|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_INT_PREDICT_LAMBDA/44217
|
135.52% |
8217.354 |
19353.908 |
99.358 |
-0.60% |
99.358 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint64_t_To_uint8_t_
|
94.29% |
19113.265 |
37134.490 |
93.427 |
0.19% |
93.427 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint64_t_To_uint32_t_
|
91.86% |
18369.340 |
35243.705 |
158.172 |
-0.20% |
158.172 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C/miniGMG/miniGMG
Profile
|
90.40% |
4.856 |
9.247 |
0.217 |
-0.25% |
0.217 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint64_t_To_uint16_t_
|
86.41% |
19122.642 |
35645.677 |
144.167 |
-0.10% |
144.167 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint16_t_To_uint64_t_
|
78.56% |
10447.098 |
18654.697 |
142.250 |
-0.11% |
142.250 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIRST_DIFF_LAMBDA/44217
|
72.51% |
103.205 |
178.039 |
6.392 |
1.83% |
6.392 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_DIFF_PREDICT_LAMBDA/44217
|
70.02% |
14260.698 |
24245.553 |
869.734 |
-0.39% |
869.734 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint8_t_To_uint64_t_
|
69.05% |
10546.940 |
17829.710 |
129.964 |
0.02% |
129.964 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint64_t_To_uint32_t_
|
68.31% |
22700.297 |
38206.696 |
86.078 |
0.13% |
86.078 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_DIFF_PREDICT_RAW/44217
|
63.59% |
14104.440 |
23073.803 |
1530.942 |
-0.97% |
1530.942 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_DIFF_PREDICT_LAMBDA/5001
|
61.17% |
1594.302 |
2569.563 |
116.381 |
-0.20% |
116.381 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_DIFF_PREDICT_RAW/5001
|
58.59% |
1617.319 |
2564.906 |
177.994 |
-0.38% |
177.994 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/32
|
57.97% |
883.898 |
1396.277 |
0.030 |
0.00% |
0.030 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/16
|
57.80% |
177.128 |
279.504 |
0.028 |
0.00% |
0.028 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/64
|
57.75% |
3918.612 |
6181.725 |
3.770 |
-0.01% |
3.770 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/256
|
56.54% |
68440.462 |
107138.601 |
7.179 |
-0.01% |
7.179 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/128
|
56.31% |
16803.715 |
26265.330 |
3.537 |
-0.02% |
3.537 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint32_t_To_uint64_t_
|
51.89% |
14888.147 |
22612.999 |
72.333 |
-0.49% |
72.333 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint64_t_To_uint8_t_
|
51.13% |
19897.249 |
30069.957 |
342.447 |
-0.14% |
342.447 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint64_t_To_uint16_t_
|
51.02% |
19174.725 |
28956.872 |
56.167 |
0.03% |
56.167 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, EqZero, None>
|
45.41% |
14105.396 |
20511.267 |
1.937 |
-0.00% |
1.937 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIRST_DIFF_RAW/44217
|
44.10% |
102.750 |
148.068 |
16.067 |
3.91% |
16.067 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint64_t_To_uint16_t_
|
39.93% |
18517.629 |
25912.165 |
5.013 |
0.06% |
5.013 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC128
|
37.76% |
940.984 |
1296.294 |
4.293 |
0.04% |
4.293 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint32_t_To_uint8_t_
|
37.47% |
9796.692 |
13467.326 |
17.524 |
-0.01% |
17.524 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC64
|
36.56% |
480.028 |
655.515 |
2.166 |
-0.17% |
2.166 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC128
|
36.27% |
407.840 |
555.768 |
1.515 |
-0.32% |
1.515 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC32
|
36.15% |
246.014 |
334.936 |
0.980 |
-0.02% |
0.980 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC16
|
34.96% |
129.058 |
174.176 |
0.526 |
-0.07% |
0.526 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC64
|
34.17% |
217.187 |
291.403 |
0.346 |
-0.15% |
0.346 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, EqZero, None>
|
31.54% |
12182.432 |
16024.399 |
0.688 |
0.01% |
0.688 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint64_t_To_uint8_t_
|
31.48% |
20680.980 |
27191.402 |
60.791 |
-0.12% |
60.791 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC128
|
30.21% |
463.868 |
604.017 |
0.037 |
0.00% |
0.037 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC128
|
30.03% |
464.490 |
603.982 |
0.018 |
-0.00% |
0.018 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC32
|
30.01% |
122.104 |
158.751 |
0.110 |
-0.08% |
0.110 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC64
|
28.78% |
243.450 |
313.510 |
0.044 |
0.00% |
0.044 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIRST_SUM_LAMBDA/44217
|
28.57% |
137.797 |
177.165 |
5.888 |
0.35% |
5.888 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint16_t_To_uint64_t_
|
28.54% |
10390.244 |
13355.555 |
422.823 |
0.65% |
422.823 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC127
|
28.47% |
478.888 |
615.209 |
0.011 |
-0.00% |
0.011 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC64
|
28.46% |
244.067 |
313.519 |
0.021 |
0.00% |
0.021 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC127
|
28.13% |
480.103 |
615.166 |
0.042 |
-0.01% |
0.042 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint16_t_To_uint32_t_
|
27.55% |
5573.317 |
7108.965 |
75.346 |
-0.03% |
75.346 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_only_autovec_uint8_t_
|
27.14% |
143417.895 |
182337.361 |
95.346 |
-0.01% |
95.346 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIND_FIRST_MIN_LAMBDA/171
|
27.06% |
1.182 |
1.501 |
0.000 |
0.02% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint8_t_To_uint32_t_
|
27.04% |
5182.004 |
6583.359 |
5.191 |
0.02% |
5.191 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIND_FIRST_MIN_LAMBDA/44217
