|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_INT_PREDICT_RAW/44217
|
-57.73% |
19368.084 |
8185.922 |
9.506 |
-9.54% |
9.506 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_INT_PREDICT_RAW/5001
|
-52.21% |
1911.292 |
913.381 |
2.305 |
-0.00% |
2.305 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_HYDRO_2D_LAMBDA/44217
|
-50.84% |
65165.666 |
32033.610 |
11427.877 |
-64.77% |
11427.877 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint64_t_To_uint32_t_
|
-50.30% |
35307.898 |
17546.382 |
175.683 |
-50.31% |
175.683 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_DISC_ORD_LAMBDA/44217
|
-49.98% |
12421.222 |
6212.988 |
2237.068 |
-55.79% |
2237.068 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint64_t_To_uint16_t_
|
-48.98% |
35695.721 |
18212.878 |
1593.393 |
-48.96% |
1593.393 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint64_t_To_uint8_t_
|
-48.95% |
37215.602 |
18998.079 |
25.996 |
-48.74% |
25.996 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_HYDRO_2D_LAMBDA/5001
|
-47.82% |
7064.406 |
3686.270 |
1201.952 |
-59.55% |
1201.952 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C/miniGMG/miniGMG
Profile
|
-47.45% |
8.778 |
4.613 |
0.214 |
-49.81% |
0.214 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint16_t_To_uint64_t_
|
-43.99% |
18649.315 |
10445.869 |
2.443 |
-44.07% |
2.443 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_DIFF_PREDICT_RAW/44217
|
-43.51% |
23872.342 |
13485.788 |
293.196 |
-42.12% |
293.196 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIRST_DIFF_RAW/44217
|
-42.85% |
178.657 |
102.104 |
1.186 |
-28.34% |
1.186 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_PIC_2D_RAW/5001
|
-42.27% |
1199.796 |
692.582 |
119.397 |
-35.78% |
119.397 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_DIFF_PREDICT_LAMBDA/44217
|
-41.43% |
23078.260 |
13517.674 |
299.393 |
-41.49% |
299.393 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint8_t_To_uint64_t_
|
-40.98% |
17806.694 |
10510.009 |
15.171 |
-40.95% |
15.171 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint64_t_To_uint32_t_
|
-40.60% |
38129.750 |
22647.568 |
19.666 |
-40.64% |
19.666 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_DIFF_PREDICT_LAMBDA/5001
|
-40.33% |
2547.371 |
1520.004 |
29.819 |
-39.43% |
29.819 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_DIFF_PREDICT_RAW/5001
|
-39.45% |
2497.565 |
1512.346 |
28.289 |
-41.26% |
28.289 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint32_t_To_uint64_t_
|
-37.46% |
22711.118 |
14204.288 |
644.111 |
-37.49% |
644.111 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/32
|
-36.70% |
1396.241 |
883.799 |
0.096 |
-36.70% |
0.096 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/64
|
-36.67% |
6181.324 |
3914.614 |
1.290 |
-36.68% |
1.290 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/16
|
-36.62% |
279.444 |
177.115 |
0.020 |
-36.62% |
0.020 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/256
|
-36.18% |
107126.821 |
68364.879 |
24.389 |
-36.20% |
24.389 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/128
|
-36.15% |
26266.383 |
16771.874 |
20.169 |
-36.16% |
20.169 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint64_t_To_uint8_t_
|
-34.94% |
30438.739 |
19804.126 |
12.749 |
-34.23% |
12.749 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint64_t_To_uint16_t_
|
-34.11% |
28973.989 |
19091.069 |
15.519 |
-34.05% |
15.519 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, EqZero, None>
|
-31.24% |
20511.133 |
14104.469 |
0.592 |
-31.24% |
0.592 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint64_t_To_uint16_t_
|
-28.95% |
25899.026 |
18401.126 |
54.354 |
-28.95% |
54.354 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIRST_DIFF_LAMBDA/44217
|
-28.43% |
142.126 |
101.720 |
1.712 |
-29.76% |
1.712 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint32_t_To_uint8_t_
|
-28.04% |
13486.475 |
9704.710 |
53.763 |
-27.95% |
53.763 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC128
|
-27.96% |
1292.192 |
930.946 |
5.306 |
-27.99% |
5.306 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC64
|
-27.48% |
654.646 |
474.740 |
3.102 |
-27.37% |
3.102 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC32
|
-27.15% |
334.658 |
243.795 |
1.172 |
-26.99% |
1.172 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC128
|
-26.87% |
557.593 |
407.751 |
0.022 |
-26.87% |
0.022 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC16
|
-26.55% |
173.790 |
127.653 |
0.800 |
-26.55% |
0.800 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIRST_SUM_RAW/44217
|
-25.73% |
181.375 |
134.712 |
0.466 |
-19.01% |
0.466 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC64
|
-25.66% |
292.080 |
217.144 |
0.066 |
-25.59% |
0.066 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint64_t_To_uint8_t_
|
-24.40% |
27231.885 |
20587.005 |
13.022 |
-24.38% |
13.022 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, EqZero, None>
|
-24.00% |
16025.624 |
12179.877 |
0.705 |
-23.99% |
0.705 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC128
|
-23.22% |
603.986 |
463.727 |
0.042 |
-23.22% |
0.042 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC128
|
-23.11% |
603.990 |
464.390 |
0.031 |
-23.11% |
0.031 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC32
|
-23.10% |
158.674 |
122.024 |
0.099 |
-23.19% |
0.099 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint16_t_To_uint64_t_
|
-22.85% |
13432.521 |
10362.863 |
0.462 |
-21.54% |
0.462 |
|
MicroBenchmarks/ImageProcessing/Blur/blur.test:BENCHMARK_boxBlurKernel/1024
|
-22.50% |
30107.504 |
23332.276 |
74.767 |
-22.61% |
74.767 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC64
|
-22.36% |
313.522 |
243.421 |
0.016 |
-22.35% |
0.016 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC127
|
-22.18% |
615.228 |
478.749 |
0.043 |
-22.18% |
0.043 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC64
|
-22.16% |
313.494 |
244.031 |
0.033 |
-22.16% |
0.033 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC127
|
-21.98% |
615.244 |
480.025 |
0.030 |
-21.97% |
0.030 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint8_t_To_uint32_t_
|
-21.77% |
6600.504 |
5163.835 |
5.954 |
-21.55% |
5.954 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint16_t_To_uint32_t_
|
-21.62% |
7104.179 |
5568.274 |
7.900 |
-21.58% |
7.900 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIND_FIRST_MIN_LAMBDA/44217
|
-21.47% |
390.211 |
306.452 |
0.572 |
-21.34% |
0.572 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_only_autovec_uint8_t_
|
-21.37% |
182362.554 |
143398.320 |
76.295 |
-21.36% |
76.295 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIND_FIRST_MIN_LAMBDA/171
