|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_INT_PREDICT_RAW/44217
|
137.74% |
8191.577 |
19474.457 |
69.319 |
0.78% |
69.319 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_INT_PREDICT_LAMBDA/44217
|
133.08% |
8197.164 |
19105.783 |
210.317 |
-1.88% |
210.317 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint64_t_To_uint32_t_
|
96.51% |
17923.805 |
35221.531 |
108.208 |
-0.26% |
108.208 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint64_t_To_uint8_t_
|
95.69% |
18991.622 |
37165.070 |
151.069 |
0.28% |
151.069 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint64_t_To_uint16_t_
|
94.47% |
18377.901 |
35738.645 |
189.678 |
0.12% |
189.678 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C/miniGMG/miniGMG
Profile
|
84.54% |
4.815 |
8.886 |
0.564 |
-3.31% |
0.564 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint16_t_To_uint64_t_
|
78.40% |
10450.244 |
18643.140 |
60.639 |
-0.17% |
60.639 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIRST_DIFF_RAW/44217
|
71.14% |
104.155 |
178.252 |
6.016 |
-0.80% |
6.016 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_DIFF_PREDICT_RAW/44217
|
70.86% |
14146.672 |
24170.445 |
825.966 |
-0.96% |
825.966 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_DIFF_PREDICT_LAMBDA/44217
|
70.18% |
14164.595 |
24105.376 |
780.820 |
-0.96% |
780.820 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint8_t_To_uint64_t_
|
69.83% |
10541.248 |
17902.249 |
87.111 |
0.43% |
87.111 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint64_t_To_uint32_t_
|
68.62% |
22684.907 |
38251.955 |
159.332 |
0.25% |
159.332 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_DIFF_PREDICT_RAW/5001
|
63.41% |
1542.543 |
2520.628 |
146.160 |
-2.10% |
146.160 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIRST_DIFF_LAMBDA/44217
|
63.39% |
104.436 |
170.641 |
3.635 |
-0.32% |
3.635 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/32
|
57.94% |
884.072 |
1396.259 |
0.032 |
-0.00% |
0.032 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/16
|
57.79% |
177.137 |
279.504 |
0.024 |
0.00% |
0.024 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/64
|
56.96% |
3938.113 |
6181.318 |
2.195 |
-0.02% |
2.195 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/256
|
56.49% |
68456.650 |
107125.993 |
14.077 |
-0.03% |
14.077 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/128
|
56.36% |
16794.304 |
26259.523 |
4.980 |
-0.05% |
4.980 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_DIFF_PREDICT_LAMBDA/5001
|
55.47% |
1636.222 |
2543.760 |
122.661 |
-1.21% |
122.661 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint32_t_To_uint64_t_
|
53.50% |
14641.173 |
22474.612 |
223.392 |
-1.10% |
223.392 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint64_t_To_uint16_t_
|
51.70% |
19117.328 |
29000.901 |
63.253 |
-0.10% |
63.253 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint64_t_To_uint8_t_
|
51.55% |
19847.570 |
30079.196 |
38.581 |
-0.11% |
38.581 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_HYDRO_2D_LAMBDA/44217
|
45.86% |
59336.746 |
86550.650 |
3123.390 |
-4.82% |
3123.390 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, EqZero, None>
|
45.42% |
14105.306 |
20511.246 |
0.511 |
-0.00% |
0.511 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint64_t_To_uint16_t_
|
40.03% |
18498.886 |
25903.150 |
12.963 |
0.02% |
12.963 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint32_t_To_uint8_t_
|
38.20% |
9750.945 |
13475.562 |
32.308 |
-0.00% |
32.308 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC128
|
36.89% |
407.937 |
558.442 |
0.240 |
-0.03% |
0.240 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC128
|
36.20% |
948.607 |
1291.987 |
3.599 |
-0.06% |
3.599 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC64
|
35.83% |
481.137 |
653.540 |
2.001 |
-0.01% |
2.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC32
|
35.39% |
246.610 |
333.877 |
1.017 |
-0.02% |
1.017 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_PIC_2D_LAMBDA/44217
|
34.91% |
8805.858 |
11880.044 |
35.577 |
0.08% |
35.577 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC64
|
34.56% |
217.189 |
292.241 |
0.090 |
0.00% |
0.090 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC16
|
33.92% |
129.776 |
173.791 |
0.375 |
0.00% |
0.375 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_HYDRO_2D_LAMBDA/5001
|
33.50% |
6724.522 |
8977.164 |
486.772 |
-1.49% |
486.772 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIRST_SUM_LAMBDA/44217
|
33.06% |
136.590 |
181.741 |
2.382 |
0.46% |
2.382 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint64_t_To_uint8_t_
|
31.85% |
20616.242 |
27182.533 |
35.561 |
-0.15% |
35.561 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, EqZero, None>
|
31.54% |
12182.232 |
16024.209 |
0.152 |
0.01% |
0.152 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIRST_SUM_RAW/44217
|
30.33% |
137.700 |
179.460 |
4.452 |
-4.08% |
4.452 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC32
|
30.22% |
122.065 |
158.952 |
0.020 |
-0.03% |
0.020 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC128
|
30.21% |
463.820 |
603.947 |
0.023 |
-0.00% |
0.023 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC128
|
30.04% |
464.446 |
603.960 |
0.731 |
0.00% |
0.731 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC64
|
28.77% |
243.449 |
313.490 |
0.020 |
-0.00% |
0.020 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC127
|
28.48% |
478.843 |
615.200 |
0.084 |
-0.00% |
0.084 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC64
|
28.45% |
244.073 |
313.507 |
0.009 |
0.00% |
0.009 |
|
MicroBenchmarks/ImageProcessing/Blur/blur.test:BENCHMARK_boxBlurKernel/1024
|
28.37% |
23441.853 |
30091.302 |
12.503 |
-0.19% |
12.503 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC127
|
28.14% |
480.111 |
615.207 |
0.025 |
