|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_INT_PREDICT_LAMBDA/44217
|
130.65% |
8206.709 |
18928.401 |
240.243 |
-2.79% |
240.243 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint64_t_To_uint16_t_
|
95.32% |
18276.381 |
35698.042 |
42.235 |
0.01% |
42.235 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint64_t_To_uint8_t_
|
94.26% |
19077.955 |
37060.570 |
192.148 |
-0.01% |
192.148 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint64_t_To_uint32_t_
|
85.85% |
18994.955 |
35301.638 |
134.855 |
-0.03% |
134.855 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C/miniGMG/miniGMG
Profile
|
79.72% |
5.089 |
9.146 |
0.188 |
-0.48% |
0.188 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint16_t_To_uint64_t_
|
78.31% |
10451.804 |
18636.898 |
40.282 |
-0.20% |
40.282 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_DIFF_PREDICT_LAMBDA/44217
|
74.45% |
13961.922 |
24356.194 |
806.008 |
0.07% |
806.008 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint8_t_To_uint64_t_
|
68.69% |
10538.593 |
17777.552 |
167.569 |
-0.12% |
167.569 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint64_t_To_uint32_t_
|
67.89% |
22737.048 |
38172.927 |
74.788 |
0.05% |
74.788 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIRST_DIFF_LAMBDA/44217
|
67.38% |
103.917 |
173.940 |
4.672 |
-0.52% |
4.672 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_DIFF_PREDICT_RAW/44217
|
65.28% |
14163.078 |
23408.180 |
1110.111 |
0.47% |
1110.111 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_DIFF_PREDICT_RAW/5001
|
64.60% |
1558.664 |
2565.512 |
99.775 |
-0.36% |
99.775 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_DIFF_PREDICT_LAMBDA/5001
|
60.27% |
1594.100 |
2554.916 |
103.916 |
-0.77% |
103.916 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/32
|
57.97% |
883.887 |
1396.238 |
0.063 |
-0.00% |
0.063 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/16
|
57.82% |
177.117 |
279.528 |
0.008 |
0.00% |
0.008 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/64
|
57.17% |
3933.807 |
6182.707 |
4.188 |
0.01% |
4.188 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/256
|
56.52% |
68441.608 |
107122.565 |
14.631 |
-0.03% |
14.631 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/128
|
56.30% |
16806.714 |
26269.481 |
1.768 |
-0.01% |
1.768 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_HYDRO_2D_LAMBDA/44217
|
55.95% |
59149.149 |
92241.677 |
3894.289 |
-0.80% |
3894.289 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint64_t_To_uint16_t_
|
51.45% |
19107.203 |
28937.854 |
79.799 |
-0.04% |
79.799 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint64_t_To_uint8_t_
|
51.09% |
19926.363 |
30106.557 |
72.464 |
-0.01% |
72.464 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_HYDRO_2D_LAMBDA/5001
|
48.12% |
6383.481 |
9454.958 |
498.497 |
-3.09% |
498.497 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_HYDRO_2D_RAW/44217
|
45.83% |
56830.170 |
82874.889 |
4405.631 |
-2.10% |
4405.631 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, EqZero, None>
|
45.41% |
14107.558 |
20513.181 |
0.575 |
-0.01% |
0.575 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_HYDRO_2D_RAW/5001
|
41.99% |
6315.945 |
8968.279 |
164.123 |
1.95% |
164.123 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint32_t_To_uint64_t_
|
41.34% |
16182.274 |
22871.984 |
72.532 |
-0.28% |
72.532 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIRST_DIFF_RAW/44217
|
39.64% |
104.094 |
145.356 |
13.249 |
2.01% |
13.249 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint64_t_To_uint16_t_
|
39.40% |
18581.914 |
25903.526 |
28.284 |
0.02% |
28.284 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint32_t_To_uint8_t_
|
38.62% |
9763.208 |
13533.517 |
20.202 |
0.42% |
20.202 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC128
|
37.91% |
936.577 |
1291.646 |
5.559 |
-0.09% |
5.559 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC128
|
36.68% |
407.771 |
557.327 |
0.658 |
-0.04% |
0.658 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC64
|
36.62% |
478.413 |
653.588 |
2.431 |
-0.00% |
2.431 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC32
|
36.13% |
245.282 |
333.914 |
1.377 |
-0.00% |
1.377 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC16
|
35.16% |
128.586 |
173.792 |
0.653 |
0.00% |
0.653 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_PIC_2D_LAMBDA/44217
|
34.85% |
8833.128 |
11911.554 |
26.938 |
0.34% |
26.938 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC64
|
34.48% |
217.237 |
292.135 |
0.091 |
-0.03% |
0.091 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_PIC_2D_RAW/44217
|
33.82% |
8866.397 |
11864.824 |
60.903 |
-0.61% |
60.903 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, EqZero, None>
|
31.55% |
12181.908 |
16025.246 |
0.233 |
-0.01% |
0.233 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint64_t_To_uint8_t_
|
31.51% |
20719.848 |
27248.897 |
23.112 |
0.04% |
23.112 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC128
|
30.21% |
463.818 |
603.937 |
0.026 |
-0.00% |
0.026 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC32
|
30.21% |
122.052 |
158.921 |
0.045 |
0.03% |
0.045 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC128
|
30.02% |
464.477 |
603.933 |
0.027 |
-0.00% |
0.027 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIRST_SUM_LAMBDA/44217
|
29.08% |
136.944 |
176.761 |
2.944 |
0.12% |
2.944 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC64
|
28.78% |
243.440 |
313.492 |
0.034 |
-0.00% |
0.034 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC127
|
28.48% |
478.860 |
615.219 |
0.017 |
0.00% |
0.017 |
|
MicroBenchmarks/ImageProcessing/Blur/blur.test:BENCHMARK_boxBlurKernel/1024
|
28.47% |
23447.450 |
30123.500 |
68.126 |
-0.08% |
68.126 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC64
|
28.45% |
244.070 |
313.516 |
0.027 |
0.00% |
0.027 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC127
