|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_INT_PREDICT_RAW/44217
|
133.02% |
8226.856 |
19170.449 |
136.227 |
-0.81% |
136.227 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint64_t_To_uint16_t_
|
106.99% |
18724.661 |
38757.466 |
119.910 |
8.95% |
119.910 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint64_t_To_uint32_t_
|
99.20% |
18057.988 |
35972.194 |
171.442 |
0.79% |
171.442 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_INT_PREDICT_LAMBDA/44217
|
93.59% |
8186.508 |
15848.271 |
1746.910 |
-14.49% |
1746.910 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint64_t_To_uint8_t_
|
91.84% |
19178.465 |
36792.897 |
15.857 |
1.34% |
15.857 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint16_t_To_uint64_t_
|
78.56% |
10451.156 |
18661.367 |
193.578 |
-1.05% |
193.578 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_INT_PREDICT_RAW/5001
|
75.07% |
924.529 |
1618.598 |
179.489 |
-18.21% |
179.489 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_DIFF_PREDICT_RAW/44217
|
70.30% |
14261.025 |
24285.975 |
979.998 |
-0.07% |
979.998 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_DIFF_PREDICT_LAMBDA/44217
|
70.00% |
14238.057 |
24205.164 |
1056.237 |
0.53% |
1056.237 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint64_t_To_uint32_t_
|
69.61% |
22720.934 |
38536.489 |
134.517 |
2.08% |
134.517 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint8_t_To_uint64_t_
|
68.22% |
10565.787 |
17773.615 |
423.387 |
-0.00% |
423.387 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIRST_DIFF_LAMBDA/44217
|
68.20% |
103.431 |
173.968 |
5.035 |
0.93% |
5.035 |
|
SingleSource/Benchmarks/Adobe-C++/loop_unroll
Profile
|
67.34% |
2.426 |
4.060 |
0.001 |
0.06% |
0.001 |
|
MultiSource/Benchmarks/MiBench/automotive-bitcount/automotive-bitcount
Profile
|
64.98% |
0.102 |
0.167 |
0.001 |
-0.29% |
0.001 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/32
|
59.41% |
883.992 |
1409.131 |
0.035 |
-0.00% |
0.035 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/64
|
59.28% |
3915.250 |
6236.147 |
0.318 |
0.00% |
0.318 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/16
|
59.25% |
177.142 |
282.092 |
0.009 |
-0.01% |
0.009 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C/miniGMG/miniGMG
Profile
|
58.01% |
5.713 |
9.028 |
0.233 |
-4.53% |
0.233 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint32_t_To_uint64_t_
|
57.98% |
15070.396 |
23808.249 |
1595.357 |
3.10% |
1595.357 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/256
|
57.82% |
68438.371 |
108006.541 |
2.640 |
0.05% |
2.640 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/128
|
57.56% |
16788.158 |
26451.708 |
9.938 |
-0.00% |
9.938 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_DIFF_PREDICT_LAMBDA/5001
|
55.50% |
1614.599 |
2510.688 |
183.098 |
-1.50% |
183.098 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIRST_DIFF_RAW/44217
|
54.57% |
104.274 |
161.181 |
11.713 |
10.72% |
11.713 |
|
MultiSource/Benchmarks/MiBench/automotive-susan/automotive-susan
Profile
|
54.44% |
0.100 |
0.155 |
0.000 |
-46.26% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint64_t_To_uint16_t_
|
54.18% |
19146.592 |
29519.583 |
116.667 |
-0.06% |
116.667 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_DIFF_PREDICT_RAW/5001
|
53.77% |
1647.547 |
2533.475 |
186.907 |
-0.42% |
186.907 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint64_t_To_uint8_t_
|
50.97% |
19850.858 |
29969.330 |
256.386 |
-0.31% |
256.386 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, EqZero, None>
|
45.41% |
14105.249 |
20509.866 |
1.242 |
0.00% |
1.242 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_HYDRO_2D_RAW/44217
|
44.08% |
59789.024 |
86145.328 |
3374.833 |
-9.50% |
3374.833 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC128
|
41.60% |
942.710 |
1334.837 |
0.026 |
-0.01% |
0.026 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC127
|
41.15% |
936.444 |
1321.799 |
0.089 |
-0.00% |
0.089 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint32_t_To_uint8_t_
|
40.98% |
9768.953 |
13772.379 |
67.539 |
2.56% |
67.539 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_HYDRO_2D_RAW/5001
|
40.95% |
6434.399 |
9069.475 |
380.758 |
-6.57% |
380.758 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_HYDRO_2D_LAMBDA/44217
|
40.37% |
66409.992 |
93220.756 |
2403.708 |
-0.10% |
2403.708 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC64
|
39.84% |
481.890 |
673.892 |
0.033 |
-0.01% |
0.033 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC63
|
38.93% |
475.636 |
660.812 |
0.254 |
0.01% |
0.254 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint64_t_To_uint16_t_
|
37.03% |
18567.418 |
25442.643 |
9.090 |
-1.94% |
9.090 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC128
|
36.98% |
407.846 |
558.676 |
0.096 |
0.03% |
0.096 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC128
|
36.86% |
945.854 |
1294.457 |
4.219 |
-0.20% |
4.219 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC32
|
36.54% |
251.579 |
343.515 |
0.017 |
-0.01% |
0.017 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_PIC_2D_RAW/44217
|
35.55% |
8745.184 |
11853.831 |
25.092 |
-1.06% |
25.092 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC64