|
26.31% |
308.172 |
389.242 |
0.376 |
-0.09% |
0.376 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC32
|
26.27% |
133.298 |
168.321 |
0.005 |
-0.00% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC32
|
25.69% |
133.934 |
168.336 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC63
|
25.65% |
258.479 |
324.789 |
0.012 |
0.00% |
0.012 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC128
|
25.23% |
218.833 |
274.047 |
1.125 |
-0.25% |
1.125 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC63
|
25.04% |
259.732 |
324.778 |
0.016 |
-0.01% |
0.016 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIND_FIRST_MIN_LAMBDA/5001
|
24.65% |
36.310 |
45.258 |
0.153 |
0.00% |
0.153 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC127
|
24.50% |
514.770 |
640.903 |
0.345 |
-0.04% |
0.345 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC127
|
24.37% |
220.863 |
274.682 |
0.904 |
-0.28% |
0.904 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC64
|
23.96% |
121.392 |
150.475 |
0.348 |
0.44% |
0.348 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC16
|
23.60% |
74.646 |
92.260 |
0.032 |
-0.02% |
0.032 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint16_t_To_uint8_t_
|
23.50% |
3090.736 |
3817.029 |
1.615 |
-0.03% |
1.615 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_VOL3D_CALC_LAMBDA/2
|
23.13% |
7.111 |
8.757 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_VOL3D_CALC_RAW/2
|
23.11% |
7.113 |
8.757 |
0.001 |
0.00% |
0.001 |
|
SingleSource/Benchmarks/Adobe-C++/loop_unroll
Profile
|
23.06% |
2.424 |
2.982 |
0.004 |
-4.00% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC16
|
22.39% |
78.224 |
95.742 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIRST_SUM_RAW/44217
|
22.30% |
136.010 |
166.345 |
9.709 |
0.01% |
9.709 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint64_t_To_uint32_t_
|
22.27% |
22159.935 |
27094.581 |
14.602 |
0.02% |
14.602 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint32_t_To_uint8_t_
|
22.22% |
11364.400 |
13890.049 |
26.529 |
-0.08% |
26.529 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint32_t_To_uint16_t_
|
22.13% |
11303.278 |
13804.338 |
7.735 |
-0.02% |
7.735 |
|
MultiSource/Benchmarks/Trimaran/enc-pc1/enc-pc1
Profile
|
22.11% |
0.905 |
1.105 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC63
|
21.98% |
123.773 |
150.983 |
1.796 |
-0.16% |
1.796 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_with_cond_arith_novec_uint8_t_
|
21.68% |
612901.864 |
745777.863 |
357.007 |
0.00% |
357.007 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_PIC_2D_LAMBDA/44217
|
21.48% |
9810.205 |
11917.027 |
23.399 |
0.39% |
23.399 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC16
|
21.41% |
78.853 |
95.739 |
0.002 |
0.00% |
0.002 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_PIC_2D_LAMBDA/5001
|
21.38% |
972.922 |
1180.961 |
35.234 |
-4.02% |
35.234 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC32
|
21.11% |
71.871 |
87.040 |
0.266 |
-0.64% |
0.266 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC31
|
21.09% |
148.312 |
179.591 |
0.007 |
0.00% |
0.007 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC128
|
20.84% |
472.302 |
570.726 |
0.048 |
-0.01% |
0.048 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC4
|
20.77% |
14.508 |
17.521 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC64
|
20.45% |
246.882 |
297.364 |
0.253 |
-0.12% |
0.253 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC31
|
20.05% |
149.583 |
179.580 |
0.011 |
-0.00% |
0.011 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_with_cond_arith_novec_int32_t_
|
19.94% |
617121.678 |
740166.178 |
474.562 |
-0.00% |
474.562 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC32
|
19.87% |
134.222 |
160.888 |
0.258 |
-0.31% |
0.258 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_HYDRO_1D_RAW/171
|
19.33% |
0.372 |
0.444 |
0.001 |
0.09% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC16
|
19.33% |
77.919 |
92.978 |
0.123 |
-0.16% |
0.123 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_VOL3D_CALC_RAW/1
|
19.22% |
218.215 |
260.156 |
0.058 |
0.01% |
0.058 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_VOL3D_CALC_LAMBDA/0
|
19.22% |
1064.105 |
1268.605 |
0.587 |
0.01% |
0.587 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_VOL3D_CALC_RAW/0
|
19.17% |
1064.834 |
1268.945 |
0.701 |
-0.15% |
0.701 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_VOL3D_CALC_LAMBDA/1
|
19.13% |
218.434 |
260.227 |
0.057 |
0.02% |
0.057 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_HYDRO_1D_LAMBDA/171
|
19.00% |
0.372 |
0.442 |
0.001 |
-0.02% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint16_t_To_uint32_t_
|
18.56% |
6294.407 |
7462.940 |
2.843 |
0.00% |
2.843 |
|
MultiSource/Benchmarks/MiBench/automotive-bitcount/automotive-bitcount
Profile
|
18.47% |
0.106 |
0.125 |
0.000 |
0.47% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint8_t_To_uint64_t_
|
18.35% |
10922.669 |
12926.911 |
254.496 |
-1.06% |
254.496 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC31
|
18.29% |
73.680 |
87.157 |
0.207 |
-0.51% |
0.207 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, EqZero, First>
|
18.19% |
14105.005 |
16670.381 |
0.975 |
-0.00% |
0.975 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_no_runtime_checks_needed<16, int>
|
18.18% |
20.650 |
24.404 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC8
|
18.17% |
49.747 |
58.784 |
0.020 |
0.03% |
0.020 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, EqZero, Mid>
|
18.15% |
14106.584 |
16666.482 |
0.900 |
0.00% |
0.900 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, EqZero, Last>
|
18.11% |
14111.537 |
16667.265 |
