|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_INT_PREDICT_RAW/44217
|
137.80% |
8212.090 |
19528.437 |
98.126 |
1.06% |
98.126 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint64_t_To_uint32_t_
|
105.25% |
17148.938 |
35198.969 |
54.620 |
-0.32% |
54.620 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint64_t_To_uint16_t_
|
101.37% |
17698.796 |
35640.402 |
52.429 |
-0.11% |
52.429 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint64_t_To_uint8_t_
|
98.11% |
18697.679 |
37041.514 |
110.181 |
-0.06% |
110.181 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C/miniGMG/miniGMG
Profile
|
85.12% |
4.692 |
8.686 |
0.617 |
-5.49% |
0.617 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint16_t_To_uint64_t_
|
78.31% |
10453.891 |
18640.107 |
270.963 |
-0.19% |
270.963 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIRST_DIFF_RAW/44217
|
70.09% |
104.205 |
177.246 |
7.725 |
-1.36% |
7.725 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_DIFF_PREDICT_RAW/44217
|
70.03% |
14179.422 |
24109.810 |
1397.090 |
-1.21% |
1397.090 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint8_t_To_uint64_t_
|
69.23% |
10536.782 |
17831.190 |
362.715 |
0.03% |
362.715 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint64_t_To_uint32_t_
|
68.31% |
22677.703 |
38169.651 |
23.412 |
0.04% |
23.412 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_DIFF_PREDICT_LAMBDA/44217
|
62.91% |
14179.051 |
23099.722 |
1609.796 |
-0.01% |
1609.796 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_DIFF_PREDICT_LAMBDA/5001
|
62.18% |
1576.657 |
2557.057 |
176.029 |
-0.69% |
176.029 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_DIFF_PREDICT_RAW/5001
|
61.86% |
1566.439 |
2535.363 |
159.400 |
-1.53% |
159.400 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/32
|
57.82% |
884.528 |
1396.001 |
0.205 |
-0.01% |
0.205 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/64
|
57.74% |
3919.213 |
6182.021 |
8.055 |
-0.00% |
8.055 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/16
|
57.54% |
177.389 |
279.460 |
0.025 |
-0.00% |
0.025 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/256
|
56.33% |
68515.712 |
107107.892 |
12.866 |
-0.04% |
12.866 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/128
|
56.26% |
16807.633 |
26263.620 |
3.831 |
-0.03% |
3.831 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint64_t_To_uint8_t_
|
51.58% |
19816.714 |
30037.356 |
109.121 |
-0.24% |
109.121 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint64_t_To_uint16_t_
|
50.60% |
19164.663 |
28861.029 |
28.106 |
-0.30% |
28.106 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint64_t_To_uint16_t_
|
39.20% |
18618.317 |
25916.534 |
9.106 |
0.07% |
9.106 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint32_t_To_uint64_t_
|
38.01% |
16338.378 |
22548.278 |
418.358 |
-0.78% |
418.358 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint32_t_To_uint8_t_
|
37.77% |
9806.138 |
13509.784 |
22.813 |
0.25% |
22.813 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC128
|
37.11% |
406.289 |
557.042 |
0.937 |
-0.09% |
0.937 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC128
|
36.81% |
947.215 |
1295.847 |
4.088 |
0.00% |
4.088 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC64
|
35.47% |
483.971 |
655.628 |
0.805 |
-0.16% |
0.805 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC32
|
35.20% |
247.747 |
334.963 |
0.049 |
-0.01% |
0.049 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC64
|
34.89% |
216.277 |
291.727 |
0.287 |
-0.03% |
0.287 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint8_t>/51
|
34.81% |
91.901 |
123.888 |
0.095 |
33.93% |
0.095 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC16
|
34.76% |
129.232 |
174.151 |
0.049 |
-0.08% |
0.049 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint64_t_To_uint8_t_
|
32.17% |
20532.685 |
27138.156 |
48.348 |
-0.31% |
48.348 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC32
|
31.50% |
120.787 |
158.833 |
0.063 |
-0.02% |
0.063 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint8_t_To_uint32_t_
|
31.08% |
5172.194 |
6779.934 |
86.099 |
2.58% |
86.099 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC128
|
30.39% |
463.199 |
603.962 |
2.263 |
0.00% |
2.263 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC128
|
30.37% |
463.246 |
603.929 |
0.064 |
-0.01% |
0.064 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIRST_SUM_RAW/44217
|
29.98% |
137.101 |
178.197 |
1.830 |
-4.76% |
1.830 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC64
|
29.11% |
242.822 |
313.509 |
0.008 |
0.00% |
0.008 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC64
|
29.11% |
242.813 |
313.490 |
0.015 |
-0.00% |
0.015 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC127
|
28.15% |
480.077 |
615.237 |
0.036 |
0.00% |
0.036 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC127
|
28.13% |
480.091 |
615.129 |
0.070 |
-0.01% |
0.070 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint16_t_To_uint64_t_
|
28.03% |
10366.562 |
13272.775 |
140.913 |
0.03% |
140.913 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint16_t_To_uint32_t_
|
27.38% |
5576.848 |
7103.930 |
168.425 |
0.04% |
168.425 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_only_autovec_uint8_t_
|
27.10% |
143512.345 |
182397.933 |
57.100 |
0.01% |
57.100 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC32
|
26.87% |
132.667 |
168.321 |
0.003 |
-0.01% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC32
|
26.87% |
132.671 |
168.318 |
0.005 |
-0.00% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC16
|
26.00% |
73.225 |
92.267 |
