|
MicroBenchmarks/LCALS/SubsetBRawLoops/lcalsBRaw.test:BM_TRAP_INT_RAW/44217
|
-65.15% |
1826.219 |
636.415 |
0.024 |
0.00% |
0.024 |
|
MicroBenchmarks/LCALS/SubsetBRawLoops/lcalsBRaw.test:BM_TRAP_INT_RAW/5001
|
-65.13% |
206.573 |
72.034 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LCALS/SubsetBRawLoops/lcalsBRaw.test:BM_TRAP_INT_RAW/171
|
-64.69% |
7.112 |
2.512 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetBLambdaLoops/lcalsBLambda.test:BM_TRAP_INT_LAMBDA/44217
|
-62.90% |
1715.466 |
636.412 |
0.036 |
-0.00% |
0.036 |
|
MicroBenchmarks/LCALS/SubsetBLambdaLoops/lcalsBLambda.test:BM_TRAP_INT_LAMBDA/5001
|
-62.88% |
194.070 |
72.036 |
0.005 |
-0.01% |
0.005 |
|
MicroBenchmarks/LCALS/SubsetBLambdaLoops/lcalsBLambda.test:BM_TRAP_INT_LAMBDA/171
|
-62.44% |
6.686 |
2.511 |
0.000 |
0.00% |
0.000 |
|
SingleSource/Benchmarks/BenchmarkGame/n-body
Profile
|
-35.61% |
3.360 |
2.163 |
0.000 |
-0.02% |
0.000 |
|
MultiSource/Benchmarks/VersaBench/beamformer/beamformer
Profile
|
-26.04% |
5.204 |
3.849 |
0.001 |
-0.04% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint32_t_To_uint64_t_
|
-21.32% |
20911.593 |
16452.294 |
225.199 |
-5.35% |
225.199 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint64_t_To_uint16_t_
|
-16.13% |
21331.021 |
17890.875 |
453.075 |
-3.56% |
453.075 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint32_t_To_uint16_t_
|
-14.96% |
10596.040 |
9011.111 |
198.356 |
-1.76% |
198.356 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC4
|
-10.02% |
15.298 |
13.765 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopFrom_uint32_t_To_uint64_t_
|
-9.86% |
15526.642 |
13994.969 |
290.687 |
-2.53% |
290.687 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1LoopWithReductionTC3
|
-9.52% |
13.140 |
11.888 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopFrom_uint32_t_To_uint16_t_
|
-9.27% |
8271.110 |
7504.424 |
279.687 |
2.72% |
279.687 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint64_t_To_uint16_t_
|
-8.88% |
38987.346 |
35525.052 |
84.483 |
-0.00% |
84.483 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint32_t_To_uint64_t_
|
-8.69% |
24468.917 |
22343.061 |
152.305 |
0.61% |
152.305 |
|
MultiSource/Benchmarks/Olden/power/power
Profile
|
-8.13% |
4.084 |
3.752 |
0.000 |
-0.02% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC1
|
-7.37% |
13.140 |
12.172 |
0.026 |
-0.84% |
0.026 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopWithReductionTC128
|
-7.27% |
77.591 |
71.954 |
0.005 |
-0.01% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopWithReductionTC127
|
-6.65% |
87.065 |
81.279 |
0.008 |
0.32% |
0.008 |
|
MultiSource/Benchmarks/FreeBench/distray/distray
Profile
|
-6.52% |
0.467 |
0.436 |
0.000 |
0.03% |
0.000 |
|
MultiSource/Benchmarks/Olden/bh/bh
Profile
|
-6.49% |
5.526 |
5.168 |
0.007 |
-0.03% |
0.007 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1LoopWithReductionTC7
|
-6.27% |
20.695 |
19.397 |
0.107 |
-0.00% |
0.107 |
|
MultiSource/Benchmarks/Olden/tsp/tsp
Profile
|
-6.13% |
5.082 |
4.770 |
0.072 |
0.51% |
0.072 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC3
|
-5.88% |
21.275 |
20.023 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopFrom_uint64_t_To_uint32_t_
|
-5.86% |
15658.663 |
14741.814 |
190.092 |
-1.18% |
190.092 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C++/PENNANT/PENNANT
Profile
|
-5.60% |
5.091 |
4.806 |
0.016 |
-0.30% |
0.016 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1LoopWithReductionTC8
|
-5.56% |
22.525 |
21.273 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC1
|
-5.27% |
11.889 |
11.262 |
0.000 |
-5.27% |
0.000 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<32, GreaterThanZero, None>
|
-5.26% |
4571.291 |
4331.063 |
45.667 |
-0.00% |
45.667 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_ORDERED_DITHER/128/8
|
-5.24% |
253.883 |
240.569 |
5.092 |
-0.44% |
5.092 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint32_t_To_uint8_t_
|
-5.10% |
9980.997 |
9471.623 |
10.852 |
0.38% |
10.852 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, GreaterThanZero, None>
|
-4.92% |
63285.231 |
60170.546 |
18.077 |
-0.02% |
