBDA/0
|
-16.28% |
1268.605 |
1062.045 |
1.407 |
-16.22% |
1.407 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC16
|
-16.22% |
92.978 |
77.901 |
0.012 |
-16.35% |
0.012 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_HYDRO_1D_RAW/171
|
-16.21% |
0.444 |
0.372 |
0.000 |
-15.84% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_VOL3D_CALC_LAMBDA/1
|
-16.17% |
260.227 |
218.143 |
0.212 |
-16.15% |
0.212 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_VOL3D_CALC_RAW/1
|
-16.10% |
260.156 |
218.281 |
0.151 |
-16.09% |
0.151 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_HYDRO_1D_LAMBDA/171
|
-15.97% |
0.442 |
0.372 |
0.000 |
-15.87% |
0.000 |
|
MicroBenchmarks/ImageProcessing/Dilate/Dilate.test:BENCHMARK_DILATE/1024
|
-15.75% |
7288.706 |
6141.002 |
242.075 |
-13.64% |
242.075 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint16_t_To_uint32_t_
|
-15.68% |
7462.940 |
6292.426 |
1.310 |
-15.68% |
1.310 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint8_t_To_uint64_t_
|
-15.59% |
12926.911 |
10912.046 |
3.346 |
-16.48% |
3.346 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint32_t_To_uint8_t_
|
-15.54% |
10652.098 |
8997.106 |
61.268 |
-15.08% |
61.268 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, EqZero, First>
|
-15.40% |
16670.381 |
14103.091 |
1.028 |
-15.40% |
1.028 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_no_runtime_checks_needed<16, int>
|
-15.39% |
24.404 |
20.649 |
0.001 |
-15.38% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC8
|
-15.37% |
58.784 |
49.747 |
0.001 |
-15.34% |
0.001 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, EqZero, Mid>
|
-15.37% |
16666.482 |
14104.427 |
0.601 |
-15.37% |
0.601 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, EqZero, Last>
|
-15.35% |
16667.265 |
14108.917 |
1.130 |
-15.35% |
1.130 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint32_t_To_uint8_t_
|
-14.99% |
11135.679 |
9466.547 |
138.400 |
-14.94% |
138.400 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC127
|
-14.83% |
605.882 |
516.043 |
0.045 |
-14.81% |
0.045 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC8
|
-14.74% |
59.446 |
50.686 |
0.000 |
-14.74% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC128
|
-14.58% |
1103.429 |
942.550 |
0.054 |
-14.57% |
0.054 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC127
|
-14.52% |
1095.334 |
936.276 |
0.048 |
-14.52% |
0.048 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint32_t_To_uint16_t_
|
-14.44% |
10914.633 |
9338.018 |
218.130 |
-13.03% |
218.130 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC64
|
-14.31% |
562.287 |
481.806 |
0.037 |
-14.32% |
0.037 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC63
|
-14.21% |
554.285 |
475.543 |
0.044 |
-14.28% |
0.044 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint8_t_To_uint16_t_
|
-14.17% |
3757.009 |
3224.535 |
8.616 |
-14.16% |
8.616 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC4
|
-14.16% |
112.500 |
96.566 |
0.983 |
-14.61% |
0.983 |
|
SingleSource/Benchmarks/Misc/salsa20
Profile
|
-14.14% |
15.386 |
13.212 |
0.001 |
-14.12% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint64_t_To_uint8_t_
|
-13.98% |
22055.664 |
18971.442 |
30.530 |
-13.95% |
30.530 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_with_cond_arith_novec_int64_t_
|
-13.89% |
789617.202 |
679974.615 |
597.592 |
-13.71% |
597.592 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC2
|
-13.87% |
51.941 |
44.739 |
0.002 |
-13.85% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC7
|
-13.86% |
51.939 |
44.739 |
0.002 |
-13.86% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC3
|
-13.86% |
51.937 |
44.738 |
0.004 |
-13.86% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC4
|
-13.86% |
51.938 |
44.739 |
0.003 |
-13.85% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC8
|
-13.85% |
51.937 |
44.742 |
0.003 |
-13.86% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC1
|
-13.85% |
51.934 |
44.740 |
0.001 |
-13.85% |
0.001 |
|
External/SPEC/CFP2017rate/508.namd_r/508.namd_r
Profile
|
-13.84% |
224.627 |
193.542 |
0.020 |
-13.43% |
0.020 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint32_t_To_uint16_t_
|
-13.76% |
12819.055 |
11054.588 |
40.228 |
-13.89% |
40.228 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC32
|
-13.69% |
291.449 |
251.545 |
0.014 |
-13.85% |
0.014 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC8
|
-13.68% |
59.443 |
51.310 |
0.005 |
-13.69% |
0.005 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, EqZero, First>
|
-13.62% |
14103.429 |
12181.897 |
0.151 |
-13.62% |
0.151 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, EqZero, Mid>
|
-13.62% |
14103.140 |
12182.296 |
0.277 |
-13.62% |
0.277 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, EqZero, Last>
|
-13.60% |
14101.451 |
12183.189 |
0.702 |
-13.62% |
0.702 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC8
|
-13.52% |
23.152 |
20.023 |
0.001 |
-13.52% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC31
|
-13.46% |
283.461 |
245.314 |
0.022 |
-13.65% |
0.022 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIRST_SUM_LAMBDA/5001
|
-13.42% |
20.373 |
17.638 |
0.475 |
0.17% |
0.475 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC63
|
-13.42% |
374.401 |
324.151 |
0.083 |
-13.43% |
