|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_HYDRO_2D_RAW/44217
|
-70.98% |
86961.739 |
25240.144 |
23588.734 |
-70.18% |
23588.734 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_INT_PREDICT_LAMBDA/44217
|
-58.38% |
19111.855 |
7954.607 |
112.874 |
-4.59% |
112.874 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_HYDRO_2D_LAMBDA/44217
|
-53.32% |
95209.827 |
44444.028 |
2737.331 |
-51.12% |
2737.331 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint64_t_To_uint32_t_
|
-51.87% |
35278.610 |
16979.643 |
556.449 |
-51.92% |
556.449 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C/miniGMG/miniGMG
Profile
|
-51.56% |
9.280 |
4.496 |
0.067 |
-51.08% |
0.067 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint64_t_To_uint16_t_
|
-50.48% |
35836.292 |
17745.837 |
195.821 |
-50.26% |
195.821 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint64_t_To_uint8_t_
|
-48.69% |
37006.481 |
18989.724 |
17.680 |
-48.76% |
17.680 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_HYDRO_2D_LAMBDA/5001
|
-48.36% |
9715.675 |
5017.006 |
350.260 |
-44.95% |
350.260 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_INT_PREDICT_LAMBDA/5001
|
-47.54% |
1744.081 |
914.987 |
1.439 |
1.13% |
1.439 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint16_t_To_uint64_t_
|
-44.04% |
18665.888 |
10446.081 |
1.591 |
-44.06% |
1.591 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_DIFF_PREDICT_LAMBDA/44217
|
-43.63% |
23943.608 |
13497.079 |
276.201 |
-41.58% |
276.201 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIRST_DIFF_LAMBDA/44217
|
-43.03% |
175.851 |
100.183 |
1.582 |
-30.82% |
1.582 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_DIFF_PREDICT_RAW/44217
|
-42.08% |
23270.094 |
13478.124 |
319.894 |
-42.15% |
319.894 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_DIFF_PREDICT_RAW/5001
|
-41.29% |
2585.043 |
1517.784 |
30.758 |
-41.05% |
30.758 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint8_t_To_uint64_t_
|
-41.08% |
17836.486 |
10509.004 |
24.430 |
-40.96% |
24.430 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint64_t_To_uint32_t_
|
-40.89% |
38263.450 |
22616.582 |
21.045 |
-40.73% |
21.045 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_DIFF_PREDICT_LAMBDA/5001
|
-39.94% |
2514.167 |
1510.013 |
45.419 |
-39.83% |
45.419 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_HYDRO_2D_RAW/5001
|
-37.92% |
8646.454 |
5367.686 |
1178.872 |
-38.98% |
1178.872 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/32
|
-36.70% |
1396.238 |
883.811 |
0.049 |
-36.70% |
0.049 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/64
|
-36.66% |
6181.407 |
3915.115 |
7.763 |
-36.67% |
7.763 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/16
|
-36.63% |
279.484 |
177.104 |
0.010 |
-36.63% |
0.010 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/256
|
-36.17% |
107098.565 |
68363.012 |
36.589 |
-36.20% |
36.589 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/128
|
-36.09% |
26262.184 |
16783.317 |
6.527 |
-36.12% |
6.527 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint32_t_To_uint64_t_
|
-34.41% |
22421.376 |
14706.615 |
209.764 |
-35.28% |
209.764 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint64_t_To_uint8_t_
|
-34.24% |
30105.212 |
19796.768 |
14.321 |
-34.25% |
14.321 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint64_t_To_uint16_t_
|
-33.87% |
28893.322 |
19107.934 |
30.700 |
-33.99% |
30.700 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_PIC_1D_LAMBDA/44217
|
-32.68% |
13469.249 |
9067.009 |
955.040 |
-32.66% |
955.040 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_DISC_ORD_LAMBDA/44217
|
-32.47% |
14813.373 |
10002.934 |
31.469 |
-28.83% |
31.469 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIRST_DIFF_RAW/44217
|
-32.33% |
146.207 |
98.935 |
2.117 |
-30.57% |
2.117 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, EqZero, None>
|
-31.24% |
20511.751 |
14103.796 |
0.411 |
-31.24% |
0.411 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint64_t_To_uint16_t_
|
-28.88% |
25896.456 |
18417.254 |
55.498 |
-28.88% |
55.498 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC128
|
-27.98% |
1291.861 |
930.448 |
2.682 |
-28.03% |
2.682 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint32_t_To_uint8_t_
|
-27.79% |
13472.382 |
9728.527 |
19.479 |
-27.77% |
19.479 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_PIC_2D_RAW/44217
|
-27.72% |
11926.282 |
8619.795 |
937.689 |
-23.15% |
937.689 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC64
|
-27.32% |
653.571 |
475.038 |
1.270 |
-27.32% |
1.270 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC32
|
-27.12% |
333.996 |
243.404 |
0.752 |
-27.11% |
0.752 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_PIC_2D_LAMBDA/44217
|
-27.05% |
11857.052 |
8649.908 |
5.219 |
-21.10% |
5.219 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC128
|
-26.99% |
558.533 |
407.790 |
0.064 |
-26.86% |
0.064 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_PIC_2D_LAMBDA/5001
|
-26.88% |
1215.689 |
888.867 |
41.991 |
-19.60% |
41.991 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC16
|
-26.48% |
173.781 |
127.757 |
0.466 |
-26.49% |
0.466 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC64
|
-25.65% |
292.090 |
217.162 |
0.023 |
-25.59% |
0.023 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIRST_SUM_LAMBDA/44217
|
-25.05% |
179.683 |
134.668 |
0.839 |
-19.40% |
0.839 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint64_t_To_uint8_t_
|
-24.65% |
27236.355 |
20522.868 |
61.623 |
-24.61% |
61.623 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, EqZero, None>
|
-23.98% |
16024.052 |
12181.128 |
0.380 |
-23.98% |
0.380 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC128
|
-23.21% |
603.962 |
463.774 |
0.063 |
-23.21% |
0.063 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC32
|
-23.17% |
158.830 |
122.025 |
0.081 |
-23.19% |
0.081 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC128
|
-23.10% |
603.910 |
464.421 |
0.018 |
-23.10% |
0.018 |
|
MicroBenchmarks/ImageProcessing/Blur/blur.test:BENCHMARK_boxBlurKernel/1024
|
-22.69% |
30031.732 |
23218.915 |
92.280 |
-22.99% |
92.280 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIRST_SUM_RAW/44217
|
-22.56% |
173.376 |
134.257 |
0.647 |
-19.29% |
0.647 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC64
|
-22.35% |
313.512 |
243.431 |
0.006 |
-22.35% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC127
|
-22.17% |
615.160 |
478.796 |
0.033 |
-22.17% |
0.033 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC64
|
-22.15% |
313.499 |
244.070 |
0.017 |
-22.15% |