|
35.51% |
482.650 |
654.020 |
2.265 |
-0.43% |
2.265 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC32
|
35.26% |
247.250 |
334.432 |
0.978 |
-0.47% |
0.978 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC31
|
34.66% |
245.347 |
330.382 |
0.296 |
-0.00% |
0.296 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC16
|
34.57% |
129.608 |
174.418 |
0.510 |
-0.56% |
0.510 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC64
|
34.47% |
217.301 |
292.200 |
0.048 |
0.05% |
0.048 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIRST_SUM_RAW/44217
|
32.53% |
137.782 |
182.597 |
0.510 |
-2.81% |
0.510 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_HYDRO_2D_LAMBDA/5001
|
31.54% |
7277.780 |
9573.303 |
342.997 |
-1.39% |
342.997 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, EqZero, None>
|
31.52% |
12183.082 |
16022.797 |
0.319 |
-0.01% |
0.319 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint32_t_To_uint8_t_
|
31.41% |
11371.911 |
14943.380 |
56.772 |
5.18% |
56.772 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC16
|
30.72% |
136.419 |
178.331 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC128
|
30.18% |
463.892 |
603.900 |
0.016 |
0.19% |
0.016 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC32
|
30.03% |
122.136 |
158.811 |
0.062 |
-0.10% |
0.062 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC128
|
30.02% |
464.466 |
603.885 |
0.045 |
-0.01% |
0.045 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIRST_SUM_LAMBDA/44217
|
29.76% |
137.709 |
178.696 |
4.389 |
-1.91% |
4.389 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint64_t_To_uint8_t_
|
29.24% |
20573.236 |
26588.836 |
17.405 |
-3.96% |
17.405 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint16_t_To_uint64_t_
|
28.91% |
10367.294 |
13364.402 |
71.287 |
-0.86% |
71.287 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC64
|
28.76% |
243.457 |
313.486 |
0.003 |
0.38% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC127
|
28.48% |
478.851 |
615.216 |
0.061 |
0.09% |
0.061 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC64
|
28.43% |
244.077 |
313.479 |
0.008 |
-0.01% |
0.008 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC127
|
28.13% |
480.110 |
615.172 |
0.041 |
-0.01% |
0.041 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint8_t_To_uint32_t_
|
27.58% |
5170.632 |
6596.582 |
86.927 |
-0.42% |
86.927 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint16_t_To_uint32_t_
|
27.54% |
5575.782 |
7111.164 |
62.342 |
-0.01% |
62.342 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_VOL3D_CALC_RAW/2
|
27.25% |
7.111 |
9.049 |
0.000 |
8.77% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_VOL3D_CALC_LAMBDA/2
|
27.24% |
7.111 |
9.048 |
0.001 |
8.76% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIND_FIRST_MIN_LAMBDA/171
|
26.94% |
1.182 |
1.500 |
0.000 |
-0.04% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC15
|
26.91% |
130.161 |
165.187 |
0.296 |
-0.00% |
0.296 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIND_FIRST_MIN_LAMBDA/44217
|
26.73% |
307.080 |
389.164 |
0.576 |
-0.02% |
0.576 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC32
|
26.27% |
133.297 |
168.310 |
0.010 |
0.73% |
0.010 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIND_FIRST_MIN_LAMBDA/5001
|
26.20% |
35.852 |
45.243 |
0.071 |
0.56% |
0.071 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC32
|
25.69% |
133.916 |
168.313 |
0.004 |
-0.00% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC63
|
25.66% |
258.461 |
324.770 |
0.045 |
0.17% |
0.045 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC127
|
25.27% |
219.678 |
275.186 |
1.398 |
3.97% |
1.398 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC63
|
25.03% |
259.751 |
324.755 |
0.005 |
-0.01% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC128
|
24.61% |
219.973 |
274.107 |
0.800 |
3.78% |
0.800 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC127
|
24.48% |
514.954 |
641.019 |
0.227 |
-0.01% |
0.227 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_PIC_2D_LAMBDA/5001
|
24.05% |
973.977 |
1208.214 |
38.067 |
1.22% |
38.067 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC16
|
23.90% |
74.488 |
92.291 |
0.013 |
-0.01% |
0.013 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint8_t_To_uint64_t_
|
23.88% |
10961.399 |
13578.459 |
124.583 |
6.23% |
124.583 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_PIC_1D_RAW/44217
|
23.18% |
11089.229 |
13659.925 |
44.006 |
-0.76% |
44.006 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC64
|
23.09% |
121.131 |
149.100 |
2.068 |
4.08% |
2.068 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint64_t_To_uint32_t_
|
22.96% |
22142.643 |
27226.371 |
27.694 |
0.41% |
27.694 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_VOL3D_CALC_LAMBDA/1
|
22.88% |
218.663 |
268.703 |
0.115 |
7.72% |
0.115 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_VOL3D_CALC_RAW/1
|
22.85% |
218.685 |
268.651 |
0.072 |
7.57% |
0.072 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC16
|
22.39% |
78.221 |
95.731 |
0.007 |
1.32% |
0.007 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_VOL3D_CALC_RAW/0
|
22.30% |
1066.505 |
1304.334 |
0.689 |
5.98% |