0.083 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_PIC_1D_LAMBDA/5001
|
-13.40% |
350.061 |
303.138 |
16.684 |
-14.11% |
16.684 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_with_cond_arith_autovec_int64_t_
|
-13.39% |
788461.848 |
682862.640 |
960.639 |
-13.74% |
960.639 |
|
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 |
70.705 |
0.008 |
-13.08% |
0.008 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC16
|
-13.07% |
156.918 |
136.403 |
0.009 |
-13.10% |
0.009 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint32_t_To_uint64_t_
|
-13.06% |
17404.769 |
15131.902 |
276.354 |
-12.00% |
276.354 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint8_t_To_uint16_t_
|
-12.95% |
4542.366 |
3953.928 |
0.337 |
-12.94% |
0.337 |
|
MultiSource/Benchmarks/MiBench/security-rijndael/security-rijndael
Profile
|
-12.90% |
0.335 |
0.292 |
0.001 |
-12.88% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC15
|
-12.87% |
107.003 |
93.234 |
0.011 |
-12.87% |
0.011 |
|
SingleSource/Benchmarks/Shootout-C++/Shootout-C++-matrix
Profile
|
-12.73% |
2.509 |
2.190 |
0.000 |
-12.70% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC63
|
-12.65% |
332.723 |
290.649 |
0.023 |
-12.67% |
0.023 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC31
|
-12.55% |
87.157 |
76.219 |
0.055 |
-11.49% |
0.055 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint16_t_To_uint8_t_
|
-12.39% |
4743.166 |
4155.298 |
0.061 |
-12.39% |
0.061 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC15
|
-12.30% |
148.414 |
130.156 |
0.004 |
-12.54% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC2
|
-11.77% |
21.276 |
18.772 |
0.001 |
-11.77% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC15
|
-11.70% |
106.997 |
94.481 |
0.008 |
-11.71% |
0.008 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC8
|
-11.53% |
89.108 |
78.837 |
0.005 |
-11.82% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC16
|
-11.46% |
51.940 |
45.989 |
0.003 |
-11.46% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC15
|
-11.45% |
51.936 |
45.990 |
0.004 |
-11.45% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC16
|
-11.37% |
33.163 |
29.393 |
0.006 |
-11.37% |
0.006 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_PRESSURE_CALC_RAW/5001
|
-11.23% |
45.883 |
40.729 |
0.756 |
-8.68% |
0.756 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC4
|
-11.11% |
22.526 |
20.023 |
0.002 |
-11.12% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC3
|
-11.11% |
22.527 |
20.024 |
0.001 |
-11.11% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC4
|
-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
|
-11.02% |
123.895 |
110.238 |
0.202 |
19.17% |
0.202 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC7
|
-10.74% |
81.317 |
72.583 |
0.005 |
-10.74% |
0.005 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_BAND_LIN_EQ_RAW/171
|
-10.61% |
0.384 |
0.343 |
0.000 |
-6.34% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC4
|
-10.60% |
41.296 |
36.917 |
0.002 |
-10.62% |
0.002 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_BAND_LIN_EQ_LAMBDA/171
|
-10.60% |
0.384 |
0.343 |
0.000 |
-6.32% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_PRESSURE_CALC_LAMBDA/5001
|
-10.57% |
46.449 |
41.539 |
1.345 |
-5.54% |
1.345 |
|
MicroBenchmarks/ImageProcessing/Dilate/Dilate.test:BENCHMARK_DILATE/128
|
-10.57% |
216.394 |
193.525 |
6.693 |
-15.11% |
6.693 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC4
|
-10.54% |
23.778 |
21.273 |
0.001 |
-10.54% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC64
|
-10.47% |
53.813 |
48.177 |
0.004 |
-10.48% |
0.004 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_DIFF_PREDICT_LAMBDA/171
|
-10.27% |
12.382 |
11.111 |
0.087 |
-7.30% |
0.087 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/16
|
-10.17% |
115.466 |
103.720 |
0.007 |
-10.17% |
0.007 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint8_t_To_uint16_t_
|
-10.10% |
5848.048 |
5257.374 |
4.136 |
-10.14% |
4.136 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC4
|
-10.07% |
55.661 |
50.058 |
0.003 |
-10.07% |
0.003 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_HYDRO_1D_RAW/5001
|
-10.05% |
16.543 |
14.881 |
0.401 |
-10.82% |
0.401 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/64
|
-10.02% |
1912.888 |
1721.166 |
0.996 |
-10.04% |
0.996 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/32
|
-9.99% |
473.014 |
425.775 |
0.011 |
-9.98% |
0.011 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_only_autovec_int64_t_
|
-9.90% |
333137.122 |
300169.542 |
718.633 |
-9.93% |
718.633 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/256
|
-9.85% |
31417.367 |
28324.031 |
21.385 |
-9.94% |
21.385 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC8
|
-9.76% |
25.655 |
23.152 |
0.001 |
-9.76% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC8
|
-9.76% |
25.655 |
23.152 |
0.001 |
-9.76% |
0.001 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/128
|
-9.64% |
7909.140 |
7146.376 |
0.655 |
-9.74% |
0.655 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC127
|
-9.63% |
101.789 |
91.985 |
0.003 |
-9.71% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC7
|
-9.62% |
32.537 |
29.409 |
0.002 |
-9.62% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC7
|
-9.52% |
26.281 |
23.778 |
0.001 |