0.017 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_PIC_2D_RAW/5001
|
-21.98% |
1176.523 |
917.872 |
29.896 |
-14.88% |
29.896 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC127
|
-21.97% |
615.184 |
480.031 |
0.032 |
-21.97% |
0.032 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint16_t_To_uint64_t_
|
-21.94% |
13274.621 |
10361.961 |
3.980 |
-21.55% |
3.980 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint16_t_To_uint32_t_
|
-21.68% |
7110.264 |
5569.103 |
0.643 |
-21.57% |
0.643 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint8_t_To_uint32_t_
|
-21.43% |
6579.050 |
5169.454 |
4.164 |
-21.46% |
4.164 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIND_FIRST_MIN_LAMBDA/44217
|
-21.37% |
389.691 |
306.428 |
0.550 |
-21.34% |
0.550 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_only_autovec_uint8_t_
|
-21.36% |
182360.369 |
143400.872 |
3.168 |
-21.36% |
3.168 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIND_FIRST_MIN_LAMBDA/171
|
-21.30% |
1.501 |
1.181 |
0.000 |
-21.28% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC32
|
-20.82% |
168.319 |
133.282 |
0.003 |
-20.82% |
0.003 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIND_FIRST_MIN_LAMBDA/5001
|
-20.70% |
45.244 |
35.879 |
0.203 |
-20.72% |
0.203 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC32
|
-20.44% |
168.327 |
133.915 |
0.004 |
-20.45% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC63
|
-20.42% |
324.774 |
258.453 |
0.008 |
-20.42% |
0.008 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC128
|
-20.41% |
273.858 |
217.954 |
0.629 |
-20.67% |
0.629 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC63
|
-20.04% |
324.783 |
259.703 |
0.012 |
-20.04% |
0.012 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC127
|
-19.93% |
273.691 |
219.151 |
0.563 |
-20.44% |
0.563 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC63
|
-19.86% |
151.397 |
121.335 |
2.065 |
-19.06% |
2.065 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC127
|
-19.71% |
640.897 |
514.587 |
0.136 |
-19.66% |
0.136 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC16
|
-19.30% |
92.274 |
74.464 |
0.014 |
-19.31% |
0.014 |
|
MultiSource/Benchmarks/MiBench/automotive-bitcount/automotive-bitcount
Profile
|
-19.23% |
0.125 |
0.101 |
0.000 |
-18.36% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint16_t_To_uint8_t_
|
-19.09% |
3817.754 |
3088.982 |
0.317 |
-19.10% |
0.317 |
|
SingleSource/Benchmarks/Adobe-C++/loop_unroll
Profile
|
-18.89% |
2.982 |
2.419 |
0.003 |
-22.14% |
0.003 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_VOL3D_CALC_RAW/2
|
-18.80% |
8.757 |
7.111 |
0.000 |
-18.80% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_VOL3D_CALC_LAMBDA/2
|
-18.79% |
8.756 |
7.111 |
0.000 |
-18.80% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint64_t_To_uint32_t_
|
-18.77% |
27114.373 |
22026.090 |
33.564 |
-18.58% |
33.564 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC64
|
-18.71% |
148.410 |
120.639 |
0.583 |
-18.83% |
0.583 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint32_t_To_uint16_t_
|
-18.71% |
13823.946 |
11237.942 |
11.084 |
-18.61% |
11.084 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint32_t_To_uint8_t_
|
-18.34% |
13903.459 |
11353.560 |
7.598 |
-18.32% |
7.598 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC16
|
-18.30% |
95.740 |
78.223 |
0.001 |
-18.30% |
0.001 |
|
MicroBenchmarks/ImageProcessing/Dilate/Dilate.test:BENCHMARK_DILATE/128
|
-18.28% |
238.770 |
195.124 |
10.487 |
-14.41% |
10.487 |
|
MultiSource/Benchmarks/Trimaran/enc-pc1/enc-pc1
Profile
|
-18.17% |
1.105 |
0.904 |
0.000 |
-18.13% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_with_cond_arith_novec_uint8_t_
|
-17.86% |
745859.804 |
612661.706 |
79.693 |
-17.85% |
79.693 |
|
MultiSource/Benchmarks/MiBench/security-rijndael/security-rijndael
Profile
|
-17.67% |
0.336 |
0.276 |
0.001 |
-17.42% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC16
|
-17.65% |
95.741 |
78.845 |
0.002 |
-17.65% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC31
|
-17.42% |
179.594 |
148.308 |
0.003 |
-17.42% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_with_cond_arith_novec_int32_t_
|
-17.40% |
740149.052 |
611397.814 |
42.104 |
-17.40% |
42.104 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC128
|
-17.33% |
570.732 |
471.821 |
0.225 |
-17.31% |
0.225 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC4
|
-17.26% |
17.520 |
14.496 |
0.011 |
-17.26% |
0.011 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC64
|
-17.12% |
297.863 |
246.860 |
0.021 |
-17.08% |
0.021 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC32
|
-16.94% |
85.228 |
70.791 |
1.286 |
-17.03% |
1.286 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC32
|
-16.88% |
161.441 |
134.197 |
0.022 |
-16.85% |
0.022 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC31
|
-16.73% |
179.589 |
149.551 |
0.010 |
-16.72% |
0.010 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC16
|
-16.47% |
93.235 |
77.879 |
0.026 |
-16.37% |
0.026 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint8_t_To_uint64_t_
|
-16.44% |
13039.732 |
10895.795 |
13.026 |
-16.60% |
13.026 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_VOL3D_CALC_LAMBDA/0
|
-16.38% |
1266.308 |
1058.933 |
2.327 |
-16.46% |
2.327 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC31
|
-16.33% |
86.170 |
72.101 |
1.821 |
-16.27% |
1.821 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC4
|
-16.17% |
113.635 |
95.260 |
0.538 |
-15.76% |
0.538 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_VOL3D_CALC_LAMBDA/1
|
-16.13% |
260.045 |
218.092 |
0.267 |
-16.17% |
0.267 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_VOL3D_CALC_RAW/0
|
-16.08% |
1266.511 |
1062.845 |
1.702 |
-15.99% |
1.702 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_VOL3D_CALC_RAW/1
|
-16.04% |
260.024 |
218.314 |
0.108 |
-16.07% |
0.108 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_HYDRO_1D_RAW/171
|
-15.98% |
0.442 |
0.372 |
0.000 |
-15.84% |
0.000 |
|
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 |
6293.362 |
0.459 |
-15.66% |
0.459 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIRST_SUM_LAMBDA/5001
|
-15.43% |
20.315 |
17.181 |
0.740 |
-2.42% |
0.740 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC8
|
-15.42% |
58.815 |
49.746 |
0.001 |
-15.35% |
0.001 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, EqZero, First>
|
-15.40% |
16671.444 |
14104.181 |
0.294 |
-15.40% |
0.294 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_no_runtime_checks_needed<16, int>
|
-15.39% |
24.404 |
20.649 |
0.000 |
-15.38% |
0.000 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, EqZero, Mid>