0.00% |
0.025 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint8_t_To_uint32_t_
|
27.40% |
5177.065 |
6595.438 |
13.818 |
0.15% |
13.818 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint16_t_To_uint64_t_
|
27.23% |
10366.306 |
13188.564 |
212.688 |
-0.15% |
212.688 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint16_t_To_uint32_t_
|
27.13% |
5584.847 |
7099.836 |
23.817 |
-0.02% |
23.817 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_only_autovec_uint8_t_
|
27.10% |
143516.695 |
182412.748 |
43.515 |
0.02% |
43.515 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIND_FIRST_MIN_LAMBDA/171
|
27.05% |
1.182 |
1.501 |
0.000 |
0.01% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIND_FIRST_MIN_LAMBDA/44217
|
26.77% |
307.226 |
389.471 |
0.254 |
-0.03% |
0.254 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC32
|
26.29% |
133.291 |
168.330 |
0.007 |
0.00% |
0.007 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC32
|
25.69% |
133.911 |
168.316 |
0.011 |
-0.01% |
0.011 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC63
|
25.66% |
258.461 |
324.775 |
0.026 |
-0.00% |
0.026 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC63
|
25.05% |
259.718 |
324.766 |
0.019 |
-0.01% |
0.019 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC127
|
24.79% |
220.486 |
275.149 |
2.947 |
-0.11% |
2.947 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC127
|
24.53% |
514.695 |
640.929 |
0.113 |
-0.04% |
0.113 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIND_FIRST_MIN_LAMBDA/5001
|
24.27% |
36.369 |
45.195 |
0.174 |
-0.14% |
0.174 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC128
|
24.24% |
221.025 |
274.610 |
2.884 |
-0.05% |
2.884 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC16
|
23.91% |
74.481 |
92.290 |
0.016 |
-0.01% |
0.016 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_PIC_2D_RAW/44217
|
23.77% |
9605.622 |
11888.674 |
39.140 |
-0.41% |
39.140 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint16_t_To_uint8_t_
|
23.58% |
3089.642 |
3818.169 |
0.819 |
0.00% |
0.819 |
|
SingleSource/Benchmarks/Adobe-C++/loop_unroll
Profile
|
23.22% |
2.425 |
2.988 |
0.001 |
-3.84% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_VOL3D_CALC_RAW/2
|
23.12% |
7.111 |
8.755 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_VOL3D_CALC_LAMBDA/2
|
23.12% |
7.112 |
8.756 |
0.000 |
-0.01% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint32_t_To_uint16_t_
|
22.73% |
11245.691 |
13802.315 |
6.803 |
-0.04% |
6.803 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint64_t_To_uint32_t_
|
22.61% |
22106.285 |
27104.443 |
18.831 |
0.06% |
18.831 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC16
|
22.39% |
78.225 |
95.740 |
0.002 |
-0.00% |
0.002 |
|
MultiSource/Benchmarks/MiBench/automotive-bitcount/automotive-bitcount
Profile
|
22.28% |
0.102 |
0.125 |
0.000 |
0.39% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint32_t_To_uint8_t_
|
22.28% |
11368.353 |
13901.450 |
23.447 |
0.00% |
23.447 |
|
MultiSource/Benchmarks/Trimaran/enc-pc1/enc-pc1
Profile
|
22.10% |
0.905 |
1.105 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_with_cond_arith_novec_uint8_t_
|
21.73% |
613192.606 |
746415.643 |
183.131 |
0.07% |
183.131 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC16
|
21.42% |
78.846 |
95.735 |
0.008 |
-0.00% |
0.008 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC31
|
21.09% |
148.305 |
179.584 |
0.010 |
-0.00% |
0.010 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint8_t_To_uint64_t_
|
20.95% |
10924.020 |
13212.106 |
161.704 |
1.13% |
161.704 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC4
|
20.93% |
14.488 |
17.520 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC128
|
20.85% |
472.294 |
570.768 |
0.007 |
-0.01% |
0.007 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_PIC_1D_LAMBDA/44217
|
20.81% |
11195.990 |
13526.018 |
76.384 |
0.24% |
76.384 |
|
MultiSource/Benchmarks/MiBench/security-rijndael/security-rijndael
Profile
|
20.72% |
0.278 |
0.336 |
0.001 |
-0.03% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC64
|
20.64% |
246.881 |
297.850 |
0.023 |
-0.01% |
0.023 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_with_cond_arith_novec_int32_t_
|
20.43% |
614755.940 |
740362.714 |
129.208 |
0.02% |
129.208 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_PIC_2D_RAW/5001
|
20.39% |
993.797 |
1196.433 |
23.916 |
0.69% |
23.916 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC32
|
20.21% |
134.295 |
161.439 |
0.016 |
-0.00% |
0.016 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC31
|
20.06% |
149.579 |
179.584 |
0.009 |
0.00% |
0.009 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC16
|
19.63% |
77.940 |
93.238 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC64
|
19.40% |
124.679 |
148.872 |
2.343 |
0.16% |
2.343 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_HYDRO_1D_RAW/171
|
19.32% |
0.372 |
0.444 |
0.001 |
0.09% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_VOL3D_CALC_LAMBDA/1
|
19.14% |
218.332 |
260.118 |
0.971 |
-0.02% |
0.971 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_VOL3D_CALC_LAMBDA/0
|
19.14% |
1064.420 |
1268.132 |
1.398 |
-0.01% |
1.398 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_PIC_2D_LAMBDA/5001
|
19.07% |
987.764 |
1176.098 |
39.666 |
-4.42% |
39.666 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_HYDRO_1D_LAMBDA/171
|
18.94% |
0.372 |
0.442 |
0.000 |
0.07% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_VOL3D_CALC_RAW/0
|
18.75% |
1065.352 |
1265.131 |
1.399 |
-0.01% |
1.399 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_VOL3D_CALC_RAW/1
|
18.71% |
218.837 |
259.787 |
0.250 |
-0.13% |
0.250 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint16_t_To_uint32_t_
|
18.56% |
6294.878 |
7463.023 |
0.507 |
0.00% |
0.507 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC8