0.008 |
-0.01% |
0.008 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint8_t>/51
|
25.44% |
152.671 |
191.515 |
5.434 |
23.99% |
5.434 |
|
MultiSource/Benchmarks/Trimaran/enc-pc1/enc-pc1
Profile
|
25.18% |
0.882 |
1.105 |
0.000 |
0.01% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC63
|
25.06% |
259.711 |
324.782 |
0.010 |
-0.00% |
0.010 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC63
|
25.05% |
259.707 |
324.776 |
0.012 |
-0.01% |
0.012 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC127
|
25.00% |
220.075 |
275.096 |
2.689 |
-0.13% |
2.689 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC127
|
24.34% |
515.380 |
640.832 |
0.263 |
-0.05% |
0.263 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC128
|
24.17% |
221.367 |
274.874 |
0.488 |
0.05% |
0.488 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint16_t_To_uint8_t_
|
23.60% |
3089.023 |
3817.995 |
0.732 |
-0.00% |
0.732 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIRST_SUM_LAMBDA/44217
|
23.45% |
137.228 |
169.415 |
3.895 |
1.39% |
3.895 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC16
|
23.38% |
77.594 |
95.733 |
0.003 |
-0.01% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC16
|
23.37% |
77.600 |
95.736 |
0.003 |
-0.00% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint8_t>/28
|
23.36% |
66.956 |
82.598 |
0.002 |
22.21% |
0.002 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, EqZero, None>
|
23.06% |
16667.400 |
20510.353 |
1.077 |
-0.01% |
1.077 |
|
SingleSource/Benchmarks/Adobe-C++/loop_unroll
Profile
|
22.87% |
2.427 |
2.982 |
0.004 |
-4.03% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC8
|
22.83% |
47.874 |
58.802 |
0.011 |
-0.03% |
0.011 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint32_t_To_uint16_t_
|
22.70% |
11248.552 |
13801.719 |
8.672 |
-0.04% |
8.672 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint64_t_To_uint32_t_
|
22.59% |
22104.937 |
27097.997 |
10.943 |
0.03% |
10.943 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC16
|
22.41% |
76.061 |
93.103 |
0.062 |
-0.02% |
0.062 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, EqZero, Last>
|
22.20% |
11540.857 |
14103.054 |
0.575 |
-0.01% |
0.575 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC32
|
21.92% |
132.340 |
161.354 |
0.037 |
-0.02% |
0.037 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_with_cond_arith_novec_uint8_t_
|
21.79% |
612808.192 |
746366.423 |
419.860 |
0.07% |
419.860 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint32_t_To_uint8_t_
|
21.62% |
11429.840 |
13900.516 |
17.142 |
-0.00% |
17.142 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC64
|
21.46% |
245.018 |
297.607 |
0.118 |
-0.03% |
0.118 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC128
|
21.26% |
470.691 |
570.751 |
0.052 |
-0.01% |
0.052 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC4
|
21.14% |
14.463 |
17.521 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_with_cond_arith_novec_int32_t_
|
20.56% |
614273.628 |
740566.940 |
427.645 |
0.05% |
427.645 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC31
|
20.08% |
149.555 |
179.580 |
0.011 |
-0.00% |
0.011 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC31
|
20.05% |
149.586 |
179.579 |
0.006 |
-0.00% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC8
|
19.91% |
19.307 |
23.151 |
0.003 |
-0.01% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint8_t>/28
|
19.55% |
100.861 |
120.578 |
0.390 |
16.96% |
0.390 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC64
|
19.14% |
126.472 |
150.682 |
1.441 |
0.57% |
1.441 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint8_t_To_uint64_t_
|
19.12% |
10981.289 |
13081.196 |
225.643 |
0.12% |
225.643 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_PIC_2D_RAW/5001
|
19.05% |
978.477 |
1164.906 |
33.890 |
-1.96% |
33.890 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_HYDRO_1D_LAMBDA/171
|
18.85% |
0.372 |
0.442 |
0.002 |
-0.01% |
0.002 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_HYDRO_1D_RAW/171
|
18.82% |
0.372 |
0.442 |
0.001 |
0.02% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC8
|
18.75% |
20.024 |
23.778 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC8
|
18.74% |
50.061 |
59.444 |
0.004 |
-0.01% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC8
|
18.74% |
50.061 |
59.443 |
0.003 |
-0.01% |
0.003 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, EqZero, None>
|
18.60% |
13510.598 |
16023.849 |
0.719 |
0.00% |
0.719 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint16_t_To_uint32_t_
|
18.55% |
6294.830 |
7462.613 |
1.366 |
-0.00% |
1.366 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_VOL3D_CALC_RAW/2
|
18.33% |
7.401 |
8.757 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_VOL3D_CALC_LAMBDA/2
|
18.32% |
7.402 |
8.757 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_no_runtime_checks_needed<16, int>
|
18.18% |
20.650 |
24.404 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, EqZero, Last>
|
18.16% |
14106.304 |
16667.568 |
0.280 |
0.00% |
0.280 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, EqZero, Mid>
|
18.15% |
14105.773 |
16665.827 |
0.594 |
-0.00% |
0.594 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, EqZero, First>
|
18.15% |
14110.172 |
16670.655 |
0.172 |
-0.00% |
0.172 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint64_t_To_uint8_t_
|
17.52% |
18734.514 |
22017.661 |
48.415 |
-0.13% |
48.415 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC127
|
17.51% |
515.450 |
605.711 |
0.053 |
-0.01% |
0.053 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC63
|
17.18% |
129.637 |