|
-15.38% |
16667.428 |
14104.408 |
0.703 |
-15.37% |
0.703 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, EqZero, Last>
|
-15.35% |
16667.131 |
14109.000 |
0.214 |
-15.35% |
0.214 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint32_t_To_uint8_t_
|
-14.90% |
10623.973 |
9040.487 |
30.296 |
-14.67% |
30.296 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC127
|
-14.81% |
605.796 |
516.048 |
0.019 |
-14.81% |
0.019 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC8
|
-14.73% |
59.443 |
50.685 |
0.002 |
-14.74% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC128
|
-14.57% |
1103.338 |
942.563 |
0.058 |
-14.57% |
0.058 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC127
|
-14.51% |
1095.293 |
936.356 |
0.047 |
-14.51% |
0.047 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC64
|
-14.35% |
562.567 |
481.863 |
0.020 |
-14.31% |
0.020 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC63
|
-14.23% |
554.502 |
475.609 |
2.714 |
-14.26% |
2.714 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint32_t_To_uint8_t_
|
-14.19% |
11094.490 |
9520.110 |
63.770 |
-14.46% |
63.770 |
|
SingleSource/Benchmarks/Misc/salsa20
Profile
|
-14.14% |
15.387 |
13.211 |
0.001 |
-14.13% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint8_t_To_uint16_t_
|
-14.13% |
3757.352 |
3226.556 |
8.900 |
-14.11% |
8.900 |
|
External/SPEC/CFP2017rate/508.namd_r/508.namd_r
Profile
|
-14.00% |
224.503 |
193.068 |
0.194 |
-13.65% |
0.194 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC32
|
-13.92% |
292.232 |
251.548 |
0.018 |
-13.85% |
0.018 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_with_cond_arith_novec_int64_t_
|
-13.90% |
790093.830 |
680242.809 |
1823.691 |
-13.68% |
1823.691 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_with_cond_arith_autovec_int64_t_
|
-13.88% |
790600.261 |
680882.532 |
1300.665 |
-13.99% |
1300.665 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC8
|
-13.86% |
51.939 |
44.740 |
0.003 |
-13.86% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC3
|
-13.86% |
51.940 |
44.741 |
0.001 |
-13.85% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC1
|
-13.86% |
51.936 |
44.740 |
0.002 |
-13.85% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC2
|
-13.85% |
51.933 |
44.739 |
0.004 |
-13.85% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint64_t_To_uint8_t_
|
-13.85% |
22048.907 |
18995.184 |
17.509 |
-13.84% |
17.509 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC4
|
-13.85% |
51.933 |
44.741 |
0.001 |
-13.85% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC7
|
-13.85% |
51.932 |
44.740 |
0.002 |
-13.85% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC8
|
-13.68% |
59.443 |
51.314 |
0.001 |
-13.69% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC31
|
-13.66% |
284.106 |
245.308 |
0.017 |
-13.65% |
0.017 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, EqZero, First>
|
-13.62% |
14102.847 |
12181.453 |
0.508 |
-13.63% |
0.508 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, EqZero, Mid>
|
-13.62% |
14103.266 |
12181.983 |
0.622 |
-13.62% |
0.622 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, EqZero, Last>
|
-13.62% |
14102.686 |
12181.525 |
0.303 |
-13.64% |
0.303 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC8
|
-13.52% |
23.153 |
20.022 |
0.001 |
-13.52% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC63
|
-13.42% |
374.451 |
324.205 |
0.028 |
-13.41% |
0.028 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint32_t_To_uint16_t_
|
-13.37% |
10709.492 |
9277.828 |
228.144 |
-13.59% |
228.144 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint32_t_To_uint16_t_
|
-13.34% |
12816.698 |
11107.472 |
5.879 |
-13.47% |
5.879 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC8
|
-13.16% |
23.779 |
20.649 |
0.001 |
-13.16% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC16
|
-13.14% |
157.044 |
136.413 |
0.006 |
-13.09% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC128
|
-13.08% |
81.349 |
70.707 |
0.012 |
-13.08% |
0.012 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_DISC_ORD_RAW/5001
|
-13.00% |
639.017 |
555.938 |
30.820 |
-16.37% |
30.820 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint8_t_To_uint16_t_
|
-12.96% |
4542.385 |
3953.812 |
0.643 |
-12.95% |
0.643 |
|
MicroBenchmarks/ImageProcessing/Blur/blur.test:BENCHMARK_boxBlurKernel/128
|
-12.90% |
452.817 |
394.404 |
12.217 |
-9.18% |
12.217 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC15
|
-12.87% |
107.012 |
93.243 |
0.001 |
-12.86% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC16
|
-12.74% |
51.941 |
45.324 |
0.296 |
-12.74% |
0.296 |
|
SingleSource/Benchmarks/Shootout-C++/Shootout-C++-matrix
Profile
|
-12.74% |
2.509 |
2.189 |
0.000 |
-12.71% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC63
|
-12.68% |
332.922 |
290.699 |
0.018 |
-12.66% |
0.018 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint32_t_To_uint16_t_
|
-12.66% |
10020.798 |
8752.246 |
90.317 |
-11.64% |
90.317 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC15
|
-12.60% |
148.919 |
130.157 |
0.003 |
-12.53% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint16_t_To_uint8_t_
|
-12.41% |
4742.573 |
4153.903 |
0.515 |
-12.42% |
0.515 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_INT_PREDICT_RAW/44217
|
-12.05% |
9097.614 |
8001.698 |
84.757 |
-11.58% |
84.757 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC8
|
-11.89% |
89.483 |
78.843 |
0.003 |
-11.81% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC2
|
-11.77% |
21.274 |
18.771 |
0.001 |
-11.77% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC15
|
-11.69% |
106.993 |
94.485 |
0.002 |
-11.70% |
0.002 |
|
MicroBenchmarks/ImageProcessing/Dilate/Dilate.test:BENCHMARK_DILATE/1024
|
-11.55% |
7196.763 |
6365.202 |
185.138 |
-10.48% |
185.138 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC15
|
-11.44% |
51.932 |
45.991 |
0.001 |
-11.45% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC16
|
-11.33% |
33.162 |
29.405 |
0.001 |
-11.33% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC4
|
-11.11% |
22.526 |
20.023 |
0.003 |
-11.12% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC3
|
-11.11% |
22.525 |
20.023 |
0.002 |
-11.11% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC4
|
-11.10% |
22.524 |
20.023 |
0.001 |
-11.11% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint8_t>/51
|
-11.10% |
123.890 |
110.134 |
0.436 |
19.06% |
0.436 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC7
|
-10.77% |
81.345 |
72.586 |
0.004 |
-10.73% |
0.004 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_BAND_LIN_EQ_LAMBDA/171
|
-10.60% |
