|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_INT_PREDICT_LAMBDA/44217
|
131.13% |
8189.580 |
18928.401 |
240.243 |
-2.79% |
240.243 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint64_t_To_uint32_t_
|
106.68% |
17080.237 |
35301.638 |
134.855 |
-0.03% |
134.855 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint64_t_To_uint16_t_
|
101.00% |
17760.336 |
35698.042 |
42.235 |
0.01% |
42.235 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint64_t_To_uint8_t_
|
97.98% |
18719.462 |
37060.570 |
192.148 |
-0.01% |
192.148 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C/miniGMG/miniGMG
Profile
|
90.20% |
4.809 |
9.146 |
0.188 |
-0.48% |
0.188 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint16_t_To_uint64_t_
|
78.00% |
10469.996 |
18636.898 |
40.282 |
-0.20% |
40.282 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_DIFF_PREDICT_LAMBDA/44217
|
73.36% |
14049.853 |
24356.194 |
806.008 |
0.07% |
806.008 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIRST_DIFF_LAMBDA/44217
|
68.77% |
103.062 |
173.940 |
4.672 |
-0.52% |
4.672 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint8_t_To_uint64_t_
|
68.50% |
10550.503 |
17777.552 |
167.569 |
-0.12% |
167.569 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint64_t_To_uint32_t_
|
67.64% |
22770.268 |
38172.927 |
74.788 |
0.05% |
74.788 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_DIFF_PREDICT_RAW/44217
|
64.09% |
14265.027 |
23408.180 |
1110.111 |
0.47% |
1110.111 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/32
|
57.95% |
883.989 |
1396.238 |
0.063 |
-0.00% |
0.063 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_DIFF_PREDICT_LAMBDA/5001
|
57.95% |
1617.589 |
2554.916 |
103.916 |
-0.77% |
103.916 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/16
|
57.82% |
177.117 |
279.528 |
0.008 |
0.00% |
0.008 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_DIFF_PREDICT_RAW/5001
|
56.81% |
1636.032 |
2565.512 |
99.775 |
-0.36% |
99.775 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/128
|
56.50% |
16786.078 |
26269.481 |
1.768 |
-0.01% |
1.768 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/64
|
56.49% |
3950.818 |
6182.707 |
4.188 |
0.01% |
4.188 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/256
|
56.49% |
68454.546 |
107122.565 |
14.631 |
-0.03% |
14.631 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint32_t_To_uint64_t_
|
56.29% |
14634.044 |
22871.984 |
72.532 |
-0.28% |
72.532 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint64_t_To_uint8_t_
|
51.93% |
19815.967 |
30106.557 |
72.464 |
-0.01% |
72.464 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint64_t_To_uint16_t_
|
50.53% |
19223.726 |
28937.854 |
79.799 |
-0.04% |
79.799 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_HYDRO_2D_LAMBDA/44217
|
40.71% |
65556.564 |
92241.677 |
3894.289 |
-0.80% |
3894.289 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint32_t_To_uint8_t_
|
38.90% |
9743.124 |
13533.517 |
20.202 |
0.42% |
20.202 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint64_t_To_uint16_t_
|
37.99% |
18772.527 |
25903.526 |
28.284 |
0.02% |
28.284 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIRST_DIFF_RAW/44217
|
37.05% |
106.058 |
145.356 |
13.249 |
2.01% |
13.249 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC128
|
36.68% |
407.768 |
557.327 |
0.658 |
-0.04% |
0.658 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC128
|
36.62% |
945.414 |
1291.646 |
5.559 |
-0.09% |
5.559 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC64
|
35.48% |
482.434 |
653.588 |
2.431 |
-0.00% |
2.431 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC32
|
35.07% |
247.208 |
333.914 |
1.377 |
-0.00% |
1.377 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC64
|
34.46% |
217.263 |
292.135 |
0.091 |
-0.03% |
0.091 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC16
|
33.92% |
129.777 |
173.792 |
0.653 |
0.00% |
0.653 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint64_t_To_uint8_t_
|
32.22% |
20608.689 |
27248.897 |
23.112 |
0.04% |
23.112 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC32
|
30.11% |
122.145 |
158.921 |
0.045 |
0.03% |
0.045 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC128
|
30.04% |
464.426 |
603.933 |
0.027 |
-0.00% |
0.027 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC128
|
30.02% |
464.486 |
603.937 |
0.026 |
-0.00% |
0.026 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIRST_SUM_LAMBDA/44217
|
28.89% |
137.137 |
176.761 |
2.944 |
0.12% |
2.944 |
|
MicroBenchmarks/ImageProcessing/Blur/blur.test:BENCHMARK_boxBlurKernel/1024
|
28.81% |
23386.247 |
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:benchForIC1VW4BigLoopWithReductionTC64
|
28.45% |
244.055 |
313.492 |
0.034 |
-0.00% |
0.034 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_PIC_2D_RAW/5001
|
28.43% |
919.898 |
1181.409 |
53.013 |
-0.57% |
53.013 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC127
|
28.15% |
480.050 |
615.203 |
0.029 |
0.00% |
0.029 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC127
|
28.14% |
480.118 |
615.219 |
0.017 |
0.00% |
0.017 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_HYDRO_2D_LAMBDA/5001
|
28.08% |
7381.918 |
9454.958 |
498.497 |
-3.09% |
498.497 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint16_t_To_uint32_t_
|
27.33% |
5587.879 |
7115.301 |
13.901 |
0.06% |
13.901 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC4
|
27.28% |
13.766 |
17.521 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_only_autovec_uint8_t_
|
27.14% |
143465.889 |
182404.075 |
16.178 |
0.01% |
