|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_INT_PREDICT_RAW/44217
|
135.85% |
8212.090 |
19368.084 |
95.740 |
0.23% |
95.740 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_INT_PREDICT_RAW/5001
|
106.49% |
925.626 |
1911.292 |
42.174 |
-5.48% |
42.174 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint64_t_To_uint32_t_
|
105.89% |
17148.938 |
35307.898 |
126.382 |
-0.02% |
126.382 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint64_t_To_uint16_t_
|
101.68% |
17698.796 |
35695.721 |
164.957 |
0.00% |
164.957 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint64_t_To_uint8_t_
|
99.04% |
18697.679 |
37215.602 |
254.394 |
0.41% |
254.394 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C/miniGMG/miniGMG
Profile
|
87.09% |
4.692 |
8.778 |
0.185 |
-4.49% |
0.185 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint16_t_To_uint64_t_
|
78.40% |
10453.891 |
18649.315 |
1195.063 |
-0.14% |
1195.063 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIRST_DIFF_RAW/44217
|
71.45% |
104.205 |
178.657 |
3.286 |
-0.58% |
3.286 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint8_t_To_uint64_t_
|
69.00% |
10536.782 |
17806.694 |
322.705 |
0.04% |
322.705 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_DIFF_PREDICT_RAW/44217
|
68.36% |
14179.422 |
23872.342 |
991.911 |
-2.18% |
991.911 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint64_t_To_uint32_t_
|
68.14% |
22677.703 |
38129.750 |
49.805 |
-0.07% |
49.805 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_DIFF_PREDICT_LAMBDA/44217
|
62.76% |
14179.051 |
23078.260 |
1397.853 |
-0.11% |
1397.853 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_DIFF_PREDICT_LAMBDA/5001
|
61.57% |
1576.657 |
2547.371 |
144.812 |
-1.07% |
144.812 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_DIFF_PREDICT_RAW/5001
|
59.44% |
1566.439 |
2497.565 |
142.073 |
-3.00% |
142.073 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/32
|
57.85% |
884.528 |
1396.241 |
0.057 |
-0.00% |
0.057 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/64
|
57.72% |
3919.213 |
6181.324 |
1.471 |
-0.02% |
1.471 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/16
|
57.53% |
177.389 |
279.444 |
0.045 |
-0.01% |
0.045 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/256
|
56.35% |
68515.712 |
107126.821 |
6.102 |
-0.02% |
6.102 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/128
|
56.28% |
16807.633 |
26266.383 |
3.103 |
-0.02% |
3.103 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint64_t_To_uint8_t_
|
53.60% |
19816.714 |
30438.739 |
426.483 |
0.43% |
426.483 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint64_t_To_uint16_t_
|
51.18% |
19164.663 |
28973.989 |
42.269 |
0.09% |
42.269 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint64_t_To_uint16_t_
|
39.11% |
18618.317 |
25899.026 |
6.032 |
0.01% |
6.032 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint32_t_To_uint64_t_
|
39.00% |
16338.378 |
22711.118 |
146.221 |
-0.06% |
146.221 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint32_t_To_uint8_t_
|
37.53% |
9806.138 |
13486.475 |
15.595 |
0.07% |
15.595 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC128
|
37.24% |
406.289 |
557.593 |
0.710 |
0.01% |
0.710 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC128
|
36.42% |
947.215 |
1292.192 |
5.394 |
-0.05% |
5.394 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC64
|
35.27% |
483.971 |
654.646 |
3.313 |
0.16% |
3.313 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC32
|
35.08% |
247.747 |
334.658 |
1.029 |
-0.10% |
1.029 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC64
|
35.05% |
216.277 |
292.080 |
0.034 |
-0.05% |
0.034 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint8_t>/51
|
34.81% |
91.901 |
123.895 |
0.090 |
33.93% |
0.090 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC16
|
34.48% |
129.232 |
173.790 |
0.696 |
0.00% |
0.696 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint64_t_To_uint8_t_
|
32.63% |
20532.685 |
27231.885 |
76.033 |
-0.02% |
76.033 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIRST_SUM_RAW/44217
|
32.29% |
137.101 |
181.375 |
0.613 |
-3.06% |
0.613 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC32
|
31.37% |
120.787 |
158.674 |
0.113 |
-0.13% |
0.113 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC128
|
30.40% |
463.199 |
603.990 |
0.012 |
-0.00% |
0.012 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC128
|
30.38% |
463.246 |
603.986 |
0.032 |
-0.00% |
0.032 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint16_t_To_uint64_t_
|
29.58% |
10366.562 |
13432.521 |
124.561 |
1.23% |
124.561 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC64
|
29.12% |
242.813 |
313.522 |
0.017 |
-0.00% |
0.017 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC64
|
29.10% |
242.822 |
313.494 |
0.022 |
-0.00% |
0.022 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC127
|
28.15% |
480.077 |
615.228 |
0.044 |
0.00% |
0.044 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC127
|
28.15% |
480.091 |
615.244 |
0.060 |
-0.00% |
0.060 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint8_t_To_uint32_t_
|
27.62% |
5172.194 |
6600.504 |
45.794 |
-0.13% |
45.794 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint16_t_To_uint32_t_
|
27.39% |
5576.848 |
7104.179 |
85.715 |
0.05% |
85.715 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_only_autovec_uint8_t_
|
27.07% |
143512.345 |
182362.554 |
152.260 |
0.01% |
152.260 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC32
|
26.88% |
132.667 |
168.327 |
0.008 |
-0.00% |
0.008 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC32
|
26.87% |
132.671 |
168.319 |
0.016 |
-0.00% |
