|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_INT_PREDICT_RAW/44217
|
134.12% |
8188.347 |
19170.449 |
136.227 |
-0.81% |
136.227 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint64_t_To_uint16_t_
|
118.08% |
17771.770 |
38757.466 |
119.910 |
8.95% |
119.910 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint64_t_To_uint32_t_
|
109.17% |
17197.178 |
35972.194 |
171.442 |
0.79% |
171.442 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint64_t_To_uint8_t_
|
96.59% |
18715.194 |
36792.897 |
15.857 |
1.34% |
15.857 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_INT_PREDICT_LAMBDA/44217
|
93.76% |
8179.155 |
15848.271 |
1746.910 |
-14.49% |
1746.910 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C/miniGMG/miniGMG
Profile
|
92.63% |
4.687 |
9.028 |
0.233 |
-4.53% |
0.233 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint16_t_To_uint64_t_
|
78.17% |
10473.889 |
18661.367 |
193.578 |
-1.05% |
193.578 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_INT_PREDICT_RAW/5001
|
76.46% |
917.248 |
1618.598 |
179.489 |
-18.21% |
179.489 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_DIFF_PREDICT_RAW/44217
|
72.10% |
14111.593 |
24285.975 |
979.998 |
-0.07% |
979.998 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_DIFF_PREDICT_LAMBDA/44217
|
71.56% |
14109.033 |
24205.164 |
1056.237 |
0.53% |
1056.237 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint64_t_To_uint32_t_
|
69.53% |
22731.461 |
38536.489 |
134.517 |
2.08% |
134.517 |
|
SingleSource/Benchmarks/Adobe-C++/loop_unroll
Profile
|
68.94% |
2.403 |
4.060 |
0.001 |
0.06% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint8_t_To_uint64_t_
|
68.52% |
10546.946 |
17773.615 |
423.387 |
-0.00% |
423.387 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIRST_DIFF_LAMBDA/44217
|
66.30% |
104.611 |
173.968 |
5.035 |
0.93% |
5.035 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_DIFF_PREDICT_LAMBDA/5001
|
63.46% |
1535.994 |
2510.688 |
183.098 |
-1.50% |
183.098 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_HYDRO_2D_LAMBDA/44217
|
62.42% |
57396.160 |
93220.756 |
2403.708 |
-0.10% |
2403.708 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_DIFF_PREDICT_RAW/5001
|
60.34% |
1580.026 |
2533.475 |
186.907 |
-0.42% |
186.907 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/32
|
59.32% |
884.443 |
1409.131 |
0.035 |
-0.00% |
0.035 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/64
|
59.25% |
3916.043 |
6236.147 |
0.318 |
0.00% |
0.318 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/16
|
59.24% |
177.147 |
282.092 |
0.009 |
-0.01% |
0.009 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/256
|
57.74% |
68469.887 |
108006.541 |
2.640 |
0.05% |
2.640 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIRST_DIFF_RAW/44217
|
57.53% |
102.317 |
161.181 |
11.713 |
10.72% |
11.713 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/128
|
57.18% |
16828.510 |
26451.708 |
9.938 |
-0.00% |
9.938 |
|
MultiSource/Benchmarks/MiBench/automotive-susan/automotive-susan
Profile
|
55.21% |
0.100 |
0.155 |
0.000 |
-46.26% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint64_t_To_uint16_t_
|
53.79% |
19194.513 |
29519.583 |
116.667 |
-0.06% |
116.667 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint64_t_To_uint8_t_
|
51.32% |
19805.177 |
29969.330 |
256.386 |
-0.31% |
256.386 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_HYDRO_2D_LAMBDA/5001
|
51.22% |
6330.538 |
9573.303 |
342.997 |
-1.39% |
342.997 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint32_t_To_uint64_t_
|
51.06% |
15760.725 |
23808.249 |
1595.357 |
3.10% |
1595.357 |
|
MultiSource/Benchmarks/MiBench/automotive-bitcount/automotive-bitcount
Profile
|
49.82% |
0.112 |
0.167 |
0.001 |
-0.29% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint32_t_To_uint8_t_
|
41.58% |
9727.301 |
13772.379 |
67.539 |
2.56% |
67.539 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC128
|
41.51% |
943.253 |
1334.837 |
0.026 |
-0.01% |
0.026 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC127
|
40.97% |
937.627 |
1321.799 |
0.089 |
-0.00% |
0.089 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC64
|
39.66% |
482.532 |
673.892 |
0.033 |
-0.01% |
0.033 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC63
|
38.56% |
476.908 |
660.812 |
0.254 |
0.01% |
0.254 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC128
|
37.34% |
942.527 |
1294.457 |
4.219 |
-0.20% |
4.219 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC128
|
37.04% |
407.670 |
558.676 |
0.096 |
0.03% |
0.096 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_PIC_2D_LAMBDA/44217
|
36.48% |
8725.627 |
11908.916 |
13.127 |
-0.11% |
13.127 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint64_t_To_uint16_t_
|
36.32% |
18664.028 |
25442.643 |
9.090 |
-1.94% |
9.090 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC32
|
36.20% |
252.211 |
343.515 |
0.017 |
-0.01% |
0.017 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC64
|
36.14% |
480.408 |
654.020 |
2.265 |
-0.43% |
2.265 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC32
|
36.05% |
245.824 |
334.432 |
0.978 |
-0.47% |
0.978 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC16
|
35.41% |
128.805 |
174.418 |
0.510 |
-0.56% |
0.510 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC64
|
34.43% |
217.356 |
292.200 |
0.048 |
0.05% |