16.178 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIND_FIRST_MIN_LAMBDA/171
|
27.04% |
1.182 |
1.501 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint16_t_To_uint64_t_
|
26.84% |
10372.439 |
13156.820 |
372.672 |
-0.39% |
372.672 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint8_t_To_uint32_t_
|
26.77% |
5175.482 |
6560.881 |
50.207 |
-0.32% |
50.207 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIND_FIRST_MIN_LAMBDA/44217
|
26.64% |
307.549 |
389.491 |
0.349 |
-0.02% |
0.349 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIND_FIRST_MIN_LAMBDA/5001
|
25.95% |
35.849 |
45.153 |
0.173 |
-0.23% |
0.173 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC32
|
25.69% |
133.923 |
168.326 |
0.008 |
-0.00% |
0.008 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC127
|
25.69% |
219.087 |
275.366 |
2.205 |
-0.03% |
2.205 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC32
|
25.69% |
133.920 |
168.321 |
0.007 |
-0.01% |
0.007 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC63
|
25.05% |
259.711 |
324.775 |
0.024 |
-0.00% |
0.024 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC63
|
25.04% |
259.736 |
324.765 |
0.018 |
-0.01% |
0.018 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC128
|
25.02% |
218.516 |
273.181 |
1.724 |
-0.57% |
1.724 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC127
|
24.42% |
514.923 |
640.657 |
0.327 |
0.03% |
0.327 |
|
SingleSource/Benchmarks/Adobe-C++/loop_unroll
Profile
|
24.39% |
2.397 |
2.981 |
0.003 |
-4.04% |
0.003 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_DISC_ORD_LAMBDA/44217
|
23.78% |
11684.099 |
14462.358 |
548.323 |
-2.48% |
548.323 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC16
|
23.70% |
74.633 |
92.324 |
0.004 |
0.03% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint16_t_To_uint8_t_
|
23.57% |
3089.655 |
3817.866 |
0.518 |
-0.01% |
0.518 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIRST_SUM_RAW/44217
|
23.35% |
136.404 |
168.252 |
9.226 |
1.15% |
9.226 |
|
MultiSource/Benchmarks/MiBench/automotive-bitcount/automotive-bitcount
Profile
|
23.22% |
0.102 |
0.126 |
0.000 |
0.87% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_VOL3D_CALC_RAW/2
|
23.15% |
7.111 |
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 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, EqZero, None>
|
23.07% |
16668.375 |
20513.181 |
0.575 |
-0.01% |
0.575 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint32_t_To_uint16_t_
|
22.89% |
11238.288 |
13811.074 |
2.438 |
0.03% |
2.438 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint64_t_To_uint32_t_
|
22.58% |
22118.425 |
27113.010 |
19.802 |
0.09% |
19.802 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC63
|
22.38% |
123.694 |
151.371 |
2.332 |
0.10% |
2.332 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, EqZero, Last>
|
22.19% |
11542.409 |
14103.888 |
1.365 |
-0.01% |
1.365 |
|
MultiSource/Benchmarks/Trimaran/enc-pc1/enc-pc1
Profile
|
22.09% |
0.905 |
1.105 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC64
|
21.95% |
122.321 |
149.171 |
1.370 |
-0.07% |
1.370 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint32_t_To_uint8_t_
|
21.80% |
11407.873 |
13895.091 |
33.402 |
-0.04% |
33.402 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_with_cond_arith_novec_uint8_t_
|
21.57% |
613461.799 |
745769.967 |
566.903 |
0.00% |
566.903 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC16
|
21.42% |
78.845 |
95.735 |
0.008 |
-0.01% |
0.008 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC16
|
21.42% |
78.846 |
95.735 |
0.003 |
-0.00% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC128
|
20.99% |
471.635 |
570.609 |
0.084 |
0.01% |
0.084 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC7
|
20.96% |
23.163 |
28.018 |
0.432 |
-2.24% |
0.432 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC64
|
20.86% |
246.278 |
297.647 |
0.110 |
-0.02% |
0.110 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_PIC_2D_LAMBDA/5001
|
20.82% |
994.436 |
1201.485 |
25.015 |
-2.35% |
25.015 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC32
|
20.64% |
133.624 |
161.197 |
0.117 |
-0.12% |
0.117 |
|
MultiSource/Benchmarks/MiBench/security-rijndael/security-rijndael
Profile
|
20.55% |
0.278 |
0.335 |
0.000 |
-0.04% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_PIC_2D_LAMBDA/44217
|
20.53% |
9882.909 |
11911.554 |
26.938 |
0.34% |
26.938 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_with_cond_arith_novec_int32_t_
|
20.40% |
614809.546 |
740245.153 |
357.638 |
0.01% |
357.638 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC16
|
20.29% |
77.327 |
93.020 |
0.103 |
-0.11% |
0.103 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint8_t_To_uint64_t_
|
20.27% |
10911.182 |
13122.761 |
810.734 |
0.44% |
810.734 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC31
|
20.07% |
149.555 |
179.576 |
0.017 |
-0.00% |
0.017 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC31
|
20.07% |
149.571 |
179.590 |
0.008 |
0.00% |
0.008 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC8
|
19.74% |
49.121 |
58.819 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_HYDRO_1D_RAW/171
|
19.40% |
0.372 |
0.444 |
0.001 |
0.14% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_VOL3D_CALC_LAMBDA/1
|
19.06% |
218.444 |
260.085 |
0.246 |
-0.03% |
0.246 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_VOL3D_CALC_RAW/1
|
19.02% |
218.468 |
260.028 |
0.133 |
-0.04% |
0.133 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_VOL3D_CALC_RAW/0
|
18.95% |
1064.691 |
1266.442 |
1.414 |
0.10% |
