|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_INT_PREDICT_RAW/44217
|
-54.21% |
17457.130 |
7993.303 |
91.748 |
-11.67% |
91.748 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint64_t_To_uint32_t_
|
-51.28% |
35036.317 |
17070.049 |
362.606 |
-51.66% |
362.606 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint64_t_To_uint16_t_
|
-49.65% |
35755.667 |
18003.607 |
555.269 |
-49.54% |
555.269 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint64_t_To_uint8_t_
|
-48.86% |
37110.648 |
18978.740 |
19.642 |
-48.79% |
19.642 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C/miniGMG/miniGMG
Profile
|
-48.75% |
8.976 |
4.600 |
0.577 |
-49.95% |
0.577 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_DIFF_PREDICT_RAW/44217
|
-44.50% |
24259.899 |
13463.319 |
285.966 |
-42.22% |
285.966 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint16_t_To_uint64_t_
|
-44.03% |
18655.233 |
10441.956 |
3.666 |
-44.09% |
3.666 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_DIFF_PREDICT_LAMBDA/44217
|
-41.92% |
23169.082 |
13455.526 |
336.277 |
-41.76% |
336.277 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint8_t_To_uint64_t_
|
-40.85% |
17771.831 |
10511.809 |
12.423 |
-40.94% |
12.423 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint64_t_To_uint32_t_
|
-40.84% |
38277.169 |
22646.420 |
25.387 |
-40.65% |
25.387 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_DIFF_PREDICT_RAW/5001
|
-40.42% |
2540.051 |
1513.442 |
16.695 |
-41.22% |
16.695 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_DIFF_PREDICT_LAMBDA/5001
|
-40.20% |
2539.831 |
1518.905 |
34.511 |
-39.47% |
34.511 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIRST_DIFF_RAW/44217
|
-38.78% |
166.306 |
101.819 |
2.545 |
-28.54% |
2.545 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/32
|
-36.70% |
1396.219 |
883.831 |
0.137 |
-36.69% |
0.137 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/64
|
-36.67% |
6180.603 |
3914.255 |
1.609 |
-36.69% |
1.609 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/16
|
-36.64% |
279.504 |
177.100 |
0.006 |
-36.63% |
0.006 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/256
|
-36.18% |
107108.738 |
68353.975 |
44.446 |
-36.21% |
44.446 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/128
|
-36.11% |
26264.478 |
16781.216 |
2.382 |
-36.12% |
2.382 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint32_t_To_uint64_t_
|
-35.76% |
22863.975 |
14687.850 |
395.281 |
-35.37% |
395.281 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint64_t_To_uint8_t_
|
-34.48% |
30250.467 |
19820.038 |
43.476 |
-34.18% |
43.476 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint64_t_To_uint16_t_
|
-34.29% |
29026.098 |
19072.668 |
30.687 |
-34.12% |
30.687 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, EqZero, None>
|
-31.24% |
20513.758 |
14104.755 |
0.403 |
-31.23% |
0.403 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIRST_DIFF_LAMBDA/44217
|
-30.41% |
143.940 |
100.168 |
5.238 |
-30.83% |
5.238 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint64_t_To_uint16_t_
|
-28.50% |
25909.049 |
18524.821 |
36.680 |
-28.47% |
36.680 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint32_t_To_uint8_t_
|
-28.07% |
13490.782 |
9703.892 |
32.648 |
-27.96% |
32.648 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC128
|
-28.01% |
1293.308 |
931.096 |
6.154 |
-27.98% |
6.154 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC64
|
-27.43% |
654.423 |
474.923 |
3.181 |
-27.34% |
3.181 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC32
|
-27.28% |
334.363 |
243.159 |
1.692 |
-27.18% |
1.692 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_PIC_2D_RAW/44217
|
-27.27% |
11879.621 |
8639.673 |
955.612 |
-22.97% |
955.612 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC128
|
-27.00% |
558.607 |
407.775 |
0.015 |
-26.86% |
0.015 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC16
|
-26.64% |
174.316 |
127.880 |
0.719 |
-26.42% |
0.719 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC64
|
-25.62% |
291.983 |
217.163 |
0.048 |
-25.59% |
0.048 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint64_t_To_uint8_t_
|
-24.52% |
27211.494 |
20540.370 |
81.122 |
-24.55% |
81.122 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, EqZero, None>
|
-23.98% |
16023.934 |
12180.704 |
0.403 |
-23.98% |
0.403 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIRST_SUM_RAW/44217
|
-23.86% |
176.581 |
134.457 |
0.725 |
-19.17% |
0.725 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC32
|
-23.22% |
158.928 |
122.025 |
0.027 |
-23.19% |
0.027 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC128
|
-23.21% |
603.991 |
463.802 |
0.033 |
-23.21% |
0.033 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC128
|
-23.10% |
603.934 |
464.414 |
0.027 |
-23.10% |
0.027 |
|
MicroBenchmarks/ImageProcessing/Blur/blur.test:BENCHMARK_boxBlurKernel/1024
|
-22.61% |
30062.168 |
23265.983 |
36.393 |
-22.83% |
36.393 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC64
|
-22.35% |
313.513 |
243.441 |
0.014 |
-22.35% |
0.014 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint16_t_To_uint64_t_
|
-22.20% |
13317.238 |
10361.235 |
3.972 |
-21.56% |
3.972 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC127
|
-22.17% |
615.260 |
478.842 |
0.022 |
-22.17% |
0.022 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC64
|
-22.15% |
313.497 |
244.055 |
0.008 |
-22.15% |
0.008 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC127
|
-21.97% |
615.190 |
480.032 |
0.035 |
-21.97% |
0.035 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint16_t_To_uint32_t_
|
-21.62% |
7105.616 |
5569.605 |
2.801 |
-21.57% |
2.801 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint8_t_To_uint32_t_
|
-21.58% |
6581.816 |
5161.314 |
3.376 |
-21.59% |
3.376 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_only_autovec_uint8_t_
|
-21.41% |
182415.331 |
143354.606 |
22.826 |
-21.39% |
22.826 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_PIC_2D_RAW/5001
|
-21.30% |
1176.051 |
925.603 |
24.055 |
-14.17% |
24.055 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIND_FIRST_MIN_LAMBDA/171
|
-21.29% |
1.501 |
1.181 |
0.000 |
-21.28% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIND_FIRST_MIN_LAMBDA/5001
|
-21.22% |
45.420 |
35.780 |
0.296 |
-20.94% |
0.296 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIND_FIRST_MIN_LAMBDA/44217
|
-21.15% |
389.192 |
306.892 |
0.623 |
-21.22% |
0.623 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC32
|
-20.81% |
168.328 |
133.292 |