0.016 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC16
|
26.01% |
73.225 |
92.272 |
0.029 |
-0.01% |
0.029 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint8_t>/51
|
25.92% |
152.671 |
192.247 |
1.448 |
24.47% |
1.448 |
|
MultiSource/Benchmarks/Trimaran/enc-pc1/enc-pc1
Profile
|
25.19% |
0.882 |
1.105 |
0.000 |
0.02% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC63
|
25.08% |
259.711 |
324.838 |
0.008 |
0.00% |
0.008 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC63
|
25.05% |
259.707 |
324.768 |
0.026 |
-0.01% |
0.026 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC127
|
24.81% |
220.075 |
274.680 |
0.475 |
-0.28% |
0.475 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC127
|
24.31% |
515.380 |
640.673 |
0.244 |
0.03% |
0.244 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIRST_SUM_LAMBDA/44217
|
24.14% |
137.228 |
170.353 |
7.408 |
1.95% |
7.408 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC128
|
23.96% |
221.367 |
274.408 |
0.814 |
-0.12% |
0.814 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint16_t_To_uint8_t_
|
23.56% |
3089.023 |
3816.916 |
0.846 |
-0.03% |
0.846 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC16
|
23.38% |
77.594 |
95.737 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC16
|
23.37% |
77.600 |
95.736 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, EqZero, None>
|
23.06% |
16667.400 |
20511.133 |
0.686 |
-0.00% |
0.686 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint8_t>/28
|
23.01% |
66.956 |
82.360 |
0.112 |
21.85% |
0.112 |
|
SingleSource/Benchmarks/Adobe-C++/loop_unroll
Profile
|
22.86% |
2.427 |
2.981 |
0.002 |
-4.04% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC8
|
22.82% |
47.874 |
58.799 |
0.013 |
-0.03% |
0.013 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint32_t_To_uint16_t_
|
22.66% |
11248.552 |
13798.013 |
7.483 |
-0.07% |
7.483 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint64_t_To_uint32_t_
|
22.64% |
22104.937 |
27110.034 |
11.193 |
0.08% |
11.193 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_PIC_2D_RAW/5001
|
22.62% |
978.477 |
1199.796 |
29.993 |
0.98% |
29.993 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, EqZero, Last>
|
22.20% |
11540.857 |
14103.116 |
0.811 |
-0.01% |
0.811 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC16
|
22.00% |
76.061 |
92.792 |
0.210 |
-0.36% |
0.210 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC32
|
21.92% |
132.340 |
161.354 |
0.045 |
-0.03% |
0.045 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_with_cond_arith_novec_uint8_t_
|
21.72% |
612808.192 |
745884.095 |
615.624 |
0.00% |
615.624 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint32_t_To_uint8_t_
|
21.59% |
11429.840 |
13897.420 |
27.941 |
-0.02% |
27.941 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC64
|
21.57% |
245.018 |
297.874 |
0.006 |
0.00% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC128
|
21.26% |
470.691 |
570.759 |
0.029 |
-0.01% |
0.029 |
|
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_
|
20.62% |
614273.628 |
740955.732 |
219.768 |
-0.01% |
219.768 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC31
|
20.09% |
149.555 |
179.600 |
0.004 |
-0.01% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC31
|
20.05% |
149.586 |
179.584 |
0.005 |
0.00% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC8
|
19.91% |
19.307 |
23.150 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint8_t_To_uint64_t_
|
19.77% |
10981.289 |
13151.896 |
776.995 |
0.66% |
776.995 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_HYDRO_1D_RAW/171
|
19.37% |
0.372 |
0.444 |
0.000 |
0.12% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_HYDRO_1D_LAMBDA/171
|
19.19% |
0.372 |
0.443 |
0.001 |
0.12% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint8_t>/28
|
19.08% |
100.861 |
120.106 |
1.070 |
16.50% |
1.070 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC8
|
18.74% |
20.024 |
23.777 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC8
|
18.74% |
50.061 |
59.442 |
0.005 |
-0.01% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC8
|
18.73% |
50.061 |
59.439 |
0.004 |
-0.02% |
0.004 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, EqZero, None>
|
18.62% |
13510.598 |
16025.624 |
0.034 |
-0.00% |
0.034 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint16_t_To_uint32_t_
|
18.56% |
6294.830 |
7462.885 |
0.281 |
0.00% |
0.281 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_VOL3D_CALC_RAW/2
|
18.32% |
7.401 |
8.757 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_VOL3D_CALC_LAMBDA/2
|
18.30% |
7.402 |
8.757 |
0.000 |
-0.01% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint64_t_To_uint8_t_
|
18.20% |
18734.514 |
22143.873 |
133.356 |
-0.13% |
133.356 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_no_runtime_checks_needed<16, int>
|
18.18% |
20.650 |
24.403 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, EqZero, Last>
|
18.16% |
14106.304 |
16668.361 |
1.083 |
0.01% |
1.083 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, EqZero, Mid>
|
18.16% |
14105.773 |
16667.187 |
0.471 |
0.01% |
0.471 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, EqZero, First>
|
18.15% |
14110.172 |
16670.718 |
0.595 |
-0.00% |
0.595 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint32_t_To_uint8_t_
|
17.56% |
9073.668 |
10666.891 |
12.494 |
0.23% |
12.494 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC127
|
17.54% |
515.450 |
605.867 |
0.030 |
0.00% |
0.030 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC64
|
17.40% |
126.472 |
148.481 |
1.226 |
-0.10% |
1.226 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC128
|
17.20% |
941.491 |
