|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint64_t_To_uint32_t_
|
105.60% |
17148.938 |
35258.087 |
141.328 |
-0.16% |
141.328 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint64_t_To_uint16_t_
|
101.89% |
17698.796 |
35732.071 |
98.680 |
0.10% |
98.680 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint64_t_To_uint8_t_
|
98.60% |
18697.679 |
37133.200 |
35.218 |
0.19% |
35.218 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C/miniGMG/miniGMG
Profile
|
92.22% |
4.692 |
9.018 |
0.230 |
-1.87% |
0.230 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint16_t_To_uint64_t_
|
78.65% |
10453.891 |
18675.590 |
23.670 |
0.00% |
23.670 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint8_t_To_uint64_t_
|
68.98% |
10536.782 |
17804.967 |
246.594 |
0.03% |
246.594 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint64_t_To_uint32_t_
|
68.33% |
22677.703 |
38173.052 |
93.161 |
0.05% |
93.161 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_DIFF_PREDICT_RAW/44217
|
64.40% |
14179.422 |
23310.586 |
1336.931 |
0.05% |
1336.931 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_DIFF_PREDICT_LAMBDA/44217
|
63.40% |
14179.051 |
23168.660 |
1304.180 |
0.29% |
1304.180 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_DIFF_PREDICT_LAMBDA/5001
|
62.84% |
1576.657 |
2567.447 |
98.063 |
-0.29% |
98.063 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_DIFF_PREDICT_RAW/5001
|
62.33% |
1566.439 |
2542.843 |
193.797 |
-1.24% |
193.797 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/32
|
57.83% |
884.528 |
1396.046 |
0.107 |
-0.01% |
0.107 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/64
|
57.72% |
3919.213 |
6181.532 |
5.052 |
-0.01% |
5.052 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/16
|
57.55% |
177.389 |
279.476 |
0.008 |
0.00% |
0.008 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/256
|
56.35% |
68515.712 |
107126.613 |
11.758 |
-0.02% |
11.758 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/128
|
56.27% |
16807.633 |
26265.667 |
7.745 |
-0.02% |
7.745 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint64_t_To_uint8_t_
|
53.11% |
19816.714 |
30342.151 |
73.876 |
0.11% |
73.876 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint64_t_To_uint16_t_
|
51.01% |
19164.663 |
28940.330 |
489.305 |
-0.03% |
489.305 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint64_t_To_uint16_t_
|
39.17% |
18618.317 |
25910.521 |
19.351 |
0.05% |
19.351 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint32_t_To_uint64_t_
|
39.00% |
16338.378 |
22710.834 |
323.516 |
-0.06% |
323.516 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint32_t_To_uint8_t_
|
37.89% |
9806.138 |
13521.953 |
8.425 |
0.34% |
8.425 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC128
|
37.47% |
406.289 |
558.532 |
0.164 |
-0.02% |
0.164 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIRST_DIFF_LAMBDA/44217
|
36.84% |
103.542 |
141.692 |
11.189 |
-2.16% |
11.189 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC128
|
36.35% |
947.215 |
1291.540 |
3.391 |
-0.10% |
3.391 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC64
|
35.09% |
216.277 |
292.159 |
0.047 |
-0.02% |
0.047 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC64
|
35.04% |
483.971 |
653.575 |
0.848 |
-0.01% |
0.848 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint8_t>/51
|
34.82% |
91.901 |
123.900 |
0.001 |
33.94% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC32
|
34.81% |
247.747 |
333.985 |
0.775 |
0.02% |
0.775 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC16
|
34.50% |
129.232 |
173.823 |
0.244 |
0.02% |
0.244 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint64_t_To_uint8_t_
|
32.73% |
20532.685 |
27252.584 |
7.143 |
0.06% |
7.143 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC32
|
31.56% |
120.787 |
158.914 |
0.009 |
0.02% |
0.009 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC128
|
30.39% |
463.199 |
603.947 |
2.154 |
-0.00% |
2.154 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC128
|
30.37% |
463.246 |
603.926 |
0.017 |
-0.01% |
0.017 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC64
|
29.11% |
242.813 |
313.503 |
0.024 |
-0.00% |
0.024 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC64
|
29.11% |
242.822 |
313.502 |
0.013 |
-0.00% |
0.013 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint16_t_To_uint64_t_
|
28.73% |
10366.562 |
13344.600 |
24.039 |
0.57% |
24.039 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC127
|
28.16% |
480.077 |
615.252 |
0.034 |
-0.00% |
0.034 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC127
|
28.14% |
480.091 |
615.199 |
0.031 |
0.00% |
0.031 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint8_t_To_uint32_t_
|
27.48% |
5172.194 |
6593.450 |
113.476 |
0.12% |
113.476 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint16_t_To_uint32_t_
|
27.48% |
5576.848 |
7109.294 |
25.761 |
-0.03% |
25.761 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_only_autovec_uint8_t_
|
27.12% |
143512.345 |
182434.985 |
94.331 |
0.03% |
94.331 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC32
|
26.88% |
132.671 |
168.330 |
0.002 |
0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC32
|
26.88% |
132.667 |
168.321 |
0.014 |
-0.01% |
0.014 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC16
|
26.01% |
73.225 |
92.268 |
0.038 |
-0.01% |
0.038 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint8_t>/51
|
25.54% |
152.671 |
191.664 |
1.871 |
24.09% |
1.871 |
|
MultiSource/Benchmarks/Trimaran/enc-pc1/enc-pc1
Profile
|
25.14% |
0.882 |
1.104 |
