|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_INT_PREDICT_LAMBDA/44217
|
-58.38% |
19111.855 |
7953.806 |
110.953 |
-4.60% |
110.953 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C/miniGMG/miniGMG
Profile
|
-50.53% |
9.280 |
4.591 |
0.097 |
-50.05% |
0.097 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint64_t_To_uint16_t_
|
-50.52% |
35836.292 |
17733.390 |
286.966 |
-50.30% |
286.966 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint64_t_To_uint32_t_
|
-50.20% |
35278.610 |
17569.633 |
163.416 |
-50.25% |
163.416 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint64_t_To_uint8_t_
|
-48.74% |
37006.481 |
18968.994 |
10.134 |
-48.82% |
10.134 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_INT_PREDICT_LAMBDA/5001
|
-47.69% |
1744.081 |
912.321 |
1.771 |
0.84% |
1.771 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_HYDRO_2D_LAMBDA/44217
|
-47.42% |
95209.827 |
50061.621 |
4030.613 |
-44.95% |
4030.613 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint16_t_To_uint64_t_
|
-44.05% |
18665.888 |
10444.364 |
2.753 |
-44.07% |
2.753 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_DIFF_PREDICT_LAMBDA/44217
|
-43.60% |
23943.608 |
13504.397 |
305.332 |
-41.55% |
305.332 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIRST_DIFF_LAMBDA/44217
|
-43.11% |
175.851 |
100.038 |
1.899 |
-30.92% |
1.899 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_HYDRO_2D_LAMBDA/5001
|
-42.36% |
9715.675 |
5600.443 |
481.029 |
-38.55% |
481.029 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_DIFF_PREDICT_RAW/44217
|
-42.01% |
23270.094 |
13494.320 |
304.329 |
-42.08% |
304.329 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_DIFF_PREDICT_RAW/5001
|
-41.36% |
2585.043 |
1515.826 |
11.266 |
-41.13% |
11.266 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint8_t_To_uint64_t_
|
-40.96% |
17836.486 |
10530.665 |
4.752 |
-40.84% |
4.752 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint64_t_To_uint32_t_
|
-40.86% |
38263.450 |
22627.751 |
25.340 |
-40.70% |
25.340 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_DIFF_PREDICT_LAMBDA/5001
|
-40.11% |
2514.167 |
1505.763 |
59.075 |
-40.00% |
59.075 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint32_t_To_uint64_t_
|
-37.71% |
22421.376 |
13966.043 |
275.773 |
-38.54% |
275.773 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/32
|
-36.70% |
1396.238 |
883.829 |
0.102 |
-36.69% |
0.102 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/64
|
-36.67% |
6181.407 |
3914.542 |
9.700 |
-36.68% |
9.700 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/16
|
-36.63% |
279.484 |
177.104 |
0.014 |
-36.63% |
0.014 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/256
|
-36.16% |
107098.565 |
68372.250 |
34.583 |
-36.19% |
34.583 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/128
|
-36.10% |
26262.184 |
16780.273 |
5.732 |
-36.13% |
5.732 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint64_t_To_uint8_t_
|
-34.25% |
30105.212 |
19794.352 |
21.728 |
-34.26% |
21.728 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint64_t_To_uint16_t_
|
-33.89% |
28893.322 |
19101.471 |
6.810 |
-34.02% |
6.810 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_DISC_ORD_LAMBDA/44217
|
-32.10% |
14813.373 |
10057.591 |
635.799 |
-28.44% |
635.799 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, EqZero, None>
|
-31.24% |
20511.751 |
14104.642 |
0.276 |
-31.24% |
0.276 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIRST_DIFF_RAW/44217
|
-29.77% |
146.207 |
102.684 |
0.611 |
-27.94% |
0.611 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint64_t_To_uint16_t_
|
-28.78% |
25896.456 |
18444.571 |
24.963 |
-28.78% |
24.963 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint32_t_To_uint8_t_
|
-27.95% |
13472.382 |
9707.209 |
18.547 |
-27.93% |
18.547 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC128
|
-27.94% |
1291.861 |
930.870 |
7.334 |
-28.00% |
7.334 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_PIC_2D_RAW/44217
|
-27.37% |
11926.282 |
8661.806 |
405.190 |
-22.77% |
405.190 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC64
|
-27.35% |
653.571 |
474.819 |
2.902 |
-27.35% |
2.902 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_PIC_2D_LAMBDA/44217
|
-27.13% |
11857.052 |
8639.756 |
70.426 |
-21.19% |
70.426 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC32
|
-27.11% |
333.996 |
243.449 |
1.403 |
-27.10% |
1.403 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC128
|
-26.99% |
558.533 |
407.767 |
0.070 |
-26.86% |
0.070 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC16
|
-26.52% |
173.781 |
127.691 |
0.916 |
-26.52% |
0.916 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_PIC_2D_LAMBDA/5001
|
-25.86% |
1215.689 |
901.292 |
35.349 |
-18.47% |
35.349 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC64
|
-25.66% |
292.090 |
217.134 |
0.025 |
-25.59% |
0.025 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIRST_SUM_LAMBDA/44217
|
-24.76% |
179.683 |
135.198 |
0.604 |
-19.09% |
0.604 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint64_t_To_uint8_t_
|
-24.43% |
27236.355 |
20583.598 |
14.308 |
-24.39% |
14.308 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, EqZero, None>
|
-23.99% |
16024.052 |
12180.370 |
0.845 |
-23.98% |
0.845 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC128
|
-23.21% |
603.962 |
463.802 |
0.007 |
-23.21% |
0.007 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC32
|
-23.16% |
158.830 |
122.048 |
0.008 |
-23.18% |
0.008 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC128
|
-23.10% |
603.910 |
464.418 |
0.012 |
-23.10% |
0.012 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_PIC_2D_RAW/5001
|
-22.87% |
1176.523 |
907.454 |
35.250 |
-15.85% |
35.250 |
|
MicroBenchmarks/ImageProcessing/Blur/blur.test:BENCHMARK_boxBlurKernel/1024
|
-22.50% |
30031.732 |
23273.972 |
77.082 |
-22.80% |
77.082 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC64
|
-22.36% |
313.512 |
243.415 |
0.014 |
-22.36% |
0.014 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC127
|
-22.17% |
615.160 |
478.784 |
0.024 |
-22.18% |
0.024 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC64
|
-22.16% |
313.499 |
244.042 |
0.013 |
-22.16% |
0.013 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIRST_SUM_RAW/44217
|
-22.08% |
173.376 |
135.092 |
1.136 |
-18.78% |
1.136 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC127
|
-21.96% |
615.184 |
480.059 |
0.024 |
-21.97% |
0.024 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint16_t_To_uint64_t_
|
-21.96% |
13274.621 |
10359.557 |
2.793 |
-21.57% |
2.793 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint16_t_To_uint32_t_