1.414 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC8
|
18.74% |
20.025 |
23.777 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_HYDRO_1D_LAMBDA/171
|
18.73% |
0.372 |
0.441 |
0.002 |
-0.11% |
0.002 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_VOL3D_CALC_LAMBDA/0
|
18.73% |
1066.738 |
1266.532 |
1.240 |
-0.08% |
1.240 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint16_t_To_uint32_t_
|
18.51% |
6297.302 |
7462.884 |
0.456 |
0.00% |
0.456 |
|
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/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint64_t_To_uint8_t_
|
18.13% |
18722.518 |
22116.174 |
12.806 |
-0.26% |
12.806 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint32_t_To_uint8_t_
|
17.81% |
9061.257 |
10674.959 |
11.178 |
0.31% |
11.178 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC15
|
17.60% |
38.176 |
44.896 |
0.013 |
0.84% |
0.013 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC127
|
17.48% |
515.457 |
605.558 |
0.146 |
-0.03% |
0.146 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC8
|
17.00% |
19.788 |
23.151 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC128
|
16.91% |
943.388 |
1102.896 |
0.220 |
-0.04% |
0.220 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC127
|
16.81% |
937.656 |
1095.323 |
0.212 |
0.00% |
0.212 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC64
|
16.48% |
482.521 |
562.061 |
0.289 |
-0.04% |
0.289 |
|
SingleSource/Benchmarks/Misc/salsa20
Profile
|
16.45% |
13.212 |
15.386 |
0.000 |
0.01% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC63
|
16.28% |
476.857 |
554.472 |
1.875 |
-0.05% |
1.875 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC7
|
16.08% |
44.743 |
51.940 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC2
|
16.08% |
44.743 |
51.939 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC8
|
16.08% |
44.744 |
51.937 |
0.003 |
-0.00% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC4
|
16.08% |
44.742 |
51.935 |
0.002 |
0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC1
|
16.07% |
44.743 |
51.934 |
0.003 |
0.00% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC3
|
16.06% |
44.747 |
51.934 |
0.003 |
-0.00% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint32_t_To_uint16_t_
|
15.98% |
11065.439 |
12833.595 |
27.326 |
-0.03% |
27.326 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint8_t_To_uint16_t_
|
15.95% |
3240.533 |
3757.263 |
0.473 |
-0.01% |
0.473 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC8
|
15.86% |
51.313 |
59.449 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC8
|
15.85% |
51.312 |
59.446 |
0.004 |
-0.01% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_with_cond_arith_novec_int64_t_
|
15.64% |
685337.694 |
792500.799 |
1431.906 |
0.25% |
1431.906 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC32
|
15.63% |
252.182 |
291.597 |
0.301 |
-0.13% |
0.301 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_with_cond_arith_autovec_int64_t_
|
15.54% |
683478.677 |
789666.618 |
906.375 |
-0.25% |
906.375 |
|
External/SPEC/CFP2017rate/508.namd_r/508.namd_r
Profile
|
15.48% |
194.022 |
224.052 |
0.086 |
0.01% |
0.086 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC63
|
15.33% |
324.588 |
374.344 |
0.246 |
-0.02% |
0.246 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC128
|
15.02% |
70.717 |
81.342 |
0.008 |
-0.00% |
0.008 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC31
|
14.91% |
246.571 |
283.327 |
0.389 |
-0.27% |
0.389 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint8_t_To_uint16_t_
|
14.86% |
3954.486 |
4542.315 |
0.318 |
0.01% |
0.318 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC63
|
14.71% |
290.066 |
332.733 |
0.094 |
-0.03% |
0.094 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint32_t_To_uint8_t_
|
14.61% |
9594.042 |
10995.400 |
8.920 |
-1.20% |
8.920 |
|
SingleSource/Benchmarks/Shootout-C++/Shootout-C++-matrix
Profile
|
14.59% |
2.190 |
2.510 |
0.000 |
0.02% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC16
|
14.45% |
137.041 |
156.849 |
0.104 |
-0.07% |
0.104 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint16_t_To_uint8_t_
|
14.16% |
4155.120 |
4743.525 |
0.239 |
0.00% |
0.239 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC31
|
13.95% |
76.337 |
86.983 |
0.254 |
0.59% |
0.254 |
|
MultiSource/Benchmarks/TSVC/CrossingThresholds-flt/CrossingThresholds-flt
Profile
|
13.86% |
9.572 |
10.898 |
0.079 |
-0.14% |
0.079 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, EqZero, None>
|
13.62% |
14104.117 |
16025.246 |
0.233 |
-0.01% |
0.233 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC2
|
13.32% |
18.775 |
21.275 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC15
|
13.24% |
94.486 |
107.001 |
0.006 |
-0.01% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC15
|
13.24% |
94.492 |
107.005 |
0.004 |
0.00% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC15
|
13.16% |
131.416 |
148.714 |
0.109 |
-0.06% |
0.109 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC16
|
12.93% |
45.988 |
51.936 |
0.004 |
-0.01% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC15
|
12.92% |
45.994 |
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:benchForIC1VW4LoopWithReductionTC4
|
12.50% |
20.025 |
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
|
12.49% |
20.026 |
22.526 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint8_t>/51
|
12.37% |
110.253 |
123.895 |
0.010 |
33.93% |
0.010 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC32
|
12.32% |
76.340 |
85.742 |
0.805 |
0.25% |
0.805 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC4
|
