|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_INT_PREDICT_LAMBDA/44217
|
-50.48% |
16363.509 |
8102.563 |
43.476 |
-2.82% |
43.476 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint64_t_To_uint16_t_
|
-50.48% |
35745.539 |
17701.979 |
246.502 |
-50.39% |
246.502 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint64_t_To_uint32_t_
|
-49.81% |
35341.147 |
17739.480 |
529.456 |
-49.77% |
529.456 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_HYDRO_2D_LAMBDA/44217
|
-49.78% |
92115.411 |
46263.103 |
5271.751 |
-49.12% |
5271.751 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint64_t_To_uint8_t_
|
-48.59% |
36947.056 |
18996.090 |
33.426 |
-48.75% |
33.426 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C/miniGMG/miniGMG
Profile
|
-47.76% |
8.732 |
4.561 |
0.234 |
-50.37% |
0.234 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_DIFF_PREDICT_LAMBDA/44217
|
-44.76% |
24492.444 |
13529.257 |
203.882 |
-41.44% |
203.882 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_HYDRO_2D_RAW/44217
|
-44.33% |
91439.718 |
50905.687 |
2702.387 |
-39.87% |
2702.387 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint16_t_To_uint64_t_
|
-44.02% |
18653.759 |
10442.538 |
4.120 |
-44.08% |
4.120 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIRST_DIFF_LAMBDA/44217
|
-43.01% |
175.579 |
100.060 |
1.599 |
-30.91% |
1.599 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_DIFF_PREDICT_RAW/44217
|
-41.87% |
23257.867 |
13518.781 |
301.880 |
-41.98% |
301.880 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint64_t_To_uint32_t_
|
-40.87% |
38322.185 |
22658.440 |
35.589 |
-40.62% |
35.589 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_HYDRO_2D_LAMBDA/5001
|
-40.82% |
9017.487 |
5336.501 |
435.342 |
-41.44% |
435.342 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint8_t_To_uint64_t_
|
-40.77% |
17775.677 |
10529.321 |
3.845 |
-40.85% |
3.845 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_DIFF_PREDICT_RAW/5001
|
-40.64% |
2560.918 |
1520.095 |
16.707 |
-40.96% |
16.707 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_DIFF_PREDICT_LAMBDA/5001
|
-40.15% |
2551.262 |
1526.907 |
30.256 |
-39.15% |
30.256 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_HYDRO_2D_RAW/5001
|
-36.99% |
9221.987 |
5811.095 |
226.420 |
-33.94% |
226.420 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/32
|
-36.70% |
1396.197 |
883.769 |
0.049 |
-36.70% |
0.049 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/64
|
-36.67% |
6181.103 |
3914.248 |
9.075 |
-36.69% |
9.075 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/16
|
-36.63% |
279.456 |
177.095 |
0.010 |
-36.63% |
0.010 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint32_t_To_uint64_t_
|
-36.42% |
22806.876 |
14500.086 |
728.279 |
-36.19% |
728.279 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/256
|
-36.24% |
107130.315 |
68309.300 |
58.656 |
-36.25% |
58.656 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/128
|
-36.09% |
26263.197 |
16785.233 |
9.947 |
-36.11% |
9.947 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_DISC_ORD_LAMBDA/44217
|
-35.20% |
14494.665 |
9392.548 |
868.629 |
-33.17% |
868.629 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint64_t_To_uint8_t_
|
-34.21% |
30142.085 |
19829.624 |
44.255 |
-34.14% |
44.255 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint64_t_To_uint16_t_
|
-34.14% |
28996.228 |
19096.283 |
4.741 |
-34.04% |
4.741 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIRST_DIFF_RAW/44217
|
-31.59% |
148.673 |
101.714 |
0.975 |
-28.62% |
0.975 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, EqZero, None>
|
-31.23% |
20509.731 |
14105.065 |
1.041 |
-31.23% |
1.041 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_DISC_ORD_RAW/44217
|
-29.46% |
14231.169 |
10039.304 |
743.684 |
-24.75% |
743.684 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint64_t_To_uint16_t_
|
-29.04% |
25907.118 |
18382.419 |
82.485 |
-29.02% |
82.485 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC128
|
-27.55% |
1291.941 |
935.983 |
0.245 |
-27.60% |
0.245 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint32_t_To_uint8_t_
|
-27.41% |
13418.957 |
9741.196 |
10.158 |
-27.68% |
10.158 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC64
|
-27.40% |
654.582 |
475.197 |
1.460 |
-27.30% |
1.460 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC32
|
-27.14% |
334.122 |
243.458 |
0.766 |
-27.09% |
0.766 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_PIC_2D_LAMBDA/44217
|
-27.11% |
11837.956 |
8629.211 |
89.451 |
-21.29% |
89.451 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC128
|
-26.65% |
555.926 |
407.763 |
0.004 |
-26.86% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC16
|
-26.51% |
173.809 |
127.733 |
0.357 |
-26.50% |
0.357 |
|
MicroBenchmarks/ImageProcessing/Dilate/Dilate.test:BENCHMARK_DILATE/128
|
-26.22% |
245.977 |
181.494 |
14.202 |
-20.39% |
14.202 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIRST_SUM_LAMBDA/44217
|
-26.06% |
181.645 |
134.305 |
1.085 |
-19.62% |
1.085 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC64
|
-25.25% |
290.495 |
217.139 |
0.040 |
-25.59% |
0.040 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint64_t_To_uint8_t_
|
-24.56% |
27223.992 |
20537.583 |
75.308 |
-24.56% |
75.308 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, EqZero, None>
|
-23.98% |
16023.164 |
12180.675 |
0.504 |
-23.98% |
0.504 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_PIC_2D_RAW/44217
|
-23.59% |
11344.658 |
8668.606 |
87.749 |
-22.71% |
87.749 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC128
|
-23.21% |
603.924 |
463.727 |
0.037 |
-23.22% |
0.037 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC128
|
-23.11% |
603.971 |
464.373 |
0.043 |
-23.11% |
0.043 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC32
|
-23.03% |
158.527 |
122.014 |
0.016 |
-23.20% |
0.016 |
|
MicroBenchmarks/ImageProcessing/Blur/blur.test:BENCHMARK_boxBlurKernel/1024
|
-22.39% |
30078.313 |
23344.643 |
45.448 |
-22.57% |
45.448 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC64
|
-22.35% |
313.505 |
243.424 |
0.007 |
-22.35% |
0.007 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC127
|
-22.18% |
615.239 |
478.793 |
0.028 |
-22.17% |
0.028 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC64
|
-22.16% |
313.515 |
244.040 |
0.014 |
-22.16% |
0.014 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC127
|
-21.97% |
615.208 |
480.029 |
0.024 |
-21.97% |
0.024 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint16_t_To_uint64_t_
|
-21.91% |
13268.954 |
10362.077 |
0.998 |
-21.55% |
0.998 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_PIC_2D_LAMBDA/5001
|
-21.90% |
1148.570 |
897.008 |
44.417 |
-18.86% |
