|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_INT_PREDICT_LAMBDA/44217
|
136.44% |
8204.957 |
19399.637 |
96.228 |
-0.34% |
96.228 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint64_t_To_uint16_t_
|
105.02% |
18975.116 |
38902.442 |
104.984 |
9.35% |
104.984 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint64_t_To_uint8_t_
|
92.21% |
19092.252 |
36696.431 |
77.004 |
1.07% |
77.004 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint64_t_To_uint32_t_
|
80.85% |
19705.444 |
35637.777 |
702.763 |
-0.15% |
702.763 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint16_t_To_uint64_t_
|
78.00% |
10534.357 |
18751.343 |
121.125 |
-0.57% |
121.125 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint64_t_To_uint32_t_
|
70.26% |
22725.120 |
38690.962 |
208.722 |
2.49% |
208.722 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_DIFF_PREDICT_LAMBDA/44217
|
70.24% |
14199.605 |
24173.965 |
466.622 |
0.40% |
466.622 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint8_t_To_uint64_t_
|
68.76% |
10544.079 |
17793.675 |
104.303 |
0.11% |
104.303 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_INT_PREDICT_LAMBDA/5001
|
66.77% |
921.690 |
1537.096 |
105.138 |
-6.78% |
105.138 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_DIFF_PREDICT_RAW/44217
|
64.47% |
14238.163 |
23417.789 |
1076.247 |
0.71% |
1076.247 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIRST_DIFF_LAMBDA/44217
|
61.63% |
103.531 |
167.342 |
6.957 |
-2.91% |
6.957 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_DIFF_PREDICT_LAMBDA/5001
|
61.03% |
1586.626 |
2554.985 |
110.218 |
0.24% |
110.218 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/32
|
59.38% |
884.116 |
1409.146 |
0.053 |
-0.00% |
0.053 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/16
|
59.29% |
177.116 |
282.126 |
0.006 |
0.00% |
0.006 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/64
|
59.05% |
3920.487 |
6235.394 |
6.718 |
-0.01% |
6.718 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/256
|
57.82% |
68407.358 |
107959.284 |
37.344 |
0.00% |
37.344 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/128
|
57.42% |
16809.301 |
26462.010 |
9.267 |
0.04% |
9.267 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_DIFF_PREDICT_RAW/5001
|
55.35% |
1635.459 |
2540.725 |
141.117 |
-0.14% |
141.117 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint64_t_To_uint16_t_
|
52.39% |
19179.687 |
29227.234 |
107.649 |
-0.02% |
107.649 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint64_t_To_uint8_t_
|
50.83% |
19927.002 |
30055.159 |
103.221 |
-0.03% |
103.221 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C/miniGMG/miniGMG
Profile
|
50.54% |
5.861 |
8.823 |
0.319 |
2.72% |
0.319 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint32_t_To_uint64_t_
|
46.71% |
16427.497 |
24100.802 |
1226.013 |
4.37% |
1226.013 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIRST_DIFF_RAW/44217
|
46.19% |
106.170 |
155.205 |
7.239 |
6.61% |
7.239 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, EqZero, None>
|
45.39% |
14106.391 |
20509.650 |
0.690 |
0.00% |
0.690 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint32_t_To_uint8_t_
|
40.88% |
9796.668 |
13801.505 |
54.754 |
2.78% |
54.754 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint64_t_To_uint16_t_
|
37.17% |
18551.494 |
25447.508 |
7.078 |
-1.92% |
7.078 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC128
|
37.09% |
407.489 |
558.620 |
0.160 |
0.02% |
0.160 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC128
|
36.71% |
945.524 |
1292.616 |
2.341 |
-0.35% |
2.341 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC32
|
35.76% |
246.472 |
334.615 |
1.030 |
-0.41% |
1.030 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC64
|
35.60% |
482.331 |
654.059 |
1.049 |
-0.42% |
1.049 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC16
|
34.86% |
129.316 |
174.397 |
0.203 |
-0.57% |
0.203 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC64
|
34.41% |
217.158 |
291.881 |
0.235 |
-0.06% |
0.235 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint32_t_To_uint64_t_
|
32.17% |
15778.856 |
20854.690 |
908.908 |
15.54% |
908.908 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, EqZero, None>
|
31.52% |
12182.746 |
16022.228 |
0.746 |
-0.01% |
0.746 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint32_t_To_uint8_t_
|
31.27% |
11388.224 |
14949.301 |
47.210 |
5.23% |
47.210 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC128
|
30.04% |
464.424 |
603.920 |
0.059 |
0.20% |
0.059 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC128
|
29.70% |
465.611 |
603.904 |
0.046 |
-0.01% |
0.046 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC32
|
29.50% |
122.648 |
158.827 |
0.109 |
-0.08% |
0.109 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIRST_SUM_LAMBDA/44217
|
29.10% |
136.537 |
176.268 |
1.787 |
-3.25% |
1.787 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint64_t_To_uint8_t_
|
29.09% |
20577.335 |
26564.223 |
48.406 |
-4.05% |
48.406 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint16_t_To_uint64_t_
|
28.98% |
10367.458 |
13371.622 |
126.244 |
-0.80% |
126.244 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC64
|