|
18.23% |
49.749 |
58.820 |
0.004 |
0.00% |
0.004 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, EqZero, First>
|
18.18% |
14105.786 |
16669.909 |
0.766 |
-0.01% |
0.766 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_no_runtime_checks_needed<16, int>
|
18.16% |
20.651 |
24.401 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, EqZero, Mid>
|
18.14% |
14106.249 |
16665.549 |
5.749 |
-0.00% |
5.749 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, EqZero, Last>
|
18.11% |
14111.506 |
16667.535 |
0.996 |
0.00% |
0.996 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint32_t_To_uint8_t_
|
17.41% |
9075.912 |
10655.932 |
20.497 |
0.13% |
20.497 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC127
|
17.38% |
516.070 |
605.761 |
0.046 |
-0.00% |
0.046 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC8
|
17.28% |
50.688 |
59.445 |
0.004 |
-0.01% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC128
|
17.03% |
942.692 |
1103.257 |
0.097 |
-0.00% |
0.097 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC127
|
16.96% |
936.429 |
1095.289 |
0.111 |
0.00% |
0.111 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC64
|
16.75% |
481.867 |
562.564 |
0.008 |
-0.01% |
0.008 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC63
|
16.59% |
475.636 |
554.539 |
1.855 |
-0.04% |
1.855 |
|
SingleSource/Benchmarks/Misc/salsa20
Profile
|
16.46% |
13.212 |
15.386 |
0.001 |
0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC32
|
16.15% |
251.564 |
292.199 |
0.027 |
-0.01% |
0.027 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC2
|
16.08% |
44.743 |
51.939 |
0.002 |
0.01% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC1
|
16.08% |
44.743 |
51.939 |
0.006 |
-0.01% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC4
|
16.08% |
44.742 |
51.937 |
0.003 |
0.01% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC8
|
16.07% |
44.745 |
51.938 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC7
|
16.07% |
44.744 |
51.936 |
0.004 |
0.00% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC3
|
16.06% |
44.749 |
51.936 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint8_t_To_uint16_t_
|
16.04% |
3237.599 |
3756.836 |
0.278 |
0.01% |
0.278 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC8
|
15.85% |
51.312 |
59.443 |
0.004 |
-0.01% |
0.004 |
|
External/SPEC/CFP2017rate/508.namd_r/508.namd_r
Profile
|
15.83% |
193.837 |
224.519 |
0.671 |
0.15% |
0.671 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC31
|
15.80% |
245.343 |
284.101 |
0.112 |
0.00% |
0.112 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, EqZero, Mid>
|
15.76% |
12183.762 |
14104.424 |
0.213 |
0.01% |
0.213 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, EqZero, Last>
|
15.76% |
12183.172 |
14103.685 |
0.563 |
-0.01% |
0.563 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_with_cond_arith_autovec_int64_t_
|
15.76% |
683444.809 |
791179.196 |
2484.675 |
-0.05% |
2484.675 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, EqZero, First>
|
15.76% |
12183.553 |
14103.845 |
0.485 |
0.01% |
0.485 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC8
|
15.62% |
20.024 |
23.151 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_with_cond_arith_novec_int64_t_
|
15.50% |
683380.938 |
789311.178 |
2796.727 |
-0.09% |
2796.727 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC63
|
15.48% |
324.217 |
374.409 |
0.048 |
-0.00% |
0.048 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint32_t_To_uint16_t_
|
15.31% |
11131.170 |
12834.832 |
21.471 |
-0.02% |
21.471 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint64_t_To_uint8_t_
|
15.18% |
19066.636 |
21960.904 |
111.916 |
-0.39% |
111.916 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC8
|
15.14% |
20.651 |
23.777 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC16
|
15.13% |
136.416 |
157.058 |
0.007 |
0.00% |
0.007 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC128
|
15.03% |
70.714 |
81.344 |
0.003 |
-0.00% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint8_t_To_uint16_t_
|
14.84% |
3955.052 |
4541.823 |
0.451 |
-0.00% |
0.451 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC15
|
14.76% |
93.239 |
106.998 |
0.008 |
-0.00% |
0.008 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint32_t_To_uint8_t_
|
14.73% |
9564.784 |
10974.048 |
128.847 |
-1.40% |
128.847 |
|
SingleSource/Benchmarks/Shootout-C++/Shootout-C++-matrix
Profile
|
14.56% |
2.190 |
2.509 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC63
|
14.52% |
290.695 |
332.897 |
0.016 |
-0.00% |
0.016 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC15
|
14.43% |
130.153 |
148.936 |
0.006 |
0.00% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint16_t_To_uint8_t_
|
14.14% |
4155.554 |
4743.174 |
0.686 |
0.00% |
0.686 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC31
|
13.76% |
76.350 |
86.860 |
0.353 |
0.45% |
0.353 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC8
|
13.41% |
78.846 |
89.422 |
0.029 |
0.02% |
0.029 |
|
MicroBenchmarks/ImageProcessing/Dilate/Dilate.test:BENCHMARK_DILATE/1024
|
13.39% |
6738.219 |
7640.611 |
59.578 |
1.88% |
59.578 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC2
|
13.32% |
18.774 |
21.275 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC4
|
13.27% |
98.670 |
111.765 |
1.021 |
-1.17% |
1.021 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC63
|
13.26% |
132.640 |
150.225 |
2.932 |
0.21% |
2.932 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC15
|
13.24% |
94.489 |
107.003 |
0.005 |
-0.01% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC16
|
12.94% |
45.992 |
51.943 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC15
|
12.92% |
45.993 |
51.937 |
0.006 |
-0.00% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC16
|
12.82% |
29.395 |
33.165 |
0.002 |
0.00% |