0.048 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC31
|
33.95% |
246.640 |
330.382 |
0.296 |
-0.00% |
0.296 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIRST_SUM_RAW/44217
|
33.61% |
136.662 |
182.597 |
0.510 |
-2.81% |
0.510 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_HYDRO_2D_RAW/44217
|
31.60% |
65460.295 |
86145.328 |
3374.833 |
-9.50% |
3374.833 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint32_t_To_uint8_t_
|
31.19% |
11390.637 |
14943.380 |
56.772 |
5.18% |
56.772 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIRST_SUM_LAMBDA/44217
|
30.60% |
136.829 |
178.696 |
4.389 |
-1.91% |
4.389 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC16
|
30.12% |
137.048 |
178.331 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC128
|
30.02% |
464.459 |
603.885 |
0.045 |
-0.01% |
0.045 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC32
|
29.94% |
122.217 |
158.811 |
0.062 |
-0.10% |
0.062 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_DISC_ORD_LAMBDA/44217
|
29.64% |
11452.023 |
14846.613 |
177.720 |
0.36% |
177.720 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint64_t_To_uint8_t_
|
29.56% |
20522.640 |
26588.836 |
17.405 |
-3.96% |
17.405 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC128
|
29.15% |
467.603 |
603.900 |
0.016 |
0.19% |
0.016 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint16_t_To_uint64_t_
|
28.77% |
10378.303 |
13364.402 |
71.287 |
-0.86% |
71.287 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC64
|
28.44% |
244.079 |
313.486 |
0.003 |
0.38% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC64
|
28.43% |
244.084 |
313.479 |
0.008 |
-0.01% |
0.008 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC127
|
28.15% |
480.086 |
615.216 |
0.061 |
0.09% |
0.061 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC127
|
28.12% |
480.169 |
615.172 |
0.041 |
-0.01% |
0.041 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint8_t_To_uint32_t_
|
27.66% |
5167.207 |
6596.582 |
86.927 |
-0.42% |
86.927 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint16_t_To_uint32_t_
|
27.29% |
5586.540 |
7111.164 |
62.342 |
-0.01% |
62.342 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC4
|
27.26% |
13.767 |
17.519 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_VOL3D_CALC_RAW/2
|
27.23% |
7.112 |
9.049 |
0.000 |
8.77% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_VOL3D_CALC_LAMBDA/2
|
27.23% |
7.112 |
9.048 |
0.001 |
8.76% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_HYDRO_2D_RAW/5001
|
27.17% |
7131.727 |
9069.475 |
380.758 |
-6.57% |
380.758 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIND_FIRST_MIN_LAMBDA/171
|
26.95% |
1.181 |
1.500 |
0.000 |
-0.04% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIND_FIRST_MIN_LAMBDA/44217
|
26.73% |
307.076 |
389.164 |
0.576 |
-0.02% |
0.576 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC63
|
26.12% |
122.177 |
154.092 |
1.066 |
7.34% |
1.066 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC127
|
25.74% |
218.854 |
275.186 |
1.398 |
3.97% |
1.398 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC15
|
25.69% |
131.425 |
165.187 |
0.296 |
-0.00% |
0.296 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC32
|
25.68% |
133.925 |
168.313 |
0.004 |
-0.00% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC32
|
25.67% |
133.925 |
168.310 |
0.010 |
0.73% |
0.010 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC63
|
25.04% |
259.740 |
324.770 |
0.045 |
0.17% |
0.045 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC63
|
25.03% |
259.749 |
324.755 |
0.005 |
-0.01% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC128
|
24.91% |
219.442 |
274.107 |
0.800 |
3.78% |
0.800 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIND_FIRST_MIN_LAMBDA/5001
|
24.65% |
36.296 |
45.243 |
0.071 |
0.56% |
0.071 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC127
|
24.49% |
514.913 |
641.019 |
0.227 |
-0.01% |
0.227 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint8_t_To_uint64_t_
|
24.34% |
10920.372 |
13578.459 |
124.583 |
6.23% |
124.583 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_PIC_2D_LAMBDA/5001
|
23.71% |
976.633 |
1208.214 |
38.067 |
1.22% |
38.067 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_PIC_2D_RAW/5001
|
23.64% |
973.631 |
1203.762 |
20.573 |
-1.19% |
20.573 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC16
|
23.62% |
74.658 |
92.291 |
0.013 |
-0.01% |
0.013 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC64
|
23.60% |
120.630 |
149.100 |
2.068 |
4.08% |
2.068 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_VOL3D_CALC_LAMBDA/1
|
23.17% |
218.164 |
268.703 |
0.115 |
7.72% |
0.115 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint64_t_To_uint32_t_
|
23.07% |
22123.375 |
27226.371 |
27.694 |
0.41% |
27.694 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, EqZero, None>
|
23.03% |
16671.251 |
20509.866 |
1.242 |
0.00% |
1.242 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_VOL3D_CALC_RAW/1
|
23.00% |
218.417 |
268.651 |
0.072 |
7.57% |
0.072 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_VOL3D_CALC_RAW/0
|
22.55% |
1064.317 |
1304.334 |
0.689 |
5.98% |
0.689 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_VOL3D_CALC_LAMBDA/0
|
22.31% |
1063.656 |
1300.964 |
1.907 |
5.75% |
1.907 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, EqZero, Last>
|
22.19% |
11541.787 |