|
-21.29% |
1.501 |
1.181 |
0.000 |
-21.29% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIND_FIRST_MIN_LAMBDA/5001
|
-20.84% |
45.262 |
35.829 |
0.060 |
-20.83% |
0.060 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_PIC_2D_LAMBDA/44217
|
-20.82% |
10886.195 |
8619.570 |
89.786 |
-21.38% |
89.786 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC32
|
-20.81% |
168.319 |
133.288 |
0.003 |
-20.82% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC32
|
-20.45% |
168.327 |
133.896 |
0.014 |
-20.46% |
0.014 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC63
|
-20.45% |
324.838 |
258.422 |
0.035 |
-20.43% |
0.035 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC127
|
-20.42% |
274.680 |
218.596 |
0.637 |
-20.64% |
0.637 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC128
|
-20.25% |
274.408 |
218.835 |
0.417 |
-20.35% |
0.417 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIRST_SUM_LAMBDA/44217
|
-20.22% |
170.353 |
135.906 |
0.834 |
-18.66% |
0.834 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint32_t_To_uint8_t_
|
-20.13% |
13897.420 |
11099.377 |
114.248 |
-20.15% |
114.248 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC63
|
-20.05% |
324.768 |
259.666 |
0.032 |
-20.05% |
0.032 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC127
|
-19.69% |
640.673 |
514.549 |
0.080 |
-19.66% |
0.080 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC16
|
-19.30% |
92.272 |
74.464 |
0.005 |
-19.31% |
0.005 |
|
MultiSource/Benchmarks/MiBench/automotive-bitcount/automotive-bitcount
Profile
|
-19.10% |
0.125 |
0.101 |
0.000 |
-18.39% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint16_t_To_uint8_t_
|
-19.07% |
3816.916 |
3089.124 |
0.803 |
-19.09% |
0.803 |
|
SingleSource/Benchmarks/Adobe-C++/loop_unroll
Profile
|
-18.87% |
2.981 |
2.419 |
0.003 |
-22.14% |
0.003 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_VOL3D_CALC_LAMBDA/2
|
-18.79% |
8.757 |
7.111 |
0.000 |
-18.80% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_VOL3D_CALC_RAW/2
|
-18.79% |
8.757 |
7.111 |
0.000 |
-18.79% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint64_t_To_uint32_t_
|
-18.56% |
27110.034 |
22079.673 |
6.099 |
-18.38% |
6.099 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint32_t_To_uint16_t_
|
-18.46% |
13798.013 |
11251.016 |
5.528 |
-18.51% |
5.528 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC16
|
-18.30% |
95.736 |
78.213 |
0.011 |
-18.31% |
0.011 |
|
MultiSource/Benchmarks/Trimaran/enc-pc1/enc-pc1
Profile
|
-18.12% |
1.105 |
0.905 |
0.000 |
-18.09% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC64
|
-18.07% |
148.481 |
121.651 |
0.749 |
-18.15% |
0.749 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_with_cond_arith_novec_uint8_t_
|
-17.87% |
745884.095 |
612626.710 |
535.888 |
-17.85% |
535.888 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC16
|
-17.65% |
95.737 |
78.839 |
0.004 |
-17.65% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_with_cond_arith_novec_int32_t_
|
-17.55% |
740955.732 |
610893.553 |
934.965 |
-17.47% |
934.965 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC31
|
-17.43% |
179.600 |
148.297 |
0.005 |
-17.42% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC128
|
-17.27% |
570.759 |
472.202 |
0.060 |
-17.24% |
0.060 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC4
|
-17.24% |
17.520 |
14.499 |
0.004 |
-17.24% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC64
|
-17.14% |
297.874 |
246.822 |
0.035 |
-17.09% |
0.035 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint8_t_To_uint64_t_
|
-17.03% |
13151.896 |
10912.046 |
3.346 |
-16.48% |
3.346 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC32
|
-16.85% |
161.354 |
134.168 |
0.021 |
-16.87% |
0.021 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC31
|
-16.72% |
179.584 |
149.557 |
0.005 |
-16.72% |
0.005 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_VOL3D_CALC_RAW/0
|
-16.64% |
1267.621 |
1056.696 |
3.579 |
-16.48% |
3.579 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_VOL3D_CALC_LAMBDA/0
|
-16.33% |
1269.375 |
1062.045 |
1.407 |
-16.22% |
1.407 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_HYDRO_1D_RAW/171
|
-16.24% |
0.444 |
0.372 |
0.000 |
-15.84% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_VOL3D_CALC_LAMBDA/1
|
-16.17% |
260.232 |
218.143 |
0.212 |
-16.15% |
0.212 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_HYDRO_1D_LAMBDA/171
|
-16.11% |
0.443 |
0.372 |
0.000 |
-15.87% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_VOL3D_CALC_RAW/1
|
-16.06% |
260.037 |
218.281 |
0.151 |
-16.09% |
0.151 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC16
|
-16.05% |
92.792 |
77.901 |
0.012 |
-16.35% |
0.012 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC63
|
-15.97% |
148.764 |
125.006 |
1.131 |
-16.61% |
1.131 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint16_t_To_uint32_t_
|
-15.68% |
7462.885 |
6292.426 |
1.310 |
-15.68% |
1.310 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint32_t_To_uint8_t_
|
-15.65% |
10666.891 |
8997.106 |
61.268 |
-15.08% |
61.268 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC4
|
-15.58% |
114.391 |
96.566 |
0.983 |
-14.61% |
0.983 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_HYDRO_1D_RAW/5001
|
-15.55% |
17.621 |
14.881 |
0.401 |
-10.82% |
0.401 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, EqZero, First>
|
-15.40% |
16670.718 |
14103.091 |
1.028 |
-15.40% |
1.028 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC8
|
-15.39% |
58.799 |
49.747 |
0.001 |
-15.34% |
0.001 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_no_runtime_checks_needed<16, int>
|
-15.38% |
24.403 |
20.649 |
0.001 |
-15.38% |
0.001 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, EqZero, Mid>
|
-15.38% |
16667.187 |
14104.427 |
0.601 |
-15.37% |
0.601 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, EqZero, Last>
|
-15.36% |
16668.361 |
14108.917 |
1.130 |
-15.35% |
1.130 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC127
|
-14.83% |
605.867 |
516.043 |
0.045 |
-14.81% |
0.045 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint32_t_To_uint64_t_
|
-14.73% |
17746.284 |
15131.902 |
276.354 |
-12.00% |
276.354 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC8
|
-14.73% |
59.442 |
50.686 |
0.000 |
-14.74% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC128
|
-14.58% |
1103.415 |
942.550 |
0.054 |
-14.57% |
0.054 |
|
MicroBenchmarks/ImageProcessing/Dilate/Dilate.test:BENCHMARK_DILATE/1024
|
-14.57% |
7188.607 |
6141.002 |
242.075 |
-13.64% |
242.075 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC127
|
-14.53% |
1095.401 |
936.276 |
0.048 |
-14.52% |