0.401 |
0.00% |
0.401 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint32_t_To_uint8_t_
|
17.45% |
9069.295 |
10652.098 |
14.537 |
0.09% |
14.537 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC127
|
17.41% |
516.031 |
605.882 |
0.053 |
0.00% |
0.053 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC8
|
17.26% |
50.695 |
59.446 |
0.009 |
-0.01% |
0.009 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC128
|
17.06% |
942.642 |
1103.429 |
0.030 |
-0.01% |
0.030 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC127
|
16.97% |
936.397 |
1095.334 |
0.310 |
0.00% |
0.310 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC64
|
16.67% |
481.966 |
562.287 |
0.144 |
-0.00% |
0.144 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC63
|
16.53% |
475.641 |
554.285 |
0.098 |
-0.08% |
0.098 |
|
SingleSource/Benchmarks/Misc/salsa20
Profile
|
16.46% |
13.212 |
15.386 |
0.000 |
0.01% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC7
|
16.08% |
44.744 |
51.939 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC4
|
16.08% |
44.743 |
51.938 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC2
|
16.08% |
44.748 |
51.941 |
0.006 |
-0.01% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC3
|
16.07% |
44.746 |
51.937 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC1
|
16.06% |
44.749 |
51.934 |
0.003 |
0.00% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC8
|
16.05% |
44.753 |
51.937 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC32
|
15.85% |
251.576 |
291.449 |
0.382 |
-0.18% |
0.382 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC8
|
15.84% |
51.313 |
59.443 |
0.003 |
-0.01% |
0.003 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, EqZero, First>
|
15.77% |
12182.795 |
14103.429 |
0.325 |
0.00% |
0.325 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, EqZero, Mid>
|
15.76% |
12182.919 |
14103.140 |
0.605 |
-0.00% |
0.605 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint8_t_To_uint16_t_
|
15.75% |
3245.667 |
3757.009 |
0.285 |
0.01% |
0.285 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, EqZero, Last>
|
15.74% |
12183.603 |
14101.451 |
1.549 |
-0.02% |
1.549 |
|
External/SPEC/CFP2017rate/508.namd_r/508.namd_r
Profile
|
15.63% |
194.258 |
224.627 |
0.311 |
0.20% |
0.311 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC8
|
15.62% |
20.025 |
23.152 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC31
|
15.55% |
245.316 |
283.461 |
0.311 |
-0.22% |
0.311 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint64_t_To_uint8_t_
|
15.52% |
19091.706 |
22055.664 |
57.425 |
0.02% |
57.425 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC63
|
15.45% |
324.299 |
374.401 |
0.118 |
-0.01% |
0.118 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_with_cond_arith_novec_int64_t_
|
15.42% |
684145.851 |
789617.202 |
1784.664 |
-0.05% |
1784.664 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint32_t_To_uint8_t_
|
15.26% |
9660.953 |
11135.679 |
18.784 |
0.06% |
18.784 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint32_t_To_uint16_t_
|
15.20% |
11127.387 |
12819.055 |
45.849 |
-0.14% |
45.849 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC8
|
15.13% |
20.652 |
23.778 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC128
|
15.04% |
70.714 |
81.348 |
0.003 |
0.00% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_with_cond_arith_autovec_int64_t_
|
15.03% |
685412.428 |
788461.848 |
2092.016 |
-0.40% |
2092.016 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC16
|
15.02% |
136.424 |
156.918 |
0.068 |
-0.03% |
0.068 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint8_t_To_uint16_t_
|
14.86% |
3954.852 |
4542.366 |
0.107 |
0.01% |
0.107 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC15
|
14.76% |
93.237 |
107.003 |
0.012 |
0.00% |
0.012 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC63
|
14.45% |
290.705 |
332.723 |
0.193 |
-0.03% |
0.193 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint16_t_To_uint8_t_
|
14.16% |
4154.735 |
4743.166 |
0.237 |
0.00% |
0.237 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC16
|
14.09% |
45.524 |
51.940 |
0.003 |
-0.00% |
0.003 |
|
MultiSource/Benchmarks/MiBench/security-rijndael/security-rijndael
Profile
|
14.05% |
0.294 |
0.335 |
0.001 |
0.02% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC4
|
14.05% |
98.645 |
112.500 |
1.548 |
-0.52% |
1.548 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC15
|
14.02% |
130.167 |
148.414 |
0.248 |
-0.27% |
0.248 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC2
|
13.30% |
18.778 |
21.276 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC15
|
13.23% |
94.497 |
106.997 |
0.006 |
-0.01% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC8
|
13.01% |
78.848 |
89.108 |
0.180 |
-0.33% |
0.180 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC15
|
12.92% |
45.992 |
51.936 |
0.002 |
-0.01% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC16
|
12.76% |
29.411 |
33.163 |
0.004 |
-0.00% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint32_t_To_uint16_t_
|
12.54% |
9698.421 |
10914.633 |
106.224 |
0.13% |
106.224 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIRST_SUM_LAMBDA/5001
|
12.52% |
18.106 |
20.373 |
0.222 |
-0.25% |
0.222 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC4
|
12.49% |
20.025 |
22.526 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC4
|
12.49% |
20.026 |
22.526 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC3
|
12.49% |
20.026 |
22.527 |
0.001 |
0.00% |
0.001 |
|
SingleSource/Benchmarks/Shootout-C++/Shootout-C++-matrix
Profile
|
12.07% |
2.239 |
2.509 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC7
|
12.00% |
72.602 |
81.317 |
0.024 |
0.01% |
0.024 |
|
MicroBenchmarks/ImageProcessing/Blur/blur.test:BENCHMARK_boxBlurKernel/1024