0.384 |
0.343 |
0.000 |
-6.33% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC4
|
-10.60% |
41.296 |
36.918 |
0.001 |
-10.61% |
0.001 |
|
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/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC4
|
-10.53% |
23.778 |
21.275 |
0.001 |
-10.53% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC64
|
-10.47% |
53.815 |
48.182 |
0.001 |
-10.47% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_DIFF_PREDICT_LAMBDA/171
|
-10.24% |
12.380 |
11.111 |
0.086 |
-7.30% |
0.086 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/16
|
-10.18% |
115.476 |
103.722 |
0.036 |
-10.17% |
0.036 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC4
|
-10.10% |
55.686 |
50.060 |
0.001 |
-10.07% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint8_t_To_uint16_t_
|
-10.08% |
5848.523 |
5258.757 |
4.888 |
-10.11% |
4.888 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC7
|
-10.04% |
354.709 |
319.087 |
2.213 |
-10.04% |
2.213 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/64
|
-10.02% |
1913.677 |
1721.910 |
9.474 |
-10.00% |
9.474 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/32
|
-10.00% |
473.031 |
425.749 |
0.006 |
-9.99% |
0.006 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/256
|
-9.96% |
31444.570 |
28313.382 |
27.450 |
-9.97% |
27.450 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/128
|
-9.95% |
7918.118 |
7130.330 |
5.066 |
-9.94% |
5.066 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC8
|
-9.76% |
25.656 |
23.151 |
0.001 |
-9.77% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC8
|
-9.75% |
25.654 |
23.152 |
0.001 |
-9.76% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_only_autovec_int64_t_
|
-9.68% |
333439.355 |
301161.269 |
173.489 |
-9.64% |
173.489 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC7
|
-9.61% |
32.537 |
29.410 |
0.001 |
-9.61% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC7
|
-9.52% |
26.280 |
23.777 |
0.001 |
-9.53% |
0.001 |
|
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 |
48.174 |
0.006 |
-9.44% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC31
|
-9.40% |
196.497 |
178.031 |
0.002 |
-9.39% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC127
|
-9.34% |
101.463 |
91.982 |
0.005 |
-9.71% |
0.005 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIRST_DIFF_LAMBDA/5001
|
-9.32% |
12.965 |
11.756 |
0.366 |
-3.56% |
0.366 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_DEL_DOT_VEC_2D_LAMBDA/1
|
-9.28% |
287.252 |
260.602 |
0.189 |
-9.24% |
0.189 |
|
MultiSource/Benchmarks/FreeBench/pifft/pifft
Profile
|
-9.21% |
0.360 |
0.326 |
0.001 |
-8.99% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_DEL_DOT_VEC_2D_RAW/1
|
-9.20% |
287.166 |
260.737 |
0.075 |
-9.15% |
0.075 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC4
|
-9.09% |
41.298 |
37.543 |
0.001 |
-9.10% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_HYDRO_1D_LAMBDA/5001
|
-8.95% |
17.164 |
15.628 |
0.401 |
-9.00% |
0.401 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC7
|
-8.88% |
28.156 |
25.655 |
0.001 |
-8.90% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_DEL_DOT_VEC_2D_LAMBDA/2
|
-8.72% |
3.510 |
3.204 |
0.000 |
-8.71% |
0.000 |
|
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/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_runtime_checks_pass<4, int>
|
-8.62% |
16.776 |
15.330 |
0.000 |
-8.25% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC16
|
-8.62% |
36.292 |
33.165 |
0.001 |
-8.62% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC8
|
-8.51% |
29.409 |
26.907 |
0.003 |
-8.51% |
0.003 |
|
MultiSource/Benchmarks/McCat/12-IOtest/iotest
Profile
|
-8.45% |
1.833 |
1.678 |
0.016 |
-8.04% |
0.016 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint16_t_To_uint8_t_
|
-8.42% |
6809.374 |
6235.828 |
7.201 |
-8.51% |
7.201 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint8_t>/28
|
-8.25% |
82.592 |
75.782 |
0.216 |
12.12% |
0.216 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC2
|
-8.20% |
38.171 |
35.042 |
0.002 |
-8.20% |
0.002 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_DIFF_PREDICT_RAW/171
|
-8.15% |
12.096 |
11.110 |
0.090 |
-6.89% |
0.090 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC64
|
-8.06% |
93.230 |
85.715 |
0.002 |
-8.07% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint8_t_To_uint32_t_
|
-7.94% |
12790.478 |
11774.640 |
16.680 |
-7.86% |
16.680 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC3
|
-7.90% |
47.557 |
43.800 |
0.001 |
-7.90% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC127
|
-7.86% |
2410.336 |
2220.789 |
5.427 |
-8.48% |
5.427 |
|
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 |
29.410 |
0.000 |
-7.84% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_INT_PREDICT_RAW/5001
|
-7.82% |
983.405 |
906.523 |
9.265 |
-0.76% |
9.265 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC32
|
-7.81% |
40.044 |
36.917 |
0.001 |
-7.82% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_HYDRO_2D_RAW/171
|
-7.78% |
88.672 |
81.774 |
0.622 |
-7.73% |
0.622 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint16_t_To_uint64_t_
|
-7.75% |
20234.112 |
18666.825 |
18.085 |
-7.33% |
18.085 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC15
|
-7.70% |
32.539 |
30.034 |
0.002 |
-7.70% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC15
|
-7.69% |
32.537 |
30.036 |
0.002 |
-7.69% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC8
|
-7.62% |
26.417 |
24.403 |
0.001 |
-9.32% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_DEL_DOT_VEC_2D_LAMBDA/0
|
-7.61% |
1795.947 |
1659.238 |
3.205 |
-7.41% |
3.205 |
|
MultiSource/Benchmarks/VersaBench/beamformer/beamformer
Profile
|
-7.59% |
5.202 |
4.807 |
0.001 |
-7.56% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_DEL_DOT_VEC_2D_RAW/0
|
-7.56% |
1795.489 |
1659.717 |
3.867 |
-7.84% |
3.867 |
|
MultiSource/Benchmarks/Trimaran/enc-md5/enc-md5
Profile
|
-7.50% |
3.506 |
3.243 |
0.000 |
-7.48% |
0.000 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_xor_no_runtime_checks_needed<16, int>
|
-7.42% |
16.896 |
15.643 |
0.001 |
-7.42% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC1
|
-7.41% |
88.978 |
82.382 |
0.383 |
-7.42% |
0.383 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_HYDRO_2D_LAMBDA/171
|
-7.31% |
88.594 |
82.122 |
0.131 |
-7.37% |
0.131 |
|
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
|
-7.22% |
173.337 |
160.817 |
0.003 |
-7.22% |
0.003 |
|
MultiSource/Applications/lambda-0.1.3/lambda
Profile
|
-7.21% |
15.872 |
14.728 |
0.011 |
-7.19% |
0.011 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint8_t>/127
|
-7.20% |
138.912 |
128.904 |