|
28.14% |
480.084 |
615.203 |
0.029 |
0.00% |
0.029 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint16_t_To_uint32_t_
|
27.67% |
5573.266 |
7115.301 |
13.901 |
0.06% |
13.901 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_only_autovec_uint8_t_
|
27.14% |
143468.696 |
182404.075 |
16.178 |
0.01% |
16.178 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIND_FIRST_MIN_LAMBDA/171
|
27.03% |
1.182 |
1.501 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint16_t_To_uint64_t_
|
26.94% |
10364.496 |
13156.820 |
372.672 |
-0.39% |
372.672 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIND_FIRST_MIN_LAMBDA/44217
|
26.72% |
307.375 |
389.491 |
0.349 |
-0.02% |
0.349 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint8_t_To_uint32_t_
|
26.68% |
5179.078 |
6560.881 |
50.207 |
-0.32% |
50.207 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC32
|
26.28% |
133.291 |
168.326 |
0.008 |
-0.00% |
0.008 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_DISC_ORD_LAMBDA/44217
|
25.96% |
11481.288 |
14462.358 |
548.323 |
-2.48% |
548.323 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC32
|
25.70% |
133.912 |
168.321 |
0.007 |
-0.01% |
0.007 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC63
|
25.66% |
258.450 |
324.775 |
0.024 |
-0.00% |
0.024 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC63
|
25.05% |
259.708 |
324.765 |
0.018 |
-0.01% |
0.018 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC127
|
24.48% |
514.648 |
640.657 |
0.327 |
0.03% |
0.327 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIND_FIRST_MIN_LAMBDA/5001
|
24.03% |
36.406 |
45.153 |
0.173 |
-0.23% |
0.173 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC16
|
23.98% |
74.466 |
92.324 |
0.004 |
0.03% |
0.004 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_PIC_1D_LAMBDA/44217
|
23.60% |
10983.879 |
13575.899 |
40.446 |
0.61% |
40.446 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint16_t_To_uint8_t_
|
23.57% |
3089.687 |
3817.866 |
0.518 |
-0.01% |
0.518 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC128
|
23.46% |
221.269 |
273.181 |
1.724 |
-0.57% |
1.724 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC127
|
23.43% |
223.099 |
275.366 |
2.205 |
-0.03% |
2.205 |
|
SingleSource/Benchmarks/Adobe-C++/loop_unroll
Profile
|
23.19% |
2.420 |
2.981 |
0.003 |
-4.04% |
0.003 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIRST_SUM_RAW/44217
|
23.19% |
136.582 |
168.252 |
9.226 |
1.15% |
9.226 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_VOL3D_CALC_RAW/2
|
23.14% |
7.112 |
8.758 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_VOL3D_CALC_LAMBDA/2
|
23.14% |
7.111 |
8.757 |
0.001 |
-0.01% |
0.001 |
|
MultiSource/Benchmarks/MiBench/automotive-bitcount/automotive-bitcount
Profile
|
22.94% |
0.102 |
0.126 |
0.000 |
0.87% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint64_t_To_uint32_t_
|
22.53% |
22127.694 |
27113.010 |
19.802 |
0.09% |
19.802 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint32_t_To_uint16_t_
|
22.53% |
11271.728 |
13811.074 |
2.438 |
0.03% |
2.438 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC16
|
22.38% |
78.225 |
95.735 |
0.008 |
-0.01% |
0.008 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint32_t_To_uint8_t_
|
22.29% |
11362.050 |
13895.091 |
33.402 |
-0.04% |
33.402 |
|
MultiSource/Benchmarks/Trimaran/enc-pc1/enc-pc1
Profile
|
22.09% |
0.905 |
1.105 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_with_cond_arith_novec_uint8_t_
|
21.64% |
613082.637 |
745769.967 |
566.903 |
0.00% |
566.903 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC16
|
21.42% |
78.848 |
95.735 |
0.003 |
-0.00% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC31
|
21.09% |
148.314 |
179.590 |
0.008 |
0.00% |
0.008 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC128
|
20.82% |
472.276 |
570.609 |
0.084 |
0.01% |
0.084 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_PIC_1D_RAW/44217
|
20.73% |
11100.402 |
13401.653 |
79.156 |
-0.94% |
79.156 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC4
|
20.67% |
14.520 |
17.521 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC64
|
20.57% |
246.860 |
297.647 |
0.110 |
-0.02% |
0.110 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_with_cond_arith_novec_int32_t_
|
20.54% |
614131.966 |
740245.153 |
357.638 |
0.01% |
357.638 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC64
|
20.21% |
124.087 |
149.171 |
1.370 |
-0.07% |
1.370 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC32
|
20.10% |
134.220 |
161.197 |
0.117 |
-0.12% |
0.117 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC31
|
20.08% |
149.553 |
179.576 |
0.017 |
-0.00% |
0.017 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint8_t_To_uint64_t_
|
20.07% |
10929.547 |
13122.761 |
810.734 |
0.44% |
810.734 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_PIC_2D_LAMBDA/5001
|
19.46% |
1005.798 |
1201.485 |
25.015 |
-2.35% |
25.015 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC16
|
19.41% |
77.901 |
93.020 |
0.103 |
-0.11% |
0.103 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_HYDRO_1D_RAW/171
|
19.39% |
0.372 |
0.444 |
0.001 |
0.14% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_VOL3D_CALC_LAMBDA/1
|
19.08% |
218.403 |
260.085 |
0.246 |
-0.03% |
0.246 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_VOL3D_CALC_RAW/1
|
19.01% |
218.492 |
260.028 |
0.133 |
-0.04% |
0.133 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_VOL3D_CALC_LAMBDA/0
|
19.00% |
1064.330 |
1266.532 |
1.240 |
-0.08% |
1.240 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_VOL3D_CALC_RAW/0
|
18.97% |
1064.496 |
1266.442 |
1.414 |
0.10% |
1.414 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_HYDRO_1D_LAMBDA/171
|
18.73% |
0.372 |
0.441 |
0.002 |
-0.11% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint16_t_To_uint32_t_
|
18.58% |
6293.501 |
7462.884 |
0.456 |
0.00% |
