|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_INT_PREDICT_LAMBDA/44217
|
134.98% |
8181.663 |
19225.077 |
213.272 |
-0.32% |
213.272 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint64_t_To_uint32_t_
|
100.23% |
17974.174 |
35989.274 |
175.390 |
0.83% |
175.390 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint64_t_To_uint8_t_
|
92.96% |
19057.832 |
36773.394 |
145.000 |
1.29% |
145.000 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C/miniGMG/miniGMG
Profile
|
90.54% |
5.084 |
9.687 |
0.012 |
2.44% |
0.012 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint16_t_To_uint64_t_
|
78.41% |
10451.346 |
18646.178 |
180.107 |
-1.13% |
180.107 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint64_t_To_uint16_t_
|
77.27% |
21986.288 |
38974.605 |
43.105 |
9.56% |
43.105 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_DIFF_PREDICT_LAMBDA/44217
|
71.40% |
14170.408 |
24288.336 |
1366.885 |
0.88% |
1366.885 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint64_t_To_uint32_t_
|
70.10% |
22695.699 |
38605.334 |
136.106 |
2.26% |
136.106 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint8_t_To_uint64_t_
|
69.84% |
10547.034 |
17913.382 |
335.608 |
-0.02% |
335.608 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIRST_DIFF_LAMBDA/44217
|
67.38% |
105.410 |
176.435 |
2.831 |
2.37% |
2.831 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_DIFF_PREDICT_RAW/44217
|
64.95% |
14124.961 |
23299.369 |
1312.071 |
0.20% |
1312.071 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint32_t_To_uint64_t_
|
60.62% |
15584.476 |
25032.491 |
397.657 |
8.40% |
397.657 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_DIFF_PREDICT_RAW/5001
|
60.61% |
1573.336 |
2526.959 |
146.661 |
-0.68% |
146.661 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_DIFF_PREDICT_LAMBDA/5001
|
60.16% |
1585.188 |
2538.865 |
150.671 |
-0.40% |
150.671 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/32
|
59.38% |
884.022 |
1408.910 |
0.123 |
-0.00% |
0.123 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/16
|
59.24% |
177.158 |
282.105 |
0.026 |
-0.00% |
0.026 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/64
|
59.18% |
3917.451 |
6235.948 |
0.690 |
-0.00% |
0.690 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/256
|
57.85% |
68424.250 |
108006.653 |
16.705 |
0.05% |
16.705 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/128
|
57.32% |
16819.139 |
26459.377 |
7.479 |
0.03% |
7.479 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint64_t_To_uint16_t_
|
52.70% |
19126.799 |
29207.222 |
168.543 |
-0.09% |
168.543 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint64_t_To_uint8_t_
|
51.05% |
19835.171 |
29961.872 |
45.310 |
-0.34% |
45.310 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_HYDRO_2D_LAMBDA/44217
|
50.59% |
59252.448 |
89229.041 |
3365.174 |
-1.89% |
3365.174 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, EqZero, None>
|
45.41% |
14105.894 |
20511.096 |
0.173 |
-0.00% |
0.173 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_HYDRO_2D_LAMBDA/5001
|
43.33% |
6502.194 |
9319.914 |
473.351 |
-0.30% |
473.351 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIRST_DIFF_RAW/44217
|
43.08% |
104.821 |
149.981 |
15.594 |
3.02% |
15.594 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint32_t_To_uint8_t_
|
40.41% |
9836.282 |
13810.985 |
5.596 |
2.85% |
5.596 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint64_t_To_uint16_t_
|
37.38% |
18531.843 |
25459.367 |
10.732 |
-1.88% |
10.732 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC128
|
36.86% |
943.826 |
1291.679 |
4.576 |
-0.42% |
4.576 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC128
|
36.49% |
407.803 |
556.607 |
0.372 |
-0.33% |
0.372 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC64
|
35.50% |
482.284 |
653.480 |
1.003 |
-0.51% |
1.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC32
|
35.39% |
246.655 |
333.952 |
0.362 |
-0.61% |
0.362 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_PIC_2D_LAMBDA/44217
|
34.81% |
8832.601 |
11906.838 |
29.500 |
-0.12% |
29.500 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC16
|
34.10% |
129.583 |
173.775 |
0.232 |
-0.93% |
0.232 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC64
|
34.04% |
217.292 |
291.262 |
0.408 |
-0.10% |
0.408 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, EqZero, None>
|
31.55% |
12181.501 |
16024.207 |
0.375 |
-0.00% |
0.375 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint32_t_To_uint8_t_
|
31.35% |
11366.365 |
14929.308 |
45.310 |
5.08% |
45.310 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC128
|
30.20% |
463.830 |
603.911 |
0.042 |
0.20% |
0.042 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC128
|
30.02% |
464.464 |
603.911 |
0.062 |
-0.01% |
0.062 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC32
|
29.96% |
122.238 |
158.864 |
0.035 |
-0.06% |
0.035 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint16_t_To_uint64_t_
|
29.43% |
10363.976 |
13414.536 |
23.856 |
-0.48% |
23.856 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint64_t_To_uint8_t_
|
29.01% |
20616.514 |
26596.760 |
14.158 |
-3.93% |
14.158 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC64
|
28.76% |
243.459 |
313.478 |
0.018 |
0.38% |
