|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_HYDRO_2D_LAMBDA/44217
|
-71.89% |
90930.583 |
25563.998 |
14122.785 |
2.80% |
14122.785 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_DISC_ORD_LAMBDA/44217
|
-54.12% |
14054.040 |
6447.318 |
2116.675 |
-0.41% |
2116.675 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint64_t_To_uint32_t_
|
-52.87% |
35313.629 |
16644.822 |
293.994 |
-2.32% |
293.994 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint64_t_To_uint16_t_
|
-52.73% |
35680.148 |
16866.068 |
237.426 |
-4.41% |
237.426 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C/miniGMG/miniGMG
Profile
|
-49.77% |
9.190 |
4.616 |
0.230 |
-3.27% |
0.230 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint64_t_To_uint8_t_
|
-49.55% |
37062.972 |
18699.969 |
12.637 |
0.07% |
12.637 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint16_t_To_uint64_t_
|
-43.96% |
18675.093 |
10466.111 |
3.871 |
0.03% |
3.871 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_DIFF_PREDICT_RAW/44217
|
-42.01% |
23299.816 |
13511.541 |
344.738 |
0.05% |
344.738 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_DIFF_PREDICT_LAMBDA/44217
|
-41.64% |
23102.783 |
13481.768 |
267.252 |
0.04% |
267.252 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_DIFF_PREDICT_RAW/5001
|
-40.79% |
2574.764 |
1524.482 |
19.657 |
0.58% |
19.657 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint8_t_To_uint64_t_
|
-40.78% |
17799.596 |
10540.629 |
4.877 |
-0.12% |
4.877 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint64_t_To_uint32_t_
|
-40.64% |
38155.754 |
22650.641 |
39.668 |
0.10% |
39.668 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_DIFF_PREDICT_LAMBDA/5001
|
-39.24% |
2509.400 |
1524.605 |
27.947 |
0.48% |
27.947 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/32
|
-36.69% |
1396.116 |
883.825 |
0.036 |
-0.00% |
0.036 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/64
|
-36.68% |
6182.288 |
3914.334 |
13.963 |
-0.01% |
13.963 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/16
|
-36.63% |
279.469 |
177.098 |
0.006 |
-0.00% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint32_t_To_uint64_t_
|
-36.55% |
22724.955 |
14418.934 |
98.465 |
0.74% |
98.465 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/256
|
-36.22% |
107153.285 |
68344.008 |
41.205 |
0.09% |
41.205 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/128
|
-36.18% |
26271.873 |
16766.682 |
19.890 |
-0.07% |
19.890 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_HYDRO_2D_LAMBDA/5001
|
-34.95% |
9113.303 |
5928.233 |
1147.792 |
60.95% |
1147.792 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint64_t_To_uint8_t_
|
-34.32% |
30110.831 |
19776.862 |
18.756 |
0.04% |
18.756 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint64_t_To_uint16_t_
|
-33.85% |
28949.218 |
19150.466 |
8.300 |
-0.16% |
8.300 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_HYDRO_2D_RAW/44217
|
-32.28% |
84652.625 |
57326.139 |
10454.309 |
-2.95% |
10454.309 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIRST_DIFF_LAMBDA/44217
|
-30.34% |
144.820 |
100.889 |
1.368 |
-0.30% |
1.368 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint64_t_To_uint16_t_
|
-28.41% |
25897.435 |
18539.085 |
28.259 |
-0.10% |
28.259 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIRST_DIFF_RAW/44217
|
-28.27% |
142.491 |
102.215 |
2.056 |
-0.48% |
2.056 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC128
|
-28.05% |
1292.822 |
930.161 |
13.558 |
-0.01% |
13.558 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint32_t_To_uint8_t_
|
-27.94% |
13469.278 |
9705.336 |
23.140 |
-0.37% |
23.140 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC64
|
-27.36% |
653.610 |
474.778 |
3.282 |
-0.06% |
3.282 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC32
|
-27.17% |
333.930 |
243.216 |
1.499 |
-0.03% |
1.499 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC128
|
-26.91% |
557.537 |
407.524 |
0.012 |
0.00% |
0.012 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC16
|
-26.65% |
173.787 |
127.476 |
0.720 |
0.04% |
0.720 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC64
|
-25.59% |
291.827 |
217.146 |
0.048 |
-0.01% |
0.048 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint64_t_To_uint8_t_
|
-25.19% |
27222.887 |
20364.762 |
59.962 |
-0.46% |
59.962 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC32
|
-23.19% |
158.873 |
122.029 |
0.008 |
-0.02% |
0.008 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC128
|
-23.11% |
603.957 |
464.383 |
0.023 |
-0.00% |
0.023 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC128
|
-23.11% |
603.966 |
464.410 |
2.073 |
0.00% |
2.073 |
|
SingleSource/Benchmarks/Adobe-C++/loop_unroll
Profile
|
-23.00% |
3.107 |
2.392 |
0.003 |
-0.15% |
0.003 |
|
MicroBenchmarks/ImageProcessing/Blur/blur.test:BENCHMARK_boxBlurKernel/1024
|
-22.96% |
30148.993 |
23226.949 |
76.038 |
-0.39% |
76.038 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_PIC_2D_RAW/44217
|
-22.89% |
11216.281 |
8649.306 |
92.510 |
-0.14% |
92.510 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC64
|
-22.16% |
313.505 |
244.047 |
0.005 |
-0.00% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC64
|
-22.15% |
313.505 |
244.051 |
0.013 |
-0.00% |
0.013 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC127
|
-21.97% |
615.213 |
480.035 |
0.010 |
-0.00% |
0.010 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC127
|
-21.97% |
615.198 |
480.029 |
0.012 |
0.00% |
0.012 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint8_t_To_uint32_t_
|
-21.52% |
6582.228 |
5166.046 |
6.165 |
-0.01% |
6.165 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint16_t_To_uint64_t_
|
-21.50% |
13208.286 |
10369.137 |
3.296 |
-0.00% |
3.296 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC4
|
-21.42% |
17.520 |
13.767 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint16_t_To_uint32_t_
|
-21.38% |
7100.968 |
5582.427 |
4.204 |
0.01% |
4.204 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_only_autovec_uint8_t_
|
-21.37% |
182351.670 |
143375.290 |
131.861 |
-0.01% |
131.861 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIND_FIRST_MIN_LAMBDA/44217
|
-21.30% |
389.578 |
306.606 |
0.618 |
0.06% |
0.618 |
|
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_PIC_2D_LAMBDA/44217