0.456 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC8
|
18.23% |
49.749 |
58.819 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, EqZero, First>
|
18.19% |
14106.018 |
16671.646 |
0.820 |
0.00% |
0.820 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_no_runtime_checks_needed<16, int>
|
18.18% |
20.650 |
24.404 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC63
|
18.18% |
128.089 |
151.371 |
2.332 |
0.10% |
2.332 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, EqZero, Mid>
|
18.17% |
14105.728 |
16668.234 |
0.498 |
-0.00% |
0.498 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, EqZero, Last>
|
18.13% |
14110.454 |
16668.237 |
0.591 |
0.01% |
0.591 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint32_t_To_uint8_t_
|
17.43% |
9090.582 |
10674.959 |
11.178 |
0.31% |
11.178 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC127
|
17.34% |
516.088 |
605.558 |
0.146 |
-0.03% |
0.146 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC8
|
17.28% |
50.689 |
59.449 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC128
|
17.00% |
942.676 |
1102.896 |
0.220 |
-0.04% |
0.220 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC127
|
16.97% |
936.402 |
1095.323 |
0.212 |
0.00% |
0.212 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_PIC_2D_RAW/5001
|
16.66% |
1012.660 |
1181.409 |
53.013 |
-0.57% |
53.013 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC64
|
16.62% |
481.951 |
562.061 |
0.289 |
-0.04% |
0.289 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC63
|
16.56% |
475.692 |
554.472 |
1.875 |
-0.05% |
1.875 |
|
SingleSource/Benchmarks/Misc/salsa20
Profile
|
16.45% |
13.213 |
15.386 |
0.000 |
0.01% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC7
|
16.09% |
44.743 |
51.940 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC8
|
16.08% |
44.742 |
51.937 |
0.003 |
-0.00% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC4
|
16.08% |
44.741 |
51.935 |
0.002 |
0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC2
|
16.08% |
44.745 |
51.939 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC1
|
16.07% |
44.745 |
51.934 |
0.003 |
0.00% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC3
|
16.06% |
44.746 |
51.934 |
0.003 |
-0.00% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint8_t_To_uint16_t_
|
15.95% |
3240.495 |
3757.263 |
0.473 |
-0.01% |
0.473 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC32
|
15.92% |
251.551 |
291.597 |
0.301 |
-0.13% |
0.301 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_with_cond_arith_novec_int64_t_
|
15.90% |
683753.539 |
792500.799 |
1431.906 |
0.25% |
1431.906 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC8
|
15.85% |
51.315 |
59.446 |
0.004 |
-0.01% |
0.004 |
|
External/SPEC/CFP2017rate/508.namd_r/508.namd_r
Profile
|
15.84% |
193.416 |
224.052 |
0.086 |
0.01% |
0.086 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, EqZero, First>
|
15.77% |
12183.801 |
14104.864 |
0.313 |
-0.00% |
0.313 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, EqZero, Last>
|
15.76% |
12183.411 |
14103.888 |
1.365 |
-0.01% |
1.365 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, EqZero, Mid>
|
15.76% |
12183.656 |
14103.406 |
0.281 |
0.00% |
0.281 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint64_t_To_uint8_t_
|
15.66% |
19121.073 |
22116.174 |
12.806 |
-0.26% |
12.806 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC8
|
15.63% |
20.023 |
23.151 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_with_cond_arith_autovec_int64_t_
|
15.55% |
683404.276 |
789666.618 |
906.375 |
-0.25% |
906.375 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint32_t_To_uint16_t_
|
15.51% |
11110.124 |
12833.595 |
27.326 |
-0.03% |
27.326 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC31
|
15.47% |
245.365 |
283.327 |
0.389 |
-0.27% |
0.389 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC63
|
15.36% |
324.504 |
374.344 |
0.246 |
-0.02% |
0.246 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC8
|
15.14% |
20.650 |
23.777 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC128
|
15.03% |
70.714 |
81.342 |
0.008 |
-0.00% |
0.008 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC16
|
14.98% |
136.419 |
156.849 |
0.104 |
-0.07% |
0.104 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint8_t_To_uint16_t_
|
14.86% |
3954.523 |
4542.315 |
0.318 |
0.01% |
0.318 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC15
|
14.75% |
93.247 |
107.005 |
0.004 |
0.00% |
0.004 |
|
SingleSource/Benchmarks/Shootout-C++/Shootout-C++-matrix
Profile
|
14.62% |
2.190 |
2.510 |
0.000 |
0.02% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC63
|
14.46% |
290.687 |
332.733 |
0.094 |
-0.03% |
0.094 |
|
MultiSource/Benchmarks/MiBench/security-rijndael/security-rijndael
Profile
|
14.44% |
0.293 |
0.335 |
0.000 |
-0.04% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC15
|
14.26% |
130.152 |
148.714 |
0.109 |
-0.06% |
0.109 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_DISC_ORD_RAW/44217
|
14.23% |
11633.283 |
13288.557 |
434.519 |
-0.39% |
434.519 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint16_t_To_uint8_t_
|
14.15% |
4155.635 |
4743.525 |
0.239 |
0.00% |
0.239 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC31
|
13.93% |
76.344 |
86.983 |
0.254 |
0.59% |
0.254 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint32_t_To_uint8_t_
|
13.60% |
9679.441 |
10995.400 |
8.920 |
-1.20% |
8.920 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC2
|
13.33% |
18.773 |
21.275 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC15
|
13.24% |
94.491 |
107.001 |
0.006 |
-0.01% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC8
|
13.18% |
78.850 |
89.244 |
0.116 |
-0.18% |
0.116 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC16
|
12.92% |
45.995 |
51.936 |
0.004 |
-0.01% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC15
|
12.90% |
46.000 |
51.935 |
0.003 |
