|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_INT_PREDICT_RAW/44217
|
136.98% |
8217.756 |
19474.457 |
69.319 |
0.78% |
69.319 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_INT_PREDICT_LAMBDA/44217
|
132.51% |
8217.354 |
19105.783 |
210.317 |
-1.88% |
210.317 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint64_t_To_uint8_t_
|
94.45% |
19113.265 |
37165.070 |
151.069 |
0.28% |
151.069 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint64_t_To_uint32_t_
|
91.74% |
18369.340 |
35221.531 |
108.208 |
-0.26% |
108.208 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint64_t_To_uint16_t_
|
86.89% |
19122.642 |
35738.645 |
189.678 |
0.12% |
189.678 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C/miniGMG/miniGMG
Profile
|
82.98% |
4.856 |
8.886 |
0.564 |
-3.31% |
0.564 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint16_t_To_uint64_t_
|
78.45% |
10447.098 |
18643.140 |
60.639 |
-0.17% |
60.639 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIRST_DIFF_RAW/44217
|
73.48% |
102.750 |
178.252 |
6.016 |
-0.80% |
6.016 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_DIFF_PREDICT_RAW/44217
|
71.37% |
14104.440 |
24170.445 |
825.966 |
-0.96% |
825.966 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint8_t_To_uint64_t_
|
69.74% |
10546.940 |
17902.249 |
87.111 |
0.43% |
87.111 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_DIFF_PREDICT_LAMBDA/44217
|
69.03% |
14260.698 |
24105.376 |
780.820 |
-0.96% |
780.820 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint64_t_To_uint32_t_
|
68.51% |
22700.297 |
38251.955 |
159.332 |
0.25% |
159.332 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIRST_DIFF_LAMBDA/44217
|
65.34% |
103.205 |
170.641 |
3.635 |
-0.32% |
3.635 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_DIFF_PREDICT_LAMBDA/5001
|
59.55% |
1594.302 |
2543.760 |
122.661 |
-1.21% |
122.661 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/32
|
57.97% |
883.898 |
1396.259 |
0.032 |
-0.00% |
0.032 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/16
|
57.80% |
177.128 |
279.504 |
0.024 |
0.00% |
0.024 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/64
|
57.74% |
3918.612 |
6181.318 |
2.195 |
-0.02% |
2.195 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/256
|
56.52% |
68440.462 |
107125.993 |
14.077 |
-0.03% |
14.077 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/128
|
56.27% |
16803.715 |
26259.523 |
4.980 |
-0.05% |
4.980 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_DIFF_PREDICT_RAW/5001
|
55.85% |
1617.319 |
2520.628 |
146.160 |
-2.10% |
146.160 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint64_t_To_uint16_t_
|
51.25% |
19174.725 |
29000.901 |
63.253 |
-0.10% |
63.253 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint64_t_To_uint8_t_
|
51.17% |
19897.249 |
30079.196 |
38.581 |
-0.11% |
38.581 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint32_t_To_uint64_t_
|
50.96% |
14888.147 |
22474.612 |
223.392 |
-1.10% |
223.392 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, EqZero, None>
|
45.41% |
14105.396 |
20511.246 |
0.511 |
-0.00% |
0.511 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint64_t_To_uint16_t_
|
39.88% |
18517.629 |
25903.150 |
12.963 |
0.02% |
12.963 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint32_t_To_uint8_t_
|
37.55% |
9796.692 |
13475.562 |
32.308 |
-0.00% |
32.308 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC128
|
37.30% |
940.984 |
1291.987 |
3.599 |
-0.06% |
3.599 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC128
|
36.93% |
407.840 |
558.442 |
0.240 |
-0.03% |
0.240 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC64
|
36.15% |
480.028 |
653.540 |
2.001 |
-0.01% |
2.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC32
|
35.71% |
246.014 |
333.877 |
1.017 |
-0.02% |
1.017 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC16
|
34.66% |
129.058 |
173.791 |
0.375 |
0.00% |
0.375 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC64
|
34.56% |
217.187 |
292.241 |
0.090 |
0.00% |
0.090 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIRST_SUM_RAW/44217
|
31.95% |
136.010 |
179.460 |
4.452 |
-4.08% |
4.452 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIRST_SUM_LAMBDA/44217
|
31.89% |
137.797 |
181.741 |
2.382 |
0.46% |
2.382 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, EqZero, None>
|
31.54% |
12182.432 |
16024.209 |
0.152 |
0.01% |
0.152 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint64_t_To_uint8_t_
|
31.44% |
20680.980 |
27182.533 |
35.561 |
-0.15% |
35.561 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC128
|
30.20% |
463.868 |
603.947 |
0.023 |
-0.00% |
0.023 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC32
|
30.18% |
122.104 |
158.952 |
0.020 |
-0.03% |
0.020 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC128
|
30.03% |
464.490 |
603.960 |
0.731 |
0.00% |
0.731 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC64
|
28.77% |
243.450 |
313.490 |
0.020 |
-0.00% |
0.020 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC127
|
28.46% |
478.888 |
615.200 |
0.084 |
-0.00% |
0.084 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC64
|
28.45% |
244.067 |
313.507 |
0.009 |
0.00% |
0.009 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC127
|
28.14% |
480.103 |
615.207 |
0.025 |
0.00% |
0.025 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint16_t_To_uint32_t_
|
27.39% |
5573.317 |
7099.836 |
23.817 |
-0.02% |
23.817 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint8_t_To_uint32_t_
|
27.28% |
5182.004 |
6595.438 |
13.818 |
0.15% |
13.818 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_only_autovec_uint8_t_
|
27.19% |
143417.895 |