|
-21.26% |
10963.150 |
8632.422 |
581.807 |
0.17% |
581.807 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC128
|
-20.80% |
274.741 |
217.606 |
1.241 |
0.38% |
1.241 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIND_FIRST_MIN_LAMBDA/5001
|
-20.59% |
45.257 |
35.941 |
0.173 |
0.29% |
0.173 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC127
|
-20.49% |
275.455 |
219.027 |
1.002 |
-0.43% |
1.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC32
|
-20.45% |
168.333 |
133.906 |
0.005 |
-0.00% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC32
|
-20.44% |
168.326 |
133.912 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC63
|
-20.05% |
324.799 |
259.691 |
0.008 |
-0.00% |
0.008 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC63
|
-20.04% |
324.785 |
259.695 |
0.044 |
-0.00% |
0.044 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC127
|
-19.63% |
640.493 |
514.751 |
0.013 |
0.00% |
0.013 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC16
|
-19.27% |
92.280 |
74.496 |
0.029 |
-0.07% |
0.029 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC7
|
-19.22% |
28.661 |
23.151 |
0.077 |
-0.05% |
0.077 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_MAT_X_MAT_LAMBDA/44217
|
-19.13% |
7608798.889 |
6153579.479 |
509066.621 |
1.48% |
509066.621 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint16_t_To_uint8_t_
|
-19.10% |
3818.115 |
3089.014 |
0.214 |
-0.02% |
0.214 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIRST_SUM_LAMBDA/44217
|
-18.92% |
167.087 |
135.470 |
0.726 |
-0.06% |
0.726 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC8
|
-18.92% |
23.153 |
18.772 |
0.166 |
-0.00% |
0.166 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint32_t_To_uint8_t_
|
-18.92% |
13900.786 |
11271.286 |
26.735 |
-0.37% |
26.735 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_csa_with_cond_arith_autovec_uint8_t_
|
-18.92% |
210082.683 |
170345.210 |
16.999 |
0.00% |
16.999 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_VOL3D_CALC_RAW/2
|
-18.80% |
8.757 |
7.110 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_VOL3D_CALC_LAMBDA/2
|
-18.80% |
8.757 |
7.111 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, EqZero, None>
|
-18.74% |
20511.394 |
16667.188 |
0.155 |
-0.00% |
0.155 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint32_t_To_uint16_t_
|
-18.66% |
13807.248 |
11230.984 |
11.856 |
0.03% |
11.856 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC64
|
-18.61% |
148.631 |
120.967 |
1.043 |
-0.90% |
1.043 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC63
|
-18.50% |
149.912 |
122.185 |
4.702 |
-1.77% |
4.702 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint64_t_To_uint32_t_
|
-18.45% |
27051.416 |
22061.193 |
26.056 |
-0.12% |
26.056 |
|
MultiSource/Benchmarks/MiBench/automotive-bitcount/automotive-bitcount
Profile
|
-18.40% |
0.124 |
0.101 |
0.001 |
-0.07% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIRST_SUM_RAW/44217
|
-18.19% |
166.336 |
136.072 |
0.124 |
0.14% |
0.124 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, EqZero, Last>
|
-18.18% |
14104.915 |
11541.144 |
0.462 |
-0.00% |
0.462 |
|
MultiSource/Benchmarks/Trimaran/enc-pc1/enc-pc1
Profile
|
-18.10% |
1.104 |
0.904 |
0.000 |
0.01% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_with_cond_arith_novec_uint8_t_
|
-17.84% |
745760.891 |
612731.916 |
444.556 |
0.02% |
444.556 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC16
|
-17.65% |
95.739 |
78.840 |
0.003 |
-0.00% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC16
|
-17.65% |
95.740 |
78.843 |
0.006 |
0.00% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC128
|
-17.36% |
570.579 |
471.538 |
0.042 |
-0.01% |
0.042 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC64
|
-17.34% |
297.710 |
246.102 |
0.071 |
-0.05% |
0.071 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_with_cond_arith_novec_int32_t_
|
-17.31% |
740190.367 |
612054.003 |
810.876 |
-0.04% |
810.876 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_MAT_X_MAT_LAMBDA/5001
|
-17.25% |
832970.330 |
689305.954 |
54318.205 |
0.67% |
54318.205 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC32
|
-17.25% |
161.394 |
133.561 |
0.027 |
-0.01% |
0.027 |
|
MultiSource/Benchmarks/MiBench/security-rijndael/security-rijndael
Profile
|
-17.14% |
0.335 |
0.277 |
0.001 |
-0.12% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC16
|
-17.05% |
93.125 |
77.249 |
0.017 |
-0.02% |
0.017 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC31
|
-16.73% |
179.581 |
149.543 |
0.008 |
-0.01% |
0.008 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC31
|
-16.72% |
179.585 |
149.554 |
0.005 |
-0.00% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint8_t_To_uint64_t_
|
-16.45% |
13065.090 |
10915.889 |
3.005 |
-0.17% |
3.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC8
|
-16.41% |
58.764 |
49.118 |
0.002 |
-0.01% |
0.002 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_VOL3D_CALC_LAMBDA/0
|
-16.27% |
1267.594 |
1061.373 |
1.086 |
-0.12% |
1.086 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_VOL3D_CALC_RAW/1
|
-16.13% |
260.130 |
218.168 |
0.139 |
-0.01% |
0.139 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_VOL3D_CALC_LAMBDA/1
|
-16.12% |
260.168 |
218.219 |
0.078 |
-0.00% |
0.078 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_VOL3D_CALC_RAW/0
|
-16.00% |
1265.194 |
1062.787 |
0.683 |
0.17% |
0.683 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC32
|
-15.98% |
85.325 |
71.687 |
1.998 |
-2.74% |
1.998 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_HYDRO_1D_LAMBDA/171
|
-15.87% |
0.442 |
0.372 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_PIC_2D_RAW/5001
|
-15.86% |
1078.372 |
907.336 |
28.933 |
1.44% |
28.933 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_HYDRO_1D_RAW/171
|
-15.84% |
0.442 |
0.372 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC8
|
-15.79% |
23.778 |
20.023 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint16_t_To_uint32_t_
|
-15.60% |
7462.263 |
6298.073 |
0.846 |
0.01% |
0.846 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint64_t_To_uint8_t_
|
-15.52% |
22047.281 |
18625.320 |
31.766 |
-0.13% |
31.766 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_no_runtime_checks_needed<16, int>
|
-15.39% |