14102.510 |
0.372 |
-0.00% |
0.372 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint16_t_To_uint8_t_
|
22.12% |
3089.858 |
3773.255 |
0.441 |
-0.58% |
0.441 |
|
MultiSource/Benchmarks/TSVC/Searching-flt/Searching-flt
Profile
|
22.11% |
4.153 |
5.071 |
0.014 |
2.34% |
0.014 |
|
MultiSource/Benchmarks/Trimaran/enc-pc1/enc-pc1
Profile
|
22.10% |
0.905 |
1.104 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC32
|
21.58% |
70.955 |
86.269 |
0.607 |
5.47% |
0.607 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC16
|
21.41% |
78.850 |
95.735 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC16
|
21.41% |
78.850 |
95.731 |
0.007 |
1.32% |
0.007 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint32_t_To_uint16_t_
|
21.24% |
11055.207 |
13403.477 |
69.406 |
0.19% |
69.406 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC128
|
21.01% |
471.653 |
570.763 |
0.008 |
0.21% |
0.008 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC64
|
20.91% |
246.330 |
297.838 |
0.031 |
0.40% |
0.031 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC32
|
20.69% |
133.625 |
161.271 |
0.078 |
0.67% |
0.078 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC16
|
20.61% |
77.293 |
93.226 |
0.006 |
1.35% |
0.006 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_PIC_2D_RAW/44217
|
20.42% |
9843.922 |
11853.831 |
25.092 |
-1.06% |
25.092 |
|
MultiSource/Benchmarks/TSVC/Searching-dbl/Searching-dbl
Profile
|
20.25% |
7.594 |
9.132 |
0.018 |
0.10% |
0.018 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC31
|
20.06% |
149.573 |
179.580 |
0.013 |
0.34% |
0.013 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC31
|
20.05% |
149.578 |
179.573 |
0.005 |
-0.01% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC8
|
19.73% |
49.122 |
58.815 |
0.003 |
2.16% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC8
|
19.50% |
80.111 |
95.732 |
0.004 |
0.00% |
0.004 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_PIC_1D_LAMBDA/44217
|
19.44% |
11365.692 |
13575.114 |
37.144 |
0.26% |
37.144 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint32_t_To_uint16_t_
|
19.00% |
11243.349 |
13379.325 |
37.586 |
-3.53% |
37.586 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_HYDRO_1D_RAW/171
|
18.95% |
0.372 |
0.442 |
0.000 |
0.12% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC8
|
18.75% |
20.023 |
23.777 |
0.002 |
0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint32_t_To_uint64_t_
|
18.71% |
16532.419 |
19625.947 |
857.055 |
8.74% |
857.055 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_HYDRO_1D_LAMBDA/171
|
18.69% |
0.372 |
0.441 |
0.001 |
-0.43% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint16_t_To_uint32_t_
|
18.39% |
6297.503 |
7455.695 |
0.241 |
-0.02% |
0.241 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC31
|
18.29% |
73.021 |
86.375 |
0.579 |
4.42% |
0.579 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_no_runtime_checks_needed<16, int>
|
18.17% |
20.650 |
24.402 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint32_t_To_uint8_t_
|
18.05% |
9547.997 |
11271.115 |
24.626 |
0.64% |
24.626 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC127
|
17.53% |
515.433 |
605.781 |
0.021 |
0.08% |
0.021 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint32_t_To_uint8_t_
|
17.15% |
9080.050 |
10637.177 |
101.969 |
-1.28% |
101.969 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC8
|
16.82% |
19.818 |
23.152 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC4
|
16.60% |
13.143 |
15.325 |
0.003 |
11.31% |
0.003 |
|
SingleSource/Benchmarks/Misc/salsa20
Profile
|
16.43% |
13.212 |
15.383 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint32_t_To_uint16_t_
|
16.33% |
8873.631 |
10322.577 |
233.447 |
1.01% |
233.447 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint8_t_To_uint16_t_
|
16.17% |
3234.303 |
3757.144 |
0.468 |
-0.01% |
0.468 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC1
|
16.07% |
44.743 |
51.934 |
0.001 |
5.06% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC4
|
16.07% |
44.744 |
51.934 |
0.002 |
5.06% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC7
|
16.07% |
44.743 |
51.933 |
0.003 |
5.06% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC2
|
16.07% |
44.745 |
51.933 |
0.002 |
5.05% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC8
|
16.06% |
44.749 |
51.937 |
0.000 |
4.91% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint64_t_To_uint16_t_
|
16.04% |
18170.761 |
21085.488 |
6.712 |
10.53% |
6.712 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC3
|
16.04% |
44.756 |
51.934 |
0.002 |
5.05% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC8
|
15.84% |
51.315 |
59.444 |
0.008 |
2.14% |
0.008 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC8
|
15.82% |
51.320 |
59.440 |
0.003 |
-0.00% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint64_t_To_uint8_t_
|
15.48% |
18710.858 |
21607.567 |
31.323 |
0.08% |
31.323 |
|
External/SPEC/CFP2017rate/508.namd_r/508.namd_r
Profile
|
15.43% |
193.464 |
223.314 |
0.445 |
1.21% |
0.445 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC63
|
15.40% |
324.483 |
374.450 |
0.106 |
-0.02% |
0.106 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC128
|
15.03% |
70.711 |
81.340 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC4
|
14.83% |
97.877 |
112.394 |
2.212 |
-0.78% |
2.212 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint8_t_To_uint16_t_