182412.748 |
43.515 |
0.02% |
43.515 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIND_FIRST_MIN_LAMBDA/171
|
27.05% |
1.182 |
1.501 |
0.000 |
0.01% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint16_t_To_uint64_t_
|
26.93% |
10390.244 |
13188.564 |
212.688 |
-0.15% |
212.688 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIND_FIRST_MIN_LAMBDA/44217
|
26.38% |
308.172 |
389.471 |
0.254 |
-0.03% |
0.254 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC32
|
26.28% |
133.298 |
168.330 |
0.007 |
0.00% |
0.007 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC32
|
25.67% |
133.934 |
168.316 |
0.011 |
-0.01% |
0.011 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC63
|
25.65% |
258.479 |
324.775 |
0.026 |
-0.00% |
0.026 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC128
|
25.49% |
218.833 |
274.610 |
2.884 |
-0.05% |
2.884 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC63
|
25.04% |
259.732 |
324.766 |
0.019 |
-0.01% |
0.019 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC127
|
24.58% |
220.863 |
275.149 |
2.947 |
-0.11% |
2.947 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC127
|
24.51% |
514.770 |
640.929 |
0.113 |
-0.04% |
0.113 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIND_FIRST_MIN_LAMBDA/5001
|
24.47% |
36.310 |
45.195 |
0.174 |
-0.14% |
0.174 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC16
|
23.64% |
74.646 |
92.290 |
0.016 |
-0.01% |
0.016 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint16_t_To_uint8_t_
|
23.54% |
3090.736 |
3818.169 |
0.819 |
0.00% |
0.819 |
|
SingleSource/Benchmarks/Adobe-C++/loop_unroll
Profile
|
23.28% |
2.424 |
2.988 |
0.001 |
-3.84% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_VOL3D_CALC_LAMBDA/2
|
23.13% |
7.111 |
8.756 |
0.000 |
-0.01% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_VOL3D_CALC_RAW/2
|
23.08% |
7.113 |
8.755 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC64
|
22.64% |
121.392 |
148.872 |
2.343 |
0.16% |
2.343 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC16
|
22.39% |
78.224 |
95.740 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint32_t_To_uint8_t_
|
22.32% |
11364.400 |
13901.450 |
23.447 |
0.00% |
23.447 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint64_t_To_uint32_t_
|
22.31% |
22159.935 |
27104.443 |
18.831 |
0.06% |
18.831 |
|
MultiSource/Benchmarks/Trimaran/enc-pc1/enc-pc1
Profile
|
22.11% |
0.905 |
1.105 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint32_t_To_uint16_t_
|
22.11% |
11303.278 |
13802.315 |
6.803 |
-0.04% |
6.803 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_with_cond_arith_novec_uint8_t_
|
21.78% |
612901.864 |
746415.643 |
183.131 |
0.07% |
183.131 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC16
|
21.41% |
78.853 |
95.735 |
0.008 |
-0.00% |
0.008 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC63
|
21.37% |
123.773 |
150.225 |
2.932 |
0.21% |
2.932 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_PIC_2D_LAMBDA/44217
|
21.10% |
9810.205 |
11880.044 |
35.577 |
0.08% |
35.577 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC31
|
21.09% |
148.312 |
179.584 |
0.010 |
-0.00% |
0.010 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_PIC_2D_RAW/5001
|
20.97% |
989.070 |
1196.433 |
23.916 |
0.69% |
23.916 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint8_t_To_uint64_t_
|
20.96% |
10922.669 |
13212.106 |
161.704 |
1.13% |
161.704 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_PIC_2D_LAMBDA/5001
|
20.88% |
972.922 |
1176.098 |
39.666 |
-4.42% |
39.666 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC128
|
20.85% |
472.302 |
570.768 |
0.007 |
-0.01% |
0.007 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC4
|
20.76% |
14.508 |
17.520 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC64
|
20.64% |
246.882 |
297.850 |
0.023 |
-0.01% |
0.023 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC32
|
20.28% |
134.222 |
161.439 |
0.016 |
-0.00% |
0.016 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC31
|
20.06% |
149.583 |
179.584 |
0.009 |
0.00% |
0.009 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_with_cond_arith_novec_int32_t_
|
19.97% |
617121.678 |
740362.714 |
129.208 |
0.02% |
129.208 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC16
|
19.66% |
77.919 |
93.238 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC32
|
19.59% |
71.871 |
85.952 |
0.781 |
0.50% |
0.781 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_PIC_2D_RAW/44217
|
19.45% |
9953.194 |
11888.674 |
39.140 |
-0.41% |
39.140 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_HYDRO_1D_RAW/171
|
19.33% |
0.372 |
0.444 |
0.001 |
0.09% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_VOL3D_CALC_LAMBDA/0
|
19.17% |
1064.105 |
1268.132 |
1.398 |
-0.01% |
1.398 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_VOL3D_CALC_LAMBDA/1
|
19.08% |
218.434 |
260.118 |
0.971 |
-0.02% |
0.971 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_VOL3D_CALC_RAW/1
|
19.05% |
218.215 |
259.787 |
0.250 |
-0.13% |
0.250 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_HYDRO_1D_LAMBDA/171
|
18.94% |
0.372 |
0.442 |
0.000 |
0.07% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_VOL3D_CALC_RAW/0
|
18.81% |
1064.834 |
1265.131 |
1.399 |
-0.01% |
1.399 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint16_t_To_uint32_t_
|
18.57% |
6294.407 |
7463.023 |
0.507 |
0.00% |
0.507 |
|
MultiSource/Benchmarks/MiBench/automotive-bitcount/automotive-bitcount
Profile
|
18.38% |
0.106 |
0.125 |
0.000 |
0.39% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC8
|
18.24% |
49.747 |
58.820 |
0.004 |
0.00% |
0.004 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, EqZero, First>