44.417 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint16_t_To_uint32_t_
|
-21.63% |
7109.300 |
5571.600 |
0.691 |
-21.54% |
0.691 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint8_t_To_uint32_t_
|
-21.43% |
6587.116 |
5175.798 |
1.340 |
-21.37% |
1.340 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_only_autovec_uint8_t_
|
-21.35% |
182343.866 |
143411.400 |
23.391 |
-21.35% |
23.391 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIND_FIRST_MIN_LAMBDA/171
|
-21.30% |
1.501 |
1.181 |
0.000 |
-21.28% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIND_FIRST_MIN_LAMBDA/44217
|
-21.27% |
389.516 |
306.649 |
0.305 |
-21.29% |
0.305 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_PIC_2D_RAW/5001
|
-21.27% |
1142.003 |
899.090 |
51.491 |
-16.63% |
51.491 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC32
|
-20.82% |
168.326 |
133.279 |
0.006 |
-20.82% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC127
|
-20.77% |
275.215 |
218.044 |
2.084 |
-20.84% |
2.084 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC128
|
-20.69% |
570.657 |
452.613 |
9.263 |
-20.67% |
9.263 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIND_FIRST_MIN_LAMBDA/5001
|
-20.60% |
45.193 |
35.883 |
0.221 |
-20.71% |
0.221 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC128
|
-20.47% |
274.580 |
218.380 |
1.189 |
-20.51% |
1.189 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC32
|
-20.44% |
168.311 |
133.907 |
0.002 |
-20.45% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC63
|
-20.42% |
324.746 |
258.446 |
0.002 |
-20.43% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC63
|
-20.04% |
324.785 |
259.701 |
0.003 |
-20.04% |
0.003 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_PIC_1D_LAMBDA/44217
|
-20.02% |
13615.965 |
10890.229 |
39.101 |
-19.12% |
39.101 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC32
|
-19.77% |
160.644 |
128.890 |
2.512 |
-20.14% |
2.512 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC127
|
-19.56% |
639.747 |
514.592 |
0.024 |
-19.66% |
0.024 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC64
|
-19.50% |
149.705 |
120.512 |
1.465 |
-18.92% |
1.465 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC16
|
-19.29% |
92.264 |
74.462 |
0.002 |
-19.31% |
0.002 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_INT_PREDICT_LAMBDA/5001
|
-19.11% |
1129.832 |
913.961 |
8.081 |
1.02% |
8.081 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint16_t_To_uint8_t_
|
-19.09% |
3818.372 |
3089.561 |
0.052 |
-19.08% |
0.052 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC64
|
-19.09% |
296.591 |
239.984 |
3.239 |
-19.39% |
3.239 |
|
SingleSource/Benchmarks/Adobe-C++/loop_unroll
Profile
|
-18.99% |
2.983 |
2.416 |
0.002 |
-22.23% |
0.002 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_PIC_1D_RAW/44217
|
-18.94% |
13661.135 |
11074.210 |
12.059 |
-18.14% |
12.059 |
|
MultiSource/Benchmarks/MiBench/automotive-bitcount/automotive-bitcount
Profile
|
-18.93% |
0.124 |
0.101 |
0.001 |
-18.63% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint32_t_To_uint8_t_
|
-18.93% |
13885.925 |
11257.874 |
42.731 |
-19.01% |
42.731 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_VOL3D_CALC_LAMBDA/2
|
-18.80% |
8.757 |
7.111 |
0.000 |
-18.80% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_VOL3D_CALC_RAW/2
|
-18.78% |
8.756 |
7.111 |
0.000 |
-18.79% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint32_t_To_uint16_t_
|
-18.62% |
13800.603 |
11230.464 |
17.632 |
-18.66% |
17.632 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint64_t_To_uint32_t_
|
-18.45% |
27097.903 |
22097.118 |
12.488 |
-18.31% |
12.488 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC16
|
-18.29% |
95.733 |
78.220 |
0.002 |
-18.30% |
0.002 |
|
MultiSource/Benchmarks/Trimaran/enc-pc1/enc-pc1
Profile
|
-18.13% |
1.105 |
0.904 |
0.000 |
-18.10% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC63
|
-18.02% |
151.821 |
124.462 |
1.505 |
-16.98% |
1.505 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_with_cond_arith_novec_uint8_t_
|
-17.88% |
746115.570 |
612679.554 |
188.216 |
-17.85% |
188.216 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC16
|
-17.64% |
95.739 |
78.846 |
0.001 |
-17.64% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC31
|
-17.42% |
179.578 |
148.302 |
0.005 |
-17.42% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_with_cond_arith_novec_int32_t_
|
-17.26% |
739994.228 |
612287.940 |
769.610 |
-17.28% |
769.610 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC4
|
-17.23% |
17.522 |
14.503 |
0.008 |
-17.22% |
0.008 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint8_t_To_uint64_t_
|
-16.98% |
13151.998 |
10919.160 |
4.264 |
-16.42% |
4.264 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC16
|
-16.93% |
92.997 |
77.251 |
0.306 |
-17.05% |
0.306 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIRST_SUM_RAW/44217
|
-16.78% |
163.681 |
136.219 |
0.154 |
-18.11% |
0.154 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC31
|
-16.73% |
179.583 |
149.540 |
0.006 |
-16.73% |
0.006 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_VOL3D_CALC_RAW/0
|
-16.56% |
1268.925 |
1058.826 |
2.542 |
-16.31% |
2.542 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_VOL3D_CALC_LAMBDA/0
|
-16.22% |
1266.384 |
1060.975 |
1.458 |
-16.30% |
1.458 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_HYDRO_1D_LAMBDA/171
|
-16.14% |
0.443 |
0.372 |
0.000 |
-15.88% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_VOL3D_CALC_LAMBDA/1
|
-16.11% |
260.097 |
218.191 |
0.096 |
-16.13% |
0.096 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_HYDRO_1D_RAW/171
|
-16.07% |
0.443 |
0.372 |
0.000 |
-15.84% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_VOL3D_CALC_RAW/1
|
-16.04% |
259.923 |
218.223 |
0.115 |
-16.11% |
0.115 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC8
|
-15.77% |
58.742 |
49.480 |
0.127 |
-15.80% |
0.127 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint16_t_To_uint32_t_
|
-15.69% |
7463.240 |
6292.318 |
0.525 |
-15.68% |
0.525 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC4
|
-15.58% |
112.830 |
95.250 |
1.609 |
-15.77% |
1.609 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC127
|
-15.44% |
605.660 |
512.149 |
1.854 |
-15.45% |
1.854 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, EqZero, First>
|
-15.39% |
16670.896 |
14104.759 |
0.514 |
-15.39% |
0.514 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_no_runtime_checks_needed<16, int>
|
-15.39% |
24.404 |
20.649 |
0.001 |
-15.38% |
0.001 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, EqZero, Mid>
|
-15.37% |
16666.332 |
14104.393 |
0.612 |
-15.37% |
0.612 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, EqZero, Last>