0.002 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIRST_SUM_RAW/5001
|
12.61% |
18.067 |
20.345 |
0.093 |
0.28% |
0.093 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC32
|
12.59% |
76.342 |
85.952 |
0.781 |
0.50% |
0.781 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC4
|
12.50% |
20.025 |
22.528 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC4
|
12.49% |
20.026 |
22.526 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC3
|
12.48% |
20.026 |
22.525 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC7
|
12.07% |
72.589 |
81.347 |
0.008 |
-0.01% |
0.008 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC4
|
11.86% |
36.918 |
41.297 |
0.003 |
-0.01% |
0.003 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_BAND_LIN_EQ_LAMBDA/171
|
11.86% |
0.343 |
0.384 |
0.000 |
4.78% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_BAND_LIN_EQ_RAW/171
|
11.84% |
0.343 |
0.384 |
0.000 |
4.77% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC4
|
11.76% |
21.276 |
23.777 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint8_t>/51
|
11.71% |
110.907 |
123.890 |
0.097 |
33.93% |
0.097 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC64
|
11.69% |
48.182 |
53.815 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/16
|
11.30% |
103.740 |
115.465 |
0.004 |
0.00% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC4
|
11.24% |
50.062 |
55.690 |
0.003 |
-0.02% |
0.003 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/32
|
11.08% |
425.818 |
473.007 |
0.025 |
0.00% |
0.025 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIRST_SUM_LAMBDA/5001
|
11.03% |
18.294 |
20.311 |
0.117 |
-0.56% |
0.117 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC8
|
10.81% |
23.153 |
25.655 |
0.003 |
-0.00% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC8
|
10.80% |
23.154 |
25.655 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint8_t_To_uint16_t_
|
10.73% |
5285.807 |
5853.154 |
2.200 |
0.05% |
2.200 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/256
|
10.68% |
28413.888 |
31449.613 |
14.399 |
0.00% |
14.399 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/128
|
10.67% |
7157.059 |
7920.401 |
1.851 |
-0.03% |
1.851 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC7
|
10.61% |
29.418 |
32.540 |
0.003 |
0.00% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC7
|
10.51% |
23.780 |
26.281 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC7
|
10.50% |
23.783 |
26.280 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC127
|
10.46% |
91.989 |
101.607 |
0.292 |
-0.27% |
0.292 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC32
|
10.40% |
48.178 |
53.189 |
0.003 |
-0.01% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_only_autovec_int64_t_
|
10.39% |
301997.534 |
333364.358 |
246.791 |
0.03% |
246.791 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC31
|
10.35% |
178.051 |
196.484 |
0.018 |
-0.00% |
0.018 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_DIFF_PREDICT_LAMBDA/171
|
10.09% |
11.187 |
12.316 |
0.029 |
-0.41% |
0.029 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_DEL_DOT_VEC_2D_LAMBDA/1
|
10.08% |
260.823 |
287.107 |
0.112 |
-0.00% |
0.112 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_DEL_DOT_VEC_2D_RAW/1
|
10.04% |
260.860 |
287.045 |
0.188 |
-0.01% |
0.188 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC8
|
10.00% |
24.407 |
26.848 |
0.133 |
-0.24% |
0.133 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC4
|
9.99% |
37.550 |
41.300 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC7
|
9.74% |
25.658 |
28.157 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_DIFF_PREDICT_RAW/171
|
9.69% |
11.211 |
12.297 |
0.038 |
-0.18% |
0.038 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/64
|
9.56% |
1746.351 |
1913.276 |
2.375 |
-0.00% |
2.375 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_DEL_DOT_VEC_2D_RAW/2
|
9.52% |
3.205 |
3.510 |
0.000 |
-0.01% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_DEL_DOT_VEC_2D_LAMBDA/2
|
9.51% |
3.205 |
3.510 |
0.000 |
0.01% |
0.000 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_runtime_checks_pass<4, int>
|
9.49% |
15.334 |
16.789 |
0.015 |
0.07% |
0.015 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC16
|
9.40% |
33.172 |
36.292 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC8
|
9.29% |
26.909 |
29.409 |
0.001 |
-0.01% |
0.001 |
|
MultiSource/Benchmarks/FreeBench/pifft/pifft
Profile
|
9.20% |
0.328 |
0.358 |
0.000 |
-0.05% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC2
|
8.92% |
35.043 |
38.171 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC64
|
8.77% |
85.726 |
93.243 |
0.003 |
0.00% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint16_t_To_uint8_t_
|
8.65% |
6267.813 |
6810.136 |
4.359 |
-0.08% |
4.359 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint8_t_To_uint32_t_
|
8.59% |
11772.601 |
12783.283 |
2.495 |
0.01% |
2.495 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC3
|
8.57% |
43.804 |
47.557 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC16
|
8.51% |
29.409 |
31.913 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC16
|
8.49% |
29.414 |
31.912 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC32
|
8.48% |
36.918 |
40.048 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint32_t_To_uint64_t_
|
8.38% |
15767.715 |
17089.218 |
511.077 |
-0.62% |
511.077 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC15
|
8.32% |
30.038 |
32.538 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC15
|
8.31% |
30.040 |
32.537 |
0.002 |
-0.01% |
0.002 |
|
MultiSource/Benchmarks/VersaBench/beamformer/beamformer
Profile
|
8.21% |
4.806 |
5.201 |
0.002 |
0.01% |
0.002 |
|
MultiSource/Benchmarks/Trimaran/enc-md5/enc-md5
Profile
|
8.14% |
3.244 |
3.507 |
0.000 |
0.02% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_DEL_DOT_VEC_2D_LAMBDA/0
|
8.00% |
1666.766 |
1800.060 |