-9.53% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC7
|
-9.52% |
26.281 |
23.779 |
0.000 |
-9.52% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint64_t_To_uint16_t_
|
-9.47% |
19397.175 |
17561.014 |
425.623 |
-7.50% |
425.623 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC32
|
-9.42% |
53.184 |
48.173 |
0.003 |
-9.44% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC7
|
-9.24% |
354.892 |
322.108 |
4.633 |
-9.19% |
4.633 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC31
|
-9.21% |
196.092 |
178.031 |
0.005 |
-9.39% |
0.005 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_DEL_DOT_VEC_2D_LAMBDA/1
|
-9.17% |
287.027 |
260.707 |
0.095 |
-9.20% |
0.095 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC8
|
-9.14% |
26.858 |
24.403 |
0.001 |
-9.32% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_DEL_DOT_VEC_2D_RAW/1
|
-9.12% |
286.962 |
260.783 |
0.015 |
-9.13% |
0.015 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC4
|
-9.10% |
41.301 |
37.541 |
0.002 |
-9.10% |
0.002 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIRST_DIFF_LAMBDA/5001
|
-9.10% |
12.864 |
11.694 |
0.368 |
-4.07% |
0.368 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC7
|
-8.88% |
28.157 |
25.656 |
0.001 |
-8.89% |
0.001 |
|
MultiSource/Benchmarks/FreeBench/pifft/pifft
Profile
|
-8.81% |
0.359 |
0.327 |
0.001 |
-8.85% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_DEL_DOT_VEC_2D_RAW/2
|
-8.71% |
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% |
36.291 |
33.162 |
0.003 |
-8.63% |
0.003 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_runtime_checks_pass<4, int>
|
-8.61% |
16.775 |
15.330 |
0.001 |
-8.25% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC8
|
-8.51% |
29.410 |
26.908 |
0.001 |
-8.51% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint16_t_To_uint8_t_
|
-8.48% |
6812.717 |
6235.256 |
7.317 |
-8.52% |
7.317 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC2
|
-8.19% |
38.170 |
35.043 |
0.001 |
-8.20% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint8_t_To_uint32_t_
|
-8.12% |
12769.759 |
11732.722 |
42.321 |
-8.19% |
42.321 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC64
|
-8.07% |
93.238 |
85.715 |
0.008 |
-8.07% |
0.008 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint8_t>/28
|
-7.97% |
82.594 |
76.014 |
0.032 |
12.46% |
0.032 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC3
|
-7.90% |
47.557 |
43.800 |
0.005 |
-7.90% |
0.005 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_HYDRO_2D_LAMBDA/171
|
-7.88% |
88.592 |
81.608 |
0.304 |
-7.95% |
0.304 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC16
|
-7.85% |
31.914 |
29.410 |
0.003 |
-7.84% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC16
|
-7.84% |
31.913 |
29.410 |
0.002 |
-7.84% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC32
|
-7.82% |
40.047 |
36.916 |
0.004 |
-7.82% |
0.004 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_DEL_DOT_VEC_2D_LAMBDA/0
|
-7.74% |
1799.566 |
1660.289 |
4.465 |
-7.35% |
4.465 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC15
|
-7.69% |
32.538 |
30.036 |
0.002 |
-7.69% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC15
|
-7.69% |
32.538 |
30.036 |
0.002 |
-7.69% |
0.002 |
|
MultiSource/Benchmarks/VersaBench/beamformer/beamformer
Profile
|
-7.66% |
5.202 |
4.803 |
0.001 |
-7.65% |
0.001 |
|
MultiSource/Benchmarks/McCat/12-IOtest/iotest
Profile
|
-7.57% |
1.808 |
1.671 |
0.034 |
-8.41% |
0.034 |
|
MultiSource/Benchmarks/Trimaran/enc-md5/enc-md5
Profile
|
-7.52% |
3.506 |
3.243 |
0.000 |
-7.50% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC127
|
-7.46% |
2405.892 |
2226.356 |
23.036 |
-8.25% |
23.036 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint16_t_To_uint64_t_
|
-7.45% |
20249.111 |
18739.720 |
42.089 |
-6.97% |
42.089 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_DEL_DOT_VEC_2D_RAW/0
|
-7.44% |
1795.511 |
1662.005 |
3.660 |
-7.71% |
3.660 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_HYDRO_1D_LAMBDA/5001
|
-7.43% |
17.377 |
16.086 |
0.036 |
-6.33% |
0.036 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_xor_no_runtime_checks_needed<16, int>
|
-7.41% |
16.895 |
15.644 |
0.001 |
-7.41% |
0.001 |
|
MultiSource/Applications/lambda-0.1.3/lambda
Profile
|
-7.32% |
15.885 |
14.722 |
0.010 |
-7.23% |
0.010 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint16_t_To_uint64_t_
|
-7.31% |
25029.536 |
23199.914 |
56.516 |
-7.15% |
56.516 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC128
|
-7.23% |
173.343 |
160.815 |
0.004 |
-7.22% |
0.004 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIND_FIRST_MIN_RAW/171
|
-7.22% |
1.497 |
1.389 |
0.000 |
-7.19% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_INT_PREDICT_RAW/44217
|
-7.21% |
8822.329 |
8185.922 |
9.506 |
-9.54% |
9.506 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint8_t>/127
|
-7.20% |
138.917 |
128.913 |
0.003 |
-7.20% |
0.003 |
|
MultiSource/Benchmarks/TSVC/NodeSplitting-dbl/NodeSplitting-dbl
Profile
|
-7.15% |
28.145 |
26.132 |
0.457 |
-1.07% |
0.457 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC7
|
-7.08% |
70.702 |
65.700 |
0.005 |
-7.09% |
0.005 |
|
SingleSource/Benchmarks/Misc/pi
Profile
|
-7.02% |
1.783 |
1.657 |
0.000 |
-7.01% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC15
|
-6.94% |
45.052 |