0.000 |
0.01% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC127
|
25.12% |
220.075 |
275.351 |
1.352 |
-0.04% |
1.352 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC63
|
25.05% |
259.707 |
324.754 |
0.028 |
-0.01% |
0.028 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC63
|
25.04% |
259.711 |
324.745 |
0.025 |
-0.01% |
0.025 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC127
|
24.36% |
515.380 |
640.952 |
0.145 |
-0.03% |
0.145 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint16_t_To_uint8_t_
|
23.62% |
3089.023 |
3818.635 |
1.281 |
0.00% |
1.281 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC128
|
23.43% |
221.367 |
273.228 |
1.333 |
-0.55% |
1.333 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC16
|
23.38% |
77.594 |
95.735 |
0.005 |
-0.00% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC16
|
23.38% |
77.600 |
95.739 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint8_t>/28
|
23.35% |
66.956 |
82.590 |
0.108 |
22.19% |
0.108 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, EqZero, None>
|
23.07% |
16667.400 |
20512.026 |
0.845 |
0.00% |
0.845 |
|
SingleSource/Benchmarks/Adobe-C++/loop_unroll
Profile
|
23.00% |
2.427 |
2.985 |
0.001 |
-3.93% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC8
|
22.85% |
47.874 |
58.814 |
0.004 |
-0.01% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint32_t_To_uint16_t_
|
22.79% |
11248.552 |
13812.197 |
2.101 |
0.04% |
2.101 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint64_t_To_uint32_t_
|
22.61% |
22104.937 |
27103.568 |
15.993 |
0.05% |
15.993 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC16
|
22.58% |
76.061 |
93.233 |
0.004 |
-0.00% |
0.004 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, EqZero, Last>
|
22.20% |
11540.857 |
14103.004 |
0.666 |
-0.01% |
0.666 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC32
|
21.99% |
132.340 |
161.442 |
0.003 |
0.00% |
0.003 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIRST_SUM_RAW/44217
|
21.86% |
137.101 |
167.065 |
6.744 |
0.44% |
6.744 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_with_cond_arith_novec_uint8_t_
|
21.74% |
612808.192 |
746046.456 |
525.417 |
0.02% |
525.417 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint32_t_To_uint8_t_
|
21.68% |
11429.840 |
13908.099 |
29.255 |
0.04% |
29.255 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC64
|
21.56% |
245.018 |
297.847 |
0.023 |
-0.01% |
0.023 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC128
|
21.25% |
470.691 |
570.717 |
0.042 |
-0.01% |
0.042 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC4
|
21.14% |
14.463 |
17.520 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_with_cond_arith_novec_int32_t_
|
20.59% |
614273.628 |
740722.146 |
195.282 |
-0.04% |
195.282 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC31
|
20.08% |
149.555 |
179.587 |
0.005 |
0.00% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC31
|
20.05% |
149.586 |
179.580 |
0.005 |
-0.00% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC8
|
19.91% |
19.307 |
23.151 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIRST_SUM_LAMBDA/44217
|
19.79% |
137.228 |
164.383 |
6.263 |
-1.62% |
6.263 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC64
|
19.73% |
126.472 |
151.425 |
0.338 |
1.07% |
0.338 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_HYDRO_1D_RAW/171
|
19.61% |
0.372 |
0.445 |
0.001 |
-0.26% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint8_t>/28
|
19.20% |
100.861 |
120.222 |
0.875 |
16.61% |
0.875 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_HYDRO_1D_LAMBDA/171
|
18.92% |
0.372 |
0.442 |
0.002 |
0.05% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC8
|
18.74% |
20.024 |
23.777 |
0.004 |
-0.01% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC8
|
18.74% |
50.061 |
59.442 |
0.004 |
-0.01% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC8
|
18.74% |
50.061 |
59.440 |
0.005 |
-0.02% |
0.005 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, EqZero, None>
|
18.60% |
13510.598 |
16023.253 |
3.158 |
-0.00% |
3.158 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint16_t_To_uint32_t_
|
18.55% |
6294.830 |
7462.499 |
0.895 |
0.00% |
0.895 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_VOL3D_CALC_LAMBDA/2
|
18.31% |
7.402 |
8.757 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_VOL3D_CALC_RAW/2
|
18.31% |
7.401 |
8.756 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_no_runtime_checks_needed<16, int>
|
18.17% |
20.650 |
24.403 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, EqZero, Last>
|
18.16% |
14106.304 |
16667.371 |
0.779 |
0.00% |
0.779 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, EqZero, Mid>
|
18.14% |
14105.773 |
16665.207 |
1.211 |
-0.01% |
1.211 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, EqZero, First>
|
18.14% |
14110.172 |
16670.209 |
1.050 |
-0.00% |
1.050 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint64_t_To_uint8_t_
|
18.14% |
18734.514 |
22132.708 |
28.237 |
-0.18% |
28.237 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint8_t_To_uint64_t_
|
18.00% |
10981.289 |
12957.811 |
432.277 |
-0.82% |
432.277 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC127
|
17.53% |
515.450 |
605.795 |
0.025 |
0.00% |
0.025 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC63
|
17.40% |
129.637 |
152.193 |
0.934 |
0.64% |
0.934 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint32_t_To_uint8_t_
|
17.20% |
9073.668 |
10634.551 |
22.666 |
-0.02% |
22.666 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC128
|