|
14.78% |
3954.464 |
4538.855 |
0.066 |
0.01% |
0.066 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC63
|
14.74% |
290.116 |
332.891 |
0.111 |
0.17% |
0.111 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIRST_SUM_RAW/5001
|
14.57% |
17.981 |
20.602 |
0.114 |
-0.11% |
0.114 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC16
|
14.37% |
45.407 |
51.934 |
0.003 |
5.04% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint16_t_To_uint8_t_
|
14.23% |
4156.010 |
4747.212 |
0.165 |
-0.56% |
0.165 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, EqZero, None>
|
13.59% |
14105.249 |
16022.797 |
0.319 |
-0.01% |
0.319 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIRST_SUM_LAMBDA/5001
|
13.55% |
18.075 |
20.525 |
0.355 |
-1.48% |
0.355 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC15
|
13.26% |
94.500 |
107.033 |
0.042 |
0.62% |
0.042 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC15
|
13.24% |
94.486 |
106.995 |
0.005 |
-0.53% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC15
|
12.90% |
45.997 |
51.933 |
0.004 |
5.05% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC16
|
12.76% |
29.410 |
33.163 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC4
|
12.48% |
20.025 |
22.525 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC4
|
12.48% |
20.026 |
22.525 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/ImageProcessing/Dilate/Dilate.test:BENCHMARK_DILATE/1024
|
12.23% |
6761.501 |
7588.491 |
19.887 |
0.91% |
19.887 |
|
MultiSource/Benchmarks/TSVC/CrossingThresholds-flt/CrossingThresholds-flt
Profile
|
11.98% |
9.661 |
10.818 |
0.250 |
-0.37% |
0.250 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC7
|
11.80% |
73.845 |
82.559 |
0.211 |
-0.05% |
0.211 |
|
MultiSource/Benchmarks/MiBench/security-rijndael/security-rijndael
Profile
|
11.78% |
0.279 |
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% |
29.410 |
32.801 |
0.034 |
0.80% |
0.034 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC16
|
11.52% |
32.544 |
36.292 |
0.073 |
-1.71% |
0.073 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C++/miniFE/miniFE
Profile
|
11.08% |
15.012 |
16.676 |
0.089 |
-0.19% |
0.089 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/16
|
11.07% |
103.739 |
115.222 |
0.010 |
-0.00% |
0.010 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/32
|
10.99% |
425.752 |
472.521 |
0.013 |
-0.01% |
0.013 |
|
SingleSource/Benchmarks/Misc-C++/oopack_v1p8
Profile
|
10.96% |
0.468 |
0.519 |
0.000 |
-0.02% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC8
|
10.81% |
23.152 |
25.654 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC8
|
10.80% |
23.153 |
25.653 |
0.003 |
-0.00% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC127
|
10.76% |
91.990 |
101.887 |
0.033 |
0.51% |
0.033 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC31
|
10.74% |
177.419 |
196.472 |
0.020 |
0.30% |
0.020 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/256
|
10.72% |
28374.602 |
31417.360 |
21.292 |
-0.02% |
21.292 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC16
|
10.70% |
28.829 |
31.912 |
0.001 |
0.35% |
0.001 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/64
|
10.67% |
1727.654 |
1912.033 |
1.278 |
-0.00% |
1.278 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/128
|
10.61% |
7149.775 |
7908.461 |
6.584 |
0.02% |
6.584 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC7
|
10.52% |
23.779 |
26.280 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC1
|
10.51% |
11.890 |
13.140 |
0.000 |
6.50% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC7
|
10.25% |
23.836 |
26.279 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_DEL_DOT_VEC_2D_RAW/1
|
10.05% |
260.736 |
286.927 |
0.153 |
-0.05% |
0.153 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_DEL_DOT_VEC_2D_LAMBDA/1
|
10.03% |
260.864 |
287.032 |
0.021 |
-0.04% |
0.021 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC4
|
9.98% |
37.549 |
41.297 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC4
|
9.98% |
37.548 |
41.296 |
0.001 |
3.12% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC32
|
9.87% |
48.406 |
53.187 |
0.007 |
0.00% |
0.007 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_DEL_DOT_VEC_2D_LAMBDA/2
|
9.53% |
3.204 |
3.510 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC2
|
9.52% |
13.141 |
14.391 |
0.000 |
4.54% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC4
|
9.52% |
13.141 |
14.391 |
0.000 |
4.54% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC15
|
9.52% |
13.141 |
14.392 |
0.000 |
4.55% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_DEL_DOT_VEC_2D_RAW/2
|
9.51% |
3.205 |
3.510 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC1
|
9.51% |
13.141 |
14.391 |
0.000 |
4.53% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC2
|
9.51% |
13.141 |
14.391 |
0.001 |
4.54% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC7
|
9.51% |
13.141 |
14.391 |
0.000 |
4.54% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC8
|
9.51% |
13.141 |
14.391 |
0.000 |
4.54% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC8
|
9.51% |
13.142 |
14.391 |
0.001 |
4.54% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC3
|
9.51% |
13.142 |
14.392 |
0.000 |
4.53% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC7
|
9.50% |
13.142 |
14.391 |
0.000 |
4.53% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC16