|
-21.62% |
7110.264 |
5573.170 |
5.170 |
-21.52% |
5.170 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint8_t_To_uint32_t_
|
-21.41% |
6579.050 |
5170.765 |
2.608 |
-21.44% |
2.608 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_only_autovec_uint8_t_
|
-21.36% |
182360.369 |
143406.094 |
51.290 |
-21.36% |
51.290 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIND_FIRST_MIN_LAMBDA/171
|
-21.30% |
1.501 |
1.181 |
0.000 |
-21.28% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIND_FIRST_MIN_LAMBDA/44217
|
-21.21% |
389.691 |
307.045 |
0.075 |
-21.19% |
0.075 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC32
|
-20.82% |
168.319 |
133.283 |
0.004 |
-20.82% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC32
|
-20.46% |
168.327 |
133.896 |
0.007 |
-20.46% |
0.007 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC63
|
-20.43% |
324.774 |
258.425 |
0.015 |
-20.43% |
0.015 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIND_FIRST_MIN_LAMBDA/5001
|
-20.27% |
45.244 |
36.073 |
0.126 |
-20.29% |
0.126 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC128
|
-20.08% |
273.858 |
218.866 |
0.908 |
-20.34% |
0.908 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC63
|
-20.04% |
324.783 |
259.682 |
0.015 |
-20.05% |
0.015 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC127
|
-19.70% |
640.897 |
514.628 |
0.030 |
-19.65% |
0.030 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC127
|
-19.65% |
273.691 |
219.923 |
0.245 |
-20.16% |
0.245 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC16
|
-19.30% |
92.274 |
74.464 |
0.007 |
-19.31% |
0.007 |
|
MultiSource/Benchmarks/MiBench/automotive-bitcount/automotive-bitcount
Profile
|
-19.21% |
0.125 |
0.101 |
0.000 |
-18.35% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint16_t_To_uint8_t_
|
-19.10% |
3817.754 |
3088.571 |
0.482 |
-19.11% |
0.482 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint32_t_To_uint8_t_
|
-19.08% |
13903.459 |
11250.444 |
49.558 |
-19.07% |
49.558 |
|
SingleSource/Benchmarks/Adobe-C++/loop_unroll
Profile
|
-18.79% |
2.982 |
2.422 |
0.001 |
-22.05% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_VOL3D_CALC_RAW/2
|
-18.79% |
8.757 |
7.111 |
0.000 |
-18.79% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_VOL3D_CALC_LAMBDA/2
|
-18.78% |
8.756 |
7.111 |
0.000 |
-18.79% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint32_t_To_uint16_t_
|
-18.68% |
13823.946 |
11242.277 |
1.565 |
-18.58% |
1.565 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint64_t_To_uint32_t_
|
-18.63% |
27114.373 |
22063.509 |
17.595 |
-18.44% |
17.595 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_PIC_1D_LAMBDA/44217
|
-18.41% |
13469.249 |
10989.175 |
84.635 |
-18.38% |
84.635 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC16
|
-18.30% |
95.740 |
78.219 |
0.002 |
-18.30% |
0.002 |
|
MultiSource/Benchmarks/Trimaran/enc-pc1/enc-pc1
Profile
|
-18.15% |
1.105 |
0.904 |
0.000 |
-18.11% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_with_cond_arith_novec_uint8_t_
|
-17.86% |
745859.804 |
612651.316 |
230.526 |
-17.85% |
230.526 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC16
|
-17.65% |
95.741 |
78.839 |
0.003 |
-17.65% |
0.003 |
|
MultiSource/Benchmarks/MiBench/security-rijndael/security-rijndael
Profile
|
-17.56% |
0.336 |
0.277 |
0.000 |
-17.30% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC31
|
-17.43% |
179.594 |
148.296 |
0.004 |
-17.42% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_with_cond_arith_novec_int32_t_
|
-17.40% |
740149.052 |
611354.750 |
1471.126 |
-17.41% |
1471.126 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC4
|
-17.39% |
17.520 |
14.474 |
0.006 |
-17.39% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC128
|
-17.25% |
570.732 |
472.271 |
0.009 |
-17.23% |
0.009 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC64
|
-17.13% |
297.863 |
246.833 |
0.020 |
-17.09% |
0.020 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC64
|
-16.97% |
148.410 |
123.221 |
0.598 |
-17.10% |
0.598 |
|
MicroBenchmarks/ImageProcessing/Dilate/Dilate.test:BENCHMARK_DILATE/128
|
-16.88% |
238.770 |
198.471 |
6.756 |
-12.94% |
6.756 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC32
|
-16.87% |
161.441 |
134.206 |
0.041 |
-16.85% |
0.041 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC31
|
-16.72% |
179.589 |
149.554 |
0.010 |
-16.72% |
0.010 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC16
|
-16.43% |
93.235 |
77.921 |
0.008 |
-16.33% |
0.008 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint8_t_To_uint64_t_
|
-16.29% |
13039.732 |
10915.658 |
3.555 |
-16.45% |
3.555 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC4
|
-16.17% |
113.635 |
95.264 |
1.398 |
-15.76% |
1.398 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_VOL3D_CALC_LAMBDA/0
|
-16.12% |
1266.308 |
1062.199 |
0.911 |
-16.20% |
0.911 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_VOL3D_CALC_RAW/0
|
-16.10% |
1266.511 |
1062.655 |
1.127 |
-16.01% |
1.127 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_VOL3D_CALC_LAMBDA/1
|
-16.08% |
260.045 |
218.222 |
0.050 |
-16.12% |
0.050 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_VOL3D_CALC_RAW/1
|
-16.08% |
260.024 |
218.207 |
0.276 |
-16.12% |
0.276 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_HYDRO_1D_RAW/171
|
-15.98% |
0.442 |
0.372 |
0.000 |
-15.84% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC63
|
-15.84% |
151.397 |
127.417 |
2.207 |
-15.01% |
2.207 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_HYDRO_1D_LAMBDA/171
|
-15.82% |
0.442 |
0.372 |
0.000 |
-15.88% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint16_t_To_uint32_t_
|
-15.68% |
7463.415 |
6293.294 |
0.652 |
-15.67% |
0.652 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC8
|
-15.42% |
58.815 |
49.748 |
0.001 |
-15.34% |
0.001 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, EqZero, First>
|
-15.40% |
16671.444 |
14103.667 |
0.970 |
-15.40% |
0.970 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_no_runtime_checks_needed<16, int>
|
-15.38% |
24.404 |
20.650 |
0.000 |
-15.38% |
0.000 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, EqZero, Mid>
|
-15.38% |
16667.428 |
14104.159 |
0.877 |
-15.37% |
0.877 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, EqZero, Last>
|
-15.35% |
16667.131 |
14108.975 |
1.037 |
-15.35% |
1.037 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint32_t_To_uint8_t_
|
-15.04% |
10623.973 |
9026.337 |
21.592 |
-14.81% |
21.592 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC127
|
-14.81% |
605.796 |
516.052 |
0.007 |
-14.81% |
0.007 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC8