0.018 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC127
|
28.47% |
478.852 |
615.177 |
0.064 |
0.09% |
0.064 |
|
SingleSource/Benchmarks/Adobe-C++/loop_unroll
Profile
|
28.43% |
2.426 |
3.115 |
0.028 |
-23.22% |
0.028 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC64
|
28.42% |
244.109 |
313.491 |
0.013 |
-0.01% |
0.013 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC127
|
28.15% |
480.098 |
615.239 |
0.008 |
0.00% |
0.008 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint8_t_To_uint32_t_
|
27.49% |
5178.341 |
6602.000 |
220.258 |
-0.34% |
220.258 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint16_t_To_uint32_t_
|
27.21% |
5587.496 |
7108.018 |
98.478 |
-0.05% |
98.478 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIND_FIRST_MIN_LAMBDA/171
|
26.92% |
1.182 |
1.500 |
0.000 |
-0.03% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIND_FIRST_MIN_LAMBDA/44217
|
26.61% |
307.851 |
389.767 |
0.147 |
0.05% |
0.147 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIRST_SUM_LAMBDA/44217
|
26.36% |
137.782 |
174.095 |
4.886 |
-4.44% |
4.886 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC32
|
26.28% |
133.294 |
168.319 |
0.005 |
0.74% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC32
|
25.68% |
133.930 |
168.317 |
0.006 |
0.00% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC63
|
25.63% |
258.506 |
324.765 |
0.011 |
0.17% |
0.011 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIND_FIRST_MIN_LAMBDA/5001
|
25.62% |
35.972 |
45.187 |
0.207 |
0.44% |
0.207 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC63
|
25.04% |
259.743 |
324.775 |
0.009 |
-0.00% |
0.009 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC127
|
24.57% |
220.073 |
274.142 |
1.033 |
3.58% |
1.033 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC128
|
24.52% |
219.721 |
273.586 |
0.513 |
3.59% |
0.513 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC127
|
24.50% |
514.743 |
640.863 |
0.187 |
-0.03% |
0.187 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC16
|
23.92% |
74.477 |
92.291 |
0.019 |
-0.01% |
0.019 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_DISC_ORD_LAMBDA/44217
|
23.80% |
11519.602 |
14261.074 |
482.430 |
0.61% |
482.430 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint64_t_To_uint32_t_
|
23.12% |
22093.580 |
27201.983 |
23.030 |
0.32% |
23.030 |
|
MultiSource/Benchmarks/TSVC/Searching-flt/Searching-flt
Profile
|
22.95% |
4.144 |
5.095 |
0.003 |
2.83% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC16
|
22.35% |
78.241 |
95.730 |
0.003 |
1.31% |
0.003 |
|
MultiSource/Benchmarks/Trimaran/enc-pc1/enc-pc1
Profile
|
22.07% |
0.905 |
1.104 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint16_t_To_uint8_t_
|
22.06% |
3090.834 |
3772.691 |
0.333 |
-0.59% |
0.333 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_PIC_1D_LAMBDA/44217
|
22.02% |
11068.475 |
13505.885 |
98.481 |
-0.11% |
98.481 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC16
|
21.41% |
78.850 |
95.732 |
0.002 |
-0.01% |
0.002 |
|
MultiSource/Benchmarks/MiBench/automotive-bitcount/automotive-bitcount
Profile
|
21.25% |
0.102 |
0.124 |
0.000 |
-26.31% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIRST_SUM_RAW/44217
|
21.24% |
135.755 |
164.588 |
8.877 |
1.56% |
8.877 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint8_t_To_uint64_t_
|
21.19% |
10919.557 |
13233.387 |
341.553 |
3.53% |
341.553 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC31
|
21.09% |
148.309 |
179.581 |
0.007 |
0.34% |
0.007 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC128
|
20.82% |
472.333 |
570.667 |
0.049 |
0.19% |
0.049 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC4
|
20.76% |
14.508 |
17.520 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC64
|
20.61% |
246.903 |
297.798 |
0.029 |
0.39% |
0.029 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC31
|
20.07% |
149.569 |
179.584 |
0.005 |
-0.00% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC32
|
20.04% |
134.214 |
161.115 |
0.146 |
0.58% |
0.146 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint32_t_To_uint16_t_
|
20.01% |
11152.994 |
13384.271 |
82.675 |
0.05% |
82.675 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC64
|
19.91% |
123.452 |
148.031 |
1.698 |
3.33% |
1.698 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC16
|
19.26% |
77.928 |
92.934 |
0.129 |
1.04% |
0.129 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_HYDRO_1D_LAMBDA/171
|
19.24% |
0.372 |
0.443 |
0.001 |
0.03% |
0.001 |
|
External/SPEC/CFP2017rate/538.imagick_r/538.imagick_r
Profile
|
18.95% |
275.281 |
327.455 |
0.322 |
11.74% |
0.322 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_HYDRO_1D_RAW/171
|
18.73% |
0.372 |
0.441 |
0.002 |
-0.07% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint32_t_To_uint16_t_
|
18.59% |
11263.671 |
13357.716 |
46.338 |
-3.69% |
46.338 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint16_t_To_uint32_t_
|
18.44% |
6295.542 |
7456.288 |
0.111 |
-0.01% |
0.111 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, EqZero, First>
|
18.18% |
14105.555 |
16670.139 |
0.365 |
-0.00% |
0.365 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC8
|
18.17% |
49.750 |
58.790 |
0.013 |
2.12% |
0.013 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_no_runtime_checks_needed<16, int>
|