0.689 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_VOL3D_CALC_LAMBDA/0
|
22.14% |
1065.142 |
1300.964 |
1.907 |
5.75% |
1.907 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint16_t_To_uint8_t_
|
22.14% |
3089.408 |
3773.255 |
0.441 |
-0.58% |
0.441 |
|
MultiSource/Benchmarks/Trimaran/enc-pc1/enc-pc1
Profile
|
22.11% |
0.904 |
1.104 |
0.000 |
-0.00% |
0.000 |
|
MultiSource/Benchmarks/TSVC/Searching-flt/Searching-flt
Profile
|
22.05% |
4.155 |
5.071 |
0.014 |
2.34% |
0.014 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC63
|
22.03% |
126.276 |
154.092 |
1.066 |
7.34% |
1.066 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC16
|
21.42% |
78.848 |
95.735 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC8
|
21.41% |
78.847 |
95.732 |
0.004 |
0.00% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC31
|
21.07% |
148.323 |
179.580 |
0.013 |
0.34% |
0.013 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_PIC_2D_RAW/5001
|
20.97% |
995.061 |
1203.762 |
20.573 |
-1.19% |
20.573 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC128
|
20.85% |
472.289 |
570.763 |
0.008 |
0.21% |
0.008 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC4
|
20.74% |
14.509 |
17.519 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_PIC_2D_LAMBDA/44217
|
20.71% |
9866.049 |
11908.916 |
13.127 |
-0.11% |
13.127 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC64
|
20.62% |
246.914 |
297.838 |
0.031 |
0.40% |
0.031 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_DISC_ORD_LAMBDA/44217
|
20.51% |
12319.427 |
14846.613 |
177.720 |
0.36% |
177.720 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC32
|
20.12% |
134.253 |
161.271 |
0.078 |
0.67% |
0.078 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC31
|
20.06% |
149.570 |
179.573 |
0.005 |
-0.01% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint32_t_To_uint16_t_
|
20.05% |
11165.335 |
13403.477 |
69.406 |
0.19% |
69.406 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC16
|
19.60% |
77.949 |
93.226 |
0.006 |
1.35% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint32_t_To_uint64_t_
|
19.57% |
16413.232 |
19625.947 |
857.055 |
8.74% |
857.055 |
|
MultiSource/Benchmarks/TSVC/Searching-dbl/Searching-dbl
Profile
|
19.55% |
7.639 |
9.132 |
0.018 |
0.10% |
0.018 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_HYDRO_1D_RAW/171
|
18.94% |
0.372 |
0.442 |
0.000 |
0.12% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint32_t_To_uint16_t_
|
18.79% |
11262.573 |
13379.325 |
37.586 |
-3.53% |
37.586 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_HYDRO_1D_LAMBDA/171
|
18.70% |
0.372 |
0.441 |
0.001 |
-0.43% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint16_t_To_uint32_t_
|
18.43% |
6295.705 |
7455.695 |
0.241 |
-0.02% |
0.241 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC8
|
18.22% |
49.751 |
58.815 |
0.003 |
2.16% |
0.003 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, EqZero, First>
|
18.19% |
14104.645 |
16669.616 |
0.469 |
0.00% |
0.469 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_no_runtime_checks_needed<16, int>
|
18.18% |
20.649 |
24.402 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, EqZero, Mid>
|
18.15% |
14105.176 |
16665.844 |
0.100 |
-0.01% |
0.100 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, EqZero, Last>
|
18.11% |
14110.490 |
16666.139 |
0.191 |
-0.00% |
0.191 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC32
|
17.70% |
73.297 |
86.269 |
0.607 |
5.47% |
0.607 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC127
|
17.38% |
516.083 |
605.781 |
0.021 |
0.08% |
0.021 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC8
|
17.26% |
50.692 |
59.444 |
0.008 |
2.14% |
0.008 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_DISC_ORD_RAW/44217
|
16.73% |
11395.732 |
13302.752 |
617.117 |
7.51% |
617.117 |
|
SingleSource/Benchmarks/Misc/salsa20
Profile
|
16.42% |
13.213 |
15.383 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint32_t_To_uint8_t_
|
16.40% |
9138.602 |
10637.177 |
101.969 |
-1.28% |
101.969 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC4
|
16.07% |
44.743 |
51.934 |
0.002 |
5.06% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC7
|
16.07% |
44.742 |
51.933 |
0.003 |
5.06% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC8
|
16.07% |
44.746 |
51.937 |
0.000 |
4.91% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC3
|
16.06% |
44.746 |
51.934 |
0.002 |
5.05% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC1
|
16.06% |
44.747 |
51.934 |
0.001 |
5.06% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC2
|
16.05% |
44.751 |
51.933 |
0.002 |
5.05% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint8_t_To_uint16_t_
|
15.97% |
3239.625 |
3757.144 |
0.468 |
-0.01% |
0.468 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint32_t_To_uint8_t_
|
15.86% |
9728.467 |
11271.115 |
24.626 |
0.64% |
24.626 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC8
|
15.83% |
51.317 |
59.440 |
0.003 |
-0.00% |
0.003 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, EqZero, Last>
|
15.76% |
12182.658 |
14102.510 |
0.372 |
-0.00% |
0.372 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, EqZero, Mid>
|
15.75% |
12184.303 |
14102.775 |
0.305 |
-0.01% |
0.305 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, EqZero, First>