1103.415 |
0.030 |
0.01% |
0.030 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC64
|
17.04% |
480.650 |
562.545 |
0.035 |
-0.01% |
0.035 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC127
|
16.97% |
936.467 |
1095.401 |
0.374 |
0.01% |
0.374 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/32
|
16.81% |
404.928 |
473.009 |
0.036 |
0.00% |
0.036 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/64
|
16.75% |
1638.306 |
1912.741 |
1.253 |
-0.03% |
1.253 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC32
|
16.72% |
250.315 |
292.172 |
0.033 |
-0.02% |
0.033 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/256
|
16.72% |
26961.833 |
31468.858 |
18.521 |
0.05% |
18.521 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC63
|
16.59% |
475.632 |
554.524 |
0.030 |
-0.04% |
0.030 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/16
|
16.54% |
99.076 |
115.464 |
0.015 |
-0.00% |
0.015 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/128
|
16.51% |
6799.779 |
7922.704 |
1.051 |
-0.00% |
1.051 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint8_t_To_uint16_t_
|
16.32% |
3229.556 |
3756.587 |
0.713 |
0.00% |
0.713 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC16
|
16.16% |
135.171 |
157.018 |
0.022 |
-0.02% |
0.022 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint32_t_To_uint16_t_
|
16.11% |
11021.960 |
12797.698 |
60.727 |
-0.31% |
60.727 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC1
|
16.09% |
44.740 |
51.939 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC4
|
16.09% |
44.739 |
51.936 |
0.002 |
0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_with_cond_arith_novec_int64_t_
|
16.08% |
682541.663 |
792306.243 |
585.158 |
0.22% |
585.158 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC8
|
16.08% |
44.741 |
51.936 |
0.024 |
-0.00% |
0.024 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC2
|
16.08% |
44.742 |
51.936 |
0.003 |
0.00% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC16
|
16.08% |
28.573 |
33.168 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC3
|
16.07% |
44.742 |
51.933 |
0.003 |
-0.00% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC7
|
16.07% |
44.741 |
51.932 |
0.004 |
-0.00% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC31
|
15.81% |
245.299 |
284.074 |
0.026 |
-0.00% |
0.026 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, EqZero, First>
|
15.77% |
12183.291 |
14104.167 |
0.187 |
-0.01% |
0.187 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_VOL3D_CALC_LAMBDA/0
|
15.59% |
1098.150 |
1269.375 |
1.302 |
0.07% |
1.302 |
|
External/SPEC/CFP2017rate/508.namd_r/508.namd_r
Profile
|
15.58% |
194.363 |
224.648 |
0.358 |
0.21% |
0.358 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, EqZero, Mid>
|
15.52% |
12209.847 |
14104.598 |
0.080 |
0.01% |
0.080 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_with_cond_arith_autovec_int64_t_
|
15.49% |
684155.890 |
790159.822 |
1422.131 |
-0.18% |
1422.131 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_VOL3D_CALC_RAW/0
|
15.43% |
1098.162 |
1267.621 |
0.340 |
0.19% |
0.340 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC63
|
15.30% |
324.799 |
374.495 |
0.063 |
0.00% |
0.063 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC15
|
15.16% |
38.796 |
44.678 |
0.085 |
0.35% |
0.085 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC8
|
15.14% |
77.607 |
89.352 |
0.060 |
-0.05% |
0.060 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC128
|
15.03% |
70.715 |
81.342 |
0.004 |
-0.00% |
0.004 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_VOL3D_CALC_LAMBDA/1
|
14.99% |
226.307 |
260.232 |
0.038 |
0.02% |
0.038 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_VOL3D_CALC_RAW/1
|
14.90% |
226.322 |
260.037 |
0.127 |
-0.04% |
0.127 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint8_t_To_uint16_t_
|
14.87% |
3953.911 |
4541.754 |
0.778 |
-0.00% |
0.778 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC63
|
14.77% |
290.074 |
332.927 |
0.005 |
0.01% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC63
|
14.75% |
129.637 |
148.764 |
2.897 |
-0.77% |
2.897 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint8_t>/16
|
14.71% |
73.350 |
84.140 |
0.728 |
11.37% |
0.728 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC7
|
14.55% |
23.923 |
27.405 |
0.688 |
-4.38% |
0.688 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC15
|
14.39% |
130.162 |
148.891 |
0.021 |
-0.03% |
0.021 |
|
MultiSource/Benchmarks/MiBench/security-rijndael/security-rijndael
Profile
|
14.27% |
0.294 |
0.336 |
0.000 |
0.11% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint16_t_To_uint8_t_
|
14.18% |
4154.694 |
4743.917 |
0.045 |
0.01% |
0.045 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint32_t_To_uint8_t_
|
14.06% |
9695.333 |
11058.606 |
46.437 |
-0.64% |
46.437 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC4
|
14.04% |
48.810 |
55.664 |
0.014 |
0.00% |
0.014 |
|
SingleSource/Benchmarks/Shootout-C++/Shootout-C++-matrix
Profile
|
14.00% |
2.201 |
2.509 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC4
|
13.78% |
36.293 |
41.296 |
0.002 |
-0.01% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC4
|
13.78% |
36.295 |
41.296 |
0.002 |
-0.01% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC4
|
13.48% |
100.806 |
114.391 |
0.564 |
-0.59% |
0.564 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIRST_SUM_RAW/5001
|
13.38% |
17.943 |
20.344 |
0.109 |
0.28% |
0.109 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC2
|
13.33% |
18.773 |
21.275 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC15
|
13.24% |
94.498 |
107.006 |
0.002 |
0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC15