0.015 |
-20.81% |
0.015 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC128
|
-20.71% |
275.024 |
218.063 |
0.432 |
-20.63% |
0.432 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC127
|
-20.65% |
274.503 |
217.816 |
0.488 |
-20.93% |
0.488 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC32
|
-20.44% |
168.323 |
133.915 |
0.002 |
-20.45% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC63
|
-20.42% |
324.771 |
258.468 |
0.002 |
-20.42% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC64
|
-20.13% |
150.609 |
120.297 |
0.513 |
-19.06% |
0.513 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC63
|
-20.03% |
324.790 |
259.722 |
0.005 |
-20.04% |
0.005 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_PIC_2D_LAMBDA/44217
|
-19.83% |
10807.147 |
8664.105 |
559.379 |
-20.97% |
559.379 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC127
|
-19.69% |
640.896 |
514.708 |
0.062 |
-19.64% |
0.062 |
|
MultiSource/Benchmarks/MiBench/automotive-bitcount/automotive-bitcount
Profile
|
-19.36% |
0.125 |
0.101 |
0.003 |
-18.42% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC16
|
-19.28% |
92.253 |
74.467 |
0.034 |
-19.30% |
0.034 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint16_t_To_uint8_t_
|
-19.12% |
3819.257 |
3088.930 |
0.136 |
-19.10% |
0.136 |
|
SingleSource/Benchmarks/Adobe-C++/loop_unroll
Profile
|
-18.94% |
2.987 |
2.421 |
0.001 |
-22.08% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC63
|
-18.88% |
150.579 |
122.153 |
0.291 |
-18.52% |
0.291 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_VOL3D_CALC_LAMBDA/2
|
-18.80% |
8.757 |
7.110 |
0.000 |
-18.80% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_VOL3D_CALC_RAW/2
|
-18.79% |
8.757 |
7.112 |
0.000 |
-18.78% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint64_t_To_uint32_t_
|
-18.72% |
27110.563 |
22035.739 |
21.779 |
-18.54% |
21.779 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint32_t_To_uint16_t_
|
-18.62% |
13813.664 |
11240.923 |
11.299 |
-18.59% |
11.299 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC64
|
-18.56% |
297.868 |
242.587 |
2.026 |
-18.52% |
2.026 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC32
|
-18.52% |
87.604 |
71.381 |
0.499 |
-16.34% |
0.499 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint32_t_To_uint8_t_
|
-18.35% |
13900.226 |
11350.192 |
22.427 |
-18.35% |
22.427 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC16
|
-18.30% |
95.733 |
78.216 |
0.004 |
-18.30% |
0.004 |
|
MultiSource/Benchmarks/Trimaran/enc-pc1/enc-pc1
Profile
|
-18.16% |
1.105 |
0.904 |
0.000 |
-18.14% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_with_cond_arith_novec_uint8_t_
|
-17.90% |
746138.101 |
612580.853 |
113.199 |
-17.86% |
113.199 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC32
|
-17.88% |
161.433 |
132.568 |
0.790 |
-17.86% |
0.790 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC16
|
-17.82% |
93.235 |
76.616 |
0.627 |
-17.73% |
0.627 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC128
|
-17.71% |
570.760 |
469.669 |
1.235 |
-17.69% |
1.235 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC16
|
-17.64% |
95.731 |
78.843 |
0.004 |
-17.65% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC31
|
-17.41% |
179.581 |
148.310 |
0.004 |
-17.42% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC4
|
-17.38% |
17.522 |
14.476 |
0.008 |
-17.37% |
0.008 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_with_cond_arith_novec_int32_t_
|
-17.30% |
739562.385 |
611586.457 |
1287.070 |
-17.37% |
1287.070 |
|
MultiSource/Benchmarks/MiBench/security-rijndael/security-rijndael
Profile
|
-17.24% |
0.335 |
0.277 |
0.001 |
-17.18% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIRST_SUM_LAMBDA/44217
|
-16.82% |
163.015 |
135.597 |
0.406 |
-18.85% |
0.406 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint8_t_To_uint64_t_
|
-16.72% |
13096.009 |
10906.448 |
36.384 |
-16.52% |
36.384 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC31
|
-16.71% |
179.576 |
149.560 |
0.006 |
-16.72% |
0.006 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_VOL3D_CALC_LAMBDA/0
|
-16.26% |
1268.457 |
1062.162 |
1.047 |
-16.21% |
1.047 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_VOL3D_CALC_RAW/0
|
-16.24% |
1267.937 |
1062.083 |
0.911 |
-16.05% |
0.911 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_VOL3D_CALC_RAW/1
|
-16.14% |
260.035 |
218.053 |
0.144 |
-16.18% |
0.144 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_VOL3D_CALC_LAMBDA/1
|
-16.09% |
260.185 |
218.314 |
0.158 |
-16.09% |
0.158 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_HYDRO_1D_LAMBDA/171
|
-16.01% |
0.443 |
0.372 |
0.000 |
-15.87% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_HYDRO_1D_RAW/171
|
-15.82% |
0.442 |
0.372 |
0.000 |
-15.84% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC127
|
-15.78% |
605.827 |
510.249 |
2.743 |
-15.77% |
2.743 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint16_t_To_uint32_t_
|
-15.68% |
7462.928 |
6292.639 |
13.558 |
-15.67% |
13.558 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC8
|
-15.63% |
58.822 |
49.628 |
0.056 |
-15.55% |
0.056 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint32_t_To_uint64_t_
|
-15.48% |
18065.048 |
15269.188 |
835.152 |
-11.21% |
835.152 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, EqZero, First>
|
-15.40% |
16670.915 |
14103.908 |
0.876 |
-15.40% |
0.876 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC31
|
-15.40% |
87.272 |
73.837 |
1.162 |
-14.26% |
1.162 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_no_runtime_checks_needed<16, int>
|
-15.39% |
24.402 |
20.647 |
0.001 |
-15.39% |
0.001 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, EqZero, Mid>
|
-15.37% |
16665.839 |
14104.072 |
0.765 |
-15.37% |
0.765 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, EqZero, Last>
|
-15.35% |
16667.096 |
14108.793 |
1.308 |
-15.35% |
1.308 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint32_t_To_uint8_t_
|
-15.09% |
10658.524 |
9050.678 |
12.707 |
-14.58% |
12.707 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC4
|
-14.81% |
113.471 |
96.668 |
0.896 |
-14.52% |
0.896 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC8
|
-14.74% |
59.446 |
50.686 |
0.004 |
-14.74% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC128
|
-14.57% |
1103.368 |
942.629 |
0.010 |
-14.56% |
0.010 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC127
|
-14.52% |
1095.425 |
936.385 |
0.080 |
-14.51% |
0.080 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_with_cond_arith_novec_int64_t_