18.077 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint32_t_To_uint8_t_
|
-4.90% |
14886.076 |
14157.251 |
38.860 |
-0.06% |
38.860 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC4
|
-4.89% |
25.656 |
24.401 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC7
|
-4.83% |
51.936 |
49.429 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC4
|
-4.83% |
51.936 |
49.430 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC2
|
-4.82% |
51.935 |
49.430 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC3
|
-4.82% |
51.936 |
49.431 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC15
|
-4.82% |
51.934 |
49.429 |
0.003 |
-0.00% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC1
|
-4.82% |
51.935 |
49.431 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC8
|
-4.82% |
51.936 |
49.432 |
0.003 |
-0.00% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC16
|
-4.82% |
51.934 |
49.431 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC2
|
-4.55% |
13.766 |
13.140 |
0.000 |
-4.55% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint64_t_To_uint32_t_
|
-4.53% |
18995.302 |
18135.450 |
262.818 |
-0.67% |
262.818 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1LoopWithReductionTC4
|
-4.43% |
14.403 |
13.765 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<32, EqZero, Last>
|
-4.39% |
7131.833 |
6818.634 |
19.997 |
-0.02% |
19.997 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC16
|
-4.36% |
14.393 |
13.765 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC15
|
-4.36% |
14.392 |
13.765 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC15
|
-4.36% |
14.392 |
13.765 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC1
|
-4.35% |
14.392 |
13.765 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC4
|
-4.35% |
14.391 |
13.765 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC16
|
-4.35% |
14.392 |
13.765 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC1
|
-4.35% |
14.392 |
13.766 |
0.000 |
-0.01% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC2
|
-4.35% |
14.391 |
13.765 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC8
|
-4.35% |
14.391 |
13.765 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC7
|
-4.35% |
14.391 |
13.765 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC8
|
-4.35% |
14.391 |
13.765 |
0.000 |
-0.01% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC3
|
-4.35% |
14.391 |
13.765 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC2
|
-4.35% |
14.391 |
13.765 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC3
|
-4.35% |
14.391 |
13.766 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC7
|
-4.35% |
14.391 |
13.766 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_ORDERED_DITHER/512/2
|
-4.26% |
3947.391 |
3779.056 |
20.408 |
-0.31% |
20.408 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC127
|
-4.23% |
275.811 |
264.147 |
0.867 |
-0.20% |
0.867 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC63
|
-4.12% |
150.016 |
143.838 |
2.127 |
0.20% |
2.127 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC3
|
-3.99% |
15.642 |
15.018 |
0.000 |
-3.99% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC128
|
-3.98% |
274.486 |
263.568 |
0.673 |
0.14% |
0.673 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_ORDERED_DITHER/512/4
|
-3.95% |
3997.629 |
3839.782 |
6.914 |
-0.41% |
6.914 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC16
|
-3.90% |
31.913 |
30.670 |
0.010 |
0.03% |
0.010 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC31
|
-3.88% |
86.676 |
83.313 |
0.252 |
0.72% |
0.252 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC3
|
-3.85% |
16.269 |
15.642 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC64
|
-3.75% |
148.554 |
142.979 |
1.222 |
-0.03% |
1.222 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC2
|
-3.71% |
16.895 |
16.268 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopWithReductionTC3
|
-3.68% |
16.269 |
15.671 |
0.153 |
-0.11% |
0.153 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_HYDRO_2D_LAMBDA/44217
|
-3.67% |
99483.190 |
95831.988 |
802.556 |
2.70% |
802.556 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC32
