|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_INT_PREDICT_LAMBDA/44217
|
133.99% |
8217.354 |
19228.072 |
13.987 |
-1.25% |
13.987 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint64_t_To_uint8_t_
|
94.59% |
19113.265 |
37192.467 |
68.951 |
0.35% |
68.951 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint64_t_To_uint32_t_
|
92.05% |
18369.340 |
35277.665 |
179.021 |
-0.10% |
179.021 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint64_t_To_uint16_t_
|
87.06% |
19122.642 |
35770.115 |
237.091 |
0.21% |
237.091 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C/miniGMG/miniGMG
Profile
|
81.80% |
4.856 |
8.829 |
0.230 |
-3.93% |
0.230 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint16_t_To_uint64_t_
|
78.37% |
10447.098 |
18634.031 |
282.152 |
-0.22% |
282.152 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_DIFF_PREDICT_LAMBDA/44217
|
70.58% |
14260.698 |
24326.129 |
765.816 |
-0.05% |
765.816 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint8_t_To_uint64_t_
|
70.03% |
10546.940 |
17932.517 |
474.003 |
0.60% |
474.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint64_t_To_uint32_t_
|
69.03% |
22700.297 |
38371.426 |
90.201 |
-0.14% |
90.201 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIRST_DIFF_LAMBDA/44217
|
68.58% |
103.205 |
173.983 |
5.436 |
-0.49% |
5.436 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_DIFF_PREDICT_RAW/44217
|
66.34% |
14104.440 |
23461.242 |
1346.771 |
0.69% |
1346.771 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_DIFF_PREDICT_LAMBDA/5001
|
61.27% |
1594.302 |
2571.122 |
164.363 |
-0.14% |
164.363 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_DIFF_PREDICT_RAW/5001
|
59.01% |
1617.319 |
2571.776 |
127.103 |
-0.12% |
127.103 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/32
|
57.96% |
883.898 |
1396.249 |
0.008 |
-0.00% |
0.008 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/16
|
57.78% |
177.128 |
279.473 |
0.011 |
0.00% |
0.011 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/64
|
57.74% |
3918.612 |
6181.079 |
1.063 |
-0.02% |
1.063 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/256
|
56.52% |
68440.462 |
107122.881 |
22.495 |
-0.03% |
22.495 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/128
|
56.29% |
16803.715 |
26262.785 |
3.386 |
-0.03% |
3.386 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint64_t_To_uint8_t_
|
51.30% |
19897.249 |
30104.022 |
134.364 |
-0.02% |
134.364 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint64_t_To_uint16_t_
|
51.21% |
19174.725 |
28994.767 |
232.071 |
-0.12% |
232.071 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint32_t_To_uint64_t_
|
51.06% |
14888.147 |
22490.233 |
874.920 |
-1.03% |
874.920 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, EqZero, None>
|
45.43% |
14105.396 |
20513.014 |
1.014 |
-0.01% |
1.014 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint64_t_To_uint16_t_
|
39.89% |
18517.629 |
25903.417 |
20.901 |
0.02% |
20.901 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC128
|
37.71% |
940.984 |
1295.797 |
0.493 |
-0.00% |
0.493 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint32_t_To_uint8_t_
|
37.44% |
9796.692 |
13464.689 |
12.975 |
-0.03% |
12.975 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC128
|
37.00% |
407.840 |
558.752 |
0.107 |
0.02% |
0.107 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC64
|
36.57% |
480.028 |
655.561 |
0.343 |
-0.17% |
0.343 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC32
|
36.15% |
246.014 |
334.956 |
0.088 |
-0.01% |
0.088 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC16
|
35.00% |
129.058 |
174.224 |
0.026 |
-0.04% |
0.026 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC64
|
34.51% |
217.187 |
292.145 |
0.052 |
-0.03% |
0.052 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint64_t_To_uint8_t_
|
31.56% |
20680.980 |
27207.002 |
39.941 |
-0.06% |
39.941 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, EqZero, None>
|
31.53% |
12182.432 |
16023.755 |
0.676 |
0.00% |
0.676 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIRST_SUM_LAMBDA/44217
|
30.55% |
137.797 |
179.893 |
4.876 |
-0.56% |
4.876 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC128
|
30.19% |
463.868 |
603.910 |
0.012 |
-0.01% |
0.012 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC32
|
30.11% |
122.104 |
158.873 |
0.047 |
0.00% |
0.047 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC128
|
30.02% |
464.490 |
603.912 |
0.062 |
-0.01% |
0.062 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC64
|
28.77% |
243.450 |
313.499 |
0.007 |
-0.00% |
0.007 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint16_t_To_uint64_t_
|
28.52% |
10390.244 |
13353.787 |
315.592 |
0.64% |
315.592 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC127
|
28.45% |
478.888 |
615.130 |
0.060 |
-0.01% |
0.060 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC64
|
28.45% |
244.067 |
313.498 |
0.008 |
-0.00% |
0.008 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC127
|
28.14% |
480.103 |
615.205 |
0.019 |
0.00% |
0.019 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint16_t_To_uint32_t_
|
27.56% |
5573.317 |
7109.352 |
57.183 |
-0.03% |
57.183 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_only_autovec_uint8_t_
|
27.16% |
143417.895 |
182373.024 |
62.220 |
-0.01% |
62.220 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint8_t_To_uint32_t_
|
27.14% |
5182.004 |
6588.477 |
99.665 |
0.04% |
99.665 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIND_FIRST_MIN_LAMBDA/171
|
27.06% |
1.182 |
1.501 |
0.000 |
0.02% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIND_FIRST_MIN_LAMBDA/44217