151.910 |
2.049 |
0.46% |
2.049 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC128
|
17.18% |
941.491 |
1103.236 |
0.112 |
-0.01% |
0.112 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/64
|
16.94% |
1638.306 |
1915.832 |
9.596 |
0.12% |
9.596 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC127
|
16.93% |
936.467 |
1095.046 |
0.223 |
-0.02% |
0.223 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC64
|
16.90% |
480.650 |
561.899 |
0.327 |
-0.07% |
0.327 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint32_t_To_uint8_t_
|
16.89% |
9073.668 |
10606.006 |
54.378 |
0.10% |
54.378 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/32
|
16.81% |
404.928 |
473.013 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC7
|
16.80% |
23.923 |
27.943 |
0.183 |
-2.50% |
0.183 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/256
|
16.64% |
26961.833 |
31448.799 |
24.510 |
-0.00% |
24.510 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC32
|
16.57% |
250.315 |
291.794 |
0.221 |
-0.07% |
0.221 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC63
|
16.55% |
475.632 |
554.361 |
1.488 |
-0.07% |
1.488 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/16
|
16.55% |
99.076 |
115.469 |
0.005 |
0.00% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint32_t_To_uint16_t_
|
16.42% |
11021.960 |
12831.870 |
33.569 |
-0.04% |
33.569 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/128
|
16.42% |
6799.779 |
7916.095 |
3.059 |
-0.02% |
3.059 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint8_t_To_uint16_t_
|
16.35% |
3229.556 |
3757.637 |
0.277 |
0.00% |
0.277 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC7
|
16.09% |
44.741 |
51.939 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC1
|
16.09% |
44.740 |
51.937 |
0.002 |
0.01% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC4
|
16.08% |
44.739 |
51.935 |
0.002 |
0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC8
|
16.08% |
44.741 |
51.936 |
0.004 |
-0.01% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC3
|
16.08% |
44.742 |
51.935 |
0.002 |
0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC2
|
16.08% |
44.742 |
51.936 |
0.008 |
0.00% |
0.008 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC16
|
16.06% |
28.573 |
33.162 |
0.004 |
-0.00% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC16
|
16.03% |
135.171 |
156.834 |
0.108 |
-0.08% |
0.108 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_with_cond_arith_novec_int64_t_
|
15.76% |
682541.663 |
790119.802 |
2121.275 |
0.01% |
2121.275 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, EqZero, First>
|
15.76% |
12183.291 |
14103.400 |
0.298 |
0.00% |
0.298 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint64_t_To_uint16_t_
|
15.71% |
16766.222 |
19400.266 |
355.574 |
-0.82% |
355.574 |
|
External/SPEC/CFP2017rate/508.namd_r/508.namd_r
Profile
|
15.68% |
194.363 |
224.837 |
0.054 |
0.30% |
0.054 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC31
|
15.62% |
245.299 |
283.615 |
0.228 |
-0.17% |
0.228 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, EqZero, Mid>
|
15.51% |
12209.847 |
14103.917 |
0.077 |
0.00% |
0.077 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_VOL3D_CALC_LAMBDA/0
|
15.49% |
1098.150 |
1268.291 |
0.441 |
0.00% |
0.441 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_with_cond_arith_autovec_int64_t_
|
15.47% |
684155.890 |
790026.768 |
1278.408 |
-0.20% |
1278.408 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC63
|
15.29% |
324.799 |
374.468 |
0.093 |
0.00% |
0.093 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_VOL3D_CALC_RAW/0
|
15.16% |
1098.162 |
1264.646 |
2.126 |
-0.04% |
2.126 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC8
|
15.14% |
77.607 |
89.359 |
0.059 |
-0.05% |
0.059 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC128
|
15.03% |
70.715 |
81.345 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_VOL3D_CALC_LAMBDA/1
|
14.96% |
226.307 |
260.153 |
0.207 |
-0.01% |
0.207 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint8_t_To_uint16_t_
|
14.87% |
3953.911 |
4542.025 |
0.236 |
0.00% |
0.236 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_VOL3D_CALC_RAW/1
|
14.87% |
226.322 |
259.980 |
0.236 |
-0.06% |
0.236 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC63
|
14.73% |
290.074 |
332.802 |
0.051 |
-0.01% |
0.051 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint8_t>/16
|
14.70% |
73.350 |
84.133 |
1.944 |
11.36% |
1.944 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIRST_SUM_RAW/5001
|
14.57% |
17.943 |
20.557 |
0.356 |
0.29% |
0.356 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC31
|
14.38% |
76.339 |
87.313 |
0.138 |
-0.33% |
0.138 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC15
|
14.36% |
130.162 |
148.849 |
0.055 |
0.03% |
0.055 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC32
|
14.25% |
76.338 |
87.216 |
0.179 |
-0.44% |
0.179 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint16_t_To_uint8_t_
|
14.17% |
4154.694 |
4743.273 |
0.361 |
-0.00% |
0.361 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC4
|
14.06% |
48.810 |
55.672 |
0.010 |
0.02% |
0.010 |
|
SingleSource/Benchmarks/Shootout-C++/Shootout-C++-matrix
Profile
|
14.02% |
2.201 |
2.510 |
0.000 |
0.02% |
0.000 |
|
MultiSource/Benchmarks/MiBench/security-rijndael/security-rijndael
Profile
|
13.96% |
0.294 |
0.335 |
0.001 |
-0.06% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC15
|
13.94% |
38.796 |
44.205 |
0.291 |
-0.51% |
0.291 |
|
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 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint32_t_To_uint8_t_