41.923 |
0.028 |
-6.94% |
0.028 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC15
|
-6.89% |
54.436 |
50.685 |
0.002 |
-6.90% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint64_t_To_uint32_t_
|
-6.87% |
18539.910 |
17266.908 |
248.220 |
-3.07% |
248.220 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC63
|
-6.75% |
74.491 |
69.462 |
0.006 |
-6.41% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC31
|
-6.73% |
74.471 |
69.457 |
0.002 |
-6.72% |
0.002 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIND_FIRST_MIN_RAW/5001
|
-6.57% |
45.433 |
42.449 |
0.149 |
-6.37% |
0.149 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC63
|
-6.56% |
114.515 |
106.999 |
0.057 |
-6.56% |
0.057 |
|
External/SPEC/CFP2017rate/538.imagick_r/538.imagick_r
Profile
|
-6.54% |
292.250 |
273.128 |
0.879 |
-6.49% |
0.879 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_xor_runtime_checks_fail<16, int>
|
-6.52% |
28.784 |
26.907 |
0.001 |
-6.52% |
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/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC1
|
-6.50% |
88.681 |
82.913 |
1.121 |
-6.82% |
1.121 |
|
SingleSource/Benchmarks/Misc/flops-6
Profile
|
-6.48% |
1.312 |
1.227 |
0.001 |
-6.54% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_only_autovec_int32_t_
|
-6.47% |
180945.148 |
169246.546 |
446.681 |
-6.56% |
446.681 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC128
|
-6.44% |
68.829 |
64.397 |
0.024 |
-6.41% |
0.024 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC127
|
-6.39% |
194.593 |
182.156 |
0.284 |
-6.40% |
0.284 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC15
|
-6.35% |
39.421 |
36.918 |
0.001 |
-6.35% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint32_t_To_uint64_t_
|
-6.32% |
21474.887 |
20118.012 |
116.804 |
-6.21% |
116.804 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC127
|
-6.31% |
68.774 |
64.436 |
0.005 |
-5.65% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint16_t>/127
|
-6.30% |
138.914 |
130.156 |
0.005 |
-6.30% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC31
|
-6.30% |
912.284 |
854.849 |
14.660 |
-6.78% |
14.660 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_DIFF_PREDICT_RAW/171
|
-6.25% |
11.838 |
11.099 |
0.145 |
-6.99% |
0.145 |
|
MicroBenchmarks/ImageProcessing/Dilate/Dilate.test:BENCHMARK_DILATE/256
|
-6.25% |
1058.647 |
992.525 |
19.292 |
-7.00% |
19.292 |
|
SingleSource/Benchmarks/Misc-C++/Large/sphereflake
Profile
|
-6.21% |
20.009 |
18.766 |
0.003 |
-6.18% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC16
|
-6.16% |
40.675 |
38.171 |
0.017 |
-6.15% |
0.017 |
|
MultiSource/Benchmarks/MiBench/telecomm-gsm/telecomm-gsm
Profile
|
-5.94% |
0.663 |
0.624 |
0.000 |
-5.98% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint8_t>/65
|
-5.92% |
95.116 |
89.483 |
0.005 |
-5.92% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint32_t>/127
|
-5.87% |
138.270 |
130.156 |
0.003 |
-5.88% |
0.003 |
|
SingleSource/Benchmarks/Misc/oourafft
Profile
|
-5.85% |
15.383 |
14.483 |
0.045 |
-4.05% |
0.045 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC16
|
-5.66% |
33.161 |
31.285 |
0.003 |
-5.66% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC32
|
-5.63% |
44.426 |
41.923 |
0.002 |
-5.64% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC32
|
-5.63% |
44.427 |
41.925 |
0.001 |
-5.64% |
0.001 |
|
SingleSource/Benchmarks/Polybench/stencils/jacobi-2d/jacobi-2d
Profile
|
-5.60% |
32.140 |
30.341 |
0.167 |
-5.84% |
0.167 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C++/miniFE/miniFE
Profile
|
-5.59% |
15.817 |
14.933 |
0.099 |
-6.48% |
0.099 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC31
|
-5.58% |
45.063 |
42.550 |
0.001 |
-5.58% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC31
|
-5.56% |
45.051 |
42.547 |
0.003 |
-5.56% |
0.003 |
|
MultiSource/Benchmarks/SciMark2-C/scimark2
Profile
|
-5.49% |
107.710 |
101.796 |
0.014 |
-5.43% |
0.014 |
|
MultiSource/Benchmarks/Rodinia/hotspot/hotspot
Profile
|
-5.49% |
2.036 |
1.924 |
0.004 |
-5.49% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint8_t_To_uint16_t_
|
-5.44% |
3631.707 |
3434.251 |
3.607 |
-5.48% |
3.607 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_PRESSURE_CALC_RAW/44217
|
-5.43% |
503.775 |
476.418 |
2.345 |
-5.13% |
2.345 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint32_t>/999
|
-5.39% |
696.472 |
658.947 |
0.066 |
-5.39% |
0.066 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_BAND_LIN_EQ_RAW/5001
|
-5.31% |
21.289 |
20.158 |
0.087 |
-2.25% |
0.087 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC7
|
-5.31% |
70.710 |
66.955 |
0.004 |
-5.32% |
0.004 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_BAND_LIN_EQ_LAMBDA/5001
|
-5.28% |
21.327 |
20.201 |
0.069 |
-2.88% |
0.069 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopWithReductionTC1
|
-5.27% |
11.888 |
11.262 |
0.001 |
-5.27% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint32_t>/999
|
-5.23% |
1365.046 |
1293.661 |
0.115 |
-5.23% |
0.115 |
|
SingleSource/Benchmarks/Stanford/Puzzle
Profile
|
-5.21% |
0.242 |
0.229 |
0.002 |
-5.05% |
0.002 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_HYDRO_2D_RAW/171
|
-5.20% |
87.381 |
82.836 |
0.079 |
-6.53% |
0.079 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC32
|
-5.13% |
61.324 |
58.177 |
0.008 |