18.17% |
20.651 |
24.403 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, EqZero, Mid>
|
18.15% |
14105.756 |
16665.868 |
0.627 |
-0.01% |
0.627 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, EqZero, Last>
|
18.10% |
14111.659 |
16666.505 |
0.529 |
0.00% |
0.529 |
|
MultiSource/Benchmarks/TSVC/Searching-dbl/Searching-dbl
Profile
|
17.72% |
7.755 |
9.129 |
0.025 |
0.07% |
0.025 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_PIC_2D_LAMBDA/5001
|
17.55% |
987.446 |
1160.774 |
39.176 |
-2.76% |
39.176 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC127
|
17.37% |
516.140 |
605.787 |
0.010 |
0.09% |
0.010 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC8
|
17.27% |
50.687 |
59.443 |
0.002 |
2.14% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC128
|
17.04% |
942.678 |
1103.344 |
0.055 |
-17.35% |
0.055 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_VOL3D_CALC_RAW/2
|
16.99% |
7.111 |
8.320 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_VOL3D_CALC_LAMBDA/2
|
16.99% |
7.111 |
8.319 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC127
|
16.98% |
936.384 |
1095.400 |
0.379 |
-17.13% |
0.379 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC64
|
16.67% |
481.896 |
562.216 |
0.164 |
-16.58% |
0.164 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC63
|
16.57% |
475.650 |
554.465 |
0.049 |
-16.09% |
0.049 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC63
|
16.54% |
127.740 |
148.872 |
3.278 |
3.70% |
3.278 |
|
SingleSource/Benchmarks/Misc/salsa20
Profile
|
16.42% |
13.213 |
15.382 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint32_t_To_uint8_t_
|
16.12% |
9146.567 |
10621.428 |
143.340 |
-1.43% |
143.340 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC1
|
16.07% |
44.743 |
51.935 |
0.001 |
5.06% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC2
|
16.07% |
44.744 |
51.934 |
0.003 |
5.05% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC7
|
16.07% |
44.743 |
51.933 |
0.001 |
5.06% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC4
|
16.06% |
44.745 |
51.934 |
0.001 |
5.06% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC3
|
16.06% |
44.747 |
51.933 |
0.002 |
5.05% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC8
|
16.06% |
44.749 |
51.936 |
0.009 |
4.91% |
0.009 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC8
|
15.82% |
51.322 |
59.442 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint8_t_To_uint16_t_
|
15.82% |
3244.916 |
3758.239 |
0.239 |
-0.00% |
0.239 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, EqZero, First>
|
15.77% |
12182.256 |
14103.590 |
0.254 |
0.00% |
0.254 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, EqZero, Mid>
|
15.76% |
12182.916 |
14103.355 |
0.223 |
-0.00% |
0.223 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, EqZero, Last>
|
15.74% |
12184.835 |
14103.265 |
0.263 |
0.00% |
0.263 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC31
|
15.73% |
245.362 |
283.954 |
0.142 |
-14.06% |
0.142 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC32
|
15.71% |
251.575 |
291.106 |
0.503 |
-15.21% |
0.503 |
|
External/SPEC/CFP2017rate/508.namd_r/508.namd_r
Profile
|
15.64% |
193.588 |
223.867 |
0.541 |
1.46% |
0.541 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC8
|
15.61% |
20.025 |
23.151 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC63
|
15.43% |
324.345 |
374.382 |
0.070 |
0.02% |
0.070 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC8
|
15.14% |
20.651 |
23.777 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint32_t_To_uint8_t_
|
15.07% |
9787.896 |
11262.904 |
16.696 |
0.57% |
16.696 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC128
|
15.01% |
70.724 |
81.342 |
0.002 |
0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC16
|
14.95% |
136.426 |
156.816 |
0.103 |
-11.98% |
0.103 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint8_t_To_uint16_t_
|
14.77% |
3954.749 |
4538.986 |
0.348 |
-0.01% |
0.348 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_VOL3D_CALC_LAMBDA/0
|
14.75% |
1065.278 |
1222.415 |
2.332 |
-0.57% |
2.332 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC15
|
14.73% |
93.257 |
106.996 |
0.003 |
0.59% |
0.003 |
|
MultiSource/Benchmarks/MiBench/security-rijndael/security-rijndael
Profile
|
14.50% |
0.293 |
0.336 |
0.001 |
7.13% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC63
|
14.49% |
290.702 |
332.831 |
0.219 |
0.16% |
0.219 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_VOL3D_CALC_RAW/0
|
14.34% |
1065.398 |
1218.171 |
1.919 |
-0.39% |
1.919 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_VOL3D_CALC_LAMBDA/1
|
14.21% |
218.645 |
249.716 |
0.034 |
0.10% |
0.034 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint16_t_To_uint8_t_
|
14.21% |
4155.447 |
4745.866 |
0.502 |
-0.59% |
0.502 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_VOL3D_CALC_RAW/1
|
14.10% |
218.641 |
249.464 |
0.148 |
0.03% |
0.148 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC15
|
14.07% |
130.164 |
148.476 |
0.217 |
-9.84% |
0.217 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopFrom_uint32_t_To_uint64_t_
|
14.03% |
14377.862 |
16395.661 |
332.723 |
5.35% |
332.723 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC4
|
13.80% |
98.684 |
112.301 |
2.339 |
-0.86% |