28.44% |
244.071 |
313.488 |
0.029 |
-0.01% |
0.029 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC64
|
28.44% |
244.072 |
313.487 |
0.018 |
0.38% |
0.018 |
|
SingleSource/Benchmarks/Adobe-C++/loop_unroll
Profile
|
28.35% |
2.425 |
3.113 |
0.023 |
-23.27% |
0.023 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC127
|
28.13% |
480.106 |
615.179 |
0.010 |
-0.01% |
0.010 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC127
|
28.13% |
480.087 |
615.154 |
0.017 |
0.08% |
0.017 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint8_t_To_uint32_t_
|
27.99% |
5171.094 |
6618.643 |
81.725 |
-0.09% |
81.725 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint16_t_To_uint32_t_
|
27.66% |
5578.098 |
7121.144 |
63.895 |
0.09% |
63.895 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIND_FIRST_MIN_LAMBDA/171
|
26.93% |
1.182 |
1.500 |
0.000 |
-0.04% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIND_FIRST_MIN_LAMBDA/44217
|
26.88% |
306.953 |
389.469 |
0.119 |
-0.03% |
0.119 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIND_FIRST_MIN_LAMBDA/5001
|
25.69% |
35.957 |
45.195 |
0.209 |
0.45% |
0.209 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC32
|
25.68% |
133.922 |
168.316 |
0.005 |
0.00% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC32
|
25.66% |
133.942 |
168.318 |
0.004 |
0.74% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC128
|
25.38% |
218.876 |
274.435 |
2.490 |
3.91% |
2.490 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC63
|
25.05% |
259.708 |
324.756 |
0.008 |
0.17% |
0.008 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC63
|
25.04% |
259.717 |
324.756 |
0.008 |
-0.01% |
0.008 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC127
|
24.70% |
219.993 |
274.325 |
3.369 |
3.64% |
3.369 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC127
|
24.48% |
514.895 |
640.960 |
0.217 |
-0.01% |
0.217 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC4
|
24.23% |
14.104 |
17.520 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC16
|
23.92% |
74.471 |
92.287 |
0.010 |
-0.02% |
0.010 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint64_t_To_uint32_t_
|
23.25% |
22097.255 |
27235.814 |
28.211 |
0.45% |
28.211 |
|
MultiSource/Benchmarks/TSVC/Searching-flt/Searching-flt
Profile
|
22.91% |
4.114 |
5.056 |
0.019 |
2.04% |
0.019 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint16_t_To_uint8_t_
|
22.11% |
3089.692 |
3772.679 |
0.542 |
-0.59% |
0.542 |
|
MultiSource/Benchmarks/Trimaran/enc-pc1/enc-pc1
Profile
|
22.09% |
0.904 |
1.104 |
0.000 |
0.01% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint32_t_To_uint16_t_
|
21.56% |
11130.453 |
13530.498 |
35.851 |
1.14% |
35.851 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC16
|
21.41% |
78.852 |
95.734 |
0.002 |
1.32% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC16
|
21.40% |
78.853 |
95.730 |
0.004 |
-0.01% |
0.004 |
|
MultiSource/Benchmarks/MiBench/security-rijndael/security-rijndael
Profile
|
21.18% |
0.278 |
0.336 |
0.000 |
7.28% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC128
|
21.02% |
471.602 |
570.714 |
0.027 |
0.20% |
0.027 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC64
|
20.95% |
246.270 |
297.866 |
0.010 |
0.41% |
0.010 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIRST_SUM_RAW/44217
|
20.86% |
137.326 |
165.967 |
6.214 |
-1.80% |
6.214 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC64
|
20.85% |
123.284 |
148.988 |
2.896 |
4.00% |
2.896 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC32
|
20.84% |
133.591 |
161.436 |
0.002 |
0.78% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC16
|
20.60% |
77.305 |
93.230 |
0.001 |
1.36% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC31
|
20.07% |
149.564 |
179.579 |
0.005 |
0.34% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC31
|
20.06% |
149.575 |
179.574 |
0.007 |
-0.01% |
0.007 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_PIC_2D_LAMBDA/44217
|
19.96% |
9909.203 |
11886.735 |
22.932 |
-0.29% |
22.932 |
|
MultiSource/Benchmarks/TSVC/Searching-dbl/Searching-dbl
Profile
|
19.87% |
7.605 |
9.116 |
0.023 |
-0.07% |
0.023 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC8
|
19.75% |
49.119 |
58.818 |
0.004 |
2.17% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint32_t_To_uint16_t_
|
19.39% |
11274.236 |
13460.163 |
5.301 |
-2.95% |
5.301 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint8_t_To_uint64_t_
|
19.17% |
10926.339 |
13021.390 |
284.851 |
1.87% |
284.851 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_HYDRO_1D_RAW/171
|
19.04% |
0.372 |
0.443 |
0.001 |
-0.12% |
0.001 |
|
External/SPEC/CFP2017rate/538.imagick_r/538.imagick_r
Profile
|
18.97% |
275.170 |
327.378 |
0.289 |
11.72% |
0.289 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC7
|
18.96% |
23.168 |
27.561 |
0.913 |
18.61% |
0.913 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_HYDRO_1D_LAMBDA/171
|
18.91% |
0.372 |
0.442 |
0.001 |
-0.23% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_PIC_2D_LAMBDA/5001
|
18.82% |
975.445 |
1158.996 |
37.468 |
-2.91% |
37.468 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_HYDRO_2D_RAW/5001
|
18.65% |
8378.037 |
9940.646 |
148.859 |
2.40% |