|
13.24% |
94.493 |
106.999 |
0.005 |
-0.01% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC2
|
12.96% |
33.791 |
38.172 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC16
|
12.93% |
45.993 |
51.939 |
0.003 |
-0.00% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC15
|
12.91% |
45.999 |
51.936 |
0.002 |
-0.01% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC31
|
12.84% |
76.339 |
86.143 |
0.599 |
0.03% |
0.599 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint8_t>/16
|
12.67% |
53.201 |
59.943 |
0.153 |
11.38% |
0.153 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC4
|
12.50% |
20.024 |
22.527 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC4
|
12.48% |
20.025 |
22.525 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC3
|
12.48% |
20.025 |
22.525 |
0.002 |
-0.01% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC32
|
12.09% |
47.451 |
53.188 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC7
|
12.02% |
72.589 |
81.312 |
0.020 |
-0.00% |
0.020 |
|
MicroBenchmarks/ImageProcessing/Blur/blur.test:BENCHMARK_boxBlurKernel/1024
|
11.97% |
26889.421 |
30107.504 |
47.789 |
-0.14% |
47.789 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC4
|
11.75% |
21.277 |
23.776 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC64
|
11.68% |
48.185 |
53.812 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC16
|
11.54% |
32.538 |
36.293 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_BAND_LIN_EQ_RAW/171
|
11.44% |
0.344 |
0.384 |
0.000 |
4.76% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_BAND_LIN_EQ_LAMBDA/171
|
11.44% |
0.344 |
0.384 |
0.000 |
4.77% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC32
|
11.35% |
76.338 |
84.999 |
1.078 |
-0.38% |
1.078 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_PIC_2D_RAW/44217
|
10.86% |
10768.122 |
11937.465 |
13.901 |
-0.01% |
13.901 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC8
|
10.81% |
23.153 |
25.655 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC8
|
10.80% |
23.154 |
25.654 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC31
|
10.74% |
177.408 |
196.461 |
0.015 |
-0.01% |
0.015 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC127
|
10.71% |
91.991 |
101.844 |
0.034 |
-0.03% |
0.034 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint8_t>/999
|
10.70% |
288.505 |
319.374 |
1.551 |
9.81% |
1.551 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC7
|
10.51% |
23.781 |
26.280 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC7
|
10.50% |
23.781 |
26.279 |
0.002 |
-0.01% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_only_autovec_int64_t_
|
10.49% |
301597.035 |
333221.519 |
266.777 |
-0.02% |
266.777 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_DIFF_PREDICT_RAW/171
|
10.19% |
11.243 |
12.389 |
0.029 |
0.07% |
0.029 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_DEL_DOT_VEC_2D_RAW/1
|
10.04% |
260.764 |
286.950 |
0.022 |
-0.01% |
0.022 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_DEL_DOT_VEC_2D_LAMBDA/1
|
10.00% |
260.903 |
286.997 |
0.011 |
-0.04% |
0.011 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint8_t_To_uint16_t_
|
9.80% |
5324.379 |
5846.418 |
1.023 |
-0.07% |
1.023 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC7
|
9.73% |
25.660 |
28.157 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC64
|
9.65% |
85.026 |
93.228 |
0.006 |
-0.02% |
0.006 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_DEL_DOT_VEC_2D_RAW/2
|
9.52% |
3.205 |
3.510 |
0.000 |
-0.00% |
0.000 |
|
MultiSource/Benchmarks/FreeBench/pifft/pifft
Profile
|
9.52% |
0.329 |
0.360 |
0.000 |
-0.16% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_DEL_DOT_VEC_2D_LAMBDA/2
|
9.51% |
3.205 |
3.509 |
0.000 |
-0.01% |
0.000 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_runtime_checks_pass<4, int>
|
9.50% |
15.333 |
16.789 |
0.010 |
0.07% |
0.010 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC8
|
9.29% |
26.909 |
29.410 |
0.000 |
-0.01% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint8_t>/10
|
8.92% |
59.586 |
64.902 |
0.258 |
5.14% |
0.258 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint8_t>/28
|
8.81% |
85.104 |
92.603 |
0.193 |
12.95% |
0.193 |
|
SingleSource/Benchmarks/Misc/salsa20
Profile
|
8.77% |
14.145 |
15.386 |
0.000 |
0.01% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC3
|
8.57% |
43.804 |
47.556 |
0.005 |
-0.00% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC16
|
8.50% |
29.411 |
31.913 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC16
|
8.50% |
29.413 |
31.911 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC32
|
8.46% |
36.921 |
40.045 |
0.003 |
-0.01% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC3
|
8.33% |
15.018 |
16.269 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC15
|
8.33% |
30.037 |
32.538 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC15
|
8.32% |
30.037 |
32.536 |
0.002 |
-0.01% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint8_t>/51
|
8.28% |
126.402 |
136.866 |
1.044 |
16.33% |
1.044 |
|
MultiSource/Benchmarks/Trimaran/enc-md5/enc-md5
Profile
|
8.28% |
3.239 |
3.508 |
0.000 |
0.03% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC128
|
8.22% |
160.158 |
173.330 |
0.016 |
0.00% |
0.016 |
|
MultiSource/Benchmarks/VersaBench/beamformer/beamformer
Profile
|
8.20% |
4.806 |
5.200 |
0.002 |
-0.02% |
0.002 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_PRESSURE_CALC_LAMBDA/5001
|
8.19% |
44.664 |
48.324 |
0.665 |
1.73% |
0.665 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint8_t_To_uint32_t_
|
8.05% |
11834.177 |
12786.419 |
18.942 |
0.01% |
18.942 |
|