|
18.18% |
14105.005 |
16669.909 |
0.766 |
-0.01% |
0.766 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_no_runtime_checks_needed<16, int>
|
18.17% |
20.650 |
24.401 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, EqZero, Mid>
|
18.14% |
14106.584 |
16665.549 |
5.749 |
-0.00% |
5.749 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, EqZero, Last>
|
18.11% |
14111.537 |
16667.535 |
0.996 |
0.00% |
0.996 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC31
|
17.89% |
73.680 |
86.860 |
0.353 |
0.45% |
0.353 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint32_t_To_uint8_t_
|
17.49% |
9069.295 |
10655.932 |
20.497 |
0.13% |
20.497 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC127
|
17.39% |
516.031 |
605.761 |
0.046 |
-0.00% |
0.046 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC8
|
17.26% |
50.695 |
59.445 |
0.004 |
-0.01% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC128
|
17.04% |
942.642 |
1103.257 |
0.097 |
-0.00% |
0.097 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC127
|
16.97% |
936.397 |
1095.289 |
0.111 |
0.00% |
0.111 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC64
|
16.72% |
481.966 |
562.564 |
0.008 |
-0.01% |
0.008 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC63
|
16.59% |
475.641 |
554.539 |
1.855 |
-0.04% |
1.855 |
|
SingleSource/Benchmarks/Misc/salsa20
Profile
|
16.45% |
13.212 |
15.386 |
0.001 |
0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC32
|
16.15% |
251.576 |
292.199 |
0.027 |
-0.01% |
0.027 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC4
|
16.08% |
44.743 |
51.937 |
0.003 |
0.01% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC7
|
16.07% |
44.744 |
51.936 |
0.004 |
0.00% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC2
|
16.07% |
44.748 |
51.939 |
0.002 |
0.01% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC3
|
16.07% |
44.746 |
51.936 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC1
|
16.07% |
44.749 |
51.939 |
0.006 |
-0.01% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC8
|
16.05% |
44.753 |
51.938 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC8
|
15.84% |
51.313 |
59.443 |
0.004 |
-0.01% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC31
|
15.81% |
245.316 |
284.101 |
0.112 |
0.00% |
0.112 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, EqZero, Mid>
|
15.77% |
12182.919 |
14104.424 |
0.213 |
0.01% |
0.213 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, EqZero, First>
|
15.77% |
12182.795 |
14103.845 |
0.485 |
0.01% |
0.485 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, EqZero, Last>
|
15.76% |
12183.603 |
14103.685 |
0.563 |
-0.01% |
0.563 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint8_t_To_uint16_t_
|
15.75% |
3245.667 |
3756.836 |
0.278 |
0.01% |
0.278 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC8
|
15.61% |
20.025 |
23.151 |
0.001 |
-0.01% |
0.001 |
|
External/SPEC/CFP2017rate/508.namd_r/508.namd_r
Profile
|
15.58% |
194.258 |
224.519 |
0.671 |
0.15% |
0.671 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC63
|
15.45% |
324.299 |
374.409 |
0.048 |
-0.00% |
0.048 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_with_cond_arith_autovec_int64_t_
|
15.43% |
685412.428 |
791179.196 |
2484.675 |
-0.05% |
2484.675 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_with_cond_arith_novec_int64_t_
|
15.37% |
684145.851 |
789311.178 |
2796.727 |
-0.09% |
2796.727 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint32_t_To_uint16_t_
|
15.34% |
11127.387 |
12834.832 |
21.471 |
-0.02% |
21.471 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC8
|
15.13% |
20.652 |
23.777 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC16
|
15.12% |
136.424 |
157.058 |
0.007 |
0.00% |
0.007 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC128
|
15.03% |
70.714 |
81.344 |
0.003 |
-0.00% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint64_t_To_uint8_t_
|
15.03% |
19091.706 |
21960.904 |
111.916 |
-0.39% |
111.916 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint8_t_To_uint16_t_
|
14.84% |
3954.852 |
4541.823 |
0.451 |
-0.00% |
0.451 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC15
|
14.76% |
93.237 |
106.998 |
0.008 |
-0.00% |
0.008 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC63
|
14.51% |
290.705 |
332.897 |
0.016 |
-0.00% |
0.016 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC15
|
14.42% |
130.167 |
148.936 |
0.006 |
0.00% |
0.006 |
|
MultiSource/Benchmarks/MiBench/security-rijndael/security-rijndael
Profile
|
14.30% |
0.294 |
0.336 |
0.001 |
-0.03% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint16_t_To_uint8_t_
|
14.16% |
4154.735 |
4743.174 |
0.686 |
0.00% |
0.686 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC16
|
14.10% |
45.524 |
51.943 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint32_t_To_uint8_t_
|
13.59% |
9660.953 |
10974.048 |
128.847 |
-1.40% |
128.847 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC8
|
13.41% |
78.848 |
89.422 |
0.029 |
0.02% |
0.029 |
|
MultiSource/Benchmarks/VersaBench/bmm/bmm
Profile
|
13.36% |
26.515 |
30.056 |
0.930 |
12.82% |
0.930 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC2
|
13.30% |
18.778 |
21.275 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC4
|
13.30% |
98.645 |
111.765 |
1.021 |
-1.17% |
1.021 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC15
|
13.23% |
94.497 |
107.003 |
0.005 |
-0.01% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC15
|
12.93% |
45.992 |
51.937 |
0.006 |
-0.00% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC16
|
12.76% |
29.411 |
33.165 |
0.002 |
0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC4
|
12.50% |