0.048 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC32
|
-14.40% |
84.999 |
72.758 |
1.487 |
-14.73% |
1.487 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint32_t_To_uint8_t_
|
-14.40% |
11058.606 |
9466.547 |
138.400 |
-14.94% |
138.400 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC64
|
-14.35% |
562.545 |
481.806 |
0.037 |
-14.32% |
0.037 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint64_t_To_uint8_t_
|
-14.33% |
22143.873 |
18971.442 |
30.530 |
-13.95% |
30.530 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC63
|
-14.24% |
554.524 |
475.543 |
0.044 |
-14.28% |
0.044 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_with_cond_arith_novec_int64_t_
|
-14.18% |
792306.243 |
679974.615 |
597.592 |
-13.71% |
597.592 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint8_t_To_uint16_t_
|
-14.16% |
3756.587 |
3224.535 |
8.616 |
-14.16% |
8.616 |
|
SingleSource/Benchmarks/Misc/salsa20
Profile
|
-14.13% |
15.386 |
13.212 |
0.001 |
-14.12% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_PRESSURE_CALC_LAMBDA/5001
|
-14.04% |
48.324 |
41.539 |
1.345 |
-5.54% |
1.345 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC32
|
-13.91% |
292.172 |
251.545 |
0.014 |
-13.85% |
0.014 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC1
|
-13.86% |
51.939 |
44.740 |
0.001 |
-13.85% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC2
|
-13.86% |
51.936 |
44.739 |
0.002 |
-13.85% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC4
|
-13.86% |
51.936 |
44.739 |
0.003 |
-13.85% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC3
|
-13.85% |
51.933 |
44.738 |
0.004 |
-13.86% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC7
|
-13.85% |
51.932 |
44.739 |
0.002 |
-13.86% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC8
|
-13.85% |
51.936 |
44.742 |
0.003 |
-13.86% |
0.003 |
|
External/SPEC/CFP2017rate/508.namd_r/508.namd_r
Profile
|
-13.85% |
224.648 |
193.542 |
0.020 |
-13.43% |
0.020 |
|
MicroBenchmarks/ImageProcessing/Dilate/Dilate.test:BENCHMARK_DILATE/128
|
-13.78% |
224.443 |
193.525 |
6.693 |
-15.11% |
6.693 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint32_t_To_uint16_t_
|
-13.76% |
10827.586 |
9338.018 |
218.130 |
-13.03% |
218.130 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC8
|
-13.68% |
59.439 |
51.310 |
0.005 |
-13.69% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC31
|
-13.64% |
284.074 |
245.314 |
0.022 |
-13.65% |
0.022 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, EqZero, First>
|
-13.63% |
14104.167 |
12181.897 |
0.151 |
-13.62% |
0.151 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, EqZero, Mid>
|
-13.63% |
14104.598 |
12182.296 |
0.277 |
-13.62% |
0.277 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint32_t_To_uint16_t_
|
-13.62% |
12797.698 |
11054.588 |
40.228 |
-13.89% |
40.228 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, EqZero, Last>
|
-13.61% |
14103.116 |
12183.189 |
0.702 |
-13.62% |
0.702 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_with_cond_arith_autovec_int64_t_
|
-13.58% |
790159.822 |
682862.640 |
960.639 |
-13.74% |
960.639 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC8
|
-13.51% |
23.150 |
20.023 |
0.001 |
-13.52% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC63
|
-13.44% |
374.495 |
324.151 |
0.083 |
-13.43% |
0.083 |
|
MultiSource/Benchmarks/MiBench/security-rijndael/security-rijndael
Profile
|
-13.21% |
0.336 |
0.292 |
0.001 |
-12.88% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC8
|
-13.15% |
23.777 |
20.649 |
0.001 |
-13.16% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC16
|
-13.13% |
157.018 |
136.403 |
0.009 |
-13.10% |
0.009 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC128
|
-13.08% |
81.342 |
70.705 |
0.008 |
-13.08% |
0.008 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint8_t_To_uint16_t_
|
-12.94% |
4541.754 |
3953.928 |
0.337 |
-12.94% |
0.337 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC15
|
-12.87% |
107.006 |
93.234 |
0.011 |
-12.87% |
0.011 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_PIC_1D_LAMBDA/5001
|
-12.75% |
347.441 |
303.138 |
16.684 |
-14.11% |
16.684 |
|
SingleSource/Benchmarks/Shootout-C++/Shootout-C++-matrix
Profile
|
-12.73% |
2.509 |
2.190 |
0.000 |
-12.70% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_PIC_2D_LAMBDA/5001
|
-12.72% |
1071.839 |
935.543 |
22.320 |
-15.37% |
22.320 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC63
|
-12.70% |
332.927 |
290.649 |
0.023 |
-12.67% |
0.023 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC15
|
-12.58% |
148.891 |
130.156 |
0.004 |
-12.54% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint16_t_To_uint8_t_
|
-12.41% |
4743.917 |
4155.298 |
0.061 |
-12.39% |
0.061 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint32_t_To_uint16_t_
|
-11.82% |
9673.332 |
8529.535 |
370.904 |
-13.89% |
370.904 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC8
|
-11.77% |
89.352 |
78.837 |
0.005 |
-11.82% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC2
|
-11.76% |
21.275 |
18.772 |
0.001 |
-11.77% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC15
|
-11.70% |
106.999 |
94.481 |
0.008 |
-11.71% |
0.008 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIRST_SUM_RAW/5001
|
-11.57% |
20.344 |
17.991 |
0.139 |
3.72% |
0.139 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC31
|
-11.52% |
86.143 |
76.219 |
0.055 |
-11.49% |
0.055 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC16
|
-11.45% |
51.939 |
45.989 |
0.003 |
-11.46% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC15
|
-11.45% |
51.936 |
45.990 |
0.004 |
-11.45% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC16
|
-11.38% |
33.168 |
29.393 |
0.006 |
-11.37% |
0.006 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIRST_DIFF_RAW/5001
|
-11.14% |
13.088 |
11.631 |
0.323 |
-3.53% |
0.323 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC4
|
-11.11% |
22.527 |
20.024 |
0.000 |
-11.11% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC4
|
-11.11% |
22.525 |
20.023 |
0.002 |
-11.12% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC3
|
-11.10% |
22.525 |
20.024 |
0.001 |
-11.11% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint8_t>/51
|
-11.02% |
123.895 |
110.238 |
0.202 |
19.17% |
0.202 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC7
|
-10.74% |
81.312 |
72.583 |
0.005 |
-10.74% |
0.005 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_PRESSURE_CALC_RAW/5001
|
-10.62% |
45.566 |
40.729 |
0.756 |
-8.68% |
0.756 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_BAND_LIN_EQ_RAW/171
|
-10.61% |
0.384 |
0.343 |
0.000 |
-6.34% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC4
|
-10.60% |
41.296 |
36.917 |
0.002 |
-10.62% |
