|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_HYDRO_2D_LAMBDA/44217
|
-54.23% |
90930.583 |
41616.385 |
11036.510 |
-18.39% |
11036.510 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint64_t_To_uint32_t_
|
-51.11% |
35313.629 |
17264.228 |
335.091 |
-0.34% |
335.091 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint64_t_To_uint16_t_
|
-50.30% |
35680.148 |
17734.428 |
448.060 |
-4.58% |
448.060 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C/miniGMG/miniGMG
Profile
|
-49.77% |
9.190 |
4.616 |
0.465 |
-0.30% |
0.465 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint64_t_To_uint8_t_
|
-48.73% |
37062.972 |
19003.005 |
75.412 |
0.13% |
75.412 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_HYDRO_2D_LAMBDA/5001
|
-48.52% |
9113.303 |
4691.776 |
1147.696 |
-20.81% |
1147.696 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint16_t_To_uint64_t_
|
-44.09% |
18675.093 |
10440.708 |
4.856 |
-0.01% |
4.856 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_DIFF_PREDICT_RAW/44217
|
-42.18% |
23299.816 |
13472.551 |
357.008 |
-0.27% |
357.008 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_DIFF_PREDICT_LAMBDA/44217
|
-41.66% |
23102.783 |
13477.232 |
352.575 |
-0.19% |
352.575 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_DIFF_PREDICT_RAW/5001
|
-41.17% |
2574.764 |
1514.769 |
62.019 |
0.75% |
62.019 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint8_t_To_uint64_t_
|
-41.10% |
17799.596 |
10483.606 |
35.600 |
-0.04% |
35.600 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_DISC_ORD_LAMBDA/44217
|
-40.99% |
14054.040 |
8293.966 |
1752.902 |
-17.66% |
1752.902 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_HYDRO_2D_RAW/44217
|
-40.64% |
84652.625 |
50245.883 |
4154.414 |
-13.24% |
4154.414 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint64_t_To_uint32_t_
|
-40.62% |
38155.754 |
22658.414 |
28.602 |
-0.21% |
28.602 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_DIFF_PREDICT_LAMBDA/5001
|
-39.84% |
2509.400 |
1509.570 |
45.297 |
0.02% |
45.297 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/32
|
-36.69% |
1396.116 |
883.842 |
0.061 |
0.00% |
0.061 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/64
|
-36.67% |
6182.288 |
3915.067 |
0.075 |
-0.00% |
0.075 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/16
|
-36.64% |
279.469 |
177.082 |
0.024 |
-0.01% |
0.024 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint32_t_To_uint64_t_
|
-36.35% |
22724.955 |
14463.942 |
257.978 |
-3.63% |
257.978 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/256
|
-36.25% |
107153.285 |
68311.946 |
58.852 |
-0.10% |
58.852 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/128
|
-36.12% |
26271.873 |
16782.716 |
2.314 |
-0.10% |
2.314 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_HYDRO_2D_RAW/5001
|
-35.77% |
8796.368 |
5650.119 |
363.778 |
-11.30% |
363.778 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint64_t_To_uint8_t_
|
-34.25% |
30110.831 |
19797.347 |
22.032 |
0.00% |
22.032 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint64_t_To_uint16_t_
|
-34.07% |
28949.218 |
19085.514 |
24.943 |
0.11% |
24.943 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, EqZero, None>
|
-31.24% |
20511.394 |
14103.749 |
0.626 |
-0.00% |
0.626 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIRST_DIFF_LAMBDA/44217
|
-29.09% |
144.820 |
102.699 |
0.320 |
-0.80% |
0.320 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint64_t_To_uint16_t_
|
-28.98% |
25897.435 |
18392.225 |
73.091 |
0.03% |
73.091 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIRST_DIFF_RAW/44217
|
-28.58% |
142.491 |
101.761 |
1.027 |
-0.43% |
1.027 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint32_t_To_uint8_t_
|
-27.83% |
13469.278 |
9720.885 |
21.582 |
0.06% |
21.582 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC128
|
-27.38% |
1292.822 |
938.867 |
3.229 |
0.29% |
3.229 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC64
|
-26.96% |
653.610 |
477.427 |
2.422 |
-0.16% |
2.422 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC128
|
-26.86% |
557.537 |
407.779 |
0.030 |
0.01% |
0.030 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC32
|
-26.70% |
333.930 |
244.770 |
1.136 |
-0.07% |
1.136 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC16
|
-26.11% |
173.787 |
128.413 |
0.500 |
0.05% |
0.500 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC64
|
-25.58% |
291.827 |
217.179 |
0.052 |
-0.00% |
0.052 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_DISC_ORD_RAW/44217
|
-24.94% |
13341.079 |
10013.585 |
651.278 |
-12.55% |
651.278 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint64_t_To_uint8_t_
|
-24.47% |
27222.887 |
20561.615 |
5.183 |
-0.04% |
5.183 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, EqZero, None>
|
-23.98% |
16023.286 |
12180.902 |
0.899 |
-0.01% |
0.899 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC128
|
-23.20% |
603.966 |
463.823 |
0.032 |
0.00% |
0.032 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC32
|
-23.18% |
158.873 |
122.042 |
0.040 |
0.02% |
0.040 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC128
|
-23.11% |
603.957 |
464.385 |
0.034 |
-0.00% |
0.034 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_PIC_2D_RAW/44217
|
-22.86% |
11216.281 |
8651.881 |
43.925 |
0.09% |
43.925 |
|
MicroBenchmarks/ImageProcessing/Blur/blur.test:BENCHMARK_boxBlurKernel/1024
|
-22.86% |
30148.993 |
23256.144 |
17.371 |
-0.11% |
17.371 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC64
|
-22.36% |
313.505 |
243.420 |
0.015 |
-0.00% |
0.015 |
|
SingleSource/Benchmarks/Adobe-C++/loop_unroll
Profile
|
-22.19% |
3.107 |
2.418 |
0.004 |
-0.03% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC127
|
-22.17% |
615.213 |
478.806 |
0.021 |
-0.00% |
0.021 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC64
|
-22.15% |
313.505 |
244.051 |
0.011 |
-0.00% |
0.011 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC127
|
-21.97% |
615.198 |
480.015 |
0.044 |
-0.01% |
0.044 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint16_t_To_uint32_t_
|
-21.64% |
7100.968 |
5564.060 |
4.845 |
-0.06% |
4.845 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint8_t_To_uint32_t_
|
-21.57% |
6582.228 |
5162.291 |
3.487 |
-0.01% |
3.487 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint16_t_To_uint64_t_
|
-21.57% |
13208.286 |
10359.299 |
3.446 |
-0.01% |