148.859 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC63
|
18.45% |
127.205 |
150.670 |
2.307 |
4.95% |
2.307 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint16_t_To_uint32_t_
|
18.44% |
6294.910 |
7455.987 |
0.417 |
-0.01% |
0.417 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, EqZero, First>
|
18.17% |
14106.064 |
16669.606 |
0.479 |
0.00% |
0.479 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_no_runtime_checks_needed<16, int>
|
18.16% |
20.652 |
24.402 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, EqZero, Mid>
|
18.15% |
14105.852 |
16665.528 |
0.873 |
-0.01% |
0.873 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, EqZero, Last>
|
18.11% |
14109.971 |
16665.967 |
0.431 |
-0.00% |
0.431 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint32_t_To_uint8_t_
|
17.60% |
9100.267 |
10701.575 |
94.664 |
-0.68% |
94.664 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC127
|
17.52% |
515.430 |
605.742 |
0.038 |
0.08% |
0.038 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_VOL3D_CALC_LAMBDA/2
|
16.97% |
7.111 |
8.319 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_VOL3D_CALC_RAW/2
|
16.97% |
7.112 |
8.319 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC128
|
16.96% |
943.330 |
1103.282 |
0.036 |
-17.35% |
0.036 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC127
|
16.83% |
937.591 |
1095.403 |
0.242 |
-17.13% |
0.242 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_HYDRO_2D_RAW/44217
|
16.81% |
81848.953 |
95609.750 |
1283.482 |
0.45% |
1283.482 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC64
|
16.59% |
482.499 |
562.554 |
0.008 |
-16.53% |
0.008 |
|
SingleSource/Benchmarks/Misc/salsa20
Profile
|
16.43% |
13.212 |
15.383 |
0.000 |
-0.00% |
0.000 |
|
MultiSource/Benchmarks/MiBench/automotive-bitcount/automotive-bitcount
Profile
|
16.41% |
0.106 |
0.124 |
0.000 |
-26.22% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC63
|
16.29% |
476.856 |
554.531 |
0.595 |
-16.08% |
0.595 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_PIC_2D_RAW/5001
|
16.27% |
997.014 |
1159.238 |
56.762 |
-4.84% |
56.762 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint8_t_To_uint16_t_
|
16.19% |
3234.686 |
3758.350 |
0.150 |
-0.00% |
0.150 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC15
|
16.18% |
38.174 |
44.352 |
0.249 |
16.20% |
0.249 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC1
|
16.08% |
44.742 |
51.935 |
0.001 |
5.06% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC7
|
16.07% |
44.743 |
51.933 |
0.001 |
5.06% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC4
|
16.06% |
44.745 |
51.933 |
0.002 |
5.06% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC2
|
16.06% |
44.747 |
51.933 |
0.003 |
5.05% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC3
|
16.04% |
44.754 |
51.934 |
0.001 |
5.05% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC8
|
15.94% |
44.794 |
51.934 |
0.003 |
4.91% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC8
|
15.93% |
20.510 |
23.777 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC32
|
15.86% |
252.209 |
292.203 |
0.014 |
-14.89% |
0.014 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC8
|
15.84% |
51.315 |
59.442 |
0.003 |
2.14% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC8
|
15.84% |
51.314 |
59.440 |
0.003 |
-0.01% |
0.003 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, EqZero, First>
|
15.76% |
12182.459 |
14102.295 |
0.549 |
-0.00% |
0.549 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, EqZero, Last>
|
15.75% |
12182.908 |
14102.299 |
0.566 |
-0.00% |
0.566 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, EqZero, Mid>
|
15.75% |
12183.177 |
14102.317 |
0.933 |
-0.01% |
0.933 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC8
|
15.62% |
20.023 |
23.151 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint32_t_To_uint8_t_
|
15.50% |
9671.914 |
11171.370 |
72.827 |
-0.25% |
72.827 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC63
|
15.50% |
324.255 |
374.525 |
0.027 |
0.00% |
0.027 |
|
External/SPEC/CFP2017rate/508.namd_r/508.namd_r
Profile
|
15.34% |
194.221 |
224.015 |
0.408 |
1.52% |
0.408 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC31
|
15.21% |
246.580 |
284.097 |
0.023 |
-14.01% |
0.023 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC128
|
15.03% |
70.713 |
81.339 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_VOL3D_CALC_LAMBDA/0
|
14.92% |
1063.843 |
1222.602 |
1.040 |
-0.56% |
1.040 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_VOL3D_CALC_RAW/0
|
14.87% |
1065.159 |
1223.568 |
0.333 |
0.05% |
0.333 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint8_t_To_uint16_t_
|
14.78% |
3954.687 |
4539.234 |
0.423 |
-0.00% |
0.423 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC63
|
14.77% |
290.053 |
332.889 |
0.231 |
0.17% |
0.231 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC4
|
14.60% |
98.849 |
113.283 |
1.474 |
0.01% |
1.474 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC16
|
14.60% |
137.047 |
157.055 |
0.006 |
-11.84% |
0.006 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_HYDRO_2D_LAMBDA/5001
|
14.60% |
8361.619 |
9582.204 |
364.460 |
-1.29% |
364.460 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_VOL3D_CALC_RAW/1