-5.13% |
0.008 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC32
|
-5.13% |
24.404 |
23.152 |
0.001 |
-5.14% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC31
|
-5.13% |
24.404 |
23.152 |
0.001 |
-5.13% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC32
|
-5.13% |
24.403 |
23.152 |
0.001 |
-5.12% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIND_FIRST_MIN_RAW/44217
|
-5.13% |
389.160 |
369.215 |
0.063 |
-5.23% |
0.063 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC31
|
-5.12% |
24.403 |
23.152 |
0.000 |
-5.12% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC15
|
-5.09% |
128.237 |
121.707 |
0.005 |
-5.11% |
0.005 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_PIC_2D_LAMBDA/171
|
-5.09% |
13.458 |
12.774 |
0.081 |
-5.36% |
0.081 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC31
|
-5.05% |
241.217 |
229.041 |
0.001 |
-5.05% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_PIC_2D_RAW/171
|
-4.90% |
13.523 |
12.861 |
0.050 |
-5.01% |
0.050 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint32_t>/256
|
-4.82% |
364.171 |
346.626 |
0.026 |
-4.82% |
0.026 |
|
SingleSource/Benchmarks/Misc/revertBits
Profile
|
-4.70% |
0.641 |
0.611 |
0.000 |
-4.70% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint16_t>/65
|
-4.60% |
95.109 |
90.732 |
0.005 |
-4.61% |
0.005 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_runtime_checks_pass<16, int>
|
-4.60% |
54.437 |
51.935 |
0.002 |
-4.60% |
0.002 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_runtime_checks_fail<16, int>
|
-4.59% |
54.438 |
51.937 |
0.001 |
-4.60% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopWithReductionTC2
|
-4.52% |
13.767 |
13.145 |
0.003 |
-4.51% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC31
|
-4.47% |
70.086 |
66.954 |
0.003 |
-4.46% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC2
|
-4.36% |
14.392 |
13.765 |
0.001 |
-4.35% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC1
|
-4.36% |
14.393 |
13.766 |
0.001 |
-4.35% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC16
|
-4.36% |
14.393 |
13.766 |
0.001 |
-4.35% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC3
|
-4.35% |
14.393 |
13.766 |
0.001 |
-4.35% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC3
|
-4.35% |
14.391 |
13.765 |
0.001 |
-4.36% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC16
|
-4.35% |
14.392 |
13.766 |
0.077 |
-4.36% |
0.077 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC8
|
-4.35% |
14.392 |
13.766 |
0.000 |
-4.35% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC1
|
-4.35% |
14.394 |
13.767 |
0.001 |
-4.35% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC7
|
-4.35% |
14.392 |
13.766 |
0.001 |
-4.35% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC2
|
-4.35% |
14.392 |
13.766 |
0.000 |
-4.35% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC4
|
-4.35% |
14.392 |
13.766 |
0.001 |
-4.35% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC4
|
-4.35% |
14.392 |
13.766 |
0.001 |
-4.35% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC128
|
-4.35% |
2970.392 |
2841.276 |
38.023 |
-4.47% |
38.023 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC15
|
-4.34% |
14.392 |
13.767 |
0.001 |
-4.35% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC127
|
-4.34% |
3123.222 |
2987.558 |
40.465 |
-4.51% |
40.465 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC8
|
-4.34% |
14.392 |
13.767 |
0.000 |
-4.35% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC7
|
-4.34% |
14.391 |
13.767 |
0.001 |
-4.35% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC15
|
-4.34% |
14.391 |
13.767 |
0.005 |
-4.35% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint64_t>/999
|
-4.26% |
1811.115 |
1733.988 |
0.187 |
-4.27% |
0.187 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_nested_cond_load_novec_int32_t_
|
-4.25% |
649717.237 |
622113.469 |
81.951 |
-3.57% |
81.951 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_ENERGY_CALC_LAMBDA/171
|
-4.24% |
14.211 |
13.608 |
0.012 |
-4.49% |
0.012 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint64_t>/999
|
-4.18% |
3595.609 |
3445.224 |
0.373 |
-4.16% |
0.373 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_runtime_checks_fail<4, int>
|
-4.18% |
15.997 |
15.329 |
0.001 |
-3.64% |
0.001 |
|
SingleSource/Benchmarks/Misc/flops-5
Profile
|
-4.17% |
2.021 |
1.937 |
0.001 |
-4.18% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_ENERGY_CALC_RAW/171
|
-4.11% |
14.195 |
13.611 |
0.017 |
-4.42% |
0.017 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint64_t>/256
|
-4.08% |
935.520 |
897.321 |
0.063 |
-4.09% |
0.063 |
|
MultiSource/Benchmarks/TSVC/Symbolics-dbl/Symbolics-dbl
Profile
|
-4.07% |
9.821 |
9.421 |
0.081 |
-2.26% |
0.081 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC31
|
-4.04% |
61.948 |
59.446 |
0.003 |
-4.04% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC16
|
-3.99% |
31.292 |
30.042 |
0.097 |
-3.98% |
0.097 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_only_autovec_uint8_t_
|
-3.98% |
96160.599 |
92336.978 |
5.367 |
-3.97% |
5.367 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint8_t_To_uint64_t_
|
-3.97% |
23461.938 |
22529.416 |
6.028 |
-4.06% |
6.028 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint32_t>/65
|
-3.97% |
94.480 |
90.729 |
0.003 |
-3.98% |