|
-14.41% |
793676.584 |
679338.431 |
2223.699 |
-13.79% |
2223.699 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC64
|
-14.37% |
562.556 |
481.723 |
0.077 |
-14.33% |
0.077 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC63
|
-14.23% |
554.579 |
475.639 |
0.472 |
-14.26% |
0.472 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint32_t_To_uint8_t_
|
-14.15% |
11064.991 |
9498.826 |
32.772 |
-14.65% |
32.772 |
|
SingleSource/Benchmarks/Misc/salsa20
Profile
|
-14.14% |
15.386 |
13.210 |
0.001 |
-14.13% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint8_t_To_uint16_t_
|
-14.11% |
3757.618 |
3227.404 |
1.778 |
-14.09% |
1.778 |
|
External/SPEC/CFP2017rate/508.namd_r/508.namd_r
Profile
|
-14.05% |
224.617 |
193.069 |
0.943 |
-13.65% |
0.943 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC32
|
-14.03% |
292.212 |
251.216 |
0.164 |
-13.96% |
0.164 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint64_t_To_uint8_t_
|
-13.94% |
22111.333 |
19028.475 |
48.306 |
-13.69% |
48.306 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_with_cond_arith_autovec_int64_t_
|
-13.91% |
791634.549 |
681518.318 |
981.730 |
-13.91% |
981.730 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC4
|
-13.86% |
51.939 |
44.737 |
0.002 |
-13.86% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC1
|
-13.86% |
51.938 |
44.739 |
0.002 |
-13.85% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC2
|
-13.86% |
51.940 |
44.742 |
0.001 |
-13.85% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC7
|
-13.86% |
51.937 |
44.741 |
0.002 |
-13.85% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC3
|
-13.85% |
51.934 |
44.740 |
0.001 |
-13.85% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC8
|
-13.85% |
51.934 |
44.744 |
0.003 |
-13.85% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint32_t_To_uint16_t_
|
-13.78% |
12852.902 |
11081.721 |
21.268 |
-13.67% |
21.268 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC31
|
-13.72% |
284.073 |
245.103 |
0.093 |
-13.72% |
0.093 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC8
|
-13.69% |
59.447 |
51.308 |
0.003 |
-13.69% |
0.003 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, EqZero, First>
|
-13.62% |
14102.142 |
12180.821 |
0.711 |
-13.63% |
0.711 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, EqZero, Mid>
|
-13.62% |
14102.750 |
12181.430 |
0.660 |
-13.63% |
0.660 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, EqZero, Last>
|
-13.62% |
14103.596 |
12183.310 |
0.291 |
-13.62% |
0.291 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint32_t_To_uint16_t_
|
-13.59% |
9909.901 |
8562.833 |
478.060 |
-13.55% |
478.060 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC8
|
-13.53% |
23.152 |
20.020 |
0.002 |
-13.53% |
0.002 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIRST_SUM_RAW/5001
|
-13.40% |
20.151 |
17.450 |
0.346 |
0.60% |
0.346 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC63
|
-13.39% |
374.370 |
324.253 |
0.202 |
-13.40% |
0.202 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC16
|
-13.32% |
156.968 |
136.061 |
0.172 |
-13.32% |
0.172 |
|
MicroBenchmarks/ImageProcessing/Dilate/Dilate.test:BENCHMARK_DILATE/1024
|
-13.27% |
7418.955 |
6434.762 |
134.573 |
-9.50% |
134.573 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC8
|
-13.15% |
23.777 |
20.650 |
0.001 |
-13.16% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC128
|
-13.08% |
81.348 |
70.709 |
0.002 |
-13.08% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint8_t_To_uint16_t_
|
-12.97% |
4542.751 |
3953.401 |
0.401 |
-12.96% |
0.401 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC15
|
-12.91% |
148.941 |
129.720 |
0.203 |
-12.83% |
0.203 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC15
|
-12.87% |
107.001 |
93.232 |
0.008 |
-12.87% |
0.008 |
|
SingleSource/Benchmarks/Shootout-C++/Shootout-C++-matrix
Profile
|
-12.75% |
2.509 |
2.189 |
0.000 |
-12.71% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC63
|
-12.75% |
332.903 |
290.472 |
0.106 |
-12.72% |
0.106 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC16
|
-12.42% |
51.936 |
45.485 |
0.143 |
-12.43% |
0.143 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint16_t_To_uint8_t_
|
-12.41% |
4742.815 |
4154.293 |
0.385 |
-12.41% |
0.385 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC8
|
-11.99% |
89.411 |
78.686 |
0.076 |
-11.98% |
0.076 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC2
|
-11.77% |
21.276 |
18.771 |
0.001 |
-11.77% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC15
|
-11.69% |
107.006 |
94.492 |
0.001 |
-11.70% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC16
|
-11.69% |
33.165 |
29.289 |
0.056 |
-11.68% |
0.056 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC15
|
-11.68% |
51.936 |
45.869 |
0.060 |
-11.69% |
0.060 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC3
|
-11.12% |
22.527 |
20.023 |
0.000 |
-11.11% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC4
|
-11.12% |
22.527 |
20.023 |
0.002 |
-11.11% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC4
|
-11.11% |
22.525 |
20.022 |
0.002 |
-11.12% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC7
|
-11.00% |
81.355 |
72.404 |
0.088 |
-10.96% |
0.088 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint8_t>/51
|
-10.99% |
123.901 |
110.286 |
0.417 |
19.22% |
0.417 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_INT_PREDICT_LAMBDA/44217
|
-10.68% |
9020.735 |
8056.901 |
69.141 |
-3.37% |
69.141 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_BAND_LIN_EQ_LAMBDA/171
|
-10.61% |
0.384 |
0.343 |
0.000 |
-6.33% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC4
|
-10.61% |
41.298 |
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 |
48.183 |
0.002 |
-10.47% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint8_t_To_uint16_t_
|
-10.24% |
5856.881 |
5257.411 |
3.380 |
-10.14% |
3.380 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIRST_DIFF_RAW/5001
|
-10.20% |
12.909 |
11.593 |
0.441 |
-3.84% |
0.441 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/16
|
-10.18% |
115.472 |
103.718 |
0.008 |
-10.17% |
0.008 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC4
|
-10.11% |
55.690 |
50.061 |
0.002 |
-10.06% |
0.002 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_DIFF_PREDICT_RAW/171
|
-10.10% |
12.355 |
11.107 |
0.042 |
-6.92% |
0.042 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/64
|
-10.07% |
1913.318 |
1720.626 |
1.647 |
-10.07% |
1.647 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/32
|
-9.98% |
472.971 |