2.339 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint64_t_To_uint8_t_
|
13.52% |
19043.586 |
21618.363 |
39.490 |
0.13% |
39.490 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC2
|
13.31% |
18.776 |
21.274 |
0.000 |
30.77% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint64_t_To_uint16_t_
|
13.29% |
18602.228 |
21075.040 |
144.078 |
10.47% |
144.078 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC15
|
13.22% |
94.500 |
106.996 |
0.000 |
-0.53% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC8
|
13.20% |
78.849 |
89.259 |
0.098 |
-6.76% |
0.098 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC16
|
12.91% |
45.995 |
51.934 |
0.005 |
5.05% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC15
|
12.90% |
46.000 |
51.934 |
0.001 |
5.05% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_HYDRO_1D_LAMBDA/5001
|
12.86% |
16.163 |
18.241 |
0.293 |
-0.35% |
0.293 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint32_t_To_uint16_t_
|
12.82% |
9434.473 |
10644.339 |
360.078 |
-1.46% |
360.078 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC16
|
12.77% |
29.407 |
33.163 |
0.002 |
0.00% |
0.002 |
|
MicroBenchmarks/ImageProcessing/Dilate/Dilate.test:BENCHMARK_DILATE/1024
|
12.56% |
6687.548 |
7527.606 |
90.490 |
0.10% |
90.490 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC4
|
12.50% |
20.024 |
22.527 |
0.001 |
0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC3
|
12.48% |
20.026 |
22.526 |
0.000 |
28.56% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC4
|
12.48% |
20.027 |
22.525 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC31
|
12.13% |
76.338 |
85.596 |
0.847 |
3.48% |
0.847 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC7
|
11.97% |
72.595 |
81.282 |
0.031 |
-1.43% |
0.031 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC4
|
11.85% |
36.923 |
41.297 |
0.001 |
3.12% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC4
|
11.75% |
21.276 |
23.776 |
0.001 |
46.57% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC64
|
11.67% |
48.187 |
53.809 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/16
|
11.30% |
103.736 |
115.463 |
0.009 |
0.19% |
0.009 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC32
|
11.13% |
76.339 |
84.834 |
1.141 |
3.72% |
1.141 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/32
|
11.08% |
425.800 |
472.992 |
0.038 |
0.07% |
0.038 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC127
|
11.08% |
91.992 |
102.181 |
0.113 |
0.80% |
0.113 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/64
|
11.05% |
1723.346 |
1913.727 |
0.981 |
-0.03% |
0.981 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC4
|
11.04% |
50.064 |
55.593 |
0.046 |
1.86% |
0.046 |
|
SingleSource/Benchmarks/Misc-C++/oopack_v1p8
Profile
|
11.02% |
0.467 |
0.519 |
0.000 |
0.01% |
0.000 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/256
|
10.83% |
28369.667 |
31441.638 |
20.148 |
-0.00% |
20.148 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC8
|
10.80% |
23.155 |
25.654 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC8
|
10.79% |
23.155 |
25.654 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/128
|
10.73% |
7147.812 |
7914.713 |
4.951 |
0.02% |
4.951 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC7
|
10.62% |
29.412 |
32.537 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC7
|
10.51% |
23.780 |
26.280 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC7
|
10.51% |
23.781 |
26.279 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC32
|
10.39% |
48.181 |
53.185 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC31
|
10.31% |
178.042 |
196.392 |
0.039 |
0.26% |
0.039 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_DEL_DOT_VEC_2D_RAW/1
|
10.02% |
260.818 |
286.961 |
0.085 |
-0.04% |
0.085 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_DEL_DOT_VEC_2D_LAMBDA/1
|
10.01% |
260.938 |
287.045 |
0.074 |
-0.04% |
0.074 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC4
|
9.99% |
37.546 |
41.297 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC7
|
9.73% |
25.659 |
28.156 |
0.001 |
24.99% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC8
|
9.68% |
24.406 |
26.767 |
0.160 |
6.95% |
0.160 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIRST_SUM_LAMBDA/5001
|
9.63% |
18.682 |
20.481 |
0.062 |
-1.68% |
0.062 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_DEL_DOT_VEC_2D_RAW/2
|
9.52% |
3.205 |
3.510 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_DEL_DOT_VEC_2D_LAMBDA/2
|
9.52% |
3.205 |
3.510 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_PRESSURE_CALC_RAW/5001
|
9.51% |
42.534 |
46.580 |
1.102 |
-0.71% |
1.102 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC16
|
9.41% |
33.170 |
36.292 |
0.003 |
-1.71% |
0.003 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_DIFF_PREDICT_LAMBDA/171
|
9.34% |
11.296 |
12.350 |
0.023 |
-0.23% |
0.023 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_runtime_checks_fail<4, int>
|
9.32% |
15.331 |
16.760 |
0.030 |
0.12% |
0.030 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC8
|
9.28% |
26.910 |
29.408 |
0.001 |
23.10% |
0.001 |
|
MultiSource/Benchmarks/FreeBench/pifft/pifft
Profile
|
9.23% |
0.329 |
0.359 |
0.000 |
0.28% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint8_t_To_uint16_t_
|
9.17% |
5267.504 |
5750.476 |