|
14.26% |
218.255 |
249.375 |
0.086 |
-0.00% |
0.086 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint16_t_To_uint8_t_
|
14.22% |
4155.265 |
4746.174 |
0.475 |
-0.58% |
0.475 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint32_t_To_uint16_t_
|
14.12% |
9343.809 |
10662.866 |
409.261 |
-1.29% |
409.261 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_VOL3D_CALC_LAMBDA/1
|
14.09% |
218.638 |
249.437 |
0.240 |
-0.00% |
0.240 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC31
|
13.60% |
76.341 |
86.721 |
0.415 |
4.84% |
0.415 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC15
|
13.32% |
131.424 |
148.923 |
0.048 |
-9.57% |
0.048 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC2
|
13.31% |
18.774 |
21.274 |
0.001 |
30.77% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC15
|
13.23% |
94.491 |
106.995 |
0.003 |
-0.53% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC15
|
13.23% |
94.495 |
106.997 |
0.001 |
0.59% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint64_t_To_uint8_t_
|
13.11% |
19113.436 |
21619.339 |
65.489 |
0.13% |
65.489 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC16
|
12.93% |
45.989 |
51.934 |
0.003 |
5.04% |
0.003 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_HYDRO_2D_LAMBDA/44217
|
12.67% |
82251.083 |
92673.255 |
2530.508 |
-0.69% |
2530.508 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC16
|
12.63% |
29.445 |
33.163 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC15
|
12.61% |
46.117 |
51.934 |
0.002 |
5.05% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC8
|
12.58% |
79.478 |
89.476 |
0.003 |
-6.54% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC4
|
12.49% |
20.024 |
22.525 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC3
|
12.49% |
20.024 |
22.525 |
0.001 |
28.56% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC4
|
12.49% |
20.027 |
22.528 |
0.000 |
-0.00% |
0.000 |
|
SingleSource/Benchmarks/Misc/pi
Profile
|
12.07% |
1.657 |
1.857 |
0.000 |
4.21% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint64_t_To_uint16_t_
|
12.05% |
18674.877 |
20925.494 |
249.211 |
9.69% |
249.211 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_DISC_ORD_RAW/44217
|
11.80% |
13229.165 |
14789.904 |
152.023 |
-0.24% |
152.023 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC32
|
11.79% |
76.342 |
85.346 |
0.930 |
4.34% |
0.930 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC4
|
11.75% |
21.276 |
23.776 |
0.001 |
46.57% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC64
|
11.67% |
48.184 |
53.808 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_PIC_2D_RAW/44217
|
11.50% |
10678.769 |
11907.333 |
30.798 |
-0.61% |
30.798 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/16
|
11.32% |
103.723 |
115.463 |
0.010 |
0.19% |
0.010 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIRST_SUM_LAMBDA/5001
|
11.20% |
18.336 |
20.390 |
0.162 |
-2.12% |
0.162 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/32
|
11.09% |
425.790 |
472.996 |
0.026 |
0.07% |
0.026 |
|
SingleSource/Benchmarks/Misc-C++/oopack_v1p8
Profile
|
11.02% |
0.467 |
0.519 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC16
|
10.98% |
32.699 |
36.291 |
0.001 |
-1.71% |
0.001 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/128
|
10.82% |
7146.894 |
7919.972 |
1.825 |
0.09% |
1.825 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC8
|
10.79% |
23.155 |
25.654 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC8
|
10.79% |
23.156 |
25.654 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/256
|
10.78% |
28387.673 |
31446.708 |
14.964 |
0.01% |
14.964 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC31
|
10.75% |
177.411 |
196.476 |
0.004 |
0.31% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC32
|
10.71% |
48.044 |
53.187 |
0.002 |
0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC7
|
10.64% |
29.412 |
32.541 |
0.001 |
0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC127
|
10.53% |
91.996 |
101.683 |
0.343 |
0.31% |
0.343 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC7
|
10.51% |
23.780 |
26.279 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC7
|
10.51% |
23.781 |
26.279 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC16
|
10.39% |
28.835 |
31.829 |
0.032 |
0.09% |
0.032 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC7
|
10.19% |
73.841 |
81.367 |
0.015 |
-1.32% |
0.015 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/64
|
10.06% |
1738.194 |
1913.130 |
9.204 |
0.05% |
9.204 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_DEL_DOT_VEC_2D_LAMBDA/1
|
10.04% |
260.792 |
286.983 |
0.042 |
-0.06% |
0.042 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_DEL_DOT_VEC_2D_RAW/1
|
10.03% |
260.707 |
286.844 |
0.063 |
-0.08% |
0.063 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC4
|
9.99% |
37.547 |
41.297 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC4
|
9.99% |
37.547 |
41.297 |
0.005 |
3.12% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC4
|
9.86% |
50.687 |
55.687 |
0.002 |
2.03% |
0.002 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_BAND_LIN_EQ_LAMBDA/44217
|
9.75% |
146.767 |
161.079 |
2.905 |
-4.31% |
2.905 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC7