20.025 |
22.528 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC4
|
12.49% |
20.026 |
22.526 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC3
|
12.48% |
20.026 |
22.525 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIRST_SUM_LAMBDA/5001
|
12.18% |
18.106 |
20.311 |
0.117 |
-0.56% |
0.117 |
|
SingleSource/Benchmarks/Shootout-C++/Shootout-C++-matrix
Profile
|
12.06% |
2.239 |
2.509 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC7
|
12.05% |
72.602 |
81.347 |
0.008 |
-0.01% |
0.008 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_BAND_LIN_EQ_RAW/171
|
11.86% |
0.343 |
0.384 |
0.000 |
4.77% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_BAND_LIN_EQ_LAMBDA/171
|
11.86% |
0.343 |
0.384 |
0.000 |
4.78% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC4
|
11.85% |
36.921 |
41.297 |
0.003 |
-0.01% |
0.003 |
|
MicroBenchmarks/ImageProcessing/Blur/blur.test:BENCHMARK_boxBlurKernel/1024
|
11.84% |
26906.325 |
30091.302 |
12.503 |
-0.19% |
12.503 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC4
|
11.76% |
21.275 |
23.777 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC64
|
11.69% |
48.184 |
53.815 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint8_t>/51
|
11.33% |
111.284 |
123.890 |
0.097 |
33.93% |
0.097 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/16
|
11.31% |
103.734 |
115.465 |
0.004 |
0.00% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC4
|
11.24% |
50.064 |
55.690 |
0.003 |
-0.02% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint8_t_To_uint16_t_
|
11.23% |
5262.180 |
5853.154 |
2.200 |
0.05% |
2.200 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/32
|
11.09% |
425.787 |
473.007 |
0.025 |
0.00% |
0.025 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/256
|
10.84% |
28372.907 |
31449.613 |
14.399 |
0.00% |
14.399 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/128
|
10.80% |
7148.089 |
7920.401 |
1.851 |
-0.03% |
1.851 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC8
|
10.80% |
23.154 |
25.655 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC8
|
10.79% |
23.156 |
25.655 |
0.003 |
-0.00% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC7
|
10.64% |
29.412 |
32.540 |
0.003 |
0.00% |
0.003 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/64
|
10.60% |
1729.951 |
1913.276 |
2.375 |
-0.00% |
2.375 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC7
|
10.52% |
23.778 |
26.281 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC7
|
10.51% |
23.781 |
26.280 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC127
|
10.45% |
91.998 |
101.607 |
0.292 |
-0.27% |
0.292 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_only_autovec_int64_t_
|
10.43% |
301880.982 |
333364.358 |
246.791 |
0.03% |
246.791 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC32
|
10.39% |
48.182 |
53.189 |
0.003 |
-0.01% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC31
|
10.36% |
178.035 |
196.484 |
0.018 |
-0.00% |
0.018 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_DEL_DOT_VEC_2D_RAW/1
|
10.12% |
260.669 |
287.045 |
0.188 |
-0.01% |
0.188 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_DEL_DOT_VEC_2D_LAMBDA/1
|
10.04% |
260.915 |
287.107 |
0.112 |
-0.00% |
0.112 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC8
|
10.01% |
24.406 |
26.848 |
0.133 |
-0.24% |
0.133 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC4
|
10.00% |
37.545 |
41.300 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC7
|
9.74% |
25.659 |
28.157 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_DEL_DOT_VEC_2D_RAW/2
|
9.53% |
3.204 |
3.510 |
0.000 |
-0.01% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_DEL_DOT_VEC_2D_LAMBDA/2
|
9.52% |
3.205 |
3.510 |
0.000 |
0.01% |
0.000 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_runtime_checks_pass<4, int>
|
9.51% |
15.331 |
16.789 |
0.015 |
0.07% |
0.015 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIRST_SUM_RAW/5001
|
9.42% |
18.593 |
20.345 |
0.093 |
0.28% |
0.093 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC16
|
9.42% |
33.169 |
36.292 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC8
|
9.30% |
26.908 |
29.409 |
0.001 |
-0.01% |
0.001 |
|
MultiSource/Benchmarks/FreeBench/pifft/pifft
Profile
|
9.17% |
0.328 |
0.358 |
0.000 |
-0.05% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_DIFF_PREDICT_LAMBDA/171
|
9.14% |
11.284 |
12.316 |
0.029 |
-0.41% |
0.029 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint16_t_To_uint8_t_
|
8.96% |
6250.333 |
6810.136 |
4.359 |
-0.08% |
4.359 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC2
|
8.92% |
35.045 |
38.171 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC64
|
8.77% |
85.727 |
93.243 |
0.003 |
0.00% |
0.003 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_DIFF_PREDICT_RAW/171
|
8.73% |
11.310 |
12.297 |
0.038 |
-0.18% |
0.038 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC3
|
8.57% |
43.805 |
47.557 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC16
|
8.50% |
29.412 |
31.913 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC16
|
8.50% |
29.412 |
31.912 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC32
|
8.47% |
36.920 |
40.048 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC15
|
8.32% |
30.038 |
32.538 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC15
|
8.32% |
30.038 |
32.537 |
0.002 |
-0.01% |
0.002 |
|
MultiSource/Benchmarks/VersaBench/beamformer/beamformer
Profile
|
8.19% |
4.807 |
5.201 |
0.002 |
0.01% |
0.002 |
|
MultiSource/Benchmarks/Trimaran/enc-md5/enc-md5
Profile
|
8.11% |
3.244 |
3.507 |
0.000 |
0.02% |
0.000 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_xor_no_runtime_checks_needed<16, int>
|