|
15.74% |
12183.755 |
14102.082 |
0.511 |
-0.01% |
0.511 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC8
|
15.64% |
20.020 |
23.152 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC63
|
15.33% |
324.677 |
374.450 |
0.106 |
-0.02% |
0.106 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC8
|
15.14% |
20.650 |
23.777 |
0.002 |
0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC128
|
15.02% |
70.720 |
81.340 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC15
|
14.79% |
93.244 |
107.033 |
0.042 |
0.62% |
0.042 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint8_t_To_uint16_t_
|
14.77% |
3954.714 |
4538.855 |
0.066 |
0.01% |
0.066 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC63
|
14.51% |
290.711 |
332.891 |
0.111 |
0.17% |
0.111 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint16_t_To_uint8_t_
|
14.22% |
4156.301 |
4747.212 |
0.165 |
-0.56% |
0.165 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIRST_SUM_LAMBDA/5001
|
14.19% |
17.974 |
20.525 |
0.355 |
-1.48% |
0.355 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC7
|
13.73% |
72.591 |
82.559 |
0.211 |
-0.05% |
0.211 |
|
External/SPEC/CFP2017rate/508.namd_r/508.namd_r
Profile
|
13.57% |
196.636 |
223.314 |
0.445 |
1.21% |
0.445 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint64_t_To_uint8_t_
|
13.25% |
19078.789 |
21607.567 |
31.323 |
0.08% |
31.323 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC15
|
13.23% |
94.494 |
106.995 |
0.005 |
-0.53% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC31
|
13.14% |
76.341 |
86.375 |
0.579 |
4.42% |
0.579 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC16
|
12.94% |
45.983 |
51.934 |
0.003 |
5.04% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC15
|
12.91% |
45.995 |
51.933 |
0.004 |
5.05% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC16
|
12.76% |
29.409 |
33.163 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC4
|
12.48% |
20.026 |
22.525 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC4
|
12.48% |
20.026 |
22.525 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/ImageProcessing/Dilate/Dilate.test:BENCHMARK_DILATE/1024
|
12.30% |
6757.460 |
7588.491 |
19.887 |
0.91% |
19.887 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC4
|
11.86% |
36.919 |
41.296 |
0.001 |
3.12% |
0.001 |
|
MultiSource/Benchmarks/MiBench/security-rijndael/security-rijndael
Profile
|
11.85% |
0.278 |
0.311 |
0.001 |
0.11% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC64
|
11.68% |
48.184 |
53.811 |
0.003 |
-0.00% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC7
|
11.53% |
29.411 |
32.801 |
0.034 |
0.80% |
0.034 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC4
|
11.31% |
13.767 |
15.325 |
0.003 |
11.31% |
0.003 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/16
|
11.07% |
103.742 |
115.222 |
0.010 |
-0.00% |
0.010 |
|
SingleSource/Benchmarks/Misc-C++/oopack_v1p8
Profile
|
11.00% |
0.467 |
0.519 |
0.000 |
-0.02% |
0.000 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/32
|
10.97% |
425.799 |
472.521 |
0.013 |
-0.01% |
0.013 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/64
|
10.89% |
1724.337 |
1912.033 |
1.278 |
-0.00% |
1.278 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIRST_SUM_RAW/5001
|
10.81% |
18.593 |
20.602 |
0.114 |
-0.11% |
0.114 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC8
|
10.80% |
23.153 |
25.653 |
0.003 |
-0.00% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC8
|
10.79% |
23.155 |
25.654 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC127
|
10.76% |
91.993 |
101.887 |
0.033 |
0.51% |
0.033 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/256
|
10.71% |
28378.662 |
31417.360 |
21.292 |
-0.02% |
21.292 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/128
|
10.64% |
7148.069 |
7908.461 |
6.584 |
0.02% |
6.584 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC1
|
10.52% |
11.890 |
13.140 |
0.000 |
6.50% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC7
|
10.51% |
23.779 |
26.280 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC7
|
10.50% |
23.782 |
26.279 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC32
|
10.39% |
48.179 |
53.187 |
0.007 |
0.00% |
0.007 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC31
|
10.35% |
178.041 |
196.472 |
0.020 |
0.30% |
0.020 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_DEL_DOT_VEC_2D_LAMBDA/1
|
10.05% |
260.828 |
287.032 |
0.021 |
-0.04% |
0.021 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_DEL_DOT_VEC_2D_RAW/1
|
9.99% |
260.858 |
286.927 |
0.153 |
-0.05% |
0.153 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC4
|
9.99% |
37.547 |
41.297 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_DIFF_PREDICT_RAW/171
|
9.88% |
11.251 |
12.363 |
0.035 |
-0.48% |
0.035 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C++/miniFE/miniFE
Profile
|
9.74% |
15.196 |
16.676 |
0.089 |
-0.19% |
0.089 |
|
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_DEL_DOT_VEC_2D_RAW/2
|
9.49% |
3.206 |
3.510 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_runtime_checks_fail<4, int>
|
9.46% |
15.331 |
16.782 |
0.022 |
0.00% |
0.022 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC16
|
9.42% |
33.167 |
36.292 |
0.073 |