|
26.39% |
308.172 |
389.490 |
0.337 |
-0.02% |
0.337 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC32
|
26.27% |
133.298 |
168.317 |
0.008 |
-0.01% |
0.008 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC128
|
25.88% |
218.833 |
275.459 |
0.765 |
0.07% |
0.765 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC32
|
25.67% |
133.934 |
168.319 |
0.002 |
-0.01% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC63
|
25.64% |
258.479 |
324.766 |
0.016 |
-0.01% |
0.016 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIND_FIRST_MIN_LAMBDA/5001
|
25.61% |
36.310 |
45.607 |
0.044 |
-0.29% |
0.044 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC63
|
25.04% |
259.732 |
324.758 |
0.008 |
-0.01% |
0.008 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC127
|
24.51% |
514.770 |
640.928 |
0.191 |
-0.04% |
0.191 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIRST_SUM_RAW/44217
|
24.50% |
136.010 |
169.334 |
6.940 |
1.80% |
6.940 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC127
|
24.31% |
220.863 |
274.556 |
1.396 |
-0.33% |
1.396 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC63
|
24.03% |
123.773 |
153.517 |
1.251 |
-0.95% |
1.251 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC64
|
23.90% |
121.392 |
150.398 |
1.349 |
0.38% |
1.349 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC16
|
23.62% |
74.646 |
92.280 |
0.047 |
0.00% |
0.047 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint16_t_To_uint8_t_
|
23.48% |
3090.736 |
3816.313 |
1.615 |
-0.05% |
1.615 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_VOL3D_CALC_LAMBDA/2
|
23.14% |
7.111 |
8.757 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_VOL3D_CALC_RAW/2
|
23.10% |
7.113 |
8.756 |
0.000 |
-0.00% |
0.000 |
|
SingleSource/Benchmarks/Adobe-C++/loop_unroll
Profile
|
23.08% |
2.424 |
2.983 |
0.004 |
-3.99% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC16
|
22.39% |
78.224 |
95.735 |
0.003 |
-0.01% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint64_t_To_uint32_t_
|
22.35% |
22159.935 |
27112.603 |
3.668 |
0.09% |
3.668 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint32_t_To_uint8_t_
|
22.32% |
11364.400 |
13900.974 |
34.239 |
0.00% |
34.239 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint32_t_To_uint16_t_
|
22.15% |
11303.278 |
13807.126 |
6.236 |
-0.00% |
6.236 |
|
MultiSource/Benchmarks/Trimaran/enc-pc1/enc-pc1
Profile
|
22.13% |
0.905 |
1.105 |
0.000 |
0.01% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_with_cond_arith_novec_uint8_t_
|
21.71% |
612901.864 |
745959.795 |
389.107 |
0.01% |
389.107 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC16
|
21.41% |
78.853 |
95.739 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_PIC_2D_RAW/5001
|
21.28% |
989.070 |
1199.556 |
59.209 |
0.96% |
59.209 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC31
|
21.09% |
148.312 |
179.584 |
0.006 |
-0.00% |
0.006 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_PIC_2D_LAMBDA/44217
|
20.87% |
9810.205 |
11857.251 |
74.866 |
-0.11% |
74.866 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC128
|
20.85% |
472.302 |
570.785 |
0.008 |
-0.00% |
0.008 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC4
|
20.77% |
14.508 |
17.520 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint8_t_To_uint64_t_
|
20.76% |
10922.669 |
13190.651 |
128.591 |
0.96% |
128.591 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC64
|
20.65% |
246.882 |
297.856 |
0.012 |
-0.01% |
0.012 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC32
|
20.24% |
134.222 |
161.391 |
0.026 |
-0.00% |
0.026 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC32
|
20.18% |
71.871 |
86.373 |
0.580 |
0.99% |
0.580 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_PIC_2D_RAW/44217
|
20.13% |
9953.194 |
11957.102 |
13.133 |
0.16% |
13.133 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC31
|
20.05% |
149.583 |
179.581 |
0.004 |
-0.00% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_with_cond_arith_novec_int32_t_
|
19.91% |
617121.678 |
739986.123 |
538.332 |
-0.03% |
538.332 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC16
|
19.64% |
77.919 |
93.225 |
0.004 |
-0.01% |
0.004 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_PIC_2D_LAMBDA/5001
|
19.43% |
972.922 |
1161.982 |
49.472 |
5.11% |
49.472 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_VOL3D_CALC_RAW/1
|
19.22% |
218.215 |
260.157 |
0.126 |
0.01% |
0.126 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_VOL3D_CALC_LAMBDA/0
|
19.14% |
1064.105 |
1267.794 |
1.278 |
0.02% |
1.278 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_HYDRO_1D_RAW/171
|
19.10% |
0.372 |
0.443 |
0.001 |
-0.11% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_VOL3D_CALC_LAMBDA/1
|
19.05% |
218.434 |
260.037 |
0.130 |
-0.05% |
0.130 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_VOL3D_CALC_RAW/0
|
18.95% |
1064.834 |
1266.572 |
1.329 |
0.11% |
1.329 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_HYDRO_1D_LAMBDA/171
|
18.92% |
0.372 |
0.442 |
0.001 |
0.05% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC31
|
18.85% |
73.680 |
87.571 |
0.016 |
-0.04% |
0.016 |
|
MultiSource/Benchmarks/MiBench/automotive-bitcount/automotive-bitcount
Profile
|
18.59% |
0.106 |
0.125 |
0.000 |
0.56% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint16_t_To_uint32_t_
|
18.55% |
6294.407 |
7462.036 |
1.042 |
-0.00% |
1.042 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC8
|
18.24% |
49.747 |
58.819 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, EqZero, First>
|
18.20% |
14105.005 |
16672.391 |
0.240 |
-0.00% |