-0.01% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC16
|
12.77% |
29.410 |
33.165 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC4
|
12.68% |
99.123 |
111.692 |
2.239 |
-1.23% |
2.239 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC4
|
12.51% |
20.023 |
22.528 |
0.002 |
0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC3
|
12.49% |
20.026 |
22.528 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC4
|
12.47% |
20.028 |
22.526 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC32
|
12.31% |
76.346 |
85.742 |
0.805 |
0.25% |
0.805 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC7
|
12.08% |
72.590 |
81.358 |
0.021 |
-0.00% |
0.021 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC4
|
11.85% |
36.923 |
41.300 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_BAND_LIN_EQ_RAW/171
|
11.85% |
0.343 |
0.384 |
0.000 |
4.76% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_BAND_LIN_EQ_LAMBDA/171
|
11.85% |
0.343 |
0.384 |
0.000 |
4.78% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint8_t>/51
|
11.84% |
110.774 |
123.895 |
0.010 |
33.93% |
0.010 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_HYDRO_1D_RAW/5001
|
11.84% |
15.643 |
17.494 |
0.284 |
-0.43% |
0.284 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC4
|
11.75% |
21.277 |
23.777 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC64
|
11.68% |
48.184 |
53.814 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/16
|
11.31% |
103.737 |
115.469 |
0.007 |
0.00% |
0.007 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC4
|
11.14% |
50.064 |
55.643 |
0.025 |
-0.04% |
0.025 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/32
|
11.10% |
425.796 |
473.041 |
0.049 |
0.00% |
0.049 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint8_t_To_uint16_t_
|
10.95% |
5269.421 |
5846.553 |
30.159 |
-0.07% |
30.159 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/256
|
10.82% |
28372.228 |
31441.735 |
4.172 |
-0.02% |
4.172 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC8
|
10.82% |
23.153 |
25.657 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC8
|
10.80% |
23.154 |
25.656 |
0.002 |
-0.01% |
0.002 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/128
|
10.72% |
7147.267 |
7913.221 |
3.505 |
-0.05% |
3.505 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC7
|
10.63% |
29.414 |
32.541 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/ImageProcessing/Dilate/Dilate.test:BENCHMARK_DILATE/1024
|
10.61% |
6772.743 |
7491.328 |
57.081 |
-0.07% |
57.081 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC7
|
10.53% |
23.779 |
26.282 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC7
|
10.51% |
23.780 |
26.280 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC127
|
10.46% |
91.992 |
101.613 |
0.340 |
-0.26% |
0.340 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC32
|
10.39% |
48.182 |
53.189 |
0.004 |
-0.01% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_only_autovec_int64_t_
|
10.30% |
301702.837 |
332783.939 |
637.661 |
-0.15% |
637.661 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC31
|
10.23% |
178.045 |
196.265 |
0.108 |
-0.10% |
0.108 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_DEL_DOT_VEC_2D_RAW/1
|
10.18% |
260.647 |
287.183 |
0.102 |
0.04% |
0.102 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC4
|
10.00% |
37.546 |
41.299 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_DEL_DOT_VEC_2D_LAMBDA/1
|
9.84% |
261.255 |
286.958 |
0.063 |
-0.06% |
0.063 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC7
|
9.75% |
25.656 |
28.157 |
0.002 |
-0.01% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC8
|
9.71% |
24.404 |
26.773 |
0.271 |
-0.52% |
0.271 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/64
|
9.62% |
1746.678 |
1914.681 |
7.090 |
0.06% |
7.090 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_DEL_DOT_VEC_2D_LAMBDA/2
|
9.54% |
3.205 |
3.510 |
0.000 |
-0.01% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_DEL_DOT_VEC_2D_RAW/2
|
9.54% |
3.205 |
3.510 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC16
|
9.42% |
33.167 |
36.292 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC8
|
9.30% |
26.908 |
29.410 |
0.003 |
-0.01% |
0.003 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_runtime_checks_pass<4, int>
|
9.27% |
15.333 |
16.754 |
0.058 |
-0.03% |
0.058 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint16_t_To_uint8_t_
|
9.09% |
6241.227 |
6808.408 |
19.594 |
-0.11% |
19.594 |
|
MultiSource/Benchmarks/FreeBench/pifft/pifft
Profile
|
8.96% |
0.329 |
0.359 |
0.000 |
0.02% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC2
|
8.92% |
35.044 |
38.170 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint8_t>/28
|
8.89% |
75.853 |
82.594 |
0.004 |
22.20% |
0.004 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_DIFF_PREDICT_LAMBDA/171
|
8.86% |
11.279 |
12.279 |
0.045 |
-0.71% |
0.045 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC64
|
8.76% |
85.733 |
93.240 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIRST_SUM_LAMBDA/5001
|
8.68% |
19.028 |
20.680 |
0.189 |
-0.34% |
0.189 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC3
|
8.57% |
43.805 |
47.558 |
0.006 |
0.00% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC16
|
8.51% |
29.411 |
31.914 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC16
|
8.51% |
29.412 |
31.913 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC32
|
8.47% |
36.922 |
40.049 |
0.003 |
-0.00% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC15
|
8.33% |
30.035 |
32.539 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC15
|
8.32% |
30.041 |
32.541 |
0.001 |
0.00% |
0.001 |
|
MultiSource/Benchmarks/Trimaran/enc-md5/enc-md5
Profile
|
8.13% |
3.244 |
3.507 |
0.000 |
0.02% |
0.000 |
|
MultiSource/Benchmarks/VersaBench/beamformer/beamformer
Profile
|
8.11% |
4.811 |
5.201 |
0.002 |
0.00% |
0.002 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_xor_no_runtime_checks_needed<16, int>