-1.71% |
0.073 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_DIFF_PREDICT_LAMBDA/171
|
9.38% |
11.259 |
12.315 |
0.029 |
-0.52% |
0.029 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC4
|
9.20% |
102.923 |
112.394 |
2.212 |
-0.78% |
2.212 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint8_t_To_uint16_t_
|
9.13% |
5269.563 |
5750.875 |
1.395 |
-0.79% |
1.395 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC64
|
8.75% |
85.728 |
93.230 |
0.009 |
-0.00% |
0.009 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC4
|
8.73% |
50.065 |
54.438 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC16
|
8.50% |
29.412 |
31.911 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC16
|
8.50% |
29.413 |
31.911 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC32
|
8.46% |
36.921 |
40.046 |
0.001 |
0.00% |
0.001 |
|
MultiSource/Benchmarks/FreeBench/pifft/pifft
Profile
|
8.41% |
0.330 |
0.357 |
0.000 |
-0.02% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC15
|
8.32% |
30.038 |
32.537 |
0.000 |
-0.01% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC15
|
8.32% |
30.037 |
32.536 |
0.001 |
0.00% |
0.001 |
|
MultiSource/Benchmarks/VersaBench/beamformer/beamformer
Profile
|
8.13% |
4.807 |
5.198 |
0.001 |
34.97% |
0.001 |
|
MultiSource/Benchmarks/Trimaran/enc-md5/enc-md5
Profile
|
8.09% |
3.244 |
3.506 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_DEL_DOT_VEC_2D_RAW/0
|
7.98% |
1665.769 |
1798.738 |
4.907 |
0.11% |
4.907 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_xor_no_runtime_checks_needed<16, int>
|
7.97% |
15.648 |
16.894 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint16_t_To_uint8_t_
|
7.83% |
6239.038 |
6727.758 |
1.340 |
-0.67% |
1.340 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC128
|
7.77% |
160.837 |
173.328 |
0.002 |
0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint8_t>/127
|
7.74% |
128.923 |
138.906 |
0.002 |
0.00% |
0.002 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIND_FIRST_MIN_RAW/171
|
7.72% |
1.389 |
1.497 |
0.000 |
-0.04% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint64_t_To_uint16_t_
|
7.71% |
19576.059 |
21085.488 |
6.712 |
10.53% |
6.712 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_DEL_DOT_VEC_2D_LAMBDA/0
|
7.65% |
1670.990 |
1798.769 |
2.051 |
-0.03% |
2.051 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC7
|
7.61% |
65.708 |
70.708 |
0.035 |
0.89% |
0.035 |
|
SingleSource/Benchmarks/Misc/pi
Profile
|
7.52% |
1.657 |
1.782 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC15
|
7.40% |
50.690 |
54.439 |
0.004 |
0.00% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC15
|
7.38% |
41.957 |
45.052 |
0.002 |
0.00% |
0.002 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_HYDRO_2D_LAMBDA/171
|
7.23% |
82.806 |
88.794 |
0.498 |
-0.17% |
0.498 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC31
|
7.20% |
69.461 |
74.465 |
0.006 |
0.01% |
0.006 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_HYDRO_2D_RAW/171
|
7.17% |
82.781 |
88.715 |
0.334 |
-0.36% |
0.334 |
|
MultiSource/Benchmarks/Ptrdist/anagram/anagram
Profile
|
7.03% |
3.504 |
3.750 |
0.001 |
-0.12% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC63
|
6.97% |
69.462 |
74.303 |
0.017 |
0.63% |
0.017 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_xor_runtime_checks_pass<16, int>
|
6.95% |
26.910 |
28.782 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_xor_runtime_checks_fail<16, int>
|
6.94% |
26.914 |
28.783 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint16_t_To_uint64_t_
|
6.93% |
18776.755 |
20078.515 |
38.144 |
-0.91% |
38.144 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC2
|
6.90% |
15.804 |
16.895 |
0.001 |
3.85% |
0.001 |
|
MultiSource/Benchmarks/MiBench/telecomm-gsm/telecomm-gsm
Profile
|
6.85% |
0.624 |
0.667 |
0.000 |
0.94% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint32_t_To_uint8_t_
|
6.76% |
9357.583 |
9990.225 |
84.374 |
4.50% |
84.374 |
|
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
|
6.74% |
0.343 |
0.366 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint16_t>/127
|
6.72% |
130.160 |
138.907 |
0.003 |
-0.00% |
0.003 |
|
SingleSource/Benchmarks/Misc/flops-6
Profile
|
6.72% |
1.228 |
1.311 |
0.000 |
1.23% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC63
|
6.67% |
107.345 |
114.508 |
0.001 |
0.00% |
0.001 |
|
SingleSource/Benchmarks/Misc-C++/Large/sphereflake
Profile
|
6.56% |
18.773 |
20.004 |
0.003 |
-0.00% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC127
|
6.43% |
182.848 |
194.602 |
0.041 |
-0.00% |
0.041 |
|
MultiSource/Benchmarks/McCat/12-IOtest/iotest
Profile
|
6.31% |
1.737 |
1.846 |
0.003 |
-0.44% |
0.003 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIND_FIRST_MIN_RAW/5001
|
6.29% |
42.593 |
45.273 |
0.038 |
-0.01% |
0.038 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint8_t>/65
|
6.28% |
89.492 |
95.109 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC16
|
6.23% |
30.040 |
31.912 |
0.001 |
0.35% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint32_t>/127
|
6.22% |
130.181 |
138.275 |
0.006 |
0.45% |
0.006 |
|
MultiSource/Benchmarks/SciMark2-C/scimark2
Profile
|
6.07% |
101.749 |
107.929 |
0.040 |
0.11% |
0.040 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC16
|