0.240 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_no_runtime_checks_needed<16, int>
|
18.18% |
20.650 |
24.403 |
0.004 |
-0.00% |
0.004 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, EqZero, Mid>
|
18.15% |
14106.584 |
16667.294 |
0.573 |
-0.01% |
0.573 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, EqZero, Last>
|
18.11% |
14111.537 |
16666.594 |
0.655 |
-0.00% |
0.655 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC127
|
17.39% |
516.031 |
605.757 |
0.046 |
-0.00% |
0.046 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC8
|
17.27% |
50.695 |
59.448 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC128
|
17.04% |
942.642 |
1103.292 |
0.054 |
-0.00% |
0.054 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint32_t_To_uint8_t_
|
17.03% |
9069.295 |
10613.369 |
12.198 |
0.17% |
12.198 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC127
|
16.97% |
936.397 |
1095.344 |
0.255 |
0.01% |
0.255 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC4
|
16.87% |
98.645 |
115.286 |
0.948 |
0.16% |
0.948 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC64
|
16.72% |
481.966 |
562.548 |
0.037 |
-0.01% |
0.037 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC63
|
16.57% |
475.641 |
554.462 |
2.031 |
-0.05% |
2.031 |
|
SingleSource/Benchmarks/Misc/salsa20
Profile
|
16.45% |
13.212 |
15.386 |
0.000 |
0.01% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC32
|
16.15% |
251.576 |
292.217 |
0.003 |
-0.00% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC4
|
16.07% |
44.743 |
51.934 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC7
|
16.07% |
44.744 |
51.933 |
0.003 |
-0.00% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC2
|
16.06% |
44.748 |
51.934 |
0.003 |
0.00% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC1
|
16.06% |
44.749 |
51.934 |
0.002 |
0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC3
|
16.06% |
44.746 |
51.931 |
0.003 |
-0.01% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC8
|
16.04% |
44.753 |
51.934 |
0.003 |
-0.01% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint64_t_To_uint8_t_
|
15.96% |
19091.706 |
22137.963 |
19.187 |
-0.16% |
19.187 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC8
|
15.85% |
51.313 |
59.447 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC31
|
15.81% |
245.316 |
284.103 |
0.044 |
0.00% |
0.044 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, EqZero, Mid>
|
15.77% |
12182.919 |
14103.694 |
0.358 |
0.00% |
0.358 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, EqZero, First>
|
15.76% |
12182.795 |
14103.308 |
0.400 |
0.00% |
0.400 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint8_t_To_uint16_t_
|
15.76% |
3245.667 |
3757.247 |
0.259 |
-0.01% |
0.259 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, EqZero, Last>
|
15.76% |
12183.603 |
14103.645 |
0.607 |
-0.01% |
0.607 |
|
External/SPEC/CFP2017rate/508.namd_r/508.namd_r
Profile
|
15.76% |
194.258 |
224.870 |
0.145 |
0.31% |
0.145 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC8
|
15.61% |
20.025 |
23.151 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint32_t_To_uint16_t_
|
15.52% |
11127.387 |
12854.619 |
16.007 |
0.14% |
16.007 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC63
|
15.46% |
324.299 |
374.421 |
0.120 |
-0.00% |
0.120 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_with_cond_arith_novec_int64_t_
|
15.35% |
684145.851 |
789192.153 |
1104.607 |
-0.11% |
1104.607 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint32_t_To_uint8_t_
|
15.32% |
9660.953 |
11141.487 |
21.183 |
0.11% |
21.183 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_with_cond_arith_autovec_int64_t_
|
15.24% |
685412.428 |
789891.135 |
896.023 |
-0.22% |
896.023 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC16
|
15.13% |
136.424 |
157.065 |
0.008 |
0.01% |
0.008 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC8
|
15.13% |
20.652 |
23.777 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC128
|
15.03% |
70.714 |
81.340 |
0.003 |
-0.01% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint8_t_To_uint16_t_
|
14.84% |
3954.852 |
4541.942 |
0.382 |
0.00% |
0.382 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC15
|
14.76% |
93.237 |
106.999 |
0.007 |
-0.00% |
0.007 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC63
|
14.53% |
290.705 |
332.950 |
0.192 |
-0.00% |
0.192 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC15
|
14.41% |
130.167 |
148.923 |
0.007 |
-0.01% |
0.007 |
|
MultiSource/Benchmarks/MiBench/security-rijndael/security-rijndael
Profile
|
14.24% |
0.294 |
0.335 |
0.000 |
0.01% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint16_t_To_uint8_t_
|
14.17% |
4154.735 |
4743.461 |
0.346 |
-0.00% |
0.346 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIRST_SUM_LAMBDA/5001
|
14.12% |
18.106 |
20.662 |
0.170 |
-0.43% |
0.170 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC16
|
14.09% |
45.524 |
51.938 |
0.003 |
-0.01% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC8
|
13.48% |
78.848 |
89.480 |
0.003 |
-0.00% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC2
|
13.30% |
18.778 |
21.275 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC15
|
13.23% |
94.497 |
107.002 |
0.002 |
-0.01% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC15
|
12.91% |
45.992 |
51.932 |
0.003 |
-0.01% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC16
|
12.75% |
29.411 |
33.162 |
0.003 |
-0.01% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC4
|
12.49% |
20.025 |
22.527 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC3
|
12.48% |
20.026 |
22.526 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC4
|