|
7.98% |
15.646 |
16.895 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_DEL_DOT_VEC_2D_LAMBDA/0
|
7.94% |
1662.909 |
1794.967 |
6.599 |
0.17% |
6.599 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint8_t_To_uint32_t_
|
7.92% |
11826.090 |
12762.493 |
28.343 |
-0.13% |
28.343 |
|
MultiSource/Applications/lambda-0.1.3/lambda
Profile
|
7.90% |
14.730 |
15.893 |
0.016 |
-0.05% |
0.016 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_DEL_DOT_VEC_2D_RAW/0
|
7.89% |
1663.799 |
1795.106 |
2.271 |
-0.32% |
2.271 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIND_FIRST_MIN_RAW/171
|
7.78% |
1.389 |
1.497 |
0.000 |
0.03% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC128
|
7.76% |
160.845 |
173.332 |
0.003 |
0.00% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint8_t>/127
|
7.75% |
128.917 |
138.913 |
0.006 |
-0.00% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC7
|
7.61% |
65.706 |
70.705 |
0.004 |
-0.01% |
0.004 |
|
SingleSource/Benchmarks/Misc/pi
Profile
|
7.52% |
1.658 |
1.782 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC15
|
7.37% |
50.701 |
54.439 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint16_t_To_uint64_t_
|
7.35% |
23285.067 |
24996.763 |
25.688 |
0.04% |
25.688 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC15
|
7.32% |
41.980 |
45.054 |
0.003 |
0.01% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC31
|
7.20% |
69.464 |
74.468 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint16_t_To_uint64_t_
|
7.17% |
18846.292 |
20196.640 |
50.485 |
0.26% |
50.485 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_xor_runtime_checks_fail<16, int>
|
6.97% |
26.909 |
28.785 |
0.002 |
0.01% |
0.002 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_xor_runtime_checks_pass<16, int>
|
6.96% |
26.912 |
28.785 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_HYDRO_2D_RAW/171
|
6.90% |
82.608 |
88.311 |
0.398 |
-0.36% |
0.398 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC63
|
6.89% |
107.125 |
114.509 |
0.007 |
-0.00% |
0.007 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC128
|
6.85% |
64.421 |
68.834 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC127
|
6.79% |
64.448 |
68.825 |
0.007 |
0.00% |
0.007 |
|
SingleSource/Benchmarks/Misc/flops-6
Profile
|
6.77% |
1.229 |
1.312 |
0.001 |
-0.04% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC15
|
6.76% |
36.925 |
39.421 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint16_t>/127
|
6.72% |
130.165 |
138.913 |
0.005 |
0.00% |
0.005 |
|
SingleSource/Benchmarks/Misc-C++/Large/sphereflake
Profile
|
6.57% |
18.775 |
20.008 |
0.003 |
-0.02% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC16
|
6.56% |
38.171 |
40.675 |
0.002 |
0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC63
|
6.49% |
69.463 |
73.970 |
0.272 |
-0.34% |
0.272 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC127
|
6.46% |
182.794 |
194.605 |
0.019 |
-0.00% |
0.019 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint8_t>/65
|
6.27% |
89.498 |
95.112 |
0.007 |
0.00% |
0.007 |
|
MultiSource/Benchmarks/MiBench/telecomm-gsm/telecomm-gsm
Profile
|
6.26% |
0.624 |
0.663 |
0.000 |
-0.01% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint32_t>/127
|
6.23% |
130.173 |
138.287 |
0.002 |
0.00% |
0.002 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIND_FIRST_MIN_RAW/5001
|
6.22% |
42.553 |
45.202 |
0.234 |
-0.30% |
0.234 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC16
|
6.22% |
30.040 |
31.907 |
0.004 |
0.00% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_only_autovec_int32_t_
|
6.18% |
170443.923 |
180971.036 |
402.790 |
-0.08% |
402.790 |
|
External/SPEC/CFP2017rate/538.imagick_r/538.imagick_r
Profile
|
6.03% |
275.461 |
292.084 |
0.443 |
0.00% |
0.443 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopTC8
|
6.02% |
137.829 |
146.123 |
1.661 |
-0.51% |
1.661 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC16
|
5.99% |
31.290 |
33.163 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC32
|
5.96% |
41.928 |
44.426 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC32
|
5.96% |
41.928 |
44.425 |
0.004 |
-0.01% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC31
|
5.92% |
42.553 |
45.070 |
0.006 |
-0.00% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC31
|
5.88% |
42.553 |
45.055 |
0.001 |
-0.00% |
0.001 |
|
MultiSource/Benchmarks/SciMark2-C/scimark2
Profile
|
5.83% |
101.791 |
107.728 |
0.011 |
0.03% |
0.011 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint32_t>/999
|
5.68% |
659.064 |
696.485 |
0.041 |
-0.01% |
0.041 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC7
|
5.62% |
330.842 |
349.445 |
6.378 |
-1.48% |
6.378 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC7
|
5.60% |
66.961 |
70.708 |
0.003 |
-0.01% |
0.003 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_runtime_checks_fail<4, int>
|
5.57% |
15.331 |
16.186 |
0.240 |
1.18% |
0.240 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint8_t_To_uint16_t_
|
5.56% |
3434.383 |
3625.402 |
22.717 |
-0.22% |
22.717 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopWithReductionTC1
|
5.54% |
11.264 |
11.888 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint32_t>/999
|
5.51% |
1293.794 |
1365.059 |
0.084 |
0.00% |
0.084 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIND_FIRST_MIN_RAW/44217
|
5.45% |
369.172 |
389.310 |
0.404 |
-0.07% |
0.404 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC32
|
5.40% |
23.153 |
24.404 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC31
|
5.39% |
23.155 |
24.404 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC32
|
5.39% |
23.155 |
24.403 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC31
|
5.37% |
23.158 |
24.403 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC32
|
5.37% |
58.198 |
61.325 |
0.004 |
-0.00% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC15
|
5.34% |
121.707 |
128.207 |
0.036 |
-0.04% |