|
-14.73% |
59.443 |
50.687 |
0.000 |
-14.74% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint32_t_To_uint64_t_
|
-14.72% |
17801.162 |
15180.473 |
252.107 |
-11.72% |
252.107 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC128
|
-14.58% |
1103.338 |
942.505 |
0.085 |
-14.57% |
0.085 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC127
|
-14.52% |
1095.293 |
936.257 |
0.071 |
-14.52% |
0.071 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC64
|
-14.36% |
562.567 |
481.791 |
0.034 |
-14.32% |
0.034 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC63
|
-14.24% |
554.502 |
475.546 |
0.042 |
-14.28% |
0.042 |
|
SingleSource/Benchmarks/Misc/salsa20
Profile
|
-14.14% |
15.387 |
13.211 |
0.000 |
-14.13% |
0.000 |
|
External/SPEC/CFP2017rate/508.namd_r/508.namd_r
Profile
|
-14.11% |
224.503 |
192.826 |
0.420 |
-13.75% |
0.420 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint8_t_To_uint16_t_
|
-14.07% |
3757.352 |
3228.755 |
3.671 |
-14.05% |
3.671 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC32
|
-13.93% |
292.232 |
251.534 |
0.013 |
-13.85% |
0.013 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint32_t_To_uint8_t_
|
-13.89% |
11094.490 |
9553.735 |
4.549 |
-14.16% |
4.549 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC3
|
-13.86% |
51.940 |
44.739 |
0.004 |
-13.85% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC8
|
-13.86% |
51.939 |
44.739 |
0.003 |
-13.86% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC1
|
-13.86% |
51.936 |
44.740 |
0.002 |
-13.85% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_with_cond_arith_autovec_int64_t_
|
-13.86% |
790600.261 |
681056.709 |
1063.972 |
-13.97% |
1063.972 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC2
|
-13.85% |
51.933 |
44.739 |
0.002 |
-13.85% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC7
|
-13.85% |
51.932 |
44.738 |
0.002 |
-13.86% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC4
|
-13.85% |
51.933 |
44.739 |
0.001 |
-13.85% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_with_cond_arith_novec_int64_t_
|
-13.76% |
790093.830 |
681411.373 |
868.962 |
-13.53% |
868.962 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint64_t_To_uint8_t_
|
-13.73% |
22048.907 |
19022.575 |
20.555 |
-13.72% |
20.555 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC8
|
-13.69% |
59.443 |
51.307 |
0.002 |
-13.70% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC31
|
-13.66% |
284.106 |
245.306 |
0.017 |
-13.65% |
0.017 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC8
|
-13.65% |
23.153 |
19.993 |
0.013 |
-13.65% |
0.013 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, EqZero, Last>
|
-13.62% |
14102.686 |
12181.505 |
0.702 |
-13.64% |
0.702 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, EqZero, First>
|
-13.62% |
14102.847 |
12181.847 |
0.697 |
-13.62% |
0.697 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, EqZero, Mid>
|
-13.62% |
14103.266 |
12182.569 |
0.489 |
-13.62% |
0.489 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC63
|
-13.43% |
374.451 |
324.160 |
0.024 |
-13.43% |
0.024 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint32_t_To_uint16_t_
|
-13.34% |
12816.698 |
11106.683 |
10.125 |
-13.48% |
10.125 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIRST_SUM_LAMBDA/5001
|
-13.25% |
20.315 |
17.623 |
0.289 |
0.09% |
0.289 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC8
|
-13.16% |
23.779 |
20.650 |
0.000 |
-13.16% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC16
|
-13.14% |
157.044 |
136.404 |
0.005 |
-13.10% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC128
|
-13.08% |
81.349 |
70.708 |
0.003 |
-13.08% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint8_t_To_uint16_t_
|
-12.95% |
4542.385 |
3954.079 |
0.449 |
-12.94% |
0.449 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC15
|
-12.88% |
107.012 |
93.229 |
0.004 |
-12.87% |
0.004 |
|
SingleSource/Benchmarks/Shootout-C++/Shootout-C++-matrix
Profile
|
-12.74% |
2.509 |
2.190 |
0.000 |
-12.71% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC63
|
-12.69% |
332.922 |
290.675 |
0.008 |
-12.66% |
0.008 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC15
|
-12.61% |
148.919 |
130.137 |
0.007 |
-12.55% |
0.007 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint16_t_To_uint8_t_
|
-12.41% |
4742.573 |
4153.950 |
0.749 |
-12.42% |
0.749 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_INT_PREDICT_RAW/44217
|
-12.17% |
9097.614 |
7990.717 |
91.493 |
-11.70% |
91.493 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC8
|
-11.94% |
89.483 |
78.803 |
0.020 |
-11.85% |
0.020 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC2
|
-11.76% |
21.274 |
18.771 |
0.001 |
-11.77% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC15
|
-11.69% |
106.993 |
94.481 |
0.004 |
-11.71% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC16
|
-11.46% |
51.941 |
45.989 |
0.002 |
-11.46% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC16
|
-11.45% |
33.162 |
29.364 |
0.014 |
-11.46% |
0.014 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC15
|
-11.45% |
51.932 |
45.988 |
0.002 |
-11.46% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC31
|
-11.41% |
86.170 |
76.337 |
0.006 |
-11.35% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC4
|
-11.11% |
22.526 |
20.023 |
0.001 |
-11.12% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC3
|
-11.10% |
22.525 |
20.025 |
0.001 |
-11.11% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC4
|
-11.10% |
22.524 |
20.025 |
0.000 |
-11.11% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC7
|
-10.77% |
81.345 |
72.583 |
0.003 |
-10.74% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint8_t>/51
|
-10.63% |
123.890 |
110.721 |
0.083 |
19.69% |
0.083 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC4
|
-10.60% |
41.296 |
36.917 |
0.000 |
-10.62% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_BAND_LIN_EQ_LAMBDA/171
|
-10.60% |
0.384 |
0.343 |
0.000 |
-6.32% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_BAND_LIN_EQ_RAW/171
|
-10.60% |
0.384 |
0.343 |
0.000 |
-6.33% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint32_t_To_uint16_t_
|
-10.56% |
10709.492 |
9578.556 |
28.018 |
-10.79% |
28.018 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC4
|
-10.53% |
23.778 |
21.273 |
0.001 |
-10.54% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC64
|
-10.47% |
53.815 |
48.178 |
0.002 |
-10.48% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC32
|
-10.43% |
85.228 |
76.340 |
0.001 |
-10.53% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_DIFF_PREDICT_LAMBDA/171
|
-10.22% |
12.380 |
11.114 |
0.032 |
-7.27% |