7.99% |
15.644 |
16.895 |
0.002 |
-0.01% |
0.002 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_DEL_DOT_VEC_2D_RAW/0
|
7.87% |
1667.062 |
1798.239 |
3.624 |
-0.15% |
3.624 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint8_t>/28
|
7.86% |
76.580 |
82.595 |
0.055 |
22.20% |
0.055 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIND_FIRST_MIN_RAW/171
|
7.78% |
1.389 |
1.497 |
0.000 |
0.03% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC128
|
7.78% |
160.820 |
173.326 |
0.007 |
-0.00% |
0.007 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint8_t>/127
|
7.76% |
128.911 |
138.911 |
0.008 |
-0.00% |
0.008 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint8_t_To_uint32_t_
|
7.73% |
11865.966 |
12783.283 |
2.495 |
0.01% |
2.495 |
|
MultiSource/Applications/lambda-0.1.3/lambda
Profile
|
7.68% |
14.738 |
15.871 |
0.037 |
0.01% |
0.037 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC7
|
7.61% |
65.707 |
70.710 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_DEL_DOT_VEC_2D_LAMBDA/0
|
7.60% |
1672.940 |
1800.060 |
2.473 |
0.10% |
2.473 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint16_t_To_uint64_t_
|
7.59% |
23285.744 |
25053.868 |
18.637 |
0.06% |
18.637 |
|
SingleSource/Benchmarks/Misc/pi
Profile
|
7.54% |
1.657 |
1.782 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint16_t_To_uint64_t_
|
7.46% |
18821.457 |
20225.844 |
46.719 |
-0.28% |
46.719 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC15
|
7.39% |
50.690 |
54.438 |
0.003 |
-0.01% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC31
|
7.18% |
69.467 |
74.458 |
0.005 |
-0.01% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC15
|
7.04% |
42.089 |
45.051 |
0.003 |
-0.00% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC63
|
6.98% |
107.035 |
114.506 |
0.006 |
-0.01% |
0.006 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_xor_runtime_checks_pass<16, int>
|
6.97% |
26.907 |
28.783 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_xor_runtime_checks_fail<16, int>
|
6.96% |
26.909 |
28.782 |
0.003 |
-0.00% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC127
|
6.78% |
64.457 |
68.828 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC128
|
6.78% |
64.462 |
68.832 |
0.003 |
-0.01% |
0.003 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_HYDRO_2D_RAW/171
|
6.77% |
83.266 |
88.905 |
0.296 |
0.31% |
0.296 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC63
|
6.77% |
69.462 |
74.163 |
0.216 |
-0.08% |
0.216 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC15
|
6.76% |
36.922 |
39.418 |
0.004 |
-0.01% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint16_t>/127
|
6.72% |
130.160 |
138.912 |
0.007 |
-0.00% |
0.007 |
|
SingleSource/Benchmarks/Misc/flops-6
Profile
|
6.65% |
1.229 |
1.311 |
0.001 |
-0.11% |
0.001 |
|
SingleSource/Benchmarks/Misc-C++/Large/sphereflake
Profile
|
6.60% |
18.775 |
20.014 |
0.002 |
0.01% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC16
|
6.56% |
38.172 |
40.676 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIND_FIRST_MIN_RAW/5001
|
6.52% |
42.520 |
45.294 |
0.194 |
-0.10% |
0.194 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC127
|
6.52% |
182.709 |
194.619 |
0.002 |
0.00% |
0.002 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_PRESSURE_CALC_LAMBDA/5001
|
6.40% |
42.094 |
44.790 |
0.869 |
-0.59% |
0.869 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint8_t>/65
|
6.28% |
89.489 |
95.111 |
0.002 |
0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_only_autovec_int32_t_
|
6.28% |
170202.977 |
180891.179 |
683.265 |
-0.13% |
683.265 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_HYDRO_2D_LAMBDA/171
|
6.24% |
83.412 |
88.619 |
0.224 |
-0.04% |
0.224 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint32_t>/127
|
6.23% |
130.169 |
138.276 |
0.006 |
-0.01% |
0.006 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIRST_DIFF_RAW/5001
|
6.20% |
12.250 |
13.010 |
0.003 |
0.17% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC16
|
6.12% |
30.040 |
31.878 |
0.015 |
-0.09% |
0.015 |
|
MultiSource/Benchmarks/MiBench/telecomm-gsm/telecomm-gsm
Profile
|
6.11% |
0.625 |
0.663 |
0.000 |
-0.07% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC7
|
6.08% |
330.050 |
350.118 |
4.150 |
-1.29% |
4.150 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC16
|
6.00% |
31.288 |
33.164 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC32
|
5.96% |
41.927 |
44.428 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC32
|
5.96% |
41.928 |
44.427 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC31
|
5.90% |
42.553 |
45.062 |
0.003 |
-0.00% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC31
|
5.87% |
42.552 |
45.051 |
0.002 |
-0.00% |
0.002 |
|
MultiSource/Benchmarks/McCat/12-IOtest/iotest
Profile
|
5.84% |
1.752 |
1.855 |
0.016 |
0.71% |
0.016 |
|
MultiSource/Benchmarks/SciMark2-C/scimark2
Profile
|
5.80% |
101.812 |
107.716 |
0.010 |
0.02% |
0.010 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint8_t_To_uint16_t_
|
5.66% |
3434.756 |
3629.066 |
6.666 |
-0.12% |
6.666 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint32_t>/999
|
5.61% |
659.554 |
696.571 |
0.018 |
-0.01% |
0.018 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC7
|
5.60% |
66.963 |
70.710 |
0.002 |
-0.01% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopWithReductionTC1
|
5.55% |
11.264 |
11.889 |
0.002 |
0.00% |
0.002 |
|
MultiSource/Benchmarks/Rodinia/hotspot/hotspot
Profile
|
5.55% |
1.928 |
2.035 |
0.002 |
-0.02% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint32_t>/999
|
5.50% |
1293.818 |
1364.928 |
0.196 |
-0.01% |
0.196 |
|
External/SPEC/CFP2017rate/538.imagick_r/538.imagick_r
Profile