12.26% |
99.491 |
111.692 |
2.239 |
-1.23% |
2.239 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_BAND_LIN_EQ_RAW/171
|
11.84% |
0.343 |
0.384 |
0.000 |
4.76% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_BAND_LIN_EQ_LAMBDA/171
|
11.83% |
0.343 |
0.384 |
0.000 |
4.78% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC4
|
11.75% |
21.276 |
23.777 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIRST_SUM_LAMBDA/5001
|
11.72% |
18.510 |
20.680 |
0.189 |
-0.34% |
0.189 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC64
|
11.68% |
48.186 |
53.814 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC16
|
11.53% |
32.541 |
36.292 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC8
|
11.42% |
80.097 |
89.244 |
0.116 |
-0.18% |
0.116 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/16
|
11.31% |
103.738 |
115.469 |
0.007 |
0.00% |
0.007 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint8_t_To_uint16_t_
|
11.18% |
5258.512 |
5846.553 |
30.159 |
-0.07% |
30.159 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/32
|
11.09% |
425.813 |
473.041 |
0.049 |
0.00% |
0.049 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC8
|
10.81% |
23.154 |
25.657 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC8
|
10.81% |
23.152 |
25.656 |
0.002 |
-0.01% |
0.002 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/256
|
10.81% |
28375.142 |
31441.735 |
4.172 |
-0.02% |
4.172 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/128
|
10.73% |
7146.363 |
7913.221 |
3.505 |
-0.05% |
3.505 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC7
|
10.65% |
29.410 |
32.541 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC31
|
10.62% |
177.419 |
196.265 |
0.108 |
-0.10% |
0.108 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC7
|
10.53% |
23.778 |
26.282 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC127
|
10.47% |
91.986 |
101.613 |
0.340 |
-0.26% |
0.340 |
|
MicroBenchmarks/ImageProcessing/Dilate/Dilate.test:BENCHMARK_DILATE/1024
|
10.34% |
6789.468 |
7491.328 |
57.081 |
-0.07% |
57.081 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_only_autovec_int64_t_
|
10.21% |
301945.541 |
332783.939 |
637.661 |
-0.15% |
637.661 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC16
|
10.20% |
28.953 |
31.907 |
0.004 |
0.00% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC7
|
10.18% |
73.841 |
81.358 |
0.021 |
-0.00% |
0.021 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_DEL_DOT_VEC_2D_RAW/1
|
10.11% |
260.809 |
287.183 |
0.102 |
0.04% |
0.102 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC4
|
10.00% |
37.546 |
41.300 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC4
|
10.00% |
37.546 |
41.299 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC7
|
9.97% |
23.898 |
26.280 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_DEL_DOT_VEC_2D_LAMBDA/1
|
9.96% |
260.973 |
286.958 |
0.063 |
-0.06% |
0.063 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC32
|
9.88% |
48.406 |
53.189 |
0.004 |
-0.01% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC4
|
9.78% |
50.686 |
55.643 |
0.025 |
-0.04% |
0.025 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC7
|
9.75% |
25.656 |
28.157 |
0.002 |
-0.01% |
0.002 |
|
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
|
9.53% |
3.205 |
3.510 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC7
|
9.52% |
13.140 |
14.392 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC4
|
9.52% |
13.141 |
14.392 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC8
|
9.52% |
13.141 |
14.392 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC3
|
9.52% |
13.140 |
14.391 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC1
|
9.52% |
13.141 |
14.392 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC2
|
9.52% |
13.141 |
14.391 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC4
|
9.52% |
13.141 |
14.392 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC15
|
9.52% |
13.142 |
14.392 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC3
|
9.52% |
13.141 |
14.392 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC1
|
9.52% |
13.143 |
14.394 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC7
|
9.52% |
13.141 |
14.391 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC8
|
9.51% |
13.141 |
14.391 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC16
|
9.51% |
13.141 |
14.392 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC15
|
9.51% |
13.141 |
14.391 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC2
|
9.51% |
13.143 |
14.392 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/64
|
9.45% |
1749.337 |
1914.681 |
7.090 |
0.06% |
7.090 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC16
|
9.41% |
13.154 |
14.392 |
0.001 |
0.00% |
0.001 |
|
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>
|
9.28% |
15.332 |
16.754 |
0.058 |
-0.03% |
0.058 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint64_t_To_uint16_t_
|
9.23% |
17183.440 |
18768.846 |
173.592 |
-1.13% |
173.592 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_DIFF_PREDICT_LAMBDA/171
|
9.21% |
11.244 |
12.279 |
0.045 |
-0.71% |
0.045 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint16_t_To_uint8_t_
|
9.20% |
6234.970 |
6808.408 |
19.594 |
-0.11% |
19.594 |
|
MultiSource/Benchmarks/FreeBench/pifft/pifft
Profile
|
9.16% |
0.329 |
0.359 |
0.000 |
0.02% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC64
|
8.75% |
85.735 |
93.240 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint8_t>/28
|
8.71% |
75.973 |
82.594 |
0.004 |
22.20% |
0.004 |
|
MicroBenchmarks/ImageProcessing/Dilate/Dilate.test:BENCHMARK_DILATE/128