0.008 |
-7.21% |
0.008 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC7
|
-7.07% |
70.707 |
65.706 |
0.005 |
-7.08% |
0.005 |
|
SingleSource/Benchmarks/Polybench/stencils/jacobi-2d/jacobi-2d
Profile
|
-7.03% |
32.224 |
29.958 |
0.277 |
-7.03% |
0.277 |
|
SingleSource/Benchmarks/Misc/pi
Profile
|
-7.03% |
1.782 |
1.657 |
0.000 |
-7.03% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint16_t_To_uint64_t_
|
-7.01% |
25022.625 |
23268.565 |
23.945 |
-6.87% |
23.945 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC15
|
-6.93% |
45.050 |
41.927 |
0.053 |
-6.94% |
0.053 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC15
|
-6.89% |
54.439 |
50.686 |
0.001 |
-6.90% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC31
|
-6.72% |
74.460 |
69.455 |
0.005 |
-6.73% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC128
|
-6.58% |
68.825 |
64.295 |
0.052 |
-6.55% |
0.052 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC63
|
-6.55% |
114.512 |
107.015 |
0.204 |
-6.55% |
0.204 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_xor_runtime_checks_fail<16, int>
|
-6.52% |
28.786 |
26.907 |
0.001 |
-6.52% |
0.001 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_xor_runtime_checks_pass<16, int>
|
-6.52% |
28.784 |
26.907 |
0.001 |
-6.52% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC31
|
-6.45% |
914.202 |
855.199 |
4.586 |
-6.74% |
4.586 |
|
SingleSource/Benchmarks/Misc/flops-6
Profile
|
-6.45% |
1.312 |
1.228 |
0.000 |
-6.47% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIND_FIRST_MIN_RAW/5001
|
-6.40% |
45.272 |
42.376 |
0.214 |
-6.54% |
0.214 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC127
|
-6.39% |
194.616 |
182.180 |
0.205 |
-6.39% |
0.205 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC127
|
-6.38% |
68.833 |
64.440 |
0.007 |
-5.64% |
0.007 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC15
|
-6.34% |
39.418 |
36.919 |
0.002 |
-6.35% |
0.002 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_BAND_LIN_EQ_LAMBDA/5001
|
-6.31% |
21.493 |
20.138 |
0.084 |
-3.18% |
0.084 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint16_t>/127
|
-6.30% |
138.906 |
130.149 |
0.006 |
-6.31% |
0.006 |
|
SingleSource/Benchmarks/Misc/oourafft
Profile
|
-6.28% |
15.396 |
14.428 |
0.108 |
-4.41% |
0.108 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC63
|
-6.26% |
74.092 |
69.455 |
0.010 |
-6.42% |
0.010 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_only_autovec_int32_t_
|
-6.26% |
180845.688 |
169530.770 |
129.924 |
-6.40% |
129.924 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_runtime_checks_fail<4, int>
|
-6.24% |
16.350 |
15.330 |
0.001 |
-3.64% |
0.001 |
|
SingleSource/Benchmarks/Misc-C++/Large/sphereflake
Profile
|
-6.23% |
20.015 |
18.768 |
0.003 |
-6.17% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC16
|
-6.15% |
40.670 |
38.169 |
0.001 |
-6.16% |
0.001 |
|
External/SPEC/CFP2017rate/538.imagick_r/538.imagick_r
Profile
|
-5.94% |
292.387 |
275.012 |
0.217 |
-5.84% |
0.217 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint8_t>/65
|
-5.93% |
95.118 |
89.481 |
0.004 |
-5.92% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint32_t>/127
|
-5.88% |
138.284 |
130.148 |
0.004 |
-5.88% |
0.004 |
|
MultiSource/Benchmarks/MiBench/telecomm-gsm/telecomm-gsm
Profile
|
-5.83% |
0.663 |
0.624 |
0.000 |
-5.92% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC16
|
-5.83% |
31.894 |
30.035 |
0.230 |
-4.01% |
0.230 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_PIC_2D_LAMBDA/171
|
-5.68% |
13.526 |
12.757 |
0.060 |
-5.49% |
0.060 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC16
|
-5.65% |
33.161 |
31.287 |
0.005 |
-5.66% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC32
|
-5.63% |
44.425 |
41.922 |
0.001 |
-5.64% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC32
|
-5.63% |
44.425 |
41.924 |
0.001 |
-5.64% |
0.001 |
|
MultiSource/Benchmarks/SciMark2-C/scimark2
Profile
|
-5.62% |
107.764 |
101.713 |
0.034 |
-5.51% |
0.034 |
|
SingleSource/Benchmarks/Stanford/Puzzle
Profile
|
-5.59% |
0.241 |
0.228 |
0.001 |
-5.53% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC31
|
-5.58% |
45.064 |
42.549 |
0.003 |
-5.58% |
0.003 |
|
MultiSource/Benchmarks/TSVC/ControlLoops-dbl/ControlLoops-dbl
Profile
|
-5.57% |
11.312 |
10.681 |
0.082 |
-3.06% |
0.082 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC31
|
-5.56% |
45.053 |
42.550 |
0.001 |
-5.56% |
0.001 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C++/miniFE/miniFE
Profile
|
-5.55% |
15.818 |
14.940 |
0.102 |
-6.44% |
0.102 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC127
|
-5.44% |
3122.280 |
2952.333 |
17.037 |
-5.64% |
17.037 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopFrom_uint32_t_To_uint16_t_
|
-5.43% |
7967.524 |
7534.660 |
82.660 |
1.13% |
82.660 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC128
|
-5.41% |
2969.248 |
2808.698 |
15.953 |
-5.57% |
15.953 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint32_t>/999
|
-5.39% |
696.511 |
658.937 |
0.021 |
-5.40% |
0.021 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIND_FIRST_MIN_RAW/44217
|
-5.38% |
389.395 |
368.442 |
0.077 |
-5.43% |
0.077 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint8_t_To_uint16_t_
|
-5.37% |
3631.255 |
3436.230 |
0.823 |
-5.43% |
0.823 |
|
MultiSource/Benchmarks/Rodinia/hotspot/hotspot
Profile
|
-5.32% |
2.035 |
1.927 |
0.011 |
-5.36% |
0.011 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC7
|
-5.31% |
70.710 |
66.954 |
0.005 |
-5.32% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopWithReductionTC1
|
-5.26% |
11.889 |
11.263 |
0.000 |
-5.26% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint32_t>/999
|
-5.22% |
1365.036 |
1293.742 |
0.015 |
-5.22% |
0.015 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC31
|
-5.14% |
24.405 |
23.151 |
0.010 |
-5.13% |
0.010 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC32
|
-5.13% |
24.405 |
23.152 |
0.000 |
-5.14% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC32
|
-5.13% |
24.404 |
23.152 |
0.004 |
-5.12% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC31
|
-5.13% |
24.404 |
23.153 |
0.000 |
-5.13% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC15
|
-5.12% |
128.278 |
121.706 |
0.004 |
-5.11% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC32
|
-5.10% |
61.320 |
58.194 |
0.001 |
-5.10% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_BAND_LIN_EQ_RAW/5001
|
-5.05% |
21.302 |
20.226 |
0.191 |
-1.92% |
0.191 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC31
|
-5.04% |
241.208 |
229.039 |
0.041 |
-5.05% |
0.041 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint32_t_To_uint64_t_
|