425.748 |
0.037 |
-9.99% |
0.037 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/256
|
-9.90% |
31449.708 |
28335.238 |
5.891 |
-9.90% |
5.891 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_only_autovec_int64_t_
|
-9.90% |
333743.028 |
300701.817 |
371.402 |
-9.78% |
371.402 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/128
|
-9.83% |
7913.676 |
7136.057 |
7.392 |
-9.87% |
7.392 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_INT_PREDICT_RAW/5001
|
-9.78% |
1003.158 |
905.083 |
7.321 |
-0.91% |
7.321 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC8
|
-9.76% |
25.655 |
23.151 |
0.001 |
-9.76% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC8
|
-9.75% |
25.653 |
23.152 |
0.000 |
-9.76% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC127
|
-9.72% |
101.890 |
91.982 |
0.003 |
-9.71% |
0.003 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_PIC_2D_LAMBDA/5001
|
-9.72% |
1045.133 |
943.577 |
14.812 |
-14.65% |
14.812 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC7
|
-9.62% |
32.540 |
29.409 |
0.002 |
-9.62% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC7
|
-9.54% |
26.283 |
23.776 |
0.003 |
-9.54% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC32
|
-9.53% |
53.190 |
48.119 |
0.026 |
-9.54% |
0.026 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC7
|
-9.53% |
26.281 |
23.776 |
0.002 |
-9.53% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC31
|
-9.49% |
196.464 |
177.815 |
0.102 |
-9.50% |
0.102 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_DEL_DOT_VEC_2D_LAMBDA/1
|
-9.23% |
287.007 |
260.522 |
0.150 |
-9.26% |
0.150 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC8
|
-9.21% |
26.879 |
24.403 |
0.001 |
-9.32% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_DEL_DOT_VEC_2D_RAW/1
|
-9.21% |
287.005 |
260.577 |
0.103 |
-9.20% |
0.103 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC7
|
-9.17% |
354.620 |
322.118 |
4.765 |
-9.19% |
4.765 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC4
|
-9.09% |
41.300 |
37.545 |
0.001 |
-9.09% |
0.001 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_runtime_checks_pass<4, int>
|
-9.00% |
16.847 |
15.330 |
0.000 |
-8.25% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC7
|
-8.90% |
28.159 |
25.654 |
0.001 |
-8.90% |
0.001 |
|
MultiSource/Benchmarks/FreeBench/pifft/pifft
Profile
|
-8.83% |
0.359 |
0.328 |
0.001 |
-8.67% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_DEL_DOT_VEC_2D_LAMBDA/2
|
-8.70% |
3.510 |
3.204 |
0.000 |
-8.70% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_DEL_DOT_VEC_2D_RAW/2
|
-8.69% |
3.509 |
3.204 |
0.000 |
-8.71% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint16_t_To_uint8_t_
|
-8.65% |
6819.611 |
6229.516 |
3.790 |
-8.60% |
3.790 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC16
|
-8.62% |
36.292 |
33.162 |
0.004 |
-8.63% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC8
|
-8.52% |
29.410 |
26.905 |
0.003 |
-8.52% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint16_t_To_uint64_t_
|
-8.46% |
20225.492 |
18514.459 |
140.880 |
-8.08% |
140.880 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint64_t_To_uint16_t_
|
-8.45% |
19298.390 |
17666.832 |
211.678 |
-6.94% |
211.678 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_DEL_DOT_VEC_2D_RAW/0
|
-8.30% |
1807.667 |
1657.616 |
2.931 |
-7.95% |
2.931 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC2
|
-8.20% |
38.171 |
35.042 |
0.002 |
-8.20% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC64
|
-8.06% |
93.240 |
85.728 |
0.001 |
-8.06% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_DEL_DOT_VEC_2D_LAMBDA/0
|
-8.00% |
1802.454 |
1658.177 |
5.149 |
-7.47% |
5.149 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC127
|
-7.95% |
2430.774 |
2237.621 |
37.902 |
-7.79% |
37.902 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC3
|
-7.91% |
47.558 |
43.798 |
0.003 |
-7.90% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint8_t_To_uint32_t_
|
-7.89% |
12794.613 |
11784.716 |
5.259 |
-7.78% |
5.259 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_PRESSURE_CALC_LAMBDA/5001
|
-7.86% |
46.238 |
42.603 |
0.597 |
-3.12% |
0.597 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint8_t>/28
|
-7.86% |
82.601 |
76.108 |
0.678 |
12.60% |
0.678 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_BAND_LIN_EQ_LAMBDA/5001
|
-7.85% |
21.796 |
20.085 |
0.060 |
-3.43% |
0.060 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC16
|
-7.85% |
31.913 |
29.408 |
0.002 |
-7.85% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC16
|
-7.85% |
31.914 |
29.410 |
0.000 |
-7.84% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC32
|
-7.81% |
40.047 |
36.918 |
0.001 |
-7.82% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC15
|
-7.70% |
32.539 |
30.034 |
0.001 |
-7.70% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC15
|
-7.69% |
32.536 |
30.035 |
0.001 |
-7.69% |
0.001 |
|
MultiSource/Benchmarks/VersaBench/beamformer/beamformer
Profile
|
-7.58% |
5.202 |
4.808 |
0.001 |
-7.56% |
0.001 |
|
MultiSource/Benchmarks/Trimaran/enc-md5/enc-md5
Profile
|
-7.56% |
3.508 |
3.243 |
0.000 |
-7.51% |
0.000 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_xor_no_runtime_checks_needed<16, int>
|
-7.40% |
16.893 |
15.644 |
0.001 |
-7.41% |
0.001 |
|
MultiSource/Applications/lambda-0.1.3/lambda
Profile
|
-7.38% |
15.895 |
14.722 |
0.007 |
-7.23% |
0.007 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_PRESSURE_CALC_RAW/5001
|
-7.30% |
45.221 |
41.919 |
1.274 |
-6.01% |
1.274 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC128
|
-7.22% |
173.338 |
160.823 |
0.002 |
-7.22% |
0.002 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIND_FIRST_MIN_RAW/171
|
-7.22% |
1.497 |
1.389 |
0.000 |
-7.18% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint8_t>/127
|
-7.20% |
138.908 |
128.905 |
0.001 |
-7.20% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint16_t_To_uint64_t_
|
-7.13% |
25005.511 |
23221.975 |
32.351 |
-7.06% |
32.351 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC7
|
-7.09% |
70.712 |
65.701 |
0.005 |
-7.09% |
0.005 |
|
SingleSource/Benchmarks/Misc/pi
Profile
|
-7.03% |
1.783 |
1.657 |
0.000 |
-7.02% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_HYDRO_2D_RAW/171
|
-7.02% |
88.277 |
82.079 |
0.592 |
-7.39% |
0.592 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC15
|
-6.95% |
45.055 |
41.922 |
0.007 |
-6.95% |
0.007 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC15
|
-6.89% |
54.440 |
50.686 |
0.002 |
-6.90% |
0.002 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_HYDRO_2D_LAMBDA/171