0.002 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_BAND_LIN_EQ_LAMBDA/171
|
-10.59% |
0.384 |
0.343 |
0.000 |
-6.32% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC4
|
-10.53% |
23.776 |
21.273 |
0.001 |
-10.54% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC64
|
-10.47% |
53.812 |
48.177 |
0.004 |
-10.48% |
0.004 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_DIFF_PREDICT_RAW/171
|
-10.41% |
12.389 |
11.099 |
0.145 |
-6.99% |
0.145 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_INT_PREDICT_LAMBDA/44217
|
-10.34% |
9083.231 |
8144.202 |
15.675 |
-2.32% |
15.675 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/16
|
-10.17% |
115.464 |
103.720 |
0.007 |
-10.17% |
0.007 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint8_t_To_uint16_t_
|
-10.08% |
5846.418 |
5257.374 |
4.136 |
-10.14% |
4.136 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC4
|
-10.07% |
55.664 |
50.058 |
0.003 |
-10.07% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC7
|
-10.05% |
358.082 |
322.108 |
4.633 |
-9.19% |
4.633 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/64
|
-10.02% |
1912.741 |
1721.166 |
0.996 |
-10.04% |
0.996 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/256
|
-9.99% |
31468.858 |
28324.031 |
21.385 |
-9.94% |
21.385 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/32
|
-9.99% |
473.009 |
425.775 |
0.011 |
-9.98% |
0.011 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_only_autovec_int64_t_
|
-9.92% |
333221.519 |
300169.542 |
718.633 |
-9.93% |
718.633 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/128
|
-9.80% |
7922.704 |
7146.376 |
0.655 |
-9.74% |
0.655 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC8
|
-9.76% |
25.655 |
23.152 |
0.001 |
-9.76% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC8
|
-9.75% |
25.654 |
23.152 |
0.001 |
-9.76% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC127
|
-9.68% |
101.844 |
91.985 |
0.003 |
-9.71% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC7
|
-9.62% |
32.539 |
29.409 |
0.002 |
-9.62% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC7
|
-9.52% |
26.280 |
23.778 |
0.001 |
-9.53% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC7
|
-9.51% |
26.279 |
23.779 |
0.000 |
-9.52% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC32
|
-9.43% |
53.188 |
48.173 |
0.003 |
-9.44% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC31
|
-9.38% |
196.461 |
178.031 |
0.005 |
-9.39% |
0.005 |
|
MultiSource/Benchmarks/FreeBench/pifft/pifft
Profile
|
-9.18% |
0.360 |
0.327 |
0.001 |
-8.85% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_DEL_DOT_VEC_2D_LAMBDA/1
|
-9.16% |
286.997 |
260.707 |
0.095 |
-9.20% |
0.095 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC8
|
-9.15% |
26.862 |
24.403 |
0.001 |
-9.32% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_DEL_DOT_VEC_2D_RAW/1
|
-9.12% |
286.950 |
260.783 |
0.015 |
-9.13% |
0.015 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC4
|
-9.09% |
41.296 |
37.541 |
0.002 |
-9.10% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC7
|
-8.88% |
28.157 |
25.656 |
0.001 |
-8.89% |
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
|
-8.69% |
3.509 |
3.204 |
0.000 |
-8.70% |
0.000 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_runtime_checks_pass<4, int>
|
-8.69% |
16.789 |
15.330 |
0.001 |
-8.25% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC16
|
-8.63% |
36.293 |
33.162 |
0.003 |
-8.63% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC8
|
-8.51% |
29.410 |
26.908 |
0.001 |
-8.51% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint16_t_To_uint8_t_
|
-8.42% |
6808.496 |
6235.256 |
7.317 |
-8.52% |
7.317 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint8_t_To_uint32_t_
|
-8.24% |
12786.419 |
11732.722 |
42.321 |
-8.19% |
42.321 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint64_t_To_uint16_t_
|
-8.23% |
19135.321 |
17561.014 |
425.623 |
-7.50% |
425.623 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC2
|
-8.20% |
38.172 |
35.043 |
0.001 |
-8.20% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC127
|
-8.19% |
2424.844 |
2226.356 |
23.036 |
-8.25% |
23.036 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC64
|
-8.06% |
93.228 |
85.715 |
0.008 |
-8.07% |
0.008 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC3
|
-7.90% |
47.556 |
43.800 |
0.005 |
-7.90% |
0.005 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_DEL_DOT_VEC_2D_LAMBDA/0
|
-7.88% |
1802.277 |
1660.289 |
4.465 |
-7.35% |
4.465 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC16
|
-7.84% |
31.913 |
29.410 |
0.002 |
-7.84% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC16
|
-7.84% |
31.911 |
29.410 |
0.003 |
-7.84% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC32
|
-7.81% |
40.045 |
36.916 |
0.004 |
-7.82% |
0.004 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_HYDRO_2D_LAMBDA/171
|
-7.79% |
88.505 |
81.608 |
0.304 |
-7.95% |
0.304 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint16_t_To_uint64_t_
|
-7.72% |
20306.543 |
18739.720 |
42.089 |
-6.97% |
42.089 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint8_t>/28
|
-7.70% |
82.360 |
76.014 |
0.032 |
12.46% |
0.032 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC15
|
-7.69% |
32.538 |
30.036 |
0.002 |
-7.69% |
0.002 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_DEL_DOT_VEC_2D_RAW/0
|
-7.69% |
1800.432 |
1662.005 |
3.660 |
-7.71% |
3.660 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC15
|
-7.68% |
32.536 |
30.036 |
0.002 |
-7.69% |
0.002 |
|
MultiSource/Benchmarks/VersaBench/beamformer/beamformer
Profile
|
-7.63% |
5.200 |
4.803 |
0.001 |
-7.65% |
0.001 |
|
MultiSource/Benchmarks/Trimaran/enc-md5/enc-md5
Profile
|
-7.55% |
3.508 |
3.243 |
0.000 |
-7.50% |
0.000 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_xor_no_runtime_checks_needed<16, int>
|
-7.40% |
16.894 |
15.644 |
0.001 |
-7.41% |
0.001 |
|
MultiSource/Applications/lambda-0.1.3/lambda
Profile
|
-7.34% |
15.887 |
14.722 |
0.010 |
-7.23% |
0.010 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint16_t_To_uint64_t_
|
-7.30% |
25027.004 |
23199.914 |
56.516 |
-7.15% |
56.516 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_DIFF_PREDICT_LAMBDA/171
|
-7.26% |
11.981 |
11.111 |
0.087 |
-7.30% |
0.087 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIND_FIRST_MIN_RAW/171
|
-7.22% |
1.497 |
1.389 |
0.000 |
-7.19% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC128
|
-7.22% |
173.330 |
160.815 |
0.004 |
-7.22% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint8_t>/127
|
-7.20% |
138.912 |
128.913 |
0.003 |
-7.20% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC7
|
-7.08% |
70.709 |
65.700 |
0.005 |
-7.09% |
0.005 |
|