|
-15.34% |
16667.075 |
14109.864 |
0.241 |
-15.34% |
0.241 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_HYDRO_1D_RAW/5001
|
-15.22% |
17.596 |
14.918 |
0.304 |
-10.59% |
0.304 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC32
|
-14.83% |
86.638 |
73.787 |
1.205 |
-13.52% |
1.205 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC8
|
-14.75% |
59.446 |
50.681 |
0.004 |
-14.75% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC128
|
-14.55% |
1103.057 |
942.533 |
0.062 |
-14.57% |
0.062 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC127
|
-14.53% |
1095.379 |
936.222 |
0.075 |
-14.52% |
0.075 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint32_t_To_uint8_t_
|
-14.30% |
10542.530 |
9035.280 |
22.643 |
-14.72% |
22.643 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC64
|
-14.17% |
561.340 |
481.774 |
0.074 |
-14.32% |
0.074 |
|
SingleSource/Benchmarks/Misc/salsa20
Profile
|
-14.14% |
15.387 |
13.211 |
0.001 |
-14.12% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC63
|
-14.13% |
553.533 |
475.292 |
0.173 |
-14.32% |
0.173 |
|
External/SPEC/CFP2017rate/508.namd_r/508.namd_r
Profile
|
-14.00% |
224.110 |
192.742 |
0.279 |
-13.79% |
0.279 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint64_t_To_uint8_t_
|
-13.96% |
22109.029 |
19022.057 |
40.425 |
-13.72% |
40.425 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint8_t_To_uint16_t_
|
-13.91% |
3757.145 |
3234.423 |
2.511 |
-13.90% |
2.511 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_with_cond_arith_novec_int64_t_
|
-13.89% |
790771.116 |
680918.296 |
1186.484 |
-13.59% |
1186.484 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC1
|
-13.87% |
51.938 |
44.736 |
0.003 |
-13.86% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC2
|
-13.86% |
51.938 |
44.737 |
0.003 |
-13.86% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC7
|
-13.86% |
51.940 |
44.739 |
0.002 |
-13.85% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC4
|
-13.86% |
51.937 |
44.739 |
0.001 |
-13.85% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC3
|
-13.86% |
51.934 |
44.738 |
0.003 |
-13.86% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC8
|
-13.85% |
51.933 |
44.740 |
0.001 |
-13.86% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_with_cond_arith_autovec_int64_t_
|
-13.75% |
791084.789 |
682288.291 |
465.802 |
-13.81% |
465.802 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC8
|
-13.68% |
59.444 |
51.311 |
0.001 |
-13.69% |
0.001 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, EqZero, First>
|
-13.62% |
14102.604 |
12182.396 |
0.578 |
-13.62% |
0.578 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint32_t_To_uint8_t_
|
-13.61% |
11096.632 |
9586.026 |
38.529 |
-13.87% |
38.529 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, EqZero, Mid>
|
-13.61% |
14102.733 |
12182.969 |
0.316 |
-13.62% |
0.316 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, EqZero, Last>
|
-13.61% |
14102.477 |
12182.923 |
0.208 |
-13.63% |
0.208 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint32_t_To_uint16_t_
|
-13.59% |
12794.879 |
11056.557 |
24.441 |
-13.87% |
24.441 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC8
|
-13.56% |
23.152 |
20.012 |
0.004 |
-13.56% |
0.004 |
|
MicroBenchmarks/ImageProcessing/Dilate/Dilate.test:BENCHMARK_DILATE/1024
|
-13.43% |
7319.840 |
6337.137 |
201.626 |
-10.88% |
201.626 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC32
|
-13.41% |
290.358 |
251.408 |
0.067 |
-13.90% |
0.067 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC63
|
-13.37% |
374.221 |
324.176 |
0.151 |
-13.42% |
0.151 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC31
|
-13.35% |
282.171 |
244.491 |
0.399 |
-13.94% |
0.399 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC63
|
-13.21% |
332.128 |
288.259 |
1.143 |
-13.39% |
1.143 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC8
|
-13.16% |
23.778 |
20.648 |
0.001 |
-13.16% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC128
|
-13.08% |
81.344 |
70.704 |
0.004 |
-13.08% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint8_t_To_uint16_t_
|
-12.94% |
4541.799 |
3954.038 |
0.201 |
-12.94% |
0.201 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC15
|
-12.86% |
106.995 |
93.239 |
0.003 |
-12.86% |
0.003 |
|
SingleSource/Benchmarks/Shootout-C++/Shootout-C++-matrix
Profile
|
-12.73% |
2.509 |
2.190 |
0.000 |
-12.71% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC16
|
-12.71% |
156.222 |
136.359 |
0.027 |
-13.13% |
0.027 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint32_t_To_uint64_t_
|
-12.71% |
17422.525 |
15207.658 |
312.766 |
-11.56% |
312.766 |
|
MultiSource/Benchmarks/MiBench/security-rijndael/security-rijndael
Profile
|
-12.55% |
0.334 |
0.292 |
0.000 |
-12.61% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC31
|
-12.48% |
86.694 |
75.874 |
0.221 |
-11.89% |
0.221 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC15
|
-12.41% |
148.500 |
130.071 |
0.038 |
-12.59% |
0.038 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint16_t_To_uint8_t_
|
-12.41% |
4743.206 |
4154.726 |
0.375 |
-12.40% |
0.375 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC15
|
-12.15% |
51.938 |
45.628 |
0.173 |
-12.15% |
0.173 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC16
|
-11.94% |
51.937 |
45.735 |
0.122 |
-11.95% |
0.122 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC2
|
-11.77% |
21.277 |
18.771 |
0.001 |
-11.77% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC15
|
-11.70% |
107.004 |
94.489 |
0.001 |
-11.70% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC16
|
-11.38% |
33.169 |
29.396 |
0.006 |
-11.36% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC8
|
-11.34% |
88.909 |
78.825 |
0.012 |
-11.83% |
0.012 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC3
|
-11.12% |
22.528 |
20.022 |
0.002 |
-11.12% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC4
|
-11.12% |
22.527 |
20.023 |
0.000 |
-11.11% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC4
|
-11.11% |
22.525 |
20.023 |
0.002 |
-11.11% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint8_t>/51
|
-10.89% |
123.888 |
110.396 |
0.161 |
19.34% |
0.161 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIRST_SUM_LAMBDA/5001
|
-10.78% |
20.394 |
18.196 |
0.348 |
3.34% |
0.348 |
|
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% |
41.299 |
36.919 |
0.002 |
-10.61% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC7
|
-10.60% |
81.171 |
72.565 |
0.012 |
-10.76% |
0.012 |
|
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
|
-10.52% |
23.778 |
21.276 |
0.001 |
-10.53% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC64
|
-10.46% |
53.810 |
48.180 |
0.002 |
-10.47% |
0.002 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/16