0.681 |
-0.80% |
0.681 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC2
|
8.91% |
35.045 |
38.169 |
0.001 |
35.52% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC64
|
8.75% |
85.732 |
93.233 |
0.001 |
-0.00% |
0.001 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C++/miniFE/miniFE
Profile
|
8.56% |
15.143 |
16.439 |
0.106 |
-1.60% |
0.106 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC3
|
8.55% |
43.813 |
47.557 |
0.002 |
15.14% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC16
|
8.49% |
29.414 |
31.911 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC16
|
8.49% |
29.416 |
31.912 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC32
|
8.45% |
36.925 |
40.044 |
0.003 |
-0.00% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC15
|
8.31% |
30.041 |
32.536 |
0.002 |
-0.01% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC15
|
8.30% |
30.042 |
32.536 |
0.001 |
0.00% |
0.001 |
|
MultiSource/Benchmarks/VersaBench/beamformer/beamformer
Profile
|
8.21% |
4.806 |
5.200 |
0.000 |
35.04% |
0.000 |
|
MultiSource/Benchmarks/Trimaran/enc-md5/enc-md5
Profile
|
8.09% |
3.243 |
3.506 |
0.001 |
-0.02% |
0.001 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_xor_no_runtime_checks_needed<16, int>
|
7.99% |
15.645 |
16.895 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_DEL_DOT_VEC_2D_RAW/0
|
7.79% |
1670.960 |
1801.150 |
9.879 |
-0.02% |
9.879 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC128
|
7.78% |
160.824 |
173.335 |
0.005 |
0.00% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint8_t>/127
|
7.75% |
128.921 |
138.910 |
0.003 |
0.00% |
0.003 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIND_FIRST_MIN_RAW/171
|
7.74% |
1.389 |
1.497 |
0.000 |
-0.04% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_HYDRO_2D_LAMBDA/171
|
7.68% |
82.308 |
88.632 |
0.318 |
-0.35% |
0.318 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC7
|
7.60% |
65.711 |
70.705 |
0.001 |
0.88% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint16_t_To_uint8_t_
|
7.59% |
6252.107 |
6726.749 |
0.713 |
-0.69% |
0.713 |
|
SingleSource/Benchmarks/Misc/pi
Profile
|
7.52% |
1.657 |
1.782 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_DEL_DOT_VEC_2D_LAMBDA/0
|
7.40% |
1669.797 |
1793.416 |
9.346 |
-0.33% |
9.346 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC15
|
7.39% |
50.691 |
54.437 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC15
|
7.29% |
41.990 |
45.051 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC31
|
7.19% |
69.462 |
74.458 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_xor_runtime_checks_pass<16, int>
|
6.97% |
26.907 |
28.783 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_xor_runtime_checks_fail<16, int>
|
6.96% |
26.910 |
28.782 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC63
|
6.89% |
107.127 |
114.504 |
0.006 |
-0.00% |
0.006 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_HYDRO_2D_RAW/171
|
6.86% |
83.025 |
88.718 |
0.327 |
-0.36% |
0.327 |
|
SingleSource/Benchmarks/Misc/flops-6
Profile
|
6.86% |
1.229 |
1.313 |
0.001 |
1.41% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC63
|
6.77% |
69.475 |
74.179 |
0.215 |
0.46% |
0.215 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC15
|
6.76% |
36.922 |
39.420 |
0.000 |
21.15% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_BAND_LIN_EQ_RAW/171
|
6.74% |
0.343 |
0.366 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_BAND_LIN_EQ_LAMBDA/171
|
6.73% |
0.343 |
0.366 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint16_t>/127
|
6.71% |
130.167 |
138.902 |
0.019 |
-0.00% |
0.019 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint64_t_To_uint32_t_
|
6.69% |
17813.328 |
19005.825 |
409.735 |
3.20% |
409.735 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC128
|
6.67% |
64.451 |
68.751 |
0.038 |
-0.11% |
0.038 |
|
SingleSource/Benchmarks/Misc-C++/Large/sphereflake
Profile
|
6.55% |
18.772 |
20.003 |
0.006 |
-0.01% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC127
|
6.47% |
182.768 |
194.596 |
0.007 |
0.00% |
0.007 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC16
|
6.45% |
38.207 |
40.671 |
0.000 |
32.65% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint32_t_To_uint8_t_
|
6.32% |
9410.386 |
10005.069 |
39.612 |
4.66% |
39.612 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint16_t_To_uint64_t_
|
6.30% |
18842.199 |
20028.718 |
52.124 |
-1.16% |
52.124 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint8_t>/65
|
6.27% |
89.493 |
95.107 |
0.004 |
-0.00% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC127
|
6.23% |
64.449 |
68.467 |
0.162 |
-0.38% |
0.162 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint32_t>/127
|
6.23% |
130.163 |
138.275 |
0.009 |
0.45% |
0.009 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_HYDRO_2D_RAW/5001
|
6.22% |
8842.660 |
9392.922 |
171.551 |
-3.24% |
171.551 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIND_FIRST_MIN_RAW/5001
|
6.21% |
42.778 |
45.437 |
0.092 |
0.35% |
0.092 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC16
|
5.98% |
31.292 |
33.162 |
0.002 |
0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC32
|
5.96% |
41.928 |
44.425 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC32
|
5.95% |
41.927 |
44.423 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC31