|
9.74% |
25.657 |
28.156 |
0.000 |
24.99% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC8
|
9.52% |
13.141 |
14.391 |
0.000 |
4.54% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC3
|
9.52% |
13.141 |
14.392 |
0.000 |
4.53% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC3
|
9.52% |
13.141 |
14.392 |
0.000 |
4.54% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC8
|
9.52% |
13.141 |
14.391 |
0.001 |
4.54% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC2
|
9.51% |
13.141 |
14.391 |
0.000 |
4.54% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC1
|
9.51% |
13.141 |
14.391 |
0.000 |
4.53% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC2
|
9.51% |
13.141 |
14.391 |
0.000 |
4.54% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC1
|
9.51% |
13.143 |
14.393 |
0.001 |
2.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC7
|
9.51% |
13.141 |
14.391 |
0.001 |
4.53% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC4
|
9.51% |
13.141 |
14.391 |
0.000 |
4.53% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC16
|
9.51% |
13.142 |
14.391 |
0.000 |
4.54% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC7
|
9.51% |
13.141 |
14.391 |
0.001 |
4.54% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC15
|
9.51% |
13.142 |
14.391 |
0.001 |
4.54% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_DEL_DOT_VEC_2D_LAMBDA/2
|
9.51% |
3.205 |
3.510 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC15
|
9.50% |
13.142 |
14.391 |
0.001 |
4.54% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC16
|
9.50% |
13.142 |
14.391 |
0.000 |
4.54% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_DEL_DOT_VEC_2D_RAW/2
|
9.50% |
3.205 |
3.509 |
0.000 |
-0.01% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC4
|
9.50% |
13.144 |
14.392 |
0.001 |
4.54% |
0.001 |
|
MultiSource/Benchmarks/FreeBench/pifft/pifft
Profile
|
9.45% |
0.329 |
0.360 |
0.000 |
0.47% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_DIFF_PREDICT_LAMBDA/171
|
9.37% |
11.258 |
12.313 |
0.236 |
-0.53% |
0.236 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC8
|
9.27% |
26.913 |
29.407 |
0.001 |
23.10% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint8_t_To_uint16_t_
|
9.09% |
5271.490 |
5750.669 |
1.430 |
-0.79% |
1.430 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_runtime_checks_fail<4, int>
|
8.83% |
15.334 |
16.688 |
0.044 |
-0.31% |
0.044 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC64
|
8.74% |
85.735 |
93.230 |
0.002 |
-0.00% |
0.002 |
|
MultiSource/Benchmarks/TSVC/NodeSplitting-dbl/NodeSplitting-dbl
Profile
|
8.59% |
26.315 |
28.576 |
0.589 |
7.71% |
0.589 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC16
|
8.50% |
29.412 |
31.911 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC16
|
8.49% |
29.412 |
31.911 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC32
|
8.46% |
36.920 |
40.044 |
0.003 |
-0.00% |
0.003 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C++/miniFE/miniFE
Profile
|
8.39% |
15.164 |
16.435 |
0.097 |
-1.63% |
0.097 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC15
|
8.31% |
30.039 |
32.535 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/ImageProcessing/Dilate/Dilate.test:BENCHMARK_DILATE/1024
|
8.26% |
6777.741 |
7337.763 |
155.644 |
0.55% |
155.644 |
|
MultiSource/Benchmarks/VersaBench/beamformer/beamformer
Profile
|
8.17% |
4.805 |
5.198 |
0.001 |
34.98% |
0.001 |
|
MultiSource/Benchmarks/Trimaran/enc-md5/enc-md5
Profile
|
8.10% |
3.244 |
3.506 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_DEL_DOT_VEC_2D_LAMBDA/0
|
8.08% |
1663.809 |
1798.280 |
8.147 |
-0.06% |
8.147 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_xor_no_runtime_checks_needed<16, int>
|
7.97% |
15.646 |
16.894 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC127
|
7.83% |
63.826 |
68.825 |
0.006 |
-0.00% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC128
|
7.82% |
63.834 |
68.826 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC128
|
7.77% |
160.821 |
173.322 |
0.003 |
-0.00% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint16_t_To_uint8_t_
|
7.75% |
6243.078 |
6726.822 |
1.188 |
-0.69% |
1.188 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIND_FIRST_MIN_RAW/171
|
7.73% |
1.389 |
1.497 |
0.000 |
-0.03% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint32_t_To_uint8_t_
|
7.68% |
9306.452 |
10021.025 |
79.731 |
4.82% |
79.731 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC63
|
7.51% |
106.502 |
114.501 |
0.020 |
-0.00% |
0.020 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_HYDRO_2D_LAMBDA/171
|
7.34% |
82.998 |
89.088 |
0.230 |
0.16% |
0.230 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC31
|
7.22% |
69.446 |
74.461 |
0.003 |
0.00% |
0.003 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_DEL_DOT_VEC_2D_RAW/0
|
7.09% |
1674.759 |
1793.579 |
1.425 |
-0.18% |
1.425 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC15
|
7.01% |
50.872 |
54.438 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC2
|
7.00% |
35.672 |
38.170 |
0.001 |
35.53% |
0.001 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_xor_runtime_checks_pass<16, int>
|
6.96% |
26.910 |
28.782 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_xor_runtime_checks_fail<16, int>