0.032 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/16
|
-10.17% |
115.476 |
103.727 |
0.006 |
-10.17% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC4
|
-10.10% |
55.686 |
50.062 |
0.000 |
-10.06% |
0.000 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/64
|
-10.10% |
1913.677 |
1720.471 |
10.649 |
-10.08% |
10.649 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint8_t_To_uint16_t_
|
-10.06% |
5848.523 |
5259.891 |
12.147 |
-10.09% |
12.147 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_only_autovec_int64_t_
|
-10.05% |
333439.355 |
299917.665 |
885.632 |
-10.01% |
885.632 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC7
|
-10.02% |
354.709 |
319.165 |
5.789 |
-10.02% |
5.789 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/32
|
-9.99% |
473.031 |
425.788 |
0.013 |
-9.98% |
0.013 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/256
|
-9.92% |
31444.570 |
28324.841 |
38.206 |
-9.94% |
38.206 |
|
MultiSource/Benchmarks/McCat/12-IOtest/iotest
Profile
|
-9.88% |
1.833 |
1.652 |
0.048 |
-9.47% |
0.048 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/128
|
-9.86% |
7918.118 |
7137.603 |
7.944 |
-9.85% |
7.944 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC8
|
-9.76% |
25.656 |
23.152 |
0.001 |
-9.76% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC8
|
-9.75% |
25.654 |
23.152 |
0.000 |
-9.76% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC7
|
-9.61% |
32.537 |
29.410 |
0.003 |
-9.61% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC7
|
-9.53% |
26.280 |
23.776 |
0.002 |
-9.53% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC7
|
-9.52% |
26.278 |
23.777 |
0.002 |
-9.53% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC32
|
-9.42% |
53.184 |
48.172 |
0.003 |
-9.44% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC31
|
-9.40% |
196.497 |
178.023 |
0.013 |
-9.39% |
0.013 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC127
|
-9.34% |
101.463 |
91.988 |
0.000 |
-9.71% |
0.000 |
|
MultiSource/Benchmarks/FreeBench/pifft/pifft
Profile
|
-9.30% |
0.360 |
0.326 |
0.001 |
-9.08% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_DEL_DOT_VEC_2D_LAMBDA/1
|
-9.27% |
287.252 |
260.630 |
0.090 |
-9.23% |
0.090 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_DEL_DOT_VEC_2D_RAW/1
|
-9.22% |
287.166 |
260.696 |
0.076 |
-9.16% |
0.076 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC15
|
-9.21% |
44.798 |
40.674 |
1.476 |
-8.46% |
1.476 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC4
|
-9.09% |
41.298 |
37.543 |
0.003 |
-9.10% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC7
|
-8.88% |
28.156 |
25.654 |
0.001 |
-8.90% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_DEL_DOT_VEC_2D_RAW/2
|
-8.71% |
3.510 |
3.204 |
0.000 |
-8.71% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_DEL_DOT_VEC_2D_LAMBDA/2
|
-8.71% |
3.510 |
3.204 |
0.000 |
-8.70% |
0.000 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_runtime_checks_pass<4, int>
|
-8.62% |
16.776 |
15.330 |
0.001 |
-8.25% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC16
|
-8.62% |
36.292 |
33.165 |
0.004 |
-8.62% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC8
|
-8.51% |
29.409 |
26.908 |
0.000 |
-8.51% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint16_t_To_uint8_t_
|
-8.43% |
6809.374 |
6235.484 |
13.483 |
-8.51% |
13.483 |
|
MicroBenchmarks/ImageProcessing/Blur/blur.test:BENCHMARK_boxBlurKernel/128
|
-8.31% |
452.817 |
415.191 |
8.377 |
-4.39% |
8.377 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint8_t_To_uint32_t_
|
-8.24% |
12790.478 |
11736.061 |
15.107 |
-8.16% |
15.107 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC127
|
-8.24% |
2410.336 |
2211.639 |
27.755 |
-8.86% |
27.755 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC2
|
-8.19% |
38.171 |
35.043 |
0.000 |
-8.19% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_DIFF_PREDICT_RAW/171
|
-8.12% |
12.096 |
11.114 |
0.040 |
-6.86% |
0.040 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC64
|
-8.07% |
93.230 |
85.704 |
0.009 |
-8.08% |
0.009 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint8_t>/28
|
-8.04% |
82.592 |
75.955 |
0.576 |
12.38% |
0.576 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint16_t_To_uint64_t_
|
-7.94% |
20234.112 |
18627.851 |
82.835 |
-7.52% |
82.835 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC3
|
-7.90% |
47.557 |
43.802 |
0.001 |
-7.90% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC16
|
-7.84% |
31.911 |
29.408 |
0.001 |
-7.85% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC16
|
-7.84% |
31.912 |
29.411 |
0.001 |
-7.84% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC32
|
-7.81% |
40.044 |
36.918 |
0.000 |
-7.82% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC15
|
-7.70% |
32.537 |
30.033 |
0.003 |
-7.70% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC15
|
-7.69% |
32.539 |
30.036 |
0.001 |
-7.69% |
0.001 |
|
MultiSource/Benchmarks/VersaBench/beamformer/beamformer
Profile
|
-7.63% |
5.202 |
4.805 |
0.001 |
-7.61% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC8
|
-7.62% |
26.417 |
24.404 |
0.001 |
-9.32% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC1
|
-7.58% |
88.978 |
82.232 |
1.449 |
-7.59% |
1.449 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint16_t_To_uint64_t_
|
-7.56% |
25022.625 |
23130.609 |
94.290 |
-7.43% |
94.290 |
|
MultiSource/Benchmarks/Trimaran/enc-md5/enc-md5
Profile
|
-7.51% |
3.506 |
3.243 |
0.000 |
-7.49% |
0.000 |
|
MicroBenchmarks/ImageProcessing/Dilate/Dilate.test:BENCHMARK_DILATE/1024
|
-7.51% |
7196.763 |
6656.296 |
38.549 |
-6.39% |
38.549 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_DEL_DOT_VEC_2D_RAW/0
|
-7.45% |
1795.489 |
1661.810 |
7.791 |
-7.72% |
7.791 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_xor_no_runtime_checks_needed<16, int>
|
-7.40% |
16.896 |
15.645 |
0.001 |
-7.41% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_HYDRO_1D_LAMBDA/5001
|
-7.36% |
17.164 |
15.901 |
0.362 |
-7.41% |
0.362 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_HYDRO_2D_LAMBDA/171
|
-7.32% |
88.594 |
82.111 |
0.462 |
-7.38% |
0.462 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_DEL_DOT_VEC_2D_LAMBDA/0
|
-7.30% |
1795.947 |
1664.763 |
0.908 |
-7.10% |
0.908 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_INT_PREDICT_RAW/5001
|
-7.29% |
983.405 |
911.728 |
2.508 |
-0.19% |
2.508 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIND_FIRST_MIN_RAW/171
|
-7.23% |
1.497 |
1.389 |
0.000 |
-7.19% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC128
|
-7.23% |
173.337 |
160.813 |
0.002 |
-7.22% |
0.002 |
|
MultiSource/Applications/lambda-0.1.3/lambda
Profile
|
-7.22% |
15.872 |