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/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint16_t_To_uint8_t_
|
7.88% |
6310.959 |
6808.496 |
0.200 |
-0.11% |
0.200 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint16_t>/28
|
7.88% |
113.320 |
122.248 |
0.242 |
0.50% |
0.242 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC127
|
7.83% |
63.830 |
68.827 |
0.002 |
0.01% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC128
|
7.80% |
63.847 |
68.827 |
0.003 |
-0.01% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint8_t>/127
|
7.76% |
128.905 |
138.912 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_DEL_DOT_VEC_2D_RAW/0
|
7.64% |
1672.632 |
1800.432 |
6.124 |
-0.02% |
6.124 |
|
SingleSource/Benchmarks/Misc/pi
Profile
|
7.54% |
1.658 |
1.783 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint16_t_To_uint64_t_
|
7.53% |
18884.337 |
20306.543 |
44.956 |
0.12% |
44.956 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC15
|
7.44% |
41.931 |
45.052 |
0.002 |
0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC15
|
7.40% |
50.688 |
54.441 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint16_t_To_uint64_t_
|
7.24% |
23338.080 |
25027.004 |
46.979 |
0.04% |
46.979 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC31
|
7.19% |
69.463 |
74.459 |
0.006 |
-0.01% |
0.006 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_DIFF_PREDICT_LAMBDA/171
|
7.02% |
11.194 |
11.981 |
0.176 |
-0.04% |
0.176 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC63
|
7.01% |
107.011 |
114.508 |
0.008 |
-0.01% |
0.008 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIRST_DIFF_RAW/5001
|
6.93% |
12.240 |
13.088 |
0.071 |
-0.26% |
0.071 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC7
|
6.89% |
30.441 |
32.539 |
0.002 |
0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC15
|
6.77% |
36.920 |
39.420 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_HYDRO_2D_LAMBDA/171
|
6.75% |
82.913 |
88.505 |
0.181 |
-0.17% |
0.181 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint16_t>/127
|
6.71% |
130.173 |
138.913 |
0.001 |
0.00% |
0.001 |
|
SingleSource/Benchmarks/Misc/flops-6
Profile
|
6.61% |
1.229 |
1.310 |
0.001 |
-0.19% |
0.001 |
|
SingleSource/Benchmarks/Misc-C++/Large/sphereflake
Profile
|
6.60% |
18.777 |
20.017 |
0.002 |
0.02% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC16
|
6.55% |
38.171 |
40.669 |
0.002 |
-0.01% |
0.002 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_DEL_DOT_VEC_2D_LAMBDA/0
|
6.55% |
1691.555 |
1802.277 |
0.566 |
-0.15% |
0.566 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC127
|
6.40% |
182.919 |
194.627 |
0.016 |
-0.00% |
0.016 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC16
|
6.38% |
29.410 |
31.287 |
0.260 |
-0.01% |
0.260 |
|
MultiSource/Benchmarks/MiBench/telecomm-gsm/telecomm-gsm
Profile
|
6.36% |
0.623 |
0.663 |
0.000 |
-0.08% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC63
|
6.35% |
69.464 |
73.874 |
0.166 |
-0.47% |
0.166 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_HYDRO_2D_RAW/171
|
6.35% |
83.344 |
88.633 |
0.339 |
0.01% |
0.339 |
|
SingleSource/Benchmarks/Misc/oourafft
Profile
|
6.31% |
14.470 |
15.383 |
0.099 |
0.91% |
0.099 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint8_t>/65
|
6.29% |
89.485 |
95.111 |
0.003 |
0.00% |
0.003 |
|
MicroBenchmarks/ImageProcessing/Dilate/Dilate.test:BENCHMARK_DILATE/128
|
6.28% |
211.190 |
224.443 |
2.567 |
-1.55% |
2.567 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint16_t>/16
|
6.27% |
79.494 |
84.475 |
0.123 |
0.39% |
0.123 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint32_t>/127
|
6.25% |
130.155 |
138.293 |
0.002 |
0.00% |
0.002 |
|
External/SPEC/CFP2017rate/538.imagick_r/538.imagick_r
Profile
|
6.04% |
274.707 |
291.297 |
0.684 |
-0.27% |
0.684 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC16
|
6.00% |
31.287 |
33.165 |
0.001 |
-0.00% |
0.001 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C++/miniFE/miniFE
Profile
|
6.00% |
14.915 |
15.809 |
0.076 |
-1.00% |
0.076 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint16_t>/51
|
5.98% |
103.364 |
109.542 |
0.172 |
0.04% |
0.172 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC32
|
5.97% |
41.925 |
44.426 |
0.003 |
-0.00% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC32
|
5.96% |
41.927 |
44.427 |
0.004 |
-0.00% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC15
|
5.92% |
121.085 |
128.256 |
0.012 |
-0.00% |
0.012 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC31
|
5.91% |
42.553 |
45.067 |
0.000 |
0.01% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC31
|
5.88% |
42.550 |
45.053 |
0.002 |
0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint32_t>/999
|
5.85% |
1289.580 |
1364.977 |
0.036 |
-0.00% |
0.036 |
|
MultiSource/Benchmarks/SciMark2-C/scimark2
Profile
|
5.84% |
101.754 |
107.696 |
0.014 |
0.00% |
0.014 |
|
MultiSource/Benchmarks/Rodinia/hotspot/hotspot
Profile
|
5.83% |
1.925 |
2.037 |
0.001 |
0.03% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint32_t>/999
|
5.68% |
658.998 |
696.451 |
0.026 |
-0.01% |
0.026 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC7
|
5.60% |
66.957 |
70.709 |
0.002 |
-0.01% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC7
|
5.59% |
66.964 |
70.711 |
0.002 |
-0.01% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint8_t>/10
|
5.58% |
46.226 |
48.807 |
0.002 |
5.16% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC127
|
5.57% |
2296.889 |
2424.844 |
21.019 |
-0.07% |
21.019 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC32
|
5.40% |
23.153 |
24.404 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC32
|
5.40% |
23.155 |
24.405 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC31
|
5.38% |