|
11.87% |
26906.325 |
30098.956 |
31.965 |
-0.17% |
31.965 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_BAND_LIN_EQ_RAW/171
|
11.86% |
0.343 |
0.384 |
0.000 |
4.76% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_BAND_LIN_EQ_LAMBDA/171
|
11.86% |
0.343 |
0.384 |
0.000 |
4.78% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC4
|
11.85% |
36.921 |
41.296 |
0.002 |
-0.01% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC4
|
11.77% |
21.275 |
23.778 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC64
|
11.68% |
48.184 |
53.813 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint8_t>/51
|
11.33% |
111.284 |
123.895 |
0.005 |
33.93% |
0.005 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/16
|
11.31% |
103.734 |
115.466 |
0.011 |
0.00% |
0.011 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC4
|
11.18% |
50.064 |
55.661 |
0.014 |
-0.00% |
0.014 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint8_t_To_uint16_t_
|
11.13% |
5262.180 |
5848.048 |
4.560 |
-0.04% |
4.560 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/32
|
11.09% |
425.787 |
473.014 |
0.012 |
-0.00% |
0.012 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC8
|
10.80% |
23.154 |
25.655 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC8
|
10.79% |
23.156 |
25.655 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/256
|
10.73% |
28372.907 |
31417.367 |
21.666 |
-0.10% |
21.666 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/128
|
10.65% |
7148.089 |
7909.140 |
6.552 |
-0.10% |
6.552 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC127
|
10.64% |
91.998 |
101.789 |
0.292 |
-0.09% |
0.292 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC7
|
10.63% |
29.412 |
32.537 |
0.005 |
-0.00% |
0.005 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/64
|
10.57% |
1729.951 |
1912.888 |
4.930 |
-0.02% |
4.930 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC7
|
10.53% |
23.778 |
26.281 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC7
|
10.51% |
23.781 |
26.281 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC32
|
10.38% |
48.182 |
53.184 |
0.007 |
-0.02% |
0.007 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_only_autovec_int64_t_
|
10.35% |
301880.982 |
333137.122 |
136.461 |
-0.04% |
136.461 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_PRESSURE_CALC_LAMBDA/5001
|
10.35% |
42.094 |
46.449 |
0.628 |
-2.22% |
0.628 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC31
|
10.14% |
178.035 |
196.092 |
0.189 |
-0.19% |
0.189 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_DEL_DOT_VEC_2D_RAW/1
|
10.09% |
260.669 |
286.962 |
0.089 |
-0.01% |
0.089 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC8
|
10.05% |
24.406 |
26.858 |
0.068 |
-0.20% |
0.068 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_DEL_DOT_VEC_2D_LAMBDA/1
|
10.01% |
260.915 |
287.027 |
0.042 |
-0.03% |
0.042 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC4
|
10.00% |
37.545 |
41.301 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC7
|
9.74% |
25.659 |
28.157 |
0.002 |
-0.01% |
0.002 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_DIFF_PREDICT_LAMBDA/171
|
9.73% |
11.284 |
12.382 |
0.009 |
0.03% |
0.009 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_DEL_DOT_VEC_2D_RAW/2
|
9.54% |
3.204 |
3.510 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_DEL_DOT_VEC_2D_LAMBDA/2
|
9.52% |
3.205 |
3.510 |
0.000 |
-0.01% |
0.000 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_runtime_checks_pass<4, int>
|
9.42% |
15.331 |
16.775 |
0.031 |
-0.01% |
0.031 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC16
|
9.41% |
33.169 |
36.291 |
0.003 |
-0.01% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC8
|
9.30% |
26.908 |
29.410 |
0.001 |
-0.01% |
0.001 |
|
MultiSource/Benchmarks/FreeBench/pifft/pifft
Profile
|
9.18% |
0.328 |
0.359 |
0.001 |
-0.04% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint16_t_To_uint8_t_
|
9.00% |
6250.333 |
6812.717 |
2.758 |
-0.05% |
2.758 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC2
|
8.92% |
35.045 |
38.170 |
0.003 |
-0.00% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC64
|
8.76% |
85.727 |
93.238 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC3
|
8.57% |
43.805 |
47.557 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC16
|
8.51% |
29.412 |
31.914 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC16
|
8.50% |
29.412 |
31.913 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC32
|
8.47% |
36.920 |
40.047 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC15
|
8.32% |
30.038 |
32.538 |
0.003 |
-0.00% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC15
|
8.32% |
30.038 |
32.538 |
0.001 |
-0.00% |
0.001 |
|
MultiSource/Benchmarks/VersaBench/beamformer/beamformer
Profile
|
8.20% |
4.807 |
5.202 |
0.002 |
-0.00% |
0.002 |
|
MultiSource/Benchmarks/Trimaran/enc-md5/enc-md5
Profile
|
8.08% |
3.244 |
3.506 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_xor_no_runtime_checks_needed<16, int>
|
7.99% |
15.644 |
16.895 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint8_t>/28
|
7.85% |
76.580 |
82.594 |
0.006 |
22.20% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC128
|
7.79% |
160.820 |
173.343 |
0.004 |
-0.00% |
0.004 |
|
MultiSource/Applications/lambda-0.1.3/lambda
Profile
|
7.78% |
14.738 |
15.885 |
0.005 |
-0.10% |
0.005 |
|
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/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint8_t>/127
|
7.76% |
128.911 |
138.917 |
0.005 |
0.00% |
0.005 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_DEL_DOT_VEC_2D_RAW/0
|
7.71% |
1667.062 |
1795.511 |
6.904 |
-0.30% |
6.904 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint8_t_To_uint32_t_