|
13.33% |
9695.333 |
10987.925 |
76.685 |
-1.27% |
76.685 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC2
|
13.33% |
18.773 |
21.276 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC15
|
13.23% |
94.493 |
106.996 |
0.005 |
-0.01% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC15
|
13.23% |
94.498 |
106.997 |
0.007 |
-0.01% |
0.007 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC2
|
12.96% |
33.791 |
38.171 |
0.002 |
0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC16
|
12.92% |
45.993 |
51.938 |
0.002 |
-0.01% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC15
|
12.90% |
45.999 |
51.933 |
0.004 |
-0.01% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint8_t>/16
|
12.70% |
53.201 |
59.959 |
0.050 |
11.41% |
0.050 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC4
|
12.49% |
20.024 |
22.526 |
0.002 |
-0.01% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC3
|
12.49% |
20.025 |
22.526 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC4
|
12.49% |
20.025 |
22.525 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC32
|
12.09% |
47.451 |
53.186 |
0.004 |
-0.01% |
0.004 |
|
MicroBenchmarks/ImageProcessing/Blur/blur.test:BENCHMARK_boxBlurKernel/1024
|
12.05% |
26889.421 |
30128.632 |
9.889 |
-0.07% |
9.889 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC7
|
11.98% |
72.589 |
81.289 |
0.034 |
-0.03% |
0.034 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC4
|
11.76% |
21.277 |
23.779 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC64
|
11.68% |
48.185 |
53.812 |
0.002 |
-0.01% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC16
|
11.54% |
32.538 |
36.292 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC4
|
11.50% |
100.806 |
112.396 |
1.753 |
-0.61% |
1.753 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_BAND_LIN_EQ_RAW/171
|
11.45% |
0.344 |
0.384 |
0.000 |
4.77% |
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/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_PIC_2D_RAW/44217
|
11.14% |
10768.122 |
11967.209 |
8.929 |
-0.08% |
8.929 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC8
|
10.82% |
23.153 |
25.657 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC8
|
10.80% |
23.154 |
25.655 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC31
|
10.68% |
177.408 |
196.351 |
0.060 |
-0.06% |
0.060 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_only_autovec_int64_t_
|
10.60% |
301597.035 |
333560.561 |
145.399 |
0.02% |
145.399 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC127
|
10.53% |
91.991 |
101.677 |
0.346 |
-0.20% |
0.346 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC7
|
10.51% |
23.781 |
26.280 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC7
|
10.51% |
23.781 |
26.280 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint8_t>/999
|
10.41% |
288.505 |
318.531 |
2.672 |
9.52% |
2.672 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_DEL_DOT_VEC_2D_RAW/1
|
10.12% |
260.764 |
287.154 |
0.038 |
0.03% |
0.038 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_DEL_DOT_VEC_2D_LAMBDA/1
|
10.11% |
260.903 |
287.290 |
0.069 |
-0.02% |
0.069 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint8_t_To_uint16_t_
|
10.02% |
5324.379 |
5857.738 |
10.799 |
-0.01% |
10.799 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_DIFF_PREDICT_RAW/171
|
9.84% |
11.243 |
12.349 |
0.018 |
0.24% |
0.018 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint8_t>/10
|
9.78% |
59.586 |
65.412 |
0.618 |
5.96% |
0.618 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC7
|
9.74% |
25.660 |
28.160 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC64
|
9.65% |
85.026 |
93.231 |
0.005 |
-0.01% |
0.005 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_runtime_checks_pass<4, int>
|
9.58% |
15.333 |
16.802 |
0.023 |
0.15% |
0.023 |
|
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 |
|
MultiSource/Benchmarks/FreeBench/pifft/pifft
Profile
|
9.34% |
0.329 |
0.359 |
0.000 |
0.13% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC8
|
9.30% |
26.909 |
29.410 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/ImageProcessing/Dilate/Dilate.test:BENCHMARK_DILATE/128
|
9.26% |
211.190 |
230.747 |
7.413 |
0.97% |
7.413 |
|
SingleSource/Benchmarks/Misc/salsa20
Profile
|
8.77% |
14.145 |
15.387 |
0.000 |
0.01% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC3
|
8.57% |
43.804 |
47.558 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC16
|
8.50% |
29.411 |
31.912 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC16
|
8.50% |
29.413 |
31.912 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC32
|
8.47% |
36.921 |
40.047 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC3
|
8.33% |
15.018 |
16.270 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC15
|
8.32% |
30.037 |
32.537 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC15
|
8.32% |
30.037 |
32.537 |
0.002 |
-0.01% |
0.002 |
|
MultiSource/Benchmarks/Trimaran/enc-md5/enc-md5
Profile
|
8.27% |
3.239 |
3.507 |
0.000 |
0.02% |
0.000 |
|
MultiSource/Benchmarks/VersaBench/beamformer/beamformer
Profile
|
8.26% |
4.806 |
5.203 |
0.001 |
0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC128
|
8.23% |
160.158 |
173.334 |
0.003 |
-0.00% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint16_t_To_uint8_t_
|
8.01% |
6310.959 |
6816.253 |
11.407 |
0.01% |
11.407 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_xor_no_runtime_checks_needed<16, int>
|
7.99% |
15.645 |
16.896 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint8_t_To_uint32_t_
|
7.97% |
11834.177 |
12777.527 |
11.410 |
-0.01% |
11.410 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC127