14.726 |
0.003 |
-7.21% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint8_t>/127
|
-7.20% |
138.912 |
128.904 |
0.003 |
-7.21% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC7
|
-7.08% |
70.707 |
65.700 |
0.002 |
-7.09% |
0.002 |
|
SingleSource/Benchmarks/Misc/oourafft
Profile
|
-7.05% |
15.396 |
14.310 |
0.144 |
-5.19% |
0.144 |
|
SingleSource/Benchmarks/Misc/pi
Profile
|
-7.01% |
1.782 |
1.657 |
0.000 |
-7.01% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC15
|
-6.94% |
45.050 |
41.923 |
0.011 |
-6.94% |
0.011 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_HYDRO_2D_RAW/171
|
-6.93% |
88.672 |
82.528 |
0.223 |
-6.88% |
0.223 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC15
|
-6.89% |
54.439 |
50.690 |
0.001 |
-6.89% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint64_t_To_uint32_t_
|
-6.84% |
18524.752 |
17257.363 |
125.977 |
-3.12% |
125.977 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC31
|
-6.72% |
74.460 |
69.457 |
0.001 |
-6.72% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint64_t_To_uint16_t_
|
-6.70% |
18808.029 |
17547.154 |
139.454 |
-7.57% |
139.454 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC63
|
-6.56% |
114.512 |
107.003 |
0.086 |
-6.56% |
0.086 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_xor_runtime_checks_pass<16, int>
|
-6.52% |
28.784 |
26.906 |
0.001 |
-6.52% |
0.001 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_xor_runtime_checks_fail<16, int>
|
-6.52% |
28.786 |
26.909 |
0.002 |
-6.51% |
0.002 |
|
SingleSource/Benchmarks/Misc/flops-6
Profile
|
-6.50% |
1.312 |
1.227 |
0.001 |
-6.51% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC31
|
-6.44% |
914.202 |
855.294 |
16.597 |
-6.73% |
16.597 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC127
|
-6.41% |
68.833 |
64.418 |
0.012 |
-5.67% |
0.012 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC128
|
-6.38% |
68.825 |
64.435 |
0.010 |
-6.35% |
0.010 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC15
|
-6.35% |
39.418 |
36.917 |
0.002 |
-6.36% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint16_t>/127
|
-6.30% |
138.906 |
130.159 |
0.005 |
-6.30% |
0.005 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_BAND_LIN_EQ_LAMBDA/5001
|
-6.28% |
21.493 |
20.144 |
0.204 |
-3.15% |
0.204 |
|
External/SPEC/CFP2017rate/538.imagick_r/538.imagick_r
Profile
|
-6.27% |
292.387 |
274.053 |
0.526 |
-6.17% |
0.526 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC63
|
-6.26% |
74.092 |
69.451 |
0.005 |
-6.43% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_only_autovec_int32_t_
|
-6.26% |
180845.688 |
169530.868 |
111.803 |
-6.40% |
111.803 |
|
SingleSource/Benchmarks/Misc-C++/Large/sphereflake
Profile
|
-6.25% |
20.015 |
18.764 |
0.005 |
-6.19% |
0.005 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_runtime_checks_fail<4, int>
|
-6.23% |
16.350 |
15.331 |
0.002 |
-3.63% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC127
|
-6.16% |
194.616 |
182.629 |
0.111 |
-6.16% |
0.111 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC16
|
-6.15% |
40.670 |
38.169 |
0.001 |
-6.16% |
0.001 |
|
MultiSource/Benchmarks/MiBench/telecomm-gsm/telecomm-gsm
Profile
|
-6.00% |
0.663 |
0.623 |
0.001 |
-6.09% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint8_t>/65
|
-5.92% |
95.118 |
89.484 |
0.001 |
-5.92% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIND_FIRST_MIN_RAW/5001
|
-5.89% |
45.272 |
42.603 |
0.070 |
-6.03% |
0.070 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint32_t>/127
|
-5.88% |
138.284 |
130.159 |
0.004 |
-5.88% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC16
|
-5.83% |
31.894 |
30.036 |
0.019 |
-4.01% |
0.019 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_PRESSURE_CALC_LAMBDA/5001
|
-5.81% |
44.788 |
42.185 |
0.584 |
-4.07% |
0.584 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint32_t_To_uint64_t_
|
-5.68% |
21403.558 |
20187.312 |
93.748 |
-5.89% |
93.748 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC16
|
-5.66% |
33.161 |
31.286 |
0.002 |
-5.66% |
0.002 |
|
MultiSource/Benchmarks/SciMark2-C/scimark2
Profile
|
-5.64% |
107.764 |
101.688 |
0.035 |
-5.53% |
0.035 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC32
|
-5.63% |
44.425 |
41.925 |
0.001 |
-5.64% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC32
|
-5.63% |
44.425 |
41.926 |
0.001 |
-5.63% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC31
|
-5.58% |
45.064 |
42.549 |
0.001 |
-5.58% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC31
|
-5.56% |
45.053 |
42.548 |
0.001 |
-5.56% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint8_t_To_uint16_t_
|
-5.55% |
3631.255 |
3429.723 |
7.276 |
-5.60% |
7.276 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C++/miniFE/miniFE
Profile
|
-5.55% |
15.818 |
14.940 |
0.080 |
-6.44% |
0.080 |
|
MultiSource/Benchmarks/TSVC/ControlLoops-dbl/ControlLoops-dbl
Profile
|
-5.54% |
11.312 |
10.685 |
0.091 |
-3.03% |
0.091 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_PIC_2D_LAMBDA/171
|
-5.49% |
13.526 |
12.783 |
0.049 |
-5.29% |
0.049 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC127
|
-5.46% |
3122.280 |
2951.689 |
51.541 |
-5.66% |
51.541 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC128
|
-5.44% |
2969.248 |
2807.801 |
48.689 |
-5.60% |
48.689 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint32_t>/999
|
-5.38% |
696.511 |
659.015 |
0.003 |
-5.38% |
0.003 |
|
SingleSource/Benchmarks/Polybench/stencils/jacobi-2d/jacobi-2d
Profile
|
-5.36% |
32.224 |
30.497 |
0.086 |
-5.36% |
0.086 |
|
SingleSource/Benchmarks/Stanford/Puzzle
Profile
|
-5.33% |
0.241 |
0.229 |
0.004 |
-5.27% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC7
|
-5.31% |
70.710 |
66.953 |
0.001 |
-5.32% |
0.001 |
|
MultiSource/Benchmarks/Rodinia/hotspot/hotspot
Profile
|
-5.30% |
2.035 |
1.927 |
0.004 |
-5.34% |
0.004 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_ENERGY_CALC_RAW/5001
|
-5.29% |
439.612 |
416.364 |
8.899 |
-2.89% |
8.899 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopWithReductionTC1
|
-5.27% |
11.889 |
11.263 |
0.000 |
-5.26% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint32_t>/999
|
-5.23% |
1365.036 |
1293.683 |
0.057 |
-5.23% |
0.057 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIND_FIRST_MIN_RAW/44217
|
-5.18% |
389.395 |
369.241 |
0.106 |
-5.22% |
0.106 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC31
|
-5.13% |
24.404 |
23.151 |
0.001 |
-5.13% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_BAND_LIN_EQ_RAW/5001
|
-5.13% |
21.302 |
20.208 |
0.167 |
-2.01% |
0.167 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC32
|
-5.13% |
24.405 |
23.152 |
0.001 |