|
8.58% |
213.241 |
231.538 |
6.539 |
1.31% |
6.539 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC16
|
8.51% |
29.410 |
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
|
8.48% |
36.920 |
40.049 |
0.003 |
-0.00% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC15
|
8.33% |
30.038 |
32.539 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC15
|
8.20% |
50.315 |
54.439 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC31
|
8.14% |
68.859 |
74.468 |
0.001 |
-0.00% |
0.001 |
|
MultiSource/Benchmarks/VersaBench/beamformer/beamformer
Profile
|
8.14% |
4.809 |
5.201 |
0.002 |
0.00% |
0.002 |
|
MultiSource/Benchmarks/Trimaran/enc-md5/enc-md5
Profile
|
8.13% |
3.244 |
3.507 |
0.000 |
0.02% |
0.000 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_xor_no_runtime_checks_needed<16, int>
|
7.99% |
15.645 |
16.895 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint8_t_To_uint32_t_
|
7.91% |
11826.851 |
12762.493 |
28.343 |
-0.13% |
28.343 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_DEL_DOT_VEC_2D_RAW/0
|
7.89% |
1663.797 |
1795.106 |
2.271 |
-0.32% |
2.271 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC128
|
7.84% |
63.829 |
68.834 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC127
|
7.83% |
63.826 |
68.825 |
0.007 |
0.00% |
0.007 |
|
MultiSource/Applications/lambda-0.1.3/lambda
Profile
|
7.82% |
14.740 |
15.893 |
0.016 |
-0.05% |
0.016 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC128
|
7.77% |
160.830 |
173.332 |
0.003 |
0.00% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint8_t>/127
|
7.77% |
128.903 |
138.913 |
0.006 |
-0.00% |
0.006 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIND_FIRST_MIN_RAW/171
|
7.72% |
1.390 |
1.497 |
0.000 |
0.03% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_DEL_DOT_VEC_2D_LAMBDA/0
|
7.67% |
1667.076 |
1794.967 |
6.599 |
0.17% |
6.599 |
|
SingleSource/Benchmarks/Misc/pi
Profile
|
7.54% |
1.657 |
1.782 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC15
|
7.46% |
41.928 |
45.054 |
0.003 |
0.01% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint16_t_To_uint64_t_
|
7.29% |
18824.360 |
20196.640 |
50.485 |
0.26% |
50.485 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC63
|
7.28% |
106.735 |
114.509 |
0.007 |
-0.00% |
0.007 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint16_t_To_uint64_t_
|
7.20% |
23317.730 |
24996.763 |
25.688 |
0.04% |
25.688 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC2
|
7.00% |
35.672 |
38.170 |
0.002 |
-0.00% |
0.002 |
|
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>
|
6.97% |
26.909 |
28.785 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC8
|
6.96% |
25.030 |
26.773 |
0.271 |
-0.52% |
0.271 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_only_autovec_int32_t_
|
6.87% |
169340.723 |
180971.036 |
402.790 |
-0.08% |
402.790 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC15
|
6.77% |
36.921 |
39.421 |
0.002 |
-0.00% |
0.002 |
|
SingleSource/Benchmarks/Misc/flops-6
Profile
|
6.76% |
1.229 |
1.312 |
0.001 |
-0.04% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint16_t>/127
|
6.73% |
130.152 |
138.913 |
0.005 |
0.00% |
0.005 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_HYDRO_2D_LAMBDA/171
|
6.65% |
83.237 |
88.771 |
0.135 |
-0.04% |
0.135 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_DIFF_PREDICT_RAW/171
|
6.63% |
11.184 |
11.925 |
0.207 |
-0.06% |
0.207 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC127
|
6.63% |
182.513 |
194.605 |
0.019 |
-0.00% |
0.019 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC16
|
6.56% |
38.172 |
40.675 |
0.002 |
0.00% |
0.002 |
|
SingleSource/Benchmarks/Misc-C++/Large/sphereflake
Profile
|
6.55% |
18.778 |
20.008 |
0.003 |
-0.02% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC32
|
6.52% |
57.572 |
61.325 |
0.004 |
-0.00% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC63
|
6.49% |
69.462 |
73.970 |
0.272 |
-0.34% |
0.272 |
|
SingleSource/Benchmarks/Misc/perlin
Profile
|
6.35% |
6.205 |
6.599 |
0.000 |
0.01% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint8_t>/65
|
6.28% |
89.489 |
95.112 |
0.007 |
0.00% |
0.007 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint32_t>/127
|
6.24% |
130.166 |
138.287 |
0.002 |
0.00% |
0.002 |
|
External/SPEC/CFP2017rate/538.imagick_r/538.imagick_r
Profile
|
6.19% |
275.066 |
292.084 |
0.443 |
0.00% |
0.443 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIND_FIRST_MIN_RAW/5001
|
6.11% |
42.597 |
45.202 |
0.234 |
-0.30% |
0.234 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC16
|
5.99% |
31.290 |
33.163 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint64_t_To_uint32_t_
|
5.98% |
16897.321 |
17907.217 |
311.171 |
0.53% |
311.171 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC63
|
5.97% |
41.299 |
43.764 |
0.018 |
-0.06% |
0.018 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC32
|
5.96% |
41.927 |
44.425 |
0.004 |
-0.01% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC32
|
5.95% |
41.929 |
44.426 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC31
|
5.92% |
42.551 |
45.070 |
0.006 |
-0.00% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC15
|
5.87% |
121.094 |
128.207 |
0.036 |
-0.04% |
0.036 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC31
|
5.87% |
42.555 |
45.055 |
0.001 |
-0.00% |
0.001 |
|
MultiSource/Benchmarks/SciMark2-C/scimark2
Profile
|
5.84% |
101.787 |
107.728 |
0.011 |
0.03% |
0.011 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint32_t>/999
|
5.69% |
658.989 |
696.485 |
0.041 |
-0.01% |
0.041 |
|
MultiSource/Benchmarks/Rodinia/hotspot/hotspot