|
7.83% |
63.830 |
68.826 |
0.006 |
0.00% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC128
|
7.81% |
63.847 |
68.830 |
0.003 |
-0.01% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint16_t>/28
|
7.77% |
113.320 |
122.127 |
0.121 |
0.40% |
0.121 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint8_t>/127
|
7.77% |
128.905 |
138.924 |
0.002 |
-0.00% |
0.002 |
|
SingleSource/Benchmarks/Misc/pi
Profile
|
7.54% |
1.658 |
1.783 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC15
|
7.45% |
41.931 |
45.053 |
0.002 |
0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC15
|
7.40% |
50.688 |
54.439 |
0.003 |
-0.01% |
0.003 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIRST_DIFF_RAW/5001
|
7.37% |
12.240 |
13.142 |
0.108 |
0.15% |
0.108 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_DEL_DOT_VEC_2D_RAW/0
|
7.35% |
1672.632 |
1795.512 |
3.250 |
-0.30% |
3.250 |
|
MultiSource/Benchmarks/McCat/12-IOtest/iotest
Profile
|
7.24% |
1.746 |
1.873 |
0.012 |
1.68% |
0.012 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint8_t>/51
|
7.22% |
126.402 |
135.526 |
0.542 |
15.19% |
0.542 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC31
|
7.20% |
69.463 |
74.466 |
0.006 |
0.00% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint16_t_To_uint64_t_
|
7.06% |
23338.080 |
24986.322 |
86.950 |
0.00% |
86.950 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC63
|
7.01% |
107.011 |
114.509 |
0.003 |
-0.00% |
0.003 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_HYDRO_2D_LAMBDA/171
|
6.99% |
82.913 |
88.708 |
0.406 |
0.06% |
0.406 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC7
|
6.89% |
30.441 |
32.538 |
0.003 |
-0.00% |
0.003 |
|
MicroBenchmarks/ImageProcessing/Dilate/Dilate.test:BENCHMARK_DILATE/1024
|
6.86% |
7006.972 |
7487.426 |
84.513 |
-0.13% |
84.513 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC63
|
6.82% |
69.464 |
74.200 |
0.241 |
-0.03% |
0.241 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC15
|
6.77% |
36.920 |
39.420 |
0.002 |
-0.01% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint16_t_To_uint64_t_
|
6.76% |
18884.337 |
20160.280 |
103.246 |
0.08% |
103.246 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_HYDRO_2D_RAW/171
|
6.74% |
83.344 |
88.958 |
0.143 |
0.37% |
0.143 |
|
SingleSource/Benchmarks/Misc/flops-6
Profile
|
6.72% |
1.229 |
1.311 |
0.001 |
-0.08% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint16_t>/127
|
6.71% |
130.173 |
138.907 |
0.007 |
-0.00% |
0.007 |
|
SingleSource/Benchmarks/Misc/oourafft
Profile
|
6.70% |
14.470 |
15.440 |
0.053 |
1.28% |
0.053 |
|
SingleSource/Benchmarks/Misc-C++/Large/sphereflake
Profile
|
6.56% |
18.777 |
20.008 |
0.006 |
-0.02% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC16
|
6.55% |
38.171 |
40.673 |
0.002 |
-0.00% |
0.002 |
|
External/SPEC/CFP2017rate/538.imagick_r/538.imagick_r
Profile
|
6.49% |
274.707 |
292.530 |
0.330 |
0.15% |
0.330 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC16
|
6.44% |
29.410 |
31.304 |
0.285 |
0.05% |
0.285 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_DEL_DOT_VEC_2D_LAMBDA/0
|
6.41% |
1691.555 |
1799.987 |
2.072 |
0.10% |
2.072 |
|
MultiSource/Benchmarks/MiBench/telecomm-gsm/telecomm-gsm
Profile
|
6.41% |
0.623 |
0.663 |
0.000 |
-0.03% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC127
|
6.39% |
182.919 |
194.604 |
0.005 |
-0.00% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint8_t>/65
|
6.29% |
89.485 |
95.111 |
0.011 |
0.00% |
0.011 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint16_t>/16
|
6.29% |
79.494 |
84.492 |
0.248 |
0.41% |
0.248 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint32_t>/127
|
6.25% |
130.155 |
138.283 |
0.004 |
-0.00% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint8_t>/28
|
6.10% |
85.104 |
90.299 |
0.994 |
10.14% |
0.994 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC16
|
6.00% |
31.287 |
33.164 |
0.002 |
0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint16_t>/51
|
6.00% |
103.364 |
109.565 |
0.126 |
0.06% |
0.126 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC64
|
5.99% |
41.299 |
43.774 |
0.014 |
-0.06% |
0.014 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC63
|
5.96% |
41.302 |
43.764 |
0.020 |
-0.06% |
0.020 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC32
|
5.96% |
41.925 |
44.425 |
0.002 |
-0.01% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC32
|
5.96% |
41.927 |
44.425 |
0.003 |
-0.01% |
0.003 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C++/miniFE/miniFE
Profile
|
5.95% |
14.915 |
15.802 |
0.076 |
-1.05% |
0.076 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC15
|
5.93% |
121.085 |
128.263 |
0.008 |
0.01% |
0.008 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC31
|
5.89% |
42.553 |
45.059 |
0.007 |
-0.01% |
0.007 |
|
MultiSource/Benchmarks/SciMark2-C/scimark2
Profile
|
5.88% |
101.754 |
107.735 |
0.022 |
0.04% |
0.022 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC31
|
5.87% |
42.550 |
45.049 |
0.002 |
-0.01% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint32_t>/999
|
5.85% |
1289.580 |
1365.010 |
0.165 |
-0.00% |
0.165 |
|
MultiSource/Benchmarks/Rodinia/hotspot/hotspot
Profile
|
5.82% |
1.925 |
2.037 |
0.002 |
0.01% |
0.002 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_DIFF_PREDICT_LAMBDA/171
|
5.78% |
11.194 |
11.841 |
0.249 |
-1.21% |
0.249 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint32_t>/999
|
5.68% |
658.998 |
696.460 |
0.065 |
-0.01% |
0.065 |
|
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 |
70.707 |
0.003 |
-0.02% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint8_t>/10