SingleSource/Benchmarks/Misc/pi
Profile
|
-7.03% |
1.783 |
1.657 |
0.000 |
-7.01% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC15
|
-6.94% |
45.052 |
41.923 |
0.028 |
-6.94% |
0.028 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint64_t_To_uint32_t_
|
-6.91% |
18548.805 |
17266.908 |
248.220 |
-3.07% |
248.220 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC15
|
-6.90% |
54.441 |
50.685 |
0.002 |
-6.90% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC1
|
-6.81% |
88.969 |
82.913 |
1.121 |
-6.82% |
1.121 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC31
|
-6.72% |
74.459 |
69.457 |
0.002 |
-6.72% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC63
|
-6.56% |
114.508 |
106.999 |
0.057 |
-6.56% |
0.057 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_HYDRO_2D_RAW/171
|
-6.54% |
88.633 |
82.836 |
0.079 |
-6.53% |
0.079 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_xor_runtime_checks_fail<16, int>
|
-6.52% |
28.784 |
26.907 |
0.001 |
-6.52% |
0.001 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_xor_runtime_checks_pass<16, int>
|
-6.52% |
28.783 |
26.906 |
0.001 |
-6.52% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_only_autovec_int32_t_
|
-6.46% |
180942.228 |
169246.546 |
446.681 |
-6.56% |
446.681 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC128
|
-6.44% |
68.827 |
64.397 |
0.024 |
-6.41% |
0.024 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_HYDRO_1D_LAMBDA/5001
|
-6.41% |
17.188 |
16.086 |
0.036 |
-6.33% |
0.036 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC127
|
-6.41% |
194.627 |
182.156 |
0.284 |
-6.40% |
0.284 |
|
MicroBenchmarks/ImageProcessing/Dilate/Dilate.test:BENCHMARK_DILATE/256
|
-6.39% |
1060.274 |
992.525 |
19.292 |
-7.00% |
19.292 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC127
|
-6.38% |
68.827 |
64.436 |
0.005 |
-5.65% |
0.005 |
|
SingleSource/Benchmarks/Misc/flops-6
Profile
|
-6.36% |
1.310 |
1.227 |
0.001 |
-6.54% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC15
|
-6.35% |
39.420 |
36.918 |
0.001 |
-6.35% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint16_t>/127
|
-6.30% |
138.913 |
130.156 |
0.005 |
-6.30% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC31
|
-6.27% |
912.078 |
854.849 |
14.660 |
-6.78% |
14.660 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_BAND_LIN_EQ_RAW/5001
|
-6.26% |
21.504 |
20.158 |
0.087 |
-2.25% |
0.087 |
|
SingleSource/Benchmarks/Misc-C++/Large/sphereflake
Profile
|
-6.25% |
20.017 |
18.766 |
0.003 |
-6.18% |
0.003 |
|
External/SPEC/CFP2017rate/538.imagick_r/538.imagick_r
Profile
|
-6.24% |
291.297 |
273.128 |
0.879 |
-6.49% |
0.879 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC16
|
-6.14% |
40.669 |
38.171 |
0.017 |
-6.15% |
0.017 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIND_FIRST_MIN_RAW/5001
|
-6.05% |
45.182 |
42.449 |
0.149 |
-6.37% |
0.149 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC63
|
-5.97% |
73.874 |
69.462 |
0.006 |
-6.41% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint8_t>/65
|
-5.92% |
95.111 |
89.483 |
0.005 |
-5.92% |
0.005 |
|
MultiSource/Benchmarks/MiBench/telecomm-gsm/telecomm-gsm
Profile
|
-5.91% |
0.663 |
0.624 |
0.000 |
-5.98% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint32_t>/127
|
-5.88% |
138.293 |
130.156 |
0.003 |
-5.88% |
0.003 |
|
SingleSource/Benchmarks/Misc/oourafft
Profile
|
-5.86% |
15.383 |
14.483 |
0.045 |
-4.05% |
0.045 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC16
|
-5.67% |
33.165 |
31.285 |
0.003 |
-5.66% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint32_t_To_uint64_t_
|
-5.65% |
21322.175 |
20118.012 |
116.804 |
-6.21% |
116.804 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC32
|
-5.63% |
44.426 |
41.923 |
0.002 |
-5.64% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC32
|
-5.63% |
44.427 |
41.925 |
0.001 |
-5.64% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC31
|
-5.59% |
45.067 |
42.550 |
0.001 |
-5.58% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC31
|
-5.56% |
45.053 |
42.547 |
0.003 |
-5.56% |
0.003 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C++/miniFE/miniFE
Profile
|
-5.54% |
15.809 |
14.933 |
0.099 |
-6.48% |
0.099 |
|
MultiSource/Benchmarks/Rodinia/hotspot/hotspot
Profile
|
-5.53% |
2.037 |
1.924 |
0.004 |
-5.49% |
0.004 |
|
MultiSource/Benchmarks/SciMark2-C/scimark2
Profile
|
-5.48% |
107.696 |
101.796 |
0.014 |
-5.43% |
0.014 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint32_t>/999
|
-5.38% |
696.451 |
658.947 |
0.066 |
-5.39% |
0.066 |
|
SingleSource/Benchmarks/Polybench/stencils/jacobi-2d/jacobi-2d
Profile
|
-5.34% |
32.052 |
30.341 |
0.167 |
-5.84% |
0.167 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint8_t_To_uint16_t_
|
-5.33% |
3627.519 |
3434.251 |
3.607 |
-5.48% |
3.607 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC7
|
-5.31% |
70.711 |
66.955 |
0.004 |
-5.32% |
0.004 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_PIC_2D_RAW/171
|
-5.31% |
13.582 |
12.861 |
0.050 |
-5.01% |
0.050 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopWithReductionTC1
|
-5.27% |
11.889 |
11.262 |
0.001 |
-5.27% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint32_t>/999
|
-5.22% |
1364.977 |
1293.661 |
0.115 |
-5.23% |
0.115 |
|
MicroBenchmarks/ImageProcessing/Dilate/Dilate.test:BENCHMARK_DILATE/512
|
-5.18% |
3593.260 |
3407.015 |
61.213 |
-4.94% |
61.213 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC32
|
-5.13% |
24.405 |
23.152 |
0.001 |
-5.12% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC32
|
-5.13% |
24.404 |
23.152 |
0.001 |
-5.14% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC32
|
-5.13% |
61.323 |
58.177 |
0.008 |
-5.13% |
0.008 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC31
|
-5.13% |
24.402 |
23.152 |
0.001 |
-5.13% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC31
|
-5.12% |
24.402 |
23.152 |
0.000 |
-5.12% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIND_FIRST_MIN_RAW/44217
|
-5.11% |
389.097 |
369.215 |
0.063 |
-5.23% |
0.063 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC15
|
-5.11% |
128.256 |
121.707 |
0.005 |
-5.11% |
0.005 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_PIC_2D_LAMBDA/171
|
-5.08% |
13.458 |
12.774 |
0.081 |
-5.36% |
0.081 |
|
SingleSource/Benchmarks/Stanford/Puzzle
Profile
|
-5.08% |
0.241 |
0.229 |
0.002 |
-5.05% |
0.002 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_BAND_LIN_EQ_LAMBDA/5001
|
-5.06% |
21.277 |
20.201 |
0.069 |
-2.88% |
0.069 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC31
|
-5.05% |
241.213 |
229.041 |
0.001 |
-5.05% |
0.001 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_FLOYD_DITHER/256
|
-4.96% |
1835.979 |
1744.957 |
2.870 |
0.66% |