|
-10.18% |
115.469 |
103.719 |
0.007 |
-10.17% |
0.007 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC127
|
-10.07% |
102.284 |
91.986 |
0.003 |
-9.71% |
0.003 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/64
|
-10.05% |
1912.612 |
1720.490 |
11.973 |
-10.08% |
11.973 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_only_autovec_int64_t_
|
-10.00% |
333607.752 |
300247.354 |
628.180 |
-9.91% |
628.180 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/32
|
-9.99% |
473.005 |
425.734 |
0.029 |
-9.99% |
0.029 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint8_t_To_uint16_t_
|
-9.99% |
5846.603 |
5262.535 |
2.948 |
-10.05% |
2.948 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC7
|
-9.96% |
354.352 |
319.059 |
4.820 |
-10.05% |
4.820 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/256
|
-9.92% |
31433.869 |
28314.632 |
26.077 |
-9.97% |
26.077 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/128
|
-9.91% |
7922.133 |
7137.401 |
4.062 |
-9.85% |
4.062 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC4
|
-9.81% |
55.506 |
50.064 |
0.000 |
-10.06% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_DIFF_PREDICT_LAMBDA/171
|
-9.78% |
12.316 |
11.111 |
0.069 |
-7.30% |
0.069 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC8
|
-9.76% |
25.655 |
23.150 |
0.001 |
-9.77% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC31
|
-9.76% |
195.923 |
176.810 |
0.577 |
-10.01% |
0.577 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC8
|
-9.76% |
25.654 |
23.152 |
0.001 |
-9.76% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC7
|
-9.62% |
32.541 |
29.410 |
0.001 |
-9.61% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_DISC_ORD_RAW/5001
|
-9.59% |
655.960 |
593.067 |
4.727 |
-10.78% |
4.727 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC7
|
-9.53% |
26.281 |
23.776 |
0.001 |
-9.53% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC7
|
-9.53% |
26.282 |
23.778 |
0.001 |
-9.53% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC32
|
-9.52% |
53.188 |
48.127 |
0.022 |
-9.52% |
0.022 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC8
|
-9.50% |
26.964 |
24.403 |
0.000 |
-9.33% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_DEL_DOT_VEC_2D_RAW/1
|
-9.25% |
287.116 |
260.555 |
0.042 |
-9.21% |
0.042 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_DEL_DOT_VEC_2D_LAMBDA/1
|
-9.20% |
286.983 |
260.593 |
0.271 |
-9.24% |
0.271 |
|
MultiSource/Benchmarks/McCat/12-IOtest/iotest
Profile
|
-9.10% |
1.862 |
1.693 |
0.028 |
-7.24% |
0.028 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC4
|
-9.09% |
41.300 |
37.544 |
0.001 |
-9.09% |
0.001 |
|
MultiSource/Benchmarks/FreeBench/pifft/pifft
Profile
|
-9.07% |
0.359 |
0.326 |
0.001 |
-9.00% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_INT_PREDICT_RAW/44217
|
-9.00% |
8847.463 |
8051.187 |
69.298 |
-11.03% |
69.298 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIRST_DIFF_LAMBDA/5001
|
-9.00% |
12.850 |
11.694 |
0.362 |
-4.08% |
0.362 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC7
|
-8.90% |
28.159 |
25.654 |
0.001 |
-8.90% |
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
|
-8.70% |
3.510 |
3.204 |
0.000 |
-8.71% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC16
|
-8.62% |
36.293 |
33.164 |
0.001 |
-8.62% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC8
|
-8.52% |
29.410 |
26.906 |
0.001 |
-8.52% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint16_t_To_uint8_t_
|
-8.50% |
6808.830 |
6230.387 |
4.614 |
-8.59% |
4.614 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_runtime_checks_pass<4, int>
|
-8.48% |
16.750 |
15.330 |
0.001 |
-8.25% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_DISC_ORD_LAMBDA/5001
|
-8.41% |
642.769 |
588.687 |
6.063 |
-7.63% |
6.063 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIRST_DIFF_RAW/5001
|
-8.32% |
12.507 |
11.467 |
0.265 |
-4.89% |
0.265 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint8_t>/28
|
-8.27% |
82.589 |
75.762 |
0.038 |
12.09% |
0.038 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC2
|
-8.20% |
38.169 |
35.041 |
0.002 |
-8.20% |
0.002 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_INT_PREDICT_RAW/5001
|
-8.16% |
997.076 |
915.751 |
8.508 |
0.26% |
8.508 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC64
|
-8.06% |
93.239 |
85.723 |
0.004 |
-8.06% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC3
|
-7.90% |
47.558 |
43.801 |
0.002 |
-7.90% |
0.002 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_DEL_DOT_VEC_2D_LAMBDA/0
|
-7.88% |
1798.238 |
1656.587 |
2.662 |
-7.56% |
2.662 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC16
|
-7.85% |
31.913 |
29.409 |
0.001 |
-7.84% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC16
|
-7.85% |
31.914 |
29.410 |
0.000 |
-7.84% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC32
|
-7.81% |
40.050 |
36.920 |
0.001 |
-7.81% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_DEL_DOT_VEC_2D_RAW/0
|
-7.79% |
1798.190 |
1658.137 |
2.626 |
-7.93% |
2.626 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint8_t_To_uint32_t_
|
-7.75% |
12777.009 |
11786.164 |
16.451 |
-7.77% |
16.451 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint16_t_To_uint64_t_
|
-7.74% |
20217.751 |
18652.353 |
80.709 |
-7.40% |
80.709 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC15
|
-7.70% |
32.539 |
30.033 |
0.001 |
-7.70% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC127
|
-7.70% |
2410.412 |
2224.827 |
21.632 |
-8.32% |
21.632 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC15
|
-7.69% |
32.540 |
30.036 |
0.002 |
-7.69% |
0.002 |
|
MultiSource/Benchmarks/VersaBench/beamformer/beamformer
Profile
|
-7.66% |
5.203 |
4.805 |
0.003 |
-7.62% |
0.003 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_HYDRO_2D_RAW/171
|
-7.61% |
88.901 |
82.134 |
0.204 |
-7.33% |
0.204 |
|
MultiSource/Benchmarks/Trimaran/enc-md5/enc-md5
Profile
|
-7.53% |
3.508 |
3.243 |
0.000 |
-7.48% |
0.000 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_xor_no_runtime_checks_needed<16, int>
|
-7.41% |
16.894 |
15.643 |
0.001 |
-7.42% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_HYDRO_2D_LAMBDA/171
|
-7.37% |
88.784 |
82.237 |
0.966 |
-7.24% |
0.966 |
|
MultiSource/Applications/lambda-0.1.3/lambda
Profile
|
-7.32% |
15.887 |
14.724 |
0.002 |
-7.22% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC1
|
-7.31% |
88.703 |
82.223 |
1.500 |
-7.60% |
1.500 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIND_FIRST_MIN_RAW/171
|
-7.23% |
1.497 |
1.389 |
0.000 |
-7.19% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC128
|
-7.22% |
173.337 |
160.819 |
0.011 |
-7.22% |
0.011 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint8_t>/127
|
-7.20% |