12.48% |
20.026 |
22.524 |
0.002 |
-0.01% |
0.002 |
|
SingleSource/Benchmarks/Shootout-C++/Shootout-C++-matrix
Profile
|
12.07% |
2.239 |
2.509 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC7
|
12.06% |
72.602 |
81.358 |
0.004 |
-0.00% |
0.004 |
|
MicroBenchmarks/ImageProcessing/Blur/blur.test:BENCHMARK_boxBlurKernel/1024
|
12.04% |
26906.325 |
30144.830 |
29.327 |
-0.01% |
29.327 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_BAND_LIN_EQ_RAW/171
|
11.86% |
0.343 |
0.384 |
0.000 |
4.76% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_BAND_LIN_EQ_LAMBDA/171
|
11.85% |
0.343 |
0.384 |
0.000 |
4.77% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC4
|
11.85% |
36.921 |
41.296 |
0.003 |
-0.01% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC4
|
11.76% |
21.275 |
23.776 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC64
|
11.68% |
48.184 |
53.814 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint8_t>/51
|
11.33% |
111.284 |
123.888 |
0.015 |
33.93% |
0.015 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/16
|
11.32% |
103.734 |
115.473 |
0.005 |
0.00% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC4
|
11.24% |
50.064 |
55.692 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint8_t_To_uint16_t_
|
11.21% |
5262.180 |
5852.183 |
1.845 |
0.03% |
1.845 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/32
|
11.09% |
425.787 |
472.989 |
0.020 |
-0.00% |
0.020 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint32_t_To_uint64_t_
|
10.92% |
15875.951 |
17609.605 |
344.414 |
-2.00% |
344.414 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/256
|
10.84% |
28372.907 |
31447.659 |
27.236 |
-0.01% |
27.236 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC8
|
10.80% |
23.154 |
25.654 |
0.000 |
-0.01% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC8
|
10.78% |
23.156 |
25.653 |
0.003 |
-0.01% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC127
|
10.74% |
91.998 |
101.882 |
0.174 |
0.00% |
0.174 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/128
|
10.71% |
7148.089 |
7913.400 |
4.892 |
-0.05% |
4.892 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC7
|
10.64% |
29.412 |
32.540 |
0.002 |
0.00% |
0.002 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/64
|
10.57% |
1729.951 |
1912.814 |
1.232 |
-0.03% |
1.232 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC7
|
10.52% |
23.778 |
26.280 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC7
|
10.51% |
23.781 |
26.279 |
0.002 |
-0.01% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC32
|
10.38% |
48.182 |
53.183 |
0.008 |
-0.02% |
0.008 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC31
|
10.36% |
178.035 |
196.480 |
0.004 |
-0.00% |
0.004 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_DEL_DOT_VEC_2D_RAW/1
|
10.20% |
260.669 |
287.252 |
0.037 |
0.06% |
0.037 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_only_autovec_int64_t_
|
10.19% |
301880.982 |
332627.655 |
584.150 |
-0.20% |
584.150 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_DEL_DOT_VEC_2D_LAMBDA/1
|
10.05% |
260.915 |
287.134 |
0.065 |
0.00% |
0.065 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC4
|
10.00% |
37.545 |
41.299 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC8
|
9.90% |
24.406 |
26.823 |
0.164 |
-0.33% |
0.164 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_runtime_checks_pass<4, int>
|
9.76% |
15.331 |
16.827 |
0.013 |
0.30% |
0.013 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC7
|
9.74% |
25.659 |
28.158 |
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 |
-0.00% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_DEL_DOT_VEC_2D_LAMBDA/2
|
9.53% |
3.205 |
3.510 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC16
|
9.41% |
33.169 |
36.291 |
0.001 |
-0.01% |
0.001 |
|
MultiSource/Benchmarks/FreeBench/pifft/pifft
Profile
|
9.37% |
0.328 |
0.359 |
0.001 |
0.06% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC8
|
9.29% |
26.908 |
29.408 |
0.003 |
-0.01% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint16_t_To_uint8_t_
|
8.97% |
6250.333 |
6811.198 |
15.796 |
-0.07% |
15.796 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC2
|
8.92% |
35.045 |
38.170 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC64
|
8.76% |
85.727 |
93.233 |
0.003 |
-0.01% |
0.003 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_DIFF_PREDICT_LAMBDA/171
|
8.68% |
11.284 |
12.264 |
0.071 |
-0.83% |
0.071 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC3
|
8.56% |
43.805 |
47.556 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC16
|
8.50% |
29.412 |
31.911 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC16
|
8.49% |
29.412 |
31.909 |
0.002 |
-0.01% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC32
|
8.47% |
36.920 |
40.046 |
0.003 |
-0.01% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC15
|
8.32% |
30.038 |
32.537 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC15
|
8.31% |
30.038 |
32.535 |
0.002 |
-0.01% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint32_t_To_uint16_t_
|
8.27% |
9698.421 |
10500.324 |
174.689 |
-2.21% |
174.689 |
|
MultiSource/Benchmarks/VersaBench/beamformer/beamformer
Profile
|
8.22% |
4.807 |
5.203 |
0.001 |
0.00% |
0.001 |
|
MultiSource/Benchmarks/Trimaran/enc-md5/enc-md5
Profile
|
8.13% |
3.244 |
3.508 |
0.000 |
0.03% |
0.000 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_xor_no_runtime_checks_needed<16, int>
|
8.01% |
15.644 |
16.897 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC7
|
8.00% |
330.050 |
356.450 |
4.568 |
0.49% |
4.568 |
|
MultiSource/Applications/lambda-0.1.3/lambda
Profile
|
7.92% |
14.738 |
15.906 |
0.006 |
-0.01% |