2.870 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_PRESSURE_CALC_RAW/44217
|
-4.91% |
501.028 |
476.418 |
2.345 |
-5.13% |
2.345 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint32_t>/256
|
-4.82% |
364.189 |
346.626 |
0.026 |
-4.82% |
0.026 |
|
SingleSource/Benchmarks/Misc/revertBits
Profile
|
-4.70% |
0.641 |
0.611 |
0.000 |
-4.70% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint16_t>/65
|
-4.61% |
95.114 |
90.732 |
0.005 |
-4.61% |
0.005 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_runtime_checks_pass<16, int>
|
-4.60% |
54.437 |
51.935 |
0.002 |
-4.60% |
0.002 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_runtime_checks_fail<16, int>
|
-4.59% |
54.436 |
51.937 |
0.001 |
-4.60% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopWithReductionTC2
|
-4.51% |
13.765 |
13.145 |
0.003 |
-4.51% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC31
|
-4.46% |
70.078 |
66.954 |
0.003 |
-4.46% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC3
|
-4.36% |
14.392 |
13.765 |
0.001 |
-4.36% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC2
|
-4.36% |
14.392 |
13.765 |
0.001 |
-4.35% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC4
|
-4.35% |
14.393 |
13.766 |
0.001 |
-4.35% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC16
|
-4.35% |
14.392 |
13.766 |
0.077 |
-4.36% |
0.077 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC15
|
-4.35% |
14.393 |
13.767 |
0.001 |
-4.35% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC7
|
-4.35% |
14.392 |
13.766 |
0.001 |
-4.35% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC1
|
-4.35% |
14.391 |
13.766 |
0.001 |
-4.35% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC3
|
-4.35% |
14.392 |
13.766 |
0.001 |
-4.35% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC16
|
-4.35% |
14.391 |
13.766 |
0.001 |
-4.35% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC1
|
-4.35% |
14.393 |
13.767 |
0.001 |
-4.35% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC2
|
-4.35% |
14.392 |
13.766 |
0.000 |
-4.35% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC4
|
-4.35% |
14.392 |
13.766 |
0.001 |
-4.35% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC7
|
-4.34% |
14.392 |
13.767 |
0.001 |
-4.35% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC15
|
-4.34% |
14.392 |
13.767 |
0.005 |
-4.35% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC8
|
-4.34% |
14.391 |
13.766 |
0.000 |
-4.35% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC8
|
-4.34% |
14.391 |
13.767 |
0.000 |
-4.35% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_nested_cond_load_novec_int32_t_
|
-4.29% |
650015.773 |
622113.469 |
81.951 |
-3.57% |
81.951 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC127
|
-4.28% |
3121.074 |
2987.558 |
40.465 |
-4.51% |
40.465 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC128
|
-4.28% |
2968.176 |
2841.276 |
38.023 |
-4.47% |
38.023 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint64_t>/999
|
-4.27% |
1811.323 |
1733.988 |
0.187 |
-4.27% |
0.187 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_ENERGY_CALC_LAMBDA/171
|
-4.24% |
14.211 |
13.608 |
0.012 |
-4.49% |
0.012 |
|
SingleSource/Benchmarks/Misc/flops-5
Profile
|
-4.23% |
2.022 |
1.937 |
0.001 |
-4.18% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_ENERGY_CALC_RAW/171
|
-4.20% |
14.208 |
13.611 |
0.017 |
-4.42% |
0.017 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC63
|
-4.19% |
43.407 |
41.590 |
0.057 |
-3.94% |
0.057 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint64_t>/999
|
-4.19% |
3595.740 |
3445.224 |
0.373 |
-4.16% |
0.373 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint64_t>/256
|
-4.09% |
935.551 |
897.321 |
0.063 |
-4.09% |
0.063 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint8_t_To_uint64_t_
|
-4.07% |
23485.128 |
22529.416 |
6.028 |
-4.06% |
6.028 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint64_t_To_uint32_t_
|
-4.04% |
19417.705 |
18633.121 |
45.783 |
-3.42% |
45.783 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC31
|
-4.03% |
61.945 |
59.446 |
0.003 |
-4.04% |
0.003 |
|
External/SPEC/CFP2017rate/519.lbm_r/519.lbm_r
Profile
|
-4.01% |
199.951 |
191.928 |
1.602 |
-4.36% |
1.602 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_only_autovec_uint8_t_
|
-3.99% |
96172.522 |
92336.978 |
5.367 |
-3.97% |
5.367 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC16
|
-3.98% |
31.287 |
30.042 |
0.097 |
-3.98% |
0.097 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint32_t>/65
|
-3.97% |
94.480 |
90.729 |
0.003 |
-3.98% |
0.003 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<31, EqZero, First>
|
-3.97% |
3346.339 |
3213.512 |
4.379 |
-3.97% |
4.379 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC32
|
-3.96% |
63.201 |
60.696 |
0.003 |
-3.96% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint32_t>/256
|
-3.95% |
221.509 |
212.751 |
0.006 |
-3.95% |
0.006 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_ADI_LAMBDA/44217
|
-3.87% |
19992.879 |
19218.781 |
280.016 |
-2.34% |
280.016 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC3
|
-3.85% |
16.269 |
15.642 |
0.001 |
-3.85% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC32
|
-3.79% |
747.634 |
719.328 |
10.922 |
-4.17% |
10.922 |
|
MultiSource/Benchmarks/TSVC/Symbolics-dbl/Symbolics-dbl
Profile
|
-3.77% |
9.790 |
9.421 |
0.081 |
-2.26% |
0.081 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC64
|
-3.71% |
43.179 |
41.578 |
0.059 |
-3.70% |
0.059 |
|
SingleSource/Benchmarks/Shootout/Shootout-matrix
Profile
|
-3.68% |
3.863 |
3.721 |
0.000 |
-3.68% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint32_t_To_uint16_t_
|
-3.68% |
9830.916 |
9468.809 |
45.357 |
-4.16% |
45.357 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC63
|
-3.66% |
1732.566 |
1669.085 |
18.521 |
-3.92% |
18.521 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint64_t>/256
|
-3.65% |
514.352 |
495.601 |
0.007 |
-3.65% |
0.007 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC64
|
-3.60% |
69.457 |
66.955 |
0.002 |
-3.61% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC64
|
-3.60% |
69.456 |
66.957 |
0.002 |
-3.60% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC63
|
-3.57% |
70.085 |
67.581 |
0.003 |
-3.58% |
0.003 |
|
SingleSource/Benchmarks/BenchmarkGame/n-body
Profile
|
-3.57% |
2.731 |
2.634 |
0.000 |
21.71% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC63
|
-3.56% |
70.077 |
67.582 |
0.004 |
-3.57% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint8_t>/16
|
-3.54% |
59.943 |
57.819 |
0.435 |
7.43% |
0.435 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<32, EqZero, Last>
|
-3.53% |
7066.863 |
6817.372 |
61.777 |
-3.34% |
61.777 |
|