|
6.95% |
26.912 |
28.781 |
0.001 |
-0.00% |
0.001 |
|
SingleSource/Benchmarks/Misc/flops-6
Profile
|
6.78% |
1.228 |
1.312 |
0.000 |
1.30% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC15
|
6.76% |
36.923 |
39.420 |
0.001 |
21.15% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_BAND_LIN_EQ_RAW/171
|
6.75% |
0.343 |
0.366 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_BAND_LIN_EQ_LAMBDA/171
|
6.73% |
0.343 |
0.366 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint16_t_To_uint64_t_
|
6.73% |
18805.307 |
20070.152 |
73.305 |
-0.96% |
73.305 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint8_t>/127
|
6.72% |
130.161 |
138.908 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC63
|
6.69% |
69.458 |
74.108 |
0.245 |
0.36% |
0.245 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_HYDRO_2D_RAW/171
|
6.60% |
83.248 |
88.740 |
0.120 |
-0.34% |
0.120 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC16
|
6.55% |
38.173 |
40.672 |
0.000 |
32.65% |
0.000 |
|
SingleSource/Benchmarks/Misc-C++/Large/sphereflake
Profile
|
6.52% |
18.774 |
19.999 |
0.005 |
-0.03% |
0.005 |
|
SingleSource/Benchmarks/Misc/perlin
Profile
|
6.32% |
6.205 |
6.598 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC15
|
6.26% |
42.400 |
45.053 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint32_t>/127
|
6.23% |
130.184 |
138.288 |
0.014 |
0.46% |
0.014 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC16
|
5.98% |
31.291 |
33.162 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC32
|
5.96% |
41.928 |
44.425 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC32
|
5.95% |
41.930 |
44.425 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC15
|
5.91% |
121.104 |
128.267 |
0.004 |
0.48% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC31
|
5.90% |
42.553 |
45.065 |
0.004 |
0.03% |
0.004 |
|
MultiSource/Benchmarks/SciMark2-C/scimark2
Profile
|
5.87% |
101.747 |
107.722 |
0.016 |
0.06% |
0.016 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC31
|
5.87% |
42.553 |
45.050 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC8
|
5.79% |
25.032 |
26.480 |
0.335 |
5.80% |
0.335 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIND_FIRST_MIN_RAW/5001
|
5.79% |
42.724 |
45.196 |
0.258 |
0.01% |
0.258 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint16_t>/127
|
5.75% |
131.351 |
138.908 |
0.003 |
-0.00% |
0.003 |
|
MultiSource/Benchmarks/Rodinia/hotspot/hotspot
Profile
|
5.66% |
1.927 |
2.036 |
0.002 |
-0.02% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC127
|
5.63% |
184.221 |
194.599 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC7
|
5.60% |
66.956 |
70.707 |
0.001 |
0.88% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC7
|
5.60% |
66.960 |
70.707 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC3
|
5.55% |
45.057 |
47.557 |
0.006 |
15.14% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC1
|
5.54% |
11.264 |
11.889 |
0.000 |
5.54% |
0.000 |
|
MultiSource/Benchmarks/MiBench/telecomm-gsm/telecomm-gsm
Profile
|
5.51% |
0.624 |
0.659 |
0.000 |
-0.16% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC32
|
5.39% |
58.180 |
61.319 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC31
|
5.28% |
229.121 |
241.214 |
0.010 |
-0.00% |
0.010 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC32
|
5.22% |
47.562 |
50.046 |
0.003 |
0.33% |
0.003 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIND_FIRST_MIN_RAW/44217
|
5.18% |
370.104 |
389.292 |
0.446 |
-0.04% |
0.446 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC15
|
5.04% |
30.975 |
32.536 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint8_t_To_uint32_t_
|
5.02% |
11795.140 |
12386.967 |
43.428 |
-0.17% |
43.428 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint32_t_To_uint64_t_
|
4.93% |
20351.384 |
21354.341 |
7.299 |
-0.37% |
7.299 |
|
MicroBenchmarks/ImageProcessing/Blur/blur.test:BENCHMARK_boxBlurKernel/1024
|
4.92% |
23389.949 |
24540.313 |
72.155 |
-18.57% |
72.155 |
|
SingleSource/Benchmarks/Misc/revertBits
Profile
|
4.86% |
0.611 |
0.641 |
0.000 |
-0.02% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC31
|
4.82% |
89.508 |
93.818 |
0.016 |
0.05% |
0.016 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint8_t>/65
|
4.81% |
90.741 |
95.107 |
0.009 |
-0.00% |
0.009 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_runtime_checks_fail<16, int>
|
4.79% |
51.943 |
54.434 |
0.003 |
-0.00% |
0.003 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_runtime_checks_pass<16, int>
|
4.79% |
51.947 |
54.435 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC2
|
4.75% |
13.141 |
13.765 |
0.001 |
4.66% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC63
|
4.73% |
41.299 |
43.252 |
0.258 |
-0.91% |
0.258 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_PIC_2D_LAMBDA/171
|
4.70% |
12.899 |
13.506 |
0.024 |
-0.03% |
0.024 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC31
|
4.66% |
66.960 |
70.082 |
0.001 |
0.00% |
0.001 |
|
MultiSource/Benchmarks/nbench/nbench
Profile
|
4.64% |
5.889 |
6.162 |
0.000 |
0.62% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC64
|
4.53% |
41.301 |
43.173 |
0.193 |
-1.36% |
0.193 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_ENERGY_CALC_LAMBDA/171