0.006 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_PRESSURE_CALC_LAMBDA/5001
|
7.88% |
42.094 |
45.412 |
0.395 |
0.79% |
0.395 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint8_t>/28
|
7.85% |
76.580 |
82.593 |
0.003 |
22.20% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC128
|
7.77% |
160.820 |
173.322 |
0.005 |
-0.00% |
0.005 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIND_FIRST_MIN_RAW/171
|
7.77% |
1.389 |
1.497 |
0.000 |
0.03% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint8_t>/127
|
7.75% |
128.911 |
138.906 |
0.004 |
-0.01% |
0.004 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_DEL_DOT_VEC_2D_RAW/0
|
7.74% |
1667.062 |
1796.045 |
1.802 |
-0.27% |
1.802 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint16_t_To_uint64_t_
|
7.65% |
18821.457 |
20261.770 |
33.363 |
-0.10% |
33.363 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint8_t_To_uint32_t_
|
7.63% |
11865.966 |
12770.934 |
28.092 |
-0.06% |
28.092 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC7
|
7.61% |
65.707 |
70.707 |
0.003 |
-0.01% |
0.003 |
|
SingleSource/Benchmarks/Misc/pi
Profile
|
7.54% |
1.657 |
1.782 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint16_t_To_uint64_t_
|
7.43% |
23285.744 |
25015.124 |
22.355 |
-0.01% |
22.355 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC15
|
7.40% |
50.690 |
54.441 |
0.003 |
-0.00% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC31
|
7.18% |
69.467 |
74.458 |
0.003 |
-0.01% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC15
|
7.04% |
42.089 |
45.054 |
0.001 |
0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC63
|
6.98% |
107.035 |
114.509 |
0.004 |
-0.00% |
0.004 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_xor_runtime_checks_pass<16, int>
|
6.97% |
26.907 |
28.784 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_xor_runtime_checks_fail<16, int>
|
6.97% |
26.909 |
28.784 |
0.002 |
0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC63
|
6.93% |
69.462 |
74.279 |
0.240 |
0.06% |
0.240 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC127
|
6.78% |
64.457 |
68.827 |
0.002 |
0.01% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC128
|
6.77% |
64.462 |
68.827 |
0.002 |
-0.01% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC15
|
6.76% |
36.922 |
39.417 |
0.003 |
-0.01% |
0.003 |
|
SingleSource/Benchmarks/Misc/flops-6
Profile
|
6.73% |
1.229 |
1.312 |
0.001 |
-0.04% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint16_t>/127
|
6.72% |
130.160 |
138.907 |
0.005 |
-0.00% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC127
|
6.70% |
2295.284 |
2449.033 |
2.645 |
0.34% |
2.645 |
|
SingleSource/Benchmarks/Misc-C++/Large/sphereflake
Profile
|
6.58% |
18.775 |
20.011 |
0.005 |
-0.01% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC16
|
6.55% |
38.172 |
40.673 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC127
|
6.51% |
182.709 |
194.599 |
0.127 |
-0.00% |
0.127 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_HYDRO_2D_RAW/171
|
6.50% |
83.266 |
88.675 |
0.703 |
0.06% |
0.703 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIND_FIRST_MIN_RAW/5001
|
6.37% |
42.520 |
45.228 |
0.225 |
-0.25% |
0.225 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_only_autovec_int32_t_
|
6.34% |
170202.977 |
180997.411 |
516.133 |
-0.07% |
516.133 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC1
|
6.31% |
85.090 |
90.457 |
0.236 |
0.99% |
0.236 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint8_t>/65
|
6.28% |
89.489 |
95.110 |
0.004 |
-0.00% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint32_t>/127
|
6.24% |
130.169 |
138.291 |
0.003 |
0.00% |
0.003 |
|
MultiSource/Benchmarks/MiBench/telecomm-gsm/telecomm-gsm
Profile
|
6.19% |
0.625 |
0.663 |
0.000 |
0.00% |
0.000 |
|
SingleSource/Benchmarks/Misc/oourafft
Profile
|
6.05% |
14.631 |
15.517 |
0.011 |
1.79% |
0.011 |
|
External/SPEC/CFP2017rate/538.imagick_r/538.imagick_r
Profile
|
6.05% |
275.993 |
292.689 |
0.816 |
-0.20% |
0.816 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC16
|
5.99% |
31.288 |
33.162 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC32
|
5.96% |
41.927 |
44.426 |
0.003 |
-0.01% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC32
|
5.96% |
41.928 |
44.425 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_BAND_LIN_EQ_LAMBDA/5001
|
5.95% |
20.243 |
21.448 |
0.030 |
1.79% |
0.030 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_HYDRO_2D_LAMBDA/171
|
5.95% |
83.412 |
88.373 |
0.466 |
-0.32% |
0.466 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC31
|
5.91% |
42.553 |
45.066 |
0.004 |
0.00% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC31
|
5.88% |
42.552 |
45.053 |
0.003 |
0.00% |
0.003 |
|
MultiSource/Benchmarks/SciMark2-C/scimark2
Profile
|
5.78% |
101.812 |
107.698 |
0.045 |
0.00% |
0.045 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_DIFF_PREDICT_RAW/171
|
5.76% |
11.310 |
11.961 |
0.208 |
0.24% |
0.208 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint8_t_To_uint16_t_
|
5.61% |
3434.756 |
3627.431 |
6.768 |
-0.16% |
6.768 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint32_t>/999
|
5.60% |
659.554 |
696.476 |
0.056 |
-0.01% |
0.056 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC7
|
5.59% |
66.963 |
70.709 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopWithReductionTC1
|
5.55% |
11.264 |
11.889 |
0.000 |
0.00% |
0.000 |
|
MultiSource/Benchmarks/Rodinia/hotspot/hotspot
Profile
|
5.55% |
1.928 |
2.035 |
0.006 |
-0.02% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint32_t>/999
|
5.51% |
1293.818 |
1365.061 |
0.055 |
0.00% |
0.055 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint32_t_To_uint64_t_