5.97% |
31.293 |
33.163 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC32
|
5.96% |
41.931 |
44.428 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC32
|
5.95% |
41.928 |
44.424 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC31
|
5.87% |
42.553 |
45.050 |
0.003 |
0.00% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC31
|
5.84% |
42.564 |
45.050 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC127
|
5.82% |
64.452 |
68.204 |
0.007 |
-0.76% |
0.007 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC128
|
5.82% |
64.454 |
68.202 |
0.001 |
-0.91% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIND_FIRST_MIN_RAW/44217
|
5.80% |
368.842 |
390.220 |
0.036 |
0.07% |
0.036 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC3
|
5.60% |
20.147 |
21.276 |
0.001 |
6.10% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_ENERGY_CALC_RAW/5001
|
5.60% |
424.276 |
448.052 |
2.475 |
-0.57% |
2.475 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC7
|
5.60% |
66.959 |
70.707 |
0.005 |
-0.01% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC1
|
5.55% |
11.264 |
11.889 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC1
|
5.54% |
11.265 |
11.888 |
0.001 |
-0.00% |
0.001 |
|
MultiSource/Benchmarks/VersaBench/ecbdes/ecbdes
Profile
|
5.42% |
5.061 |
5.335 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC31
|
5.40% |
23.153 |
24.403 |
0.001 |
2.33% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC31
|
5.39% |
23.155 |
24.402 |
0.001 |
2.55% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC32
|
5.39% |
23.155 |
24.402 |
0.001 |
2.63% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC15
|
5.39% |
121.713 |
128.269 |
0.003 |
0.48% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC32
|
5.38% |
23.157 |
24.402 |
0.001 |
2.61% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC32
|
5.37% |
58.196 |
61.320 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint8_t_To_uint32_t_
|
5.35% |
11798.837 |
12430.173 |
52.890 |
-0.04% |
52.890 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC31
|
5.24% |
229.178 |
241.176 |
0.044 |
-0.02% |
0.044 |
|
MultiSource/Benchmarks/Rodinia/hotspot/hotspot
Profile
|
5.20% |
1.936 |
2.036 |
0.002 |
-0.02% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC4
|
5.08% |
24.413 |
25.654 |
0.004 |
5.10% |
0.004 |
|
MicroBenchmarks/ImageProcessing/Blur/blur.test:BENCHMARK_boxBlurKernel/1024
|
5.05% |
23298.692 |
24475.372 |
60.918 |
-18.79% |
60.918 |
|
MultiSource/Benchmarks/nbench/nbench
Profile
|
5.03% |
5.914 |
6.212 |
0.001 |
1.44% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1LoopWithReductionTC3
|
4.93% |
12.522 |
13.140 |
0.001 |
10.52% |
0.001 |
|
SingleSource/Benchmarks/Polybench/stencils/jacobi-2d/jacobi-2d
Profile
|
4.89% |
30.580 |
32.077 |
0.080 |
-0.63% |
0.080 |
|
SingleSource/Benchmarks/Misc/revertBits
Profile
|
4.87% |
0.612 |
0.641 |
0.000 |
0.01% |
0.000 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_runtime_checks_pass<16, int>
|
4.81% |
51.940 |
54.437 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint16_t>/65
|
4.80% |
90.752 |
95.110 |
0.005 |
-0.01% |
0.005 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_runtime_checks_fail<16, int>
|
4.80% |
51.940 |
54.435 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC2
|
4.75% |
13.141 |
13.766 |
0.036 |
-0.00% |
0.036 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_PIC_2D_RAW/171
|
4.70% |
12.956 |
13.565 |
0.046 |
-0.25% |
0.046 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC31
|
4.66% |
66.959 |
70.082 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_PIC_2D_LAMBDA/171
|
4.64% |
12.891 |
13.490 |
0.047 |
-0.15% |
0.047 |
|
MicroBenchmarks/ImageProcessing/Dilate/Dilate.test:BENCHMARK_DILATE/256
|
4.54% |
1020.410 |
1066.728 |
5.586 |
-0.05% |
5.586 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC2
|
4.54% |
13.767 |
14.391 |
0.001 |
4.54% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC4
|
4.54% |
13.767 |
14.391 |
0.000 |
4.54% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC16
|
4.54% |
13.767 |
14.392 |
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:benchAutoVecForLoopTC2
|
4.54% |
13.767 |
14.391 |
0.000 |
4.54% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC15
|
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:benchAutoVecForLoopTC8
|
4.53% |
13.767 |
14.391 |
0.000 |
4.54% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC3
|
4.53% |
13.768 |
14.392 |
0.000 |
4.53% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC15
|
4.53% |
13.768 |
14.392 |
0.000 |
4.55% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC1
|
4.53% |
13.769 |
14.393 |
0.001 |
2.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC7
|
4.53% |
13.767 |
14.391 |
0.000 |
4.54% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC8
|
4.53% |
13.768 |
14.391 |
0.001 |
4.54% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC7
|
4.51% |
13.770 |
14.391 |
0.000 |
4.53% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_ENERGY_CALC_RAW/171
|
4.31% |
13.642 |
14.230 |
0.026 |
-0.01% |
0.026 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint32_t_To_uint64_t_
|
4.29% |
20474.678 |
21352.493 |
81.666 |
-0.38% |
81.666 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_ENERGY_CALC_LAMBDA/171