-5.04% |
21403.558 |
20324.693 |
30.866 |
-5.25% |
30.866 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_PIC_2D_RAW/171
|
-5.00% |
13.528 |
12.851 |
0.051 |
-5.09% |
0.051 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_ENERGY_CALC_RAW/5001
|
-4.97% |
439.612 |
417.783 |
5.368 |
-2.56% |
5.368 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint32_t>/256
|
-4.81% |
364.175 |
346.668 |
0.014 |
-4.81% |
0.014 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC63
|
-4.79% |
43.790 |
41.691 |
0.005 |
-3.70% |
0.005 |
|
SingleSource/Benchmarks/Misc/revertBits
Profile
|
-4.72% |
0.641 |
0.611 |
0.000 |
-4.69% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint16_t>/65
|
-4.60% |
95.106 |
90.731 |
0.006 |
-4.61% |
0.006 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_runtime_checks_fail<16, int>
|
-4.60% |
54.438 |
51.934 |
0.003 |
-4.60% |
0.003 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_runtime_checks_pass<16, int>
|
-4.60% |
54.437 |
51.934 |
0.003 |
-4.60% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC63
|
-4.54% |
1639.582 |
1565.193 |
9.102 |
-4.78% |
9.102 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopWithReductionTC2
|
-4.52% |
13.766 |
13.144 |
0.002 |
-4.52% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC31
|
-4.47% |
70.087 |
66.951 |
0.002 |
-4.47% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint8_t>/16
|
-4.46% |
60.052 |
57.374 |
0.180 |
6.61% |
0.180 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC63
|
-4.46% |
1732.633 |
1655.404 |
7.430 |
-4.70% |
7.430 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint8_t_To_uint64_t_
|
-4.41% |
23539.781 |
22502.471 |
27.854 |
-4.18% |
27.854 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint32_t_To_uint16_t_
|
-4.39% |
9877.414 |
9444.043 |
53.959 |
-4.41% |
53.959 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_nested_cond_load_novec_int32_t_
|
-4.37% |
649898.525 |
621525.071 |
201.332 |
-3.66% |
201.332 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC7
|
-4.35% |
14.392 |
13.766 |
0.000 |
-4.35% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC2
|
-4.35% |
14.392 |
13.766 |
0.000 |
-4.35% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC16
|
-4.35% |
14.392 |
13.766 |
0.000 |
-4.36% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC1
|
-4.35% |
14.394 |
13.768 |
0.000 |
-4.34% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC8
|
-4.35% |
14.392 |
13.766 |
0.000 |
-4.35% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC8
|
-4.35% |
14.392 |
13.766 |
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 |
0.000 |
-4.35% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC4
|
-4.35% |
14.392 |
13.766 |
0.000 |
-4.35% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC2
|
-4.35% |
14.392 |
13.766 |
0.000 |
-4.34% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC15
|
-4.35% |
14.391 |
13.766 |
0.000 |
-4.35% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC4
|
-4.35% |
14.391 |
13.766 |
0.001 |
-4.36% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC3
|
-4.34% |
14.391 |
13.766 |
0.000 |
-4.35% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC16
|
-4.34% |
14.391 |
13.766 |
0.001 |
-4.35% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC3
|
-4.34% |
14.392 |
13.766 |
0.000 |
-4.35% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC7
|
-4.34% |
14.391 |
13.767 |
0.000 |
-4.34% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint64_t>/999
|
-4.25% |
1810.927 |
1733.943 |
0.106 |
-4.27% |
0.106 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint64_t>/999
|
-4.15% |
3594.841 |
3445.600 |
0.284 |
-4.15% |
0.284 |
|
SingleSource/Benchmarks/Misc/flops-5
Profile
|
-4.13% |
2.021 |
1.937 |
0.000 |
-4.15% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_ENERGY_CALC_LAMBDA/171
|
-4.13% |
14.193 |
13.607 |
0.009 |
-4.50% |
0.009 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC64
|
-4.08% |
1487.713 |
1426.956 |
7.597 |
-4.27% |
7.597 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint64_t>/256
|
-4.08% |
935.508 |
897.372 |
0.037 |
-4.08% |
0.037 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC31
|
-4.04% |
61.948 |
59.446 |
0.002 |
-4.04% |
0.002 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_ENERGY_CALC_RAW/171
|
-4.00% |
14.207 |
13.638 |
0.011 |
-4.23% |
0.011 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_PIC_1D_LAMBDA/5001
|
-4.00% |
345.692 |
331.857 |
4.820 |
-5.98% |
4.820 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint64_t_To_uint32_t_
|
-3.99% |
19355.916 |
18582.995 |
43.703 |
-3.68% |
43.703 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_only_autovec_uint8_t_
|
-3.98% |
96159.254 |
92333.778 |
2.791 |
-3.98% |
2.791 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC32
|
-3.96% |
63.203 |
60.697 |
0.004 |
-3.96% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint32_t>/256
|
-3.96% |
221.514 |
212.750 |
0.009 |
-3.95% |
0.009 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint32_t>/65
|
-3.93% |
94.439 |
90.728 |
0.004 |
-3.98% |
0.004 |
|
MicroBenchmarks/ImageProcessing/Dilate/Dilate.test:BENCHMARK_DILATE/256
|
-3.91% |
1062.888 |
1021.348 |
5.195 |
-4.30% |
5.195 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC3
|
-3.84% |
16.268 |
15.643 |
0.001 |
-3.84% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC32
|
-3.82% |
744.972 |
716.490 |
4.150 |
-4.55% |
4.150 |
|
External/SPEC/CFP2017rate/519.lbm_r/519.lbm_r
Profile
|
-3.82% |
199.954 |
192.316 |
1.312 |
-4.17% |
1.312 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_PRESSURE_CALC_LAMBDA/44217
|
-3.80% |
500.410 |
481.411 |
2.836 |
-3.44% |
2.836 |
|
MultiSource/Benchmarks/nbench/nbench
Profile
|
-3.78% |
6.114 |
5.883 |
0.001 |
-3.98% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopTC16
|
-3.76% |
278.035 |
267.580 |
1.088 |
-3.13% |
1.088 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_ENERGY_CALC_LAMBDA/5001
|
-3.74% |
431.556 |
415.428 |
2.934 |
-5.16% |
2.934 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopFrom_uint64_t_To_uint32_t_
|
-3.72% |
15598.779 |
15018.704 |
98.297 |
-0.61% |
98.297 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC31
|
-3.72% |
31.255 |
30.093 |
0.181 |
-3.51% |
0.181 |
|
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 |
495.604 |
0.022 |
-3.65% |
0.022 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC64
|
-3.61% |
69.458 |
66.953 |
0.005 |
-3.61% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC64
|
-3.60% |
69.452 |
66.954 |
0.001 |
-3.60% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint16_t_To_uint8_t_
|
-3.59% |
2874.657 |
2771.383 |
4.424 |
-3.71% |