|
5.59% |
46.226 |
48.808 |
0.003 |
5.16% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC32
|
5.40% |
23.153 |
24.402 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC32
|
5.39% |
23.155 |
24.404 |
0.000 |
-0.01% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC31
|
5.38% |
23.155 |
24.401 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC31
|
5.36% |
23.163 |
24.404 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC8
|
5.35% |
25.656 |
27.030 |
0.089 |
0.01% |
0.089 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_only_autovec_int32_t_
|
5.32% |
171862.809 |
180999.729 |
145.150 |
-0.07% |
145.150 |
|
MultiSource/Benchmarks/TSVC/ControlLoops-dbl/ControlLoops-dbl
Profile
|
5.30% |
10.780 |
11.351 |
0.058 |
-0.29% |
0.058 |
|
MultiSource/Applications/lambda-0.1.3/lambda
Profile
|
5.17% |
15.098 |
15.877 |
0.014 |
0.05% |
0.014 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint32_t_To_uint64_t_
|
5.16% |
20264.715 |
21309.535 |
126.622 |
-0.66% |
126.622 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint16_t>/10
|
5.05% |
62.577 |
65.734 |
0.018 |
0.31% |
0.018 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint32_t>/256
|
5.04% |
346.690 |
364.168 |
0.013 |
-0.00% |
0.013 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC31
|
5.02% |
229.676 |
241.203 |
0.030 |
-0.01% |
0.030 |
|
SingleSource/Benchmarks/Misc/revertBits
Profile
|
4.87% |
0.611 |
0.641 |
0.000 |
-0.02% |
0.000 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_runtime_checks_pass<16, int>
|
4.81% |
51.943 |
54.443 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint16_t>/65
|
4.81% |
90.741 |
95.107 |
0.006 |
-0.01% |
0.006 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_runtime_checks_fail<16, int>
|
4.81% |
51.944 |
54.442 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC127
|
4.73% |
2296.889 |
2405.608 |
18.108 |
-0.87% |
18.108 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_PIC_2D_RAW/171
|
4.68% |
12.967 |
13.574 |
0.039 |
0.15% |
0.039 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC31
|
4.67% |
66.958 |
70.085 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_PIC_2D_LAMBDA/171
|
4.64% |
12.898 |
13.496 |
0.046 |
-0.01% |
0.046 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC3
|
4.55% |
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:benchAutoVecForBigLoopTC8
|
4.54% |
13.767 |
14.392 |
0.000 |
-0.01% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC2
|
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 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC3
|
4.54% |
13.767 |
14.392 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC4
|
4.54% |
13.767 |
14.392 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC2
|
4.54% |
13.766 |
14.391 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC8
|
4.54% |
13.767 |
14.392 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC16
|
4.54% |
13.767 |
14.392 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC1
|
4.53% |
13.767 |
14.391 |
0.003 |
-0.00% |
0.003 |
|
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 |
14.393 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC15
|
4.53% |
13.768 |
14.392 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC7
|
4.53% |
13.767 |
14.390 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC7
|
4.52% |
13.769 |
14.391 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint64_t>/999
|
4.44% |
3442.293 |
3595.011 |
0.191 |
0.00% |
0.191 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint64_t>/999
|
4.43% |
1734.480 |
1811.363 |
0.062 |
0.00% |
0.062 |
|
SingleSource/Benchmarks/Misc/flops-5
Profile
|
4.22% |
1.939 |
2.021 |
0.001 |
-0.02% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC31
|
4.20% |
59.446 |
61.945 |
0.003 |
-0.00% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint64_t>/256
|
4.20% |
897.838 |
935.535 |
0.023 |
-0.00% |
0.023 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_PRESSURE_CALC_LAMBDA/44217
|
4.17% |
483.653 |
503.820 |
1.416 |
-0.08% |
1.416 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC32
|
4.17% |
58.871 |
61.325 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC32
|
4.17% |
30.035 |
31.287 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_ENERGY_CALC_RAW/171
|
4.15% |
13.651 |
14.217 |
0.017 |
-0.17% |
0.017 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint64_t_To_uint8_t_
|
4.15% |
19038.240 |
19827.562 |
21.380 |
-0.07% |
21.380 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_only_autovec_uint8_t_
|
4.14% |
92348.779 |
96167.508 |
14.849 |
0.00% |
14.849 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint32_t>/65
|
4.13% |
90.736 |
94.485 |
0.006 |
-0.00% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint32_t>/256
|
4.12% |
212.758 |
221.514 |
0.019 |
0.01% |
0.019 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC32
|
4.11% |
60.700 |
63.196 |
0.003 |
-0.00% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint32_t_To_uint16_t_
|
4.10% |
9460.434 |
9847.859 |
7.404 |
-0.32% |
7.404 |
|
SingleSource/Benchmarks/Polybench/stencils/jacobi-2d/jacobi-2d
Profile
|
4.01% |
30.742 |
31.976 |
0.173 |
-0.77% |
0.173 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_only_novec_uint8_t_
|
3.98% |
404341.180 |
420424.773 |
31.678 |
6.20% |
31.678 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC31
|
3.97% |
90.111 |
93.688 |
0.080 |
-0.18% |
0.080 |
|
MultiSource/Benchmarks/VersaBench/ecbdes/ecbdes
Profile
|
3.92% |
4.947 |
5.141 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC32
|
3.88% |
48.183 |
50.055 |
0.003 |
0.01% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_cond_load_autovec_int64_t_