24.403 |
20.649 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint32_t_To_uint8_t_
|
-15.13% |
10595.349 |
8991.922 |
25.381 |
-0.62% |
25.381 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint32_t_To_uint16_t_
|
-15.12% |
9904.984 |
8406.872 |
328.990 |
-3.79% |
328.990 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC16
|
-15.09% |
33.164 |
28.159 |
0.582 |
-0.00% |
0.582 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC127
|
-14.92% |
605.768 |
515.407 |
0.006 |
0.00% |
0.006 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_PIC_2D_LAMBDA/5001
|
-14.78% |
1105.490 |
942.135 |
24.396 |
-0.62% |
24.396 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint32_t_To_uint8_t_
|
-14.77% |
11129.319 |
9485.341 |
89.275 |
-0.44% |
89.275 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC4
|
-14.70% |
113.088 |
96.461 |
1.790 |
0.02% |
1.790 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC128
|
-14.51% |
1103.306 |
943.164 |
0.027 |
0.00% |
0.027 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint32_t_To_uint16_t_
|
-14.40% |
12837.101 |
10988.403 |
15.308 |
0.02% |
15.308 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC127
|
-14.40% |
1095.285 |
937.575 |
0.020 |
-0.00% |
0.020 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC64
|
-14.20% |
562.307 |
482.450 |
0.015 |
-0.00% |
0.015 |
|
SingleSource/Benchmarks/Misc/salsa20
Profile
|
-14.13% |
15.384 |
13.211 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC15
|
-14.09% |
44.431 |
38.171 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC63
|
-14.04% |
554.742 |
476.832 |
0.012 |
-0.00% |
0.012 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint8_t_To_uint16_t_
|
-14.02% |
3756.543 |
3229.951 |
3.016 |
-0.07% |
3.016 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC3
|
-13.93% |
51.935 |
44.702 |
0.017 |
-0.08% |
0.017 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC8
|
-13.86% |
51.939 |
44.738 |
0.008 |
-0.00% |
0.008 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC4
|
-13.85% |
51.934 |
44.739 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC1
|
-13.85% |
51.934 |
44.739 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC2
|
-13.85% |
51.934 |
44.739 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC7
|
-13.85% |
51.935 |
44.741 |
0.003 |
0.00% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC31
|
-13.76% |
86.114 |
74.265 |
1.044 |
-1.32% |
1.044 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_with_cond_arith_autovec_int64_t_
|
-13.74% |
791606.520 |
682806.912 |
294.179 |
0.11% |
294.179 |
|
External/SPEC/CFP2017rate/508.namd_r/508.namd_r
Profile
|
-13.70% |
223.577 |
192.944 |
0.698 |
0.07% |
0.698 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC8
|
-13.69% |
59.450 |
51.310 |
0.003 |
-0.00% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC8
|
-13.69% |
59.450 |
51.312 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC32
|
-13.64% |
291.986 |
252.172 |
0.007 |
-0.00% |
0.007 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_csa_with_cond_arith_autovec_int32_t_
|
-13.54% |
396356.005 |
342684.984 |
287.807 |
-0.06% |
287.807 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_with_cond_arith_novec_int64_t_
|
-13.41% |
788035.947 |
682386.299 |
732.163 |
-0.03% |
732.163 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC63
|
-13.38% |
374.427 |
324.344 |
0.057 |
0.01% |
0.057 |
|
MultiSource/Benchmarks/TSVC/CrossingThresholds-flt/CrossingThresholds-flt
Profile
|
-13.29% |
10.762 |
9.331 |
0.123 |
2.29% |
0.123 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC31
|
-13.21% |
284.084 |
246.548 |
0.004 |
-0.00% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC128
|
-13.08% |
81.345 |
70.704 |
0.003 |
-0.01% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint8_t_To_uint16_t_
|
-12.94% |
4541.860 |
3954.141 |
0.246 |
-0.01% |
0.246 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC63
|
-12.85% |
332.823 |
290.050 |
0.004 |
-0.01% |
0.004 |
|
SingleSource/Benchmarks/Shootout-C++/Shootout-C++-matrix
Profile
|
-12.72% |
2.508 |
2.189 |
0.000 |
-0.01% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC16
|
-12.70% |
156.964 |
137.036 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint16_t_To_uint8_t_
|
-12.39% |
4742.772 |
4155.037 |
0.177 |
0.00% |
0.177 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC16
|
-12.28% |
51.941 |
45.562 |
0.193 |
-0.62% |
0.193 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, EqZero, None>
|
-11.99% |
16023.286 |
14102.380 |
0.829 |
-0.00% |
0.829 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_INT_PREDICT_RAW/44217
|
-11.92% |
9049.170 |
7970.541 |
104.052 |
-0.29% |
104.052 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC2
|
-11.77% |
21.276 |
18.772 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC15
|
-11.70% |
107.009 |
94.486 |
0.003 |
0.00% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC15
|
-11.70% |
148.810 |
131.399 |
0.009 |
-0.01% |
0.009 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC15
|
-11.70% |
107.003 |
94.486 |
0.007 |
-0.00% |
0.007 |
|
MicroBenchmarks/ImageProcessing/Dilate/Dilate.test:BENCHMARK_DILATE/1024
|
-11.53% |
7110.540 |
6290.977 |
249.412 |
2.28% |
249.412 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC15
|
-11.45% |
51.939 |
45.990 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC4
|
-11.12% |
22.527 |
20.023 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC4
|
-11.12% |
22.527 |
20.023 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC3
|
-11.11% |
22.526 |
20.024 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_with_cond_arith_autovec_uint8_t_
|
-10.95% |
295250.544 |
262915.790 |
239.396 |
0.00% |
239.396 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint64_t_To_uint16_t_
|
-10.85% |
18983.917 |
16924.838 |
211.494 |
-0.57% |
211.494 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC32
|
-10.58% |
53.193 |
47.565 |
0.358 |
0.47% |
0.358 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC4
|
-10.53% |
23.779 |
21.274 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC64
|
-10.47% |
53.816 |
48.182 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC8
|
-10.41% |
89.401 |
80.092 |
0.004 |
0.00% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC16
|
-10.35% |
36.293 |