4.424 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC63
|
-3.59% |
70.094 |
67.579 |
0.002 |
-3.58% |
0.002 |
|
SingleSource/Benchmarks/BenchmarkGame/n-body
Profile
|
-3.58% |
2.731 |
2.634 |
0.000 |
21.70% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC63
|
-3.57% |
70.076 |
67.577 |
0.004 |
-3.58% |
0.004 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<31, EqZero, First>
|
-3.51% |
3340.260 |
3223.055 |
0.057 |
-3.68% |
0.057 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<64, EqZero, Mid>
|
-3.50% |
2747.147 |
2651.044 |
35.942 |
-3.40% |
35.942 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC64
|
-3.42% |
43.171 |
41.695 |
0.016 |
-3.43% |
0.016 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC31
|
-3.34% |
1500.380 |
1450.321 |
5.614 |
-4.27% |
5.614 |
|
External/SPEC/CFP2017rate/544.nab_r/544.nab_r
Profile
|
-3.30% |
476.157 |
460.423 |
0.020 |
-3.65% |
0.020 |
|
MultiSource/Applications/JM/lencod/lencod
Profile
|
-3.27% |
32.749 |
31.676 |
0.019 |
-2.65% |
0.019 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC15
|
-3.22% |
44.798 |
43.354 |
0.185 |
-2.42% |
0.185 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint16_t_To_uint8_t_
|
-3.20% |
4513.358 |
4369.016 |
2.861 |
-3.28% |
2.861 |
|
MultiSource/Benchmarks/TSVC/ControlLoops-flt/ControlLoops-flt
Profile
|
-3.18% |
5.496 |
5.321 |
0.030 |
-2.31% |
0.030 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint16_t>/999
|
-3.16% |
514.969 |
498.706 |
0.033 |
-3.17% |
0.033 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_PRESSURE_CALC_LAMBDA/5001
|
-3.15% |
44.788 |
43.379 |
0.451 |
-1.35% |
0.451 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1BigLoopWithReductionTC1
|
-3.13% |
20.025 |
19.397 |
0.001 |
-3.14% |
0.001 |
|
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 |
4865536.160 |
350.347 |
-3.07% |
350.347 |
|
SingleSource/Benchmarks/Shootout/Shootout-lists
Profile
|
-3.05% |
11.316 |
10.971 |
0.002 |
-3.02% |
0.002 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<32, EqZero, Last>
|
-3.02% |
7053.050 |
6840.365 |
56.206 |
-3.01% |
56.206 |
|
MultiSource/Benchmarks/Rodinia/pathfinder/pathfinder
Profile
|
-2.97% |
1.265 |
1.227 |
0.008 |
-2.44% |
0.008 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_FLOYD_DITHER/256
|
-2.89% |
1800.194 |
1748.083 |
2.696 |
0.84% |
2.696 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint16_t>/999
|
-2.84% |
1013.793 |
984.962 |
0.126 |
-2.85% |
0.126 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC64
|
-2.81% |
111.389 |
108.256 |
0.004 |
-2.81% |
0.004 |
|
MultiSource/Benchmarks/mafft/pairlocalalign
Profile
|
-2.81% |
94.147 |
91.502 |
0.414 |
-2.72% |
0.414 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC1
|
-2.78% |
22.527 |
21.902 |
0.000 |
-2.77% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC1
|
-2.78% |
22.526 |
21.900 |
0.001 |
-2.77% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC32
|
-2.75% |
31.287 |
30.425 |
0.023 |
-2.75% |
0.023 |
|
SingleSource/Benchmarks/BenchmarkGame/puzzle
Profile
|
-2.75% |
0.870 |
0.846 |
0.005 |
-2.60% |
0.005 |
|
MultiSource/Benchmarks/FreeBench/mason/mason
Profile
|
-2.74% |
0.553 |
0.538 |
0.000 |
-2.72% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetBLambdaLoops/lcalsBLambda.test:BM_MULADDSUB_LAMBDA/171
|
-2.72% |
0.432 |
0.420 |
0.003 |
0.02% |
0.003 |
|
MultiSource/Benchmarks/TSVC/NodeSplitting-dbl/NodeSplitting-dbl
Profile
|
-2.71% |
26.894 |
26.165 |
0.235 |
-0.95% |
0.235 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C/CoMD/CoMD
Profile
|
-2.69% |
9.893 |
9.627 |
0.002 |
-2.75% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC31
|
-2.68% |
93.312 |
90.811 |
0.051 |
-3.24% |
0.051 |
|
MicroBenchmarks/ImageProcessing/Dilate/Dilate.test:BENCHMARK_DILATE/512
|
-2.68% |
3551.171 |
3456.046 |
28.191 |
-3.57% |
28.191 |
|
SingleSource/Benchmarks/Misc-C++/oopack_v1p8
Profile
|
-2.67% |
0.480 |
0.467 |
0.000 |
-10.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopTC15
|
-2.65% |
738.965 |
719.417 |
4.831 |
-2.59% |
4.831 |
|
MultiSource/Benchmarks/FreeBench/fourinarow/fourinarow
Profile
|
-2.62% |
0.651 |
0.634 |
0.001 |
-2.63% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC63
|
-2.61% |
120.148 |
117.013 |
0.003 |
-2.61% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint64_t_To_uint8_t_
|
-2.59% |
19767.280 |
19255.985 |
45.926 |
-2.95% |
45.926 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint8_t>/10
|
-2.55% |
48.805 |
47.560 |
0.202 |
2.47% |
0.202 |
|
MultiSource/Benchmarks/FreeBench/pcompress2/pcompress2
Profile
|
-2.54% |
0.404 |
0.394 |
0.001 |
-2.67% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint8_t_To_uint32_t_
|
-2.52% |
7078.378 |
6899.896 |
0.925 |
-2.51% |
0.925 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_FLOYD_DITHER/128
|
-2.46% |
438.996 |
428.217 |
0.392 |
-2.56% |
0.392 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchVecWithRuntimeChecks4PointersDBeforeA/32
|
-2.44% |
166189.320 |
162129.286 |
14.830 |
-2.45% |
14.830 |
|
MultiSource/Benchmarks/sim/sim
Profile
|
-2.42% |
9.701 |
9.466 |
0.018 |
-2.41% |
0.018 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint16_t_To_uint32_t_
|
-2.40% |
11316.385 |
11045.207 |
26.097 |
-2.62% |
26.097 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC4
|
-2.39% |
348.022 |
339.692 |
2.254 |
-2.77% |
2.254 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_only_autovec_int64_t_
|
-2.36% |
1447896.561 |
1413760.796 |
393.696 |
-2.30% |
393.696 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, LessThanZero, None>
|
-2.35% |
37325.096 |
36448.303 |
33.310 |
-3.00% |
33.310 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC63
|
-2.33% |
106.993 |
104.498 |
0.004 |
-2.34% |
0.004 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_PRESSURE_CALC_RAW/44217
|
-2.31% |
493.578 |
482.161 |
1.680 |
-3.99% |
1.680 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC64
|
-2.31% |
108.253 |
105.751 |
0.002 |
-2.31% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC32
|
-2.30% |
50.008 |
48.859 |
0.100 |
-2.38% |
0.100 |
|
SingleSource/Benchmarks/Misc/flops-1
Profile
|
-2.17% |
9.001 |
8.806 |
0.000 |
-2.15% |
0.000 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_FLOYD_DITHER/512
|
-2.14% |
6662.192 |
6519.743 |
8.956 |
-1.89% |
8.956 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint32_t_To_uint64_t_
|
-2.12% |
26323.170 |
25764.347 |
50.154 |
-1.96% |
50.154 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint32_t>/10
|
-2.10% |
47.295 |
46.303 |
0.008 |
-0.00% |
0.008 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC128
|
-2.10% |
119.520 |
117.015 |
0.002 |
-2.10% |
0.002 |