138.900 |
128.899 |
0.007 |
-7.21% |
0.007 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint16_t_To_uint64_t_
|
-7.15% |
24998.763 |
23211.172 |
30.715 |
-7.10% |
30.715 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC7
|
-7.08% |
70.708 |
65.703 |
0.001 |
-7.09% |
0.001 |
|
MicroBenchmarks/ImageProcessing/Blur/blur.test:BENCHMARK_boxBlurKernel/128
|
-7.07% |
424.241 |
394.248 |
11.381 |
-9.22% |
11.381 |
|
SingleSource/Benchmarks/Misc/pi
Profile
|
-7.02% |
1.783 |
1.657 |
0.000 |
-7.01% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC15
|
-6.94% |
45.054 |
41.925 |
0.024 |
-6.94% |
0.024 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC15
|
-6.89% |
54.436 |
50.687 |
0.006 |
-6.90% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC128
|
-6.75% |
68.828 |
64.185 |
0.106 |
-6.71% |
0.106 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC31
|
-6.73% |
74.466 |
69.456 |
0.004 |
-6.73% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC127
|
-6.61% |
68.833 |
64.286 |
0.073 |
-5.87% |
0.073 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC63
|
-6.56% |
114.513 |
107.000 |
0.057 |
-6.56% |
0.057 |
|
SingleSource/Benchmarks/Polybench/stencils/jacobi-2d/jacobi-2d
Profile
|
-6.55% |
32.274 |
30.161 |
0.202 |
-6.40% |
0.202 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_xor_runtime_checks_pass<16, int>
|
-6.52% |
28.783 |
26.906 |
0.003 |
-6.52% |
0.003 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_xor_runtime_checks_fail<16, int>
|
-6.51% |
28.784 |
26.909 |
0.000 |
-6.51% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC63
|
-6.49% |
74.279 |
69.460 |
0.002 |
-6.42% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_only_autovec_int32_t_
|
-6.43% |
181103.021 |
169462.444 |
415.388 |
-6.44% |
415.388 |
|
SingleSource/Benchmarks/Misc/flops-6
Profile
|
-6.42% |
1.312 |
1.228 |
0.000 |
-6.46% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC127
|
-6.42% |
194.599 |
182.110 |
0.318 |
-6.42% |
0.318 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC15
|
-6.35% |
39.422 |
36.918 |
0.003 |
-6.35% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint16_t>/127
|
-6.30% |
138.907 |
130.156 |
0.004 |
-6.30% |
0.004 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_DIFF_PREDICT_RAW/171
|
-6.29% |
11.856 |
11.111 |
0.099 |
-6.89% |
0.099 |
|
SingleSource/Benchmarks/Misc/oourafft
Profile
|
-6.25% |
15.370 |
14.409 |
0.080 |
-4.53% |
0.080 |
|
SingleSource/Benchmarks/Misc-C++/Large/sphereflake
Profile
|
-6.22% |
20.009 |
18.766 |
0.004 |
-6.18% |
0.004 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIND_FIRST_MIN_RAW/5001
|
-6.21% |
45.292 |
42.479 |
0.033 |
-6.31% |
0.033 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC16
|
-6.15% |
40.674 |
38.170 |
0.001 |
-6.16% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_BAND_LIN_EQ_RAW/44217
|
-6.14% |
184.164 |
172.863 |
3.497 |
6.71% |
3.497 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C/miniAMR/miniAMR
Profile
|
-6.10% |
3.429 |
3.220 |
0.048 |
-0.90% |
0.048 |
|
MultiSource/Benchmarks/MiBench/telecomm-gsm/telecomm-gsm
Profile
|
-6.08% |
0.663 |
0.623 |
0.000 |
-6.04% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint32_t_To_uint64_t_
|
-6.04% |
21535.118 |
20233.493 |
38.658 |
-5.68% |
38.658 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopFrom_uint32_t_To_uint16_t_
|
-5.92% |
7845.999 |
7381.510 |
51.850 |
-0.93% |
51.850 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint8_t>/65
|
-5.91% |
95.104 |
89.482 |
0.006 |
-5.92% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint32_t>/127
|
-5.88% |
138.279 |
130.150 |
0.010 |
-5.88% |
0.010 |
|
External/SPEC/CFP2017rate/538.imagick_r/538.imagick_r
Profile
|
-5.83% |
291.524 |
274.520 |
0.421 |
-6.01% |
0.421 |
|
SingleSource/Benchmarks/Stanford/Puzzle
Profile
|
-5.71% |
0.241 |
0.228 |
0.001 |
-5.72% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC127
|
-5.65% |
3129.346 |
2952.533 |
51.895 |
-5.63% |
51.895 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC16
|
-5.65% |
33.162 |
31.289 |
0.001 |
-5.65% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC32
|
-5.64% |
44.429 |
41.925 |
0.001 |
-5.64% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC32
|
-5.64% |
44.424 |
41.921 |
0.003 |
-5.64% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC128
|
-5.62% |
2975.674 |
2808.413 |
49.597 |
-5.58% |
49.597 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC31
|
-5.60% |
45.069 |
42.547 |
0.002 |
-5.58% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC31
|
-5.57% |
905.891 |
855.394 |
14.314 |
-6.72% |
14.314 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC31
|
-5.55% |
45.050 |
42.549 |
0.001 |
-5.56% |
0.001 |
|
MultiSource/Benchmarks/SciMark2-C/scimark2
Profile
|
-5.53% |
107.701 |
101.747 |
0.018 |
-5.47% |
0.018 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_PIC_1D_RAW/5001
|
-5.52% |
355.178 |
335.583 |
1.323 |
-2.74% |
1.323 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C++/miniFE/miniFE
Profile
|
-5.47% |
15.815 |
14.950 |
0.056 |
-6.38% |
0.056 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint8_t_To_uint16_t_
|
-5.46% |
3627.021 |
3428.987 |
2.210 |
-5.62% |
2.210 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIND_FIRST_MIN_RAW/44217
|
-5.42% |
389.229 |
368.121 |
0.466 |
-5.51% |
0.466 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC32
|
-5.41% |
61.323 |
58.006 |
0.090 |
-5.41% |
0.090 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint32_t>/999
|
-5.39% |
696.456 |
658.914 |
0.066 |
-5.40% |
0.066 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_PRESSURE_CALC_RAW/5001
|
-5.36% |
46.139 |
43.664 |
0.481 |
-2.10% |
0.481 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC7
|
-5.31% |
70.706 |
66.952 |
0.004 |
-5.33% |
0.004 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_BAND_LIN_EQ_RAW/5001
|
-5.28% |
21.297 |
20.173 |
0.056 |
-2.18% |
0.056 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopWithReductionTC1
|
-5.26% |
11.889 |
11.264 |
0.000 |
-5.26% |
0.000 |
|
MultiSource/Benchmarks/TSVC/NodeSplitting-dbl/NodeSplitting-dbl
Profile
|
-5.25% |
26.590 |
25.195 |
0.427 |
-4.62% |
0.427 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint32_t>/999
|
-5.23% |
1365.086 |
1293.663 |
0.054 |
-5.23% |
0.054 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_PIC_2D_RAW/171
|
-5.16% |
13.525 |
12.827 |
0.062 |
-5.26% |
0.062 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC15
|
-5.14% |
128.213 |
121.622 |
0.036 |
-5.17% |
0.036 |
|
MultiSource/Benchmarks/Rodinia/hotspot/hotspot
Profile
|
-5.13% |
2.035 |
1.931 |
0.009 |
-5.18% |
0.009 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC32
|
-5.13% |
24.402 |
23.151 |
0.001 |
-5.14% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC32