2.473 |
0.10% |
2.473 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_xor_no_runtime_checks_needed<16, int>
|
7.98% |
15.647 |
16.895 |
0.002 |
-0.01% |
0.002 |
|
MultiSource/Benchmarks/TSVC/LoopRestructuring-dbl/LoopRestructuring-dbl
Profile
|
7.80% |
53.287 |
57.443 |
1.121 |
0.38% |
1.121 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC128
|
7.78% |
160.818 |
173.326 |
0.007 |
-0.00% |
0.007 |
|
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
|
7.76% |
128.910 |
138.911 |
0.008 |
-0.00% |
0.008 |
|
MultiSource/Applications/lambda-0.1.3/lambda
Profile
|
7.73% |
14.732 |
15.871 |
0.037 |
0.01% |
0.037 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC7
|
7.62% |
65.704 |
70.710 |
0.002 |
-0.00% |
0.002 |
|
SingleSource/Benchmarks/Misc/pi
Profile
|
7.52% |
1.658 |
1.782 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint16_t_To_uint64_t_
|
7.51% |
18812.759 |
20225.844 |
46.719 |
-0.28% |
46.719 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC15
|
7.40% |
41.948 |
45.051 |
0.003 |
-0.00% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC15
|
7.39% |
50.692 |
54.438 |
0.003 |
-0.01% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint16_t_To_uint64_t_
|
7.26% |
23357.088 |
25053.868 |
18.637 |
0.06% |
18.637 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC31
|
7.20% |
69.460 |
74.458 |
0.005 |
-0.01% |
0.005 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_HYDRO_2D_RAW/44217
|
7.09% |
87910.192 |
94140.428 |
2336.891 |
-0.64% |
2336.891 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_HYDRO_2D_RAW/171
|
7.07% |
83.034 |
88.905 |
0.296 |
0.31% |
0.296 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_DEL_DOT_VEC_2D_RAW/0
|
7.01% |
1680.448 |
1798.239 |
3.624 |
-0.15% |
3.624 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_xor_runtime_checks_pass<16, int>
|
6.96% |
26.909 |
28.783 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint8_t>/28
|
6.96% |
77.223 |
82.595 |
0.055 |
22.20% |
0.055 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_xor_runtime_checks_fail<16, int>
|
6.94% |
26.913 |
28.782 |
0.003 |
-0.00% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC63
|
6.83% |
107.185 |
114.506 |
0.006 |
-0.01% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC127
|
6.80% |
64.446 |
68.828 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC128
|
6.78% |
64.459 |
68.832 |
0.003 |
-0.01% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC63
|
6.77% |
69.461 |
74.163 |
0.216 |
-0.08% |
0.216 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC15
|
6.76% |
36.922 |
39.418 |
0.004 |
-0.01% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint16_t>/127
|
6.72% |
130.170 |
138.912 |
0.007 |
-0.00% |
0.007 |
|
SingleSource/Benchmarks/Misc/flops-6
Profile
|
6.62% |
1.230 |
1.311 |
0.001 |
-0.11% |
0.001 |
|
SingleSource/Benchmarks/Misc-C++/Large/sphereflake
Profile
|
6.60% |
18.774 |
20.014 |
0.002 |
0.01% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC16
|
6.56% |
38.172 |
40.676 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_only_autovec_int32_t_
|
6.53% |
169800.590 |
180891.179 |
683.265 |
-0.13% |
683.265 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_HYDRO_2D_LAMBDA/171
|
6.47% |
83.235 |
88.619 |
0.224 |
-0.04% |
0.224 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC127
|
6.41% |
182.895 |
194.619 |
0.002 |
0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint8_t>/65
|
6.29% |
89.487 |
95.111 |
0.002 |
0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint32_t>/127
|
6.23% |
130.169 |
138.276 |
0.006 |
-0.01% |
0.006 |
|
MultiSource/Benchmarks/MiBench/telecomm-gsm/telecomm-gsm
Profile
|
6.18% |
0.624 |
0.663 |
0.000 |
-0.07% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC16
|
5.99% |
30.075 |
31.878 |
0.015 |
-0.09% |
0.015 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC16
|
5.99% |
31.290 |
33.164 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC32
|
5.96% |
41.927 |
44.428 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC32
|
5.96% |
41.927 |
44.427 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIND_FIRST_MIN_RAW/5001
|
5.93% |
42.760 |
45.294 |
0.194 |
-0.10% |
0.194 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC31
|
5.90% |
42.552 |
45.062 |
0.003 |
-0.00% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC31
|
5.88% |
42.550 |
45.051 |
0.002 |
-0.00% |
0.002 |
|
MultiSource/Benchmarks/SciMark2-C/scimark2
Profile
|
5.84% |
101.772 |
107.716 |
0.010 |
0.02% |
0.010 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint32_t>/999
|
5.70% |
659.022 |
696.571 |
0.018 |
-0.01% |
0.018 |
|
External/SPEC/CFP2017rate/538.imagick_r/538.imagick_r
Profile
|
5.69% |
275.330 |
291.006 |
0.865 |
-0.37% |
0.865 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC7
|
5.61% |
66.955 |
70.710 |
0.002 |
-0.01% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopWithReductionTC1
|
5.55% |
11.264 |
11.889 |
0.002 |
0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint32_t>/999
|
5.50% |
1293.809 |
1364.928 |
0.196 |
-0.01% |
0.196 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC31
|
5.40% |
23.153 |
24.404 |
0.002 |
0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC32
|
5.40% |
23.155 |
24.405 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC32
|
5.39% |
23.155 |
24.403 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC15
|
5.39% |
121.713 |
128.269 |
0.006 |
-0.01% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC31
|
5.38% |
23.157 |
24.402 |
0.003 |
-0.00% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC32
|
5.37% |
58.196 |
61.323 |
0.003 |
0.00% |
0.003 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIND_FIRST_MIN_RAW/44217
|
5.36% |
369.501 |
389.296 |
0.158 |
-0.07% |
0.158 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint8_t_To_uint16_t_
|
5.30% |
3446.410 |
3629.066 |
6.666 |