|
-3.66% |
85.448 |
82.319 |
0.711 |
0.64% |
0.711 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC32
|
-3.56% |
52.561 |
50.691 |
0.007 |
0.02% |
0.007 |
|
MultiSource/Applications/hexxagon/hexxagon
Profile
|
-3.54% |
12.730 |
12.280 |
0.002 |
0.01% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1LoopWithReductionTC15
|
-3.51% |
35.665 |
34.413 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_ORDERED_DITHER/512/3
|
-3.40% |
3354.365 |
3240.282 |
2.340 |
-0.56% |
2.340 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<32, LessThanZero, None>
|
-3.39% |
4566.526 |
4411.539 |
59.692 |
0.01% |
59.692 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC7
|
-3.34% |
37.543 |
36.290 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1LoopWithReductionTC16
|
-3.34% |
37.543 |
36.291 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC128
|
-3.30% |
86.551 |
83.693 |
0.850 |
-0.36% |
0.850 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC4
|
-3.04% |
41.297 |
40.043 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC4
|
-3.03% |
41.298 |
40.046 |
0.001 |
-3.03% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC8
|
-3.00% |
41.927 |
40.669 |
0.004 |
-0.03% |
0.004 |
|
MultiSource/Benchmarks/TSVC/Symbolics-dbl/Symbolics-dbl
Profile
|
-2.94% |
9.789 |
9.501 |
0.027 |
-0.81% |
0.027 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_ORDERED_DITHER/512/8
|
-2.93% |
3995.507 |
3878.356 |
35.838 |
-0.42% |
35.838 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_ORDERED_DITHER/256/3
|
-2.88% |
950.257 |
922.928 |
1.396 |
-0.10% |
1.396 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC1
|
-2.78% |
22.526 |
21.900 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC1
|
-2.76% |
95.472 |
92.833 |
0.386 |
-0.13% |
0.386 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC128
|
-2.70% |
86.239 |
83.913 |
0.804 |
-0.09% |
0.804 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopTC16
|
-2.69% |
281.052 |
273.498 |
1.887 |
-1.05% |
1.887 |
|
MicroBenchmarks/ImageProcessing/Blur/blur.test:BENCHMARK_boxBlurKernel/256
|
-2.68% |
1741.489 |
1694.833 |
5.577 |
-0.25% |
5.577 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopWithReductionTC7
|
-2.64% |
23.779 |
23.152 |
0.061 |
-0.00% |
0.061 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint64_t_To_uint32_t_
|
-2.62% |
38575.009 |
37562.900 |
18.197 |
-0.11% |
18.197 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<6, GreaterThanZero, None>
|
-2.62% |
29701.668 |
28924.030 |
15.729 |
0.01% |
15.729 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC32
|
-2.57% |
24.404 |
23.776 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC31
|
-2.57% |
24.404 |
23.776 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC32
|
-2.57% |
24.403 |
23.776 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC31
|
-2.56% |
24.403 |
23.777 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_ORDERED_DITHER/256/4
|
-2.54% |
1083.261 |
1055.764 |
0.961 |
-0.03% |
0.961 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC8
|
-2.50% |
25.028 |
24.402 |
0.001 |
-2.50% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopTC8
|
-2.49% |
148.365 |
144.665 |
0.573 |
-0.34% |
0.573 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint32_t_To_uint8_t_
|
-2.46% |
13759.689 |
13421.164 |
15.203 |
-0.05% |
15.203 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_COUPLE_RAW/0
|
-2.43% |
8193.864 |
7994.364 |
1.945 |
-0.04% |
1.945 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopTC1
|
-2.43% |
90.959 |
88.747 |
0.277 |
-0.00% |
0.277 |
|
MultiSource/Benchmarks/TSVC/ControlFlow-dbl/ControlFlow-dbl
Profile
|
-2.36% |
22.568 |
22.037 |
0.179 |
0.22% |
0.179 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC1
|
-2.34% |
91.033 |
88.907 |
0.274 |
0.01% |
0.274 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_ORDERED_DITHER/256/8
|
-2.29% |
1091.893 |
1066.898 |
1.092 |
-0.20% |
1.092 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_ORDERED_DITHER/256/2
|
-2.27% |
1067.443 |
1043.248 |
5.673 |
-0.30% |
5.673 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC64
|
-2.25% |
92.855 |