|
3.88% |
532402.417 |
553043.881 |
213.639 |
0.01% |
213.639 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint8_t_To_uint64_t_
|
3.82% |
22517.532 |
23377.798 |
63.797 |
-0.45% |
63.797 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<31, EqZero, First>
|
3.81% |
3223.224 |
3346.058 |
0.253 |
-0.01% |
0.253 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_ENERGY_CALC_LAMBDA/171
|
3.80% |
13.664 |
14.184 |
0.028 |
-0.45% |
0.028 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint64_t>/256
|
3.78% |
495.638 |
514.367 |
0.040 |
-0.01% |
0.040 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC31
|
3.78% |
30.036 |
31.170 |
0.052 |
-0.06% |
0.052 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint8_t_To_uint16_t_
|
3.76% |
3500.050 |
3631.502 |
13.579 |
-0.05% |
13.579 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint64_t_To_uint32_t_
|
3.74% |
18685.726 |
19384.021 |
19.345 |
-0.11% |
19.345 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC64
|
3.73% |
66.956 |
69.457 |
0.005 |
0.00% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC64
|
3.73% |
66.961 |
69.456 |
0.003 |
-0.01% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC63
|
3.71% |
67.583 |
70.090 |
0.004 |
-0.00% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC63
|
3.70% |
67.582 |
70.085 |
0.001 |
-0.00% |
0.001 |
|
SingleSource/Benchmarks/BenchmarkGame/n-body
Profile
|
3.69% |
2.634 |
2.731 |
0.000 |
26.22% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint16_t>/999
|
3.56% |
978.918 |
1013.718 |
0.057 |
-0.01% |
0.057 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC31
|
3.45% |
58.199 |
60.206 |
0.111 |
-0.12% |
0.111 |
|
SingleSource/Benchmarks/Shootout/Shootout-lists
Profile
|
3.29% |
10.955 |
11.315 |
0.001 |
-0.00% |
0.001 |
|
External/SPEC/CFP2017rate/544.nab_r/544.nab_r
Profile
|
3.28% |
460.935 |
476.070 |
0.299 |
-0.38% |
0.299 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint16_t>/999
|
3.26% |
498.743 |
515.000 |
0.019 |
-0.00% |
0.019 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint8_t>/16
|
3.23% |
62.584 |
64.608 |
0.133 |
5.30% |
0.133 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1BigLoopWithReductionTC1
|
3.22% |
19.400 |
20.025 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC7
|
3.19% |
344.171 |
355.158 |
3.575 |
0.13% |
3.575 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchVecWithRuntimeChecks4PointersDBeforeA/1000
|
3.17% |
4866336.215 |
5020362.993 |
343.553 |
-0.00% |
343.553 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint8_t>/10
|
3.13% |
69.465 |
71.636 |
0.597 |
1.30% |
0.597 |
|
MultiSource/Benchmarks/TSVC/Symbolics-flt/Symbolics-flt
Profile
|
3.03% |
4.761 |
4.905 |
0.018 |
0.85% |
0.018 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_acosf_novec_float_
|
2.93% |
820.929 |
844.979 |
0.156 |
-0.00% |
0.156 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_acosf_autovec_float_
|
2.89% |
821.018 |
844.724 |
0.184 |
-0.01% |
0.184 |
|
MultiSource/Benchmarks/BitBench/drop3/drop3
Profile
|
2.87% |
0.711 |
0.732 |
0.000 |
0.05% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC1
|
2.85% |
21.901 |
22.526 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC1
|
2.82% |
21.908 |
22.526 |
0.003 |
0.00% |
0.003 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C/CoMD/CoMD
Profile
|
2.72% |
9.641 |
9.904 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<32, EqZero, Last>
|
2.70% |
6941.080 |
7128.503 |
31.692 |
-0.80% |
31.692 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint16_t_To_uint32_t_
|
2.68% |
10967.246 |
11260.864 |
68.982 |
-0.72% |
68.982 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC63
|
2.67% |
117.021 |
120.143 |
0.002 |
-0.00% |
0.002 |
|
MultiSource/Applications/JM/lencod/lencod
Profile
|
2.61% |
31.898 |
32.732 |
0.010 |
0.51% |
0.010 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint16_t_To_uint8_t_
|
2.61% |
2807.751 |
2881.159 |
12.842 |
-0.10% |
12.842 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint8_t_To_uint32_t_
|
2.56% |
6901.629 |
7078.288 |
0.207 |
-0.00% |
0.207 |
|
MultiSource/Benchmarks/Ptrdist/yacr2/yacr2
Profile
|
2.53% |
2.026 |
2.078 |
0.001 |
0.08% |
0.001 |
|
SingleSource/Benchmarks/Misc-C++/oopack_v1p8
Profile
|
2.51% |
0.468 |
0.480 |
0.000 |
-7.58% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint32_t>/10
|
2.44% |
56.441 |
57.818 |
0.015 |
0.31% |
0.015 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC63
|
2.40% |
104.502 |
107.008 |
0.004 |
0.00% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint8_t>/10
|
2.38% |
52.342 |
53.590 |
0.390 |
3.17% |
0.390 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<31, GreaterThanZero, Last>
|
2.37% |
8149.968 |
8343.020 |
8.881 |
-0.26% |
8.881 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint16_t>/16
|
2.36% |
52.576 |
53.815 |
0.001 |
0.56% |
0.001 |
|
SingleSource/Benchmarks/Misc-C++/Large/ray
Profile
|
2.31% |
11.831 |
12.104 |
0.001 |
0.02% |
0.001 |
|
SingleSource/Benchmarks/Shootout/Shootout-matrix
Profile
|
2.28% |
3.777 |
3.864 |
0.000 |
0.01% |
0.000 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<16, EqZero, None>
|
2.26% |
8021.674 |
8203.325 |
37.485 |
0.02% |
37.485 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint16_t>/10
|
2.26% |
45.193 |
46.213 |
0.009 |
0.81% |
0.009 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchVecWithRuntimeChecks4PointersDBeforeA/32
|
2.25% |
162540.603 |
166192.448 |
6.011 |
-0.01% |
6.011 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint64_t>/51
|
2.24% |
224.018 |
229.027 |
0.004 |
-0.00% |
0.004 |
|