17.19% |
941.491 |
1103.374 |
0.020 |
0.00% |
0.020 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC64
|
17.04% |
480.650 |
562.559 |
0.036 |
-0.01% |
0.036 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC127
|
16.98% |
936.467 |
1095.482 |
0.033 |
0.02% |
0.033 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/32
|
16.80% |
404.928 |
472.955 |
0.020 |
-0.01% |
0.020 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/64
|
16.75% |
1638.306 |
1912.642 |
6.339 |
-0.04% |
6.339 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC32
|
16.74% |
250.315 |
292.219 |
0.013 |
0.00% |
0.013 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC63
|
16.58% |
475.632 |
554.486 |
2.041 |
-0.05% |
2.041 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/256
|
16.57% |
26961.833 |
31430.130 |
35.328 |
-0.06% |
35.328 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/16
|
16.54% |
99.076 |
115.467 |
0.011 |
-0.00% |
0.011 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/128
|
16.43% |
6799.779 |
7916.817 |
4.447 |
-0.01% |
4.447 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint8_t_To_uint16_t_
|
16.31% |
3229.556 |
3756.362 |
0.637 |
-0.00% |
0.637 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC16
|
16.19% |
135.171 |
157.056 |
0.003 |
0.00% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint32_t_To_uint16_t_
|
16.18% |
11021.960 |
12805.435 |
45.775 |
-0.25% |
45.775 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_with_cond_arith_novec_int64_t_
|
16.11% |
682541.663 |
792482.106 |
1613.608 |
0.25% |
1613.608 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC2
|
16.08% |
44.742 |
51.937 |
0.001 |
0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC1
|
16.08% |
44.740 |
51.935 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC7
|
16.08% |
44.741 |
51.935 |
0.004 |
0.00% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC4
|
16.08% |
44.739 |
51.932 |
0.006 |
-0.00% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC8
|
16.08% |
44.741 |
51.934 |
0.004 |
-0.01% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC3
|
16.07% |
44.742 |
51.931 |
0.003 |
-0.01% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC16
|
16.06% |
28.573 |
33.164 |
0.002 |
0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC7
|
15.95% |
23.923 |
27.738 |
0.342 |
-3.22% |
0.342 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC31
|
15.82% |
245.299 |
284.093 |
0.019 |
-0.00% |
0.019 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, EqZero, First>
|
15.76% |
12183.291 |
14102.979 |
1.183 |
-0.00% |
1.183 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_with_cond_arith_autovec_int64_t_
|
15.71% |
684155.890 |
791619.617 |
1253.225 |
0.00% |
1253.225 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_VOL3D_CALC_LAMBDA/0
|
15.62% |
1098.150 |
1269.693 |
0.638 |
0.10% |
0.638 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, EqZero, Mid>
|
15.51% |
12209.847 |
14103.450 |
1.226 |
0.00% |
1.226 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_VOL3D_CALC_RAW/0
|
15.50% |
1098.162 |
1268.389 |
0.118 |
-0.20% |
0.118 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC8
|
15.30% |
77.607 |
89.480 |
0.005 |
-0.00% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC63
|
15.27% |
324.799 |
374.394 |
0.187 |
-0.01% |
0.187 |
|
External/SPEC/CFP2017rate/508.namd_r/508.namd_r
Profile
|
15.15% |
194.363 |
223.815 |
0.401 |
-0.10% |
0.401 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC128
|
15.03% |
70.715 |
81.345 |
0.002 |
0.00% |
0.002 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_VOL3D_CALC_RAW/1
|
15.01% |
226.322 |
260.295 |
0.158 |
-0.00% |
0.158 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_VOL3D_CALC_LAMBDA/1
|
14.98% |
226.307 |
260.197 |
0.090 |
0.01% |
0.090 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC15
|
14.97% |
38.796 |
44.605 |
0.083 |
0.19% |
0.083 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint8_t_To_uint16_t_
|
14.86% |
3953.911 |
4541.559 |
0.337 |
-0.01% |
0.337 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC63
|
14.76% |
290.074 |
332.895 |
0.008 |
-0.00% |
0.008 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC31
|
14.76% |
76.339 |
87.604 |
0.002 |
0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC15
|
14.42% |
130.162 |
148.934 |
0.052 |
-0.00% |
0.052 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint32_t_To_uint8_t_
|
14.24% |
9695.333 |
11075.581 |
20.628 |
-0.48% |
20.628 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint16_t_To_uint8_t_
|
14.16% |
4154.694 |
4743.171 |
0.754 |
0.00% |
0.754 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC4
|
14.10% |
48.810 |
55.691 |
0.001 |
-0.01% |
0.001 |
|
SingleSource/Benchmarks/Shootout-C++/Shootout-C++-matrix
Profile
|
14.00% |
2.201 |
2.509 |
0.000 |
-0.00% |
0.000 |
|
MultiSource/Benchmarks/MiBench/security-rijndael/security-rijndael
Profile
|
13.88% |
0.294 |
0.335 |
0.001 |
0.05% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC4
|
13.79% |
36.293 |
41.297 |
0.002 |
-0.01% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC4
|
13.78% |
36.295 |
41.298 |
0.003 |
-0.00% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC2
|
13.32% |
18.773 |
21.273 |
0.002 |
-0.01% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC15
|
13.24% |
94.498 |
107.008 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC15
|
13.23% |
94.493 |
106.993 |
0.008 |
-0.02% |
0.008 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC2
|
12.96% |
33.791 |
38.170 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC16