-0.12% |
6.666 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC31
|
5.28% |
229.057 |
241.159 |
0.048 |
-0.03% |
0.048 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC7
|
5.24% |
332.678 |
350.118 |
4.150 |
-1.29% |
4.150 |
|
MultiSource/Benchmarks/Rodinia/hotspot/hotspot
Profile
|
5.18% |
1.935 |
2.035 |
0.002 |
-0.02% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint32_t>/256
|
5.05% |
346.684 |
364.197 |
0.026 |
-0.00% |
0.026 |
|
MultiSource/Benchmarks/McCat/12-IOtest/iotest
Profile
|
5.03% |
1.766 |
1.855 |
0.016 |
0.71% |
0.016 |
|
SingleSource/Benchmarks/Polybench/stencils/jacobi-2d/jacobi-2d
Profile
|
4.90% |
30.707 |
32.212 |
0.077 |
-0.04% |
0.077 |
|
SingleSource/Benchmarks/Misc/revertBits
Profile
|
4.88% |
0.611 |
0.641 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_runtime_checks_pass<16, int>
|
4.81% |
51.941 |
54.440 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint16_t>/65
|
4.80% |
90.754 |
95.111 |
0.004 |
-0.00% |
0.004 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_runtime_checks_fail<16, int>
|
4.80% |
51.942 |
54.435 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC127
|
4.75% |
2279.261 |
2387.637 |
16.326 |
-1.61% |
16.326 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_runtime_checks_fail<4, int>
|
4.75% |
15.335 |
16.064 |
0.238 |
0.42% |
0.238 |
|
SingleSource/Benchmarks/Misc/oourafft
Profile
|
4.68% |
14.642 |
15.328 |
0.107 |
0.55% |
0.107 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C++/miniFE/miniFE
Profile
|
4.67% |
15.112 |
15.818 |
0.067 |
-0.94% |
0.067 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC31
|
4.66% |
66.962 |
70.081 |
0.004 |
-0.00% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint32_t_To_uint64_t_
|
4.61% |
20387.000 |
21327.188 |
91.577 |
-0.58% |
91.577 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC8
|
4.54% |
13.766 |
14.392 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC4
|
4.54% |
13.767 |
14.392 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC7
|
4.54% |
13.766 |
14.391 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC2
|
4.54% |
13.767 |
14.392 |
0.000 |
0.01% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC3
|
4.54% |
13.767 |
14.392 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC4
|
4.54% |
13.767 |
14.392 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC15
|
4.53% |
13.768 |
14.392 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC16
|
4.53% |
13.767 |
14.391 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC1
|
4.53% |
13.767 |
14.392 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC2
|
4.53% |
13.767 |
14.391 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopWithReductionTC2
|
4.53% |
13.169 |
13.766 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC3
|
4.53% |
13.768 |
14.391 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC1
|
4.53% |
13.769 |
14.393 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC8
|
4.53% |
13.767 |
14.391 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC15
|
4.53% |
13.768 |
14.392 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC7
|
4.52% |
13.769 |
14.391 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_nested_cond_load_novec_int32_t_
|
4.44% |
622843.720 |
650485.851 |
604.393 |
0.70% |
604.393 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint64_t>/999
|
4.43% |
1734.337 |
1811.156 |
0.231 |
-0.00% |
0.231 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint64_t>/999
|
4.33% |
3445.976 |
3595.224 |
0.222 |
0.01% |
0.222 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_PIC_2D_LAMBDA/171
|
4.29% |
12.900 |
13.453 |
0.083 |
-0.33% |
0.083 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint64_t>/256
|
4.26% |
897.399 |
935.590 |
0.044 |
0.00% |
0.044 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_PIC_2D_RAW/171
|
4.23% |
12.971 |
13.520 |
0.094 |
-0.15% |
0.094 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint8_t_To_uint64_t_
|
4.21% |
22524.556 |
23471.939 |
32.783 |
-0.05% |
32.783 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_ENERGY_CALC_LAMBDA/171
|
4.20% |
13.631 |
14.203 |
0.010 |
-0.31% |
0.010 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC31
|
4.19% |
59.454 |
61.947 |
0.002 |
0.00% |
0.002 |
|
SingleSource/Benchmarks/Misc/flops-5
Profile
|
4.17% |
1.939 |
2.020 |
0.001 |
-0.05% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_ENERGY_CALC_RAW/171
|
4.15% |
13.637 |
14.203 |
0.029 |
-0.27% |
0.029 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_only_autovec_uint8_t_
|
4.14% |
92345.434 |
96168.923 |
8.856 |
0.01% |
8.856 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC32
|
4.11% |
60.702 |
63.199 |
0.002 |
0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint32_t>/65
|
4.11% |
90.755 |
94.486 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint32_t>/256
|
4.09% |
212.803 |
221.506 |
0.009 |
0.00% |
0.009 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_PRESSURE_CALC_LAMBDA/44217
|
4.01% |
484.022 |
503.440 |
2.234 |
-0.15% |
2.234 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC3
|
4.00% |
15.644 |
16.270 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<31, EqZero, First>
|
3.82% |
3223.089 |
3346.183 |
0.053 |
-0.00% |
0.053 |
|
SingleSource/Benchmarks/Shootout/Shootout-matrix
Profile
|
3.82% |
3.722 |
3.864 |
0.000 |
0.02% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint64_t>/256
|
3.77% |
495.698 |
514.380 |
0.024 |
-0.00% |
0.024 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC31
|
3.75% |
58.200 |
60.380 |
0.071 |
0.02% |
0.071 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC64
|
3.73% |
66.961 |
69.456 |
0.002 |
-0.01% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC63
|
3.70% |
67.586 |
70.088 |
0.006 |
-0.01% |
0.006 |
|
SingleSource/Benchmarks/BenchmarkGame/n-body
Profile
|
3.70% |
2.634 |
2.731 |