|
7.62% |
11865.966 |
12769.759 |
12.108 |
-0.07% |
12.108 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC7
|
7.60% |
65.707 |
70.702 |
0.006 |
-0.02% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint16_t_To_uint64_t_
|
7.59% |
18821.457 |
20249.111 |
82.278 |
-0.16% |
82.278 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_DEL_DOT_VEC_2D_LAMBDA/0
|
7.57% |
1672.940 |
1799.566 |
3.127 |
0.07% |
3.127 |
|
SingleSource/Benchmarks/Misc/pi
Profile
|
7.55% |
1.657 |
1.783 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC7
|
7.53% |
330.050 |
354.892 |
3.174 |
0.05% |
3.174 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint16_t_To_uint64_t_
|
7.49% |
23285.744 |
25029.536 |
58.618 |
-0.04% |
58.618 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC15
|
7.39% |
50.690 |
54.436 |
0.004 |
-0.01% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC63
|
7.24% |
69.462 |
74.491 |
0.109 |
0.17% |
0.109 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC31
|
7.20% |
69.467 |
74.471 |
0.003 |
-0.00% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC15
|
7.04% |
42.089 |
45.052 |
0.003 |
0.00% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC63
|
6.99% |
107.035 |
114.515 |
0.004 |
0.00% |
0.004 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_xor_runtime_checks_pass<16, int>
|
6.97% |
26.907 |
28.783 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_xor_runtime_checks_fail<16, int>
|
6.97% |
26.909 |
28.784 |
0.001 |
0.01% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIND_FIRST_MIN_RAW/5001
|
6.85% |
42.520 |
45.433 |
0.122 |
0.10% |
0.122 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC128
|
6.77% |
64.462 |
68.829 |
0.002 |
-0.01% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC15
|
6.77% |
36.922 |
39.421 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint16_t>/127
|
6.73% |
130.160 |
138.914 |
0.007 |
0.00% |
0.007 |
|
SingleSource/Benchmarks/Misc/flops-6
Profile
|
6.71% |
1.229 |
1.312 |
0.001 |
-0.06% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC127
|
6.70% |
64.457 |
68.774 |
0.028 |
-0.07% |
0.028 |
|
SingleSource/Benchmarks/Misc-C++/Large/sphereflake
Profile
|
6.57% |
18.775 |
20.009 |
0.006 |
-0.02% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC16
|
6.56% |
38.172 |
40.675 |
0.003 |
-0.00% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC127
|
6.50% |
182.709 |
194.593 |
0.012 |
-0.01% |
0.012 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_only_autovec_int32_t_
|
6.31% |
170202.977 |
180945.148 |
538.273 |
-0.10% |
538.273 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint8_t>/65
|
6.29% |
89.489 |
95.116 |
0.004 |
-0.00% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint32_t>/127
|
6.22% |
130.169 |
138.270 |
0.005 |
-0.01% |
0.005 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_HYDRO_2D_LAMBDA/171
|
6.21% |
83.412 |
88.592 |
0.517 |
-0.07% |
0.517 |
|
MultiSource/Benchmarks/MiBench/telecomm-gsm/telecomm-gsm
Profile
|
6.15% |
0.625 |
0.663 |
0.000 |
-0.03% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC16
|
5.99% |
31.288 |
33.161 |
0.002 |
-0.01% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC32
|
5.96% |
41.927 |
44.427 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC32
|
5.96% |
41.928 |
44.426 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC31
|
5.90% |
42.553 |
45.063 |
0.010 |
-0.00% |
0.010 |
|
External/SPEC/CFP2017rate/538.imagick_r/538.imagick_r
Profile
|
5.89% |
275.993 |
292.250 |
0.260 |
0.06% |
0.260 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC31
|
5.87% |
42.552 |
45.051 |
0.004 |
-0.00% |
0.004 |
|
MultiSource/Benchmarks/SciMark2-C/scimark2
Profile
|
5.79% |
101.812 |
107.710 |
0.035 |
0.02% |
0.035 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint8_t_To_uint16_t_
|
5.73% |
3434.756 |
3631.707 |
6.082 |
-0.05% |
6.082 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint32_t_To_uint64_t_
|
5.68% |
20319.821 |
21474.887 |
145.784 |
0.11% |
145.784 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint32_t>/999
|
5.60% |
659.554 |
696.472 |
0.042 |
-0.01% |
0.042 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC7
|
5.60% |
66.963 |
70.710 |
0.002 |
-0.01% |
0.002 |
|
MultiSource/Benchmarks/Rodinia/hotspot/hotspot
Profile
|
5.57% |
1.928 |
2.036 |
0.008 |
0.00% |
0.008 |
|
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% |
1293.818 |
1365.046 |
0.098 |
0.00% |
0.098 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC31
|
5.40% |
23.154 |
24.404 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC32
|
5.40% |
23.154 |
24.404 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC31
|
5.40% |
23.154 |
24.403 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC32
|
5.39% |
23.155 |
24.403 |
0.001 |
0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC32
|
5.37% |
58.197 |
61.324 |
0.005 |
0.00% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC15
|
5.36% |
121.711 |
128.237 |
0.020 |
-0.01% |
0.020 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_BAND_LIN_EQ_LAMBDA/5001
|
5.35% |
20.243 |
21.327 |
0.137 |
1.22% |
0.137 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIRST_DIFF_LAMBDA/5001
|
5.35% |
12.210 |
12.864 |
0.160 |
-0.00% |
0.160 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIND_FIRST_MIN_RAW/44217
|
5.28% |
369.628 |
389.160 |
0.387 |
-0.11% |
0.387 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC31
|
5.24% |
229.216 |
241.217 |
0.036 |
-0.01% |
0.036 |
|
SingleSource/Benchmarks/Misc/oourafft
Profile
|
5.14% |
14.631 |
15.383 |
0.033 |
0.91% |
0.033 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint32_t>/256
|
5.03% |
346.715 |
364.171 |
0.029 |
0.00% |
0.029 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C++/miniFE/miniFE