Profile
|
5.67% |
1.927 |
2.036 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC7
|
5.61% |
66.954 |
70.708 |
0.003 |
-0.01% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC7
|
5.60% |
66.955 |
70.705 |
0.004 |
-0.01% |
0.004 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_runtime_checks_fail<4, int>
|
5.58% |
15.330 |
16.186 |
0.240 |
1.18% |
0.240 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC3
|
5.56% |
45.054 |
47.558 |
0.006 |
0.00% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC1
|
5.54% |
11.265 |
11.890 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint32_t>/999
|
5.47% |
1294.287 |
1365.059 |
0.084 |
0.00% |
0.084 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint8_t_To_uint16_t_
|
5.46% |
3437.715 |
3625.402 |
22.717 |
-0.22% |
22.717 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C++/miniFE/miniFE
Profile
|
5.45% |
14.997 |
15.815 |
0.069 |
-0.96% |
0.069 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIND_FIRST_MIN_RAW/44217
|
5.41% |
369.342 |
389.310 |
0.404 |
-0.07% |
0.404 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC31
|
5.19% |
229.304 |
241.208 |
0.062 |
-0.01% |
0.062 |
|
SingleSource/Benchmarks/Polybench/stencils/jacobi-2d/jacobi-2d
Profile
|
5.17% |
30.521 |
32.100 |
0.121 |
-0.39% |
0.121 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC64
|
5.17% |
41.300 |
43.435 |
0.162 |
0.60% |
0.162 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC15
|
5.05% |
30.978 |
32.541 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint32_t>/256
|
5.01% |
346.802 |
364.183 |
0.023 |
0.00% |
0.023 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint32_t_To_uint64_t_
|
5.01% |
20382.448 |
21402.938 |
48.166 |
-0.22% |
48.166 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC32
|
4.96% |
47.684 |
50.049 |
0.005 |
-0.01% |
0.005 |
|
SingleSource/Benchmarks/Stanford/Puzzle
Profile
|
4.82% |
0.230 |
0.241 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_runtime_checks_fail<16, int>
|
4.82% |
51.939 |
54.440 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint16_t>/65
|
4.81% |
90.743 |
95.110 |
0.008 |
-0.01% |
0.008 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_runtime_checks_pass<16, int>
|
4.81% |
51.938 |
54.436 |
0.003 |
-0.00% |
0.003 |
|
SingleSource/Benchmarks/Misc/revertBits
Profile
|
4.78% |
0.612 |
0.641 |
0.000 |
-0.01% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC2
|
4.75% |
13.142 |
13.766 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC31
|
4.67% |
66.958 |
70.086 |
0.003 |
0.00% |
0.003 |
|
MultiSource/Benchmarks/McCat/12-IOtest/iotest
Profile
|
4.62% |
1.742 |
1.822 |
0.028 |
-0.13% |
0.028 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint8_t_To_uint64_t_
|
4.61% |
22492.503 |
23528.604 |
19.974 |
0.08% |
19.974 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_HYDRO_2D_RAW/171
|
4.55% |
84.470 |
88.311 |
0.398 |
-0.36% |
0.398 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC31
|
4.54% |
89.779 |
93.858 |
0.002 |
0.01% |
0.002 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_PIC_2D_RAW/171
|
4.50% |
12.957 |
13.540 |
0.065 |
0.01% |
0.065 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint16_t_To_uint8_t_
|
4.45% |
2750.140 |
2872.612 |
21.552 |
-0.19% |
21.552 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint64_t>/999
|
4.41% |
1734.805 |
1811.363 |
0.170 |
0.00% |
0.170 |
|
SingleSource/Benchmarks/Misc/flops-5
Profile
|
4.35% |
1.937 |
2.021 |
0.001 |
0.02% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint64_t>/999
|
4.32% |
3446.453 |
3595.415 |
0.058 |
0.01% |
0.058 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_BAND_LIN_EQ_RAW/5001
|
4.31% |
20.448 |
21.330 |
0.121 |
-0.71% |
0.121 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_cond_load_novec_int32_t_
|
4.24% |
403418.527 |
420510.640 |
250.006 |
2.15% |
250.006 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint64_t>/256
|
4.23% |
897.541 |
935.491 |
0.073 |
-0.01% |
0.073 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC31
|
4.20% |
59.448 |
61.946 |
0.003 |
0.00% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC3
|
4.16% |
15.019 |
15.644 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC32
|
4.15% |
30.039 |
31.285 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint32_t>/65
|
4.13% |
90.733 |
94.484 |
0.005 |
-0.00% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC32
|
4.12% |
60.698 |
63.196 |
0.003 |
-0.00% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint32_t>/256
|
4.11% |
212.756 |
221.501 |
0.016 |
-0.00% |
0.016 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_only_autovec_uint8_t_
|
4.10% |
92381.156 |
96168.132 |
7.704 |
0.01% |
7.704 |
|
MultiSource/Benchmarks/sim/sim
Profile
|
4.05% |
9.327 |
9.705 |
0.007 |
0.00% |
0.007 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_ENERGY_CALC_RAW/171
|
4.04% |
13.649 |
14.200 |
0.016 |
-0.28% |
0.016 |
|
SingleSource/Benchmarks/Misc/oourafft
Profile
|
4.03% |
14.748 |
15.341 |
0.139 |
0.64% |
0.139 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_ENERGY_CALC_LAMBDA/171
|
4.00% |
13.647 |
14.193 |
0.027 |
-0.38% |
0.027 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_PIC_2D_LAMBDA/171
|
3.93% |
12.959 |
13.468 |
0.064 |
-0.22% |
0.064 |
|
External/SPEC/CFP2017rate/544.nab_r/544.nab_r
Profile
|
3.93% |
458.515 |
476.521 |
0.073 |
-0.28% |
0.073 |
|
SingleSource/Benchmarks/Shootout/Shootout-matrix
Profile
|
3.82% |
3.721 |
3.864 |
0.000 |
0.01% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint64_t>/256
|
3.78% |
495.631 |
514.366 |
0.029 |