23.155 |
24.402 |
0.016 |
-0.00% |
0.016 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC31
|
5.35% |
23.163 |
24.402 |
0.015 |
-0.00% |
0.015 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_only_autovec_int32_t_
|
5.28% |
171862.809 |
180942.228 |
108.567 |
-0.10% |
108.567 |
|
MultiSource/Applications/lambda-0.1.3/lambda
Profile
|
5.23% |
15.098 |
15.887 |
0.008 |
-0.08% |
0.008 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint32_t_To_uint64_t_
|
5.22% |
20264.715 |
21322.175 |
121.344 |
-0.60% |
121.344 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint16_t>/10
|
5.11% |
62.577 |
65.774 |
0.086 |
0.37% |
0.086 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC63
|
5.10% |
41.302 |
43.407 |
0.172 |
0.26% |
0.172 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint32_t>/256
|
5.05% |
346.690 |
364.189 |
0.007 |
-0.00% |
0.007 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC31
|
5.02% |
229.676 |
241.213 |
0.011 |
-0.01% |
0.011 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_FLOYD_DITHER/256
|
4.92% |
1749.810 |
1835.979 |
12.398 |
1.49% |
12.398 |
|
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
|
4.82% |
90.741 |
95.114 |
0.009 |
-0.00% |
0.009 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_runtime_checks_pass<16, int>
|
4.80% |
51.943 |
54.437 |
0.018 |
-0.00% |
0.018 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_runtime_checks_fail<16, int>
|
4.80% |
51.944 |
54.436 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC2
|
4.76% |
13.141 |
13.767 |
0.002 |
4.63% |
0.002 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_PIC_2D_RAW/171
|
4.74% |
12.967 |
13.582 |
0.029 |
0.21% |
0.029 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC8
|
4.70% |
25.656 |
26.862 |
0.176 |
-0.19% |
0.176 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC31
|
4.66% |
66.958 |
70.078 |
0.003 |
-0.01% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC64
|
4.55% |
41.299 |
43.179 |
0.254 |
0.01% |
0.254 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC15
|
4.55% |
13.767 |
14.393 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC3
|
4.55% |
13.766 |
14.392 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC2
|
4.54% |
13.766 |
14.392 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC4
|
4.54% |
13.767 |
14.393 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC16
|
4.54% |
13.766 |
14.391 |
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:benchAutoVecForLoopTC3
|
4.54% |
13.767 |
14.392 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC16
|
4.54% |
13.767 |
14.392 |
0.000 |
-0.01% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC1
|
4.53% |
13.767 |
14.391 |
0.001 |
-0.00% |
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 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC7
|
4.53% |
13.767 |
14.392 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC8
|
4.53% |
13.767 |
14.391 |
0.002 |
-0.01% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC15
|
4.53% |
13.768 |
14.392 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC4
|
4.52% |
13.769 |
14.392 |
0.001 |
-0.00% |
0.001 |
|
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
|
4.46% |
3442.293 |
3595.740 |
0.160 |
0.02% |
0.160 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint64_t>/999
|
4.43% |
1734.480 |
1811.323 |
0.081 |
0.00% |
0.081 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_PIC_2D_LAMBDA/171
|
4.34% |
12.898 |
13.458 |
0.060 |
-0.30% |
0.060 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint8_t_To_uint64_t_
|
4.30% |
22517.532 |
23485.128 |
47.118 |
0.00% |
47.118 |
|
SingleSource/Benchmarks/Misc/flops-5
Profile
|
4.29% |
1.939 |
2.022 |
0.000 |
-0.01% |
0.000 |
|
SingleSource/Benchmarks/Polybench/stencils/jacobi-2d/jacobi-2d
Profile
|
4.26% |
30.742 |
32.052 |
0.090 |
-0.53% |
0.090 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC31
|
4.20% |
59.446 |
61.945 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint64_t>/256
|
4.20% |
897.838 |
935.551 |
0.056 |
-0.00% |
0.056 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC32
|
4.17% |
30.035 |
31.287 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC32
|
4.17% |
58.871 |
61.323 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_only_autovec_uint8_t_
|
4.14% |
92348.779 |
96172.522 |
5.533 |
0.01% |
5.533 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint32_t>/65
|
4.13% |
90.736 |
94.480 |
0.006 |
-0.01% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC32
|
4.12% |
60.700 |
63.201 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint32_t>/256
|
4.11% |
212.758 |
221.509 |
0.003 |
0.00% |
0.003 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_ENERGY_CALC_RAW/171
|
4.08% |
13.651 |
14.208 |
0.014 |
-0.23% |
0.014 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC7
|
4.04% |
344.171 |
358.082 |
1.795 |
-0.12% |
1.795 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_ENERGY_CALC_LAMBDA/171
|
4.00% |
13.664 |
14.211 |
0.011 |
-0.26% |
0.011 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint64_t_To_uint8_t_
|
3.97% |
19038.240 |
19793.399 |
65.557 |
-0.24% |
65.557 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_only_novec_uint8_t_
|
3.96% |
404341.180 |
420367.290 |
57.601 |
6.18% |
57.601 |
|
MultiSource/Benchmarks/VersaBench/ecbdes/ecbdes
Profile
|
3.92% |
4.947 |
5.141 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint64_t_To_uint32_t_
|
3.92% |
18685.726 |
19417.705 |
27.265 |
0.06% |
27.265 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint32_t_To_uint16_t_
|
3.92% |
9460.434 |
9830.916 |
35.812 |
-0.49% |
35.812 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_BAND_LIN_EQ_LAMBDA/5001