-5.14% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC31
|
-5.13% |
24.405 |
23.152 |
0.002 |
-5.13% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC32
|
-5.13% |
24.404 |
23.153 |
0.001 |
-5.12% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC15
|
-5.12% |
128.278 |
121.707 |
0.003 |
-5.11% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC32
|
-5.10% |
61.320 |
58.192 |
0.002 |
-5.10% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC63
|
-5.07% |
43.790 |
41.568 |
0.065 |
-3.99% |
0.065 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC31
|
-5.05% |
241.208 |
229.024 |
0.014 |
-5.06% |
0.014 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_PIC_2D_RAW/171
|
-5.05% |
13.528 |
12.845 |
0.058 |
-5.13% |
0.058 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint32_t>/256
|
-4.81% |
364.175 |
346.663 |
0.009 |
-4.81% |
0.009 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint8_t_To_uint64_t_
|
-4.75% |
23539.781 |
22421.885 |
47.182 |
-4.52% |
47.182 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIRST_SUM_RAW/5001
|
-4.74% |
18.353 |
17.483 |
0.265 |
0.79% |
0.265 |
|
SingleSource/Benchmarks/Misc/revertBits
Profile
|
-4.74% |
0.641 |
0.611 |
0.000 |
-4.71% |
0.000 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_runtime_checks_pass<16, int>
|
-4.60% |
54.437 |
51.935 |
0.003 |
-4.60% |
0.003 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_runtime_checks_fail<16, int>
|
-4.60% |
54.438 |
51.936 |
0.003 |
-4.60% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint16_t>/65
|
-4.59% |
95.106 |
90.738 |
0.007 |
-4.60% |
0.007 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC63
|
-4.53% |
1639.582 |
1565.288 |
26.930 |
-4.77% |
26.930 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopWithReductionTC2
|
-4.50% |
13.766 |
13.146 |
0.010 |
-4.50% |
0.010 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC31
|
-4.47% |
70.087 |
66.954 |
0.003 |
-4.46% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC63
|
-4.45% |
1732.633 |
1655.473 |
23.240 |
-4.70% |
23.240 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC1
|
-4.36% |
14.394 |
13.767 |
0.001 |
-4.35% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC3
|
-4.35% |
14.392 |
13.765 |
0.001 |
-4.36% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC8
|
-4.35% |
14.392 |
13.765 |
0.000 |
-4.36% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC8
|
-4.35% |
14.392 |
13.766 |
0.001 |
-4.35% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC2
|
-4.35% |
14.392 |
13.766 |
0.001 |
-4.35% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC16
|
-4.35% |
14.392 |
13.766 |
0.143 |
-4.36% |
0.143 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC4
|
-4.35% |
14.391 |
13.765 |
0.001 |
-4.36% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC15
|
-4.35% |
14.392 |
13.766 |
0.001 |
-4.35% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC1
|
-4.35% |
14.392 |
13.766 |
0.001 |
-4.34% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC2
|
-4.35% |
14.392 |
13.767 |
0.000 |
-4.34% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC4
|
-4.35% |
14.392 |
13.766 |
0.000 |
-4.35% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC7
|
-4.35% |
14.392 |
13.767 |
0.001 |
-4.35% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC7
|
-4.35% |
14.391 |
13.766 |
0.000 |
-4.35% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC15
|
-4.34% |
14.391 |
13.766 |
0.001 |
-4.35% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC16
|
-4.34% |
14.391 |
13.766 |
0.000 |
-4.35% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC3
|
-4.34% |
14.391 |
13.767 |
0.000 |
-4.34% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_nested_cond_load_novec_int32_t_
|
-4.31% |
649898.525 |
621879.780 |
394.636 |
-3.61% |
394.636 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_ENERGY_CALC_LAMBDA/171
|
-4.27% |
14.193 |
13.587 |
0.018 |
-4.64% |
0.018 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint64_t>/999
|
-4.24% |
1810.927 |
1734.165 |
0.070 |
-4.26% |
0.070 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_ENERGY_CALC_RAW/171
|
-4.23% |
14.207 |
13.606 |
0.014 |
-4.46% |
0.014 |
|
MicroBenchmarks/LCALS/SubsetBLambdaLoops/lcalsBLambda.test:BM_MULADDSUB_LAMBDA/171
|
-4.16% |
0.432 |
0.414 |
0.003 |
-0.94% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint64_t>/999
|
-4.16% |
3594.841 |
3445.355 |
0.256 |
-4.15% |
0.256 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint64_t_To_uint32_t_
|
-4.11% |
19355.916 |
18560.309 |
86.675 |
-3.79% |
86.675 |
|
SingleSource/Benchmarks/Misc/flops-5
Profile
|
-4.10% |
2.021 |
1.938 |
0.000 |
-4.11% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint64_t>/256
|
-4.09% |
935.508 |
897.282 |
0.053 |
-4.09% |
0.053 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC31
|
-4.03% |
61.948 |
59.449 |
0.002 |
-4.03% |
0.002 |
|
External/SPEC/CFP2017rate/519.lbm_r/519.lbm_r
Profile
|
-4.02% |
199.954 |
191.910 |
1.473 |
-4.37% |
1.473 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint32_t_To_uint16_t_
|
-4.02% |
9877.414 |
9480.168 |
26.585 |
-4.05% |
26.585 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_only_autovec_uint8_t_
|
-3.98% |
96159.254 |
92331.448 |
5.812 |
-3.98% |
5.812 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC32
|
-3.96% |
63.203 |
60.698 |
0.001 |
-3.95% |
0.001 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_FLOYD_DITHER/256
|
-3.96% |
1800.194 |
1728.891 |
10.868 |
-0.27% |
10.868 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint32_t>/256
|
-3.94% |
221.514 |
212.776 |
0.011 |
-3.94% |
0.011 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint32_t>/65
|
-3.92% |
94.439 |
90.734 |
0.009 |
-3.97% |
0.009 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC3
|
-3.84% |
16.268 |
15.644 |
0.000 |
-3.84% |
0.000 |
|
MultiSource/Benchmarks/TSVC/NodeSplitting-dbl/NodeSplitting-dbl
Profile
|
-3.78% |
26.894 |
25.876 |
0.243 |
-2.04% |
0.243 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_PRESSURE_CALC_LAMBDA/44217
|
-3.72% |
500.410 |
481.776 |
1.034 |
-3.36% |
1.034 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint16_t_To_uint8_t_
|
-3.72% |
2874.657 |
2767.624 |
15.910 |
-3.84% |
15.910 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopTC16
|
-3.71% |
278.035 |
267.714 |
2.678 |
-3.08% |
2.678 |
|
SingleSource/Benchmarks/Shootout/Shootout-matrix
Profile
|
-3.69% |
3.863 |
3.721 |
0.000 |
-3.68% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint64_t>/256
|
-3.65% |
514.369 |
495.588 |
0.047 |
-3.66% |
0.047 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC64
|
-3.60% |
69.458 |
66.958 |
0.001 |
-3.60% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC64