|
5.44% |
275.993 |
291.006 |
0.865 |
-0.37% |
0.865 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC32
|
5.40% |
23.154 |
24.405 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC31
|
5.40% |
23.154 |
24.404 |
0.002 |
0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC31
|
5.39% |
23.154 |
24.402 |
0.003 |
-0.00% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC32
|
5.39% |
23.155 |
24.403 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC15
|
5.39% |
121.711 |
128.269 |
0.006 |
-0.01% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC32
|
5.37% |
58.197 |
61.323 |
0.003 |
0.00% |
0.003 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIND_FIRST_MIN_RAW/44217
|
5.32% |
369.628 |
389.296 |
0.158 |
-0.07% |
0.158 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC31
|
5.21% |
229.216 |
241.159 |
0.048 |
-0.03% |
0.048 |
|
SingleSource/Benchmarks/Polybench/stencils/jacobi-2d/jacobi-2d
Profile
|
5.09% |
30.653 |
32.212 |
0.077 |
-0.04% |
0.077 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint32_t>/256
|
5.04% |
346.715 |
364.197 |
0.026 |
-0.00% |
0.026 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C++/miniFE/miniFE
Profile
|
5.00% |
15.065 |
15.818 |
0.067 |
-0.94% |
0.067 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint32_t_To_uint64_t_
|
4.96% |
20319.821 |
21327.188 |
91.577 |
-0.58% |
91.577 |
|
SingleSource/Benchmarks/Misc/revertBits
Profile
|
4.91% |
0.611 |
0.641 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_runtime_checks_pass<16, int>
|
4.82% |
51.937 |
54.440 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint16_t>/65
|
4.81% |
90.747 |
95.111 |
0.004 |
-0.00% |
0.004 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_runtime_checks_fail<16, int>
|
4.81% |
51.939 |
54.435 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_runtime_checks_fail<4, int>
|
4.78% |
15.331 |
16.064 |
0.238 |
0.42% |
0.238 |
|
SingleSource/Benchmarks/Misc/oourafft
Profile
|
4.76% |
14.631 |
15.328 |
0.107 |
0.55% |
0.107 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopWithReductionTC2
|
4.66% |
13.153 |
13.766 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC31
|
4.66% |
66.964 |
70.081 |
0.004 |
-0.00% |
0.004 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_BAND_LIN_EQ_LAMBDA/5001
|
4.63% |
20.243 |
21.181 |
0.132 |
0.52% |
0.132 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC4
|
4.54% |
13.767 |
14.392 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC3
|
4.54% |
13.767 |
14.392 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC4
|
4.54% |
13.766 |
14.392 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC2
|
4.54% |
13.767 |
14.392 |
0.000 |
0.01% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC1
|
4.54% |
13.767 |
14.392 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC8
|
4.54% |
13.767 |
14.392 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC7
|
4.54% |
13.767 |
14.391 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC1
|
4.54% |
13.769 |
14.393 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC15
|
4.54% |
13.767 |
14.392 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC15
|
4.53% |
13.768 |
14.392 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC16
|
4.53% |
13.767 |
14.391 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC7
|
4.53% |
13.768 |
14.391 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC3
|
4.53% |
13.768 |
14.391 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC2
|
4.53% |
13.767 |
14.391 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC8
|
4.52% |
13.769 |
14.391 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint64_t>/999
|
4.43% |
1734.336 |
1811.156 |
0.231 |
-0.00% |
0.231 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_PRESSURE_CALC_RAW/44217
|
4.39% |
483.335 |
504.539 |
5.542 |
0.10% |
5.542 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_nested_cond_load_novec_int32_t_
|
4.33% |
623484.192 |
650485.851 |
604.393 |
0.70% |
604.393 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint64_t>/999
|
4.31% |
3446.813 |
3595.224 |
0.222 |
0.01% |
0.222 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_ENERGY_CALC_LAMBDA/171
|
4.29% |
13.619 |
14.203 |
0.010 |
-0.31% |
0.010 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_PIC_2D_RAW/171
|
4.27% |
12.966 |
13.520 |
0.094 |
-0.15% |
0.094 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint64_t>/256
|
4.26% |
897.394 |
935.590 |
0.044 |
0.00% |
0.044 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_PIC_2D_LAMBDA/171
|
4.24% |
12.905 |
13.453 |
0.083 |
-0.33% |
0.083 |
|
SingleSource/Benchmarks/Misc/flops-5
Profile
|
4.20% |
1.939 |
2.020 |
0.001 |
-0.05% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC31
|
4.19% |
59.453 |
61.947 |
0.002 |
0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_only_autovec_uint8_t_
|
4.13% |
92353.371 |
96168.923 |
8.856 |
0.01% |
8.856 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint32_t>/65
|
4.12% |
90.744 |
94.486 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC32
|
4.11% |
60.703 |
63.199 |
0.002 |
0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint32_t>/256
|
4.10% |
212.779 |
221.506 |
0.009 |
0.00% |
0.009 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_BAND_LIN_EQ_RAW/5001
|
4.09% |
20.398 |
21.232 |
0.234 |
0.54% |
0.234 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_ENERGY_CALC_RAW/171
|
4.06% |
13.648 |
14.203 |
0.029 |
-0.27% |
0.029 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC127
|
4.02% |
2295.284 |
2387.637 |
16.326 |
-1.61% |
16.326 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC3
|
4.00% |
15.644 |
16.270 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint8_t_To_uint64_t_