32.537 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint8_t_To_uint16_t_
|
-10.18% |
5850.367 |
5254.517 |
12.325 |
-0.67% |
12.325 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/16
|
-10.16% |
115.465 |
103.728 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/64
|
-10.08% |
1913.314 |
1720.403 |
13.009 |
-0.09% |
13.009 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_ADI_LAMBDA/5001
|
-10.01% |
2234.931 |
2011.169 |
74.150 |
-8.55% |
74.150 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/32
|
-10.00% |
473.003 |
425.714 |
0.027 |
-0.00% |
0.027 |
|
SingleSource/Benchmarks/Misc-C++/oopack_v1p8
Profile
|
-9.96% |
0.519 |
0.467 |
0.001 |
-0.03% |
0.001 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/256
|
-9.95% |
31449.377 |
28318.875 |
17.014 |
-0.06% |
17.014 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/128
|
-9.90% |
7917.293 |
7133.693 |
4.794 |
-0.15% |
4.794 |
|
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/Dilate/Dilate.test:BENCHMARK_DILATE/128
|
-9.76% |
227.968 |
205.729 |
1.910 |
0.86% |
1.910 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint64_t_To_uint32_t_
|
-9.74% |
17813.492 |
16077.748 |
591.699 |
-1.14% |
591.699 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_only_autovec_int64_t_
|
-9.72% |
333280.792 |
300877.578 |
167.961 |
-0.12% |
167.961 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC127
|
-9.71% |
101.879 |
91.986 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC31
|
-9.71% |
196.470 |
177.403 |
0.015 |
0.00% |
0.015 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC7
|
-9.62% |
32.539 |
29.409 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_with_cond_arith_autovec_int32_t_
|
-9.57% |
940875.108 |
850862.514 |
403.920 |
-0.03% |
403.920 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC7
|
-9.53% |
26.282 |
23.778 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC7
|
-9.50% |
26.282 |
23.785 |
0.026 |
-0.09% |
0.026 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_DEL_DOT_VEC_2D_LAMBDA/1
|
-9.22% |
287.120 |
260.637 |
0.100 |
0.00% |
0.100 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_DEL_DOT_VEC_2D_RAW/1
|
-9.20% |
286.991 |
260.577 |
0.042 |
0.02% |
0.042 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC7
|
-9.20% |
81.312 |
73.833 |
0.006 |
-0.00% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC4
|
-9.10% |
41.302 |
37.544 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC4
|
-9.10% |
41.299 |
37.543 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC4
|
-8.94% |
55.663 |
50.685 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC7
|
-8.90% |
28.160 |
25.655 |
0.001 |
-0.01% |
0.001 |
|
MultiSource/Benchmarks/McCat/12-IOtest/iotest
Profile
|
-8.88% |
1.825 |
1.663 |
0.032 |
-0.56% |
0.032 |
|
MultiSource/Benchmarks/FreeBench/pifft/pifft
Profile
|
-8.72% |
0.359 |
0.327 |
0.001 |
0.02% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC4
|
-8.70% |
14.393 |
13.140 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC16
|
-8.70% |
14.393 |
13.140 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC15
|
-8.70% |
14.392 |
13.140 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC3
|
-8.70% |
14.393 |
13.140 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC8
|
-8.70% |
14.392 |
13.140 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC8
|
-8.70% |
14.393 |
13.140 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC15
|
-8.70% |
14.392 |
13.140 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC4
|
-8.70% |
14.392 |
13.140 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC7
|
-8.70% |
14.392 |
13.140 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC2
|
-8.70% |
14.392 |
13.140 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_DEL_DOT_VEC_2D_RAW/2
|
-8.70% |
3.510 |
3.205 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC1
|
-8.70% |
14.392 |
13.140 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC1
|
-8.70% |
14.393 |
13.142 |
0.000 |
-0.01% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC3
|
-8.70% |
14.392 |
13.141 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC16
|
-8.69% |
14.392 |
13.140 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC2
|
-8.69% |
14.391 |
13.140 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC7
|
-8.69% |
14.391 |
13.140 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_DEL_DOT_VEC_2D_LAMBDA/2
|
-8.69% |
3.510 |
3.205 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint16_t_To_uint8_t_
|
-8.60% |
6815.821 |
6229.705 |
12.791 |
-0.54% |
12.791 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC8
|
-8.51% |
29.411 |
26.907 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_runtime_checks_pass<4, int>
|
-8.24% |
16.708 |
15.330 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC64
|
-8.06% |
93.242 |
85.729 |
0.007 |
0.00% |
0.007 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC16
|
-7.93% |
31.289 |
28.807 |
0.131 |
-0.04% |
0.131 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint8_t_To_uint32_t_
|
-7.91% |
12778.752 |
11768.402 |
26.509 |
-0.33% |
26.509 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC16
|
-7.85% |
31.913 |
29.409 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC16
|
-7.84% |
31.911 |
29.409 |
0.003 |
-0.00% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC32
|
-7.82% |
40.050 |
36.917 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_DEL_DOT_VEC_2D_RAW/0
|
-7.80% |
1800.857 |
1660.467 |
3.148 |
0.02% |
3.148 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC15
|
-7.69% |
32.538 |
30.036 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC15
|
-7.64% |
54.442 |
50.282 |
0.006 |
-0.02% |
0.006 |
|
MultiSource/Benchmarks/VersaBench/beamformer/beamformer
Profile
|
-7.61% |
5.201 |
4.805 |
0.001 |
0.02% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC127
|
-7.60% |
2426.612 |
2242.221 |
25.770 |
-0.44% |
25.770 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_DEL_DOT_VEC_2D_LAMBDA/0
|
-7.59% |
1791.999 |
1656.067 |
3.135 |
0.00% |
3.135 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC31
|
-7.56% |
74.464 |
68.836 |
0.007 |
-0.00% |
0.007 |
|
MultiSource/Benchmarks/Trimaran/enc-md5/enc-md5
Profile
|
-7.50% |
3.506 |
3.243 |
0.000 |
-0.01% |
0.000 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_xor_no_runtime_checks_needed<16, int>