|
-3.60% |
69.452 |
66.954 |
0.012 |
-3.60% |
0.012 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC63
|
-3.59% |
70.094 |
67.579 |
0.003 |
-3.58% |
0.003 |
|
SingleSource/Benchmarks/BenchmarkGame/n-body
Profile
|
-3.58% |
2.731 |
2.633 |
0.000 |
21.69% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC63
|
-3.56% |
70.076 |
67.581 |
0.002 |
-3.57% |
0.002 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<31, EqZero, First>
|
-3.52% |
3340.260 |
3222.745 |
0.152 |
-3.69% |
0.152 |
|
MultiSource/Applications/JM/lencod/lencod
Profile
|
-3.46% |
32.749 |
31.616 |
0.018 |
-2.84% |
0.018 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC64
|
-3.40% |
43.171 |
41.702 |
0.012 |
-3.41% |
0.012 |
|
MultiSource/Benchmarks/nbench/nbench
Profile
|
-3.39% |
6.114 |
5.907 |
0.001 |
-3.59% |
0.001 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<32, EqZero, Last>
|
-3.36% |
7053.050 |
6815.915 |
21.629 |
-3.36% |
21.629 |
|
MicroBenchmarks/ImageProcessing/Dilate/Dilate.test:BENCHMARK_DILATE/256
|
-3.30% |
1062.888 |
1027.865 |
1.860 |
-3.69% |
1.860 |
|
External/SPEC/CFP2017rate/544.nab_r/544.nab_r
Profile
|
-3.23% |
476.157 |
460.786 |
0.006 |
-3.58% |
0.006 |
|
MultiSource/Benchmarks/Rodinia/pathfinder/pathfinder
Profile
|
-3.18% |
1.265 |
1.224 |
0.006 |
-2.65% |
0.006 |
|
SingleSource/Benchmarks/Shootout/Shootout-lists
Profile
|
-3.16% |
11.316 |
10.959 |
0.010 |
-3.13% |
0.010 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint16_t_To_uint8_t_
|
-3.16% |
4513.358 |
4370.950 |
8.480 |
-3.24% |
8.480 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint16_t>/999
|
-3.15% |
514.969 |
498.749 |
0.012 |
-3.16% |
0.012 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1BigLoopWithReductionTC1
|
-3.13% |
20.025 |
19.398 |
0.001 |
-3.13% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetBLambdaLoops/lcalsBLambda.test:BM_INIT3_LAMBDA/171
|
-3.12% |
0.431 |
0.417 |
0.002 |
-2.20% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC31
|
-3.12% |
60.070 |
58.194 |
0.003 |
-3.45% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchVecWithRuntimeChecks4PointersDBeforeA/1000
|
-3.08% |
5020141.777 |
4865416.931 |
418.493 |
-3.08% |
418.493 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint8_t>/16
|
-3.00% |
60.052 |
58.253 |
0.471 |
8.24% |
0.471 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC32
|
-2.96% |
31.287 |
30.361 |
0.047 |
-2.96% |
0.047 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC64
|
-2.92% |
111.389 |
108.131 |
0.058 |
-2.92% |
0.058 |
|
MultiSource/Benchmarks/Olden/health/health
Profile
|
-2.92% |
1.598 |
1.551 |
0.004 |
-2.54% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint16_t>/999
|
-2.85% |
1013.793 |
984.905 |
0.079 |
-2.86% |
0.079 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_ENERGY_CALC_LAMBDA/44217
|
-2.79% |
4339.935 |
4218.705 |
30.275 |
-2.44% |
30.275 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC1
|
-2.78% |
22.526 |
21.901 |
0.001 |
-2.77% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC1
|
-2.77% |
22.527 |
21.902 |
0.001 |
-2.77% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC31
|
-2.77% |
93.312 |
90.731 |
0.101 |
-3.33% |
0.101 |
|
MultiSource/Benchmarks/FreeBench/mason/mason
Profile
|
-2.69% |
0.553 |
0.538 |
0.000 |
-2.67% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_PRESSURE_CALC_RAW/44217
|
-2.65% |
493.578 |
480.484 |
2.893 |
-4.32% |
2.893 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint64_t_To_uint8_t_
|
-2.64% |
19767.280 |
19244.488 |
23.784 |
-3.01% |
23.784 |
|
MultiSource/Benchmarks/mafft/pairlocalalign
Profile
|
-2.63% |
94.147 |
91.670 |
0.305 |
-2.54% |
0.305 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_FLOYD_DITHER/128
|
-2.62% |
438.996 |
427.487 |
2.963 |
-2.73% |
2.963 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC63
|
-2.61% |
120.148 |
117.009 |
0.010 |
-2.61% |
0.010 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C/CoMD/CoMD
Profile
|
-2.57% |
9.893 |
9.639 |
0.007 |
-2.63% |
0.007 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<32, EqZero, None>
|
-2.57% |
4444.981 |
4330.699 |
41.540 |
-1.83% |
41.540 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_ADI_LAMBDA/5001
|
-2.57% |
2182.931 |
2126.907 |
19.656 |
-4.83% |
19.656 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint8_t>/10
|
-2.56% |
48.805 |
47.557 |
0.016 |
2.47% |
0.016 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_FLOYD_DITHER/512
|
-2.54% |
6662.192 |
6492.875 |
10.737 |
-2.29% |
10.737 |
|
SingleSource/Benchmarks/Misc-C++/oopack_v1p8
Profile
|
-2.54% |
0.480 |
0.468 |
0.000 |
-9.88% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC31
|
-2.52% |
31.255 |
30.467 |
0.012 |
-2.32% |
0.012 |
|
MultiSource/Benchmarks/FreeBench/fourinarow/fourinarow
Profile
|
-2.51% |
0.651 |
0.634 |
0.001 |
-2.52% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint8_t_To_uint32_t_
|
-2.51% |
7078.378 |
6900.915 |
0.406 |
-2.49% |
0.406 |
|
MultiSource/Benchmarks/sim/sim
Profile
|
-2.47% |
9.701 |
9.462 |
0.029 |
-2.46% |
0.029 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchVecWithRuntimeChecks4PointersDBeforeA/32
|
-2.45% |
166189.320 |
162118.108 |
15.805 |
-2.46% |
15.805 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint16_t_To_uint32_t_
|
-2.41% |
11316.385 |
11043.979 |
31.233 |
-2.63% |
31.233 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC32
|
-2.40% |
50.008 |
48.809 |
0.222 |
-2.48% |
0.222 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_only_autovec_int64_t_
|
-2.38% |
1447896.561 |
1413497.465 |
1275.471 |
-2.31% |
1275.471 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC63
|
-2.34% |
106.993 |
104.495 |
0.005 |
-2.34% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC64
|
-2.31% |
108.253 |
105.750 |
0.002 |
-2.31% |
0.002 |
|
MultiSource/Applications/ClamAV/clamscan
Profile
|
-2.30% |
0.493 |
0.482 |
0.002 |
-1.58% |
0.002 |
|
SingleSource/Benchmarks/BenchmarkGame/puzzle
Profile
|
-2.29% |
0.870 |
0.850 |
0.003 |
-2.13% |
0.003 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<64, GreaterThanZero, Mid>
|
-2.27% |
2746.405 |
2683.960 |
15.670 |
-2.25% |
15.670 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, LessThanZero, None>
|
-2.22% |
37325.096 |
36495.529 |
30.484 |
-2.88% |
30.484 |
|
MultiSource/Applications/sgefa/sgefa
Profile
|
-2.19% |
0.578 |
0.565 |
0.004 |
-1.44% |
0.004 |
|
SingleSource/Benchmarks/Misc/flops-1
Profile
|
-2.17% |
9.001 |
8.806 |
0.000 |
-2.15% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_ENERGY_CALC_LAMBDA/5001
|
-2.13% |
431.556 |
422.379 |
0.441 |
-3.58% |
0.441 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<16, GreaterThanZero, First>