|
12.92% |
45.993 |
51.934 |
0.004 |
-0.02% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC15
|
12.90% |
45.999 |
51.932 |
0.003 |
-0.01% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint64_t_To_uint16_t_
|
12.82% |
16766.222 |
18914.990 |
145.131 |
-0.36% |
145.131 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC32
|
12.65% |
76.338 |
85.992 |
0.422 |
0.54% |
0.422 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint8_t>/16
|
12.59% |
53.201 |
59.896 |
0.101 |
11.29% |
0.101 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC4
|
12.50% |
20.024 |
22.527 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC3
|
12.49% |
20.025 |
22.526 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC4
|
12.48% |
20.025 |
22.524 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint8_t>/16
|
12.46% |
73.350 |
82.488 |
0.709 |
9.18% |
0.709 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC32
|
12.08% |
47.451 |
53.185 |
0.006 |
-0.02% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC7
|
12.06% |
72.589 |
81.342 |
0.010 |
-0.02% |
0.010 |
|
MicroBenchmarks/ImageProcessing/Blur/blur.test:BENCHMARK_boxBlurKernel/1024
|
11.78% |
26889.421 |
30056.859 |
81.814 |
-0.31% |
81.814 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC4
|
11.75% |
21.277 |
23.776 |
0.002 |
-0.01% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC4
|
11.74% |
100.806 |
112.639 |
1.206 |
-0.40% |
1.206 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC64
|
11.68% |
48.185 |
53.812 |
0.003 |
-0.01% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC16
|
11.54% |
32.538 |
36.293 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_BAND_LIN_EQ_RAW/171
|
11.44% |
0.344 |
0.384 |
0.000 |
4.77% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_BAND_LIN_EQ_LAMBDA/171
|
11.43% |
0.344 |
0.384 |
0.000 |
4.77% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_BAND_LIN_EQ_RAW/44217
|
11.36% |
136.294 |
151.780 |
2.493 |
-2.53% |
2.493 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC127
|
10.93% |
91.991 |
102.044 |
0.067 |
0.16% |
0.067 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC8
|
10.80% |
23.154 |
25.654 |
0.002 |
-0.01% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC8
|
10.80% |
23.153 |
25.653 |
0.002 |
-0.01% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC31
|
10.75% |
177.408 |
196.475 |
0.010 |
0.00% |
0.010 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_only_autovec_int64_t_
|
10.52% |
301597.035 |
333314.027 |
432.563 |
0.01% |
432.563 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC7
|
10.52% |
23.781 |
26.281 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC7
|
10.50% |
23.781 |
26.280 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint8_t>/999
|
10.39% |
288.505 |
318.492 |
1.161 |
9.51% |
1.161 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_DEL_DOT_VEC_2D_RAW/1
|
10.12% |
260.764 |
287.154 |
0.096 |
0.03% |
0.096 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_DEL_DOT_VEC_2D_LAMBDA/1
|
10.05% |
260.903 |
287.130 |
0.114 |
0.00% |
0.114 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint8_t>/51
|
10.03% |
126.402 |
139.077 |
0.590 |
18.21% |
0.590 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint8_t_To_uint16_t_
|
9.89% |
5324.379 |
5851.144 |
7.874 |
0.01% |
7.874 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC7
|
9.73% |
25.660 |
28.156 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC64
|
9.66% |
85.026 |
93.236 |
0.007 |
-0.01% |
0.007 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_DEL_DOT_VEC_2D_LAMBDA/2
|
9.53% |
3.205 |
3.510 |
0.000 |
-0.00% |
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/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_runtime_checks_pass<4, int>
|
9.36% |
15.333 |
16.768 |
0.044 |
-0.05% |
0.044 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC8
|
9.28% |
26.909 |
29.407 |
0.002 |
-0.01% |
0.002 |
|
MultiSource/Benchmarks/FreeBench/pifft/pifft
Profile
|
9.08% |
0.329 |
0.358 |
0.002 |
-0.04% |
0.002 |
|
SingleSource/Benchmarks/Misc/salsa20
Profile
|
8.78% |
14.145 |
15.387 |
0.000 |
0.01% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC3
|
8.56% |
43.804 |
47.554 |
0.026 |
-0.01% |
0.026 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC16
|
8.50% |
29.411 |
31.910 |
0.002 |
-0.01% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC16
|
8.49% |
29.413 |
31.911 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC32
|
8.46% |
36.921 |
40.046 |
0.003 |
-0.01% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC16
|
8.46% |
29.410 |
31.899 |
0.006 |
-0.02% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC3
|
8.33% |
15.018 |
16.269 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC15
|
8.32% |
30.037 |
32.537 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC15
|
8.32% |
30.037 |
32.536 |
0.002 |
-0.01% |
0.002 |
|
MultiSource/Benchmarks/VersaBench/beamformer/beamformer
Profile
|
8.26% |
4.806 |
5.202 |
0.001 |
0.00% |
0.001 |
|
MultiSource/Benchmarks/Trimaran/enc-md5/enc-md5
Profile
|
8.26% |
3.239 |
3.507 |
0.001 |
0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC128
|
8.22% |
160.158 |
173.328 |
0.006 |
-0.00% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint8_t>/10
|
8.16% |
59.586 |
64.449 |
0.753 |
4.40% |
0.753 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint8_t_To_uint32_t_
|
8.13% |
11834.177 |
12796.004 |
35.576 |
0.08% |
35.576 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint16_t>/28
|
8.09% |
113.320 |
122.489 |
0.124 |
0.70% |
0.124 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint16_t_To_uint8_t_