|
5.47% |
20319.821 |
21432.231 |
86.025 |
-0.09% |
86.025 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC31
|
5.40% |
23.154 |
24.404 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC31
|
5.40% |
23.154 |
24.403 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC32
|
5.40% |
23.154 |
24.403 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC15
|
5.39% |
121.711 |
128.273 |
0.003 |
-0.00% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC32
|
5.39% |
23.155 |
24.403 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC32
|
5.37% |
58.197 |
61.322 |
0.003 |
0.00% |
0.003 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIND_FIRST_MIN_RAW/44217
|
5.30% |
369.628 |
389.227 |
0.455 |
-0.09% |
0.455 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC31
|
5.25% |
229.216 |
241.248 |
0.003 |
0.01% |
0.003 |
|
SingleSource/Benchmarks/Polybench/stencils/jacobi-2d/jacobi-2d
Profile
|
5.19% |
30.653 |
32.245 |
0.034 |
0.07% |
0.034 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint32_t>/256
|
5.04% |
346.715 |
364.180 |
0.009 |
0.00% |
0.009 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C++/miniFE/miniFE
Profile
|
4.99% |
15.065 |
15.817 |
0.084 |
-0.95% |
0.084 |
|
SingleSource/Benchmarks/Misc/revertBits
Profile
|
4.90% |
0.611 |
0.641 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC64
|
4.85% |
41.734 |
43.759 |
0.020 |
-0.10% |
0.020 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC16
|
4.83% |
30.040 |
31.491 |
0.190 |
0.49% |
0.190 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_runtime_checks_pass<16, int>
|
4.81% |
51.937 |
54.436 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_runtime_checks_fail<16, int>
|
4.81% |
51.939 |
54.438 |
0.003 |
-0.00% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint16_t>/65
|
4.81% |
90.747 |
95.113 |
0.006 |
-0.00% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopWithReductionTC2
|
4.65% |
13.153 |
13.765 |
0.000 |
-0.01% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC31
|
4.65% |
66.964 |
70.077 |
0.002 |
-0.01% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC1
|
4.54% |
13.769 |
14.394 |
0.000 |
-0.01% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC3
|
4.54% |
13.767 |
14.392 |
0.000 |
-0.01% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC8
|
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:benchAutoVecForLoopTC4
|
4.54% |
13.766 |
14.391 |
0.003 |
-0.01% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC4
|
4.54% |
13.767 |
14.392 |
0.003 |
-0.01% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC2
|
4.54% |
13.767 |
14.392 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC7
|
4.54% |
13.767 |
14.391 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC2
|
4.54% |
13.767 |
14.391 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC15
|
4.54% |
13.767 |
14.392 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC7
|
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 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC3
|
4.53% |
13.768 |
14.392 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC15
|
4.53% |
13.768 |
14.391 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC8
|
4.52% |
13.769 |
14.391 |
0.000 |
-0.01% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint64_t>/999
|
4.43% |
1734.336 |
1811.179 |
0.075 |
-0.00% |
0.075 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_PIC_2D_RAW/171
|
4.41% |
12.966 |
13.539 |
0.068 |
-0.01% |
0.068 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_PIC_2D_LAMBDA/171
|
4.37% |
12.905 |
13.469 |
0.056 |
-0.21% |
0.056 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_nested_cond_load_novec_int32_t_
|
4.37% |
623484.192 |
650727.114 |
311.959 |
0.73% |
311.959 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint64_t>/999
|
4.30% |
3446.813 |
3595.178 |
0.191 |
0.00% |
0.191 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint64_t>/256
|
4.24% |
897.394 |
935.471 |
0.048 |
-0.01% |
0.048 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_runtime_checks_fail<4, int>
|
4.24% |
15.331 |
15.981 |
0.218 |
-0.10% |
0.218 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_ENERGY_CALC_RAW/171
|
4.23% |
13.648 |
14.225 |
0.015 |
-0.11% |
0.015 |
|
SingleSource/Benchmarks/Misc/flops-5
Profile
|
4.21% |
1.939 |
2.020 |
0.001 |
-0.03% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_ENERGY_CALC_LAMBDA/171
|
4.20% |
13.619 |
14.192 |
0.033 |
-0.39% |
0.033 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_BAND_LIN_EQ_RAW/5001
|
4.20% |
20.398 |
21.256 |
0.138 |
0.65% |
0.138 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC31
|
4.19% |
59.453 |
61.945 |
0.004 |
-0.00% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_only_autovec_uint8_t_
|
4.16% |
92353.371 |
96192.045 |
5.873 |
0.01% |
5.873 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint32_t>/65
|
4.12% |
90.744 |
94.484 |
0.005 |
-0.00% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC32
|
4.11% |
60.703 |
63.199 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint32_t>/256
|
4.10% |
212.779 |
221.504 |
0.002 |
0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC3
|
4.00% |
15.644 |
16.269 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_PRESSURE_CALC_RAW/44217
|
3.96% |
483.335 |
502.484 |
2.008 |
0.06% |
2.008 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint8_t_To_uint64_t_
|
3.91% |
22589.749 |
23472.043 |
50.448 |
-0.05% |
50.448 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<31, EqZero, First>
|
3.82% |
3223.385 |
3346.437 |
0.074 |
0.00% |
0.074 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint64_t>/256