|
5.89% |
42.551 |
45.056 |
0.006 |
0.01% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC31
|
5.87% |
42.554 |
45.051 |
0.001 |
0.00% |
0.001 |
|
MultiSource/Benchmarks/SciMark2-C/scimark2
Profile
|
5.81% |
101.828 |
107.745 |
0.023 |
-0.06% |
0.023 |
|
MultiSource/Benchmarks/MiBench/telecomm-gsm/telecomm-gsm
Profile
|
5.62% |
0.624 |
0.659 |
0.000 |
-0.07% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC7
|
5.59% |
66.965 |
70.705 |
0.002 |
-0.01% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopWithReductionTC1
|
5.53% |
11.265 |
11.888 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIND_FIRST_MIN_RAW/44217
|
5.42% |
369.349 |
389.377 |
0.078 |
-0.02% |
0.078 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC31
|
5.40% |
23.153 |
24.403 |
0.029 |
2.55% |
0.029 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC31
|
5.39% |
23.154 |
24.402 |
0.023 |
2.33% |
0.023 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC32
|
5.39% |
23.154 |
24.402 |
0.001 |
2.60% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC32
|
5.39% |
23.155 |
24.402 |
0.001 |
2.63% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC32
|
5.37% |
58.195 |
61.321 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC15
|
5.33% |
121.719 |
128.208 |
0.028 |
0.43% |
0.028 |
|
MultiSource/Benchmarks/Rodinia/hotspot/hotspot
Profile
|
5.33% |
1.933 |
2.036 |
0.000 |
-0.05% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC31
|
5.30% |
229.044 |
241.172 |
0.028 |
-0.02% |
0.028 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC7
|
5.26% |
332.877 |
350.373 |
6.410 |
-0.84% |
6.410 |
|
SingleSource/Benchmarks/Misc/revertBits
Profile
|
4.84% |
0.612 |
0.641 |
0.000 |
-0.02% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint16_t>/65
|
4.82% |
90.744 |
95.119 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_runtime_checks_pass<16, int>
|
4.81% |
51.939 |
54.437 |
0.002 |
0.00% |
0.002 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_runtime_checks_fail<16, int>
|
4.81% |
51.939 |
54.436 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_PIC_1D_LAMBDA/5001
|
4.78% |
339.480 |
355.711 |
1.647 |
-1.36% |
1.647 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC127
|
4.73% |
2279.361 |
2387.114 |
32.639 |
-0.67% |
32.639 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint8_t_To_uint32_t_
|
4.69% |
11835.733 |
12390.538 |
71.192 |
-0.14% |
71.192 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopWithReductionTC2
|
4.67% |
13.151 |
13.766 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC31
|
4.66% |
66.962 |
70.080 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint32_t_To_uint64_t_
|
4.59% |
20378.216 |
21313.999 |
93.880 |
-0.56% |
93.880 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC8
|
4.54% |
13.767 |
14.391 |
0.000 |
4.54% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC1
|
4.54% |
13.767 |
14.391 |
0.000 |
4.53% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC2
|
4.53% |
13.767 |
14.391 |
0.001 |
4.54% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC7
|
4.53% |
13.767 |
14.391 |
0.000 |
4.54% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC3
|
4.53% |
13.767 |
14.391 |
0.000 |
4.53% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC4
|
4.53% |
13.768 |
14.392 |
0.001 |
4.53% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC2
|
4.53% |
13.768 |
14.391 |
0.000 |
4.54% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC15
|
4.53% |
13.768 |
14.391 |
0.000 |
4.55% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC16
|
4.53% |
13.768 |
14.391 |
0.001 |
4.54% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC4
|
4.53% |
13.768 |
14.391 |
0.000 |
4.54% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC8
|
4.53% |
13.768 |
14.391 |
0.001 |
4.54% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC3
|
4.53% |
13.768 |
14.391 |
0.000 |
4.53% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC1
|
4.52% |
13.771 |
14.393 |
0.000 |
2.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC7
|
4.52% |
13.769 |
14.391 |
0.000 |
4.53% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_PRESSURE_CALC_RAW/44217
|
4.46% |
482.126 |
503.608 |
3.820 |
-0.45% |
3.820 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_ENERGY_CALC_LAMBDA/171
|
4.45% |
13.637 |
14.244 |
0.029 |
0.02% |
0.029 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC15
|
4.44% |
13.778 |
14.391 |
0.000 |
4.54% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_ENERGY_CALC_RAW/171
|
4.41% |
13.651 |
14.253 |
0.018 |
0.15% |
0.018 |
|
MicroBenchmarks/ImageProcessing/Blur/blur.test:BENCHMARK_boxBlurKernel/1024
|
4.33% |
23502.339 |
24520.009 |
24.718 |
-18.64% |
24.718 |
|
MultiSource/Benchmarks/nbench/nbench
Profile
|
4.30% |
5.909 |
6.163 |
0.003 |
0.63% |
0.003 |
|
SingleSource/Benchmarks/Misc/flops-5
Profile
|
4.28% |
1.938 |
2.021 |
0.001 |
0.90% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC31
|
4.19% |
59.453 |
61.945 |
0.001 |
17.85% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint16_t_To_uint64_t_
|
4.15% |
23329.750 |
24298.377 |
42.533 |
-2.95% |
42.533 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC32
|
4.11% |
60.704 |
63.196 |
0.001 |
24.69% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint32_t>/65
|
4.09% |
90.736 |