3.446 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_PIC_2D_LAMBDA/44217
|
-21.52% |
10963.150 |
8603.722 |
576.171 |
-0.10% |
576.171 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_only_autovec_uint8_t_
|
-21.37% |
182351.670 |
143375.213 |
91.975 |
-0.05% |
91.975 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIND_FIRST_MIN_LAMBDA/44217
|
-21.32% |
389.578 |
306.506 |
0.237 |
-0.02% |
0.237 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIND_FIRST_MIN_LAMBDA/171
|
-21.28% |
1.501 |
1.181 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIND_FIRST_MIN_LAMBDA/5001
|
-20.97% |
45.257 |
35.767 |
0.036 |
0.00% |
0.036 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC32
|
-20.82% |
168.326 |
133.278 |
0.008 |
-0.00% |
0.008 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC127
|
-20.59% |
275.455 |
218.733 |
0.413 |
0.07% |
0.413 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC128
|
-20.47% |
274.741 |
218.493 |
0.643 |
-0.36% |
0.643 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC32
|
-20.45% |
168.333 |
133.907 |
0.004 |
-0.00% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC63
|
-20.42% |
324.785 |
258.459 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_PIC_2D_LAMBDA/5001
|
-20.09% |
1105.490 |
883.412 |
38.378 |
-3.69% |
38.378 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC63
|
-20.05% |
324.799 |
259.685 |
0.027 |
-0.00% |
0.027 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint32_t_To_uint8_t_
|
-19.83% |
13900.786 |
11144.192 |
105.304 |
-0.62% |
105.304 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC64
|
-19.70% |
148.631 |
119.353 |
0.785 |
-0.88% |
0.785 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC127
|
-19.62% |
640.493 |
514.819 |
0.058 |
0.01% |
0.058 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC16
|
-19.30% |
92.280 |
74.469 |
0.008 |
0.00% |
0.008 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint16_t_To_uint8_t_
|
-19.09% |
3818.115 |
3089.209 |
0.086 |
-0.00% |
0.086 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_csa_with_cond_arith_autovec_uint8_t_
|
-18.89% |
210082.683 |
170390.765 |
18.260 |
-0.01% |
18.260 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIRST_SUM_LAMBDA/44217
|
-18.82% |
167.087 |
135.633 |
0.917 |
-0.08% |
0.917 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_VOL3D_CALC_LAMBDA/2
|
-18.80% |
8.757 |
7.111 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_VOL3D_CALC_RAW/2
|
-18.79% |
8.757 |
7.111 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIRST_SUM_RAW/44217
|
-18.73% |
166.336 |
135.188 |
1.107 |
-0.38% |
1.107 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_PIC_1D_RAW/44217
|
-18.65% |
13528.696 |
11005.737 |
34.699 |
-0.72% |
34.699 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint32_t_To_uint16_t_
|
-18.49% |
13807.248 |
11253.990 |
3.532 |
0.07% |
3.532 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC16
|
-18.30% |
95.740 |
78.221 |
0.000 |
0.00% |
0.000 |
|
MultiSource/Benchmarks/MiBench/automotive-bitcount/automotive-bitcount
Profile
|
-18.28% |
0.124 |
0.101 |
0.000 |
0.16% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint64_t_To_uint32_t_
|
-18.27% |
27051.416 |
22108.986 |
13.744 |
0.12% |
13.744 |
|
MultiSource/Benchmarks/Trimaran/enc-pc1/enc-pc1
Profile
|
-18.11% |
1.104 |
0.904 |
0.000 |
-0.01% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC63
|
-17.93% |
149.912 |
123.033 |
1.504 |
0.22% |
1.504 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_with_cond_arith_novec_uint8_t_
|
-17.87% |
745760.891 |
612521.013 |
341.461 |
-0.03% |
341.461 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC16
|
-17.65% |
95.739 |
78.843 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_with_cond_arith_novec_int32_t_
|
-17.47% |
740190.367 |
610886.236 |
366.871 |
-0.14% |
366.871 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC31
|
-17.41% |
179.585 |
148.313 |
0.004 |
-0.01% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC4
|
-17.32% |
17.520 |
14.485 |
0.010 |
-0.04% |
0.010 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC128
|
-17.24% |
570.579 |
472.230 |
0.025 |
-0.00% |
0.025 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC31
|
-17.16% |
86.114 |
71.335 |
2.059 |
-2.22% |
2.059 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC64
|
-17.08% |
297.710 |
246.869 |
0.018 |
-0.00% |
0.018 |
|
MultiSource/Benchmarks/MiBench/security-rijndael/security-rijndael
Profile
|
-16.91% |
0.335 |
0.278 |
0.000 |
0.07% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC32
|
-16.83% |
161.394 |
134.224 |
0.013 |
0.09% |
0.013 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC31
|
-16.72% |
179.581 |
149.559 |
0.004 |
-0.00% |
0.004 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_VOL3D_CALC_LAMBDA/0
|
-16.68% |
1267.594 |
1056.147 |
4.194 |
-0.64% |
4.194 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint8_t_To_uint64_t_
|
-16.53% |
13065.090 |
10904.831 |
23.494 |
-0.14% |
23.494 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC16
|
-16.36% |
93.125 |
77.892 |
0.025 |
-0.01% |
0.025 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC32
|
-16.25% |
85.325 |
71.459 |
0.775 |
-1.13% |
0.775 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_VOL3D_CALC_LAMBDA/1
|
-16.19% |
260.168 |
218.052 |
0.250 |
-0.11% |
0.250 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_VOL3D_CALC_RAW/1
|
-16.14% |
260.130 |
218.143 |
0.223 |
-0.00% |
0.223 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_VOL3D_CALC_RAW/0
|
-15.96% |
1265.194 |
1063.328 |
1.378 |
-0.03% |
1.378 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_HYDRO_1D_LAMBDA/171
|
-15.87% |
0.442 |
0.372 |
0.000 |
-0.01% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_HYDRO_1D_RAW/171
|
-15.83% |
0.442 |
0.372 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint16_t_To_uint32_t_
|
-15.70% |
7462.263 |
6290.848 |
1.983 |
-0.03% |
1.983 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_PIC_2D_RAW/5001
|
-15.62% |
1078.372 |
909.954 |
36.619 |
-2.32% |
36.619 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, EqZero, First>
|
-15.40% |
16670.947 |
14104.070 |
0.240 |
-0.00% |
0.240 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_no_runtime_checks_needed<16, int>
|
-15.39% |
24.403 |
20.648 |
0.000 |
-0.01% |
0.000 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, EqZero, Mid>
|
-15.38% |
16666.201 |
14103.436 |
0.715 |
-0.01% |