90.764 |
0.055 |
-1.32% |
0.055 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<63, LessThanZero, First>
|
-2.24% |
1640.288 |
1603.609 |
0.587 |
0.00% |
0.587 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<3, LessThanZero, Mid>
|
-2.19% |
38093.344 |
37259.870 |
312.511 |
-0.55% |
312.511 |
|
External/SPEC/CINT2017rate/523.xalancbmk_r/523.xalancbmk_r
Profile
|
-2.18% |
250.346 |
244.884 |
0.097 |
-0.88% |
0.097 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<63, GreaterThanZero, None>
|
-2.18% |
4703.936 |
4601.515 |
2.298 |
-0.00% |
2.298 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC8
|
-2.11% |
59.446 |
58.191 |
0.002 |
0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC8
|
-2.11% |
59.442 |
58.190 |
0.001 |
-2.11% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC7
|
-2.05% |
358.358 |
351.013 |
1.204 |
-0.66% |
1.204 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopWithReductionTC31
|
-2.04% |
44.426 |
43.519 |
0.109 |
0.51% |
0.109 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC16
|
-1.98% |
31.916 |
31.284 |
0.001 |
-1.28% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint32_t_To_uint64_t_
|
-1.97% |
25542.954 |
25038.759 |
11.977 |
0.02% |
11.977 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopTC15
|
-1.94% |
751.564 |
736.970 |
2.029 |
-0.35% |
2.029 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<16, EqZero, None>
|
-1.93% |
8176.022 |
8018.112 |
5.132 |
-0.05% |
5.132 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1LoopWithReductionTC31
|
-1.91% |
65.700 |
64.447 |
0.004 |
-0.00% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1LoopWithReductionTC32
|
-1.86% |
67.578 |
66.322 |
0.004 |
-0.00% |
0.004 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<16, EqZero, Mid>
|
-1.85% |
8657.507 |
8497.240 |
1.997 |
-0.03% |
1.997 |
|
MicroBenchmarks/ImageProcessing/Blur/blur.test:BENCHMARK_GAUSSIAN_BLUR/1024
|
-1.83% |
436555.477 |
428566.186 |
236.012 |
-0.04% |
236.012 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<16, GreaterThanZero, None>
|
-1.80% |
8164.471 |
8017.785 |
0.915 |
0.00% |
0.915 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint8_t_To_uint64_t_
|
-1.79% |
12971.739 |
12739.823 |
17.814 |
-0.05% |
17.814 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC4
|
-1.79% |
114.973 |
112.919 |
0.650 |
-0.31% |
0.650 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC15
|
-1.78% |
70.075 |
68.829 |
0.005 |
-0.00% |
0.005 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_COUPLE_RAW/2
|
-1.76% |
10.837 |
10.646 |
0.000 |
0.67% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint16_t_To_uint32_t_
|
-1.74% |
12544.692 |
12326.311 |
18.168 |
-0.12% |
18.168 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC8
|
-1.73% |
667.402 |
655.840 |
1.456 |
0.04% |
1.456 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopTC32
|
-1.70% |
552.583 |
543.172 |
0.648 |
-0.21% |
0.648 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint32_t_To_uint8_t_
|
-1.68% |
11235.894 |
11046.686 |
46.041 |
-0.30% |
46.041 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<3, GreaterThanZero, Mid>
|
-1.68% |
37928.406 |
37290.764 |
14.954 |
-0.05% |
14.954 |
|
SingleSource/Benchmarks/Adobe-C++/simple_types_loop_invariant
Profile
|
-1.58% |
1.854 |
1.824 |
0.002 |
-0.04% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC15
|
-1.55% |
1266.610 |
1246.929 |
2.743 |
-0.04% |
2.743 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopFrom_uint64_t_To_uint16_t_
|
-1.54% |
14963.722 |
14733.979 |
25.907 |
0.18% |
25.907 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopTC64
|
-1.53% |
1101.304 |
1084.479 |
1.576 |
-0.10% |
1.576 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC8
|
-1.47% |
58.741 |
57.877 |
0.002 |
0.54% |
0.002 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, GreaterThanZero, None>
|
-1.46% |
37086.904 |
36544.988 |
75.273 |
0.06% |
75.273 |
|
SingleSource/Benchmarks/Misc-C++/Large/ray
Profile
|
-1.46% |
12.279 |
12.100 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC63
|
-1.44% |
1662.041 |
1638.079 |
2.105 |
-0.01% |