|
-7.42% |
16.896 |
15.643 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_HYDRO_2D_RAW/171
|
-7.40% |
88.626 |
82.071 |
0.972 |
-0.18% |
0.972 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_DIFF_PREDICT_LAMBDA/171
|
-7.32% |
11.986 |
11.108 |
0.103 |
-0.09% |
0.103 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C++/miniFE/miniFE
Profile
|
-7.31% |
15.969 |
14.801 |
0.084 |
0.00% |
0.084 |
|
MultiSource/Applications/lambda-0.1.3/lambda
Profile
|
-7.29% |
15.870 |
14.713 |
0.007 |
-0.08% |
0.007 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC128
|
-7.24% |
68.804 |
63.825 |
0.003 |
-0.01% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC128
|
-7.22% |
173.330 |
160.816 |
0.003 |
-0.00% |
0.003 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_HYDRO_2D_LAMBDA/171
|
-7.22% |
88.658 |
82.257 |
0.346 |
0.56% |
0.346 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint8_t>/127
|
-7.20% |
138.913 |
128.910 |
0.006 |
-0.00% |
0.006 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIND_FIRST_MIN_RAW/171
|
-7.14% |
1.497 |
1.390 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/harris/harris.test:BENCHMARK_HARRIS/2048/2048
|
-7.10% |
167029.260 |
155176.823 |
4032.285 |
-0.35% |
4032.285 |
|
SingleSource/Benchmarks/Misc/pi
Profile
|
-7.02% |
1.782 |
1.657 |
0.000 |
-0.01% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC8
|
-7.00% |
26.912 |
25.029 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC63
|
-6.99% |
114.514 |
106.512 |
0.023 |
-0.03% |
0.023 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC15
|
-6.95% |
45.051 |
41.922 |
0.002 |
-0.01% |
0.002 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_DIFF_PREDICT_RAW/171
|
-6.89% |
11.933 |
11.110 |
0.094 |
-0.06% |
0.094 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint16_t_To_uint64_t_
|
-6.84% |
20143.016 |
18765.011 |
41.067 |
-0.31% |
41.067 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint16_t_To_uint64_t_
|
-6.75% |
24986.152 |
23298.378 |
3.985 |
0.20% |
3.985 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC1
|
-6.66% |
88.984 |
83.058 |
1.576 |
-0.43% |
1.576 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC127
|
-6.62% |
194.608 |
181.723 |
0.295 |
0.00% |
0.295 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC2
|
-6.56% |
38.171 |
35.667 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC127
|
-6.54% |
68.292 |
63.825 |
0.002 |
0.00% |
0.002 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_xor_runtime_checks_pass<16, int>
|
-6.52% |
28.783 |
26.906 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_xor_runtime_checks_fail<16, int>
|
-6.52% |
28.783 |
26.907 |
0.001 |
-0.00% |
0.001 |
|
SingleSource/Benchmarks/Misc/flops-6
Profile
|
-6.48% |
1.312 |
1.227 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_only_autovec_int32_t_
|
-6.44% |
181119.283 |
169452.243 |
430.136 |
-0.03% |
430.136 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC63
|
-6.42% |
74.223 |
69.455 |
0.003 |
-0.01% |
0.003 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_PRESSURE_CALC_LAMBDA/5001
|
-6.40% |
43.974 |
41.159 |
1.072 |
-0.90% |
1.072 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint32_t_To_uint64_t_
|
-6.37% |
21450.888 |
20083.747 |
84.280 |
-0.90% |
84.280 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC15
|
-6.35% |
39.422 |
36.919 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_BAND_LIN_EQ_RAW/171
|
-6.32% |
0.366 |
0.343 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_BAND_LIN_EQ_LAMBDA/171
|
-6.32% |
0.366 |
0.343 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint16_t>/127
|
-6.30% |
138.912 |
130.156 |
0.003 |
0.00% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC7
|
-6.23% |
354.707 |
332.598 |
6.167 |
0.06% |
6.167 |
|
SingleSource/Benchmarks/Misc-C++/Large/sphereflake
Profile
|
-6.18% |
20.002 |
18.766 |
0.002 |
-0.02% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC16
|
-6.16% |
40.674 |
38.169 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC32
|
-6.12% |
61.321 |
57.568 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIND_FIRST_MIN_RAW/5001
|
-6.04% |
45.339 |
42.602 |
0.074 |
0.23% |
0.074 |
|
SingleSource/Benchmarks/Misc/perlin
Profile
|
-5.96% |
6.598 |
6.205 |
0.000 |
-0.00% |
0.000 |
|
External/SPEC/CFP2017rate/538.imagick_r/538.imagick_r
Profile
|
-5.95% |
292.080 |
274.691 |
0.426 |
-0.39% |
0.426 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint8_t>/65
|
-5.92% |
95.111 |
89.483 |
0.008 |
0.00% |
0.008 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint32_t>/127
|
-5.88% |
138.286 |
130.156 |
0.003 |
0.00% |
0.003 |
|
MultiSource/Benchmarks/Rodinia/hotspot/hotspot
Profile
|
-5.68% |
2.036 |
1.920 |
0.007 |
-0.54% |
0.007 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC16
|
-5.66% |
33.163 |
31.286 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC32
|
-5.64% |
44.429 |
41.924 |
0.003 |
0.00% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC32
|
-5.64% |
44.427 |
41.924 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint8_t_To_uint16_t_
|
-5.62% |
3633.347 |
3429.170 |
12.155 |
-0.81% |
12.155 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC15
|
-5.59% |
128.256 |
121.085 |
0.005 |
0.00% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC31
|
-5.58% |
45.064 |
42.549 |
0.002 |
0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC31
|
-5.55% |
45.052 |
42.552 |
0.001 |
0.00% |
0.001 |
|
MultiSource/Benchmarks/SciMark2-C/scimark2
Profile
|
-5.54% |
107.639 |
101.673 |
0.054 |
-0.02% |
0.054 |
|
SingleSource/Benchmarks/Polybench/stencils/jacobi-2d/jacobi-2d
Profile
|
-5.49% |
32.224 |
30.453 |
0.093 |
-0.37% |
0.093 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIND_FIRST_MIN_RAW/44217
|
-5.44% |
389.585 |
368.386 |
0.778 |
-0.15% |
0.778 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint32_t>/999
|
-5.39% |
696.521 |
658.985 |
0.007 |
0.00% |
0.007 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC7
|
-5.33% |
70.719 |
66.951 |
0.004 |
-0.01% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC7
|
-5.32% |
70.713 |
66.953 |
0.007 |
-0.00% |
0.007 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC3
|
-5.27% |
47.558 |
45.051 |
0.003 |
0.00% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC1
|
-5.27% |