|
-5.13% |
24.402 |
23.151 |
0.002 |
-5.13% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC31
|
-5.12% |
24.402 |
23.152 |
0.003 |
-5.13% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC31
|
-5.12% |
24.402 |
23.152 |
0.001 |
-5.13% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_PIC_2D_LAMBDA/171
|
-5.09% |
13.455 |
12.770 |
0.054 |
-5.39% |
0.054 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC31
|
-5.07% |
241.269 |
229.041 |
0.046 |
-5.05% |
0.046 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC64
|
-5.03% |
43.802 |
41.598 |
0.060 |
-3.65% |
0.060 |
|
MultiSource/Benchmarks/TSVC/ControlLoops-dbl/ControlLoops-dbl
Profile
|
-4.90% |
11.079 |
10.537 |
0.180 |
-4.38% |
0.180 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint32_t>/256
|
-4.81% |
364.206 |
346.677 |
0.007 |
-4.80% |
0.007 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC63
|
-4.78% |
1643.655 |
1565.008 |
26.280 |
-4.79% |
26.280 |
|
SingleSource/Benchmarks/Misc/revertBits
Profile
|
-4.70% |
0.641 |
0.611 |
0.000 |
-4.67% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_PRESSURE_CALC_RAW/44217
|
-4.62% |
502.243 |
479.064 |
3.780 |
-4.61% |
3.780 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_runtime_checks_fail<16, int>
|
-4.60% |
54.439 |
51.933 |
0.002 |
-4.60% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint16_t>/65
|
-4.60% |
95.110 |
90.732 |
0.008 |
-4.61% |
0.008 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_runtime_checks_pass<16, int>
|
-4.60% |
54.440 |
51.937 |
0.002 |
-4.59% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC63
|
-4.53% |
1734.086 |
1655.492 |
24.783 |
-4.70% |
24.783 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint32_t_To_uint16_t_
|
-4.53% |
9877.584 |
9430.376 |
40.592 |
-4.55% |
40.592 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopWithReductionTC2
|
-4.52% |
13.766 |
13.143 |
0.004 |
-4.52% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC31
|
-4.48% |
70.086 |
66.950 |
0.005 |
-4.47% |
0.005 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_ENERGY_CALC_RAW/171
|
-4.46% |
14.233 |
13.598 |
0.012 |
-4.51% |
0.012 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint8_t_To_uint64_t_
|
-4.37% |
23490.313 |
22463.984 |
73.898 |
-4.34% |
73.898 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC3
|
-4.36% |
14.393 |
13.765 |
0.001 |
-4.35% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC64
|
-4.36% |
1490.946 |
1425.995 |
23.128 |
-4.33% |
23.128 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC4
|
-4.36% |
14.392 |
13.765 |
0.001 |
-4.36% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC4
|
-4.35% |
14.392 |
13.766 |
0.001 |
-4.35% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC2
|
-4.35% |
14.393 |
13.766 |
0.000 |
-4.34% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC3
|
-4.35% |
14.393 |
13.766 |
0.000 |
-4.35% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC7
|
-4.35% |
14.392 |
13.766 |
0.000 |
-4.34% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC8
|
-4.35% |
14.393 |
13.767 |
0.000 |
-4.35% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC15
|
-4.35% |
14.392 |
13.766 |
0.003 |
-4.35% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC8
|
-4.35% |
14.391 |
13.765 |
0.001 |
-4.36% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC2
|
-4.35% |
14.391 |
13.765 |
0.001 |
-4.35% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC15
|
-4.35% |
14.392 |
13.766 |
0.000 |
-4.35% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC7
|
-4.35% |
14.391 |
13.765 |
0.000 |
-4.35% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC16
|
-4.35% |
14.392 |
13.766 |
0.002 |
-4.35% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC1
|
-4.34% |
14.391 |
13.766 |
0.001 |
-4.35% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC31
|
-4.34% |
1518.809 |
1452.942 |
19.794 |
-4.09% |
19.794 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC1
|
-4.33% |
14.392 |
13.768 |
0.001 |
-4.34% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC63
|
-4.33% |
43.567 |
41.679 |
0.022 |
-3.73% |
0.022 |
|
External/SPEC/CFP2017rate/519.lbm_r/519.lbm_r
Profile
|
-4.26% |
199.966 |
191.449 |
1.860 |
-4.60% |
1.860 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint64_t>/999
|
-4.24% |
1810.879 |
1734.101 |
0.035 |
-4.26% |
0.035 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint64_t>/999
|
-4.16% |
3595.245 |
3445.690 |
0.219 |
-4.14% |
0.219 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_nested_cond_load_novec_int32_t_
|
-4.16% |
649482.730 |
622487.876 |
290.384 |
-3.51% |
290.384 |
|
SingleSource/Benchmarks/Misc/flops-5
Profile
|
-4.14% |
2.021 |
1.937 |
0.001 |
-4.14% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_ENERGY_CALC_LAMBDA/171
|
-4.12% |
14.193 |
13.608 |
0.023 |
-4.49% |
0.023 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint64_t>/256
|
-4.08% |
935.529 |
897.386 |
0.036 |
-4.08% |
0.036 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC31
|
-4.04% |
61.945 |
59.442 |
0.004 |
-4.04% |
0.004 |
|
MicroBenchmarks/ImageProcessing/Dilate/Dilate.test:BENCHMARK_DILATE/256
|
-4.03% |
1064.727 |
1021.767 |
0.514 |
-4.26% |
0.514 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_runtime_checks_fail<4, int>
|
-4.03% |
15.974 |
15.331 |
0.000 |
-3.63% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC16
|
-4.02% |
31.295 |
30.036 |
0.001 |
-4.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_only_autovec_uint8_t_
|
-3.98% |
96160.108 |
92331.585 |
19.347 |
-3.98% |
19.347 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint32_t>/65
|
-3.96% |
94.482 |
90.736 |
0.000 |
-3.97% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC32
|
-3.96% |
63.199 |
60.694 |
0.003 |
-3.96% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint32_t>/256
|
-3.96% |
221.523 |
212.755 |
0.004 |
-3.95% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC15
|
-3.95% |
44.705 |
42.937 |
0.407 |
-3.36% |
0.407 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint8_t>/16
|
-3.93% |
59.975 |
57.620 |
0.230 |
7.06% |
0.230 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC32
|
-3.92% |
31.283 |
30.057 |
0.183 |
-3.93% |
0.183 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint64_t_To_uint32_t_
|
-3.90% |
19320.465 |
18567.791 |
55.986 |
-3.76% |
55.986 |
|
SingleSource/Benchmarks/Misc/ffbench
Profile
|
-3.87% |
11.063 |
10.635 |
0.138 |
-4.05% |
0.138 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC3
|
-3.85% |
16.270 |
15.643 |
0.001 |
-3.85% |
0.001 |
|
MicroBenchmarks/ImageProcessing/Dilate/Dilate.test:BENCHMARK_DILATE/512
|
-3.74% |
3637.062 |
3500.983 |
20.286 |
-2.32% |
20.286 |
|
SingleSource/Benchmarks/Shootout/Shootout-matrix
Profile
|
-3.69% |
3.864 |
3.721 |