2.105 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint64_t_To_uint8_t_
|
-1.39% |
36785.561 |
36273.335 |
19.442 |
-0.02% |
19.442 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<7, LessThanZero, Mid>
|
-1.36% |
20419.523 |
20142.642 |
7.555 |
0.00% |
7.555 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC64
|
-1.35% |
1507.660 |
1487.299 |
1.546 |
0.01% |
1.546 |
|
MultiSource/Benchmarks/McCat/17-bintr/bintr
Profile
|
-1.33% |
1.249 |
1.233 |
0.006 |
0.01% |
0.006 |
|
MicroBenchmarks/ImageProcessing/Blur/blur.test:BENCHMARK_GAUSSIAN_BLUR/512
|
-1.33% |
93072.989 |
91836.630 |
16.381 |
0.02% |
16.381 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopWithReductionTC64
|
-1.32% |
47.555 |
46.927 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_COUPLE_LAMBDA/1
|
-1.32% |
1346.454 |
1328.726 |
6.333 |
0.27% |
6.333 |
|
External/SPEC/CINT2017rate/525.x264_r/525.x264_r
Profile
|
-1.32% |
131.285 |
129.557 |
0.205 |
0.08% |
0.205 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint64_t_To_uint32_t_
|
-1.31% |
36170.304 |
35695.545 |
119.729 |
0.01% |
119.729 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC16
|
-1.31% |
95.736 |
94.482 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopTC3
|
-1.31% |
254.831 |
251.495 |
0.588 |
0.00% |
0.588 |
|
External/SPEC/CFP2017rate/544.nab_r/544.nab_r
Profile
|
-1.31% |
482.283 |
475.976 |
0.076 |
0.02% |
0.076 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC16
|
-1.31% |
95.732 |
94.482 |
0.002 |
-1.31% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopTC31
|
-1.30% |
990.553 |
977.719 |
1.452 |
-0.00% |
1.452 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC127
|
-1.29% |
87.041 |
85.913 |
0.400 |
0.68% |
0.400 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC32
|
-1.26% |
50.059 |
49.428 |
0.005 |
-0.75% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC127
|
-1.25% |
3161.770 |
3122.243 |
4.004 |
0.00% |
4.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC3
|
-1.24% |
254.698 |
251.543 |
0.637 |
-0.01% |
0.637 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC128
|
-1.24% |
3006.702 |
2969.511 |
3.984 |
0.00% |
3.984 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopWithReductionTC63
|
-1.24% |
56.959 |
56.255 |
0.019 |
0.50% |
0.019 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC16
|
-1.23% |
93.108 |
91.968 |
0.005 |
-0.01% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopTC63
|
-1.21% |
1532.904 |
1514.371 |
0.614 |
-0.01% |
0.614 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<16, EqZero, Last>
|
-1.21% |
13142.589 |
12984.014 |
0.457 |
0.01% |
0.457 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_COUPLE_LAMBDA/0
|
-1.20% |
8089.986 |
7993.244 |
2.927 |
0.54% |
2.927 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC7
|
-1.19% |
596.460 |
589.363 |
1.349 |
-0.01% |
1.349 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, LessThanZero, First>
|
-1.18% |
48643.152 |
48069.184 |
3.716 |
0.00% |
3.716 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC63
|
-1.16% |
1750.372 |
1730.103 |
1.735 |
-0.06% |
1.735 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopTC128
|
-1.08% |
2208.156 |
2184.255 |
2.135 |
-0.02% |
2.135 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC128
|
-1.08% |
172.697 |
170.829 |
0.017 |
0.00% |
0.017 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopTC7
|
-1.08% |
579.443 |
573.175 |
0.130 |
-0.00% |
0.130 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopTC127
|
-1.04% |
2642.499 |
2615.065 |
2.187 |
-0.00% |
2.187 |
|
MicroBenchmarks/Builtins/Int128/Builtins.test:BM_RemainderIntrinsic128UniformDivisor<__uint128_t>
|
-1.04% |
55.713 |
55.135 |
0.083 |
-0.20% |
0.083 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_COUPLE_LAMBDA/2
|
-1.04% |
10.756 |
10.645 |
0.001 |
1.11% |
0.001 |
|
External/SPEC/CFP2017rate/511.povray_r/511.povray_r
Profile
|
-1.03% |
33.951 |
33.601 |
0.125 |
-0.15% |
0.125 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1LoopWithReductionTC63
|
-1.00% |
125.772 |
124.511 |
0.005 |
0.00% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC127
|
-1.00% |
86.924 |
86.053 |
0.085 |
0.21% |
0.085 |