|
4.51% |
13.630 |
14.244 |
0.016 |
0.02% |
0.016 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC1
|
4.36% |
85.250 |
88.971 |
0.961 |
0.08% |
0.961 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_PRESSURE_CALC_LAMBDA/44217
|
4.36% |
484.977 |
506.106 |
1.261 |
0.20% |
1.261 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint16_t_To_uint64_t_
|
4.35% |
23340.895 |
24355.161 |
63.193 |
-2.72% |
63.193 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_ENERGY_CALC_RAW/171
|
4.32% |
13.643 |
14.233 |
0.016 |
0.02% |
0.016 |
|
SingleSource/Benchmarks/Misc/flops-5
Profile
|
4.25% |
1.938 |
2.020 |
0.001 |
0.87% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC31
|
4.19% |
59.452 |
61.942 |
0.002 |
17.85% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC3
|
4.16% |
15.019 |
15.643 |
0.001 |
-3.84% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC32
|
4.14% |
30.039 |
31.281 |
0.003 |
-0.01% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint32_t>/65
|
4.13% |
90.736 |
94.481 |
0.005 |
0.66% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC32
|
4.11% |
60.698 |
63.194 |
0.003 |
24.69% |
0.003 |
|
SingleSource/Benchmarks/Polybench/stencils/jacobi-2d/jacobi-2d
Profile
|
4.04% |
30.676 |
31.914 |
0.148 |
-1.14% |
0.148 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_PIC_2D_RAW/171
|
4.01% |
12.985 |
13.506 |
0.048 |
-0.18% |
0.048 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<31, EqZero, First>
|
3.81% |
3223.129 |
3345.971 |
0.021 |
3.47% |
0.021 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC31
|
3.76% |
30.037 |
31.166 |
0.050 |
-0.38% |
0.050 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC64
|
3.73% |
66.960 |
69.455 |
0.003 |
0.00% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC64
|
3.71% |
66.966 |
69.453 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC63
|
3.69% |
67.583 |
70.079 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC63
|
3.69% |
67.588 |
70.082 |
0.010 |
-0.00% |
0.010 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint16_t>/65
|
3.69% |
91.728 |
95.112 |
0.007 |
-0.00% |
0.007 |
|
External/SPEC/CFP2017rate/544.nab_r/544.nab_r
Profile
|
3.65% |
460.787 |
477.627 |
0.150 |
0.32% |
0.150 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC31
|
3.49% |
58.202 |
60.232 |
0.119 |
0.27% |
0.119 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_PRESSURE_CALC_RAW/5001
|
3.30% |
43.875 |
45.323 |
0.513 |
-1.63% |
0.513 |
|
MicroBenchmarks/ImageProcessing/Dilate/Dilate.test:BENCHMARK_DILATE/256
|
3.29% |
1030.131 |
1063.979 |
2.705 |
-0.31% |
2.705 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1BigLoopWithReductionTC1
|
3.20% |
19.403 |
20.023 |
0.001 |
-0.00% |
0.001 |
|
SingleSource/Benchmarks/Shootout/Shootout-lists
Profile
|
3.19% |
10.963 |
11.313 |
0.001 |
2.15% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetBLambdaLoops/lcalsBLambda.test:BM_MULADDSUB_LAMBDA/171
|
3.19% |
0.415 |
0.428 |
0.001 |
-0.50% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchVecWithRuntimeChecks4PointersDBeforeA/1000
|
3.14% |
4866849.521 |
5019773.662 |
343.191 |
-0.00% |
343.191 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, LessThanZero, None>
|
3.05% |
36513.085 |
37627.102 |
43.572 |
1.38% |
43.572 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC64
|
2.91% |
108.228 |
111.376 |
0.004 |
-0.00% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC1
|
2.85% |
21.901 |
22.525 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/ImageProcessing/Blur/blur.test:BENCHMARK_boxBlurKernel/128
|
2.78% |
435.440 |
447.537 |
2.541 |
-0.85% |
2.541 |
|
MultiSource/Applications/JM/lencod/lencod
Profile
|
2.76% |
31.665 |
32.540 |
0.035 |
13.62% |
0.035 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopTC16
|
2.73% |
270.173 |
277.550 |
1.472 |
0.04% |
1.472 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC63
|
2.66% |
117.024 |
120.133 |
0.007 |
-0.00% |
0.007 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C/CoMD/CoMD
Profile
|
2.64% |
9.649 |
9.904 |
0.007 |
-0.61% |
0.007 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC31
|
2.62% |
23.780 |
24.404 |
0.022 |
2.33% |
0.022 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC31
|
2.62% |
23.780 |
24.402 |
0.001 |
2.55% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC32
|
2.61% |
23.781 |
24.402 |
0.001 |
2.60% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC32
|
2.61% |
23.781 |
24.402 |
0.001 |
2.63% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint8_t_To_uint32_t_
|
2.58% |
6900.270 |
7078.478 |
0.598 |
0.00% |
0.598 |
|
MultiSource/Benchmarks/FreeBench/mason/mason
Profile
|
2.55% |
0.539 |
0.553 |
0.000 |
4.11% |
0.000 |
|
SingleSource/Benchmarks/BenchmarkGame/puzzle
Profile
|
2.42% |
0.855 |
0.875 |
0.002 |
-0.41% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC63
|
2.39% |
104.503 |
107.002 |
0.001 |
15.54% |
0.001 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<31, GreaterThanZero, Last>
|
2.37% |
8158.924 |
8352.157 |
23.800 |
2.45% |
23.800 |
|
SingleSource/Benchmarks/Misc/fbench
Profile
|
2.36% |
5.628 |
5.760 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC64
|
2.35% |
105.755 |
108.243 |
0.007 |