0.000 |
26.21% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC64
|
3.69% |
66.983 |
69.458 |
0.004 |
0.00% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC63
|
3.69% |
67.587 |
70.079 |
0.004 |
-0.01% |
0.004 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_PRESSURE_CALC_RAW/44217
|
3.55% |
487.238 |
504.539 |
5.542 |
0.10% |
5.542 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC63
|
3.52% |
41.709 |
43.177 |
0.295 |
-0.27% |
0.295 |
|
MultiSource/Applications/JM/lencod/lencod
Profile
|
3.52% |
31.657 |
32.770 |
0.046 |
0.62% |
0.046 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC64
|
3.47% |
41.727 |
43.176 |
0.296 |
0.00% |
0.296 |
|
MultiSource/Benchmarks/nbench/nbench
Profile
|
3.47% |
5.910 |
6.115 |
0.002 |
-0.19% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopFrom_uint32_t_To_uint64_t_
|
3.46% |
13883.003 |
14363.396 |
126.440 |
2.75% |
126.440 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC7
|
3.34% |
27.587 |
28.509 |
0.353 |
-0.53% |
0.353 |
|
External/SPEC/CFP2017rate/544.nab_r/544.nab_r
Profile
|
3.34% |
460.800 |
476.181 |
0.134 |
-0.36% |
0.134 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint16_t>/999
|
3.25% |
498.775 |
514.993 |
0.020 |
-0.01% |
0.020 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint64_t_To_uint32_t_
|
3.25% |
18768.072 |
19377.814 |
76.344 |
-0.14% |
76.344 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1BigLoopWithReductionTC1
|
3.21% |
19.400 |
20.023 |
0.004 |
-0.01% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint32_t_To_uint16_t_
|
3.20% |
9544.762 |
9849.981 |
54.895 |
-0.30% |
54.895 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchVecWithRuntimeChecks4PointersDBeforeA/1000
|
3.16% |
4866396.104 |
5020347.403 |
42.691 |
-0.01% |
42.691 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC31
|
3.09% |
90.969 |
93.779 |
0.036 |
-0.08% |
0.036 |
|
SingleSource/Benchmarks/Shootout/Shootout-lists
Profile
|
3.04% |
10.982 |
11.316 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, LessThanZero, None>
|
3.02% |
36567.216 |
37670.557 |
22.576 |
0.02% |
22.576 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_BAND_LIN_EQ_RAW/5001
|
2.98% |
20.618 |
21.232 |
0.234 |
0.54% |
0.234 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint16_t>/999
|
2.92% |
985.097 |
1013.823 |
0.059 |
-0.00% |
0.059 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_BAND_LIN_EQ_LAMBDA/5001
|
2.92% |
20.581 |
21.181 |
0.132 |
0.52% |
0.132 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC1
|
2.89% |
85.612 |
88.090 |
0.846 |
-1.00% |
0.846 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC64
|
2.88% |
108.261 |
111.378 |
0.008 |
-0.00% |
0.008 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC1
|
2.84% |
21.903 |
22.526 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC1
|
2.83% |
21.905 |
22.526 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint16_t_To_uint8_t_
|
2.81% |
4390.942 |
4514.233 |
10.163 |
-0.07% |
10.163 |
|
MicroBenchmarks/ImageProcessing/Dilate/Dilate.test:BENCHMARK_DILATE/256
|
2.69% |
1032.106 |
1059.875 |
7.778 |
-0.69% |
7.778 |
|
MultiSource/Benchmarks/FreeBench/pcompress2/pcompress2
Profile
|
2.67% |
0.394 |
0.405 |
0.000 |
-0.02% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC32
|
2.66% |
30.475 |
31.286 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC63
|
2.66% |
117.033 |
120.145 |
0.012 |
0.00% |
0.012 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_PIC_1D_RAW/5001
|
2.64% |
350.208 |
359.444 |
1.180 |
1.12% |
1.180 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<31, GreaterThanZero, Last>
|
2.62% |
8135.186 |
8348.528 |
17.846 |
-0.19% |
17.846 |
|
MultiSource/Benchmarks/FreeBench/mason/mason
Profile
|
2.61% |
0.539 |
0.553 |
0.000 |
-0.05% |
0.000 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C/CoMD/CoMD
Profile
|
2.59% |
9.655 |
9.906 |
0.004 |
0.02% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint8_t>/10
|
2.55% |
47.593 |
48.807 |
0.002 |
5.16% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint8_t_To_uint32_t_
|
2.55% |
6901.843 |
7077.629 |
0.342 |
0.00% |
0.342 |
|
SingleSource/Benchmarks/Misc-C++/oopack_v1p8
Profile
|
2.51% |
0.468 |
0.480 |
0.000 |
-7.57% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchVecWithRuntimeChecks4PointersDBeforeA/32
|
2.50% |
162153.984 |
166202.823 |
4.504 |
0.00% |
4.504 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint16_t_To_uint8_t_
|
2.49% |
2804.529 |
2874.394 |
2.940 |
-0.13% |
2.940 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC31
|
2.39% |
30.495 |
31.225 |
0.024 |
0.00% |
0.024 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC63
|
2.39% |
104.507 |
107.002 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<32, EqZero, Last>
|
2.34% |
6868.469 |
7029.249 |
55.266 |
-0.34% |
55.266 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint64_t_To_uint8_t_
|
2.32% |
19298.462 |
19746.494 |
20.322 |
-0.48% |
20.322 |
|
MultiSource/Benchmarks/FreeBench/fourinarow/fourinarow
Profile
|
2.32% |
0.636 |
0.651 |
0.001 |
-0.00% |
0.001 |
|
External/SPEC/CFP2017rate/519.lbm_r/519.lbm_r
Profile
|
2.31% |
195.505 |
200.030 |
1.713 |
-0.32% |
1.713 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_only_autovec_int64_t_
|
2.28% |
1416532.638 |
1448879.652 |
572.031 |
-0.06% |
572.031 |
|
MultiSource/Benchmarks/Olden/health/health
Profile
|
2.24% |
1.560 |
1.595 |
0.003 |
0.10% |
0.003 |
|
SingleSource/Benchmarks/Misc/flops-1
Profile
|
2.21% |
8.807 |
9.002 |
0.000 |
0.01% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC127
|
2.18% |
85.012 |
86.868 |
0.640 |
0.23% |
0.640 |
|
SingleSource/Benchmarks/BenchmarkGame/puzzle
Profile
|
2.16% |
0.857 |
0.876 |
0.003 |
0.13% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC128
|
2.14% |
117.023 |
119.523 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC127
|
2.13% |