|
3.88% |
20.482 |
21.277 |
0.283 |
0.98% |
0.283 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<31, EqZero, First>
|
3.82% |
3223.224 |
3346.339 |
0.054 |
-0.00% |
0.054 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint64_t>/256
|
3.78% |
495.638 |
514.352 |
0.026 |
-0.01% |
0.026 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC64
|
3.73% |
66.956 |
69.456 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC64
|
3.73% |
66.961 |
69.457 |
0.002 |
-0.01% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC63
|
3.70% |
67.583 |
70.085 |
0.009 |
-0.01% |
0.009 |
|
SingleSource/Benchmarks/BenchmarkGame/n-body
Profile
|
3.69% |
2.634 |
2.731 |
0.000 |
26.21% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC63
|
3.69% |
67.582 |
70.077 |
0.006 |
-0.01% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC32
|
3.66% |
48.183 |
49.946 |
0.051 |
-0.21% |
0.051 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_cond_load_autovec_int64_t_
|
3.65% |
532402.417 |
551813.602 |
874.213 |
-0.15% |
874.213 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint8_t_To_uint16_t_
|
3.64% |
3500.050 |
3627.519 |
4.323 |
-0.16% |
4.323 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint16_t>/999
|
3.56% |
978.918 |
1013.739 |
0.023 |
-0.01% |
0.023 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC31
|
3.52% |
58.199 |
60.248 |
0.116 |
-0.05% |
0.116 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC31
|
3.47% |
90.111 |
93.235 |
0.262 |
-0.66% |
0.262 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_runtime_checks_fail<4, int>
|
3.44% |
15.331 |
15.857 |
0.155 |
-0.32% |
0.155 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint8_t>/51
|
3.39% |
223.387 |
230.966 |
2.654 |
12.52% |
2.654 |
|
External/SPEC/CFP2017rate/544.nab_r/544.nab_r
Profile
|
3.33% |
460.935 |
476.293 |
0.128 |
-0.33% |
0.128 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_HYDRO_1D_RAW/5001
|
3.29% |
17.060 |
17.621 |
0.083 |
0.29% |
0.083 |
|
SingleSource/Benchmarks/Shootout/Shootout-lists
Profile
|
3.28% |
10.955 |
11.315 |
0.000 |
-0.01% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint16_t>/999
|
3.26% |
498.743 |
515.008 |
0.005 |
-0.00% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1BigLoopWithReductionTC1
|
3.21% |
19.400 |
20.023 |
0.004 |
-0.01% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchVecWithRuntimeChecks4PointersDBeforeA/1000
|
3.16% |
4866336.215 |
5020230.791 |
232.256 |
0.01% |
232.256 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint16_t_To_uint32_t_
|
3.16% |
10967.246 |
11313.892 |
58.587 |
-0.25% |
58.587 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_acosf_novec_float_
|
2.89% |
820.929 |
844.635 |
0.218 |
-0.00% |
0.218 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_acosf_autovec_float_
|
2.87% |
821.018 |
844.621 |
0.274 |
-0.02% |
0.274 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC31
|
2.87% |
30.036 |
30.899 |
0.134 |
-0.93% |
0.134 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC1
|
2.85% |
21.901 |
22.526 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_EOS_LAMBDA/5001
|
2.82% |
29.902 |
30.746 |
0.244 |
0.82% |
0.244 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC1
|
2.81% |
21.908 |
22.525 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint8_t>/16
|
2.79% |
91.995 |
94.564 |
0.324 |
4.92% |
0.324 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_PRESSURE_CALC_LAMBDA/44217
|
2.75% |
483.653 |
496.942 |
3.538 |
-0.32% |
3.538 |
|
MultiSource/Benchmarks/BitBench/drop3/drop3
Profile
|
2.74% |
0.711 |
0.731 |
0.001 |
0.01% |
0.001 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C/CoMD/CoMD
Profile
|
2.70% |
9.641 |
9.901 |
0.049 |
-0.01% |
0.049 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC63
|
2.67% |
117.021 |
120.143 |
0.005 |
-0.00% |
0.005 |
|
MultiSource/Applications/JM/lencod/lencod
Profile
|
2.60% |
31.898 |
32.727 |
0.006 |
0.49% |
0.006 |
|
SingleSource/Benchmarks/Misc-C++/oopack_v1p8
Profile
|
2.57% |
0.468 |
0.480 |
0.000 |
-7.52% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint8_t_To_uint32_t_
|
2.55% |
6901.629 |
7077.650 |
0.716 |
0.00% |
0.716 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint32_t>/10
|
2.55% |
56.441 |
57.879 |
0.006 |
0.41% |
0.006 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<31, GreaterThanZero, Last>
|
2.51% |
8149.968 |
8354.826 |
27.540 |
-0.11% |
27.540 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<16, EqZero, None>
|
2.48% |
8021.674 |
8220.390 |
67.610 |
0.22% |
67.610 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_ENERGY_CALC_LAMBDA/5001
|
2.45% |
427.358 |
437.844 |
2.167 |
-0.05% |
2.167 |
|
MultiSource/Benchmarks/Ptrdist/yacr2/yacr2
Profile
|
2.44% |
2.026 |
2.076 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC63
|
2.39% |
104.502 |
107.001 |
0.003 |
-0.00% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint16_t>/16
|
2.35% |
52.576 |
53.814 |
0.005 |
0.55% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint8_t>/28
|
2.34% |
137.051 |
140.263 |
1.230 |
8.28% |
1.230 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint16_t_To_uint8_t_
|
2.33% |
2807.751 |
2873.081 |
2.272 |
-0.18% |
2.272 |
|
SingleSource/Benchmarks/Misc-C++/Large/ray
Profile
|
2.31% |
11.831 |
12.104 |
0.001 |
0.02% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint8_t>/16
|
2.30% |
62.584 |
64.021 |
0.191 |
4.35% |
0.191 |
|
SingleSource/Benchmarks/Shootout/Shootout-matrix
Profile
|
2.27% |
3.777 |
3.863 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint16_t>/10
|
2.25% |
45.193 |
46.209 |
0.002 |
0.80% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchVecWithRuntimeChecks4PointersDBeforeA/32