94.444 |
0.018 |
0.62% |
0.018 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_PIC_2D_RAW/171
|
4.08% |
12.968 |
13.498 |
0.071 |
-0.24% |
0.071 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC3
|
3.99% |
15.644 |
16.269 |
0.002 |
3.95% |
0.002 |
|
SingleSource/Benchmarks/Polybench/stencils/jacobi-2d/jacobi-2d
Profile
|
3.95% |
30.728 |
31.943 |
0.206 |
-1.05% |
0.206 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIRST_DIFF_LAMBDA/5001
|
3.94% |
12.539 |
13.034 |
0.023 |
0.06% |
0.023 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_HYDRO_2D_RAW/44217
|
3.94% |
87939.864 |
91400.656 |
626.541 |
-3.98% |
626.541 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_FLOYD_DITHER/256
|
3.88% |
1751.830 |
1819.887 |
16.074 |
3.62% |
16.074 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<31, EqZero, First>
|
3.82% |
3222.956 |
3346.125 |
0.047 |
3.47% |
0.047 |
|
MicroBenchmarks/ImageProcessing/Blur/blur.test:BENCHMARK_boxBlurKernel/128
|
3.81% |
421.484 |
437.564 |
1.618 |
0.38% |
1.618 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_PIC_2D_LAMBDA/171
|
3.80% |
12.950 |
13.441 |
0.067 |
-0.51% |
0.067 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC64
|
3.73% |
66.961 |
69.456 |
0.006 |
0.00% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC64
|
3.72% |
66.960 |
69.453 |
0.004 |
-0.00% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC63
|
3.70% |
67.589 |
70.090 |
0.001 |
0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC63
|
3.68% |
67.590 |
70.079 |
0.002 |
-0.01% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC64
|
3.68% |
41.720 |
43.255 |
0.123 |
-1.18% |
0.123 |
|
External/SPEC/CFP2017rate/544.nab_r/544.nab_r
Profile
|
3.62% |
460.855 |
477.525 |
0.360 |
0.30% |
0.360 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_runtime_checks_pass<4, int>
|
3.54% |
15.332 |
15.876 |
0.095 |
-5.20% |
0.095 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC63
|
3.50% |
41.714 |
43.174 |
0.257 |
-1.09% |
0.257 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC16
|
3.45% |
30.249 |
31.294 |
0.248 |
-1.25% |
0.248 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC31
|
3.41% |
58.194 |
60.178 |
0.113 |
0.18% |
0.113 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC16
|
3.30% |
13.932 |
14.391 |
0.000 |
4.54% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1BigLoopWithReductionTC1
|
3.22% |
19.400 |
20.024 |
0.000 |
0.00% |
0.000 |
|
SingleSource/Benchmarks/Shootout/Shootout-lists
Profile
|
3.17% |
10.967 |
11.315 |
0.000 |
2.17% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchVecWithRuntimeChecks4PointersDBeforeA/1000
|
3.15% |
4866730.590 |
5020052.137 |
328.901 |
0.00% |
328.901 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, LessThanZero, None>
|
3.14% |
36527.035 |
37673.081 |
20.349 |
1.51% |
20.349 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<31, GreaterThanZero, Last>
|
2.94% |
8099.863 |
8337.942 |
5.693 |
2.27% |
5.693 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC64
|
2.87% |
108.276 |
111.378 |
0.000 |
0.00% |
0.000 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C/CoMD/CoMD
Profile
|
2.84% |
9.639 |
9.913 |
0.015 |
-0.51% |
0.015 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC1
|
2.83% |
21.905 |
22.525 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC1
|
2.83% |
21.906 |
22.526 |
0.000 |
2.84% |
0.000 |
|
MultiSource/Applications/JM/lencod/lencod
Profile
|
2.79% |
31.645 |
32.527 |
0.026 |
13.57% |
0.026 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC63
|
2.66% |
117.026 |
120.137 |
0.015 |
0.00% |
0.015 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC32
|
2.66% |
30.473 |
31.283 |
0.004 |
-0.01% |
0.004 |
|
MultiSource/Benchmarks/FreeBench/mason/mason
Profile
|
2.58% |
0.539 |
0.553 |
0.000 |
4.08% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint8_t_To_uint32_t_
|
2.57% |
6901.885 |
7079.135 |
0.206 |
0.01% |
0.206 |
|
External/SPEC/CINT2017rate/523.xalancbmk_r/523.xalancbmk_r
Profile
|
2.55% |
244.623 |
250.862 |
1.006 |
1.44% |
1.006 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchVecWithRuntimeChecks4PointersDBeforeA/32
|
2.48% |
162159.755 |
166187.494 |
4.623 |
0.00% |
4.623 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC63
|
2.38% |
104.506 |
106.996 |
0.004 |
15.54% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC64
|
2.35% |
105.762 |
108.250 |
0.001 |
17.67% |
0.001 |
|
SingleSource/Benchmarks/Misc/fbench
Profile
|
2.35% |
5.628 |
5.760 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_PRESSURE_CALC_LAMBDA/44217
|
2.27% |
490.448 |
501.581 |
2.536 |
0.19% |
2.536 |
|
MicroBenchmarks/ImageProcessing/Dilate/Dilate.test:BENCHMARK_DILATE/256
|
2.26% |
1038.984 |
1062.426 |
8.282 |
-0.45% |
8.282 |
|
MultiSource/Benchmarks/FreeBench/fourinarow/fourinarow
Profile
|
2.25% |
0.636 |
0.650 |
0.001 |
-0.04% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopFrom_uint8_t_To_uint16_t_
|
2.23% |
2176.933 |
2225.530 |
3.287 |
-1.27% |
3.287 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC31
|
2.21% |
30.536 |
31.210 |
0.031 |
-0.24% |
0.031 |
|
SingleSource/Benchmarks/Misc/flops-1
Profile
|
2.19% |
8.806 |
9.000 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_FLOYD_DITHER/128
|
2.13% |
429.228 |
438.379 |
0.373 |
-0.07% |