17.67% |
0.007 |
|
External/SPEC/CFP2017rate/519.lbm_r/519.lbm_r
Profile
|
2.33% |
195.427 |
199.980 |
1.163 |
-1.19% |
1.163 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchVecWithRuntimeChecks4PointersDBeforeA/32
|
2.30% |
162436.963 |
166177.112 |
13.757 |
-0.00% |
13.757 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC63
|
2.28% |
127.206 |
130.105 |
0.025 |
0.12% |
0.025 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<64, GreaterThanZero, Mid>
|
2.22% |
2694.650 |
2754.550 |
22.854 |
0.48% |
22.854 |
|
SingleSource/Benchmarks/Misc/flops-1
Profile
|
2.19% |
8.807 |
9.000 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC128
|
2.13% |
117.017 |
119.509 |
0.003 |
0.00% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC128
|
2.13% |
117.016 |
119.508 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC127
|
2.13% |
117.640 |
120.143 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC127
|
2.10% |
117.656 |
120.131 |
0.009 |
-0.00% |
0.009 |
|
SingleSource/Benchmarks/Misc-C++/Large/ray
Profile
|
2.09% |
11.852 |
12.100 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<32, EqZero, Last>
|
2.06% |
6908.265 |
7050.806 |
0.936 |
1.48% |
0.936 |
|
MultiSource/Applications/obsequi/Obsequi
Profile
|
1.99% |
7.601 |
7.752 |
0.030 |
-0.76% |
0.030 |
|
MultiSource/Benchmarks/sim/sim
Profile
|
1.95% |
9.509 |
9.694 |
0.032 |
-1.60% |
0.032 |
|
External/SPEC/CINT2017rate/531.deepsjeng_r/531.deepsjeng_r
Profile
|
1.89% |
255.478 |
260.310 |
0.492 |
-5.45% |
0.492 |
|
MultiSource/Benchmarks/FreeBench/fourinarow/fourinarow
Profile
|
1.89% |
0.638 |
0.650 |
0.000 |
-0.02% |
0.000 |
|
SingleSource/Benchmarks/Misc/ReedSolomon
Profile
|
1.88% |
20.414 |
20.799 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopFrom_uint8_t_To_uint16_t_
|
1.87% |
2177.185 |
2217.906 |
8.814 |
-1.61% |
8.814 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint32_t_To_uint16_t_
|
1.82% |
9470.434 |
9642.594 |
52.520 |
-3.01% |
52.520 |
|
MultiSource/Benchmarks/VersaBench/ecbdes/ecbdes
Profile
|
1.62% |
5.058 |
5.139 |
0.000 |
-3.66% |
0.000 |
|
MultiSource/Benchmarks/ASC_Sequoia/CrystalMk/CrystalMk
Profile
|
1.58% |
15.328 |
15.571 |
0.000 |
-0.13% |
0.000 |
|
SingleSource/Benchmarks/Misc/mandel-2
Profile
|
1.55% |
2.496 |
2.535 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC128
|
1.54% |
208.279 |
211.494 |
0.013 |
-0.01% |
0.013 |
|
MultiSource/Benchmarks/mafft/pairlocalalign
Profile
|
1.53% |
92.440 |
93.854 |
0.347 |
0.07% |
0.347 |
|
MultiSource/Benchmarks/Fhourstones-3.1/fhourstones3.1
Profile
|
1.46% |
3.932 |
3.989 |
0.007 |
0.15% |
0.007 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_INT_PREDICT_RAW/171
|
1.46% |
6.826 |
6.925 |
0.011 |
0.01% |
0.011 |
|
SingleSource/Benchmarks/Adobe-C++/simple_types_loop_invariant
Profile
|
1.44% |
1.844 |
1.870 |
0.006 |
2.45% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC64
|
1.43% |
85.107 |
86.324 |
0.012 |
0.09% |
0.012 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC127
|
1.42% |
217.167 |
220.261 |
0.006 |
-0.00% |
0.006 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_INT_PREDICT_LAMBDA/171
|
1.41% |
6.829 |
6.925 |
0.016 |
-0.01% |
0.016 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_erff_autovec_float_
|
1.40% |
737.893 |
748.196 |
0.205 |
0.60% |
0.205 |
|
External/SPEC/CINT2017rate/525.x264_r/525.x264_r
Profile
|
1.37% |
128.264 |
130.025 |
0.087 |
-0.06% |
0.087 |
|
SingleSource/Benchmarks/Misc/oourafft
Profile
|
1.35% |
14.675 |
14.872 |
0.075 |
2.09% |
0.075 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint16_t_To_uint8_t_
|
1.29% |
4379.776 |
4436.142 |
0.756 |
-0.70% |
0.756 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC128
|
1.27% |
195.868 |
198.355 |
0.006 |
16.12% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC127
|
1.27% |
194.628 |
197.093 |
0.003 |
14.13% |
0.003 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<3, EqZero, Mid>
|
1.21% |
37169.178 |
37619.392 |
11.946 |
-0.05% |
11.946 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_EOS_RAW/171
|
1.21% |
0.861 |
0.871 |
0.001 |
-0.14% |
0.001 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<6, LessThanZero, Mid>
|
1.20% |
23554.318 |
23837.586 |
18.817 |
1.41% |
18.817 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, LessThanZero, Mid>
|
1.19% |
55897.657 |
56565.087 |
6.235 |
-1.83% |
6.235 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<16, LessThanZero, Last>
|
1.12% |
12996.635 |
13142.493 |
0.112 |
1.12% |
0.112 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_sinhf_novec_float_
|
1.08% |
2217.735 |
2241.655 |
0.462 |
-0.02% |
0.462 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<64, EqZero, None>
|
1.08% |
2921.758 |
2953.252 |
7.146 |
-0.18% |
7.146 |
|
SingleSource/Benchmarks/SmallPT/smallpt
Profile
|
1.02% |
29.712 |
30.017 |
0.003 |
0.01% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_sinh_novec_double_
|
1.02% |
2448.674 |
2473.609 |
1.652 |
0.02% |
1.652 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<8, LessThanZero, Mid>
|
1.00% |
19266.833 |
19460.439 |
30.866 |
1.17% |
30.866 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_sinhf_autovec_float_
|
1.00% |
2219.659 |
2241.921 |
0.526 |
-0.03% |
0.526 |