|
8.02% |
6310.959 |
6816.970 |
1.392 |
0.02% |
1.392 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_xor_no_runtime_checks_needed<16, int>
|
7.98% |
15.645 |
16.894 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC127
|
7.85% |
63.830 |
68.841 |
0.003 |
0.01% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC128
|
7.80% |
63.847 |
68.829 |
0.003 |
-0.01% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint8_t>/127
|
7.77% |
128.905 |
138.919 |
0.003 |
-0.00% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint8_t>/28
|
7.73% |
85.104 |
91.686 |
0.372 |
11.83% |
0.372 |
|
SingleSource/Benchmarks/Misc/pi
Profile
|
7.52% |
1.658 |
1.782 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC15
|
7.44% |
41.931 |
45.052 |
0.006 |
0.00% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC15
|
7.40% |
50.688 |
54.439 |
0.005 |
-0.00% |
0.005 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_DEL_DOT_VEC_2D_RAW/0
|
7.38% |
1672.632 |
1796.006 |
5.937 |
-0.27% |
5.937 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint16_t_To_uint64_t_
|
7.36% |
23338.080 |
25055.548 |
31.972 |
0.06% |
31.972 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC31
|
7.20% |
69.463 |
74.463 |
0.004 |
-0.00% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC63
|
7.00% |
107.011 |
114.502 |
0.009 |
-0.01% |
0.009 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint16_t_To_uint64_t_
|
6.98% |
18884.337 |
20203.007 |
68.488 |
0.29% |
68.488 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC7
|
6.89% |
30.441 |
32.539 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC63
|
6.78% |
69.464 |
74.173 |
0.187 |
-0.07% |
0.187 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC15
|
6.77% |
36.920 |
39.418 |
0.003 |
-0.01% |
0.003 |
|
SingleSource/Benchmarks/Misc/flops-6
Profile
|
6.76% |
1.229 |
1.312 |
0.001 |
-0.05% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint16_t>/127
|
6.71% |
130.173 |
138.903 |
0.007 |
-0.01% |
0.007 |
|
External/SPEC/CFP2017rate/538.imagick_r/538.imagick_r
Profile
|
6.65% |
274.707 |
292.967 |
0.398 |
-0.10% |
0.398 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_HYDRO_2D_LAMBDA/171
|
6.60% |
82.913 |
88.387 |
0.223 |
-0.31% |
0.223 |
|
SingleSource/Benchmarks/Misc-C++/Large/sphereflake
Profile
|
6.57% |
18.777 |
20.011 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC16
|
6.55% |
38.171 |
40.672 |
0.002 |
-0.01% |
0.002 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_DIFF_PREDICT_RAW/171
|
6.41% |
11.243 |
11.963 |
0.184 |
0.25% |
0.184 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC127
|
6.39% |
182.919 |
194.609 |
0.013 |
0.00% |
0.013 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_DEL_DOT_VEC_2D_LAMBDA/0
|
6.29% |
1691.555 |
1797.873 |
7.433 |
-0.02% |
7.433 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint16_t>/16
|
6.29% |
79.494 |
84.490 |
0.319 |
0.41% |
0.319 |
|
MultiSource/Benchmarks/MiBench/telecomm-gsm/telecomm-gsm
Profile
|
6.28% |
0.623 |
0.662 |
0.001 |
-0.15% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint8_t>/65
|
6.28% |
89.485 |
95.107 |
0.017 |
-0.00% |
0.017 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint32_t>/127
|
6.24% |
130.155 |
138.277 |
0.002 |
-0.01% |
0.002 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_HYDRO_2D_RAW/171
|
6.17% |
83.344 |
88.482 |
0.370 |
-0.16% |
0.370 |
|
SingleSource/Benchmarks/Misc/oourafft
Profile
|
6.08% |
14.470 |
15.350 |
0.076 |
0.70% |
0.076 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_DIFF_PREDICT_LAMBDA/171
|
6.05% |
11.194 |
11.872 |
0.222 |
-0.95% |
0.222 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC16
|
6.00% |
31.287 |
33.164 |
0.001 |
0.00% |
0.001 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C++/miniFE/miniFE
Profile
|
5.99% |
14.915 |
15.809 |
0.072 |
-1.00% |
0.072 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint16_t>/51
|
5.97% |
103.364 |
109.538 |
0.315 |
0.03% |
0.315 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC32
|
5.97% |
41.925 |
44.427 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC32
|
5.96% |
41.927 |
44.426 |
0.002 |
-0.01% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC15
|
5.94% |
121.085 |
128.273 |
0.005 |
-0.00% |
0.005 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_HYDRO_2D_RAW/44217
|
5.93% |
87097.421 |
92261.635 |
1922.090 |
-2.62% |
1922.090 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC31
|
5.89% |
42.553 |
45.060 |
0.006 |
-0.01% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC31
|
5.87% |
42.550 |
45.050 |
0.002 |
-0.01% |
0.002 |
|
MultiSource/Benchmarks/SciMark2-C/scimark2
Profile
|
5.87% |
101.754 |
107.729 |
0.066 |
0.03% |
0.066 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint32_t>/999
|
5.85% |
1289.580 |
1365.021 |
0.078 |
-0.00% |
0.078 |
|
MultiSource/Benchmarks/Rodinia/hotspot/hotspot
Profile
|
5.75% |
1.925 |
2.035 |
0.003 |
-0.03% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint32_t>/999
|
5.69% |
658.998 |
696.473 |
0.077 |
-0.01% |
0.077 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_only_autovec_int32_t_
|
5.63% |
171862.809 |
181537.330 |
287.016 |
0.02% |
287.016 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC7
|
5.61% |
66.957 |
70.710 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC7
|
5.59% |
66.964 |
70.706 |
0.001 |
-0.02% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint8_t>/10
|
5.58% |
46.226 |
48.805 |
0.012 |
5.16% |
0.012 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint32_t_To_uint64_t_
|
5.52% |
20264.715 |
21382.956 |