0.715 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC8
|
-15.35% |
58.764 |
49.745 |
0.002 |
0.00% |
0.002 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, EqZero, Last>
|
-15.35% |
16667.200 |
14109.470 |
0.432 |
-0.00% |
0.432 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC127
|
-14.81% |
605.768 |
516.046 |
0.015 |
0.00% |
0.015 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC8
|
-14.75% |
59.450 |
50.682 |
0.004 |
0.00% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint8_t_To_uint16_t_
|
-14.62% |
3756.543 |
3207.454 |
13.252 |
-0.21% |
13.252 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint32_t_To_uint8_t_
|
-14.57% |
10595.349 |
9051.140 |
37.914 |
-0.01% |
37.914 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC128
|
-14.56% |
1103.306 |
942.648 |
0.027 |
0.00% |
0.027 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC127
|
-14.51% |
1095.285 |
936.327 |
0.050 |
0.00% |
0.050 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC64
|
-14.31% |
562.307 |
481.827 |
0.025 |
-0.01% |
0.025 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC63
|
-14.27% |
554.742 |
475.586 |
0.021 |
-0.00% |
0.021 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint32_t_To_uint8_t_
|
-14.20% |
11129.319 |
9549.454 |
80.074 |
0.64% |
80.074 |
|
SingleSource/Benchmarks/Misc/salsa20
Profile
|
-14.12% |
15.384 |
13.211 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_csa_with_cond_arith_autovec_int32_t_
|
-13.96% |
396356.005 |
341018.311 |
428.221 |
0.04% |
428.221 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC8
|
-13.91% |
23.153 |
19.931 |
0.042 |
-0.09% |
0.042 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC8
|
-13.86% |
51.939 |
44.739 |
0.003 |
0.00% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC3
|
-13.86% |
51.935 |
44.737 |
0.004 |
-0.01% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_with_cond_arith_autovec_int64_t_
|
-13.86% |
791606.520 |
681901.312 |
154.779 |
0.05% |
154.779 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC1
|
-13.86% |
51.934 |
44.738 |
0.004 |
-0.00% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC7
|
-13.85% |
51.935 |
44.740 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC4
|
-13.85% |
51.934 |
44.740 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC2
|
-13.85% |
51.934 |
44.741 |
0.004 |
-0.00% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC32
|
-13.85% |
291.986 |
251.557 |
0.009 |
0.01% |
0.009 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint64_t_To_uint8_t_
|
-13.78% |
22047.281 |
19008.947 |
28.569 |
0.02% |
28.569 |
|
External/SPEC/CFP2017rate/508.namd_r/508.namd_r
Profile
|
-13.69% |
223.577 |
192.960 |
1.603 |
-0.03% |
1.603 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC8
|
-13.69% |
59.450 |
51.310 |
0.003 |
0.00% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC31
|
-13.65% |
284.084 |
245.301 |
0.018 |
0.01% |
0.018 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, EqZero, Last>
|
-13.64% |
14104.915 |
12181.632 |
0.428 |
-0.00% |
0.428 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, EqZero, First>
|
-13.63% |
14103.013 |
12181.474 |
0.967 |
-0.00% |
0.967 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, EqZero, Mid>
|
-13.62% |
14103.223 |
12182.115 |
0.965 |
-0.00% |
0.965 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_with_cond_arith_novec_int64_t_
|
-13.53% |
788035.947 |
681377.440 |
928.378 |
0.05% |
928.378 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC63
|
-13.41% |
374.427 |
324.204 |
0.207 |
-0.00% |
0.207 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint32_t_To_uint16_t_
|
-13.33% |
12837.101 |
11126.376 |
17.867 |
-0.19% |
17.867 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC8
|
-13.16% |
23.778 |
20.649 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC16
|
-13.10% |
156.964 |
136.409 |
0.004 |
-0.01% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC128
|
-13.07% |
81.345 |
70.709 |
0.005 |
0.00% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint8_t_To_uint16_t_
|
-12.96% |
4541.860 |
3953.336 |
0.571 |
-0.02% |
0.571 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC16
|
-12.95% |
51.941 |
45.217 |
0.320 |
-0.75% |
0.320 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC15
|
-12.87% |
107.003 |
93.234 |
0.004 |
-0.00% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC4
|
-12.78% |
113.088 |
98.640 |
1.764 |
1.53% |
1.764 |
|
SingleSource/Benchmarks/Shootout-C++/Shootout-C++-matrix
Profile
|
-12.72% |
2.508 |
2.189 |
0.000 |
-0.01% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC63
|
-12.67% |
332.823 |
290.671 |
0.017 |
-0.01% |
0.017 |
|
MicroBenchmarks/ImageProcessing/Dilate/Dilate.test:BENCHMARK_DILATE/1024
|
-12.60% |
7110.540 |
6214.458 |
228.645 |
-0.23% |
228.645 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC15
|
-12.54% |
148.810 |
130.149 |
0.005 |
-0.01% |
0.005 |
|
MicroBenchmarks/ImageProcessing/Dilate/Dilate.test:BENCHMARK_DILATE/128
|
-12.45% |
227.968 |
199.593 |
7.310 |
2.91% |
7.310 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint16_t_To_uint8_t_
|
-12.40% |
4742.772 |
4154.566 |
0.708 |
0.00% |
0.708 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_INT_PREDICT_RAW/44217
|
-12.03% |
9049.170 |
7960.583 |
117.586 |
-0.24% |
117.586 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC8
|
-11.81% |
89.401 |
78.842 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC2
|
-11.77% |
21.276 |
18.772 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC15
|
-11.70% |
107.009 |
94.488 |
0.003 |
-0.00% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC15
|
-11.46% |
51.939 |
45.989 |
0.002 |
-0.01% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC16
|
-11.36% |
33.164 |
29.397 |
0.005 |
-0.01% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC4
|
-11.12% |
22.527 |
20.022 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC4
|
-11.12% |
22.527 |
20.023 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC3
|
-11.12% |
22.526 |
20.022 |
0.000 |
-0.01% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_with_cond_arith_autovec_uint8_t_
|
-10.94% |
295250.544 |
262939.299 |
116.616 |
0.00% |
116.616 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC7
|
-10.73% |
81.312 |
72.584 |
0.003 |
-0.00% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC4
|
-10.61% |
41.302 |
36.919 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC4
|
-10.53% |
23.779 |