Profile
|
4.99% |
15.065 |
15.817 |
0.073 |
-0.95% |
0.073 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_HYDRO_2D_RAW/171
|
4.94% |
83.266 |
87.381 |
0.524 |
-1.41% |
0.524 |
|
SingleSource/Benchmarks/Misc/revertBits
Profile
|
4.90% |
0.611 |
0.641 |
0.000 |
-0.00% |
0.000 |
|
SingleSource/Benchmarks/Polybench/stencils/jacobi-2d/jacobi-2d
Profile
|
4.85% |
30.653 |
32.140 |
0.071 |
-0.26% |
0.071 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC127
|
4.82% |
2295.284 |
2405.892 |
17.436 |
-0.85% |
17.436 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_runtime_checks_pass<16, int>
|
4.82% |
51.937 |
54.437 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_runtime_checks_fail<16, int>
|
4.81% |
51.939 |
54.438 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint16_t>/65
|
4.81% |
90.747 |
95.109 |
0.012 |
-0.01% |
0.012 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC31
|
4.66% |
66.964 |
70.086 |
0.002 |
0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopWithReductionTC2
|
4.66% |
13.153 |
13.767 |
0.001 |
-0.00% |
0.001 |
|
MultiSource/Benchmarks/TSVC/NodeSplitting-dbl/NodeSplitting-dbl
Profile
|
4.62% |
26.901 |
28.145 |
0.364 |
-0.46% |
0.364 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC1
|
4.55% |
13.767 |
14.393 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC16
|
4.55% |
13.767 |
14.393 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC2
|
4.54% |
13.767 |
14.392 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC4
|
4.54% |
13.766 |
14.392 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC8
|
4.54% |
13.767 |
14.392 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC3
|
4.54% |
13.768 |
14.393 |
0.000 |
0.01% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC4
|
4.54% |
13.767 |
14.392 |
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:benchAutoVecForLoopTC1
|
4.54% |
13.769 |
14.394 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC3
|
4.54% |
13.767 |
14.391 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC2
|
4.54% |
13.767 |
14.392 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC15
|
4.53% |
13.768 |
14.392 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC15
|
4.53% |
13.767 |
14.391 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC7
|
4.53% |
13.768 |
14.391 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC8
|
4.52% |
13.769 |
14.392 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint64_t>/999
|
4.43% |
1734.336 |
1811.115 |
0.146 |
-0.01% |
0.146 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_BAND_LIN_EQ_RAW/5001
|
4.37% |
20.398 |
21.289 |
0.306 |
0.81% |
0.306 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_ENERGY_CALC_LAMBDA/171
|
4.35% |
13.619 |
14.211 |
0.005 |
-0.26% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint64_t>/999
|
4.32% |
3446.813 |
3595.609 |
0.158 |
0.02% |
0.158 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_PIC_2D_RAW/171
|
4.29% |
12.966 |
13.523 |
0.060 |
-0.12% |
0.060 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_PIC_2D_LAMBDA/171
|
4.29% |
12.905 |
13.458 |
0.057 |
-0.29% |
0.057 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint64_t>/256
|
4.25% |
897.394 |
935.520 |
0.060 |
-0.01% |
0.060 |
|
SingleSource/Benchmarks/Misc/flops-5
Profile
|
4.24% |
1.939 |
2.021 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_PRESSURE_CALC_RAW/44217
|
4.23% |
483.335 |
503.775 |
1.557 |
-0.05% |
1.557 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_nested_cond_load_novec_int32_t_
|
4.21% |
623484.192 |
649717.237 |
335.211 |
0.58% |
335.211 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC31
|
4.20% |
59.453 |
61.948 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC16
|
4.17% |
30.040 |
31.292 |
0.289 |
0.01% |
0.289 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_only_autovec_uint8_t_
|
4.12% |
92353.371 |
96160.599 |
27.378 |
-0.00% |
27.378 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint32_t>/65
|
4.12% |
90.744 |
94.480 |
0.008 |
-0.01% |
0.008 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC32
|
4.11% |
60.703 |
63.199 |
0.003 |
0.00% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint32_t>/256
|
4.10% |
212.779 |
221.504 |
0.009 |
0.00% |
0.009 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_ENERGY_CALC_RAW/171
|
4.01% |
13.648 |
14.195 |
0.009 |
-0.32% |
0.009 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC3
|
3.99% |
15.644 |
16.268 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint8_t_To_uint64_t_
|
3.86% |
22589.749 |
23461.938 |
54.145 |
-0.09% |
54.145 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint64_t_To_uint32_t_
|
3.84% |
18684.265 |
19400.843 |
8.691 |
-0.02% |
8.691 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<31, EqZero, First>
|
3.81% |
3223.385 |
3346.058 |
0.238 |
-0.01% |
0.238 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint64_t>/256
|
3.75% |
495.737 |
514.340 |
0.054 |
-0.01% |
0.054 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC64
|
3.73% |
66.960 |
69.459 |
0.002 |
0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC64
|
3.73% |
66.963 |
69.457 |
0.007 |
-0.01% |
0.007 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC63
|
3.69% |
67.598 |
70.096 |
0.003 |
-0.01% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC63
|
3.69% |
67.587 |
70.081 |
0.001 |
-0.00% |
0.001 |
|
SingleSource/Benchmarks/BenchmarkGame/n-body
Profile
|
3.68% |
2.634 |
2.731 |
0.000 |
26.20% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC63
|
3.66% |
41.654 |
43.177 |
0.291 |
-0.27% |
0.291 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC31
|
3.56% |
58.196 |
60.266 |
0.094 |
-0.02% |
0.094 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint16_t_To_uint8_t_
|
3.46% |
2777.140 |