SingleSource/Benchmarks/Misc/flops-1
Profile
|
2.21% |
8.807 |
9.002 |
0.000 |
0.01% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC64
|
2.19% |
109.001 |
111.385 |
0.007 |
0.00% |
0.007 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_PRESSURE_CALC_RAW/44217
|
2.18% |
491.150 |
501.833 |
2.904 |
-0.07% |
2.904 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC127
|
2.13% |
117.645 |
120.151 |
0.013 |
-0.00% |
0.013 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC128
|
2.13% |
117.025 |
119.516 |
0.005 |
-0.00% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC128
|
2.12% |
117.026 |
119.512 |
0.009 |
-0.01% |
0.009 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC127
|
2.11% |
117.660 |
120.143 |
0.005 |
0.00% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint16_t_To_uint8_t_
|
2.06% |
4429.870 |
4521.284 |
11.311 |
0.07% |
11.311 |
|
External/SPEC/CFP2017rate/511.povray_r/511.povray_r
Profile
|
2.03% |
33.446 |
34.124 |
0.052 |
0.93% |
0.052 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_EOS_RAW/171
|
1.88% |
0.856 |
0.873 |
0.001 |
-0.04% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint16_t>/256
|
1.85% |
267.877 |
272.824 |
0.012 |
-0.01% |
0.012 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<16, EqZero, Mid>
|
1.83% |
8501.490 |
8656.791 |
27.986 |
-0.01% |
27.986 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_INT_PREDICT_RAW/171
|
1.79% |
6.803 |
6.925 |
0.003 |
0.00% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint32_t_To_uint64_t_
|
1.76% |
25943.732 |
26400.979 |
60.191 |
0.17% |
60.191 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_EOS_LAMBDA/171
|
1.75% |
0.857 |
0.872 |
0.002 |
-0.05% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint64_t>/51
|
1.71% |
145.802 |
148.296 |
0.004 |
-0.01% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_csa_with_in_loop_arith_novec_int64_t_
|
1.69% |
1012990.227 |
1030137.636 |
151.107 |
-0.04% |
151.107 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_erf_novec_double_
|
1.64% |
874.880 |
889.186 |
1.131 |
-0.02% |
1.131 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_erf_autovec_double_
|
1.59% |
875.165 |
889.072 |
1.158 |
-0.00% |
1.158 |
|
SingleSource/Benchmarks/Misc/mandel-2
Profile
|
1.58% |
2.496 |
2.536 |
0.000 |
0.01% |
0.000 |
|
MultiSource/Benchmarks/mafft/pairlocalalign
Profile
|
1.57% |
92.468 |
93.919 |
0.329 |
-0.15% |
0.329 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC63
|
1.56% |
127.662 |
129.647 |
0.214 |
-0.40% |
0.214 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<32, LessThanZero, Mid>
|
1.55% |
4501.161 |
4570.806 |
9.595 |
-0.00% |
9.595 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_FLOYD_DITHER/512
|
1.48% |
6551.752 |
6648.946 |
4.255 |
0.06% |
4.255 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<16, GreaterThanZero, First>
|
1.46% |
8503.091 |
8627.377 |
5.169 |
0.17% |
5.169 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint32_t>/28
|
1.44% |
71.492 |
72.524 |
0.003 |
-0.28% |
0.003 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_FLOYD_DITHER/128
|
1.43% |
432.962 |
439.164 |
0.772 |
-0.07% |
0.772 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<6, LessThanZero, Mid>
|
1.41% |
23486.878 |
23818.540 |
30.795 |
0.04% |
30.795 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<8, LessThanZero, Mid>
|
1.41% |
19230.780 |
19501.799 |
4.968 |
-0.03% |
4.968 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_csa_with_cond_arith_novec_int64_t_
|
1.38% |
735267.747 |
745414.560 |
2801.434 |
0.09% |
2801.434 |
|
SingleSource/Benchmarks/Misc/ReedSolomon
Profile
|
1.35% |
20.314 |
20.587 |
0.003 |
-1.01% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_csa_with_cond_arith_autovec_int64_t_
|
1.34% |
735512.153 |
745347.575 |
778.463 |
0.06% |
778.463 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC128
|
1.28% |
195.859 |
198.362 |
0.007 |
-0.00% |
0.007 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC127
|
1.27% |
194.627 |
197.101 |
0.004 |
0.00% |
0.004 |
|
MultiSource/Benchmarks/MallocBench/cfrac/cfrac
Profile
|
1.26% |
2.745 |
2.779 |
0.000 |
-0.03% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint32_t>/51
|
1.23% |
77.036 |
77.983 |
0.010 |
-0.54% |
0.010 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint16_t_To_uint32_t_
|
1.22% |
13365.498 |
13529.169 |
10.852 |
0.03% |
10.852 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_INT_PREDICT_LAMBDA/171
|
1.21% |
6.833 |
6.916 |
0.004 |
-0.13% |
0.004 |
|
MultiSource/Benchmarks/Olden/health/health
Profile
|
1.17% |
1.576 |
1.595 |
0.002 |
0.10% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopFrom_uint64_t_To_uint16_t_
|
1.15% |
14694.241 |
14863.551 |
30.577 |
0.19% |
30.577 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_nested_cond_load_novec_uint8_t_
|
1.15% |
499041.933 |
504787.042 |
222.292 |
0.01% |
222.292 |
|
External/SPEC/CINT2017rate/525.x264_r/525.x264_r
Profile
|
1.14% |
128.142 |
129.604 |
0.117 |
-0.01% |
0.117 |
|
MultiSource/Benchmarks/nbench/nbench
Profile
|
1.14% |
6.037 |
6.106 |
0.001 |
-0.34% |
0.001 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, LessThanZero, None>
|
1.13% |
37153.707 |
37575.346 |
72.790 |
-0.00% |
72.790 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<7, EqZero, None>
|
1.12% |
26875.358 |
27176.367 |
6.588 |
-0.02% |
6.588 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_nested_cond_load_novec_int32_t_
|
1.11% |
642702.280 |
649831.896 |
751.966 |
0.59% |
751.966 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint32_t>/51
|
1.07% |
117.013 |
118.261 |
0.014 |
-0.00% |
0.014 |