|
4.20% |
13.653 |
14.226 |
0.033 |
-0.01% |
0.033 |
|
SingleSource/Benchmarks/Misc/flops-5
Profile
|
4.17% |
1.939 |
2.020 |
0.000 |
0.85% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC3
|
4.15% |
15.019 |
15.643 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1LoopWithReductionTC7
|
4.14% |
20.027 |
20.855 |
0.290 |
7.51% |
0.290 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint32_t>/65
|
4.12% |
90.741 |
94.483 |
0.001 |
0.66% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC3
|
3.99% |
15.645 |
16.269 |
0.001 |
3.95% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC31
|
3.86% |
58.202 |
60.451 |
0.023 |
0.64% |
0.023 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopWithReductionTC2
|
3.83% |
13.150 |
13.654 |
0.043 |
-0.81% |
0.043 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC64
|
3.73% |
66.959 |
69.453 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC64
|
3.71% |
66.966 |
69.451 |
0.005 |
-0.00% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint16_t_To_uint64_t_
|
3.70% |
23393.452 |
24258.758 |
30.462 |
-3.11% |
30.462 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC63
|
3.69% |
67.585 |
70.080 |
0.002 |
0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC63
|
3.69% |
67.586 |
70.078 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC63
|
3.51% |
41.707 |
43.171 |
0.005 |
-1.09% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC64
|
3.48% |
41.722 |
43.173 |
0.001 |
-1.36% |
0.001 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<31, EqZero, First>
|
3.46% |
3223.218 |
3334.845 |
5.336 |
3.12% |
5.336 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC31
|
3.40% |
90.804 |
93.893 |
0.073 |
0.13% |
0.073 |
|
External/SPEC/CFP2017rate/544.nab_r/544.nab_r
Profile
|
3.30% |
460.729 |
475.929 |
0.336 |
0.01% |
0.336 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_PRESSURE_CALC_LAMBDA/44217
|
3.25% |
489.103 |
504.985 |
3.872 |
-0.02% |
3.872 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1BigLoopWithReductionTC1
|
3.21% |
19.400 |
20.023 |
0.002 |
-0.00% |
0.002 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C/CoMD/CoMD
Profile
|
3.17% |
9.637 |
9.943 |
0.006 |
-0.22% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchVecWithRuntimeChecks4PointersDBeforeA/1000
|
3.15% |
4866070.868 |
5019558.439 |
436.472 |
-0.01% |
436.472 |
|
SingleSource/Benchmarks/BenchmarkGame/puzzle
Profile
|
3.15% |
0.857 |
0.884 |
0.001 |
-0.26% |
0.001 |
|
SingleSource/Benchmarks/Shootout/Shootout-lists
Profile
|
3.11% |
10.971 |
11.312 |
0.001 |
2.14% |
0.001 |
|
External/SPEC/CINT2017rate/531.deepsjeng_r/531.deepsjeng_r
Profile
|
3.08% |
255.661 |
263.543 |
0.085 |
-4.27% |
0.085 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC8
|
3.06% |
40.676 |
41.922 |
0.003 |
3.02% |
0.003 |
|
External/SPEC/CINT2017rate/525.x264_r/525.x264_r
Profile
|
2.90% |
127.856 |
131.568 |
0.168 |
1.13% |
0.168 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC64
|
2.86% |
108.275 |
111.375 |
0.009 |
0.00% |
0.009 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_PRESSURE_CALC_RAW/44217
|
2.84% |
489.062 |
502.960 |
3.148 |
0.40% |
3.148 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC1
|
2.83% |
21.902 |
22.523 |
0.001 |
2.83% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC1
|
2.81% |
21.908 |
22.525 |
0.011 |
0.00% |
0.011 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<31, GreaterThanZero, Last>
|
2.71% |
8133.487 |
8354.139 |
25.145 |
2.47% |
25.145 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC63
|
2.66% |
117.023 |
120.139 |
0.002 |
0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint8_t_To_uint32_t_
|
2.59% |
6898.645 |
7077.209 |
0.205 |
0.00% |
0.205 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC8
|
2.55% |
24.405 |
25.027 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1LoopWithReductionTC8
|
2.52% |
21.972 |
22.525 |
0.003 |
5.88% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchVecWithRuntimeChecks4PointersDBeforeA/32
|
2.49% |
162142.156 |
166180.169 |
1.798 |
-0.00% |
1.798 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_BAND_LIN_EQ_LAMBDA/5001
|
2.48% |
20.248 |
20.750 |
0.069 |
-2.04% |
0.069 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC7
|
2.42% |
36.657 |
37.544 |
0.001 |
3.36% |
0.001 |
|
SingleSource/Benchmarks/Misc/fbench
Profile
|
2.36% |
5.628 |
5.761 |
0.000 |
0.00% |
0.000 |
|
External/SPEC/CFP2017rate/519.lbm_r/519.lbm_r
Profile
|
2.31% |
195.515 |
200.022 |
1.009 |
-1.17% |
1.009 |
|
MultiSource/Applications/obsequi/Obsequi
Profile
|
2.29% |
7.631 |
7.806 |
0.021 |
-0.08% |
0.021 |
|
SingleSource/Benchmarks/Misc/flops-1
Profile
|
2.19% |
8.807 |
9.000 |
0.000 |
0.00% |
0.000 |
|
MultiSource/Benchmarks/FreeBench/fourinarow/fourinarow
Profile
|
2.18% |
0.637 |
0.650 |
0.000 |
0.02% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC128
|
2.13% |
117.022 |
119.515 |
0.002 |
0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC128
|
2.12% |
117.028 |
119.507 |
0.002 |
0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC127
|
2.12% |
117.644 |
120.136 |
0.006 |
0.00% |
0.006 |
|
SingleSource/Benchmarks/Misc-C++/Large/ray
Profile
|
2.11% |
11.850 |
12.100 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC127