2873.206 |
4.124 |
-0.17% |
4.124 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC64
|
3.46% |
41.734 |
43.177 |
0.294 |
0.00% |
0.294 |
|
External/SPEC/CFP2017rate/544.nab_r/544.nab_r
Profile
|
3.44% |
460.466 |
476.310 |
0.017 |
-0.33% |
0.017 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_PRESSURE_CALC_LAMBDA/44217
|
3.38% |
487.912 |
504.391 |
3.607 |
0.04% |
3.607 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<32, EqZero, Last>
|
3.37% |
6815.452 |
7045.217 |
14.002 |
-0.11% |
14.002 |
|
MultiSource/Benchmarks/nbench/nbench
Profile
|
3.33% |
5.907 |
6.104 |
0.003 |
-0.38% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint16_t>/999
|
3.26% |
498.735 |
515.004 |
0.024 |
-0.00% |
0.024 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1BigLoopWithReductionTC1
|
3.22% |
19.401 |
20.025 |
0.003 |
0.00% |
0.003 |
|
MultiSource/Benchmarks/McCat/12-IOtest/iotest
Profile
|
3.19% |
1.752 |
1.808 |
0.016 |
-0.90% |
0.016 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchVecWithRuntimeChecks4PointersDBeforeA/1000
|
3.17% |
4866096.042 |
5020489.187 |
175.523 |
-0.00% |
175.523 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint32_t_To_uint16_t_
|
3.15% |
9544.489 |
9844.897 |
15.773 |
-0.35% |
15.773 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint16_t_To_uint8_t_
|
3.11% |
4378.426 |
4514.789 |
2.731 |
-0.05% |
2.731 |
|
SingleSource/Benchmarks/Shootout/Shootout-lists
Profile
|
3.10% |
10.976 |
11.316 |
0.001 |
0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC31
|
3.06% |
91.054 |
93.839 |
0.013 |
-0.02% |
0.013 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC31
|
2.95% |
886.148 |
912.284 |
1.526 |
-0.51% |
1.526 |
|
MultiSource/Benchmarks/sim/sim
Profile
|
2.92% |
9.424 |
9.699 |
0.037 |
-0.02% |
0.037 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint16_t>/999
|
2.90% |
985.122 |
1013.664 |
0.083 |
-0.02% |
0.083 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC64
|
2.90% |
108.260 |
111.395 |
0.003 |
-0.01% |
0.003 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, LessThanZero, None>
|
2.85% |
36558.154 |
37600.000 |
31.120 |
0.06% |
31.120 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC1
|
2.84% |
21.905 |
22.528 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC1
|
2.84% |
21.904 |
22.526 |
0.002 |
0.00% |
0.002 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<31, GreaterThanZero, Last>
|
2.71% |
8112.027 |
8332.004 |
22.328 |
-0.39% |
22.328 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<64, EqZero, Mid>
|
2.67% |
2690.711 |
2762.641 |
9.936 |
0.25% |
9.936 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC63
|
2.66% |
117.035 |
120.150 |
0.004 |
0.00% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC16
|
2.66% |
14.020 |
14.392 |
0.000 |
-0.00% |
0.000 |
|
MultiSource/Benchmarks/FreeBench/mason/mason
Profile
|
2.63% |
0.538 |
0.553 |
0.000 |
-0.07% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC32
|
2.63% |
30.483 |
31.285 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint8_t>/10
|
2.58% |
47.581 |
48.807 |
0.015 |
5.16% |
0.015 |
|
SingleSource/Benchmarks/Misc-C++/oopack_v1p8
Profile
|
2.55% |
0.468 |
0.479 |
0.000 |
-7.59% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint8_t_To_uint32_t_
|
2.55% |
6902.034 |
7077.887 |
0.332 |
-0.01% |
0.332 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchVecWithRuntimeChecks4PointersDBeforeA/32
|
2.49% |
162142.305 |
166180.390 |
14.151 |
-0.01% |
14.151 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_only_autovec_int64_t_
|
2.47% |
1414576.176 |
1449564.263 |
294.539 |
-0.01% |
294.539 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C/CoMD/CoMD
Profile
|
2.42% |
9.663 |
9.898 |
0.007 |
-0.01% |
0.007 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC63
|
2.39% |
104.515 |
107.012 |
0.002 |
0.00% |
0.002 |
|
External/SPEC/CFP2017rate/519.lbm_r/519.lbm_r
Profile
|
2.38% |
195.142 |
199.780 |
1.761 |
-0.45% |
1.761 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC32
|
2.37% |
48.896 |
50.053 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC64
|
2.36% |
105.762 |
108.260 |
0.004 |
-0.00% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC15
|
2.30% |
43.808 |
44.813 |
0.075 |
0.66% |
0.075 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_EOS_RAW/5001
|
2.22% |
29.639 |
30.297 |
0.118 |
0.34% |
0.118 |
|
SingleSource/Benchmarks/Misc/flops-1
Profile
|
2.22% |
8.807 |
9.002 |
0.000 |
0.01% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC128
|
2.13% |
117.028 |
119.520 |
0.003 |
0.00% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC127
|
2.12% |
117.652 |
120.151 |
0.000 |
-0.00% |
0.000 |
|
SingleSource/Benchmarks/Misc-C++/Large/ray
Profile
|
2.12% |
11.852 |
12.104 |
0.001 |
0.02% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC127
|
2.12% |
117.654 |
120.143 |
0.007 |
-0.00% |
0.007 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC128
|
2.11% |
117.049 |
119.517 |
0.002 |
-0.01% |
0.002 |
|
MultiSource/Benchmarks/FreeBench/fourinarow/fourinarow
Profile
|
2.08% |
0.637 |
0.650 |
0.000 |
-0.02% |
0.000 |
|
SingleSource/Benchmarks/BenchmarkGame/puzzle
Profile
|
2.05% |
0.858 |
0.876 |
0.002 |
0.10% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint64_t_To_uint8_t_
|
2.01% |
19402.007 |
19792.953 |
26.815 |
-0.24% |
26.815 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint32_t_To_uint64_t_
|
1.97% |
25848.044 |
26356.228 |
38.318 |
-0.00% |
38.318 |
|
SingleSource/Benchmarks/Shootout/Shootout-matrix
Profile
|
1.92% |
3.791 |
3.864 |
0.000 |
0.01% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_ENERGY_CALC_LAMBDA/5001
|
1.92% |
429.799 |
438.037 |
2.837 |
-0.00% |
2.837 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_EOS_RAW/171