-0.01% |
0.029 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC64
|
3.74% |
66.956 |
69.460 |
0.008 |
-0.00% |
0.008 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC64
|
3.74% |
66.954 |
69.457 |
0.005 |
-0.01% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC31
|
3.72% |
30.036 |
31.155 |
0.035 |
-0.11% |
0.035 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC63
|
3.72% |
67.582 |
70.093 |
0.004 |
0.00% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC63
|
3.71% |
67.580 |
70.085 |
0.004 |
-0.00% |
0.004 |
|
SingleSource/Benchmarks/BenchmarkGame/n-body
Profile
|
3.70% |
2.634 |
2.731 |
0.000 |
26.21% |
0.000 |
|
MultiSource/Benchmarks/nbench/nbench
Profile
|
3.68% |
5.899 |
6.116 |
0.002 |
-0.17% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint32_t_To_uint16_t_
|
3.65% |
9490.206 |
9836.734 |
28.983 |
-0.44% |
28.983 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_nested_cond_load_novec_int32_t_
|
3.65% |
626821.412 |
649699.037 |
459.099 |
0.57% |
459.099 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC31
|
3.63% |
58.197 |
60.312 |
0.091 |
0.06% |
0.091 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<31, EqZero, First>
|
3.63% |
3228.990 |
3346.185 |
0.641 |
-0.00% |
0.641 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_cond_load_autovec_int64_t_
|
3.58% |
533480.355 |
552568.147 |
823.190 |
-0.01% |
823.190 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint64_t_To_uint32_t_
|
3.50% |
18701.101 |
19354.951 |
44.354 |
-0.26% |
44.354 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC64
|
3.47% |
107.652 |
111.392 |
0.002 |
0.01% |
0.002 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_BAND_LIN_EQ_LAMBDA/5001
|
3.38% |
20.761 |
21.463 |
0.252 |
1.86% |
0.252 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint16_t>/999
|
3.26% |
498.731 |
514.991 |
0.015 |
-0.01% |
0.015 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_PRESSURE_CALC_LAMBDA/44217
|
3.22% |
486.946 |
502.617 |
3.982 |
0.05% |
3.982 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1BigLoopWithReductionTC1
|
3.22% |
19.399 |
20.023 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint16_t_To_uint8_t_
|
3.10% |
4375.945 |
4511.715 |
21.585 |
-0.12% |
21.585 |
|
SingleSource/Benchmarks/Shootout/Shootout-lists
Profile
|
3.09% |
10.975 |
11.314 |
0.002 |
0.01% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint64_t_To_uint8_t_
|
3.09% |
19177.567 |
19769.223 |
36.417 |
-0.36% |
36.417 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchVecWithRuntimeChecks4PointersDBeforeA/1000
|
3.01% |
4873224.514 |
5019920.849 |
445.142 |
-0.00% |
445.142 |
|
MicroBenchmarks/ImageProcessing/Dilate/Dilate.test:BENCHMARK_DILATE/256
|
2.95% |
1034.674 |
1065.168 |
2.419 |
-0.20% |
2.419 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint16_t>/999
|
2.90% |
985.199 |
1013.750 |
0.151 |
-0.01% |
0.151 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC1
|
2.85% |
21.902 |
22.526 |
0.001 |
0.00% |
0.001 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C/CoMD/CoMD
Profile
|
2.77% |
9.636 |
9.903 |
0.005 |
0.01% |
0.005 |
|
SingleSource/Benchmarks/Misc-C++/oopack_v1p8
Profile
|
2.71% |
0.467 |
0.480 |
0.000 |
-7.50% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC63
|
2.67% |
117.019 |
120.141 |
0.005 |
-0.00% |
0.005 |
|
MultiSource/Benchmarks/FreeBench/mason/mason
Profile
|
2.63% |
0.539 |
0.553 |
0.000 |
-0.01% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC32
|
2.63% |
23.780 |
24.404 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC31
|
2.62% |
23.779 |
24.403 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC31
|
2.62% |
23.780 |
24.404 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC32
|
2.62% |
23.781 |
24.403 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint16_t_To_uint32_t_
|
2.58% |
10992.116 |
11275.597 |
28.196 |
-0.59% |
28.196 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint8_t>/10
|
2.57% |
47.582 |
48.806 |
0.023 |
5.16% |
0.023 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint8_t_To_uint32_t_
|
2.56% |
6901.265 |
7077.819 |
0.506 |
0.01% |
0.506 |
|
MultiSource/Applications/JM/lencod/lencod
Profile
|
2.51% |
31.932 |
32.734 |
0.034 |
0.51% |
0.034 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC63
|
2.39% |
104.503 |
107.003 |
0.007 |
-0.00% |
0.007 |
|
SingleSource/Benchmarks/Misc/fbench
Profile
|
2.39% |
5.628 |
5.762 |
0.000 |
0.01% |
0.000 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_FLOYD_DITHER/256
|
2.38% |
1749.215 |
1790.857 |
9.031 |
-0.98% |
9.031 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC64
|
2.36% |
105.751 |
108.252 |
0.005 |
-0.00% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchVecWithRuntimeChecks4PointersDBeforeA/32
|
2.35% |
162387.166 |
166198.767 |
0.703 |
-0.00% |
0.703 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC2
|
2.34% |
13.142 |
13.450 |
0.111 |
2.23% |
0.111 |
|
MultiSource/Benchmarks/FreeBench/fourinarow/fourinarow
Profile
|
2.33% |
0.636 |
0.651 |
0.000 |
-0.01% |
0.000 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<31, GreaterThanZero, Last>
|
2.31% |
8136.279 |
8324.478 |
29.653 |
0.35% |
29.653 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_ENERGY_CALC_RAW/44217
|
2.30% |
4268.717 |
4366.904 |
10.310 |
-0.11% |
10.310 |
|
External/SPEC/CFP2017rate/519.lbm_r/519.lbm_r
Profile
|
2.26% |
195.386 |
199.810 |
1.680 |
-0.43% |
1.680 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_nested_cond_load_novec_uint8_t_
|
2.23% |
493636.193 |
504635.136 |
46.249 |
-0.02% |
46.249 |
|
SingleSource/Benchmarks/Misc/flops-1