143.501 |
-0.32% |
143.501 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC32
|
5.40% |
23.153 |
24.403 |
0.000 |
-0.01% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC32
|
5.39% |
23.155 |
24.403 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC31
|
5.38% |
23.155 |
24.401 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC31
|
5.35% |
23.163 |
24.402 |
0.002 |
-0.01% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC8
|
5.25% |
25.656 |
27.003 |
0.173 |
-0.09% |
0.173 |
|
MultiSource/Applications/lambda-0.1.3/lambda
Profile
|
5.15% |
15.098 |
15.874 |
0.013 |
0.03% |
0.013 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint32_t>/256
|
5.04% |
346.690 |
364.157 |
0.008 |
-0.00% |
0.008 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint16_t>/10
|
5.03% |
62.577 |
65.725 |
0.139 |
0.29% |
0.139 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC31
|
5.02% |
229.676 |
241.213 |
0.082 |
-0.01% |
0.082 |
|
SingleSource/Benchmarks/Misc/revertBits
Profile
|
4.90% |
0.611 |
0.641 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint16_t>/65
|
4.81% |
90.741 |
95.104 |
0.007 |
-0.01% |
0.007 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_runtime_checks_pass<16, int>
|
4.81% |
51.943 |
54.441 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_runtime_checks_fail<16, int>
|
4.80% |
51.944 |
54.436 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC31
|
4.66% |
66.958 |
70.079 |
0.005 |
-0.01% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC64
|
4.55% |
41.299 |
43.176 |
0.294 |
0.00% |
0.294 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC2
|
4.54% |
13.766 |
14.392 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC15
|
4.54% |
13.767 |
14.392 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC2
|
4.54% |
13.767 |
14.392 |
0.000 |
-0.01% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC8
|
4.54% |
13.767 |
14.392 |
0.000 |
-0.01% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC63
|
4.54% |
41.302 |
43.176 |
0.295 |
-0.27% |
0.295 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC3
|
4.54% |
13.766 |
14.391 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC16
|
4.54% |
13.767 |
14.392 |
0.000 |
-0.01% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC16
|
4.54% |
13.766 |
14.391 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC3
|
4.54% |
13.767 |
14.392 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC7
|
4.54% |
13.767 |
14.392 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC1
|
4.54% |
13.767 |
14.392 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC4
|
4.53% |
13.767 |
14.391 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC8
|
4.53% |
13.767 |
14.391 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC1
|
4.53% |
13.769 |
14.393 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC4
|
4.53% |
13.769 |
14.392 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC15
|
4.53% |
13.768 |
14.392 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC7
|
4.52% |
13.769 |
14.392 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint64_t>/999
|
4.44% |
3442.293 |
3595.209 |
0.233 |
0.01% |
0.233 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_PIC_2D_LAMBDA/171
|
4.44% |
12.898 |
13.471 |
0.053 |
-0.20% |
0.053 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint8_t_To_uint64_t_
|
4.42% |
22517.532 |
23513.306 |
14.789 |
0.02% |
14.789 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint64_t>/999
|
4.41% |
1734.480 |
1811.052 |
0.356 |
-0.01% |
0.356 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint32_t_To_uint16_t_
|
4.38% |
9460.434 |
9874.950 |
16.066 |
-0.05% |
16.066 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_PIC_2D_RAW/171
|
4.33% |
12.967 |
13.529 |
0.047 |
-0.08% |
0.047 |
|
SingleSource/Benchmarks/Misc/flops-5
Profile
|
4.29% |
1.939 |
2.022 |
0.000 |
-0.02% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC31
|
4.20% |
59.446 |
61.943 |
0.003 |
-0.00% |
0.003 |
|
MultiSource/Benchmarks/McCat/12-IOtest/iotest
Profile
|
4.19% |
1.746 |
1.820 |
0.012 |
-0.29% |
0.012 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint64_t>/256
|
4.19% |
897.838 |
935.464 |
0.045 |
-0.01% |
0.045 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC32
|
4.16% |
58.871 |
61.320 |
0.006 |
-0.00% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC31
|
4.16% |
90.111 |
93.856 |
0.003 |
0.00% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_only_autovec_uint8_t_
|
4.14% |
92348.779 |
96169.575 |
3.877 |
0.01% |
3.877 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC31
|
4.13% |
30.036 |
31.275 |
0.003 |
-0.04% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint32_t>/65
|
4.13% |
90.736 |
94.479 |
0.003 |
-0.01% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC32
|
4.11% |
60.700 |
63.197 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint32_t>/256
|
4.11% |
212.758 |
221.505 |
0.005 |
0.00% |
0.005 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_ENERGY_CALC_LAMBDA/171
|
4.06% |
13.664 |
14.219 |
0.009 |
-0.20% |
0.009 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_ENERGY_CALC_RAW/171
|
4.04% |
13.651 |
14.203 |
0.026 |
-0.26% |
0.026 |
|
SingleSource/Benchmarks/Polybench/stencils/jacobi-2d/jacobi-2d
Profile
|
3.97% |
30.742 |
31.962 |
0.241 |
-0.81% |
0.241 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_only_novec_uint8_t_
|
3.95% |
404341.180 |
420317.465 |
49.485 |
6.17% |
49.485 |
|
MultiSource/Benchmarks/VersaBench/ecbdes/ecbdes
Profile
|
3.93% |
4.947 |
5.141 |
0.000 |
0.01% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_cond_load_autovec_int64_t_