|
3.91% |
22589.749 |
23471.939 |
32.783 |
-0.05% |
32.783 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<31, EqZero, First>
|
3.81% |
3223.385 |
3346.183 |
0.053 |
-0.00% |
0.053 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint64_t>/256
|
3.76% |
495.737 |
514.380 |
0.024 |
-0.00% |
0.024 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC31
|
3.75% |
58.196 |
60.380 |
0.071 |
0.02% |
0.071 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC64
|
3.73% |
66.960 |
69.458 |
0.004 |
0.00% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC64
|
3.72% |
66.963 |
69.456 |
0.002 |
-0.01% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint64_t_To_uint32_t_
|
3.71% |
18684.265 |
19377.814 |
76.344 |
-0.14% |
76.344 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC63
|
3.69% |
67.587 |
70.079 |
0.004 |
-0.01% |
0.004 |
|
SingleSource/Benchmarks/BenchmarkGame/n-body
Profile
|
3.69% |
2.634 |
2.731 |
0.000 |
26.21% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC63
|
3.68% |
67.598 |
70.088 |
0.006 |
-0.01% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC63
|
3.66% |
41.654 |
43.177 |
0.295 |
-0.27% |
0.295 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC1
|
3.53% |
85.090 |
88.090 |
0.846 |
-1.00% |
0.846 |
|
MultiSource/Benchmarks/nbench/nbench
Profile
|
3.52% |
5.907 |
6.115 |
0.002 |
-0.19% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint16_t_To_uint8_t_
|
3.50% |
2777.140 |
2874.394 |
2.940 |
-0.13% |
2.940 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC64
|
3.46% |
41.734 |
43.176 |
0.296 |
0.00% |
0.296 |
|
External/SPEC/CFP2017rate/544.nab_r/544.nab_r
Profile
|
3.41% |
460.466 |
476.181 |
0.134 |
-0.36% |
0.134 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint16_t>/999
|
3.26% |
498.735 |
514.993 |
0.020 |
-0.01% |
0.020 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1BigLoopWithReductionTC1
|
3.21% |
19.401 |
20.023 |
0.004 |
-0.01% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint32_t_To_uint16_t_
|
3.20% |
9544.489 |
9849.981 |
54.895 |
-0.30% |
54.895 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_PRESSURE_CALC_LAMBDA/44217
|
3.18% |
487.912 |
503.440 |
2.234 |
-0.15% |
2.234 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchVecWithRuntimeChecks4PointersDBeforeA/1000
|
3.17% |
4866096.042 |
5020347.403 |
42.691 |
-0.01% |
42.691 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<32, EqZero, Last>
|
3.14% |
6815.452 |
7029.249 |
55.266 |
-0.34% |
55.266 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint16_t_To_uint8_t_
|
3.10% |
4378.426 |
4514.233 |
10.163 |
-0.07% |
10.163 |
|
SingleSource/Benchmarks/Shootout/Shootout-lists
Profile
|
3.09% |
10.976 |
11.316 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, LessThanZero, None>
|
3.04% |
36558.154 |
37670.557 |
22.576 |
0.02% |
22.576 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC31
|
2.99% |
91.054 |
93.779 |
0.036 |
-0.08% |
0.036 |
|
MicroBenchmarks/ImageProcessing/Dilate/Dilate.test:BENCHMARK_DILATE/1024
|
2.99% |
7418.678 |
7640.611 |
59.578 |
1.88% |
59.578 |
|
MultiSource/Benchmarks/sim/sim
Profile
|
2.94% |
9.424 |
9.701 |
0.002 |
0.00% |
0.002 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<31, GreaterThanZero, Last>
|
2.92% |
8112.027 |
8348.528 |
17.846 |
-0.19% |
17.846 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint16_t>/999
|
2.91% |
985.122 |
1013.823 |
0.059 |
-0.00% |
0.059 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC64
|
2.88% |
108.260 |
111.378 |
0.008 |
-0.00% |
0.008 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC1
|
2.84% |
21.904 |
22.526 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC1
|
2.83% |
21.905 |
22.526 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC63
|
2.66% |
117.035 |
120.145 |
0.012 |
0.00% |
0.012 |
|
MultiSource/Benchmarks/FreeBench/mason/mason
Profile
|
2.65% |
0.538 |
0.553 |
0.000 |
-0.05% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC16
|
2.65% |
14.020 |
14.392 |
0.000 |
-0.01% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC32
|
2.63% |
30.483 |
31.286 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint8_t>/10
|
2.58% |
47.581 |
48.807 |
0.002 |
5.16% |
0.002 |
|
SingleSource/Benchmarks/Misc-C++/oopack_v1p8
Profile
|
2.57% |
0.468 |
0.480 |
0.000 |
-7.57% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint8_t_To_uint32_t_
|
2.54% |
6902.034 |
7077.629 |
0.342 |
0.00% |
0.342 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C/CoMD/CoMD
Profile
|
2.51% |
9.663 |
9.906 |
0.004 |
0.02% |
0.004 |
|
External/SPEC/CFP2017rate/519.lbm_r/519.lbm_r
Profile
|
2.50% |
195.142 |
200.030 |
1.713 |
-0.32% |
1.713 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchVecWithRuntimeChecks4PointersDBeforeA/32
|
2.50% |
162142.305 |
166202.823 |
4.504 |
0.00% |
4.504 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_only_autovec_int64_t_
|
2.43% |
1414576.176 |
1448879.652 |
572.031 |
-0.06% |
572.031 |
|
MicroBenchmarks/LCALS/SubsetBRawLoops/lcalsBRaw.test:BM_INIT3_RAW/44217
|
2.40% |
393.215 |
402.657 |
1.564 |
1.30% |
1.564 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC63
|
2.38% |
104.515 |
107.002 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC32
|
2.37% |
48.896 |
50.054 |
0.003 |
0.00% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC31
|
2.35% |
30.509 |
31.225 |
0.024 |
0.00% |
0.024 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopFrom_uint32_t_To_uint64_t_
|
2.32% |
14037.521 |
14363.396 |
126.440 |
2.75% |
126.440 |
|
SingleSource/Benchmarks/Misc/flops-1
Profile
|
2.22% |
8.807 |
9.002 |
0.000 |
0.01% |
0.000 |
|
SingleSource/Benchmarks/Misc-C++/Large/ray
Profile