0.036 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint32_t_To_uint64_t_
|
5.29% |
20326.711 |
21402.938 |
48.166 |
-0.22% |
48.166 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC31
|
5.27% |
229.139 |
241.208 |
0.062 |
-0.01% |
0.062 |
|
SingleSource/Benchmarks/Stanford/Puzzle
Profile
|
5.26% |
0.229 |
0.241 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_BAND_LIN_EQ_RAW/5001
|
5.11% |
20.293 |
21.330 |
0.121 |
-0.71% |
0.121 |
|
SingleSource/Benchmarks/Misc/oourafft
Profile
|
5.10% |
14.597 |
15.341 |
0.139 |
0.64% |
0.139 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_DIFF_PREDICT_RAW/171
|
5.06% |
11.351 |
11.925 |
0.207 |
-0.06% |
0.207 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint32_t>/256
|
5.04% |
346.693 |
364.183 |
0.023 |
0.00% |
0.023 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC127
|
5.03% |
2277.102 |
2391.650 |
23.278 |
-1.44% |
23.278 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_HYDRO_2D_LAMBDA/171
|
4.99% |
84.551 |
88.771 |
0.135 |
-0.04% |
0.135 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C++/miniFE/miniFE
Profile
|
4.92% |
15.073 |
15.815 |
0.069 |
-0.96% |
0.069 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC63
|
4.87% |
41.732 |
43.764 |
0.018 |
-0.06% |
0.018 |
|
SingleSource/Benchmarks/Misc/revertBits
Profile
|
4.87% |
0.611 |
0.641 |
0.000 |
-0.01% |
0.000 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_runtime_checks_fail<16, int>
|
4.82% |
51.937 |
54.440 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint16_t>/65
|
4.80% |
90.751 |
95.110 |
0.008 |
-0.01% |
0.008 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_runtime_checks_pass<16, int>
|
4.80% |
51.941 |
54.436 |
0.003 |
-0.00% |
0.003 |
|
SingleSource/Benchmarks/Polybench/stencils/jacobi-2d/jacobi-2d
Profile
|
4.80% |
30.629 |
32.100 |
0.121 |
-0.39% |
0.121 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC31
|
4.67% |
66.961 |
70.086 |
0.003 |
0.00% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopWithReductionTC2
|
4.66% |
13.153 |
13.766 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC15
|
4.55% |
13.767 |
14.392 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC3
|
4.54% |
13.767 |
14.392 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC7
|
4.54% |
13.766 |
14.391 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC2
|
4.54% |
13.767 |
14.392 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC4
|
4.54% |
13.767 |
14.392 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC2
|
4.54% |
13.767 |
14.391 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC4
|
4.54% |
13.767 |
14.392 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC3
|
4.54% |
13.767 |
14.391 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC7
|
4.54% |
13.767 |
14.392 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC8
|
4.53% |
13.768 |
14.392 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC8
|
4.53% |
13.767 |
14.391 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC1
|
4.53% |
13.770 |
14.394 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC1
|
4.53% |
13.768 |
14.392 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC16
|
4.51% |
13.771 |
14.392 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC15
|
4.49% |
13.773 |
14.391 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint64_t>/999
|
4.45% |
1734.176 |
1811.363 |
0.170 |
0.00% |
0.170 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_PIC_2D_LAMBDA/171
|
4.43% |
12.897 |
13.468 |
0.064 |
-0.22% |
0.064 |
|
MultiSource/Benchmarks/Rodinia/hotspot/hotspot
Profile
|
4.39% |
1.951 |
2.036 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_PIC_2D_RAW/171
|
4.34% |
12.977 |
13.540 |
0.065 |
0.01% |
0.065 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint64_t>/999
|
4.33% |
3446.173 |
3595.415 |
0.058 |
0.01% |
0.058 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_nested_cond_load_novec_int32_t_
|
4.27% |
623120.888 |
649699.037 |
459.099 |
0.57% |
459.099 |
|
SingleSource/Benchmarks/Misc/flops-5
Profile
|
4.25% |
1.939 |
2.021 |
0.001 |
0.02% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint64_t>/256
|
4.24% |
897.472 |
935.491 |
0.073 |
-0.01% |
0.073 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_ENERGY_CALC_RAW/171
|
4.21% |
13.627 |
14.200 |
0.016 |
-0.28% |
0.016 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC31
|
4.20% |
59.451 |
61.946 |
0.003 |
0.00% |
0.003 |
|
MicroBenchmarks/ImageProcessing/Dilate/Dilate.test:BENCHMARK_DILATE/256
|
4.13% |
1022.884 |
1065.168 |
2.419 |
-0.20% |
2.419 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint32_t>/65
|
4.13% |
90.737 |
94.484 |
0.005 |
-0.00% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC32
|
4.11% |
60.700 |
63.196 |
0.003 |
-0.00% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_only_autovec_uint8_t_
|
4.11% |
92374.697 |
96168.132 |
7.704 |
0.01% |
7.704 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint32_t>/256
|
4.11% |
212.765 |
221.501 |
0.016 |
-0.00% |
0.016 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC64
|
4.09% |
41.729 |
43.435 |
0.162 |
0.60% |
0.162 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC3
|
4.00% |
15.644 |
16.270 |
0.002 |
0.00% |
0.002 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_ENERGY_CALC_RAW/5001
|
3.97% |
424.517 |
441.377 |
2.008 |
-1.64% |
2.008 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint8_t_To_uint64_t_
|
3.91% |
22643.616 |
23528.604 |
19.974 |
0.08% |
19.974 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_ENERGY_CALC_LAMBDA/171
|
3.89% |
13.662 |
14.193 |
0.027 |
-0.38% |
0.027 |
|
SingleSource/Benchmarks/Shootout/Shootout-matrix
Profile
|
3.82% |
3.721 |
3.864 |
0.000 |
0.01% |
0.000 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<31, EqZero, First>
|
3.81% |
3223.487 |
3346.185 |
0.641 |
-0.00% |
0.641 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint64_t>/256
|
3.77% |