|
-6.82% |
88.026 |
82.021 |
0.451 |
-7.49% |
0.451 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC63
|
-6.80% |
74.526 |
69.459 |
0.003 |
-6.42% |
0.003 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_BAND_LIN_EQ_RAW/5001
|
-6.77% |
21.516 |
20.060 |
0.395 |
-2.73% |
0.395 |
|
MultiSource/Benchmarks/TSVC/ControlLoops-dbl/ControlLoops-dbl
Profile
|
-6.76% |
11.307 |
10.543 |
0.091 |
-4.32% |
0.091 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC31
|
-6.73% |
74.463 |
69.454 |
0.005 |
-6.73% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC31
|
-6.66% |
915.816 |
854.789 |
12.686 |
-6.78% |
12.686 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC1
|
-6.61% |
88.969 |
83.087 |
0.799 |
-6.63% |
0.799 |
|
SingleSource/Benchmarks/Misc/flops-6
Profile
|
-6.56% |
1.313 |
1.227 |
0.000 |
-6.49% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC63
|
-6.56% |
114.511 |
107.002 |
0.059 |
-6.56% |
0.059 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_xor_runtime_checks_fail<16, int>
|
-6.53% |
28.783 |
26.905 |
0.003 |
-6.53% |
0.003 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_DIFF_PREDICT_LAMBDA/171
|
-6.52% |
11.864 |
11.090 |
0.032 |
-7.48% |
0.032 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_only_autovec_int32_t_
|
-6.52% |
181160.940 |
169345.365 |
105.672 |
-6.50% |
105.672 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_xor_runtime_checks_pass<16, int>
|
-6.52% |
28.781 |
26.906 |
0.001 |
-6.52% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC127
|
-6.41% |
68.803 |
64.391 |
0.027 |
-5.71% |
0.027 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC128
|
-6.38% |
68.832 |
64.439 |
0.006 |
-6.34% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC15
|
-6.36% |
39.422 |
36.916 |
0.002 |
-6.36% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint16_t>/127
|
-6.30% |
138.904 |
130.154 |
0.004 |
-6.30% |
0.004 |
|
SingleSource/Benchmarks/Misc-C++/Large/sphereflake
Profile
|
-6.22% |
20.014 |
18.769 |
0.002 |
-6.17% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC16
|
-6.15% |
40.673 |
38.170 |
0.002 |
-6.16% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC127
|
-6.08% |
194.626 |
182.802 |
0.073 |
-6.07% |
0.073 |
|
External/SPEC/CFP2017rate/538.imagick_r/538.imagick_r
Profile
|
-6.04% |
291.277 |
273.670 |
0.739 |
-6.30% |
0.739 |
|
MultiSource/Benchmarks/MiBench/telecomm-gsm/telecomm-gsm
Profile
|
-6.01% |
0.663 |
0.623 |
0.001 |
-6.02% |
0.001 |
|
SingleSource/Benchmarks/Polybench/stencils/jacobi-2d/jacobi-2d
Profile
|
-5.97% |
32.219 |
30.295 |
0.159 |
-5.99% |
0.159 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint8_t>/65
|
-5.91% |
95.109 |
89.485 |
0.003 |
-5.92% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint32_t>/127
|
-5.89% |
138.290 |
130.145 |
0.008 |
-5.89% |
0.008 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIND_FIRST_MIN_RAW/5001
|
-5.85% |
45.179 |
42.535 |
0.113 |
-6.18% |
0.113 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC16
|
-5.67% |
33.165 |
31.285 |
0.002 |
-5.66% |
0.002 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C++/miniFE/miniFE
Profile
|
-5.67% |
15.838 |
14.941 |
0.081 |
-6.44% |
0.081 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC32
|
-5.64% |
44.429 |
41.925 |
0.004 |
-5.64% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC32
|
-5.63% |
44.425 |
41.926 |
0.004 |
-5.63% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC31
|
-5.58% |
45.064 |
42.549 |
0.003 |
-5.58% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint8_t_To_uint16_t_
|
-5.56% |
3630.500 |
3428.646 |
4.529 |
-5.63% |
4.529 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC31
|
-5.55% |
45.051 |
42.551 |
0.001 |
-5.55% |
0.001 |
|
MultiSource/Benchmarks/SciMark2-C/scimark2
Profile
|
-5.47% |
107.680 |
101.785 |
0.008 |
-5.44% |
0.008 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint32_t>/999
|
-5.39% |
696.503 |
658.927 |
0.031 |
-5.40% |
0.031 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_PIC_2D_LAMBDA/171
|
-5.38% |
13.475 |
12.750 |
0.063 |
-5.54% |
0.063 |
|
SingleSource/Benchmarks/Stanford/Puzzle
Profile
|
-5.37% |
0.241 |
0.228 |
0.001 |
-5.45% |
0.001 |
|
MicroBenchmarks/ImageProcessing/Dilate/Dilate.test:BENCHMARK_DILATE/512
|
-5.37% |
3598.917 |
3405.758 |
57.735 |
-4.97% |
57.735 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC7
|
-5.31% |
70.705 |
66.951 |
0.003 |
-5.33% |
0.003 |
|
MultiSource/Benchmarks/McCat/12-IOtest/iotest
Profile
|
-5.31% |
1.805 |
1.709 |
0.022 |
-6.35% |
0.022 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_PIC_2D_RAW/171
|
-5.31% |
13.547 |
12.828 |
0.064 |
-5.25% |
0.064 |
|
SingleSource/Benchmarks/Misc/oourafft
Profile
|
-5.30% |
15.419 |
14.603 |
0.058 |
-3.25% |
0.058 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIND_FIRST_MIN_RAW/44217
|
-5.28% |
389.373 |
368.820 |
0.502 |
-5.33% |
0.502 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC15
|
-5.27% |
128.269 |
121.510 |
0.100 |
-5.26% |
0.100 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopWithReductionTC1
|
-5.26% |
11.889 |
11.263 |
0.001 |
-5.26% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint32_t_To_uint64_t_
|
-5.26% |
21402.665 |
20277.168 |
15.381 |
-5.47% |
15.381 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint32_t>/999
|
-5.23% |
1365.039 |
1293.591 |
0.114 |
-5.23% |
0.114 |
|
MultiSource/Benchmarks/Rodinia/hotspot/hotspot
Profile
|
-5.17% |
2.036 |
1.931 |
0.004 |
-5.17% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC31
|
-5.13% |
24.403 |
23.152 |
0.001 |
-5.13% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC31
|
-5.13% |
24.402 |
23.151 |
0.001 |
-5.13% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC32
|
-5.13% |
24.403 |
23.152 |
0.002 |
-5.12% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC32
|
-5.12% |
61.317 |
58.176 |
0.009 |
-5.13% |
0.009 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC32
|
-5.12% |
24.402 |
23.153 |
0.001 |
-5.13% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_PRESSURE_CALC_RAW/44217
|
-5.02% |
500.635 |
475.522 |
2.410 |
-5.31% |
2.410 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC31
|
-5.02% |
241.147 |
229.051 |
0.005 |
-5.05% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint32_t>/256
|
-4.81% |
364.167 |
346.645 |
0.012 |
-4.81% |
0.012 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_FLOYD_DITHER/256
|
-4.70% |
1812.834 |
1727.715 |
15.497 |
-0.34% |
15.497 |
|
SingleSource/Benchmarks/Misc/revertBits
Profile
|
-4.68% |
0.641 |
0.611 |
0.000 |