11.889 |
11.263 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_PIC_2D_LAMBDA/171
|
-5.23% |
13.498 |
12.792 |
0.044 |
-0.14% |
0.044 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint32_t>/999
|
-5.21% |
1365.037 |
1293.902 |
0.082 |
0.00% |
0.082 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_cond_load_novec_uint8_t_
|
-5.20% |
314092.103 |
297762.210 |
91.718 |
-0.00% |
91.718 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC31
|
-4.99% |
241.230 |
229.183 |
0.065 |
-0.00% |
0.065 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC32
|
-4.93% |
50.052 |
47.582 |
0.149 |
-0.00% |
0.149 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC15
|
-4.81% |
32.539 |
30.973 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint32_t>/256
|
-4.81% |
364.169 |
346.655 |
0.010 |
0.00% |
0.010 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_PIC_2D_RAW/171
|
-4.78% |
13.539 |
12.892 |
0.047 |
0.18% |
0.047 |
|
SingleSource/Benchmarks/Misc/revertBits
Profile
|
-4.71% |
0.641 |
0.611 |
0.000 |
-0.05% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC31
|
-4.66% |
93.853 |
89.478 |
0.100 |
-0.07% |
0.100 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint8_t_To_uint64_t_
|
-4.63% |
23483.830 |
22396.886 |
20.830 |
-0.10% |
20.830 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC63
|
-4.62% |
43.294 |
41.296 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint16_t>/65
|
-4.61% |
95.115 |
90.733 |
0.005 |
-0.01% |
0.005 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_runtime_checks_fail<16, int>
|
-4.60% |
54.439 |
51.934 |
0.003 |
-0.00% |
0.003 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_runtime_checks_pass<16, int>
|
-4.60% |
54.438 |
51.935 |
0.002 |
-0.00% |
0.002 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C++/HPCCG/HPCCG
Profile
|
-4.59% |
3.915 |
3.735 |
0.055 |
-0.22% |
0.055 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC2
|
-4.54% |
13.765 |
13.140 |
0.001 |
-0.00% |
0.001 |
|
SingleSource/Benchmarks/Stanford/Puzzle
Profile
|
-4.47% |
0.241 |
0.231 |
0.004 |
0.06% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC31
|
-4.47% |
70.083 |
66.953 |
0.003 |
-0.00% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint64_t_To_uint8_t_
|
-4.46% |
19841.137 |
18956.003 |
36.663 |
-0.08% |
36.663 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint16_t_To_uint8_t_
|
-4.45% |
2878.208 |
2750.165 |
8.636 |
-0.91% |
8.636 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint32_t_To_uint16_t_
|
-4.45% |
9879.809 |
9440.491 |
28.396 |
-0.06% |
28.396 |
|
SingleSource/Benchmarks/Misc/oourafft
Profile
|
-4.42% |
15.093 |
14.426 |
0.087 |
0.06% |
0.087 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_ENERGY_CALC_RAW/171
|
-4.41% |
14.241 |
13.612 |
0.020 |
-0.02% |
0.020 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC64
|
-4.35% |
43.175 |
41.297 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_ENERGY_CALC_LAMBDA/171
|
-4.33% |
14.248 |
13.630 |
0.006 |
-0.07% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint64_t>/999
|
-4.22% |
1811.241 |
1734.790 |
0.177 |
-0.00% |
0.177 |
|
External/SPEC/CFP2017rate/519.lbm_r/519.lbm_r
Profile
|
-4.15% |
200.678 |
192.354 |
1.396 |
0.09% |
1.396 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint64_t>/999
|
-4.13% |
3594.644 |
3446.176 |
0.110 |
0.00% |
0.110 |
|
MicroBenchmarks/ImageProcessing/Dilate/Dilate.test:BENCHMARK_DILATE/512
|
-4.12% |
3584.064 |
3436.389 |
43.658 |
-1.12% |
43.658 |
|
SingleSource/Benchmarks/Misc/flops-5
Profile
|
-4.12% |
2.021 |
1.938 |
0.000 |
-0.02% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_INT_PREDICT_LAMBDA/44217
|
-4.10% |
8337.702 |
7995.945 |
91.093 |
-0.13% |
91.093 |
|
MultiSource/Benchmarks/TSVC/Recurrences-dbl/Recurrences-dbl
Profile
|
-4.09% |
10.357 |
9.934 |
0.065 |
-1.89% |
0.065 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint16_t_To_uint32_t_
|
-4.08% |
11342.699 |
10880.209 |
12.094 |
-0.05% |
12.094 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint64_t>/256
|
-4.07% |
935.580 |
897.487 |
0.043 |
0.01% |
0.043 |
|
External/SPEC/CFP2017rate/544.nab_r/544.nab_r
Profile
|
-4.07% |
477.880 |
458.433 |
0.076 |
0.04% |
0.076 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_cond_load_autovec_int64_t_
|
-4.05% |
552633.768 |
530232.344 |
1156.076 |
-0.14% |
1156.076 |
|
MicroBenchmarks/ImageProcessing/Dilate/Dilate.test:BENCHMARK_DILATE/256
|
-4.05% |
1067.252 |
1024.036 |
0.703 |
-0.02% |
0.703 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC31
|
-4.03% |
61.945 |
59.446 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC3
|
-4.00% |
15.644 |
15.018 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC32
|
-4.00% |
31.286 |
30.035 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_only_autovec_uint8_t_
|
-3.98% |
96157.793 |
92330.005 |
10.952 |
-0.01% |
10.952 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint32_t>/65
|
-3.98% |
94.488 |
90.729 |
0.007 |
0.00% |
0.007 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC32
|
-3.96% |
63.198 |
60.697 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint32_t>/256
|
-3.95% |
221.503 |
212.745 |
0.013 |
-0.00% |
0.013 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint64_t_To_uint32_t_
|
-3.92% |
19292.425 |
18535.756 |
41.032 |
-0.62% |
41.032 |
|
MultiSource/Benchmarks/sim/sim
Profile
|
-3.87% |
9.701 |
9.326 |
0.004 |
-0.05% |
0.004 |
|
MultiSource/Benchmarks/nbench/nbench
Profile
|
-3.78% |
6.127 |
5.895 |
0.001 |
-0.07% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC31
|
-3.70% |
31.189 |
30.034 |
0.000 |
-0.00% |
0.000 |
|
SingleSource/Benchmarks/Shootout/Shootout-matrix
Profile
|
-3.68% |
3.863 |
3.721 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_PRESSURE_CALC_RAW/44217
|
-3.67% |
502.197 |
483.792 |
1.957 |
0.64% |
1.957 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint64_t>/256
|
-3.65% |
514.395 |
495.632 |
0.024 |
0.00% |
0.024 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_runtime_checks_fail<4, int>
|
-3.64% |
15.908 |
15.330 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC64
|
-3.61% |
69.461 |
66.953 |
0.004 |
-0.00% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC64
|
-3.61% |
69.457 |
66.951 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC63
|
-3.59% |
70.092 |
67.578 |
0.003 |