495.703 |
514.366 |
0.029 |
-0.01% |
0.029 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC64
|
3.74% |
66.959 |
69.460 |
0.008 |
-0.00% |
0.008 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC64
|
3.73% |
66.957 |
69.457 |
0.005 |
-0.01% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC63
|
3.71% |
67.583 |
70.093 |
0.004 |
0.00% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC63
|
3.70% |
67.582 |
70.085 |
0.004 |
-0.00% |
0.004 |
|
SingleSource/Benchmarks/BenchmarkGame/n-body
Profile
|
3.68% |
2.634 |
2.731 |
0.000 |
26.21% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC31
|
3.64% |
58.196 |
60.312 |
0.091 |
0.06% |
0.091 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint16_t_To_uint8_t_
|
3.59% |
2773.003 |
2872.612 |
21.552 |
-0.19% |
21.552 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint64_t_To_uint32_t_
|
3.49% |
18702.358 |
19354.951 |
44.354 |
-0.26% |
44.354 |
|
MultiSource/Benchmarks/nbench/nbench
Profile
|
3.49% |
5.910 |
6.116 |
0.002 |
-0.17% |
0.002 |
|
External/SPEC/CFP2017rate/544.nab_r/544.nab_r
Profile
|
3.41% |
460.810 |
476.521 |
0.073 |
-0.28% |
0.073 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_PRESSURE_CALC_LAMBDA/44217
|
3.36% |
486.281 |
502.617 |
3.982 |
0.05% |
3.982 |
|
MultiSource/Applications/JM/lencod/lencod
Profile
|
3.35% |
31.675 |
32.734 |
0.034 |
0.51% |
0.034 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint32_t_To_uint16_t_
|
3.33% |
9519.998 |
9836.734 |
28.983 |
-0.44% |
28.983 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint16_t>/999
|
3.25% |
498.774 |
514.991 |
0.015 |
-0.01% |
0.015 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1BigLoopWithReductionTC1
|
3.21% |
19.400 |
20.023 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC31
|
3.21% |
90.941 |
93.858 |
0.002 |
0.01% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchVecWithRuntimeChecks4PointersDBeforeA/1000
|
3.17% |
4865903.340 |
5019920.849 |
445.142 |
-0.00% |
445.142 |
|
SingleSource/Benchmarks/Shootout/Shootout-lists
Profile
|
3.07% |
10.977 |
11.314 |
0.002 |
0.01% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint16_t_To_uint8_t_
|
3.02% |
4379.583 |
4511.715 |
21.585 |
-0.12% |
21.585 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint16_t>/999
|
2.91% |
985.052 |
1013.750 |
0.151 |
-0.01% |
0.151 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC64
|
2.89% |
108.259 |
111.392 |
0.002 |
0.01% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC1
|
2.84% |
21.904 |
22.526 |
0.001 |
0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC1
|
2.83% |
21.906 |
22.526 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint8_t>/16
|
2.79% |
58.184 |
59.809 |
0.110 |
11.13% |
0.110 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<31, GreaterThanZero, Last>
|
2.76% |
8101.254 |
8324.478 |
29.653 |
0.35% |
29.653 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC32
|
2.71% |
30.459 |
31.285 |
0.001 |
-0.00% |
0.001 |
|
MultiSource/Benchmarks/FreeBench/mason/mason
Profile
|
2.66% |
0.539 |
0.553 |
0.000 |
-0.01% |
0.000 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C/CoMD/CoMD
Profile
|
2.65% |
9.647 |
9.903 |
0.005 |
0.01% |
0.005 |
|
SingleSource/Benchmarks/Misc-C++/oopack_v1p8
Profile
|
2.63% |
0.468 |
0.480 |
0.000 |
-7.50% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC63
|
2.57% |
117.127 |
120.141 |
0.005 |
-0.00% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint8_t_To_uint32_t_
|
2.55% |
6902.154 |
7077.819 |
0.506 |
0.01% |
0.506 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC32
|
2.53% |
48.813 |
50.049 |
0.005 |
-0.01% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC15
|
2.50% |
43.802 |
44.896 |
0.013 |
0.84% |
0.013 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchVecWithRuntimeChecks4PointersDBeforeA/32
|
2.50% |
162150.953 |
166198.767 |
0.703 |
-0.00% |
0.703 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint8_t>/10
|
2.47% |
47.628 |
48.806 |
0.023 |
5.16% |
0.023 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC63
|
2.39% |
104.503 |
107.003 |
0.007 |
-0.00% |
0.007 |
|
SingleSource/Benchmarks/Misc/fbench
Profile
|
2.38% |
5.628 |
5.762 |
0.000 |
0.01% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC64
|
2.36% |
105.755 |
108.252 |
0.005 |
-0.00% |
0.005 |
|
MultiSource/Benchmarks/FreeBench/fourinarow/fourinarow
Profile
|
2.28% |
0.636 |
0.651 |
0.000 |
-0.01% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_only_autovec_int64_t_
|
2.24% |
1417682.655 |
1449435.940 |
424.909 |
-0.02% |
424.909 |
|
SingleSource/Benchmarks/Misc/flops-1
Profile
|
2.21% |
8.807 |
9.002 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC31
|
2.19% |
30.486 |
31.155 |
0.035 |
-0.11% |
0.035 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC128
|
2.14% |
117.017 |
119.519 |
0.004 |
-0.00% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC128
|
2.13% |
117.021 |
119.514 |
0.005 |
-0.01% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC127
|
2.12% |
117.655 |
120.148 |
0.005 |
0.00% |
0.005 |
|
SingleSource/Benchmarks/Misc-C++/Large/ray
Profile
|
2.12% |
11.852 |
12.103 |
0.002 |
0.01% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC127
|
2.12% |
117.645 |
120.136 |
0.010 |
-0.00% |
0.010 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint32_t_To_uint64_t_
|
2.00% |
25866.662 |
26384.258 |
14.496 |
0.10% |
14.496 |
|
SingleSource/Benchmarks/Misc/ReedSolomon
Profile
|
2.00% |
20.413 |
20.821 |
0.001 |
0.10% |
0.001 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, LessThanZero, None>
|
2.00% |
36640.262 |
37371.281 |
143.927 |
-0.55% |
143.927 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<32, EqZero, Last>
|
1.98% |
6917.622 |
7054.696 |
9.746 |
0.02% |
9.746 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_FLOYD_DITHER/512
|
1.92% |
6529.256 |
6654.365 |
5.915 |
-0.04% |
5.915 |
|
MultiSource/Benchmarks/Rodinia/pathfinder/pathfinder
Profile
|
1.89% |