|
2.12% |
11.852 |
12.104 |
0.001 |
0.02% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC128
|
2.12% |
117.028 |
119.509 |
0.007 |
-0.01% |
0.007 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC127
|
2.12% |
117.652 |
120.145 |
0.007 |
-0.00% |
0.007 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC128
|
2.11% |
117.049 |
119.523 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC127
|
2.11% |
117.654 |
120.137 |
0.005 |
-0.00% |
0.005 |
|
MultiSource/Benchmarks/FreeBench/fourinarow/fourinarow
Profile
|
2.10% |
0.637 |
0.651 |
0.001 |
-0.00% |
0.001 |
|
SingleSource/Benchmarks/BenchmarkGame/puzzle
Profile
|
2.08% |
0.858 |
0.876 |
0.003 |
0.13% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint32_t_To_uint64_t_
|
2.03% |
25848.044 |
26371.663 |
52.518 |
0.06% |
52.518 |
|
SingleSource/Benchmarks/Misc/ReedSolomon
Profile
|
1.97% |
20.417 |
20.819 |
0.000 |
0.09% |
0.000 |
|
SingleSource/Benchmarks/Shootout/Shootout-matrix
Profile
|
1.93% |
3.791 |
3.864 |
0.000 |
0.02% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_EOS_RAW/171
|
1.92% |
0.856 |
0.873 |
0.001 |
-0.02% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint16_t_To_uint32_t_
|
1.89% |
11074.855 |
11284.401 |
49.967 |
-0.51% |
49.967 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint16_t>/256
|
1.86% |
267.845 |
272.837 |
0.012 |
-0.00% |
0.012 |
|
MultiSource/Applications/JM/lencod/lencod
Profile
|
1.84% |
32.179 |
32.770 |
0.046 |
0.62% |
0.046 |
|
MultiSource/Applications/sgefa/sgefa
Profile
|
1.81% |
0.566 |
0.577 |
0.001 |
0.27% |
0.001 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_FLOYD_DITHER/128
|
1.78% |
429.931 |
437.575 |
0.875 |
-0.43% |
0.875 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint64_t_To_uint8_t_
|
1.78% |
19402.007 |
19746.494 |
20.322 |
-0.48% |
20.322 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint64_t>/51
|
1.70% |
145.813 |
148.299 |
0.001 |
-0.01% |
0.001 |
|
MultiSource/Benchmarks/Olden/health/health
Profile
|
1.66% |
1.569 |
1.595 |
0.003 |
0.10% |
0.003 |
|
External/SPEC/CINT2017rate/531.deepsjeng_r/531.deepsjeng_r
Profile
|
1.59% |
256.027 |
260.106 |
0.198 |
-0.00% |
0.198 |
|
MultiSource/Benchmarks/VersaBench/ecbdes/ecbdes
Profile
|
1.59% |
5.061 |
5.141 |
0.000 |
0.01% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_EOS_LAMBDA/171
|
1.57% |
0.858 |
0.871 |
0.001 |
0.07% |
0.001 |
|
SingleSource/Benchmarks/Misc/mandel-2
Profile
|
1.57% |
2.496 |
2.536 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_FLOYD_DITHER/512
|
1.56% |
6546.570 |
6648.394 |
4.778 |
0.05% |
4.778 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_nested_cond_load_novec_uint8_t_
|
1.55% |
496811.685 |
504512.505 |
281.629 |
-0.04% |
281.629 |
|
MultiSource/Benchmarks/mafft/pairlocalalign
Profile
|
1.52% |
92.603 |
94.013 |
0.311 |
-0.05% |
0.311 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC128
|
1.49% |
208.390 |
211.489 |
0.016 |
-0.01% |
0.016 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_csa_with_in_loop_arith_novec_int64_t_
|
1.47% |
1013118.896 |
1028012.557 |
876.328 |
-0.01% |
876.328 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_INT_PREDICT_RAW/171
|
1.46% |
6.817 |
6.917 |
0.004 |
-0.11% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC15
|
1.43% |
43.808 |
44.434 |
0.161 |
0.01% |
0.161 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint64_t>/51
|
1.36% |
225.939 |
229.010 |
0.018 |
0.00% |
0.018 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<6, LessThanZero, Mid>
|
1.33% |
23547.096 |
23861.210 |
9.178 |
-0.03% |
9.178 |
|
External/SPEC/CINT2017rate/525.x264_r/525.x264_r
Profile
|
1.33% |
128.209 |
129.916 |
0.088 |
0.24% |
0.088 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC127
|
1.29% |
217.465 |
220.262 |
0.010 |
-0.01% |
0.010 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC128
|
1.27% |
195.871 |
198.364 |
0.003 |
-0.00% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC127
|
1.27% |
194.635 |
197.110 |
0.019 |
0.00% |
0.019 |
|
MultiSource/Benchmarks/MallocBench/cfrac/cfrac
Profile
|
1.23% |
2.746 |
2.780 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_INT_PREDICT_LAMBDA/171
|
1.21% |
6.842 |
6.925 |
0.008 |
-0.00% |
0.008 |
|
External/SPEC/CFP2017rate/511.povray_r/511.povray_r
Profile
|
1.21% |
33.583 |
33.990 |
0.063 |
0.54% |
0.063 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint8_t>/16
|
1.19% |
59.307 |
60.014 |
0.169 |
11.51% |
0.169 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<8, LessThanZero, Mid>
|
1.14% |
19269.432 |
19488.931 |
15.502 |
-0.04% |
15.502 |
|
SingleSource/Benchmarks/SmallPT/smallpt
Profile
|
1.11% |
29.711 |
30.041 |
0.001 |
0.02% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC63
|
1.10% |
128.729 |
130.145 |
0.007 |
-0.02% |
0.007 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<32, GreaterThanZero, Mid>
|
1.09% |
4499.808 |
4549.056 |
3.650 |
-0.14% |
3.650 |
|
MultiSource/Benchmarks/Bullet/bullet
Profile
|
1.09% |
30.221 |
30.550 |
0.058 |
-0.37% |
0.058 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<16, EqZero, None>
|
1.09% |
8094.444 |
8182.309 |
10.857 |
0.06% |
10.857 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_sinhf_novec_float_
|
1.08% |
2218.467 |
2242.536 |
0.575 |
0.00% |
0.575 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<6, GreaterThanZero, None>
|
1.03% |
29416.572 |
29720.398 |
8.123 |
0.02% |
8.123 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_csa_with_cond_arith_autovec_int64_t_
|
1.02% |
737807.733 |
745337.025 |
2181.171 |
0.05% |
2181.171 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_sinhf_autovec_float_
|
1.01% |
2219.026 |
2241.545 |
0.912 |
-0.05% |
0.912 |