|
9.50% |
13.142 |
14.391 |
0.001 |
4.54% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC3
|
9.50% |
13.142 |
14.391 |
0.000 |
4.53% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC16
|
9.50% |
13.143 |
14.392 |
0.000 |
4.54% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC1
|
9.49% |
13.145 |
14.393 |
0.001 |
2.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC15
|
9.48% |
13.144 |
14.391 |
0.000 |
4.54% |
0.000 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_runtime_checks_fail<4, int>
|
9.47% |
15.330 |
16.782 |
0.022 |
0.00% |
0.022 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint8_t_To_uint16_t_
|
9.37% |
5258.192 |
5750.875 |
1.395 |
-0.79% |
1.395 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_DIFF_PREDICT_LAMBDA/171
|
9.28% |
11.269 |
12.315 |
0.029 |
-0.52% |
0.029 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC64
|
8.74% |
85.736 |
93.230 |
0.009 |
-0.00% |
0.009 |
|
MultiSource/Benchmarks/FreeBench/pifft/pifft
Profile
|
8.53% |
0.329 |
0.357 |
0.000 |
-0.02% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC16
|
8.50% |
29.412 |
31.911 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC16
|
8.49% |
29.413 |
31.911 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC32
|
8.47% |
36.920 |
40.046 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC15
|
8.31% |
30.039 |
32.537 |
0.000 |
-0.01% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint64_t_To_uint32_t_
|
8.25% |
17419.098 |
18855.343 |
525.753 |
2.38% |
525.753 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_DIFF_PREDICT_RAW/171
|
8.22% |
11.424 |
12.363 |
0.035 |
-0.48% |
0.035 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_DEL_DOT_VEC_2D_LAMBDA/0
|
8.19% |
1662.613 |
1798.769 |
2.051 |
-0.03% |
2.051 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC15
|
8.18% |
50.323 |
54.439 |
0.004 |
0.00% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC31
|
8.12% |
68.874 |
74.465 |
0.006 |
0.01% |
0.006 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_DEL_DOT_VEC_2D_RAW/0
|
8.11% |
1663.877 |
1798.738 |
4.907 |
0.11% |
4.907 |
|
MultiSource/Benchmarks/VersaBench/beamformer/beamformer
Profile
|
8.10% |
4.808 |
5.198 |
0.001 |
34.97% |
0.001 |
|
MultiSource/Benchmarks/Trimaran/enc-md5/enc-md5
Profile
|
8.07% |
3.245 |
3.506 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_HYDRO_2D_LAMBDA/171
|
8.07% |
82.164 |
88.794 |
0.498 |
-0.17% |
0.498 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC2
|
7.99% |
15.645 |
16.895 |
0.001 |
3.85% |
0.001 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_xor_no_runtime_checks_needed<16, int>
|
7.99% |
15.645 |
16.894 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint16_t_To_uint8_t_
|
7.95% |
6232.541 |
6727.758 |
1.340 |
-0.67% |
1.340 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC128
|
7.76% |
160.846 |
173.328 |
0.002 |
0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint8_t>/127
|
7.74% |
128.927 |
138.906 |
0.002 |
0.00% |
0.002 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIND_FIRST_MIN_RAW/171
|
7.66% |
1.390 |
1.497 |
0.000 |
-0.04% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIRST_DIFF_RAW/5001
|
7.66% |
12.076 |
13.001 |
0.178 |
0.05% |
0.178 |
|
SingleSource/Benchmarks/Misc/pi
Profile
|
7.52% |
1.657 |
1.782 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC15
|
7.46% |
41.926 |
45.052 |
0.002 |
0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC4
|
7.40% |
50.688 |
54.438 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC63
|
7.21% |
106.807 |
114.508 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_HYDRO_2D_RAW/171
|
7.12% |
82.821 |
88.715 |
0.334 |
-0.36% |
0.334 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC63
|
6.98% |
69.457 |
74.303 |
0.017 |
0.63% |
0.017 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_xor_runtime_checks_fail<16, int>
|
6.97% |
26.908 |
28.783 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_xor_runtime_checks_pass<16, int>
|
6.93% |
26.915 |
28.782 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC127
|
6.85% |
63.829 |
68.204 |
0.007 |
-0.76% |
0.007 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC128
|
6.85% |
63.829 |
68.202 |
0.001 |
-0.91% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint32_t_To_uint8_t_
|
6.75% |
9358.594 |
9990.225 |
84.374 |
4.50% |
84.374 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_BAND_LIN_EQ_LAMBDA/171
|
6.74% |
0.343 |
0.366 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_BAND_LIN_EQ_RAW/171
|
6.73% |
0.343 |
0.366 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint16_t_To_uint64_t_
|
6.73% |
18812.070 |
20078.515 |
38.144 |
-0.91% |
38.144 |
|
MultiSource/Benchmarks/MiBench/telecomm-gsm/telecomm-gsm
Profile
|
6.73% |
0.625 |
0.667 |
0.000 |
0.94% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint16_t>/127
|
6.72% |
130.160 |
138.907 |
0.003 |
-0.00% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC127
|
6.66% |
182.443 |
194.602 |
0.041 |
-0.00% |
0.041 |
|
MultiSource/Benchmarks/TSVC/LoopRestructuring-flt/LoopRestructuring-flt
Profile
|
6.66% |
18.759 |
20.008 |
0.429 |
-0.28% |
0.429 |
|
SingleSource/Benchmarks/Misc-C++/Large/sphereflake
Profile
|
6.57% |
18.770 |
20.004 |
0.003 |
-0.00% |
0.003 |
|
SingleSource/Benchmarks/Misc/flops-6
Profile
|
6.55% |
1.230 |
1.311 |
0.000 |
1.23% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC32