21.274 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC64
|
-10.48% |
53.816 |
48.179 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/16
|
-10.19% |
115.465 |
103.702 |
0.016 |
-0.02% |
0.016 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint8_t_To_uint16_t_
|
-10.17% |
5850.367 |
5255.384 |
6.086 |
-0.23% |
6.086 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC4
|
-10.06% |
55.663 |
50.063 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/64
|
-10.03% |
1913.314 |
1721.350 |
1.226 |
-0.06% |
1.226 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/32
|
-9.98% |
473.003 |
425.789 |
0.004 |
0.01% |
0.004 |
|
SingleSource/Benchmarks/Misc-C++/oopack_v1p8
Profile
|
-9.96% |
0.519 |
0.467 |
0.000 |
-0.01% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint32_t_To_uint16_t_
|
-9.89% |
10737.333 |
9675.096 |
168.250 |
-3.71% |
168.250 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/256
|
-9.89% |
31449.377 |
28340.173 |
15.721 |
-0.08% |
15.721 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_only_autovec_int64_t_
|
-9.80% |
333280.792 |
300635.469 |
561.627 |
-0.15% |
561.627 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC8
|
-9.76% |
25.657 |
23.152 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC8
|
-9.76% |
25.656 |
23.152 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/128
|
-9.75% |
7917.293 |
7145.049 |
1.310 |
-0.01% |
1.310 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC127
|
-9.71% |
101.879 |
91.985 |
0.003 |
-0.00% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC32
|
-9.68% |
53.193 |
48.043 |
0.063 |
-0.29% |
0.063 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC7
|
-9.61% |
32.539 |
29.411 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_with_cond_arith_autovec_int32_t_
|
-9.53% |
940875.108 |
851169.606 |
291.606 |
-0.01% |
291.606 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC7
|
-9.53% |
26.282 |
23.777 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC7
|
-9.53% |
26.282 |
23.778 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC31
|
-9.38% |
196.470 |
178.035 |
0.003 |
-0.00% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC8
|
-9.32% |
26.912 |
24.404 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_DEL_DOT_VEC_2D_LAMBDA/1
|
-9.24% |
287.120 |
260.596 |
0.098 |
-0.04% |
0.098 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_DEL_DOT_VEC_2D_RAW/1
|
-9.15% |
286.991 |
260.719 |
0.059 |
-0.00% |
0.059 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_DISC_ORD_LAMBDA/5001
|
-9.09% |
637.345 |
579.397 |
14.318 |
-10.66% |
14.318 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC4
|
-9.09% |
41.299 |
37.546 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC7
|
-8.90% |
28.160 |
25.655 |
0.001 |
-0.00% |
0.001 |
|
MultiSource/Benchmarks/FreeBench/pifft/pifft
Profile
|
-8.83% |
0.359 |
0.327 |
0.001 |
-0.47% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_HYDRO_1D_RAW/5001
|
-8.73% |
16.686 |
15.229 |
0.498 |
-0.76% |
0.498 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_DEL_DOT_VEC_2D_RAW/2
|
-8.71% |
3.510 |
3.204 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_DEL_DOT_VEC_2D_LAMBDA/2
|
-8.69% |
3.510 |
3.204 |
0.000 |
-0.01% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC16
|
-8.62% |
36.293 |
33.165 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint16_t_To_uint8_t_
|
-8.60% |
6815.821 |
6229.622 |
3.909 |
-0.51% |
3.909 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC8
|
-8.52% |
29.411 |
26.905 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_runtime_checks_pass<4, int>
|
-8.25% |
16.708 |
15.329 |
0.000 |
-0.01% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC2
|
-8.19% |
38.171 |
35.043 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint8_t_To_uint32_t_
|
-8.18% |
12778.752 |
11732.848 |
27.290 |
-0.20% |
27.290 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC64
|
-8.06% |
93.242 |
85.726 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint32_t_To_uint64_t_
|
-8.05% |
17196.059 |
15811.446 |
251.588 |
0.01% |
251.588 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC3
|
-7.90% |
47.558 |
43.803 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC16
|
-7.84% |
31.913 |
29.410 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC16
|
-7.84% |
31.911 |
29.410 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC32
|
-7.82% |
40.050 |
36.918 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC15
|
-7.69% |
32.538 |
30.035 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC15
|
-7.69% |
32.539 |
30.036 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_DEL_DOT_VEC_2D_RAW/0
|
-7.64% |
1800.857 |
1663.195 |
1.180 |
-0.16% |
1.180 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_HYDRO_2D_LAMBDA/171
|
-7.63% |
88.658 |
81.890 |
0.374 |
-0.91% |
0.374 |
|
MultiSource/Benchmarks/VersaBench/beamformer/beamformer
Profile
|
-7.63% |
5.201 |
4.804 |
0.001 |
0.01% |
0.001 |
|
MultiSource/Benchmarks/McCat/12-IOtest/iotest
Profile
|
-7.60% |
1.825 |
1.686 |
0.021 |
-1.20% |
0.021 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_DEL_DOT_VEC_2D_LAMBDA/0
|
-7.59% |
1791.999 |
1656.029 |
6.197 |
-0.20% |
6.197 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint16_t_To_uint64_t_
|
-7.55% |
20143.016 |
18623.022 |
66.973 |
0.17% |
66.973 |
|
MultiSource/Benchmarks/Trimaran/enc-md5/enc-md5
Profile
|
-7.48% |
3.506 |
3.243 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_xor_no_runtime_checks_needed<16, int>
|
-7.42% |
16.896 |
15.643 |
0.002 |
-0.01% |
0.002 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_PRESSURE_CALC_RAW/5001
|
-7.36% |
44.600 |
41.319 |
0.961 |
3.56% |
0.961 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_DIFF_PREDICT_LAMBDA/171
|
-7.30% |
11.986 |
11.110 |
0.064 |
0.00% |
0.064 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_HYDRO_2D_RAW/171
|
-7.25% |
88.626 |
82.198 |
0.269 |
-0.09% |
0.269 |
|
MultiSource/Applications/lambda-0.1.3/lambda
Profile
|
-7.24% |
15.870 |
14.721 |
0.003 |
-0.01% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC128
|
-7.22% |
173.330 |
160.812 |
0.012 |
-0.00% |
0.012 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint8_t>/127
|
-7.21% |
138.913 |
128.896 |
0.012 |
-0.01% |
0.012 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIND_FIRST_MIN_RAW/171
|
-7.19% |
1.497 |
1.389 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC7
|
-7.08% |
70.713 |
65.703 |
0.002 |
-0.00% |
0.002 |
|