|
3.76% |
495.737 |
514.393 |
0.028 |
-0.00% |
0.028 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC64
|
3.73% |
66.960 |
69.458 |
0.006 |
0.00% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC64
|
3.72% |
66.963 |
69.453 |
0.005 |
-0.01% |
0.005 |
|
SingleSource/Benchmarks/BenchmarkGame/n-body
Profile
|
3.69% |
2.634 |
2.731 |
0.000 |
26.22% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC63
|
3.68% |
67.587 |
70.075 |
0.006 |
-0.01% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC63
|
3.68% |
67.598 |
70.087 |
0.007 |
-0.01% |
0.007 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC63
|
3.65% |
41.654 |
43.173 |
0.295 |
-0.28% |
0.295 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC31
|
3.55% |
58.196 |
60.261 |
0.149 |
-0.02% |
0.149 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint16_t_To_uint8_t_
|
3.52% |
2777.140 |
2874.937 |
5.224 |
-0.11% |
5.224 |
|
External/SPEC/CFP2017rate/544.nab_r/544.nab_r
Profile
|
3.48% |
460.466 |
476.468 |
0.129 |
-0.30% |
0.129 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<32, EqZero, Last>
|
3.46% |
6815.452 |
7050.998 |
47.196 |
-0.03% |
47.196 |
|
MultiSource/Benchmarks/nbench/nbench
Profile
|
3.37% |
5.907 |
6.106 |
0.002 |
-0.34% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint16_t_To_uint8_t_
|
3.32% |
4378.426 |
4523.702 |
4.046 |
0.12% |
4.046 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint64_t_To_uint32_t_
|
3.29% |
18684.265 |
19298.284 |
89.698 |
0.03% |
89.698 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint16_t>/999
|
3.26% |
498.735 |
514.971 |
0.018 |
-0.01% |
0.018 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint32_t_To_uint16_t_
|
3.23% |
9544.489 |
9852.453 |
20.147 |
-0.28% |
20.147 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1BigLoopWithReductionTC1
|
3.21% |
19.401 |
20.025 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchVecWithRuntimeChecks4PointersDBeforeA/1000
|
3.17% |
4866096.042 |
5020205.317 |
208.068 |
0.00% |
208.068 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC31
|
3.14% |
886.148 |
913.978 |
8.162 |
-0.33% |
8.162 |
|
SingleSource/Benchmarks/Shootout/Shootout-lists
Profile
|
3.09% |
10.976 |
11.315 |
0.001 |
0.00% |
0.001 |
|
MultiSource/Benchmarks/sim/sim
Profile
|
3.05% |
9.424 |
9.711 |
0.007 |
0.06% |
0.007 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint16_t>/999
|
2.90% |
985.122 |
1013.684 |
0.046 |
-0.02% |
0.046 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_PRESSURE_CALC_LAMBDA/44217
|
2.89% |
487.912 |
502.031 |
0.474 |
-0.06% |
0.474 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC64
|
2.88% |
108.260 |
111.373 |
0.011 |
-0.01% |
0.011 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_DISC_ORD_LAMBDA/5001
|
2.86% |
612.064 |
629.547 |
6.180 |
-1.22% |
6.180 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC1
|
2.84% |
21.904 |
22.526 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC1
|
2.83% |
21.905 |
22.525 |
0.001 |
-0.01% |
0.001 |
|
MultiSource/Benchmarks/Rodinia/pathfinder/pathfinder
Profile
|
2.80% |
1.242 |
1.277 |
0.008 |
0.02% |
0.008 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC127
|
2.74% |
3078.697 |
3163.192 |
24.098 |
0.09% |
24.098 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC128
|
2.72% |
2928.472 |
3008.194 |
22.741 |
0.10% |
22.741 |
|
MultiSource/Benchmarks/FreeBench/mason/mason
Profile
|
2.69% |
0.538 |
0.553 |
0.000 |
-0.02% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC63
|
2.66% |
117.035 |
120.144 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC16
|
2.65% |
14.020 |
14.392 |
0.000 |
-0.01% |
0.000 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, LessThanZero, None>
|
2.65% |
36558.154 |
37527.637 |
66.789 |
-0.13% |
66.789 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC32
|
2.63% |
30.483 |
31.286 |
0.000 |
-0.00% |
0.000 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C/CoMD/CoMD
Profile
|
2.62% |
9.663 |
9.917 |
0.004 |
0.13% |
0.004 |
|
SingleSource/Benchmarks/Misc-C++/oopack_v1p8
Profile
|
2.58% |
0.468 |
0.480 |
0.000 |
-7.56% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint8_t>/10
|
2.57% |
47.581 |
48.806 |
0.002 |
5.16% |
0.002 |
|
External/SPEC/CFP2017rate/519.lbm_r/519.lbm_r
Profile
|
2.57% |
195.142 |
200.156 |
1.751 |
-0.26% |
1.751 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint8_t_To_uint32_t_
|
2.54% |
6902.034 |
7077.066 |
0.853 |
-0.00% |
0.853 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC31
|
2.50% |
91.054 |
93.331 |
0.248 |
-0.56% |
0.248 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchVecWithRuntimeChecks4PointersDBeforeA/32
|
2.50% |
162142.305 |
166190.003 |
6.919 |
-0.01% |
6.919 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_only_autovec_int64_t_
|
2.41% |
1414576.176 |
1448650.324 |
343.435 |
-0.07% |
343.435 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC63
|
2.40% |
1709.695 |
1750.712 |
9.727 |
0.01% |
9.727 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint16_t_To_uint32_t_
|
2.39% |
11074.855 |
11339.714 |
56.421 |
-0.03% |
56.421 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC63
|
2.38% |
104.515 |
106.999 |
0.004 |
-0.00% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC31
|
2.36% |
30.509 |
31.228 |
0.024 |
0.01% |
0.024 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC64
|
2.35% |
105.762 |
108.246 |
0.003 |
-0.00% |
0.003 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<31, GreaterThanZero, Last>
|
2.32% |
8112.027 |
8300.395 |
16.446 |
0.06% |
16.446 |
|
SingleSource/Benchmarks/Misc/flops-1
Profile
|
2.21% |
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 |