|
6.50% |
57.579 |
61.320 |
0.001 |
-0.00% |
0.001 |
|
SingleSource/Benchmarks/Misc/perlin
Profile
|
6.33% |
6.205 |
6.598 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC127
|
6.28% |
2259.373 |
2401.204 |
29.545 |
-0.09% |
29.545 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint8_t>/65
|
6.27% |
89.496 |
95.109 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC3
|
6.24% |
20.026 |
21.276 |
0.001 |
6.10% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint32_t>/127
|
6.22% |
130.175 |
138.275 |
0.006 |
0.45% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopWithReductionTC127
|
6.08% |
82.115 |
87.107 |
0.190 |
7.51% |
0.190 |
|
MultiSource/Benchmarks/SciMark2-C/scimark2
Profile
|
6.01% |
101.811 |
107.929 |
0.040 |
0.11% |
0.040 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC16
|
5.98% |
31.292 |
33.163 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC32
|
5.97% |
41.925 |
44.428 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC32
|
5.93% |
41.937 |
44.424 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC15
|
5.93% |
121.094 |
128.269 |
0.003 |
0.48% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC31
|
5.87% |
42.552 |
45.050 |
0.003 |
0.00% |
0.003 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIND_FIRST_MIN_RAW/44217
|
5.87% |
368.582 |
390.220 |
0.036 |
0.07% |
0.036 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC31
|
5.87% |
42.554 |
45.050 |
0.001 |
-0.00% |
0.001 |
|
MultiSource/Benchmarks/Rodinia/hotspot/hotspot
Profile
|
5.65% |
1.927 |
2.036 |
0.002 |
-0.02% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC7
|
5.60% |
66.958 |
70.708 |
0.035 |
0.89% |
0.035 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIND_FIRST_MIN_RAW/5001
|
5.59% |
42.876 |
45.273 |
0.038 |
-0.01% |
0.038 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC7
|
5.59% |
66.964 |
70.707 |
0.005 |
-0.01% |
0.005 |
|
MultiSource/Benchmarks/VersaBench/ecbdes/ecbdes
Profile
|
5.47% |
5.059 |
5.335 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC1
|
5.46% |
84.365 |
88.974 |
1.599 |
0.09% |
1.599 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint8_t_To_uint32_t_
|
5.30% |
11804.469 |
12430.173 |
52.890 |
-0.04% |
52.890 |
|
MultiSource/Benchmarks/nbench/nbench
Profile
|
5.26% |
5.902 |
6.212 |
0.001 |
1.44% |
0.001 |
|
SingleSource/Benchmarks/Polybench/stencils/jacobi-2d/jacobi-2d
Profile
|
5.22% |
30.485 |
32.077 |
0.080 |
-0.63% |
0.080 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC31
|
5.18% |
229.290 |
241.176 |
0.044 |
-0.02% |
0.044 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC32
|
5.17% |
47.598 |
50.057 |
0.003 |
0.35% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC4
|
5.12% |
24.405 |
25.654 |
0.004 |
5.10% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC15
|
5.02% |
30.980 |
32.536 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1LoopWithReductionTC3
|
4.99% |
12.515 |
13.140 |
0.001 |
10.52% |
0.001 |
|
MicroBenchmarks/ImageProcessing/Blur/blur.test:BENCHMARK_boxBlurKernel/1024
|
4.82% |
23349.686 |
24475.372 |
60.918 |
-18.79% |
60.918 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_runtime_checks_pass<16, int>
|
4.82% |
51.936 |
54.437 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint16_t>/65
|
4.81% |
90.749 |
95.110 |
0.005 |
-0.01% |
0.005 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_runtime_checks_fail<16, int>
|
4.80% |
51.939 |
54.435 |
0.001 |
0.00% |
0.001 |
|
SingleSource/Benchmarks/Misc/revertBits
Profile
|
4.80% |
0.612 |
0.641 |
0.000 |
0.01% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC2
|
4.75% |
13.141 |
13.765 |
0.005 |
-0.00% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC31
|
4.66% |
66.963 |
70.082 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_PIC_2D_RAW/171
|
4.64% |
12.964 |
13.565 |
0.046 |
-0.25% |
0.046 |
|
MultiSource/Benchmarks/McCat/12-IOtest/iotest
Profile
|
4.62% |
1.765 |
1.846 |
0.003 |
-0.44% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC31
|
4.60% |
89.766 |
93.893 |
0.073 |
0.13% |
0.073 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_PIC_2D_LAMBDA/171
|
4.59% |
12.898 |
13.490 |
0.047 |
-0.15% |
0.047 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint32_t_To_uint64_t_
|
4.58% |
20418.122 |
21352.493 |
81.666 |
-0.38% |
81.666 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC64
|
4.53% |
41.300 |
43.173 |
0.001 |
-1.36% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC63
|
4.53% |
41.302 |
43.171 |
0.005 |
-1.09% |
0.005 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_PIC_1D_LAMBDA/5001
|
4.40% |
338.038 |
352.904 |
2.475 |
-2.14% |
2.475 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_ENERGY_CALC_RAW/171
|
4.38% |
13.633 |
14.230 |
0.026 |
-0.01% |
0.026 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_ENERGY_CALC_LAMBDA/171
|
4.26% |
13.644 |
14.226 |
0.033 |
-0.01% |
0.033 |
|
SingleSource/Benchmarks/Misc/flops-5
Profile
|
4.20% |
1.938 |
2.020 |
0.000 |
0.85% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint16_t_To_uint64_t_
|
4.16% |
23290.640 |
24258.758 |
30.462 |
-3.11% |
30.462 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1LoopWithReductionTC7
|
4.14% |
20.025 |
20.855 |
0.290 |
7.51% |
0.290 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint32_t>/65
|
4.12% |
90.745 |
94.483 |
0.001 |
0.66% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopWithReductionTC3