SingleSource/Benchmarks/Misc/pi
Profile
|
-7.01% |
1.782 |
1.657 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC15
|
-6.94% |
45.051 |
41.923 |
0.016 |
-0.00% |
0.016 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_DIFF_PREDICT_RAW/171
|
-6.92% |
11.933 |
11.107 |
0.063 |
-0.02% |
0.063 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC15
|
-6.90% |
54.442 |
50.685 |
0.002 |
0.00% |
0.002 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIRST_DIFF_LAMBDA/171
|
-6.73% |
0.277 |
0.258 |
0.006 |
-3.30% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC31
|
-6.73% |
74.464 |
69.456 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint16_t_To_uint64_t_
|
-6.66% |
24986.152 |
23322.220 |
30.517 |
0.02% |
30.517 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC63
|
-6.56% |
114.514 |
106.999 |
0.160 |
-0.01% |
0.160 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_only_autovec_int32_t_
|
-6.52% |
181119.283 |
169307.845 |
193.854 |
-0.11% |
193.854 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_xor_runtime_checks_fail<16, int>
|
-6.52% |
28.783 |
26.907 |
0.003 |
-0.00% |
0.003 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_xor_runtime_checks_pass<16, int>
|
-6.51% |
28.783 |
26.909 |
0.001 |
0.01% |
0.001 |
|
SingleSource/Benchmarks/Misc/flops-6
Profile
|
-6.49% |
1.312 |
1.227 |
0.000 |
-0.01% |
0.000 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C++/miniFE/miniFE
Profile
|
-6.44% |
15.969 |
14.940 |
0.119 |
-0.13% |
0.119 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC63
|
-6.42% |
74.223 |
69.458 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC128
|
-6.37% |
68.804 |
64.420 |
0.014 |
-0.04% |
0.014 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC15
|
-6.35% |
39.422 |
36.919 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_BAND_LIN_EQ_LAMBDA/171
|
-6.33% |
0.366 |
0.343 |
0.000 |
-0.01% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_BAND_LIN_EQ_RAW/171
|
-6.33% |
0.366 |
0.343 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint16_t>/127
|
-6.31% |
138.912 |
130.145 |
0.006 |
-0.00% |
0.006 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIND_FIRST_MIN_RAW/5001
|
-6.31% |
45.339 |
42.478 |
0.047 |
0.12% |
0.047 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC127
|
-6.20% |
194.608 |
182.545 |
0.132 |
0.03% |
0.132 |
|
SingleSource/Benchmarks/Misc-C++/Large/sphereflake
Profile
|
-6.19% |
20.002 |
18.764 |
0.004 |
-0.03% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC16
|
-6.16% |
40.674 |
38.168 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC7
|
-6.13% |
354.707 |
332.975 |
3.232 |
3.11% |
3.232 |
|
MultiSource/Benchmarks/Rodinia/hotspot/hotspot
Profile
|
-6.07% |
2.036 |
1.912 |
0.009 |
-0.44% |
0.009 |
|
MultiSource/Benchmarks/MiBench/telecomm-gsm/telecomm-gsm
Profile
|
-6.03% |
0.663 |
0.623 |
0.000 |
-0.06% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint8_t>/65
|
-5.92% |
95.111 |
89.480 |
0.005 |
0.00% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint32_t>/127
|
-5.88% |
138.286 |
130.154 |
0.011 |
0.00% |
0.011 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint32_t_To_uint64_t_
|
-5.74% |
21450.888 |
20219.328 |
113.558 |
-0.29% |
113.558 |
|
External/SPEC/CFP2017rate/538.imagick_r/538.imagick_r
Profile
|
-5.73% |
292.080 |
275.334 |
0.324 |
0.06% |
0.324 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC127
|
-5.72% |
68.292 |
64.383 |
0.030 |
-0.05% |
0.030 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC16
|
-5.66% |
33.163 |
31.287 |
0.003 |
-0.00% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC32
|
-5.64% |
44.427 |
41.922 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC32
|
-5.63% |
44.429 |
41.927 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC31
|
-5.58% |
45.064 |
42.549 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint8_t_To_uint16_t_
|
-5.56% |
3633.347 |
3431.220 |
6.328 |
-0.30% |
6.328 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC31
|
-5.55% |
45.052 |
42.552 |
0.005 |
0.00% |
0.005 |
|
MultiSource/Benchmarks/SciMark2-C/scimark2
Profile
|
-5.50% |
107.639 |
101.724 |
0.010 |
0.01% |
0.010 |
|
MicroBenchmarks/harris/harris.test:BENCHMARK_HARRIS/2048/2048
|
-5.43% |
167029.260 |
157960.008 |
2829.548 |
-1.38% |
2829.548 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIND_FIRST_MIN_RAW/44217
|
-5.40% |
389.585 |
368.531 |
0.131 |
0.00% |
0.131 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint32_t>/999
|
-5.39% |
696.521 |
658.965 |
0.025 |
0.00% |
0.025 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC7
|
-5.32% |
70.719 |
66.956 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_PIC_2D_LAMBDA/171
|
-5.32% |
13.498 |
12.780 |
0.051 |
-0.00% |
0.051 |
|
SingleSource/Benchmarks/Polybench/stencils/jacobi-2d/jacobi-2d
Profile
|
-5.31% |
32.224 |
30.514 |
0.028 |
-0.13% |
0.028 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopWithReductionTC1
|
-5.26% |
11.888 |
11.263 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint32_t>/999
|
-5.23% |
1365.037 |
1293.671 |
0.055 |
0.00% |
0.055 |
|
SingleSource/Benchmarks/Stanford/Puzzle
Profile
|
-5.17% |
0.241 |
0.229 |
0.005 |
-0.01% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC127
|
-5.16% |
2426.612 |
2301.322 |
19.525 |
0.85% |
19.525 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC32
|
-5.15% |
61.321 |
58.164 |
0.015 |
-0.05% |
0.015 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC32
|
-5.13% |
24.405 |
23.152 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC31
|
-5.13% |
24.404 |
23.152 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC31
|
-5.13% |
24.403 |
23.152 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC32
|
-5.12% |
24.402 |
23.153 |
0.002 |
0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC15
|
-5.11% |
128.256 |
121.708 |
0.002 |
0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC31
|
-5.05% |
241.230 |
229.036 |
0.059 |
-0.01% |
0.059 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_PIC_2D_RAW/171
|
-5.00% |
13.539 |
12.862 |
0.042 |
0.04% |
0.042 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC1
|
-4.93% |
88.984 |
84.594 |
1.246 |
1.65% |
1.246 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint32_t>/256
|
-4.81% |
364.169 |
346.639 |
0.033 |
-0.01% |
0.033 |
|
MicroBenchmarks/ImageProcessing/Dilate/Dilate.test:BENCHMARK_DILATE/256
|
-4.79% |
1067.252 |
1016.181 |
1.754 |
0.07% |