0.003 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<31, EqZero, First>
|
-3.96% |
3346.058 |
3213.512 |
4.379 |
-3.97% |
4.379 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC32
|
-3.96% |
63.199 |
60.696 |
0.003 |
-3.96% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint64_t_To_uint32_t_
|
-3.96% |
19400.843 |
18633.121 |
45.783 |
-3.42% |
45.783 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint32_t>/256
|
-3.95% |
221.504 |
212.751 |
0.006 |
-3.95% |
0.006 |
|
External/SPEC/CFP2017rate/519.lbm_r/519.lbm_r
Profile
|
-3.93% |
199.780 |
191.928 |
1.602 |
-4.36% |
1.602 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC3
|
-3.85% |
16.268 |
15.642 |
0.001 |
-3.85% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint32_t_To_uint16_t_
|
-3.82% |
9844.897 |
9468.809 |
45.357 |
-4.16% |
45.357 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC64
|
-3.70% |
43.177 |
41.578 |
0.059 |
-3.70% |
0.059 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint8_t>/16
|
-3.70% |
60.042 |
57.819 |
0.435 |
7.43% |
0.435 |
|
SingleSource/Benchmarks/Shootout/Shootout-matrix
Profile
|
-3.70% |
3.864 |
3.721 |
0.000 |
-3.68% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC63
|
-3.68% |
43.177 |
41.590 |
0.057 |
-3.94% |
0.057 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint64_t>/256
|
-3.64% |
514.340 |
495.601 |
0.007 |
-3.65% |
0.007 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC63
|
-3.60% |
1731.485 |
1669.085 |
18.521 |
-3.92% |
18.521 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC64
|
-3.60% |
69.459 |
66.957 |
0.002 |
-3.60% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC64
|
-3.60% |
69.457 |
66.955 |
0.002 |
-3.61% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC63
|
-3.59% |
70.096 |
67.581 |
0.003 |
-3.58% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC63
|
-3.57% |
70.081 |
67.582 |
0.004 |
-3.57% |
0.004 |
|
SingleSource/Benchmarks/BenchmarkGame/n-body
Profile
|
-3.56% |
2.731 |
2.634 |
0.000 |
21.71% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC31
|
-3.44% |
60.266 |
58.193 |
0.000 |
-3.46% |
0.000 |
|
MultiSource/Applications/JM/lencod/lencod
Profile
|
-3.43% |
32.730 |
31.605 |
0.017 |
-2.87% |
0.017 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC63
|
-3.39% |
1639.714 |
1584.136 |
21.359 |
-3.63% |
21.359 |
|
MultiSource/Benchmarks/Rodinia/pathfinder/pathfinder
Profile
|
-3.31% |
1.265 |
1.223 |
0.009 |
-2.77% |
0.009 |
|
External/SPEC/CFP2017rate/544.nab_r/544.nab_r
Profile
|
-3.28% |
476.310 |
460.697 |
0.072 |
-3.60% |
0.072 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint16_t_To_uint8_t_
|
-3.27% |
2873.206 |
2779.111 |
2.393 |
-3.44% |
2.393 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC31
|
-3.26% |
93.839 |
90.776 |
0.249 |
-3.28% |
0.249 |
|
MultiSource/Benchmarks/nbench/nbench
Profile
|
-3.25% |
6.104 |
5.905 |
0.002 |
-3.62% |
0.002 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<32, EqZero, Last>
|
-3.23% |
7045.217 |
6817.372 |
61.777 |
-3.34% |
61.777 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint16_t>/999
|
-3.16% |
515.004 |
498.723 |
0.030 |
-3.16% |
0.030 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1BigLoopWithReductionTC1
|
-3.14% |
20.025 |
19.397 |
0.001 |
-3.14% |
0.001 |
|
SingleSource/Benchmarks/Shootout/Shootout-lists
Profile
|
-3.13% |
11.316 |
10.962 |
0.002 |
-3.10% |
0.002 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_ENERGY_CALC_LAMBDA/5001
|
-3.11% |
438.037 |
424.426 |
4.819 |
-3.11% |
4.819 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchVecWithRuntimeChecks4PointersDBeforeA/1000
|
-3.08% |
5020489.187 |
4865677.069 |
461.688 |
-3.07% |
461.688 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint16_t_To_uint8_t_
|
-3.07% |
4514.789 |
4376.152 |
15.241 |
-3.12% |
15.241 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC32
|
-3.04% |
31.285 |
30.333 |
0.061 |
-3.05% |
0.061 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_PRESSURE_CALC_LAMBDA/44217
|
-2.96% |
504.391 |
489.461 |
0.436 |
-1.82% |
0.436 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, LessThanZero, None>
|
-2.92% |
37600.000 |
36502.557 |
10.038 |
-2.86% |
10.038 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint16_t>/999
|
-2.83% |
1013.664 |
984.958 |
0.111 |
-2.85% |
0.111 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<64, EqZero, Mid>
|
-2.83% |
2762.641 |
2684.409 |
12.487 |
-2.18% |
12.487 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC64
|
-2.83% |
111.395 |
108.245 |
0.013 |
-2.82% |
0.013 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<31, GreaterThanZero, Last>
|
-2.80% |
8332.004 |
8098.638 |
0.567 |
-2.37% |
0.567 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_FLOYD_DITHER/256
|
-2.80% |
1795.222 |
1744.957 |
2.870 |
0.66% |
2.870 |
|
SingleSource/Benchmarks/BenchmarkGame/puzzle
Profile
|
-2.78% |
0.876 |
0.851 |
0.004 |
-2.02% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC1
|
-2.78% |
22.528 |
21.901 |
0.002 |
-2.77% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC1
|
-2.77% |
22.526 |
21.902 |
0.002 |
-2.77% |
0.002 |
|
MultiSource/Benchmarks/FreeBench/mason/mason
Profile
|
-2.68% |
0.553 |
0.538 |
0.000 |
-2.76% |
0.000 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C/CoMD/CoMD
Profile
|
-2.66% |
9.898 |
9.634 |
0.002 |