-4.68% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC64
|
-4.68% |
43.793 |
41.744 |
0.014 |
-3.31% |
0.014 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_runtime_checks_pass<16, int>
|
-4.60% |
54.437 |
51.930 |
0.004 |
-4.61% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint16_t>/65
|
-4.60% |
95.114 |
90.736 |
0.004 |
-4.60% |
0.004 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_runtime_checks_fail<16, int>
|
-4.59% |
54.436 |
51.936 |
0.003 |
-4.60% |
0.003 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIRST_DIFF_LAMBDA/171
|
-4.59% |
0.275 |
0.262 |
0.003 |
-5.28% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopWithReductionTC2
|
-4.52% |
13.766 |
13.143 |
0.011 |
-4.53% |
0.011 |
|
MultiSource/Benchmarks/TSVC/NodeSplitting-dbl/NodeSplitting-dbl
Profile
|
-4.48% |
27.104 |
25.890 |
0.091 |
-1.99% |
0.091 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC128
|
-4.47% |
2975.462 |
2842.521 |
39.366 |
-4.43% |
39.366 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC31
|
-4.47% |
70.081 |
66.951 |
0.004 |
-4.47% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_nested_cond_load_novec_int32_t_
|
-4.46% |
649933.658 |
620917.889 |
792.128 |
-3.76% |
792.128 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC127
|
-4.45% |
3129.063 |
2989.813 |
41.213 |
-4.44% |
41.213 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC16
|
-4.36% |
31.406 |
30.037 |
0.051 |
-4.00% |
0.051 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC7
|
-4.36% |
14.392 |
13.765 |
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:benchAutoVecForLoopTC4
|
-4.35% |
14.391 |
13.765 |
0.001 |
-4.36% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC16
|
-4.35% |
14.392 |
13.766 |
0.001 |
-4.35% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC7
|
-4.35% |
14.392 |
13.766 |
0.000 |
-4.35% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC2
|
-4.35% |
14.392 |
13.766 |
0.001 |
-4.35% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_ENERGY_CALC_LAMBDA/171
|
-4.35% |
14.247 |
13.628 |
0.032 |
-4.35% |
0.032 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC2
|
-4.35% |
14.392 |
13.766 |
0.000 |
-4.35% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC3
|
-4.35% |
14.392 |
13.766 |
0.000 |
-4.35% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC1
|
-4.35% |
14.392 |
13.766 |
0.000 |
-4.35% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC4
|
-4.35% |
14.392 |
13.766 |
0.001 |
-4.35% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC3
|
-4.35% |
14.391 |
13.766 |
0.001 |
-4.35% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC8
|
-4.35% |
14.392 |
13.766 |
0.000 |
-4.35% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC8
|
-4.34% |
14.391 |
13.766 |
0.000 |
-4.35% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC15
|
-4.34% |
14.391 |
13.767 |
0.000 |
-4.35% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC15
|
-4.34% |
14.391 |
13.766 |
0.001 |
-4.35% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC16
|
-4.34% |
14.391 |
13.766 |
0.031 |
-4.35% |
0.031 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint64_t>/999
|
-4.27% |
1811.180 |
1733.932 |
0.312 |
-4.27% |
0.312 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopTC16
|
-4.22% |
278.796 |
267.018 |
2.202 |
-3.33% |
2.202 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint8_t>/16
|
-4.21% |
60.063 |
57.535 |
0.484 |
6.91% |
0.484 |
|
SingleSource/Benchmarks/Misc/flops-5
Profile
|
-4.19% |
2.022 |
1.937 |
0.001 |
-4.15% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC32
|
-4.16% |
750.558 |
719.313 |
11.131 |
-4.18% |
11.131 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint64_t>/999
|
-4.16% |
3594.668 |
3445.168 |
0.285 |
-4.16% |
0.285 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint64_t>/256
|
-4.07% |
935.483 |
897.403 |
0.022 |
-4.08% |
0.022 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC31
|
-4.04% |
61.943 |
59.440 |
0.007 |
-4.04% |
0.007 |
|
MicroBenchmarks/ImageProcessing/Dilate/Dilate.test:BENCHMARK_DILATE/256
|
-4.02% |
1057.795 |
1015.250 |
8.789 |
-4.87% |
8.789 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_ENERGY_CALC_RAW/171
|
-3.99% |
14.203 |
13.636 |
0.013 |
-4.25% |
0.013 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_only_autovec_uint8_t_
|
-3.99% |
96169.585 |
92331.815 |
6.676 |
-3.98% |
6.676 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint32_t>/65
|
-3.97% |
94.480 |
90.733 |
0.003 |
-3.97% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC32
|
-3.95% |
63.196 |
60.697 |
0.003 |
-3.96% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint32_t>/256
|
-3.95% |
221.494 |
212.741 |
0.018 |
-3.96% |
0.018 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint8_t_To_uint64_t_
|
-3.94% |
23468.762 |
22544.079 |
18.963 |
-4.00% |
18.963 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC3
|
-3.85% |
16.270 |
15.643 |
0.000 |
-3.84% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint32_t_To_uint16_t_
|
-3.85% |
9827.951 |
9449.986 |
48.252 |
-4.35% |
48.252 |
|
External/SPEC/CFP2017rate/519.lbm_r/519.lbm_r
Profile
|
-3.84% |
200.014 |
192.343 |
1.264 |
-4.15% |
1.264 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC63
|
-3.79% |
43.181 |
41.542 |
0.064 |
-4.05% |
0.064 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<31, EqZero, First>
|
-3.74% |
3342.771 |
3217.595 |
2.667 |
-3.85% |
2.667 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_runtime_checks_fail<4, int>
|
-3.72% |
15.922 |
15.330 |
0.001 |
-3.64% |
0.001 |
|
SingleSource/Benchmarks/Shootout/Shootout-matrix
Profile
|
-3.70% |
3.864 |
3.721 |
0.000 |
-3.68% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint16_t_To_uint8_t_
|
-3.69% |
2874.573 |
2768.414 |
4.778 |
-3.81% |
4.778 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_ENERGY_CALC_LAMBDA/5001
|
-3.68% |
434.811 |
418.794 |
1.669 |
-4.39% |
1.669 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint64_t_To_uint32_t_
|
-3.65% |
19343.102 |
18637.258 |
65.718 |
-3.40% |
65.718 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint64_t>/256
|
-3.64% |
514.371 |
495.627 |
0.022 |
-3.65% |
0.022 |
|
MultiSource/Benchmarks/Rodinia/pathfinder/pathfinder
Profile
|
-3.63% |
1.265 |
1.219 |
0.010 |
-3.05% |
0.010 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC64
|
-3.61% |
69.457 |
66.950 |
0.003 |
-3.61% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC63
|
-3.59% |
70.095 |
67.578 |
0.004 |
-3.59% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC64
|
-3.59% |
69.451 |
66.957 |
0.001 |
-3.60% |