|
3.82% |
532402.417 |
552754.962 |
638.333 |
0.02% |
638.333 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC32
|
3.81% |
30.035 |
31.180 |
0.051 |
-0.34% |
0.051 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<31, EqZero, First>
|
3.81% |
3223.224 |
3345.965 |
0.307 |
-0.01% |
0.307 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC127
|
3.80% |
2296.889 |
2384.250 |
28.632 |
-1.75% |
28.632 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint64_t>/256
|
3.77% |
495.638 |
514.339 |
0.041 |
-0.01% |
0.041 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint64_t_To_uint8_t_
|
3.76% |
19038.240 |
19754.775 |
59.126 |
-0.44% |
59.126 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC64
|
3.74% |
66.956 |
69.457 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC64
|
3.73% |
66.961 |
69.457 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint8_t_To_uint16_t_
|
3.72% |
3500.050 |
3630.128 |
0.396 |
-0.09% |
0.396 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC63
|
3.70% |
67.582 |
70.081 |
0.005 |
-0.00% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC63
|
3.69% |
67.583 |
70.079 |
0.008 |
-0.02% |
0.008 |
|
SingleSource/Benchmarks/BenchmarkGame/n-body
Profile
|
3.68% |
2.634 |
2.731 |
0.000 |
26.20% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint64_t_To_uint32_t_
|
3.67% |
18685.726 |
19371.070 |
51.506 |
-0.18% |
51.506 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_runtime_checks_fail<4, int>
|
3.63% |
15.331 |
15.888 |
0.142 |
-0.13% |
0.142 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_BAND_LIN_EQ_LAMBDA/5001
|
3.61% |
20.482 |
21.222 |
0.209 |
0.72% |
0.209 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint16_t>/999
|
3.56% |
978.918 |
1013.747 |
0.111 |
-0.01% |
0.111 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC32
|
3.39% |
48.183 |
49.814 |
0.112 |
-0.47% |
0.112 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_BAND_LIN_EQ_RAW/5001
|
3.32% |
20.695 |
21.383 |
0.047 |
-0.47% |
0.047 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC31
|
3.31% |
58.199 |
60.124 |
0.114 |
-0.25% |
0.114 |
|
External/SPEC/CFP2017rate/544.nab_r/544.nab_r
Profile
|
3.30% |
460.935 |
476.161 |
0.248 |
-0.36% |
0.248 |
|
SingleSource/Benchmarks/Shootout/Shootout-lists
Profile
|
3.29% |
10.955 |
11.315 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint16_t>/999
|
3.25% |
498.743 |
514.969 |
0.017 |
-0.01% |
0.017 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1BigLoopWithReductionTC1
|
3.21% |
19.400 |
20.023 |
0.003 |
-0.01% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint16_t_To_uint32_t_
|
3.18% |
10967.246 |
11315.708 |
34.675 |
-0.24% |
34.675 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchVecWithRuntimeChecks4PointersDBeforeA/1000
|
3.16% |
4866336.215 |
5020016.763 |
495.891 |
0.00% |
495.891 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_acosf_novec_float_
|
2.91% |
820.929 |
844.856 |
0.055 |
0.01% |
0.055 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_acosf_autovec_float_
|
2.89% |
821.018 |
844.746 |
0.136 |
-0.00% |
0.136 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC1
|
2.85% |
21.901 |
22.526 |
0.000 |
-0.00% |
0.000 |
|
MultiSource/Benchmarks/BitBench/drop3/drop3
Profile
|
2.83% |
0.711 |
0.732 |
0.000 |
0.01% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC1
|
2.81% |
21.908 |
22.524 |
0.001 |
-0.01% |
0.001 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C/CoMD/CoMD
Profile
|
2.69% |
9.641 |
9.901 |
0.007 |
-0.02% |
0.007 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC63
|
2.67% |
117.021 |
120.147 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint8_t_To_uint32_t_
|
2.55% |
6901.629 |
7077.510 |
0.244 |
0.00% |
0.244 |
|
SingleSource/Benchmarks/Misc-C++/oopack_v1p8
Profile
|
2.55% |
0.468 |
0.480 |
0.000 |
-7.54% |
0.000 |
|
MultiSource/Applications/JM/lencod/lencod
Profile
|
2.52% |
31.898 |
32.702 |
0.043 |
0.41% |
0.043 |
|
SingleSource/Benchmarks/Misc/ReedSolomon
Profile
|
2.49% |
20.314 |
20.820 |
0.001 |
0.09% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint16_t_To_uint8_t_
|
2.47% |
2807.751 |
2877.192 |
0.989 |
-0.04% |
0.989 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint32_t>/10
|
2.45% |
56.441 |
57.826 |
0.055 |
0.32% |
0.055 |
|
MultiSource/Benchmarks/Ptrdist/yacr2/yacr2
Profile
|
2.45% |
2.026 |
2.076 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC63
|
2.39% |
104.502 |
107.001 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_PRESSURE_CALC_LAMBDA/44217
|
2.36% |
483.653 |
495.070 |
3.048 |
-0.70% |
3.048 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_PRESSURE_CALC_RAW/44217
|
2.35% |
491.150 |
502.692 |
0.373 |
0.10% |
0.373 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint16_t>/16
|
2.35% |
52.576 |
53.810 |
0.002 |
0.54% |
0.002 |
|
SingleSource/Benchmarks/Misc-C++/Large/ray
Profile
|
2.29% |
11.831 |
12.102 |
0.002 |
-0.00% |
0.002 |
|
SingleSource/Benchmarks/Shootout/Shootout-matrix
Profile
|
2.27% |
3.777 |
3.863 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchVecWithRuntimeChecks4PointersDBeforeA/32
|
2.25% |
162540.603 |
166195.957 |
1.989 |
-0.00% |
1.989 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint16_t>/10
|
2.24% |
45.193 |
46.206 |
0.004 |
0.79% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint64_t>/51
|
2.23% |
224.018 |
229.012 |
0.005 |
0.00% |
0.005 |
|
SingleSource/Benchmarks/Misc/flops-1
Profile
|
2.21% |
8.807 |
9.002 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC64
|
2.18% |
109.001 |