117.644 |
120.145 |
0.007 |
-0.00% |
0.007 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC128
|
2.12% |
117.027 |
119.509 |
0.007 |
-0.01% |
0.007 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC127
|
2.11% |
117.652 |
120.137 |
0.005 |
-0.00% |
0.005 |
|
SingleSource/Benchmarks/Misc-C++/Large/ray
Profile
|
2.11% |
11.854 |
12.104 |
0.001 |
0.02% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC16
|
2.11% |
14.095 |
14.392 |
0.000 |
-0.01% |
0.000 |
|
MultiSource/Benchmarks/Rodinia/pathfinder/pathfinder
Profile
|
2.09% |
1.237 |
1.263 |
0.009 |
0.42% |
0.009 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_FLOYD_DITHER/512
|
2.01% |
6517.147 |
6648.394 |
4.778 |
0.05% |
4.778 |
|
SingleSource/Benchmarks/Misc/ReedSolomon
Profile
|
1.97% |
20.418 |
20.819 |
0.000 |
0.09% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint16_t>/256
|
1.87% |
267.834 |
272.837 |
0.012 |
-0.00% |
0.012 |
|
MultiSource/Benchmarks/mafft/pairlocalalign
Profile
|
1.82% |
92.328 |
94.013 |
0.311 |
-0.05% |
0.311 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint32_t_To_uint64_t_
|
1.81% |
25903.163 |
26371.663 |
52.518 |
0.06% |
52.518 |
|
MultiSource/Benchmarks/TSVC/Packing-dbl/Packing-dbl
Profile
|
1.79% |
36.963 |
37.626 |
0.229 |
-0.10% |
0.229 |
|
MultiSource/Benchmarks/sim/sim
Profile
|
1.78% |
9.531 |
9.701 |
0.002 |
0.00% |
0.002 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_EOS_RAW/171
|
1.75% |
0.858 |
0.873 |
0.001 |
-0.02% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint64_t>/51
|
1.71% |
145.809 |
148.299 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_DISC_ORD_RAW/5001
|
1.65% |
635.325 |
645.782 |
2.059 |
-2.85% |
2.059 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_EOS_LAMBDA/171
|
1.63% |
0.857 |
0.871 |
0.001 |
0.07% |
0.001 |
|
MultiSource/Benchmarks/VersaBench/ecbdes/ecbdes
Profile
|
1.62% |
5.059 |
5.141 |
0.000 |
0.01% |
0.000 |
|
External/SPEC/CINT2017rate/531.deepsjeng_r/531.deepsjeng_r
Profile
|
1.57% |
256.083 |
260.106 |
0.198 |
-0.00% |
0.198 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC32
|
1.57% |
49.282 |
50.054 |
0.003 |
0.00% |
0.003 |
|
SingleSource/Benchmarks/Misc/mandel-2
Profile
|
1.56% |
2.497 |
2.536 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_nested_cond_load_novec_uint8_t_
|
1.55% |
496804.469 |
504512.505 |
281.629 |
-0.04% |
281.629 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint16_t_To_uint32_t_
|
1.49% |
11118.450 |
11284.401 |
49.967 |
-0.51% |
49.967 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC128
|
1.49% |
208.387 |
211.489 |
0.016 |
-0.01% |
0.016 |
|
MultiSource/Benchmarks/tramp3d-v4/tramp3d-v4
Profile
|
1.48% |
1.058 |
1.074 |
0.001 |
-0.19% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_INT_PREDICT_RAW/171
|
1.48% |
6.816 |
6.917 |
0.004 |
-0.11% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC15
|
1.43% |
43.807 |
44.434 |
0.161 |
0.01% |
0.161 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<6, LessThanZero, Mid>
|
1.42% |
23528.215 |
23861.210 |
9.178 |
-0.03% |
9.178 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_INT_PREDICT_LAMBDA/171
|
1.39% |
6.830 |
6.925 |
0.008 |
-0.00% |
0.008 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint64_t>/51
|
1.37% |
225.912 |
229.010 |
0.018 |
0.00% |
0.018 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC127
|
1.34% |
217.355 |
220.262 |
0.010 |
-0.01% |
0.010 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_csa_with_in_loop_arith_novec_int64_t_
|
1.34% |
1014461.167 |
1028012.557 |
876.328 |
-0.01% |
876.328 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<8, LessThanZero, Mid>
|
1.29% |
19240.672 |
19488.931 |
15.502 |
-0.04% |
15.502 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC127
|
1.28% |
194.625 |
197.110 |
0.019 |
0.00% |
0.019 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC128
|
1.28% |
195.865 |
198.364 |
0.003 |
-0.00% |
0.003 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_ENERGY_CALC_LAMBDA/44217
|
1.28% |
4286.179 |
4340.849 |
4.056 |
0.36% |
4.056 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_csa_with_cond_arith_autovec_int64_t_
|
1.27% |
735990.096 |
745337.025 |
2181.171 |
0.05% |
2181.171 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC63
|
1.23% |
128.565 |
130.145 |
0.007 |
-0.02% |
0.007 |
|
MultiSource/Benchmarks/MallocBench/cfrac/cfrac
Profile
|
1.22% |
2.746 |
2.780 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<3, EqZero, Mid>
|
1.22% |
37169.279 |
37622.041 |
168.416 |
-0.02% |
168.416 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<16, LessThanZero, Last>
|
1.14% |
12993.660 |
13141.491 |
0.377 |
-0.01% |
0.377 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<16, EqZero, None>
|
1.14% |
8090.324 |
8182.309 |
10.857 |
0.06% |
10.857 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<64, LessThanZero, Last>
|
1.13% |
4133.324 |
4180.019 |
7.936 |
0.22% |
7.936 |
|
SingleSource/Benchmarks/SmallPT/smallpt
Profile
|
1.10% |
29.714 |
30.041 |
0.001 |
0.02% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_sinhf_novec_float_
|
1.10% |
2218.179 |
2242.536 |
0.575 |
0.00% |
0.575 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<6, GreaterThanZero, None>
|
1.07% |
29405.637 |
29720.398 |
8.123 |
0.02% |
8.123 |
|
MultiSource/Benchmarks/Fhourstones-3.1/fhourstones3.1
Profile
|
1.06% |
3.930 |
3.972 |
0.012 |
0.00% |
0.012 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint8_t>/16
|
1.06% |
59.384 |
60.014 |
0.169 |
11.51% |
0.169 |
|
External/SPEC/CFP2017rate/511.povray_r/511.povray_r
Profile
|
1.04% |
33.640 |
33.990 |
0.063 |
0.54% |
0.063 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_sinhf_autovec_float_
|
1.04% |
2218.494 |
2241.545 |
0.912 |
-0.05% |
0.912 |
|
External/SPEC/CINT2017rate/525.x264_r/525.x264_r
Profile
|
1.01% |
128.622 |
129.916 |
0.088 |
0.24% |
0.088 |