-2.68% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC63
|
-2.61% |
120.150 |
117.010 |
0.007 |
-2.61% |
0.007 |
|
SingleSource/Benchmarks/Misc-C++/oopack_v1p8
Profile
|
-2.59% |
0.479 |
0.467 |
0.000 |
-9.98% |
0.000 |
|
MultiSource/Benchmarks/mafft/pairlocalalign
Profile
|
-2.59% |
94.007 |
91.576 |
0.287 |
-2.64% |
0.287 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint8_t>/10
|
-2.57% |
48.807 |
47.555 |
0.019 |
2.46% |
0.019 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_ENERGY_CALC_LAMBDA/44217
|
-2.56% |
4328.589 |
4217.739 |
25.495 |
-2.47% |
25.495 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint8_t_To_uint32_t_
|
-2.55% |
7077.887 |
6897.148 |
1.943 |
-2.55% |
1.943 |
|
MultiSource/Benchmarks/FreeBench/pcompress2/pcompress2
Profile
|
-2.55% |
0.403 |
0.393 |
0.001 |
-2.82% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopTC16
|
-2.55% |
277.298 |
270.239 |
1.663 |
-2.16% |
1.663 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint64_t_To_uint8_t_
|
-2.54% |
19792.953 |
19290.383 |
26.683 |
-2.78% |
26.683 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC32
|
-2.49% |
50.053 |
48.809 |
0.177 |
-2.48% |
0.177 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_only_autovec_int64_t_
|
-2.47% |
1449564.263 |
1413757.230 |
508.350 |
-2.30% |
508.350 |
|
MultiSource/Benchmarks/sim/sim
Profile
|
-2.45% |
9.699 |
9.461 |
0.013 |
-2.47% |
0.013 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchVecWithRuntimeChecks4PointersDBeforeA/32
|
-2.44% |
166180.390 |
162126.110 |
14.060 |
-2.45% |
14.060 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC63
|
-2.35% |
107.012 |
104.502 |
0.002 |
-2.34% |
0.002 |
|
MultiSource/Benchmarks/FreeBench/fourinarow/fourinarow
Profile
|
-2.33% |
0.650 |
0.635 |
0.000 |
-2.34% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC64
|
-2.32% |
108.260 |
105.751 |
0.004 |
-2.31% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC15
|
-2.26% |
44.813 |
43.802 |
0.002 |
-1.42% |
0.002 |
|
MultiSource/Benchmarks/Olden/health/health
Profile
|
-2.25% |
1.593 |
1.558 |
0.005 |
-2.13% |
0.005 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C/SimpleMOC/SimpleMOC
Profile
|
-2.24% |
10.445 |
10.211 |
0.024 |
-1.87% |
0.024 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_FLOYD_DITHER/512
|
-2.17% |
6651.214 |
6506.561 |
22.064 |
-2.09% |
22.064 |
|
SingleSource/Benchmarks/Misc/flops-1
Profile
|
-2.17% |
9.002 |
8.806 |
0.000 |
-2.15% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_ENERGY_CALC_RAW/44217
|
-2.13% |
4347.556 |
4254.910 |
35.053 |
-1.77% |
35.053 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint32_t_To_uint64_t_
|
-2.12% |
26356.228 |
25798.177 |
47.569 |
-1.84% |
47.569 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_FLOYD_DITHER/128
|
-2.12% |
438.059 |
428.787 |
0.198 |
-2.43% |
0.198 |
|
SingleSource/Benchmarks/Misc-C++/Large/ray
Profile
|
-2.11% |
12.104 |
11.849 |
0.001 |
-2.08% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC128
|
-2.10% |
119.520 |
117.014 |
0.003 |
-2.10% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC127
|
-2.10% |
120.151 |
117.632 |
0.008 |
-2.09% |
0.008 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC128
|
-2.10% |
119.517 |
117.011 |
0.004 |
-2.10% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC127
|
-2.09% |
120.143 |
117.634 |
0.005 |
-2.08% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint8_t>/51
|
-1.97% |
240.860 |
236.119 |
0.347 |
15.03% |
0.347 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<64, GreaterThanZero, Mid>
|
-1.94% |
2745.465 |
2692.107 |
7.543 |
-1.95% |
7.543 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_EOS_RAW/171
|
-1.93% |
0.873 |
0.856 |
0.001 |
-1.73% |
0.001 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<3, GreaterThanZero, None>
|
-1.88% |
45231.984 |
44380.127 |
92.936 |
-1.69% |
92.936 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC31
|
-1.88% |
31.075 |
30.491 |
0.019 |
-2.24% |
0.019 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint16_t>/256
|
-1.85% |
272.853 |
267.796 |
0.025 |
-1.85% |
0.025 |
|
MicroBenchmarks/ImageProcessing/Blur/blur.test:BENCHMARK_boxBlurKernel/512
|
-1.80% |
6619.143 |
6499.834 |
34.868 |
-1.72% |
34.868 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint32_t>/10
|
-1.79% |
47.158 |
46.315 |
0.009 |
0.01% |
0.009 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_EOS_LAMBDA/171
|
-1.79% |
0.871 |
0.855 |
0.001 |
-1.78% |
0.001 |
|
MultiSource/Benchmarks/Bullet/bullet
Profile
|
-1.75% |
30.433 |
29.900 |
0.141 |
-1.74% |
0.141 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_csa_with_cond_arith_novec_int64_t_
|
-1.73% |
748737.167 |
735756.972 |
912.820 |
-1.20% |
912.820 |
|
MultiSource/Benchmarks/ASC_Sequoia/AMGmk/AMGmk
Profile
|
-1.70% |
33.360 |
32.793 |
0.017 |
-0.80% |
0.017 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_INT_PREDICT_LAMBDA/171
|
-1.70% |
6.925 |
6.807 |
0.019 |
-1.70% |
0.019 |
|
MicroBenchmarks/Builtins/Int128/Builtins.test:BM_RemainderIntrinsic128UniformDivisor<__int128_t>
|
-1.70% |
67.122 |
65.983 |
0.215 |
-0.37% |
0.215 |
|
MultiSource/Benchmarks/Fhourstones-3.1/fhourstones3.1
Profile
|
-1.69% |
3.975 |
3.908 |
0.011 |
-1.60% |
0.011 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint64_t>/51
|
-1.69% |
148.302 |
145.794 |