0.373 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC128
|
2.13% |
117.022 |
119.514 |
0.002 |
-0.00% |
0.002 |
|
External/SPEC/CFP2017rate/519.lbm_r/519.lbm_r
Profile
|
2.13% |
195.790 |
199.953 |
1.083 |
-1.20% |
1.083 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC128
|
2.13% |
117.021 |
119.509 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC127
|
2.12% |
117.646 |
120.135 |
0.005 |
-0.00% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC127
|
2.11% |
117.652 |
120.137 |
0.003 |
0.00% |
0.003 |
|
MultiSource/Benchmarks/sim/sim
Profile
|
2.11% |
9.491 |
9.691 |
0.005 |
-1.63% |
0.005 |
|
SingleSource/Benchmarks/Misc-C++/Large/ray
Profile
|
2.10% |
11.852 |
12.100 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC31
|
2.07% |
91.344 |
93.237 |
0.289 |
-0.31% |
0.289 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_EOS_LAMBDA/171
|
1.93% |
0.858 |
0.875 |
0.001 |
0.27% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_EOS_RAW/171
|
1.89% |
0.858 |
0.874 |
0.002 |
-0.02% |
0.002 |
|
SingleSource/Benchmarks/Misc/ReedSolomon
Profile
|
1.88% |
20.414 |
20.798 |
0.001 |
0.00% |
0.001 |
|
MultiSource/Benchmarks/mafft/pairlocalalign
Profile
|
1.87% |
92.204 |
93.924 |
0.319 |
0.15% |
0.319 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC15
|
1.76% |
43.806 |
44.576 |
0.095 |
16.79% |
0.095 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC32
|
1.64% |
49.240 |
50.046 |
0.007 |
0.33% |
0.007 |
|
External/SPEC/CINT2017rate/525.x264_r/525.x264_r
Profile
|
1.61% |
128.130 |
130.198 |
0.073 |
0.07% |
0.073 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_FLOYD_DITHER/512
|
1.61% |
6555.129 |
6660.602 |
8.642 |
0.14% |
8.642 |
|
MultiSource/Benchmarks/ASC_Sequoia/CrystalMk/CrystalMk
Profile
|
1.59% |
15.328 |
15.571 |
0.000 |
-0.13% |
0.000 |
|
SingleSource/Benchmarks/Adobe-C++/simple_types_loop_invariant
Profile
|
1.55% |
1.838 |
1.867 |
0.004 |
2.26% |
0.004 |
|
SingleSource/Benchmarks/Misc/mandel-2
Profile
|
1.55% |
2.496 |
2.535 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC128
|
1.50% |
208.385 |
211.513 |
0.014 |
-0.00% |
0.014 |
|
MultiSource/Benchmarks/VersaBench/ecbdes/ecbdes
Profile
|
1.49% |
5.064 |
5.140 |
0.000 |
-3.65% |
0.000 |
|
MultiSource/Benchmarks/Rodinia/pathfinder/pathfinder
Profile
|
1.48% |
1.243 |
1.261 |
0.007 |
-0.09% |
0.007 |
|
MultiSource/Benchmarks/TSVC/GlobalDataFlow-dbl/GlobalDataFlow-dbl
Profile
|
1.47% |
18.238 |
18.506 |
0.095 |
0.06% |
0.095 |
|
MultiSource/Applications/obsequi/Obsequi
Profile
|
1.47% |
7.688 |
7.801 |
0.009 |
-0.13% |
0.009 |
|
External/SPEC/CINT2017rate/531.deepsjeng_r/531.deepsjeng_r
Profile
|
1.39% |
255.847 |
259.400 |
0.238 |
-5.78% |
0.238 |
|
SingleSource/Benchmarks/Misc/oourafft
Profile
|
1.37% |
14.591 |
14.791 |
0.072 |
1.53% |
0.072 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_INT_PREDICT_RAW/171
|
1.36% |
6.831 |
6.923 |
0.002 |
-0.02% |
0.002 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<3, GreaterThanZero, None>
|
1.34% |
44602.553 |
45200.978 |
5.109 |
-0.79% |
5.109 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint8_t_To_uint64_t_
|
1.34% |
22544.080 |
22845.768 |
18.222 |
0.31% |
18.222 |
|
MultiSource/Benchmarks/tramp3d-v4/tramp3d-v4
Profile
|
1.30% |
1.065 |
1.079 |
0.001 |
0.40% |
0.001 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<6, LessThanZero, Mid>
|
1.30% |
23541.623 |
23847.291 |
7.288 |
1.45% |
7.288 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC127
|
1.29% |
217.463 |
220.273 |
0.015 |
0.00% |
0.015 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC127
|
1.27% |
194.621 |
197.095 |
0.009 |
14.13% |
0.009 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC128
|
1.25% |
195.905 |
198.346 |
0.008 |
16.11% |
0.008 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC63
|
1.22% |
128.585 |
130.148 |
0.006 |
0.16% |
0.006 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<16, LessThanZero, Last>
|
1.13% |
12995.233 |
13141.463 |
6.187 |
1.12% |
6.187 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<32, EqZero, Last>
|
1.13% |
6963.853 |
7042.206 |
4.488 |
1.36% |
4.488 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_sinh_novec_double_
|
1.12% |
2449.636 |
2477.042 |
2.680 |
0.02% |
2.680 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<8, LessThanZero, Mid>
|
1.10% |
19263.612 |
19476.459 |
20.232 |
1.25% |
20.232 |
|
SingleSource/Benchmarks/Shootout-C++/Shootout-C++-hash2
Profile
|
1.09% |
9.242 |
9.342 |
0.009 |
0.17% |
0.009 |
|
MultiSource/Benchmarks/Fhourstones-3.1/fhourstones3.1
Profile
|
1.09% |
3.932 |
3.975 |
0.003 |
-0.02% |
0.003 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<32, LessThanZero, Mid>
|
1.04% |
4523.441 |
4570.544 |
8.210 |
-0.02% |
8.210 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_sinhf_novec_float_
|
1.04% |
2218.809 |
2241.842 |
0.492 |
-0.01% |
0.492 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<6, GreaterThanZero, None>
|
1.04% |
29427.899 |
29733.094 |
13.387 |
2.64% |
13.387 |
|
MultiSource/Benchmarks/Olden/health/health
Profile
|
1.03% |
1.570 |
1.587 |
0.004 |
-0.21% |
0.004 |
|
SingleSource/Benchmarks/SmallPT/smallpt
Profile
|
1.02% |
29.706 |
30.009 |
0.006 |
-0.02% |
0.006 |
|
External/SPEC/CINT2017rate/557.xz_r/557.xz_r
Profile
|
1.00% |
210.872 |
212.984 |
0.805 |
0.66% |
0.805 |