0.009 |
-0.01% |
0.009 |
|
MultiSource/Benchmarks/FreeBench/fourinarow/fourinarow
Profile
|
2.11% |
0.637 |
0.651 |
0.000 |
0.01% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC127
|
2.11% |
117.652 |
120.136 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC127
|
2.11% |
117.654 |
120.135 |
0.004 |
-0.00% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC128
|
2.11% |
117.049 |
119.516 |
0.003 |
-0.01% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC15
|
2.10% |
43.808 |
44.728 |
0.076 |
0.46% |
0.076 |
|
MultiSource/Applications/sgefa/sgefa
Profile
|
2.05% |
0.566 |
0.578 |
0.001 |
0.52% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_EOS_RAW/171
|
1.99% |
0.856 |
0.873 |
0.001 |
0.01% |
0.001 |
|
SingleSource/Benchmarks/Shootout/Shootout-matrix
Profile
|
1.92% |
3.791 |
3.864 |
0.000 |
0.01% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint64_t_To_uint8_t_
|
1.90% |
19402.007 |
19769.776 |
13.819 |
-0.36% |
13.819 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint16_t>/256
|
1.86% |
267.845 |
272.815 |
0.012 |
-0.01% |
0.012 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_FLOYD_DITHER/128
|
1.85% |
429.931 |
437.899 |
1.136 |
-0.36% |
1.136 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<64, EqZero, None>
|
1.81% |
2900.642 |
2953.197 |
6.697 |
0.27% |
6.697 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint32_t_To_uint64_t_
|
1.80% |
25848.044 |
26313.062 |
74.843 |
0.12% |
74.843 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<64, GreaterThanZero, Mid>
|
1.75% |
2708.579 |
2756.003 |
11.270 |
-0.29% |
11.270 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint64_t>/51
|
1.70% |
145.813 |
148.296 |
0.008 |
-0.01% |
0.008 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_EOS_LAMBDA/171
|
1.65% |
0.858 |
0.872 |
0.001 |
-0.05% |
0.001 |
|
SingleSource/Benchmarks/BenchmarkGame/puzzle
Profile
|
1.62% |
0.858 |
0.872 |
0.003 |
-0.17% |
0.003 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_INT_PREDICT_RAW/171
|
1.58% |
6.817 |
6.925 |
0.004 |
-0.01% |
0.004 |
|
MultiSource/Benchmarks/VersaBench/ecbdes/ecbdes
Profile
|
1.58% |
5.061 |
5.141 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_csa_with_in_loop_arith_novec_int64_t_
|
1.58% |
1013118.896 |
1029099.652 |
473.248 |
-0.03% |
473.248 |
|
MultiSource/Applications/JM/lencod/lencod
Profile
|
1.57% |
32.179 |
32.684 |
0.049 |
0.36% |
0.049 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_nested_cond_load_novec_uint8_t_
|
1.57% |
496811.685 |
504589.910 |
195.380 |
-0.02% |
195.380 |
|
SingleSource/Benchmarks/Misc/mandel-2
Profile
|
1.56% |
2.496 |
2.535 |
0.000 |
0.00% |
0.000 |
|
MultiSource/Benchmarks/Olden/health/health
Profile
|
1.56% |
1.569 |
1.593 |
0.002 |
0.00% |
0.002 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_FLOYD_DITHER/512
|
1.52% |
6546.570 |
6646.202 |
3.394 |
0.02% |
3.394 |
|
External/SPEC/CINT2017rate/531.deepsjeng_r/531.deepsjeng_r
Profile
|
1.52% |
256.027 |
259.910 |
0.239 |
-0.08% |
0.239 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC32
|
1.50% |
48.896 |
49.630 |
0.200 |
-0.84% |
0.200 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC128
|
1.50% |
208.390 |
211.509 |
0.286 |
-0.00% |
0.286 |
|
MultiSource/Benchmarks/ASC_Sequoia/AMGmk/AMGmk
Profile
|
1.42% |
32.865 |
33.333 |
0.035 |
0.56% |
0.035 |
|
MultiSource/Applications/spiff/spiff
Profile
|
1.41% |
10.193 |
10.337 |
0.053 |
-0.60% |
0.053 |
|
MultiSource/Benchmarks/mafft/pairlocalalign
Profile
|
1.41% |
92.603 |
93.907 |
0.289 |
-0.16% |
0.289 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint64_t>/51
|
1.37% |
225.939 |
229.024 |
0.009 |
0.01% |
0.009 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<6, LessThanZero, Mid>
|
1.35% |
23547.096 |
23864.821 |
8.419 |
-0.02% |
8.419 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint8_t>/16
|
1.28% |
59.307 |
60.066 |
0.010 |
11.61% |
0.010 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC127
|
1.28% |
217.465 |
220.245 |
0.019 |
-0.01% |
0.019 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC127
|
1.27% |
194.635 |
197.104 |
0.004 |
0.00% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC128
|
1.27% |
195.871 |
198.355 |
0.002 |
-0.01% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint8_t_To_uint32_t_
|
1.22% |
12003.931 |
12149.936 |
29.135 |
-0.05% |
29.135 |
|
External/SPEC/CFP2017rate/511.povray_r/511.povray_r
Profile
|
1.21% |
33.583 |
33.990 |
0.031 |
0.54% |
0.031 |
|
MultiSource/Benchmarks/MallocBench/cfrac/cfrac
Profile
|
1.19% |
2.746 |
2.779 |
0.001 |
-0.04% |
0.001 |
|
SingleSource/Benchmarks/SmallPT/smallpt
Profile
|
1.13% |
29.711 |
30.047 |
0.001 |
0.04% |
0.001 |
|
MultiSource/Benchmarks/Fhourstones-3.1/fhourstones3.1
Profile
|
1.12% |
3.935 |
3.979 |
0.006 |
-0.00% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC63
|
1.10% |
128.729 |
130.151 |
0.002 |
-0.01% |
0.002 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_INT_PREDICT_LAMBDA/171
|
1.09% |
6.842 |
6.917 |
0.007 |
-0.12% |
0.007 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_csa_with_cond_arith_autovec_int64_t_
|
1.07% |
737807.733 |
745678.830 |
301.347 |
0.10% |
301.347 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_sinhf_novec_float_
|
1.05% |
2218.467 |
2241.820 |
0.970 |
-0.00% |
0.970 |
|
External/SPEC/CINT2017rate/525.x264_r/525.x264_r
Profile
|
1.05% |
128.209 |
129.551 |
0.146 |
-0.05% |
0.146 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_sinhf_autovec_float_
|
1.04% |
2219.026 |
2242.098 |
0.189 |
-0.03% |
0.189 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<16, EqZero, None>
|
1.01% |
8094.444 |
8176.278 |
0.716 |
-0.02% |
0.716 |