0.000 |
-3.68% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint64_t>/256
|
-3.64% |
514.357 |
495.618 |
0.036 |
-3.65% |
0.036 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<31, EqZero, First>
|
-3.63% |
3344.114 |
3222.795 |
0.304 |
-3.69% |
0.304 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint16_t_To_uint8_t_
|
-3.62% |
2873.019 |
2769.076 |
1.719 |
-3.79% |
1.719 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<32, EqZero, Last>
|
-3.61% |
7070.097 |
6814.645 |
47.557 |
-3.38% |
47.557 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC64
|
-3.61% |
69.458 |
66.953 |
0.002 |
-3.60% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC63
|
-3.61% |
70.102 |
67.575 |
0.003 |
-3.59% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC64
|
-3.60% |
69.452 |
66.951 |
0.002 |
-3.61% |
0.002 |
|
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% |
70.081 |
67.575 |
0.003 |
-3.58% |
0.003 |
|
MultiSource/Applications/JM/lencod/lencod
Profile
|
-3.56% |
32.778 |
31.610 |
0.030 |
-2.86% |
0.030 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC31
|
-3.49% |
60.298 |
58.194 |
0.001 |
-3.45% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_PRESSURE_CALC_LAMBDA/44217
|
-3.47% |
498.504 |
481.208 |
2.125 |
-3.48% |
2.125 |
|
MultiSource/Benchmarks/nbench/nbench
Profile
|
-3.46% |
6.115 |
5.904 |
0.003 |
-3.63% |
0.003 |
|
MultiSource/Benchmarks/Rodinia/pathfinder/pathfinder
Profile
|
-3.40% |
1.264 |
1.221 |
0.009 |
-2.89% |
0.009 |
|
External/SPEC/CFP2017rate/544.nab_r/544.nab_r
Profile
|
-3.29% |
476.318 |
460.629 |
0.075 |
-3.61% |
0.075 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC31
|
-3.25% |
93.859 |
90.804 |
0.058 |
-3.25% |
0.058 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_ENERGY_CALC_LAMBDA/5001
|
-3.17% |
438.815 |
424.912 |
1.482 |
-3.00% |
1.482 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint16_t>/999
|
-3.16% |
514.985 |
498.732 |
0.017 |
-3.16% |
0.017 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint16_t_To_uint8_t_
|
-3.14% |
4512.743 |
4370.894 |
3.888 |
-3.24% |
3.888 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1BigLoopWithReductionTC1
|
-3.14% |
20.025 |
19.396 |
0.001 |
-3.14% |
0.001 |
|
SingleSource/Benchmarks/Shootout/Shootout-lists
Profile
|
-3.13% |
11.315 |
10.961 |
0.007 |
-3.11% |
0.007 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC4
|
-3.10% |
350.629 |
339.752 |
3.869 |
-2.75% |
3.869 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchVecWithRuntimeChecks4PointersDBeforeA/1000
|
-3.09% |
5020240.683 |
4865339.396 |
230.272 |
-3.08% |
230.272 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, LessThanZero, None>
|
-3.06% |
37659.638 |
36507.563 |
56.730 |
-2.84% |
56.730 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_FLOYD_DITHER/256
|
-2.97% |
1790.901 |
1737.764 |
14.899 |
0.24% |
14.899 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_ENERGY_CALC_RAW/5001
|
-2.92% |
428.713 |
416.195 |
3.453 |
-2.93% |
3.453 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint16_t>/999
|
-2.83% |
1013.739 |
985.011 |
0.019 |
-2.85% |
0.019 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC31
|
-2.83% |
31.266 |
30.382 |
0.046 |
-2.59% |
0.046 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC64
|
-2.81% |
111.382 |
108.254 |
0.002 |
-2.81% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC1
|
-2.77% |
22.525 |
21.900 |
0.002 |
-2.78% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC1
|
-2.77% |
22.526 |
21.902 |
0.001 |
-2.77% |
0.001 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<31, GreaterThanZero, Last>
|
-2.72% |
8326.104 |
8099.272 |
0.814 |
-2.37% |
0.814 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_FLOYD_DITHER/128
|
-2.72% |
438.573 |
426.643 |
2.695 |
-2.92% |
2.695 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C/CoMD/CoMD
Profile
|
-2.69% |
9.908 |
9.642 |
0.003 |
-2.60% |
0.003 |
|
MultiSource/Benchmarks/mafft/pairlocalalign
Profile
|
-2.69% |
94.143 |
91.614 |
0.350 |
-2.60% |
0.350 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_FLOYD_DITHER/512
|
-2.69% |
6661.906 |
6482.985 |
20.934 |
-2.44% |
20.934 |
|
MultiSource/Benchmarks/FreeBench/mason/mason
Profile
|
-2.62% |
0.553 |
0.538 |
0.000 |
-2.68% |
0.000 |
|
SingleSource/Benchmarks/Misc-C++/oopack_v1p8
Profile
|
-2.60% |
0.480 |
0.467 |
0.000 |
-9.96% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC63
|
-2.60% |
120.142 |
117.021 |
0.049 |
-2.60% |
0.049 |
|
MultiSource/Benchmarks/FreeBench/fourinarow/fourinarow
Profile
|
-2.58% |
0.651 |
0.634 |
0.001 |
-2.54% |
0.001 |
|
SingleSource/Benchmarks/BenchmarkGame/puzzle
Profile
|
-2.57% |
0.872 |
0.849 |
0.004 |
-2.23% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint8_t>/10
|
-2.56% |
48.808 |
47.558 |
0.029 |
2.47% |
0.029 |
|
MultiSource/Benchmarks/FreeBench/pcompress2/pcompress2
Profile
|
-2.51% |
0.405 |
0.395 |
0.000 |
-2.41% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint8_t_To_uint32_t_
|
-2.51% |
7077.317 |
6899.723 |
0.993 |
-2.51% |
0.993 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC32
|
-2.50% |
50.057 |
48.808 |
0.002 |
-2.49% |
0.002 |
|
MultiSource/Benchmarks/TSVC/Expansion-flt/Expansion-flt
Profile
|
-2.48% |
11.639 |
11.350 |
0.066 |
0.27% |
0.066 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_BAND_LIN_EQ_LAMBDA/5001
|
-2.48% |
21.197 |
20.672 |
0.072 |
-0.61% |
0.072 |
|
MultiSource/Benchmarks/sim/sim
Profile
|
-2.48% |
9.698 |
9.458 |
0.035 |
-2.50% |
0.035 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchVecWithRuntimeChecks4PointersDBeforeA/32
|
-2.44% |
166181.459 |
162124.053 |
11.064 |
-2.45% |
11.064 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_only_autovec_int64_t_
|
-2.38% |
1448411.400 |
1413885.606 |
1666.857 |
-2.29% |
1666.857 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC63
|
-2.35% |
106.999 |
104.490 |
0.006 |
-2.35% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC64
|
-2.31% |
108.248 |
105.745 |
0.004 |
-2.31% |
0.004 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_ENERGY_CALC_LAMBDA/44217
|
-2.31% |
4342.317 |
4242.059 |
10.066 |
-1.90% |
10.066 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint64_t_To_uint8_t_
|
-2.28% |
19757.699 |
19307.602 |
42.233 |
-2.69% |
42.233 |
|
SingleSource/Benchmarks/Misc/flops-1
Profile
|
-2.17% |
9.002 |
8.806 |
0.000 |
-2.15% |
0.000 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<64, EqZero, Mid>
|
-2.15% |
2746.828 |
2687.809 |
6.682 |
-2.06% |
6.682 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<32, EqZero, None>
|
-2.14% |
4425.520 |
4330.790 |
3.745 |
-1.83% |
3.745 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint16_t_To_uint32_t_
|
-2.13% |
11268.991 |
11028.769 |
16.648 |
-2.77% |
16.648 |
|