1.754 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_PRESSURE_CALC_RAW/44217
|
-4.76% |
502.197 |
478.276 |
4.692 |
0.08% |
4.692 |
|
SingleSource/Benchmarks/Misc/revertBits
Profile
|
-4.68% |
0.641 |
0.611 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint16_t>/65
|
-4.61% |
95.115 |
90.728 |
0.010 |
-0.01% |
0.010 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_runtime_checks_fail<16, int>
|
-4.60% |
54.439 |
51.935 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_runtime_checks_pass<16, int>
|
-4.59% |
54.438 |
51.939 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopWithReductionTC2
|
-4.52% |
13.766 |
13.144 |
0.003 |
0.02% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC31
|
-4.47% |
70.083 |
66.950 |
0.004 |
-0.00% |
0.004 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_ENERGY_CALC_LAMBDA/171
|
-4.38% |
14.248 |
13.624 |
0.012 |
-0.01% |
0.012 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC15
|
-4.36% |
14.392 |
13.765 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC4
|
-4.36% |
14.393 |
13.766 |
0.000 |
-0.01% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC3
|
-4.36% |
14.393 |
13.766 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC8
|
-4.36% |
14.393 |
13.766 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC8
|
-4.36% |
14.392 |
13.766 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC7
|
-4.35% |
14.392 |
13.766 |
0.002 |
-0.01% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC3
|
-4.35% |
14.392 |
13.766 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC2
|
-4.35% |
14.392 |
13.766 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC16
|
-4.35% |
14.392 |
13.766 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC4
|
-4.35% |
14.392 |
13.766 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC15
|
-4.35% |
14.392 |
13.767 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC1
|
-4.34% |
14.392 |
13.766 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC1
|
-4.34% |
14.393 |
13.768 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC2
|
-4.34% |
14.391 |
13.766 |
0.000 |
-0.01% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC7
|
-4.34% |
14.391 |
13.766 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_ENERGY_CALC_RAW/171
|
-4.34% |
14.241 |
13.623 |
0.008 |
0.11% |
0.008 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopFrom_uint32_t_To_uint16_t_
|
-4.32% |
8192.284 |
7838.707 |
111.918 |
2.21% |
111.918 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint64_t>/999
|
-4.28% |
1811.241 |
1733.776 |
0.353 |
-0.02% |
0.353 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_INT_PREDICT_LAMBDA/44217
|
-4.24% |
8337.702 |
7984.098 |
92.625 |
-0.73% |
92.625 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint8_t_To_uint64_t_
|
-4.16% |
23483.830 |
22506.456 |
22.078 |
0.04% |
22.078 |
|
SingleSource/Benchmarks/Misc/flops-5
Profile
|
-4.15% |
2.021 |
1.937 |
0.001 |
0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint64_t>/999
|
-4.14% |
3594.644 |
3445.813 |
0.189 |
-0.01% |
0.189 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC16
|
-4.12% |
14.393 |
13.800 |
0.151 |
0.23% |
0.151 |
|
External/SPEC/CFP2017rate/519.lbm_r/519.lbm_r
Profile
|
-4.09% |
200.678 |
192.470 |
1.244 |
0.08% |
1.244 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint64_t>/256
|
-4.09% |
935.580 |
897.345 |
0.056 |
0.00% |
0.056 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC31
|
-4.04% |
61.945 |
59.445 |
0.003 |
-0.00% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC63
|
-4.03% |
43.294 |
41.550 |
0.068 |
-0.12% |
0.068 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC16
|
-4.01% |
31.289 |
30.035 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint32_t>/65
|
-3.98% |
94.488 |
90.731 |
0.004 |
-0.00% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC32
|
-3.96% |
63.198 |
60.694 |
0.003 |
-0.00% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_only_autovec_uint8_t_
|
-3.96% |
96157.793 |
92351.086 |
10.528 |
0.00% |
10.528 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint32_t>/256
|
-3.96% |
221.503 |
212.741 |
0.009 |
-0.01% |
0.009 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC15
|
-3.89% |
44.431 |
42.704 |
0.450 |
-0.43% |
0.450 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint16_t_To_uint8_t_
|
-3.87% |
2878.208 |
2766.963 |
4.896 |
-0.79% |
4.896 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC3
|
-3.85% |
16.269 |
15.643 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<31, EqZero, First>
|
-3.69% |
3346.347 |
3223.026 |
0.080 |
0.00% |
0.080 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint32_t_To_uint16_t_
|
-3.68% |
9879.809 |
9515.950 |
15.132 |
0.24% |
15.132 |
|
SingleSource/Benchmarks/Shootout/Shootout-matrix
Profile
|
-3.68% |
3.863 |
3.721 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC64
|
-3.68% |
43.175 |
41.587 |
0.058 |
-0.22% |
0.058 |
|
External/SPEC/CFP2017rate/544.nab_r/544.nab_r
Profile
|
-3.65% |
477.880 |
460.421 |
0.141 |
-0.01% |
0.141 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint64_t>/256
|
-3.65% |
514.395 |
495.605 |
0.005 |
-0.00% |
0.005 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_runtime_checks_fail<4, int>
|
-3.64% |
15.908 |
15.330 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC64
|
-3.61% |
69.461 |
66.952 |
0.006 |
-0.00% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC64
|
-3.61% |
69.457 |
66.952 |
0.003 |
-0.00% |
0.003 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_ENERGY_CALC_LAMBDA/5001
|
-3.59% |
438.042 |
422.295 |
1.098 |
-0.55% |
1.098 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC63
|
-3.58% |
70.092 |
67.580 |
0.002 |
0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint64_t_To_uint32_t_
|
-3.57% |
19292.425 |
18602.878 |
46.223 |
0.23% |
46.223 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC63
|
-3.57% |
70.083 |
67.581 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_nested_cond_load_novec_int32_t_
|
-3.55% |
645149.252 |
622239.377 |
326.742 |
0.02% |
326.742 |
|
MultiSource/Benchmarks/nbench/nbench
Profile
|
-3.51% |
6.127 |
5.912 |
0.001 |
-0.02% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC31
|
-3.46% |
60.276 |
58.193 |
0.004 |
-0.00% |
0.004 |
|
MicroBenchmarks/ImageProcessing/Dilate/Dilate.test:BENCHMARK_DILATE/512
|
-3.39% |
3584.064 |
3462.481 |
33.471 |
0.67% |
33.471 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<32, EqZero, Last>
|
-3.38% |
7052.998 |
6814.958 |