111.373 |
0.006 |
-0.01% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC128
|
2.13% |
117.026 |
119.521 |
0.005 |
-0.00% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC128
|
2.13% |
117.025 |
119.513 |
0.005 |
-0.01% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC127
|
2.12% |
117.645 |
120.142 |
0.004 |
-0.00% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC127
|
2.12% |
117.660 |
120.149 |
0.007 |
0.00% |
0.007 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC2
|
2.11% |
13.141 |
13.418 |
0.045 |
1.98% |
0.045 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<31, GreaterThanZero, Last>
|
2.00% |
8149.968 |
8313.199 |
36.456 |
0.21% |
36.456 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC63
|
1.95% |
127.662 |
130.154 |
0.006 |
-0.01% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint16_t_To_uint8_t_
|
1.94% |
4429.870 |
4515.676 |
8.630 |
-0.03% |
8.630 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<16, EqZero, None>
|
1.93% |
8021.674 |
8176.687 |
0.506 |
-0.01% |
0.506 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint16_t>/256
|
1.84% |
267.877 |
272.810 |
0.009 |
-0.01% |
0.009 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_EOS_LAMBDA/171
|
1.84% |
0.857 |
0.873 |
0.002 |
0.03% |
0.002 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<16, EqZero, Mid>
|
1.84% |
8501.490 |
8657.497 |
13.992 |
0.00% |
13.992 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_ENERGY_CALC_RAW/5001
|
1.80% |
427.496 |
435.170 |
2.019 |
1.50% |
2.019 |
|
MultiSource/Benchmarks/mafft/pairlocalalign
Profile
|
1.79% |
92.468 |
94.121 |
0.237 |
0.05% |
0.237 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_INT_PREDICT_RAW/171
|
1.78% |
6.803 |
6.925 |
0.007 |
0.00% |
0.007 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint64_t>/51
|
1.71% |
145.802 |
148.289 |
0.005 |
-0.01% |
0.005 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_EOS_RAW/171
|
1.68% |
0.856 |
0.871 |
0.003 |
-0.01% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint32_t_To_uint64_t_
|
1.67% |
25943.732 |
26377.172 |
32.261 |
0.08% |
32.261 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_ENERGY_CALC_LAMBDA/44217
|
1.65% |
4262.749 |
4332.876 |
24.450 |
0.17% |
24.450 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_erf_novec_double_
|
1.64% |
874.880 |
889.221 |
0.679 |
-0.01% |
0.679 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_erf_autovec_double_
|
1.63% |
875.165 |
889.473 |
0.536 |
0.04% |
0.536 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<32, EqZero, Last>
|
1.59% |
6941.080 |
7051.399 |
6.909 |
-0.02% |
6.909 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_csa_with_in_loop_arith_novec_int64_t_
|
1.56% |
1012990.227 |
1028839.589 |
324.980 |
-0.06% |
324.980 |
|
SingleSource/Benchmarks/Misc/mandel-2
Profile
|
1.56% |
2.496 |
2.535 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_FLOYD_DITHER/512
|
1.47% |
6551.752 |
6648.065 |
8.555 |
0.04% |
8.555 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint16_t_To_uint32_t_
|
1.47% |
13365.498 |
13561.384 |
19.697 |
0.27% |
19.697 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_FLOYD_DITHER/128
|
1.38% |
432.962 |
438.957 |
0.684 |
-0.12% |
0.684 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint32_t>/28
|
1.34% |
71.492 |
72.453 |
0.050 |
0.28% |
0.050 |
|
External/SPEC/CFP2017rate/511.povray_r/511.povray_r
Profile
|
1.34% |
33.446 |
33.894 |
0.045 |
0.25% |
0.045 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_csa_with_cond_arith_autovec_int64_t_
|
1.32% |
735512.153 |
745249.864 |
875.535 |
0.04% |
875.535 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_ADI_LAMBDA/44217
|
1.32% |
19334.921 |
19590.043 |
96.491 |
-0.45% |
96.491 |
|
External/SPEC/CINT2017rate/525.x264_r/525.x264_r
Profile
|
1.31% |
128.142 |
129.815 |
0.109 |
0.16% |
0.109 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<32, GreaterThanZero, Mid>
|
1.30% |
4495.111 |
4553.599 |
14.237 |
-0.04% |
14.237 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, LessThanZero, None>
|
1.29% |
37153.707 |
37631.621 |
42.888 |
-0.08% |
42.888 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC128
|
1.27% |
195.859 |
198.354 |
0.008 |
-0.01% |
0.008 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC127
|
1.27% |
194.627 |
197.093 |
0.022 |
-0.00% |
0.022 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<6, LessThanZero, Mid>
|
1.26% |
23486.878 |
23782.312 |
39.138 |
-0.11% |
39.138 |
|
MultiSource/Benchmarks/MallocBench/cfrac/cfrac
Profile
|
1.23% |
2.745 |
2.778 |
0.000 |
-0.06% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_INT_PREDICT_LAMBDA/171
|
1.22% |
6.833 |
6.916 |
0.011 |
-0.13% |
0.011 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<8, LessThanZero, Mid>
|
1.21% |
19230.780 |
19463.419 |
27.143 |
0.15% |
27.143 |
|
MultiSource/Benchmarks/nbench/nbench
Profile
|
1.16% |
6.037 |
6.107 |
0.003 |
-0.32% |
0.003 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<7, EqZero, None>
|
1.16% |
26875.358 |
27186.773 |
14.664 |
0.02% |
14.664 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_nested_cond_load_novec_int32_t_
|
1.09% |
642702.280 |
649699.795 |
556.760 |
0.57% |
556.760 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint32_t>/51
|
1.07% |
117.013 |
118.259 |
0.004 |
-0.00% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_nested_cond_load_novec_uint8_t_
|
1.06% |
499041.933 |
504309.345 |
438.199 |
-0.08% |
438.199 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint8_t>/16
|
1.03% |
91.995 |
92.941 |
0.275 |
3.12% |
0.275 |