|
4.00% |
15.644 |
16.269 |
0.000 |
3.34% |
0.000 |
|
External/SPEC/CFP2017rate/544.nab_r/544.nab_r
Profile
|
3.89% |
458.087 |
475.929 |
0.336 |
0.01% |
0.336 |
|
MultiSource/Benchmarks/sim/sim
Profile
|
3.88% |
9.334 |
9.697 |
0.011 |
-1.57% |
0.011 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC31
|
3.86% |
58.201 |
60.451 |
0.023 |
0.64% |
0.023 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_PRESSURE_CALC_RAW/44217
|
3.86% |
484.285 |
502.960 |
3.148 |
0.40% |
3.148 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC64
|
3.73% |
66.958 |
69.453 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC64
|
3.72% |
66.962 |
69.451 |
0.005 |
-0.00% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC63
|
3.69% |
67.583 |
70.078 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC63
|
3.69% |
67.586 |
70.080 |
0.002 |
0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopWithReductionTC128
|
3.67% |
74.843 |
77.590 |
0.001 |
7.83% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopWithReductionTC4
|
3.56% |
17.522 |
18.146 |
0.001 |
1.77% |
0.001 |
|
External/SPEC/CINT2017rate/523.xalancbmk_r/523.xalancbmk_r
Profile
|
3.54% |
237.457 |
245.861 |
0.211 |
-0.49% |
0.211 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC64
|
3.47% |
107.643 |
111.375 |
0.009 |
0.00% |
0.009 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<32, EqZero, Last>
|
3.45% |
6816.409 |
7051.588 |
1.191 |
1.49% |
1.191 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC7
|
3.44% |
36.294 |
37.544 |
0.001 |
3.36% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1BigLoopWithReductionTC1
|
3.22% |
19.398 |
20.023 |
0.002 |
-0.00% |
0.002 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C/CoMD/CoMD
Profile
|
3.22% |
9.633 |
9.943 |
0.006 |
-0.22% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchVecWithRuntimeChecks4PointersDBeforeA/1000
|
3.12% |
4867599.813 |
5019558.439 |
436.472 |
-0.01% |
436.472 |
|
MicroBenchmarks/ImageProcessing/Dilate/Dilate.test:BENCHMARK_DILATE/256
|
3.08% |
1034.837 |
1066.728 |
5.586 |
-0.05% |
5.586 |
|
SingleSource/Benchmarks/Shootout/Shootout-lists
Profile
|
3.08% |
10.975 |
11.312 |
0.001 |
2.14% |
0.001 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<31, EqZero, First>
|
3.08% |
3235.296 |
3334.845 |
5.336 |
3.12% |
5.336 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC8
|
3.06% |
40.676 |
41.922 |
0.003 |
3.02% |
0.003 |
|
MultiSource/Benchmarks/Ptrdist/yacr2/yacr2
Profile
|
2.99% |
2.119 |
2.182 |
0.002 |
4.99% |
0.002 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_PRESSURE_CALC_LAMBDA/44217
|
2.94% |
490.562 |
504.985 |
3.872 |
-0.02% |
3.872 |
|
External/SPEC/CINT2017rate/531.deepsjeng_r/531.deepsjeng_r
Profile
|
2.86% |
256.212 |
263.543 |
0.085 |
-4.27% |
0.085 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC1
|
2.85% |
21.902 |
22.525 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1LoopWithReductionTC8
|
2.84% |
21.903 |
22.525 |
0.003 |
5.88% |
0.003 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_BAND_LIN_EQ_LAMBDA/5001
|
2.81% |
20.183 |
20.750 |
0.069 |
-2.04% |
0.069 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopWithReductionTC7
|
2.69% |
23.152 |
23.776 |
0.002 |
2.69% |
0.002 |
|
SingleSource/Benchmarks/BenchmarkGame/puzzle
Profile
|
2.69% |
0.861 |
0.884 |
0.001 |
-0.26% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC63
|
2.66% |
117.028 |
120.139 |
0.002 |
0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC32
|
2.62% |
23.779 |
24.402 |
0.001 |
2.63% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC32
|
2.62% |
23.779 |
24.402 |
0.001 |
2.61% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint8_t_To_uint32_t_
|
2.55% |
6901.512 |
7077.209 |
0.205 |
0.00% |
0.205 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC31
|
2.50% |
23.807 |
24.403 |
0.001 |
2.33% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC31
|
2.49% |
23.810 |
24.402 |
0.001 |
2.55% |
0.001 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<31, GreaterThanZero, Last>
|
2.46% |
8153.407 |
8354.139 |
25.145 |
2.47% |
25.145 |
|
MultiSource/Applications/obsequi/Obsequi
Profile
|
2.45% |
7.619 |
7.806 |
0.021 |
-0.08% |
0.021 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_ENERGY_CALC_RAW/5001
|
2.39% |
437.585 |
448.052 |
2.475 |
-0.57% |
2.475 |
|
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
|
2.34% |
195.457 |
200.022 |
1.009 |
-1.17% |
1.009 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC31
|
2.33% |
882.519 |
903.103 |
6.698 |
-0.53% |
6.698 |
|
MultiSource/Benchmarks/FreeBench/fourinarow/fourinarow
Profile
|
2.28% |
0.636 |
0.650 |
0.000 |
0.02% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchVecWithRuntimeChecks4PointersDBeforeA/32
|
2.21% |
162582.551 |
166180.169 |
1.798 |
-0.00% |
1.798 |
|
SingleSource/Benchmarks/Misc/flops-1
Profile
|
2.19% |
8.807 |
9.000 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC63
|
2.14% |
44.720 |
45.675 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC128
|
2.13% |
117.024 |
119.515 |
0.002 |
0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC63
|
2.12% |
44.718 |
45.666 |
0.007 |
-0.03% |
0.007 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC127
|
2.12% |
117.643 |
120.136 |
0.006 |
0.00% |
0.006 |
|
SingleSource/Benchmarks/Misc-C++/Large/ray
Profile
|
2.10% |
11.851 |