1.241 |
1.264 |
0.009 |
0.53% |
0.009 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint64_t_To_uint8_t_
|
1.88% |
19405.138 |
19769.223 |
36.417 |
-0.36% |
36.417 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint16_t_To_uint32_t_
|
1.87% |
11068.185 |
11275.597 |
28.196 |
-0.59% |
28.196 |
|
MultiSource/Benchmarks/Olden/health/health
Profile
|
1.87% |
1.564 |
1.593 |
0.002 |
0.02% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint16_t>/256
|
1.85% |
267.844 |
272.804 |
0.025 |
-0.01% |
0.025 |
|
MultiSource/Benchmarks/mafft/pairlocalalign
Profile
|
1.84% |
92.411 |
94.113 |
0.285 |
0.04% |
0.285 |
|
MicroBenchmarks/ImageProcessing/Dilate/Dilate.test:BENCHMARK_DILATE/512
|
1.78% |
3549.979 |
3613.049 |
10.388 |
0.79% |
10.388 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_EOS_LAMBDA/171
|
1.72% |
0.859 |
0.873 |
0.001 |
0.09% |
0.001 |
|
MultiSource/Benchmarks/sim/sim
Profile
|
1.71% |
9.541 |
9.705 |
0.007 |
0.00% |
0.007 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint64_t>/51
|
1.70% |
145.805 |
148.289 |
0.013 |
-0.01% |
0.013 |
|
SingleSource/Benchmarks/BenchmarkGame/puzzle
Profile
|
1.69% |
0.859 |
0.873 |
0.002 |
-0.03% |
0.002 |
|
External/SPEC/CINT2017rate/531.deepsjeng_r/531.deepsjeng_r
Profile
|
1.67% |
255.759 |
260.039 |
0.299 |
-0.03% |
0.299 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_nested_cond_load_novec_uint8_t_
|
1.62% |
496610.864 |
504635.136 |
46.249 |
-0.02% |
46.249 |
|
MultiSource/Benchmarks/VersaBench/ecbdes/ecbdes
Profile
|
1.60% |
5.060 |
5.141 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_csa_with_in_loop_arith_novec_int64_t_
|
1.60% |
1013255.427 |
1029433.453 |
430.079 |
0.00% |
430.079 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_ENERGY_CALC_RAW/44217
|
1.59% |
4298.531 |
4366.904 |
10.310 |
-0.11% |
10.310 |
|
SingleSource/Benchmarks/Misc/mandel-2
Profile
|
1.58% |
2.496 |
2.536 |
0.000 |
0.01% |
0.000 |
|
MultiSource/Benchmarks/TSVC/ControlLoops-flt/ControlLoops-flt
Profile
|
1.56% |
5.348 |
5.431 |
0.016 |
-0.29% |
0.016 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_cond_load_autovec_int64_t_
|
1.55% |
544112.821 |
552568.147 |
823.190 |
-0.01% |
823.190 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_EOS_RAW/171
|
1.53% |
0.860 |
0.873 |
0.002 |
0.02% |
0.002 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<64, EqZero, Mid>
|
1.51% |
2704.073 |
2744.775 |
10.284 |
0.02% |
10.284 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC128
|
1.50% |
208.383 |
211.513 |
0.010 |
-0.00% |
0.010 |
|
MicroBenchmarks/ImageProcessing/Blur/blur.test:BENCHMARK_boxBlurKernel/128
|
1.48% |
421.900 |
428.136 |
0.872 |
-1.41% |
0.872 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_INT_PREDICT_RAW/171
|
1.40% |
6.828 |
6.924 |
0.004 |
-0.01% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint64_t>/51
|
1.38% |
225.916 |
229.028 |
0.002 |
-0.00% |
0.002 |
|
MultiSource/Benchmarks/tramp3d-v4/tramp3d-v4
Profile
|
1.37% |
1.058 |
1.073 |
0.001 |
-0.26% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC127
|
1.35% |
217.307 |
220.251 |
0.031 |
-0.01% |
0.031 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint32_t>/10
|
1.31% |
46.367 |
46.974 |
0.196 |
1.43% |
0.196 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_FLOYD_DITHER/128
|
1.31% |
432.768 |
438.430 |
0.698 |
-0.24% |
0.698 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopFrom_uint64_t_To_uint16_t_
|
1.29% |
14673.751 |
14863.734 |
69.329 |
0.19% |
69.329 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC127
|
1.28% |
194.621 |
197.108 |
0.005 |
-0.00% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC128
|
1.27% |
195.874 |
198.364 |
0.006 |
-0.00% |
0.006 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<3, EqZero, Mid>
|
1.23% |
37170.627 |
37628.356 |
104.278 |
0.00% |
104.278 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C/SimpleMOC/SimpleMOC
Profile
|
1.23% |
10.307 |
10.433 |
0.011 |
-0.12% |
0.011 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_csa_with_cond_arith_novec_int64_t_
|
1.22% |
736545.253 |
745530.382 |
3054.647 |
0.11% |
3054.647 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<6, LessThanZero, Mid>
|
1.21% |
23529.757 |
23815.143 |
25.538 |
0.03% |
25.538 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_csa_with_cond_arith_autovec_int64_t_
|
1.15% |
737444.763 |
745897.948 |
733.908 |
0.13% |
733.908 |
|
SingleSource/Benchmarks/SmallPT/smallpt
Profile
|
1.11% |
29.712 |
30.041 |
0.004 |
0.02% |
0.004 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_INT_PREDICT_LAMBDA/171
|
1.11% |
6.840 |
6.915 |
0.005 |
-0.14% |
0.005 |
|
MultiSource/Benchmarks/MallocBench/cfrac/cfrac
Profile
|
1.10% |
2.747 |
2.777 |
0.002 |
-0.11% |
0.002 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, LessThanZero, Last>
|
1.10% |
55839.243 |
56454.197 |
105.067 |
0.03% |
105.067 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC63
|
1.10% |
128.737 |
130.148 |
0.016 |
-0.01% |
0.016 |
|
MultiSource/Benchmarks/Fhourstones-3.1/fhourstones3.1
Profile
|
1.09% |
3.942 |
3.985 |
0.003 |
0.14% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_sinhf_autovec_float_
|
1.06% |
2217.728 |
2241.264 |
0.666 |
-0.06% |
0.666 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_sinhf_novec_float_
|
1.06% |
2218.198 |
2241.667 |
0.853 |
-0.01% |
0.853 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<32, LessThanZero, Mid>
|
1.04% |
4524.094 |
4570.978 |
3.545 |
-0.00% |
3.545 |
|
SingleSource/Benchmarks/Shootout-C++/Shootout-C++-hash2
Profile
|
1.03% |
9.245 |
9.340 |
0.021 |
-0.00% |
0.021 |
|
External/SPEC/CFP2017rate/511.povray_r/511.povray_r
Profile
|
1.02% |
33.561 |
33.904 |
0.039 |
0.28% |
0.039 |
|
External/SPEC/CINT2017rate/525.x264_r/525.x264_r
Profile
|
1.02% |
128.307 |
129.612 |
0.076 |
0.00% |
0.076 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC127
|
1.01% |
86.746 |
87.623 |
0.288 |
-0.47% |
0.288 |