|
-2.11% |
8548.717 |
8368.581 |
52.194 |
-1.50% |
52.194 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint32_t>/10
|
-2.10% |
47.295 |
46.302 |
0.011 |
-0.00% |
0.011 |
|
SingleSource/Benchmarks/Misc-C++/Large/ray
Profile
|
-2.10% |
12.104 |
11.850 |
0.002 |
-2.07% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC128
|
-2.09% |
119.520 |
117.018 |
0.002 |
-2.10% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC127
|
-2.09% |
120.147 |
117.635 |
0.008 |
-2.08% |
0.008 |
|
MultiSource/Benchmarks/tramp3d-v4/tramp3d-v4
Profile
|
-2.09% |
1.074 |
1.051 |
0.003 |
-2.25% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC127
|
-2.09% |
120.143 |
117.636 |
0.003 |
-2.09% |
0.003 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C/SimpleMOC/SimpleMOC
Profile
|
-2.09% |
10.409 |
10.192 |
0.068 |
-2.05% |
0.068 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC128
|
-2.08% |
119.505 |
117.018 |
0.004 |
-2.09% |
0.004 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<64, EqZero, Mid>
|
-2.06% |
2747.147 |
2690.678 |
9.761 |
-1.95% |
9.761 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint32_t_To_uint64_t_
|
-2.04% |
26323.170 |
25784.885 |
48.911 |
-1.89% |
48.911 |
|
External/SPEC/CINT2017rate/531.deepsjeng_r/531.deepsjeng_r
Profile
|
-2.02% |
260.560 |
255.285 |
0.354 |
-1.86% |
0.354 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<31, GreaterThanZero, Last>
|
-1.99% |
8263.975 |
8099.121 |
16.909 |
-2.37% |
16.909 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<16, EqZero, None>
|
-1.96% |
8178.311 |
8017.882 |
33.763 |
-1.95% |
33.763 |
|
SingleSource/Benchmarks/Misc/ReedSolomon
Profile
|
-1.96% |
20.821 |
20.412 |
0.002 |
-1.85% |
0.002 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_EOS_LAMBDA/171
|
-1.88% |
0.872 |
0.856 |
0.001 |
-1.73% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint16_t>/256
|
-1.84% |
272.825 |
267.801 |
0.016 |
-1.85% |
0.016 |
|
MultiSource/Benchmarks/Fhourstones-3.1/fhourstones3.1
Profile
|
-1.79% |
3.987 |
3.915 |
0.006 |
-1.41% |
0.006 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_EOS_RAW/171
|
-1.78% |
0.872 |
0.857 |
0.000 |
-1.65% |
0.000 |
|
MicroBenchmarks/ImageProcessing/Dilate/Dilate.test:BENCHMARK_DILATE/512
|
-1.75% |
3551.171 |
3489.176 |
15.509 |
-2.65% |
15.509 |
|
MultiSource/Benchmarks/Bullet/bullet
Profile
|
-1.70% |
30.402 |
29.884 |
0.170 |
-1.80% |
0.170 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_csa_with_in_loop_arith_novec_int64_t_
|
-1.70% |
1029500.118 |
1012018.868 |
1017.682 |
-1.57% |
1017.682 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint8_t>/10
|
-1.68% |
66.828 |
65.702 |
0.003 |
6.43% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint64_t>/51
|
-1.68% |
148.302 |
145.807 |
0.001 |
-1.69% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_INT_PREDICT_RAW/171
|
-1.68% |
6.919 |
6.802 |
0.006 |
-1.76% |
0.006 |
|
MultiSource/Benchmarks/VersaBench/ecbdes/ecbdes
Profile
|
-1.64% |
5.141 |
5.057 |
0.001 |
-1.60% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_INT_PREDICT_LAMBDA/171
|
-1.60% |
6.926 |
6.815 |
0.007 |
-1.59% |
0.007 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_nested_cond_load_novec_uint8_t_
|
-1.59% |
504571.719 |
496553.524 |
115.295 |
-1.62% |
115.295 |
|
SingleSource/Benchmarks/Misc/mandel-2
Profile
|
-1.58% |
2.535 |
2.495 |
0.000 |
-1.56% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC128
|
-1.51% |
211.511 |
208.316 |
0.031 |
-1.51% |
0.031 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<6, LessThanZero, Mid>
|
-1.49% |
23845.560 |
23490.411 |
16.841 |
-0.32% |
16.841 |
|
External/SPEC/CINT2017rate/525.x264_r/525.x264_r
Profile
|
-1.43% |
129.899 |
128.036 |
0.256 |
-1.09% |
0.256 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<32, LessThanZero, Mid>
|
-1.41% |
4571.240 |
4506.917 |
23.543 |
-1.40% |
23.543 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC127
|
-1.40% |
220.265 |
217.183 |
0.079 |
-1.40% |
0.079 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC63
|
-1.40% |
130.150 |
128.334 |
0.094 |
-1.41% |
0.094 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint64_t>/51
|
-1.37% |
229.014 |
225.886 |
0.012 |
-1.36% |
0.012 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<3, GreaterThanZero, None>
|
-1.36% |
44998.078 |
44388.041 |
119.863 |
-1.67% |
119.863 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_csa_with_cond_arith_autovec_int64_t_
|
-1.35% |
745431.265 |
735393.834 |
243.643 |
-1.28% |
243.643 |
|
External/SPEC/CFP2017rate/511.povray_r/511.povray_r
Profile
|
-1.28% |
33.916 |
33.482 |
0.072 |
-0.90% |
0.072 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC127
|
-1.27% |
197.105 |
194.609 |
0.006 |
-1.26% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC128
|
-1.26% |
198.351 |
195.858 |
0.004 |
-1.27% |
0.004 |
|
MultiSource/Benchmarks/MallocBench/cfrac/cfrac
Profile
|
-1.24% |
2.780 |
2.745 |
0.000 |
-1.25% |
0.000 |
|
MultiSource/Applications/obsequi/Obsequi
Profile
|
-1.22% |
7.693 |
7.599 |
0.006 |
-0.81% |
0.006 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<16, LessThanZero, Last>
|
-1.21% |
13146.840 |
12987.372 |
2.919 |
-1.18% |
2.919 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint8_t>/16
|
-1.16% |
85.468 |
84.477 |
0.003 |
11.82% |
0.003 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C++/PENNANT/PENNANT
Profile
|
-1.14% |
4.797 |
4.742 |
0.017 |
-1.55% |
0.017 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<64, EqZero, None>
|
-1.14% |
2928.091 |
2894.849 |
12.812 |
-1.18% |
12.812 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<6, GreaterThanZero, None>
|
-1.12% |
29721.295 |
29387.652 |
7.518 |
-0.65% |
7.518 |
|
SingleSource/Benchmarks/SmallPT/smallpt
Profile
|
-1.12% |
30.042 |
29.706 |
0.003 |
-1.08% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_sinhf_novec_float_
|
-1.11% |
2242.194 |
2217.208 |
0.438 |
-1.10% |
0.438 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<3, EqZero, Mid>
|
-1.11% |
37579.598 |
37161.726 |
3.278 |
-1.16% |
3.278 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint8_t_To_uint32_t_
|
-1.07% |
12064.707 |
11935.981 |
17.443 |
-1.54% |
17.443 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_sinhf_autovec_float_
|
-1.05% |
2241.293 |
2217.727 |
0.317 |
-1.11% |
0.317 |
|
External/SPEC/CINT2017rate/541.leela_r/541.leela_r
Profile
|
-1.03% |
228.046 |
225.686 |
0.583 |
-1.61% |
0.583 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C++/CLAMR/CLAMR
Profile
|
-1.02% |
12.249 |
12.124 |
0.036 |
-0.73% |
0.036 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, LessThanZero, Mid>
|
-1.01% |
31797.469 |
31475.809 |
42.941 |
-0.96% |
42.941 |