|
2.10% |
117.654 |
120.130 |
0.007 |
-0.00% |
0.007 |
|
MultiSource/Benchmarks/sim/sim
Profile
|
2.00% |
9.506 |
9.697 |
0.011 |
-1.57% |
0.011 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, LessThanZero, None>
|
1.85% |
36534.793 |
37212.026 |
81.321 |
0.27% |
81.321 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopFrom_uint8_t_To_uint16_t_
|
1.82% |
2176.903 |
2216.619 |
5.072 |
-1.66% |
5.072 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC15
|
1.79% |
68.851 |
70.082 |
0.002 |
1.79% |
0.002 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_FLOYD_DITHER/128
|
1.79% |
430.744 |
438.444 |
2.338 |
-0.05% |
2.338 |
|
MultiSource/Benchmarks/Olden/health/health
Profile
|
1.79% |
1.565 |
1.593 |
0.004 |
-0.03% |
0.004 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_EOS_RAW/171
|
1.77% |
0.857 |
0.872 |
0.000 |
0.01% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1LoopWithReductionTC15
|
1.77% |
35.044 |
35.665 |
0.002 |
3.63% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC16
|
1.68% |
14.154 |
14.391 |
0.001 |
4.54% |
0.001 |
|
MultiSource/Benchmarks/ASC_Sequoia/CrystalMk/CrystalMk
Profile
|
1.67% |
15.329 |
15.584 |
0.000 |
-0.04% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1LoopWithReductionTC16
|
1.67% |
36.926 |
37.542 |
0.001 |
3.43% |
0.001 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<16, EqZero, None>
|
1.64% |
8043.870 |
8175.421 |
49.650 |
-0.02% |
49.650 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint8_t_To_uint32_t_
|
1.63% |
11974.047 |
12168.939 |
11.740 |
0.22% |
11.740 |
|
MicroBenchmarks/ImageProcessing/Dilate/Dilate.test:BENCHMARK_DILATE/512
|
1.61% |
3536.436 |
3593.433 |
14.137 |
0.15% |
14.137 |
|
MultiSource/Benchmarks/tramp3d-v4/tramp3d-v4
Profile
|
1.56% |
1.062 |
1.079 |
0.003 |
0.40% |
0.003 |
|
SingleSource/Benchmarks/Misc/mandel-2
Profile
|
1.55% |
2.496 |
2.535 |
0.000 |
-0.00% |
0.000 |
|
MultiSource/Benchmarks/MallocBench/cfrac/cfrac
Profile
|
1.51% |
2.746 |
2.787 |
0.001 |
-0.36% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC128
|
1.49% |
208.400 |
211.510 |
0.007 |
-0.00% |
0.007 |
|
MultiSource/Benchmarks/mafft/pairlocalalign
Profile
|
1.48% |
92.417 |
93.780 |
0.298 |
-0.00% |
0.298 |
|
SingleSource/Benchmarks/Misc/ReedSolomon
Profile
|
1.46% |
20.416 |
20.714 |
0.000 |
-0.40% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_INT_PREDICT_RAW/171
|
1.42% |
6.829 |
6.925 |
0.011 |
0.01% |
0.011 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC127
|
1.40% |
217.207 |
220.258 |
0.020 |
-0.00% |
0.020 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<6, LessThanZero, Mid>
|
1.39% |
23545.600 |
23872.948 |
6.687 |
1.56% |
6.687 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_COUPLE_RAW/2
|
1.37% |
10.597 |
10.743 |
0.003 |
1.59% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint8_t_To_uint64_t_
|
1.34% |
22560.535 |
22862.537 |
18.910 |
0.39% |
18.910 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_INT_PREDICT_LAMBDA/171
|
1.29% |
6.833 |
6.922 |
0.006 |
-0.05% |
0.006 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_EOS_LAMBDA/171
|
1.29% |
0.860 |
0.871 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint16_t_To_uint8_t_
|
1.29% |
4380.077 |
4436.466 |
0.927 |
-0.69% |
0.927 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC32
|
1.27% |
49.430 |
50.057 |
0.003 |
0.35% |
0.003 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_COUPLE_RAW/0
|
1.23% |
8012.445 |
8111.312 |
8.088 |
1.35% |
8.088 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, LessThanZero, Mid>
|
1.23% |
55843.266 |
56528.374 |
30.854 |
-1.89% |
30.854 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC63
|
1.21% |
128.643 |
130.204 |
0.010 |
0.20% |
0.010 |
|
MicroBenchmarks/Builtins/Int128/Builtins.test:BM_RemainderIntrinsic128UniformDivisor<__int128_t>
|
1.20% |
66.040 |
66.832 |
0.176 |
0.13% |
0.176 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<16, LessThanZero, Last>
|
1.15% |
12992.322 |
13141.576 |
0.936 |
1.12% |
0.936 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_FLOYD_DITHER/512
|
1.15% |
6579.770 |
6655.111 |
1.087 |
0.05% |
1.087 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<8, LessThanZero, Mid>
|
1.13% |
19265.590 |
19483.295 |
23.456 |
1.29% |
23.456 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<32, EqZero, Last>
|
1.10% |
6974.929 |
7051.588 |
1.191 |
1.49% |
1.191 |
|
MultiSource/Benchmarks/Ptrdist/bc/bc
Profile
|
1.09% |
1.562 |
1.580 |
0.002 |
-0.02% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_sinhf_autovec_float_
|
1.05% |
2218.601 |
2241.958 |
0.424 |
-0.03% |
0.424 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_sinhf_novec_float_
|
1.05% |
2218.802 |
2242.067 |
0.343 |
0.00% |
0.343 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<3, EqZero, Mid>
|
1.04% |
37213.961 |
37601.131 |
49.280 |
-0.10% |
49.280 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_sinh_novec_double_
|
1.03% |
2448.115 |
2473.286 |
1.535 |
0.00% |
1.535 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<6, GreaterThanZero, None>
|
1.02% |
29406.081 |
29705.709 |
59.320 |
2.54% |
59.320 |
|
SingleSource/Benchmarks/SmallPT/smallpt
Profile
|
1.00% |
29.714 |
30.012 |
0.005 |
-0.01% |
0.005 |