SingleSource/Benchmarks/Misc-C++/Large/ray
Profile
|
-2.11% |
12.104 |
11.849 |
0.001 |
-2.08% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC128
|
-2.11% |
119.526 |
117.010 |
0.003 |
-2.10% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC128
|
-2.10% |
119.524 |
117.014 |
0.003 |
-2.10% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC127
|
-2.10% |
120.154 |
117.636 |
0.008 |
-2.09% |
0.008 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC127
|
-2.08% |
120.146 |
117.642 |
0.001 |
-2.08% |
0.001 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C/SimpleMOC/SimpleMOC
Profile
|
-2.06% |
10.428 |
10.213 |
0.040 |
-1.85% |
0.040 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<16, EqZero, None>
|
-2.06% |
8185.574 |
8017.077 |
53.461 |
-1.96% |
53.461 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<3, GreaterThanZero, None>
|
-2.06% |
45122.115 |
44194.333 |
117.831 |
-2.10% |
117.831 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_EOS_LAMBDA/171
|
-2.04% |
0.874 |
0.856 |
0.001 |
-1.68% |
0.001 |
|
MultiSource/Applications/sgefa/sgefa
Profile
|
-2.01% |
0.577 |
0.566 |
0.002 |
-1.39% |
0.002 |
|
SingleSource/Benchmarks/Misc/ReedSolomon
Profile
|
-1.96% |
20.819 |
20.412 |
0.000 |
-1.85% |
0.000 |
|
MultiSource/Benchmarks/tramp3d-v4/tramp3d-v4
Profile
|
-1.94% |
1.075 |
1.055 |
0.002 |
-1.95% |
0.002 |
|
External/SPEC/CFP2017rate/511.povray_r/511.povray_r
Profile
|
-1.90% |
33.994 |
33.348 |
0.092 |
-1.30% |
0.092 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_EOS_RAW/171
|
-1.89% |
0.872 |
0.856 |
0.002 |
-1.74% |
0.002 |
|
MultiSource/Benchmarks/Bullet/bullet
Profile
|
-1.86% |
30.525 |
29.958 |
0.084 |
-1.55% |
0.084 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<16, EqZero, Mid>
|
-1.85% |
8657.812 |
8497.764 |
57.741 |
-1.84% |
57.741 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<64, GreaterThanZero, Mid>
|
-1.84% |
2742.142 |
2691.621 |
16.494 |
-1.97% |
16.494 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint16_t>/256
|
-1.84% |
272.829 |
267.821 |
0.010 |
-1.84% |
0.010 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint32_t_To_uint64_t_
|
-1.78% |
26261.296 |
25793.303 |
29.951 |
-1.85% |
29.951 |
|
External/SPEC/CINT2017rate/531.deepsjeng_r/531.deepsjeng_r
Profile
|
-1.78% |
260.084 |
255.457 |
0.123 |
-1.79% |
0.123 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_INT_PREDICT_LAMBDA/171
|
-1.76% |
6.926 |
6.805 |
0.014 |
-1.74% |
0.014 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint64_t>/51
|
-1.69% |
148.297 |
145.786 |
0.008 |
-1.70% |
0.008 |
|
MultiSource/Benchmarks/Fhourstones-3.1/fhourstones3.1
Profile
|
-1.67% |
3.992 |
3.925 |
0.007 |
-1.17% |
0.007 |
|
MultiSource/Benchmarks/Olden/health/health
Profile
|
-1.67% |
1.586 |
1.559 |
0.002 |
-2.02% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_nested_cond_load_novec_uint8_t_
|
-1.66% |
504472.790 |
496099.025 |
209.882 |
-1.71% |
209.882 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<32, LessThanZero, Mid>
|
-1.65% |
4570.412 |
4494.941 |
12.524 |
-1.66% |
12.524 |
|
MultiSource/Benchmarks/TSVC/ControlLoops-flt/ControlLoops-flt
Profile
|
-1.65% |
5.424 |
5.334 |
0.006 |
-2.08% |
0.006 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_INT_PREDICT_RAW/171
|
-1.63% |
6.925 |
6.812 |
0.007 |
-1.63% |
0.007 |
|
MultiSource/Benchmarks/VersaBench/ecbdes/ecbdes
Profile
|
-1.63% |
5.142 |
5.058 |
0.001 |
-1.59% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint32_t>/10
|
-1.57% |
57.900 |
56.990 |
0.076 |
-0.10% |
0.076 |
|
SingleSource/Benchmarks/Misc/mandel-2
Profile
|
-1.55% |
2.536 |
2.496 |
0.000 |
-1.53% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_csa_with_in_loop_arith_novec_int64_t_
|
-1.51% |
1028068.009 |
1012520.256 |
300.474 |
-1.52% |
300.474 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC128
|
-1.49% |
211.506 |
208.353 |
0.013 |
-1.50% |
0.013 |
|
MultiSource/Applications/minisat/minisat
Profile
|
-1.47% |
61.404 |
60.501 |
0.344 |
-0.96% |
0.344 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC63
|
-1.45% |
130.156 |
128.270 |
0.198 |
-1.46% |
0.198 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC127
|
-1.42% |
220.268 |
217.146 |
0.073 |
-1.42% |
0.073 |
|
MicroBenchmarks/ImageProcessing/Blur/blur.test:BENCHMARK_boxBlurKernel/512
|
-1.41% |
6625.750 |
6532.041 |
28.352 |
-1.23% |
28.352 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_csa_with_cond_arith_autovec_int64_t_
|
-1.39% |
747163.412 |
736808.645 |
260.692 |
-1.09% |
260.692 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_csa_with_cond_arith_novec_int64_t_
|
-1.39% |
746050.021 |
735712.554 |
343.482 |
-1.21% |
343.482 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<6, LessThanZero, Mid>
|
-1.37% |
23845.365 |
23518.730 |
4.647 |
-0.20% |
4.647 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint64_t>/51
|
-1.35% |
228.997 |
225.901 |
0.006 |
-1.36% |
0.006 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, LessThanZero, Mid>
|
-1.28% |
31936.416 |
31526.899 |
79.796 |
-0.80% |
79.796 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC128
|
-1.27% |
198.366 |
195.847 |
0.011 |
-1.27% |
0.011 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC127
|
-1.27% |
197.097 |
194.601 |
0.008 |
-1.27% |
0.008 |
|
MultiSource/Benchmarks/MallocBench/cfrac/cfrac
Profile
|
-1.19% |
2.778 |
2.745 |
0.001 |
-1.27% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_sinhf_novec_float_
|
-1.14% |
2242.582 |
2217.117 |
0.508 |
-1.10% |
0.508 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_ENERGY_CALC_RAW/44217
|
-1.12% |
4330.618 |
4281.902 |
6.843 |
-1.14% |
6.843 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<16, LessThanZero, Last>
|
-1.12% |
13143.932 |
12996.236 |
24.798 |
-1.11% |
24.798 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_sinhf_autovec_float_
|
-1.11% |
2241.819 |
2217.031 |
0.294 |
-1.14% |
0.294 |
|
SingleSource/Benchmarks/SmallPT/smallpt
Profile
|
-1.09% |
30.033 |
29.706 |
0.003 |
-1.08% |
0.003 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<16, GreaterThanZero, First>
|
-1.09% |
8563.154 |
8470.002 |
10.662 |
-0.31% |
10.662 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, LessThanZero, Last>
|
-1.08% |
56400.344 |
55793.784 |
20.074 |
-0.45% |
20.074 |
|
External/SPEC/CINT2017rate/525.x264_r/525.x264_r
Profile
|
-1.06% |
129.463 |
128.096 |
0.092 |
-1.04% |
0.092 |
|
External/SPEC/CINT2017rate/541.leela_r/541.leela_r
Profile
|
-1.02% |
228.011 |
225.688 |
0.405 |
-1.61% |
0.405 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_sinh_novec_double_
|
-1.01% |
2470.198 |
2445.247 |
0.353 |
-1.16% |
0.353 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C++/PENNANT/PENNANT
Profile
|
-1.00% |
4.785 |
4.738 |
0.017 |
-1.65% |
0.017 |