0.013 |
-1.69% |
0.013 |
|
MultiSource/Applications/SPASS/SPASS
Profile
|
-1.68% |
119.481 |
117.471 |
0.700 |
-0.72% |
0.700 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_csa_with_in_loop_arith_novec_int64_t_
|
-1.64% |
1029077.753 |
1012222.256 |
368.162 |
-1.55% |
368.162 |
|
MultiSource/Benchmarks/VersaBench/ecbdes/ecbdes
Profile
|
-1.62% |
5.141 |
5.058 |
0.003 |
-1.58% |
0.003 |
|
External/SPEC/CFP2017rate/511.povray_r/511.povray_r
Profile
|
-1.62% |
33.959 |
33.410 |
0.025 |
-1.11% |
0.025 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<32, LessThanZero, Mid>
|
-1.61% |
4570.400 |
4496.867 |
11.302 |
-1.62% |
11.302 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_INT_PREDICT_RAW/171
|
-1.59% |
6.918 |
6.808 |
0.010 |
-1.69% |
0.010 |
|
SingleSource/Benchmarks/Misc/mandel-2
Profile
|
-1.58% |
2.536 |
2.496 |
0.000 |
-1.55% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_nested_cond_load_novec_uint8_t_
|
-1.58% |
504533.926 |
496585.786 |
118.063 |
-1.61% |
118.063 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_csa_with_cond_arith_autovec_int64_t_
|
-1.57% |
746010.126 |
734285.750 |
905.355 |
-1.43% |
905.355 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC128
|
-1.50% |
211.528 |
208.356 |
0.012 |
-1.49% |
0.012 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint32_t>/10
|
-1.48% |
57.902 |
57.048 |
0.030 |
-0.00% |
0.030 |
|
External/SPEC/CINT2017rate/531.deepsjeng_r/531.deepsjeng_r
Profile
|
-1.47% |
259.450 |
255.632 |
0.089 |
-1.72% |
0.089 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C++/PENNANT/PENNANT
Profile
|
-1.46% |
4.799 |
4.729 |
0.022 |
-1.84% |
0.022 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<6, LessThanZero, Mid>
|
-1.46% |
23851.572 |
23503.900 |
16.379 |
-0.27% |
16.379 |
|
MultiSource/Benchmarks/tramp3d-v4/tramp3d-v4
Profile
|
-1.45% |
1.073 |
1.057 |
0.004 |
-1.71% |
0.004 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<31, EqZero, None>
|
-1.44% |
7989.984 |
7874.661 |
33.134 |
-1.51% |
33.134 |
|
External/SPEC/CINT2017rate/525.x264_r/525.x264_r
Profile
|
-1.43% |
129.590 |
127.731 |
0.172 |
-1.32% |
0.172 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint8_t_To_uint32_t_
|
-1.41% |
12110.101 |
11939.102 |
39.078 |
-1.51% |
39.078 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<16, GreaterThanZero, First>
|
-1.41% |
8614.006 |
8492.820 |
1.415 |
-0.04% |
1.415 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, LessThanZero, Mid>
|
-1.40% |
56553.954 |
55760.011 |
147.939 |
-1.36% |
147.939 |
|
MultiSource/Benchmarks/MallocBench/cfrac/cfrac
Profile
|
-1.40% |
2.781 |
2.743 |
0.001 |
-1.35% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC127
|
-1.38% |
220.289 |
217.238 |
0.093 |
-1.38% |
0.093 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint64_t>/51
|
-1.37% |
229.013 |
225.886 |
0.011 |
-1.36% |
0.011 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<32, GreaterThanZero, Mid>
|
-1.36% |
4557.761 |
4495.681 |
15.127 |
-1.31% |
15.127 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<16, EqZero, Mid>
|
-1.31% |
8657.343 |
8544.112 |
12.678 |
-1.31% |
12.678 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC127
|
-1.28% |
197.115 |
194.595 |
0.011 |
-1.27% |
0.011 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC128
|
-1.25% |
198.364 |
195.876 |
0.013 |
-1.26% |
0.013 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<64, LessThanZero, Last>
|
-1.20% |
4185.499 |
4135.195 |
0.564 |
-0.86% |
0.564 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, LessThanZero, Last>
|
-1.19% |
56428.647 |
55758.291 |
46.023 |
-0.51% |
46.023 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<16, LessThanZero, Last>
|
-1.18% |
13141.822 |
12986.633 |
3.832 |
-1.18% |
3.832 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_ENERGY_CALC_RAW/5001
|
-1.17% |
429.312 |
424.304 |
1.942 |
-1.03% |
1.942 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_sinhf_novec_float_
|
-1.17% |
2243.408 |
2217.268 |
0.635 |
-1.10% |
0.635 |
|
SingleSource/Benchmarks/SmallPT/smallpt
Profile
|
-1.14% |
30.046 |
29.705 |
0.001 |
-1.08% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint16_t_To_uint32_t_
|
-1.13% |
11252.894 |
11126.169 |
13.025 |
-1.91% |
13.025 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_sinh_autovec_double_
|
-1.10% |
2471.758 |
2444.535 |
9.791 |
-1.26% |
9.791 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<8, LessThanZero, Mid>
|
-1.09% |
19453.091 |
19241.012 |
9.300 |
-1.00% |
9.300 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_sinhf_autovec_float_
|
-1.09% |
2241.792 |
2217.382 |
1.048 |
-1.13% |
1.048 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<6, GreaterThanZero, None>
|
-1.06% |
29719.635 |
29405.505 |
9.144 |
-0.59% |
9.144 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<64, EqZero, None>
|
-1.05% |
2942.820 |
2911.808 |
10.243 |
-0.60% |
10.243 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, LessThanZero, Mid>
|
-1.05% |
31787.751 |
31454.053 |
76.673 |
-1.03% |
76.673 |
|
MicroBenchmarks/Builtins/Int128/Builtins.test:BM_RemainderIntrinsic128UniformDivisor<__uint128_t>
|
-1.01% |
55.762 |
55.196 |
0.051 |
-0.98% |
0.051 |
|
External/SPEC/CINT2017rate/500.perlbench_r/500.perlbench_r
Profile
|
-1.00% |
146.837 |
145.362 |
0.250 |
-0.91% |
0.250 |