69.309 |
-0.02% |
69.309 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_BAND_LIN_EQ_LAMBDA/5001
|
-3.33% |
20.799 |
20.106 |
0.058 |
0.02% |
0.058 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_cond_load_novec_uint8_t_
|
-3.33% |
314092.103 |
303645.399 |
1797.387 |
0.23% |
1797.387 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint16_t_To_uint8_t_
|
-3.29% |
4517.211 |
4368.802 |
4.619 |
-0.44% |
4.619 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC31
|
-3.28% |
93.853 |
90.778 |
0.011 |
0.00% |
0.011 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint16_t>/999
|
-3.17% |
515.023 |
498.693 |
0.071 |
-0.00% |
0.071 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1BigLoopWithReductionTC1
|
-3.13% |
20.025 |
19.398 |
0.001 |
-0.00% |
0.001 |
|
SingleSource/Benchmarks/Shootout/Shootout-lists
Profile
|
-3.12% |
11.312 |
10.959 |
0.005 |
-0.07% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchVecWithRuntimeChecks4PointersDBeforeA/1000
|
-3.09% |
5019862.993 |
4864986.382 |
460.402 |
-0.01% |
460.402 |
|
MultiSource/Benchmarks/TSVC/Recurrences-dbl/Recurrences-dbl
Profile
|
-3.05% |
10.357 |
10.041 |
0.035 |
-0.36% |
0.035 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_ADI_LAMBDA/5001
|
-3.04% |
2234.931 |
2166.988 |
15.874 |
-0.80% |
15.874 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint64_t_To_uint8_t_
|
-3.01% |
19841.137 |
19244.676 |
58.718 |
-0.23% |
58.718 |
|
SingleSource/Benchmarks/Misc/oourafft
Profile
|
-2.94% |
15.093 |
14.649 |
0.085 |
-0.05% |
0.085 |
|
MultiSource/Applications/JM/lencod/lencod
Profile
|
-2.93% |
32.540 |
31.586 |
0.024 |
0.00% |
0.024 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_FLOYD_DITHER/128
|
-2.91% |
439.467 |
426.693 |
1.662 |
-0.30% |
1.662 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint16_t>/999
|
-2.85% |
1013.869 |
985.009 |
0.006 |
-0.00% |
0.006 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, LessThanZero, None>
|
-2.82% |
37576.235 |
36514.910 |
8.135 |
-0.00% |
8.135 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC64
|
-2.82% |
111.383 |
108.242 |
0.014 |
-0.01% |
0.014 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C/CoMD/CoMD
Profile
|
-2.80% |
9.899 |
9.621 |
0.007 |
-0.11% |
0.007 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC32
|
-2.80% |
31.286 |
30.410 |
0.032 |
0.23% |
0.032 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC1
|
-2.78% |
22.526 |
21.900 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC1
|
-2.78% |
22.525 |
21.900 |
0.004 |
-0.00% |
0.004 |
|
MultiSource/Benchmarks/FreeBench/mason/mason
Profile
|
-2.71% |
0.553 |
0.538 |
0.000 |
0.01% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_PRESSURE_CALC_LAMBDA/44217
|
-2.67% |
498.539 |
485.218 |
1.589 |
0.12% |
1.589 |
|
MultiSource/Benchmarks/sim/sim
Profile
|
-2.65% |
9.701 |
9.443 |
0.026 |
-0.21% |
0.026 |
|
MultiSource/Benchmarks/FreeBench/pcompress2/pcompress2
Profile
|
-2.61% |
0.404 |
0.394 |
0.001 |
0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC63
|
-2.61% |
120.145 |
117.012 |
0.005 |
-0.00% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint8_t_To_uint32_t_
|
-2.57% |
7077.318 |
6895.355 |
1.532 |
-0.04% |
1.532 |
|
MultiSource/Benchmarks/FreeBench/fourinarow/fourinarow
Profile
|
-2.49% |
0.651 |
0.634 |
0.001 |
0.02% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC32
|
-2.48% |
50.052 |
48.810 |
0.258 |
-0.00% |
0.258 |
|
MultiSource/Benchmarks/mafft/pairlocalalign
Profile
|
-2.47% |
94.062 |
91.736 |
0.314 |
0.00% |
0.314 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchVecWithRuntimeChecks4PointersDBeforeA/32
|
-2.45% |
166201.466 |
162134.613 |
3.084 |
0.00% |
3.084 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_only_autovec_int64_t_
|
-2.43% |
1446971.267 |
1411871.711 |
1601.495 |
-0.13% |
1601.495 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<31, GreaterThanZero, Last>
|
-2.36% |
8295.600 |
8099.522 |
13.960 |
0.01% |
13.960 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC31
|
-2.35% |
31.189 |
30.456 |
0.045 |
0.15% |
0.045 |
|
MultiSource/Benchmarks/Olden/health/health
Profile
|
-2.34% |
1.591 |
1.554 |
0.005 |
-0.12% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC63
|
-2.34% |
107.004 |
104.500 |
0.002 |
-0.01% |
0.002 |
|
SingleSource/Benchmarks/Misc/fbench
Profile
|
-2.32% |
5.761 |
5.627 |
0.000 |
-0.01% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC64
|
-2.31% |
108.247 |
105.749 |
0.017 |
-0.00% |
0.017 |
|
MultiSource/Benchmarks/TSVC/GlobalDataFlow-flt/GlobalDataFlow-flt
Profile
|
-2.30% |
6.658 |
6.505 |
0.058 |
-0.05% |
0.058 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<64, GreaterThanZero, Mid>
|
-2.26% |
2745.767 |
2683.804 |
15.772 |
-0.22% |
15.772 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint32_t>/51
|
-2.17% |
83.849 |
82.032 |
0.272 |
-0.78% |
0.272 |
|
SingleSource/Benchmarks/Misc/flops-1
Profile
|
-2.15% |
9.000 |
8.806 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC128
|
-2.10% |
119.525 |
117.011 |
0.005 |
-0.00% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC128
|
-2.10% |
119.520 |
117.011 |
0.008 |
-0.00% |
0.008 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC127
|
-2.09% |
120.146 |
117.637 |
0.003 |
-0.00% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC127
|
-2.08% |
120.138 |
117.635 |
0.008 |
-0.00% |
0.008 |
|
SingleSource/Benchmarks/Misc-C++/Large/ray
Profile
|
-2.07% |
12.101 |
11.850 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_ENERGY_CALC_RAW/5001
|
-2.01% |
428.738 |
420.101 |
1.866 |
-0.17% |
1.866 |
|
MultiSource/Benchmarks/Rodinia/pathfinder/pathfinder
Profile
|
-2.00% |
1.258 |
1.233 |
0.003 |
-0.31% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint16_t_To_uint32_t_
|
-1.99% |
11342.699 |
11117.058 |
27.292 |
0.03% |
27.292 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<16, EqZero, None>
|
-1.98% |
8177.641 |
8016.094 |
12.776 |
-0.08% |
12.776 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<64, EqZero, Mid>
|
-1.89% |
2744.265 |
2692.394 |
12.088 |
0.23% |
12.088 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C/SimpleMOC/SimpleMOC
Profile
|
-1.89% |
10.405 |
10.209 |
0.048 |
0.05% |
0.048 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint32_t>/10
|
-1.86% |
61.947 |
60.793 |
0.013 |
0.02% |
0.013 |
|
SingleSource/Benchmarks/Misc/ReedSolomon
Profile
|
-1.86% |
20.797 |
20.410 |
0.002 |
-0.01% |
0.002 |
|
MultiSource/Benchmarks/Bullet/bullet