MultiSource/Applications/JM/lencod/lencod
Profile
|
-3.43% |
32.727 |
31.605 |
0.017 |
-2.87% |
0.017 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC31
|
-3.41% |
60.248 |
58.193 |
0.000 |
-3.46% |
0.000 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_runtime_checks_fail<4, int>
|
-3.33% |
15.857 |
15.329 |
0.001 |
-3.64% |
0.001 |
|
MultiSource/Benchmarks/nbench/nbench
Profile
|
-3.32% |
6.108 |
5.905 |
0.002 |
-3.62% |
0.002 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_EOS_LAMBDA/5001
|
-3.31% |
30.746 |
29.728 |
0.379 |
0.17% |
0.379 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_INT_PREDICT_LAMBDA/5001
|
-3.29% |
936.382 |
905.620 |
6.994 |
0.10% |
6.994 |
|
External/SPEC/CFP2017rate/544.nab_r/544.nab_r
Profile
|
-3.27% |
476.293 |
460.697 |
0.072 |
-3.60% |
0.072 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint16_t_To_uint8_t_
|
-3.27% |
2873.081 |
2779.111 |
2.393 |
-3.44% |
2.393 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint16_t>/999
|
-3.16% |
515.008 |
498.723 |
0.030 |
-3.16% |
0.030 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1BigLoopWithReductionTC1
|
-3.13% |
20.023 |
19.397 |
0.001 |
-3.14% |
0.001 |
|
SingleSource/Benchmarks/Shootout/Shootout-lists
Profile
|
-3.12% |
11.315 |
10.962 |
0.002 |
-3.10% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchVecWithRuntimeChecks4PointersDBeforeA/1000
|
-3.08% |
5020230.791 |
4865677.069 |
461.688 |
-3.07% |
461.688 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<31, GreaterThanZero, Last>
|
-3.07% |
8354.826 |
8098.638 |
0.567 |
-2.37% |
0.567 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_ENERGY_CALC_LAMBDA/5001
|
-3.06% |
437.844 |
424.426 |
4.819 |
-3.11% |
4.819 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC32
|
-3.05% |
31.287 |
30.333 |
0.061 |
-3.05% |
0.061 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint16_t_To_uint8_t_
|
-3.02% |
4512.349 |
4376.152 |
15.241 |
-3.12% |
15.241 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, LessThanZero, None>
|
-2.92% |
37600.758 |
36502.557 |
10.038 |
-2.86% |
10.038 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint16_t>/999
|
-2.84% |
1013.739 |
984.958 |
0.111 |
-2.85% |
0.111 |
|
MultiSource/Benchmarks/Rodinia/pathfinder/pathfinder
Profile
|
-2.83% |
1.259 |
1.223 |
0.009 |
-2.77% |
0.009 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC64
|
-2.81% |
111.377 |
108.245 |
0.013 |
-2.82% |
0.013 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC1
|
-2.77% |
22.527 |
21.902 |
0.002 |
-2.77% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC1
|
-2.77% |
22.525 |
21.901 |
0.002 |
-2.77% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopTC16
|
-2.73% |
277.817 |
270.239 |
1.663 |
-2.16% |
1.663 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C/CoMD/CoMD
Profile
|
-2.70% |
9.901 |
9.634 |
0.002 |
-2.68% |
0.002 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_ENERGY_CALC_RAW/5001
|
-2.69% |
436.052 |
424.304 |
1.942 |
-1.03% |
1.942 |
|
MultiSource/Benchmarks/FreeBench/mason/mason
Profile
|
-2.69% |
0.553 |
0.538 |
0.000 |
-2.76% |
0.000 |
|
SingleSource/Benchmarks/Misc-C++/oopack_v1p8
Profile
|
-2.66% |
0.480 |
0.467 |
0.000 |
-9.98% |
0.000 |
|
MultiSource/Benchmarks/FreeBench/pcompress2/pcompress2
Profile
|
-2.64% |
0.404 |
0.393 |
0.001 |
-2.82% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC31
|
-2.64% |
93.235 |
90.776 |
0.249 |
-3.28% |
0.249 |
|
MultiSource/Benchmarks/mafft/pairlocalalign
Profile
|
-2.64% |
94.055 |
91.576 |
0.287 |
-2.64% |
0.287 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC63
|
-2.61% |
120.143 |
117.010 |
0.007 |
-2.61% |
0.007 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint8_t>/10
|
-2.56% |
48.807 |
47.555 |
0.019 |
2.46% |
0.019 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint8_t_To_uint32_t_
|
-2.55% |
7077.650 |
6897.148 |
1.943 |
-2.55% |
1.943 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint64_t_To_uint8_t_
|
-2.54% |
19793.399 |
19290.383 |
26.683 |
-2.78% |
26.683 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<16, EqZero, None>
|
-2.49% |
8220.390 |
8015.982 |
76.461 |
-1.98% |
76.461 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchVecWithRuntimeChecks4PointersDBeforeA/32
|
-2.45% |
166192.891 |
162126.110 |
14.060 |
-2.45% |
14.060 |
|
MultiSource/Benchmarks/sim/sim
Profile
|
-2.43% |
9.697 |
9.461 |
0.013 |
-2.47% |
0.013 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_ENERGY_CALC_LAMBDA/44217
|
-2.40% |
4321.244 |
4217.739 |
25.495 |
-2.47% |
25.495 |
|
MultiSource/Benchmarks/FreeBench/fourinarow/fourinarow
Profile
|
-2.38% |
0.651 |
0.635 |
0.000 |
-2.34% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC63
|
-2.33% |
107.001 |
104.502 |
0.002 |
-2.34% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_only_autovec_int64_t_
|
-2.32% |
1447355.325 |
1413757.230 |
508.350 |
-2.30% |
508.350 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<64, GreaterThanZero, Mid>
|
-2.31% |
2755.725 |
2692.107 |
7.543 |
-1.95% |
7.543 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC64
|
-2.30% |
108.246 |
105.751 |
0.004 |
-2.31% |
0.004 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_FLOYD_DITHER/128
|
-2.29% |
438.838 |
428.787 |
0.198 |
-2.43% |
0.198 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint32_t_To_uint64_t_
|
-2.28% |
26400.802 |
25798.177 |
47.569 |
-1.84% |
47.569 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC32
|
-2.28% |
49.946 |
48.809 |
0.177 |
-2.48% |
0.177 |
|
SingleSource/Benchmarks/BenchmarkGame/puzzle
Profile
|
-2.27% |
0.871 |
0.851 |
0.004 |
-2.02% |
0.004 |
|
MultiSource/Benchmarks/TSVC/Recurrences-dbl/Recurrences-dbl
Profile
|
-2.19% |
10.181 |
9.957 |
0.084 |
-3.86% |
0.084 |
|
SingleSource/Benchmarks/Misc/flops-1
Profile
|
-2.17% |
9.002 |
8.806 |
0.000 |
-2.15% |
0.000 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_FLOYD_DITHER/512
|
-2.12% |
6647.811 |
6506.561 |
22.064 |
-2.09% |
22.064 |
|
MultiSource/Benchmarks/Olden/health/health
Profile
|
-2.12% |
1.591 |
1.558 |
0.005 |
-2.13% |
0.005 |
|
SingleSource/Benchmarks/Misc-C++/Large/ray
Profile
|
-2.11% |
12.104 |
11.849 |
0.001 |
-2.08% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC128
|
-2.10% |
119.519 |
117.011 |
0.004 |
-2.10% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC128
|
-2.09% |
119.515 |
117.014 |
0.003 |
-2.10% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC127
|
-2.09% |
120.141 |
117.632 |
0.008 |
-2.09% |
0.008 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC127
|
-2.08% |
120.136 |
117.634 |
0.005 |
-2.08% |
0.005 |
|
MultiSource/Benchmarks/Fhourstones-3.1/fhourstones3.1
Profile
|
-2.07% |
3.990 |
3.908 |
0.011 |
-1.60% |