0.001 |
|
SingleSource/Benchmarks/BenchmarkGame/n-body
Profile
|
-3.59% |
2.731 |
2.633 |
0.000 |
21.69% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC63
|
-3.58% |
70.083 |
67.577 |
0.002 |
-3.58% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC63
|
-3.56% |
1643.562 |
1585.126 |
21.276 |
-3.56% |
21.276 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIRST_SUM_LAMBDA/5001
|
-3.48% |
18.444 |
17.802 |
0.211 |
1.10% |
0.211 |
|
MultiSource/Applications/JM/lencod/lencod
Profile
|
-3.42% |
32.734 |
31.616 |
0.014 |
-2.84% |
0.014 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC31
|
-3.31% |
60.185 |
58.193 |
0.004 |
-3.46% |
0.004 |
|
MultiSource/Benchmarks/nbench/nbench
Profile
|
-3.30% |
6.106 |
5.905 |
0.001 |
-3.62% |
0.001 |
|
External/SPEC/CFP2017rate/544.nab_r/544.nab_r
Profile
|
-3.26% |
476.274 |
460.763 |
0.070 |
-3.58% |
0.070 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_PRESSURE_CALC_LAMBDA/44217
|
-3.22% |
491.753 |
475.919 |
3.673 |
-4.54% |
3.673 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint16_t>/999
|
-3.16% |
514.970 |
498.696 |
0.042 |
-3.17% |
0.042 |
|
SingleSource/Benchmarks/Shootout/Shootout-lists
Profile
|
-3.13% |
11.316 |
10.961 |
0.002 |
-3.10% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint16_t_To_uint8_t_
|
-3.13% |
4514.182 |
4372.766 |
5.143 |
-3.20% |
5.143 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1BigLoopWithReductionTC1
|
-3.13% |
20.023 |
19.397 |
0.003 |
-3.14% |
0.003 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<16, EqZero, None>
|
-3.09% |
8271.989 |
8016.375 |
73.197 |
-1.97% |
73.197 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchVecWithRuntimeChecks4PointersDBeforeA/1000
|
-3.09% |
5020205.914 |
4865193.271 |
150.907 |
-3.08% |
150.907 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<32, EqZero, Last>
|
-3.08% |
7044.401 |
6827.542 |
68.421 |
-3.20% |
68.421 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, LessThanZero, None>
|
-3.07% |
37687.041 |
36528.772 |
8.817 |
-2.79% |
8.817 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC63
|
-2.99% |
1735.953 |
1684.012 |
14.277 |
-3.06% |
14.277 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint16_t>/999
|
-2.85% |
1013.835 |
984.949 |
0.073 |
-2.85% |
0.073 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<32, EqZero, None>
|
-2.84% |
4459.143 |
4332.570 |
16.210 |
-1.79% |
16.210 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC64
|
-2.81% |
111.384 |
108.255 |
0.003 |
-2.81% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC1
|
-2.77% |
22.526 |
21.902 |
0.000 |
-2.77% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC1
|
-2.77% |
22.526 |
21.902 |
0.003 |
-2.77% |
0.003 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_ENERGY_CALC_RAW/5001
|
-2.75% |
433.032 |
421.102 |
3.038 |
-1.78% |
3.038 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C/CoMD/CoMD
Profile
|
-2.73% |
9.903 |
9.633 |
0.008 |
-2.68% |
0.008 |
|
MultiSource/Benchmarks/FreeBench/fourinarow/fourinarow
Profile
|
-2.72% |
0.651 |
0.634 |
0.001 |
-2.62% |
0.001 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<31, GreaterThanZero, Last>
|
-2.68% |
8322.869 |
8099.787 |
22.914 |
-2.36% |
22.914 |
|
MultiSource/Benchmarks/Olden/health/health
Profile
|
-2.64% |
1.598 |
1.555 |
0.003 |
-2.26% |
0.003 |
|
SingleSource/Benchmarks/BenchmarkGame/puzzle
Profile
|
-2.63% |
0.873 |
0.850 |
0.002 |
-2.12% |
0.002 |
|
SingleSource/Benchmarks/Misc-C++/oopack_v1p8
Profile
|
-2.62% |
0.480 |
0.467 |
0.000 |
-9.98% |
0.000 |
|
MultiSource/Benchmarks/FreeBench/mason/mason
Profile
|
-2.62% |
0.553 |
0.538 |
0.000 |
-2.71% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC32
|
-2.61% |
31.284 |
30.466 |
0.012 |
-2.62% |
0.012 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC63
|
-2.59% |
120.132 |
117.015 |
0.008 |
-2.61% |
0.008 |
|
MultiSource/Benchmarks/mafft/pairlocalalign
Profile
|
-2.59% |
94.053 |
91.616 |
0.301 |
-2.60% |
0.301 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC31
|
-2.55% |
93.238 |
90.855 |
0.149 |
-3.19% |
0.149 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint8_t>/10
|
-2.55% |
48.804 |
47.558 |
0.012 |
2.47% |
0.012 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint8_t_To_uint32_t_
|
-2.55% |
7077.899 |
6897.681 |
0.176 |
-2.54% |
0.176 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_FLOYD_DITHER/128
|
-2.55% |
436.473 |
425.360 |
3.205 |
-3.21% |
3.205 |
|
MultiSource/Applications/sgefa/sgefa
Profile
|
-2.52% |
0.577 |
0.562 |
0.005 |
-1.93% |
0.005 |
|
MultiSource/Benchmarks/FreeBench/pcompress2/pcompress2
Profile
|
-2.51% |
0.404 |
0.394 |
0.001 |
-2.65% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC32
|
-2.49% |
50.048 |
48.803 |
0.003 |
-2.50% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchVecWithRuntimeChecks4PointersDBeforeA/32
|
-2.45% |
166199.460 |
162124.661 |
2.730 |
-2.45% |
2.730 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_only_autovec_int64_t_
|
-2.41% |
1447842.903 |
1412881.488 |
1328.310 |
-2.36% |
1328.310 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<64, EqZero, Mid>
|
-2.40% |
2748.885 |
2682.796 |
13.944 |
-2.24% |
13.944 |
|
MultiSource/Benchmarks/sim/sim
Profile
|
-2.39% |
9.701 |
9.469 |
0.005 |
-2.39% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC31
|
-2.38% |
31.200 |
30.457 |
0.025 |
-2.35% |
0.025 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC63
|
-2.34% |
106.997 |
104.493 |
0.004 |
-2.35% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC64
|
-2.32% |
108.249 |
105.741 |
0.004 |
-2.32% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint8_t>/16
|
-2.27% |
86.429 |
84.467 |
0.004 |
11.80% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint32_t_To_uint64_t_
|
-2.27% |
26351.141 |
25753.097 |
35.293 |
-2.01% |
35.293 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C/SimpleMOC/SimpleMOC
Profile
|
-2.25% |
10.431 |
10.196 |
0.068 |
-2.01% |
0.068 |
|
SingleSource/Benchmarks/Misc/flops-1
Profile
|
-2.17% |
9.001 |
8.806 |
0.000 |
-2.15% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint64_t_To_uint8_t_
|
-2.12% |
19735.976 |
19317.756 |
33.357 |
-2.64% |
33.357 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC128
|
-2.10% |
119.519 |
117.006 |
0.007 |
-2.10% |
0.007 |
|
SingleSource/Benchmarks/Misc-C++/Large/ray
Profile
|
-2.10% |
12.104 |
11.850 |
0.001 |
-2.07% |
0.001 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_FLOYD_DITHER/512
|
-2.09% |
6654.646 |
6515.285 |
19.440 |
-1.95% |
19.440 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC128