Profile
|
-1.86% |
30.431 |
29.866 |
0.146 |
-0.12% |
0.146 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint16_t>/256
|
-1.84% |
272.838 |
267.816 |
0.007 |
0.00% |
0.007 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_FLOYD_DITHER/512
|
-1.84% |
6645.158 |
6522.880 |
24.644 |
0.15% |
24.644 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_EOS_RAW/171
|
-1.79% |
0.871 |
0.855 |
0.001 |
-0.21% |
0.001 |
|
SingleSource/Benchmarks/BenchmarkGame/puzzle
Profile
|
-1.75% |
0.869 |
0.854 |
0.001 |
0.06% |
0.001 |
|
External/SPEC/CINT2017rate/531.deepsjeng_r/531.deepsjeng_r
Profile
|
-1.75% |
260.112 |
255.561 |
0.046 |
-0.05% |
0.046 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint32_t_To_uint64_t_
|
-1.72% |
26280.748 |
25828.429 |
25.300 |
-0.01% |
25.300 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_EOS_LAMBDA/171
|
-1.70% |
0.871 |
0.856 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint64_t>/51
|
-1.70% |
148.307 |
145.791 |
0.009 |
0.00% |
0.009 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<3, GreaterThanZero, None>
|
-1.69% |
45142.879 |
44380.246 |
269.039 |
0.00% |
269.039 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_only_novec_int32_t_
|
-1.66% |
450922.862 |
443416.533 |
127.688 |
0.08% |
127.688 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_nested_cond_load_novec_uint8_t_
|
-1.65% |
504714.718 |
496384.809 |
93.895 |
-0.01% |
93.895 |
|
MultiSource/Benchmarks/VersaBench/ecbdes/ecbdes
Profile
|
-1.63% |
5.139 |
5.056 |
0.002 |
-0.03% |
0.002 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_INT_PREDICT_RAW/171
|
-1.61% |
6.925 |
6.813 |
0.007 |
-0.04% |
0.007 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_INT_PREDICT_LAMBDA/171
|
-1.61% |
6.925 |
6.813 |
0.009 |
-0.02% |
0.009 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<32, LessThanZero, Mid>
|
-1.61% |
4570.992 |
4497.542 |
18.002 |
-0.22% |
18.002 |
|
MultiSource/Benchmarks/ASC_Sequoia/CrystalMk/CrystalMk
Profile
|
-1.57% |
15.572 |
15.327 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_csa_with_in_loop_arith_novec_int64_t_
|
-1.56% |
1028155.144 |
1012100.239 |
698.476 |
0.04% |
698.476 |
|
SingleSource/Benchmarks/Misc/mandel-2
Profile
|
-1.54% |
2.535 |
2.496 |
0.000 |
0.00% |
0.000 |
|
MultiSource/Benchmarks/tramp3d-v4/tramp3d-v4
Profile
|
-1.52% |
1.076 |
1.059 |
0.001 |
0.05% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint8_t_To_uint32_t_
|
-1.52% |
12122.484 |
11938.233 |
14.673 |
-0.07% |
14.673 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC128
|
-1.49% |
211.515 |
208.373 |
0.013 |
0.00% |
0.013 |
|
External/SPEC/CINT2017rate/525.x264_r/525.x264_r
Profile
|
-1.44% |
129.445 |
127.578 |
0.126 |
-0.12% |
0.126 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC127
|
-1.42% |
220.275 |
217.153 |
0.025 |
-0.15% |
0.025 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint32_t>/28
|
-1.41% |
82.597 |
81.428 |
0.028 |
0.01% |
0.028 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC63
|
-1.37% |
130.166 |
128.383 |
0.109 |
-0.08% |
0.109 |
|
MultiSource/Benchmarks/Fhourstones-3.1/fhourstones3.1
Profile
|
-1.36% |
3.972 |
3.917 |
0.010 |
-0.08% |
0.010 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, LessThanZero, Mid>
|
-1.36% |
56527.388 |
55756.229 |
37.197 |
-0.00% |
37.197 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint64_t>/51
|
-1.36% |
229.009 |
225.891 |
0.028 |
-0.00% |
0.028 |
|
External/SPEC/CINT2017rate/541.leela_r/541.leela_r
Profile
|
-1.34% |
229.386 |
226.307 |
0.401 |
0.18% |
0.401 |
|
MultiSource/Benchmarks/TSVC/Searching-dbl/Searching-dbl
Profile
|
-1.32% |
7.666 |
7.565 |
0.033 |
-0.06% |
0.033 |
|
SingleSource/Benchmarks/Adobe-C++/simple_types_loop_invariant
Profile
|
-1.30% |
1.863 |
1.838 |
0.001 |
0.24% |
0.001 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<32, GreaterThanZero, Mid>
|
-1.29% |
4555.446 |
4496.509 |
1.958 |
0.03% |
1.958 |
|
External/SPEC/CFP2017rate/511.povray_r/511.povray_r
Profile
|
-1.28% |
33.786 |
33.354 |
0.063 |
-0.39% |
0.063 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC127
|
-1.27% |
197.100 |
194.595 |
0.007 |
-0.00% |
0.007 |
|
MultiSource/Benchmarks/MallocBench/cfrac/cfrac
Profile
|
-1.27% |
2.780 |
2.745 |
0.000 |
-0.01% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC128
|
-1.27% |
198.368 |
195.857 |
0.007 |
0.01% |
0.007 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_csa_with_cond_arith_autovec_int64_t_
|
-1.25% |
744936.248 |
735640.689 |
211.247 |
-0.10% |
211.247 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_csa_with_cond_arith_novec_int64_t_
|
-1.25% |
744710.098 |
735430.993 |
1896.775 |
-0.04% |
1896.775 |
|
MicroBenchmarks/ImageProcessing/Blur/blur.test:BENCHMARK_boxBlurKernel/512
|
-1.24% |
6613.679 |
6531.805 |
24.352 |
-0.24% |
24.352 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<16, EqZero, Mid>
|
-1.23% |
8657.236 |
8550.899 |
30.820 |
-0.00% |
30.820 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_ENERGY_CALC_LAMBDA/44217
|
-1.19% |
4324.422 |
4272.993 |
4.767 |
-0.03% |
4.767 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<16, LessThanZero, Last>
|
-1.19% |
13142.214 |
12986.172 |
2.511 |
-0.02% |
2.511 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<3, EqZero, Mid>
|
-1.15% |
37598.714 |
37167.373 |
19.691 |
0.00% |
19.691 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_DISC_ORD_RAW/171
|
-1.13% |
18.543 |
18.334 |
0.031 |
-0.12% |
0.031 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_sinhf_autovec_float_
|
-1.13% |
2242.663 |
2217.333 |
0.530 |
0.02% |
0.530 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_sinh_novec_double_
|
-1.11% |
2473.865 |
2446.505 |
0.726 |
0.03% |
0.726 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<3, LessThanZero, Mid>
|
-1.09% |
37669.791 |
37259.289 |
111.688 |
-0.25% |
111.688 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_sinhf_novec_float_
|
-1.07% |
2241.857 |
2217.924 |
0.368 |
-0.01% |
0.368 |
|
SingleSource/Benchmarks/SmallPT/smallpt
Profile
|
-1.06% |
30.029 |
29.711 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint32_t>/51
|
-1.02% |
78.409 |
77.612 |
0.022 |
0.04% |
0.022 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<8, LessThanZero, Mid>
|
-1.02% |
19434.559 |
19237.257 |
12.303 |
0.02% |
12.303 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_ENERGY_CALC_RAW/44217
|
-1.01% |
4331.435 |
4287.613 |
10.191 |
0.02% |
10.191 |