|
2.25% |
162540.603 |
166192.891 |
9.587 |
-0.01% |
9.587 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint64_t>/51
|
2.23% |
224.018 |
229.023 |
0.001 |
0.01% |
0.001 |
|
SingleSource/Benchmarks/Misc/flops-1
Profile
|
2.21% |
8.807 |
9.002 |
0.000 |
0.01% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC64
|
2.18% |
109.001 |
111.377 |
0.009 |
-0.01% |
0.009 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC128
|
2.13% |
117.026 |
119.519 |
0.005 |
-0.00% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC128
|
2.13% |
117.025 |
119.515 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC127
|
2.12% |
117.645 |
120.141 |
0.003 |
-0.00% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC127
|
2.10% |
117.660 |
120.136 |
0.008 |
-0.00% |
0.008 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_PRESSURE_CALC_RAW/44217
|
2.01% |
491.150 |
501.028 |
2.582 |
-0.23% |
2.582 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_EOS_RAW/171
|
1.94% |
0.856 |
0.873 |
0.001 |
0.02% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint16_t_To_uint8_t_
|
1.86% |
4429.870 |
4512.349 |
0.959 |
-0.11% |
0.959 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint16_t>/256
|
1.85% |
267.877 |
272.835 |
0.013 |
-0.00% |
0.013 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<16, EqZero, Mid>
|
1.84% |
8501.490 |
8657.856 |
17.710 |
-0.00% |
17.710 |
|
External/SPEC/CFP2017rate/511.povray_r/511.povray_r
Profile
|
1.82% |
33.446 |
34.056 |
0.019 |
0.73% |
0.019 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<32, EqZero, Last>
|
1.81% |
6941.080 |
7066.863 |
19.824 |
0.12% |
19.824 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_INT_PREDICT_RAW/171
|
1.80% |
6.803 |
6.926 |
0.013 |
0.00% |
0.013 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint32_t_To_uint64_t_
|
1.76% |
25943.732 |
26400.802 |
46.113 |
0.17% |
46.113 |
|
MultiSource/Benchmarks/TSVC/InductionVariable-dbl/InductionVariable-dbl
Profile
|
1.72% |
17.098 |
17.392 |
0.106 |
-1.93% |
0.106 |
|
MultiSource/Benchmarks/mafft/pairlocalalign
Profile
|
1.72% |
92.468 |
94.055 |
0.268 |
-0.01% |
0.268 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint64_t>/51
|
1.71% |
145.802 |
148.298 |
0.005 |
-0.01% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_erf_novec_double_
|
1.64% |
874.880 |
889.206 |
0.857 |
-0.01% |
0.857 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_EOS_LAMBDA/171
|
1.63% |
0.857 |
0.871 |
0.002 |
0.02% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC63
|
1.62% |
127.662 |
129.725 |
0.200 |
-0.34% |
0.200 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_erf_autovec_double_
|
1.60% |
875.165 |
889.125 |
0.920 |
0.00% |
0.920 |
|
SingleSource/Benchmarks/Misc/mandel-2
Profile
|
1.57% |
2.496 |
2.536 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<32, LessThanZero, Mid>
|
1.55% |
4501.161 |
4570.740 |
0.457 |
-0.01% |
0.457 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_csa_with_cond_arith_autovec_int64_t_
|
1.50% |
735512.153 |
746528.367 |
716.328 |
-0.06% |
716.328 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_csa_with_in_loop_arith_novec_int64_t_
|
1.50% |
1012990.227 |
1028143.713 |
769.212 |
-0.00% |
769.212 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_FLOYD_DITHER/512
|
1.47% |
6551.752 |
6647.811 |
5.945 |
0.04% |
5.945 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<6, LessThanZero, Mid>
|
1.43% |
23486.878 |
23823.369 |
24.326 |
0.06% |
24.326 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint32_t>/28
|
1.41% |
71.492 |
72.502 |
0.014 |
-0.31% |
0.014 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_ENERGY_CALC_LAMBDA/44217
|
1.37% |
4262.749 |
4321.244 |
9.719 |
-0.07% |
9.719 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_INT_PREDICT_LAMBDA/171
|
1.36% |
6.833 |
6.926 |
0.010 |
0.01% |
0.010 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<32, GreaterThanZero, Mid>
|
1.36% |
4495.111 |
4556.232 |
9.802 |
0.02% |
9.802 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_FLOYD_DITHER/128
|
1.36% |
432.962 |
438.838 |
1.024 |
-0.14% |
1.024 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint16_t_To_uint32_t_
|
1.29% |
13365.498 |
13538.190 |
18.886 |
0.10% |
18.886 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC127
|
1.28% |
194.627 |
197.115 |
0.003 |
0.00% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC128
|
1.28% |
195.859 |
198.361 |
0.006 |
-0.00% |
0.006 |
|
MultiSource/Benchmarks/MallocBench/cfrac/cfrac
Profile
|
1.26% |
2.745 |
2.779 |
0.000 |
-0.03% |
0.000 |
|
MultiSource/Benchmarks/ASC_Sequoia/AMGmk/AMGmk
Profile
|
1.22% |
32.897 |
33.297 |
0.022 |
0.45% |
0.022 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, LessThanZero, None>
|
1.20% |
37153.707 |
37600.758 |
21.998 |
0.07% |
21.998 |
|
MultiSource/Benchmarks/nbench/nbench
Profile
|
1.17% |
6.037 |
6.108 |
0.001 |
-0.31% |
0.001 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<7, EqZero, None>
|
1.17% |
26875.358 |
27189.255 |
16.887 |
0.03% |
16.887 |
|
External/SPEC/CINT2017rate/525.x264_r/525.x264_r
Profile
|
1.17% |
128.142 |
129.636 |
0.076 |
0.02% |
0.076 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_nested_cond_load_novec_int32_t_
|
1.14% |
642702.280 |
650015.773 |
187.273 |
0.62% |
187.273 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<8, LessThanZero, Mid>
|
1.11% |
19230.780 |
19443.499 |
26.147 |
0.05% |
26.147 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_nested_cond_load_novec_uint8_t_
|
1.10% |
499041.933 |
504512.973 |
498.790 |
-0.04% |
498.790 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint32_t>/51
|
1.07% |
117.013 |
118.265 |
0.001 |
0.00% |
0.001 |