|
SingleSource/Benchmarks/Misc-C++/Large/ray
Profile
|
-2.10% |
12.104 |
11.850 |
0.000 |
-2.07% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC127
|
-2.09% |
120.147 |
117.636 |
0.004 |
-2.08% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC127
|
-2.08% |
120.143 |
117.639 |
0.001 |
-2.09% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC128
|
-2.08% |
119.505 |
117.016 |
0.003 |
-2.09% |
0.003 |
|
MultiSource/Applications/sgefa/sgefa
Profile
|
-2.07% |
0.578 |
0.566 |
0.002 |
-1.32% |
0.002 |
|
External/SPEC/CINT2017rate/531.deepsjeng_r/531.deepsjeng_r
Profile
|
-2.06% |
260.560 |
255.187 |
0.344 |
-1.89% |
0.344 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<31, GreaterThanZero, Last>
|
-1.99% |
8263.975 |
8099.275 |
10.258 |
-2.37% |
10.258 |
|
SingleSource/Benchmarks/Misc/ReedSolomon
Profile
|
-1.96% |
20.821 |
20.412 |
0.000 |
-1.85% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_EOS_RAW/171
|
-1.95% |
0.872 |
0.855 |
0.000 |
-1.81% |
0.000 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<16, GreaterThanZero, First>
|
-1.94% |
8548.717 |
8382.552 |
52.769 |
-1.34% |
52.769 |
|
MultiSource/Benchmarks/Bullet/bullet
Profile
|
-1.94% |
30.402 |
29.813 |
0.200 |
-2.03% |
0.200 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_EOS_LAMBDA/171
|
-1.92% |
0.872 |
0.855 |
0.001 |
-1.77% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_ENERGY_CALC_LAMBDA/44217
|
-1.87% |
4339.935 |
4258.669 |
9.349 |
-1.52% |
9.349 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint16_t>/256
|
-1.83% |
272.825 |
267.829 |
0.007 |
-1.84% |
0.007 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C/SimpleMOC/SimpleMOC
Profile
|
-1.79% |
10.409 |
10.223 |
0.066 |
-1.75% |
0.066 |
|
MultiSource/Benchmarks/Olden/health/health
Profile
|
-1.72% |
1.598 |
1.570 |
0.001 |
-1.33% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_csa_with_in_loop_arith_novec_int64_t_
|
-1.72% |
1029500.118 |
1011834.599 |
985.872 |
-1.59% |
985.872 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_INT_PREDICT_RAW/171
|
-1.71% |
6.919 |
6.801 |
0.011 |
-1.79% |
0.011 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_csa_with_cond_arith_autovec_int64_t_
|
-1.69% |
745431.265 |
732820.129 |
1657.740 |
-1.63% |
1657.740 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<16, EqZero, Mid>
|
-1.69% |
8658.186 |
8511.965 |
49.642 |
-1.68% |
49.642 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint64_t>/51
|
-1.69% |
148.302 |
145.798 |
0.014 |
-1.69% |
0.014 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_nested_cond_load_novec_uint8_t_
|
-1.68% |
504571.719 |
496101.240 |
149.396 |
-1.71% |
149.396 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint8_t>/10
|
-1.68% |
66.828 |
65.707 |
0.003 |
6.44% |
0.003 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_INT_PREDICT_LAMBDA/171
|
-1.68% |
6.926 |
6.810 |
0.006 |
-1.67% |
0.006 |
|
MultiSource/Benchmarks/VersaBench/ecbdes/ecbdes
Profile
|
-1.66% |
5.141 |
5.056 |
0.000 |
-1.62% |
0.000 |
|
MultiSource/Benchmarks/Fhourstones-3.1/fhourstones3.1
Profile
|
-1.65% |
3.987 |
3.921 |
0.003 |
-1.27% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC15
|
-1.63% |
518.669 |
510.192 |
3.057 |
-2.89% |
3.057 |
|
MicroBenchmarks/ImageProcessing/Blur/blur.test:BENCHMARK_boxBlurKernel/512
|
-1.62% |
6614.044 |
6507.060 |
27.942 |
-1.61% |
27.942 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<32, LessThanZero, Mid>
|
-1.61% |
4571.240 |
4497.589 |
2.398 |
-1.61% |
2.398 |
|
MultiSource/Benchmarks/tramp3d-v4/tramp3d-v4
Profile
|
-1.61% |
1.074 |
1.057 |
0.002 |
-1.77% |
0.002 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<3, GreaterThanZero, None>
|
-1.58% |
44998.078 |
44288.703 |
223.237 |
-1.89% |
223.237 |
|
SingleSource/Benchmarks/Misc/mandel-2
Profile
|
-1.56% |
2.535 |
2.496 |
0.000 |
-1.54% |
0.000 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<6, LessThanZero, Mid>
|
-1.53% |
23845.560 |
23480.894 |
13.730 |
-0.37% |
13.730 |
|
External/SPEC/CINT2017rate/525.x264_r/525.x264_r
Profile
|
-1.51% |
129.899 |
127.936 |
0.277 |
-1.17% |
0.277 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC128
|
-1.49% |
211.511 |
208.358 |
0.021 |
-1.49% |
0.021 |
|
External/SPEC/CFP2017rate/511.povray_r/511.povray_r
Profile
|
-1.47% |
33.916 |
33.420 |
0.028 |
-1.08% |
0.028 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<64, GreaterThanZero, Mid>
|
-1.43% |
2746.405 |
2707.116 |
6.681 |
-1.41% |
6.681 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC127
|
-1.41% |
220.265 |
217.157 |
0.025 |
-1.42% |
0.025 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC63
|
-1.39% |
130.150 |
128.347 |
0.104 |
-1.40% |
0.104 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint64_t>/51
|
-1.37% |
229.014 |
225.886 |
0.020 |
-1.36% |
0.020 |
|
External/SPEC/CINT2017rate/500.perlbench_r/500.perlbench_r
Profile
|
-1.32% |
147.287 |
145.345 |
0.334 |
-0.92% |
0.334 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC127
|
-1.27% |
197.105 |
194.603 |
0.028 |
-1.27% |
0.028 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC128
|
-1.26% |
198.351 |
195.845 |
0.008 |
-1.27% |
0.008 |
|
MultiSource/Benchmarks/MallocBench/cfrac/cfrac
Profile
|
-1.24% |
2.780 |
2.745 |
0.001 |
-1.25% |
0.001 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<64, EqZero, None>
|
-1.24% |
2928.091 |
2891.906 |
13.562 |
-1.28% |
13.562 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_EOS_LAMBDA/44217
|
-1.23% |
270.990 |
267.656 |
1.121 |
-0.69% |
1.121 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_csa_with_cond_arith_novec_int64_t_
|
-1.20% |
743977.235 |
735049.038 |
1309.452 |
-1.30% |
1309.452 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<32, GreaterThanZero, Mid>
|
-1.17% |
4546.826 |
4493.539 |
9.433 |
-1.36% |
9.433 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint8_t>/16
|
-1.16% |
85.468 |
84.474 |
0.002 |
11.81% |
0.002 |
|
SingleSource/Benchmarks/SmallPT/smallpt
Profile
|
-1.12% |
30.042 |
29.706 |
0.003 |
-1.07% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_sinhf_autovec_float_
|
-1.10% |
2241.293 |
2216.662 |
0.882 |
-1.16% |
0.882 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<6, GreaterThanZero, None>
|
-1.09% |
29721.295 |
29397.965 |
3.660 |
-0.61% |
3.660 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_sinhf_novec_float_
|
-1.07% |
2242.194 |
2218.128 |
0.516 |
-1.06% |
0.516 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint8_t_To_uint32_t_
|
-1.06% |
12064.707 |
11937.204 |
23.949 |
-1.53% |
23.949 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<3, EqZero, Mid>
|
-1.03% |
37579.598 |
37191.080 |
52.731 |
-1.08% |
52.731 |