|
1.91% |
0.856 |
0.873 |
0.002 |
-0.02% |
0.002 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_FLOYD_DITHER/128
|
1.89% |
429.931 |
438.059 |
0.604 |
-0.32% |
0.604 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint16_t>/256
|
1.87% |
267.845 |
272.853 |
0.016 |
-0.00% |
0.016 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC31
|
1.86% |
30.509 |
31.075 |
0.078 |
-0.37% |
0.078 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint32_t>/10
|
1.82% |
46.315 |
47.158 |
0.082 |
1.83% |
0.082 |
|
MultiSource/Benchmarks/Rodinia/pathfinder/pathfinder
Profile
|
1.82% |
1.242 |
1.265 |
0.006 |
0.55% |
0.006 |
|
MultiSource/Applications/JM/lencod/lencod
Profile
|
1.71% |
32.179 |
32.730 |
0.033 |
0.50% |
0.033 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint64_t>/51
|
1.71% |
145.813 |
148.302 |
0.009 |
-0.00% |
0.009 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_csa_with_cond_arith_novec_int64_t_
|
1.67% |
736437.079 |
748737.167 |
3009.969 |
-0.27% |
3009.969 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint16_t_To_uint32_t_
|
1.61% |
11074.855 |
11252.894 |
66.995 |
-0.79% |
66.995 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_FLOYD_DITHER/512
|
1.60% |
6546.570 |
6651.214 |
5.738 |
-0.08% |
5.738 |
|
MultiSource/Benchmarks/VersaBench/ecbdes/ecbdes
Profile
|
1.60% |
5.061 |
5.141 |
0.000 |
0.02% |
0.000 |
|
SingleSource/Benchmarks/Misc/mandel-2
Profile
|
1.58% |
2.496 |
2.536 |
0.000 |
0.02% |
0.000 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<3, GreaterThanZero, None>
|
1.58% |
44528.517 |
45231.984 |
79.924 |
-0.01% |
79.924 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_csa_with_in_loop_arith_novec_int64_t_
|
1.58% |
1013118.896 |
1029077.753 |
180.278 |
-0.03% |
180.278 |
|
MultiSource/Benchmarks/Olden/health/health
Profile
|
1.57% |
1.569 |
1.593 |
0.002 |
0.02% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_nested_cond_load_novec_uint8_t_
|
1.55% |
496811.685 |
504533.926 |
166.752 |
-0.04% |
166.752 |
|
MultiSource/Benchmarks/mafft/pairlocalalign
Profile
|
1.52% |
92.603 |
94.007 |
0.287 |
-0.06% |
0.287 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC128
|
1.51% |
208.390 |
211.528 |
0.005 |
0.01% |
0.005 |
|
MultiSource/Benchmarks/ASC_Sequoia/AMGmk/AMGmk
Profile
|
1.50% |
32.865 |
33.360 |
0.029 |
0.64% |
0.029 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_EOS_LAMBDA/171
|
1.49% |
0.858 |
0.871 |
0.003 |
0.01% |
0.003 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_INT_PREDICT_RAW/171
|
1.47% |
6.817 |
6.918 |
0.003 |
-0.10% |
0.003 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<64, EqZero, None>
|
1.45% |
2900.642 |
2942.820 |
10.422 |
-0.01% |
10.422 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<16, GreaterThanZero, First>
|
1.41% |
8494.283 |
8614.006 |
17.527 |
0.02% |
17.527 |
|
MicroBenchmarks/LCALS/SubsetBRawLoops/lcalsBRaw.test:BM_INIT3_RAW/44217
|
1.36% |
393.215 |
398.577 |
1.657 |
0.28% |
1.657 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<64, GreaterThanZero, Mid>
|
1.36% |
2708.579 |
2745.465 |
6.937 |
-0.01% |
6.937 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint64_t>/51
|
1.36% |
225.939 |
229.013 |
0.004 |
0.00% |
0.004 |
|
External/SPEC/CINT2017rate/531.deepsjeng_r/531.deepsjeng_r
Profile
|
1.34% |
256.027 |
259.450 |
0.520 |
-0.25% |
0.520 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC127
|
1.30% |
217.465 |
220.289 |
0.011 |
0.01% |
0.011 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<6, LessThanZero, Mid>
|
1.29% |
23547.096 |
23851.572 |
17.611 |
-0.07% |
17.611 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint32_t>/10
|
1.29% |
57.165 |
57.902 |
0.011 |
0.45% |
0.011 |
|
MultiSource/Benchmarks/MallocBench/cfrac/cfrac
Profile
|
1.28% |
2.746 |
2.781 |
0.001 |
0.04% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC127
|
1.27% |
194.635 |
197.115 |
0.002 |
0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC128
|
1.27% |
195.871 |
198.364 |
0.005 |
-0.00% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint8_t>/16
|
1.24% |
59.307 |
60.042 |
0.009 |
11.56% |
0.009 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, LessThanZero, Mid>
|
1.21% |
55876.921 |
56553.954 |
23.520 |
-0.00% |
23.520 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_INT_PREDICT_LAMBDA/171
|
1.21% |
6.842 |
6.925 |
0.008 |
-0.00% |
0.008 |
|
SingleSource/Benchmarks/SmallPT/smallpt
Profile
|
1.13% |
29.711 |
30.046 |
0.001 |
0.04% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_sinhf_novec_float_
|
1.12% |
2218.467 |
2243.408 |
0.043 |
0.00% |
0.043 |
|
External/SPEC/CFP2017rate/511.povray_r/511.povray_r
Profile
|
1.12% |
33.583 |
33.959 |
0.042 |
0.45% |
0.042 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_csa_with_cond_arith_autovec_int64_t_
|
1.11% |
737807.733 |
746010.126 |
318.710 |
-0.12% |
318.710 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<64, LessThanZero, Last>
|
1.09% |
4140.236 |
4185.499 |
6.978 |
-0.12% |
6.978 |
|
External/SPEC/CINT2017rate/525.x264_r/525.x264_r
Profile
|
1.08% |
128.209 |
129.590 |
0.186 |
-0.02% |
0.186 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<6, GreaterThanZero, None>
|
1.03% |
29416.572 |
29719.635 |
7.938 |
0.02% |
7.938 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_sinhf_autovec_float_
|
1.03% |
2219.026 |
2241.792 |
0.277 |
-0.04% |
0.277 |
|
MicroBenchmarks/Builtins/Int128/Builtins.test:BM_RemainderIntrinsic128UniformDivisor<__int128_t>
|
1.03% |
66.441 |
67.122 |
0.075 |
-0.12% |
0.075 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_sinh_novec_double_
|
1.02% |
2447.555 |
2472.486 |
0.412 |
-0.06% |
0.412 |
|
MultiSource/Benchmarks/Fhourstones-3.1/fhourstones3.1
Profile
|
1.01% |
3.935 |
3.975 |
0.010 |
0.09% |
0.010 |