Profile
|
2.21% |
8.807 |
9.002 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_ENERGY_CALC_RAW/5001
|
2.15% |
432.072 |
441.377 |
2.008 |
-1.64% |
2.008 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint32_t_To_uint64_t_
|
2.13% |
25833.638 |
26384.258 |
14.496 |
0.10% |
14.496 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC128
|
2.13% |
117.022 |
119.514 |
0.005 |
-0.01% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC127
|
2.12% |
117.648 |
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/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_only_autovec_int64_t_
|
2.11% |
1419450.041 |
1449435.940 |
424.909 |
-0.02% |
424.909 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC127
|
2.10% |
117.663 |
120.136 |
0.010 |
-0.00% |
0.010 |
|
SingleSource/Benchmarks/Misc/ReedSolomon
Profile
|
2.10% |
20.392 |
20.821 |
0.001 |
0.10% |
0.001 |
|
MultiSource/Benchmarks/Rodinia/pathfinder/pathfinder
Profile
|
2.06% |
1.239 |
1.264 |
0.009 |
0.53% |
0.009 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_FLOYD_DITHER/128
|
2.05% |
429.609 |
438.430 |
0.698 |
-0.24% |
0.698 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC63
|
2.01% |
127.590 |
130.148 |
0.016 |
-0.01% |
0.016 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_ADI_LAMBDA/44217
|
1.97% |
19507.417 |
19892.182 |
80.389 |
0.54% |
80.389 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<32, EqZero, Last>
|
1.89% |
6923.725 |
7054.696 |
9.746 |
0.02% |
9.746 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_EOS_RAW/171
|
1.89% |
0.857 |
0.873 |
0.002 |
0.02% |
0.002 |
|
MicroBenchmarks/ImageProcessing/Dilate/Dilate.test:BENCHMARK_DILATE/512
|
1.88% |
3546.282 |
3613.049 |
10.388 |
0.79% |
10.388 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint16_t>/256
|
1.83% |
267.900 |
272.804 |
0.025 |
-0.01% |
0.025 |
|
MultiSource/Benchmarks/mafft/pairlocalalign
Profile
|
1.82% |
92.430 |
94.113 |
0.285 |
0.04% |
0.285 |
|
SingleSource/Benchmarks/BenchmarkGame/puzzle
Profile
|
1.79% |
0.858 |
0.873 |
0.002 |
-0.03% |
0.002 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<6, GreaterThanZero, None>
|
1.78% |
29149.760 |
29669.020 |
15.000 |
-0.07% |
15.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_csa_with_in_loop_arith_novec_int64_t_
|
1.70% |
1012210.683 |
1029433.453 |
430.079 |
0.00% |
430.079 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint64_t>/51
|
1.70% |
145.812 |
148.289 |
0.013 |
-0.01% |
0.013 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<16, LessThanZero, Mid>
|
1.67% |
8521.750 |
8663.849 |
1.828 |
0.05% |
1.828 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_FLOYD_DITHER/512
|
1.64% |
6547.008 |
6654.365 |
5.915 |
-0.04% |
5.915 |
|
MultiSource/Benchmarks/VersaBench/ecbdes/ecbdes
Profile
|
1.59% |
5.060 |
5.141 |
0.000 |
0.00% |
0.000 |
|
SingleSource/Benchmarks/Misc/mandel-2
Profile
|
1.57% |
2.497 |
2.536 |
0.000 |
0.01% |
0.000 |
|
External/SPEC/CINT2017rate/531.deepsjeng_r/531.deepsjeng_r
Profile
|
1.55% |
256.061 |
260.039 |
0.299 |
-0.03% |
0.299 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, GreaterThanZero, None>
|
1.55% |
36617.276 |
37183.877 |
122.028 |
0.02% |
122.028 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_INT_PREDICT_RAW/171
|
1.54% |
6.819 |
6.924 |
0.004 |
-0.01% |
0.004 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<16, EqZero, Mid>
|
1.52% |
8527.656 |
8657.544 |
4.948 |
0.00% |
4.948 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_EOS_LAMBDA/171
|
1.52% |
0.860 |
0.873 |
0.001 |
0.09% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint16_t_To_uint32_t_
|
1.47% |
13332.598 |
13529.077 |
19.251 |
0.03% |
19.251 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C/SimpleMOC/SimpleMOC
Profile
|
1.46% |
10.283 |
10.433 |
0.011 |
-0.12% |
0.011 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_INT_PREDICT_LAMBDA/171
|
1.46% |
6.816 |
6.915 |
0.005 |
-0.14% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC127
|
1.43% |
217.146 |
220.251 |
0.031 |
-0.01% |
0.031 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint64_t>/51
|
1.38% |
225.900 |
229.028 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC128
|
1.37% |
117.904 |
119.519 |
0.004 |
-0.00% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC64
|
1.35% |
85.202 |
86.353 |
0.004 |
0.00% |
0.004 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<6, LessThanZero, Mid>
|
1.34% |
23499.560 |
23815.143 |
25.538 |
0.03% |
25.538 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopFrom_uint64_t_To_uint16_t_
|
1.30% |
14672.912 |
14863.734 |
69.329 |
0.19% |
69.329 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC128
|
1.27% |
195.868 |
198.364 |
0.006 |
-0.00% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC127
|
1.27% |
194.628 |
197.108 |
0.005 |
-0.00% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint32_t>/10
|
1.24% |
46.400 |
46.974 |
0.196 |
1.43% |
0.196 |
|
MultiSource/Benchmarks/Olden/health/health
Profile
|
1.19% |
1.575 |
1.593 |
0.002 |
0.02% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint8_t>/16
|
1.15% |
59.129 |
59.809 |
0.110 |
11.13% |
0.110 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, LessThanZero, Mid>
|
1.12% |
31446.582 |
31799.044 |
113.290 |
0.02% |
113.290 |
|
SingleSource/Benchmarks/SmallPT/smallpt
Profile
|
1.11% |
29.710 |
30.041 |
0.004 |
0.02% |
0.004 |
|
MultiSource/Benchmarks/MallocBench/cfrac/cfrac
Profile
|
1.11% |
2.747 |
2.777 |
0.002 |
-0.11% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_sinhf_autovec_float_
|
1.02% |
2218.646 |
2241.264 |
0.666 |
-0.06% |
0.666 |