-0.01% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC63
|
-3.57% |
70.083 |
67.580 |
0.006 |
-0.00% |
0.006 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<31, EqZero, First>
|
-3.47% |
3346.347 |
3230.078 |
2.276 |
0.00% |
2.276 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC31
|
-3.45% |
60.276 |
58.196 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC64
|
-3.38% |
111.383 |
107.623 |
0.004 |
-0.01% |
0.004 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<32, EqZero, Last>
|
-3.26% |
7052.998 |
6822.779 |
28.201 |
-0.21% |
28.201 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint16_t_To_uint8_t_
|
-3.26% |
4517.211 |
4369.962 |
11.753 |
-0.74% |
11.753 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint16_t>/999
|
-3.17% |
515.023 |
498.704 |
0.058 |
-0.01% |
0.058 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1BigLoopWithReductionTC1
|
-3.13% |
20.025 |
19.399 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_FLOYD_DITHER/128
|
-3.09% |
439.467 |
425.898 |
1.886 |
0.10% |
1.886 |
|
SingleSource/Benchmarks/Shootout/Shootout-lists
Profile
|
-3.05% |
11.312 |
10.967 |
0.003 |
-0.02% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchVecWithRuntimeChecks4PointersDBeforeA/1000
|
-3.04% |
5019862.993 |
4867045.410 |
329.870 |
-0.00% |
329.870 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_nested_cond_load_novec_int32_t_
|
-2.95% |
645149.252 |
626107.450 |
540.292 |
-0.11% |
540.292 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint16_t>/999
|
-2.84% |
1013.869 |
985.054 |
0.230 |
-0.00% |
0.230 |
|
MultiSource/Benchmarks/Rodinia/pathfinder/pathfinder
Profile
|
-2.79% |
1.258 |
1.223 |
0.008 |
-0.14% |
0.008 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC1
|
-2.77% |
22.526 |
21.901 |
0.001 |
-0.00% |
0.001 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C/CoMD/CoMD
Profile
|
-2.75% |
9.899 |
9.627 |
0.003 |
-0.00% |
0.003 |
|
MultiSource/Benchmarks/mafft/pairlocalalign
Profile
|
-2.71% |
94.062 |
91.516 |
0.379 |
0.05% |
0.379 |
|
MultiSource/Benchmarks/FreeBench/mason/mason
Profile
|
-2.68% |
0.553 |
0.538 |
0.000 |
-0.01% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC63
|
-2.61% |
120.145 |
117.014 |
0.002 |
0.00% |
0.002 |
|
MultiSource/Benchmarks/FreeBench/pcompress2/pcompress2
Profile
|
-2.60% |
0.404 |
0.394 |
0.001 |
0.02% |
0.001 |
|
MultiSource/Benchmarks/FreeBench/fourinarow/fourinarow
Profile
|
-2.60% |
0.651 |
0.634 |
0.001 |
-0.25% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_cond_load_novec_int32_t_
|
-2.58% |
410715.023 |
400115.244 |
348.513 |
0.06% |
348.513 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC32
|
-2.57% |
24.405 |
23.778 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC31
|
-2.56% |
24.404 |
23.778 |
0.002 |
0.00% |
0.002 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_PRESSURE_CALC_LAMBDA/44217
|
-2.56% |
498.539 |
485.772 |
1.321 |
0.07% |
1.321 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC31
|
-2.56% |
24.403 |
23.778 |
0.002 |
0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC32
|
-2.56% |
24.402 |
23.778 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint8_t_To_uint32_t_
|
-2.50% |
7077.318 |
6900.472 |
0.557 |
0.03% |
0.557 |
|
MultiSource/Benchmarks/TSVC/GlobalDataFlow-flt/GlobalDataFlow-flt
Profile
|
-2.49% |
6.658 |
6.492 |
0.063 |
0.32% |
0.063 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchVecWithRuntimeChecks4PointersDBeforeA/32
|
-2.43% |
166201.466 |
162162.145 |
144.537 |
0.01% |
144.537 |
|
SingleSource/Benchmarks/BenchmarkGame/puzzle
Profile
|
-2.35% |
0.869 |
0.848 |
0.003 |
-0.48% |
0.003 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<31, GreaterThanZero, Last>
|
-2.35% |
8295.600 |
8100.689 |
21.765 |
0.01% |
21.765 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC63
|
-2.34% |
107.004 |
104.499 |
0.003 |
-0.00% |
0.003 |
|
SingleSource/Benchmarks/Misc/fbench
Profile
|
-2.32% |
5.761 |
5.628 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC64
|
-2.31% |
108.247 |
105.750 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_FLOYD_DITHER/512
|
-2.31% |
6645.158 |
6491.961 |
23.186 |
0.02% |
23.186 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC63
|
-2.26% |
130.166 |
127.229 |
0.083 |
0.02% |
0.083 |
|
MultiSource/Applications/JM/lencod/lencod
Profile
|
-2.26% |
32.540 |
31.806 |
0.037 |
0.03% |
0.037 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_nested_cond_load_novec_uint8_t_
|
-2.24% |
504714.718 |
493387.860 |
345.082 |
0.00% |
345.082 |
|
SingleSource/Benchmarks/Misc/flops-1
Profile
|
-2.15% |
9.000 |
8.806 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_only_autovec_int64_t_
|
-2.14% |
1446971.267 |
1416026.079 |
1544.732 |
-0.06% |
1544.732 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC128
|
-2.10% |
119.525 |
117.010 |
0.003 |
-0.00% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC128
|
-2.10% |
119.520 |
117.007 |
0.007 |
-0.01% |
0.007 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC127
|
-2.09% |
120.146 |
117.637 |
0.001 |
-0.00% |
0.001 |
|
SingleSource/Benchmarks/Misc-C++/Large/ray
Profile
|
-2.08% |
12.101 |
11.849 |
0.002 |
-0.01% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC127
|
-2.08% |
120.138 |
117.642 |
0.002 |
-0.00% |
0.002 |
|
MultiSource/Benchmarks/Bullet/bullet
Profile
|
-2.02% |
30.431 |
29.816 |
0.163 |
-0.16% |
0.163 |
|
MultiSource/Benchmarks/TSVC/ControlLoops-flt/ControlLoops-flt
Profile
|
-2.00% |
5.447 |
5.338 |
0.031 |
-0.11% |
0.031 |
|
SingleSource/Benchmarks/Misc/ReedSolomon
Profile
|
-1.95% |
20.797 |
20.391 |
0.001 |
0.00% |
0.001 |
|
MultiSource/Benchmarks/tramp3d-v4/tramp3d-v4
Profile
|
-1.93% |
1.076 |
1.055 |
0.005 |
-0.16% |
0.005 |
|
External/SPEC/CINT2017rate/531.deepsjeng_r/531.deepsjeng_r
Profile
|
-1.90% |
260.112 |
255.170 |
0.351 |
-0.19% |
0.351 |
|
MultiSource/Applications/sgefa/sgefa
Profile
|
-1.88% |
0.573 |
0.563 |
0.001 |
-0.47% |
0.001 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<16, LessThanZero, Mid>
|
-1.87% |
8659.949 |
8497.946 |
13.867 |
-0.05% |
13.867 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_ENERGY_CALC_RAW/44217
|
-1.86% |
4331.435 |
4250.885 |
6.491 |
0.29% |
6.491 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint16_t>/256
|
-1.84% |
272.838 |
267.820 |
0.010 |
0.00% |