12.100 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC127
|
2.09% |
117.676 |
120.130 |
0.007 |
-0.00% |
0.007 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_FLOYD_DITHER/128
|
2.08% |
429.498 |
438.444 |
2.338 |
-0.05% |
2.338 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC31
|
2.08% |
30.036 |
30.659 |
0.000 |
-2.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC32
|
2.07% |
30.039 |
30.660 |
0.000 |
-1.90% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC63
|
2.02% |
127.631 |
130.204 |
0.010 |
0.20% |
0.010 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<6, GreaterThanZero, None>
|
1.97% |
29131.864 |
29705.709 |
59.320 |
2.54% |
59.320 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_BAND_LIN_EQ_RAW/5001
|
1.88% |
20.464 |
20.849 |
0.041 |
0.28% |
0.041 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<16, LessThanZero, Mid>
|
1.86% |
8504.709 |
8663.206 |
33.817 |
0.07% |
33.817 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_GEN_LIN_RECUR_LAMBDA/5001
|
1.84% |
86.919 |
88.520 |
0.182 |
0.08% |
0.182 |
|
MultiSource/Benchmarks/mafft/pairlocalalign
Profile
|
1.82% |
92.108 |
93.780 |
0.298 |
-0.00% |
0.298 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_FLOYD_DITHER/512
|
1.82% |
6536.447 |
6655.111 |
1.087 |
0.05% |
1.087 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopFrom_uint8_t_To_uint16_t_
|
1.81% |
2177.158 |
2216.619 |
5.072 |
-1.66% |
5.072 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC15
|
1.81% |
68.836 |
70.082 |
0.002 |
1.79% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1LoopWithReductionTC15
|
1.78% |
35.041 |
35.665 |
0.002 |
3.63% |
0.002 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_EOS_RAW/171
|
1.75% |
0.857 |
0.872 |
0.000 |
0.01% |
0.000 |
|
MultiSource/Benchmarks/Olden/health/health
Profile
|
1.70% |
1.566 |
1.593 |
0.004 |
-0.03% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1LoopWithReductionTC16
|
1.68% |
36.922 |
37.542 |
0.001 |
3.43% |
0.001 |
|
MultiSource/Benchmarks/ASC_Sequoia/CrystalMk/CrystalMk
Profile
|
1.65% |
15.331 |
15.584 |
0.000 |
-0.04% |
0.000 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<6, LessThanZero, Mid>
|
1.61% |
23495.244 |
23872.948 |
6.687 |
1.56% |
6.687 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint8_t_To_uint64_t_
|
1.59% |
22504.431 |
22862.537 |
18.910 |
0.39% |
18.910 |
|
SingleSource/Benchmarks/Misc/ReedSolomon
Profile
|
1.57% |
20.394 |
20.714 |
0.000 |
-0.40% |
0.000 |
|
SingleSource/Benchmarks/Misc/mandel-2
Profile
|
1.55% |
2.497 |
2.535 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, GreaterThanZero, None>
|
1.52% |
36536.374 |
37093.337 |
4.990 |
0.20% |
4.990 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC128
|
1.50% |
85.132 |
86.409 |
0.171 |
2.54% |
0.171 |
|
MultiSource/Benchmarks/MallocBench/cfrac/cfrac
Profile
|
1.46% |
2.747 |
2.787 |
0.001 |
-0.36% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint16_t_To_uint8_t_
|
1.45% |
4372.944 |
4436.466 |
0.927 |
-0.69% |
0.927 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_erff_autovec_float_
|
1.45% |
737.891 |
748.571 |
0.137 |
0.65% |
0.137 |
|
External/SPEC/CINT2017rate/525.x264_r/525.x264_r
Profile
|
1.42% |
129.721 |
131.568 |
0.168 |
1.13% |
0.168 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopWithReductionTC31
|
1.42% |
43.804 |
44.425 |
0.003 |
2.61% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC127
|
1.42% |
217.179 |
220.258 |
0.020 |
-0.00% |
0.020 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<16, EqZero, Mid>
|
1.39% |
8538.000 |
8656.315 |
6.533 |
1.74% |
6.533 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_INT_PREDICT_RAW/171
|
1.38% |
6.831 |
6.925 |
0.011 |
0.01% |
0.011 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_COUPLE_RAW/2
|
1.37% |
10.598 |
10.743 |
0.003 |
1.59% |
0.003 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, LessThanZero, Mid>
|
1.36% |
55770.153 |
56528.374 |
30.854 |
-1.89% |
30.854 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint8_t_To_uint32_t_
|
1.34% |
12008.102 |
12168.939 |
11.740 |
0.22% |
11.740 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_INT_PREDICT_LAMBDA/171
|
1.30% |
6.833 |
6.922 |
0.006 |
-0.05% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC64
|
1.30% |
85.247 |
86.351 |
0.003 |
0.12% |
0.003 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_EOS_LAMBDA/171
|
1.25% |
0.860 |
0.871 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_ENERGY_CALC_LAMBDA/44217
|
1.21% |
4271.552 |
4323.387 |
14.564 |
0.07% |
14.564 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_COUPLE_RAW/0
|
1.21% |
8014.350 |
8111.312 |
8.088 |
1.35% |
8.088 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<8, LessThanZero, Mid>
|
1.18% |
19256.330 |
19483.295 |
23.456 |
1.29% |
23.456 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<7, EqZero, None>
|
1.13% |
26894.482 |
27197.320 |
8.182 |
1.21% |
8.182 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_sinhf_autovec_float_
|
1.05% |
2218.564 |
2241.958 |
0.424 |
-0.03% |
0.424 |
|
MicroBenchmarks/ImageProcessing/Dilate/Dilate.test:BENCHMARK_DILATE/512
|
1.05% |
3556.222 |
3593.433 |
14.137 |
0.15% |
14.137 |
|
SingleSource/Benchmarks/SmallPT/smallpt
Profile
|
1.01% |
29.711 |
30.012 |
0.005 |
-0.01% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_sinhf_novec_float_
|
1.00% |
2219.793 |
2242.067 |
0.343 |
0.00% |
0.343 |