0.011 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<32, GreaterThanZero, None>
|
-2.03% |
4501.509 |
4410.289 |
14.952 |
-0.42% |
14.952 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_EOS_RAW/171
|
-1.97% |
0.873 |
0.856 |
0.001 |
-1.73% |
0.001 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C/SimpleMOC/SimpleMOC
Profile
|
-1.96% |
10.415 |
10.211 |
0.024 |
-1.87% |
0.024 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC15
|
-1.96% |
44.678 |
43.802 |
0.002 |
-1.42% |
0.002 |
|
MicroBenchmarks/ImageProcessing/Blur/blur.test:BENCHMARK_boxBlurKernel/512
|
-1.96% |
6629.803 |
6499.834 |
34.868 |
-1.72% |
34.868 |
|
External/SPEC/CFP2017rate/511.povray_r/511.povray_r
Profile
|
-1.89% |
34.056 |
33.410 |
0.025 |
-1.11% |
0.025 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<64, EqZero, Mid>
|
-1.85% |
2735.108 |
2684.409 |
12.487 |
-2.18% |
12.487 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint16_t>/256
|
-1.85% |
272.835 |
267.796 |
0.025 |
-1.85% |
0.025 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_EOS_LAMBDA/171
|
-1.82% |
0.871 |
0.855 |
0.001 |
-1.78% |
0.001 |
|
MultiSource/Benchmarks/Bullet/bullet
Profile
|
-1.73% |
30.426 |
29.900 |
0.141 |
-1.74% |
0.141 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_INT_PREDICT_LAMBDA/171
|
-1.72% |
6.926 |
6.807 |
0.019 |
-1.70% |
0.019 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1LoopWithReductionTC3
|
-1.71% |
12.732 |
12.515 |
0.006 |
5.25% |
0.006 |
|
External/SPEC/CINT2017rate/531.deepsjeng_r/531.deepsjeng_r
Profile
|
-1.71% |
260.073 |
255.632 |
0.089 |
-1.72% |
0.089 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_INT_PREDICT_RAW/171
|
-1.71% |
6.926 |
6.808 |
0.010 |
-1.69% |
0.010 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint64_t>/51
|
-1.69% |
148.298 |
145.794 |
0.013 |
-1.69% |
0.013 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint16_t_To_uint32_t_
|
-1.66% |
11313.892 |
11126.169 |
13.025 |
-1.91% |
13.025 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_csa_with_cond_arith_autovec_int64_t_
|
-1.64% |
746528.367 |
734285.750 |
905.355 |
-1.43% |
905.355 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<32, LessThanZero, Mid>
|
-1.62% |
4570.740 |
4496.867 |
11.302 |
-1.62% |
11.302 |
|
MultiSource/Benchmarks/tramp3d-v4/tramp3d-v4
Profile
|
-1.61% |
1.075 |
1.057 |
0.004 |
-1.71% |
0.004 |
|
MultiSource/Benchmarks/VersaBench/ecbdes/ecbdes
Profile
|
-1.60% |
5.141 |
5.058 |
0.003 |
-1.58% |
0.003 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<31, EqZero, None>
|
-1.58% |
8000.742 |
7874.661 |
33.134 |
-1.51% |
33.134 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_nested_cond_load_novec_uint8_t_
|
-1.57% |
504512.973 |
496585.786 |
118.063 |
-1.61% |
118.063 |
|
SingleSource/Benchmarks/Misc/mandel-2
Profile
|
-1.56% |
2.536 |
2.496 |
0.000 |
-1.55% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_csa_with_in_loop_arith_novec_int64_t_
|
-1.55% |
1028143.713 |
1012222.256 |
368.162 |
-1.55% |
368.162 |
|
MultiSource/Benchmarks/ASC_Sequoia/AMGmk/AMGmk
Profile
|
-1.51% |
33.297 |
32.793 |
0.017 |
-0.80% |
0.017 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_PRESSURE_CALC_LAMBDA/44217
|
-1.51% |
496.942 |
489.461 |
0.436 |
-1.82% |
0.436 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC128
|
-1.50% |
211.535 |
208.356 |
0.012 |
-1.49% |
0.012 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC63
|
-1.49% |
47.639 |
46.929 |
0.080 |
2.73% |
0.080 |
|
External/SPEC/CINT2017rate/525.x264_r/525.x264_r
Profile
|
-1.47% |
129.636 |
127.731 |
0.172 |
-1.32% |
0.172 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint32_t>/10
|
-1.44% |
57.879 |
57.048 |
0.030 |
-0.00% |
0.030 |
|
MicroBenchmarks/Builtins/Int128/Builtins.test:BM_RemainderIntrinsic128UniformDivisor<__int128_t>
|
-1.43% |
66.940 |
65.983 |
0.215 |
-0.37% |
0.215 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, LessThanZero, Mid>
|
-1.42% |
56563.821 |
55760.011 |
147.939 |
-1.36% |
147.939 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C++/PENNANT/PENNANT
Profile
|
-1.39% |
4.795 |
4.729 |
0.022 |
-1.84% |
0.022 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC127
|
-1.39% |
220.291 |
217.238 |
0.093 |
-1.38% |
0.093 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint64_t>/51
|
-1.37% |
229.023 |
225.886 |
0.011 |
-1.36% |
0.011 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<6, LessThanZero, Mid>
|
-1.34% |
23823.369 |
23503.900 |
16.379 |
-0.27% |
16.379 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<32, GreaterThanZero, Mid>
|
-1.33% |
4556.232 |
4495.681 |
15.127 |
-1.31% |
15.127 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC31
|
-1.32% |
30.899 |
30.491 |
0.019 |
-2.24% |
0.019 |
|
MultiSource/Benchmarks/MallocBench/cfrac/cfrac
Profile
|
-1.32% |
2.779 |
2.743 |
0.001 |
-1.35% |
0.001 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<16, EqZero, Mid>
|
-1.31% |
8657.856 |
8544.112 |
12.678 |
-1.31% |
12.678 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC127
|
-1.28% |
197.115 |
194.595 |
0.011 |
-1.27% |
0.011 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC128
|
-1.25% |
198.361 |
195.876 |
0.013 |
-1.26% |
0.013 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint8_t_To_uint32_t_
|
-1.25% |
12089.671 |
11939.102 |
39.078 |
-1.51% |
39.078 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<3, GreaterThanZero, None>
|
-1.21% |
44923.021 |
44380.127 |
92.936 |
-1.69% |
92.936 |
|
SingleSource/Benchmarks/Shootout-C++/Shootout-C++-heapsort
Profile
|
-1.19% |
22.235 |
21.971 |
0.043 |
-0.13% |
0.043 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<16, LessThanZero, Last>
|
-1.19% |
13142.435 |
12986.633 |
3.832 |
-1.18% |
3.832 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<3, EqZero, Mid>
|
-1.18% |
37614.128 |
37169.892 |
68.995 |
-1.14% |
68.995 |
|
External/SPEC/CFP2017rate/526.blender_r/526.blender_r
Profile
|
-1.14% |
890.522 |
880.338 |
2.314 |
-0.55% |
2.314 |
|
SingleSource/Benchmarks/SmallPT/smallpt
Profile
|
-1.12% |
30.042 |
29.705 |
0.001 |
-1.08% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_sinhf_novec_float_
|
-1.09% |
2241.813 |
2217.268 |
0.635 |
-1.10% |
0.635 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_sinhf_autovec_float_
|
-1.08% |
2241.678 |
2217.382 |
1.048 |
-1.13% |
1.048 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_csa_with_cond_arith_novec_int64_t_
|
-1.06% |
743612.755 |
735756.972 |
912.820 |
-1.20% |
912.820 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<8, LessThanZero, Mid>
|
-1.04% |
19443.499 |
19241.012 |
9.300 |
-1.00% |
9.300 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC63
|
-1.02% |
129.725 |
128.395 |
0.086 |
-1.36% |
0.086 |