|
-2.09% |
119.514 |
117.012 |
0.004 |
-2.10% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC127
|
-2.09% |
120.144 |
117.638 |
0.016 |
-2.09% |
0.016 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC127
|
-2.08% |
120.140 |
117.637 |
0.013 |
-2.08% |
0.013 |
|
External/SPEC/CFP2017rate/511.povray_r/511.povray_r
Profile
|
-1.97% |
34.135 |
33.464 |
0.082 |
-0.95% |
0.082 |
|
MultiSource/Benchmarks/Bullet/bullet
Profile
|
-1.90% |
30.381 |
29.803 |
0.189 |
-2.06% |
0.189 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint16_t>/256
|
-1.83% |
272.821 |
267.822 |
0.005 |
-1.84% |
0.005 |
|
MultiSource/Benchmarks/Fhourstones-3.1/fhourstones3.1
Profile
|
-1.81% |
3.981 |
3.909 |
0.009 |
-1.56% |
0.009 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_EOS_RAW/171
|
-1.80% |
0.872 |
0.856 |
0.000 |
-1.72% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_EOS_LAMBDA/171
|
-1.76% |
0.871 |
0.856 |
0.002 |
-1.71% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC63
|
-1.76% |
47.919 |
47.077 |
0.220 |
3.06% |
0.220 |
|
External/SPEC/CINT2017rate/531.deepsjeng_r/531.deepsjeng_r
Profile
|
-1.76% |
259.901 |
255.336 |
0.345 |
-1.84% |
0.345 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_asin_novec_double_
|
-1.75% |
1160.531 |
1140.194 |
7.739 |
0.06% |
7.739 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_INT_PREDICT_RAW/171
|
-1.75% |
6.926 |
6.804 |
0.007 |
-1.74% |
0.007 |
|
MultiSource/Benchmarks/ASC_Sequoia/AMGmk/AMGmk
Profile
|
-1.73% |
33.374 |
32.797 |
0.041 |
-0.79% |
0.041 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_csa_with_cond_arith_autovec_int64_t_
|
-1.70% |
746711.710 |
733993.499 |
451.375 |
-1.47% |
451.375 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_INT_PREDICT_LAMBDA/171
|
-1.70% |
6.923 |
6.805 |
0.003 |
-1.73% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint64_t>/51
|
-1.69% |
148.301 |
145.788 |
0.018 |
-1.70% |
0.018 |
|
MicroBenchmarks/ImageProcessing/Blur/blur.test:BENCHMARK_boxBlurKernel/512
|
-1.67% |
6647.702 |
6536.661 |
12.884 |
-1.16% |
12.884 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_ENERGY_CALC_LAMBDA/44217
|
-1.64% |
4312.580 |
4241.793 |
19.143 |
-1.91% |
19.143 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_nested_cond_load_novec_uint8_t_
|
-1.63% |
504476.150 |
496228.191 |
222.547 |
-1.68% |
222.547 |
|
MultiSource/Benchmarks/VersaBench/ecbdes/ecbdes
Profile
|
-1.63% |
5.141 |
5.057 |
0.001 |
-1.60% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_csa_with_in_loop_arith_novec_int64_t_
|
-1.61% |
1028249.201 |
1011714.961 |
438.098 |
-1.60% |
438.098 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<6, LessThanZero, Mid>
|
-1.59% |
23878.607 |
23499.434 |
17.664 |
-0.29% |
17.664 |
|
MultiSource/Applications/obsequi/Obsequi
Profile
|
-1.59% |
7.700 |
7.577 |
0.031 |
-1.09% |
0.031 |
|
SingleSource/Benchmarks/Misc/mandel-2
Profile
|
-1.57% |
2.536 |
2.496 |
0.000 |
-1.54% |
0.000 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<32, LessThanZero, Mid>
|
-1.57% |
4570.654 |
4499.098 |
15.476 |
-1.57% |
15.476 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<64, EqZero, None>
|
-1.54% |
2938.436 |
2893.158 |
14.941 |
-1.24% |
14.941 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC128
|
-1.51% |
211.509 |
208.324 |
0.026 |
-1.51% |
0.026 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC15
|
-1.45% |
44.447 |
43.804 |
0.003 |
-1.41% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint16_t_To_uint32_t_
|
-1.43% |
11255.674 |
11094.996 |
23.031 |
-2.18% |
23.031 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<32, GreaterThanZero, Mid>
|
-1.41% |
4558.916 |
4494.734 |
6.618 |
-1.33% |
6.618 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC127
|
-1.40% |
220.276 |
217.195 |
0.132 |
-1.40% |
0.132 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<16, GreaterThanZero, First>
|
-1.39% |
8610.608 |
8490.675 |
2.496 |
-0.06% |
2.496 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint64_t>/51
|
-1.38% |
229.047 |
225.880 |
0.002 |
-1.37% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC63
|
-1.32% |
130.049 |
128.327 |
0.108 |
-1.41% |
0.108 |
|
MultiSource/Benchmarks/tramp3d-v4/tramp3d-v4
Profile
|
-1.30% |
1.066 |
1.052 |
0.002 |
-2.16% |
0.002 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C++/PENNANT/PENNANT
Profile
|
-1.30% |
4.803 |
4.741 |
0.015 |
-1.59% |
0.015 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint32_t>/10
|
-1.28% |
57.827 |
57.086 |
0.097 |
0.06% |
0.097 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC127
|
-1.27% |
197.111 |
194.598 |
0.014 |
-1.27% |
0.014 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC128
|
-1.26% |
198.345 |
195.850 |
0.010 |
-1.27% |
0.010 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint8_t_To_uint32_t_
|
-1.25% |
12092.440 |
11941.888 |
13.316 |
-1.49% |
13.316 |
|
MultiSource/Benchmarks/MallocBench/cfrac/cfrac
Profile
|
-1.21% |
2.779 |
2.745 |
0.001 |
-1.25% |
0.001 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<16, LessThanZero, Last>
|
-1.18% |
13143.606 |
12987.994 |
8.252 |
-1.17% |
8.252 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<3, EqZero, Mid>
|
-1.14% |
37592.910 |
37164.892 |
39.191 |
-1.15% |
39.191 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_sinhf_autovec_float_
|
-1.14% |
2242.458 |
2216.985 |
0.347 |
-1.14% |
0.347 |
|
SingleSource/Benchmarks/SmallPT/smallpt
Profile
|
-1.10% |
30.039 |
29.707 |
0.002 |
-1.07% |
0.002 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, LessThanZero, Mid>
|
-1.10% |
56388.136 |
55767.836 |
8.343 |
-1.34% |
8.343 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_ENERGY_CALC_RAW/44217
|
-1.09% |
4330.111 |
4282.760 |
3.885 |
-1.12% |
3.885 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_sinhf_novec_float_
|
-1.08% |
2241.598 |
2217.290 |
0.475 |
-1.10% |
0.475 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_csa_with_cond_arith_novec_int64_t_
|
-1.07% |
743109.405 |
735172.365 |
514.431 |
-1.28% |
514.431 |
|
External/SPEC/CINT2017rate/525.x264_r/525.x264_r
Profile
|
-1.07% |
129.768 |
128.384 |
0.282 |
-0.82% |
0.282 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_csa_with_in_loop_arith_autovec_int32_t_
|
-1.05% |
265464.770 |
262688.902 |
825.708 |
0.42% |
825.708 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<64, LessThanZero, Last>
|
-1.03% |
4178.226 |
4135.198 |
3.352 |
-0.86% |
3.352 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<6, GreaterThanZero, None>
|
-1.03% |
29702.933 |
29397.782 |
15.533 |
-0.61% |
15.533 |