0.010 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<16, EqZero, Mid>
|
-1.83% |
8657.236 |
8499.131 |
2.516 |
-0.02% |
2.516 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint32_t>/10
|
-1.82% |
61.947 |
60.821 |
0.016 |
0.00% |
0.016 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_EOS_RAW/171
|
-1.81% |
0.871 |
0.855 |
0.000 |
-0.10% |
0.000 |
|
External/SPEC/CINT2017rate/523.xalancbmk_r/523.xalancbmk_r
Profile
|
-1.78% |
240.953 |
236.652 |
0.291 |
-0.10% |
0.291 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint32_t_To_uint64_t_
|
-1.78% |
26280.748 |
25811.868 |
55.775 |
-0.02% |
55.775 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC128
|
-1.78% |
211.515 |
207.752 |
1.206 |
-0.65% |
1.206 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, GreaterThanZero, None>
|
-1.78% |
37175.735 |
36515.297 |
6.154 |
0.01% |
6.154 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<6, GreaterThanZero, None>
|
-1.78% |
29578.660 |
29053.478 |
47.054 |
-0.12% |
47.054 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_ADI_LAMBDA/44217
|
-1.77% |
19679.530 |
19331.925 |
81.459 |
0.20% |
81.459 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint32_t>/51
|
-1.75% |
83.849 |
82.379 |
0.159 |
-0.25% |
0.159 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_ENERGY_CALC_LAMBDA/44217
|
-1.73% |
4324.422 |
4249.560 |
20.253 |
-0.17% |
20.253 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_EOS_LAMBDA/171
|
-1.71% |
0.871 |
0.856 |
0.000 |
0.03% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint64_t>/51
|
-1.70% |
148.307 |
145.791 |
0.006 |
-0.00% |
0.006 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<32, LessThanZero, Mid>
|
-1.68% |
4570.992 |
4494.138 |
5.785 |
0.04% |
5.785 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_csa_with_in_loop_arith_novec_int64_t_
|
-1.68% |
1028155.144 |
1010917.386 |
800.679 |
-0.00% |
800.679 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_INT_PREDICT_RAW/171
|
-1.67% |
6.925 |
6.809 |
0.007 |
-0.09% |
0.007 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C/SimpleMOC/SimpleMOC
Profile
|
-1.62% |
10.405 |
10.236 |
0.045 |
-0.00% |
0.045 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_INT_PREDICT_LAMBDA/171
|
-1.62% |
6.925 |
6.813 |
0.011 |
-0.04% |
0.011 |
|
MultiSource/Benchmarks/VersaBench/ecbdes/ecbdes
Profile
|
-1.60% |
5.139 |
5.057 |
0.001 |
0.03% |
0.001 |
|
MultiSource/Benchmarks/Olden/health/health
Profile
|
-1.57% |
1.591 |
1.566 |
0.002 |
0.01% |
0.002 |
|
MultiSource/Benchmarks/ASC_Sequoia/CrystalMk/CrystalMk
Profile
|
-1.56% |
15.572 |
15.329 |
0.000 |
-0.00% |
0.000 |
|
SingleSource/Benchmarks/Misc/ffbench
Profile
|
-1.55% |
11.084 |
10.912 |
0.001 |
-0.64% |
0.001 |
|
SingleSource/Benchmarks/Misc/mandel-2
Profile
|
-1.54% |
2.535 |
2.496 |
0.000 |
-0.01% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint16_t>/16
|
-1.52% |
58.454 |
57.564 |
0.006 |
-0.00% |
0.006 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, LessThanZero, None>
|
-1.51% |
37576.235 |
37007.199 |
22.236 |
-0.12% |
22.236 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint32_t>/28
|
-1.45% |
82.597 |
81.396 |
0.006 |
0.01% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC127
|
-1.42% |
220.275 |
217.146 |
0.016 |
-0.01% |
0.016 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC64
|
-1.39% |
86.350 |
85.147 |
0.210 |
-0.05% |
0.210 |
|
SingleSource/Benchmarks/Adobe-C++/simple_types_loop_invariant
Profile
|
-1.38% |
1.863 |
1.837 |
0.006 |
-0.23% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint8_t_To_uint32_t_
|
-1.37% |
12122.484 |
11955.958 |
30.762 |
-0.33% |
30.762 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, LessThanZero, Mid>
|
-1.36% |
56527.388 |
55757.478 |
6.537 |
-0.02% |
6.537 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint64_t>/51
|
-1.36% |
229.009 |
225.890 |
0.007 |
-0.00% |
0.007 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint16_t>/28
|
-1.34% |
75.469 |
74.459 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC128
|
-1.27% |
198.368 |
195.856 |
0.005 |
-0.00% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC127
|
-1.27% |
197.100 |
194.606 |
0.003 |
-0.00% |
0.003 |
|
MultiSource/Benchmarks/MallocBench/cfrac/cfrac
Profile
|
-1.24% |
2.780 |
2.745 |
0.001 |
0.01% |
0.001 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<32, GreaterThanZero, Mid>
|
-1.24% |
4555.446 |
4498.884 |
14.322 |
-0.07% |
14.322 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint16_t_To_uint32_t_
|
-1.20% |
13483.541 |
13321.882 |
5.606 |
0.08% |
5.606 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_sinh_autovec_double_
|
-1.15% |
2475.629 |
2447.181 |
0.699 |
-0.03% |
0.699 |
|
External/SPEC/CINT2017rate/500.perlbench_r/500.perlbench_r
Profile
|
-1.15% |
146.700 |
145.018 |
0.625 |
-0.17% |
0.625 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<7, EqZero, None>
|
-1.13% |
27180.943 |
26872.686 |
4.638 |
-0.01% |
4.638 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_sinhf_autovec_float_
|
-1.12% |
2242.663 |
2217.597 |
0.321 |
0.01% |
0.321 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, LessThanZero, Mid>
|
-1.11% |
31782.155 |
31429.512 |
9.513 |
0.01% |
9.513 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_sinh_novec_double_
|
-1.11% |
2473.865 |
2446.463 |
2.160 |
-0.01% |
2.160 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_sinhf_novec_float_
|
-1.10% |
2241.857 |
2217.225 |
1.140 |
-0.06% |
1.140 |
|
External/SPEC/CINT2017rate/541.leela_r/541.leela_r
Profile
|
-1.10% |
229.386 |
226.870 |
0.333 |
-0.03% |
0.333 |
|
SingleSource/Benchmarks/SmallPT/smallpt
Profile
|
-1.08% |
30.029 |
29.706 |
0.003 |
-0.00% |
0.003 |
|
SingleSource/Benchmarks/Shootout-C++/Shootout-C++-hash2
Profile
|
-1.06% |
9.336 |
9.237 |
0.007 |
-0.14% |
0.007 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint32_t>/51
|
-1.05% |
78.409 |
77.586 |
0.004 |
-0.01% |
0.004 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<64, LessThanZero, None>
|
-1.05% |
2961.853 |
2930.892 |
2.017 |
0.05% |
2.017 |
|
MultiSource/Benchmarks/TSVC/Searching-dbl/Searching-dbl
Profile
|
-1.04% |
7.666 |
7.587 |
0.013 |
0.02% |
0.013 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<8, LessThanZero, Mid>
|
-1.02% |
19434.559 |
19235.758 |
4.890 |
0.02% |
4.890 |