|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_INT_PREDICT_LAMBDA/44217
|
-56.97% |
18827.934 |
8102.563 |
43.476 |
-2.82% |
43.476 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint64_t_To_uint16_t_
|
-50.43% |
35713.935 |
17701.979 |
246.502 |
-50.39% |
246.502 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint64_t_To_uint32_t_
|
-49.45% |
35095.315 |
17739.480 |
529.456 |
-49.77% |
529.456 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint64_t_To_uint8_t_
|
-48.79% |
37095.772 |
18996.090 |
33.426 |
-48.75% |
33.426 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C/miniGMG/miniGMG
Profile
|
-48.44% |
8.846 |
4.561 |
0.234 |
-50.37% |
0.234 |
|
SingleSource/Benchmarks/Polybench/stencils/seidel-2d/seidel-2d
Profile
|
-47.42% |
230.505 |
121.200 |
0.224 |
0.09% |
0.224 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_HYDRO_2D_LAMBDA/44217
|
-45.67% |
85155.255 |
46263.103 |
5271.751 |
-49.12% |
5271.751 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_INT_PREDICT_RAW/44217
|
-44.93% |
14618.701 |
8051.187 |
69.298 |
-11.03% |
69.298 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_DIFF_PREDICT_LAMBDA/44217
|
-44.88% |
24545.595 |
13529.257 |
203.882 |
-41.44% |
203.882 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint16_t_To_uint64_t_
|
-44.02% |
18654.252 |
10442.538 |
4.120 |
-44.08% |
4.120 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_HYDRO_2D_RAW/44217
|
-41.25% |
86652.354 |
50905.687 |
2702.387 |
-39.87% |
2702.387 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint8_t_To_uint64_t_
|
-41.08% |
17869.595 |
10529.321 |
3.845 |
-40.85% |
3.845 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint64_t_To_uint32_t_
|
-40.86% |
38314.536 |
22658.440 |
35.589 |
-40.62% |
35.589 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_DIFF_PREDICT_LAMBDA/5001
|
-40.86% |
2581.724 |
1526.907 |
30.256 |
-39.15% |
30.256 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_HYDRO_2D_LAMBDA/5001
|
-40.60% |
8984.709 |
5336.501 |
435.342 |
-41.44% |
435.342 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIRST_DIFF_LAMBDA/44217
|
-40.12% |
167.090 |
100.060 |
1.599 |
-30.91% |
1.599 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/32
|
-36.70% |
1396.154 |
883.769 |
0.049 |
-36.70% |
0.049 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/64
|
-36.69% |
6182.310 |
3914.248 |
9.075 |
-36.69% |
9.075 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/16
|
-36.63% |
279.476 |
177.095 |
0.010 |
-36.63% |
0.010 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_HYDRO_2D_RAW/5001
|
-36.48% |
9148.630 |
5811.095 |
226.420 |
-33.94% |
226.420 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/256
|
-36.23% |
107119.791 |
68309.300 |
58.656 |
-36.25% |
58.656 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/128
|
-36.09% |
26262.585 |
16785.233 |
9.947 |
-36.11% |
9.947 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint32_t_To_uint64_t_
|
-35.36% |
22431.063 |
14500.086 |
728.279 |
-36.19% |
728.279 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint64_t_To_uint16_t_
|
-34.22% |
29028.743 |
19096.283 |
4.741 |
-34.04% |
4.741 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint64_t_To_uint8_t_
|
-34.17% |
30124.020 |
19829.624 |
44.255 |
-34.14% |
44.255 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_INT_PREDICT_LAMBDA/5001
|
-31.37% |
1331.706 |
913.961 |
8.081 |
1.02% |
8.081 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, EqZero, None>
|
-31.23% |
20510.975 |
14105.065 |
1.041 |
-31.23% |
1.041 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint64_t_To_uint16_t_
|
-29.04% |
25906.699 |
18382.419 |
82.485 |
-29.02% |
82.485 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_DISC_ORD_LAMBDA/44217
|
-28.56% |
13147.172 |
9392.548 |
868.629 |
-33.17% |
868.629 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint32_t_To_uint8_t_
|
-27.81% |
13493.288 |
9741.196 |
10.158 |
-27.68% |
10.158 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC128
|
-27.77% |
1295.817 |
935.983 |
0.245 |
-27.60% |
0.245 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC64
|
-27.52% |
655.666 |
475.197 |
1.460 |
-27.30% |
1.460 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC32
|
-27.32% |
334.976 |
243.458 |
0.766 |
-27.09% |
0.766 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIRST_SUM_LAMBDA/44217
|
-27.30% |
184.741 |
134.305 |
1.085 |
-19.62% |
1.085 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_PIC_2D_LAMBDA/44217
|
-27.07% |
11832.869 |
8629.211 |
89.451 |
-21.29% |
89.451 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC128
|
-27.03% |
558.772 |
407.763 |
0.004 |
-26.86% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC16
|
-26.70% |
174.271 |
127.733 |
0.357 |
-26.50% |
0.357 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC64
|
-25.66% |
292.105 |
217.139 |
0.040 |
-25.59% |
0.040 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_PIC_2D_LAMBDA/5001
|
-25.38% |
1202.057 |
897.008 |
44.417 |
-18.86% |
44.417 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint64_t_To_uint8_t_
|
-24.60% |
27236.864 |
20537.583 |
75.308 |
-24.56% |
75.308 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_DISC_ORD_RAW/44217
|
-24.20% |
13244.621 |
10039.304 |
743.684 |
-24.75% |
743.684 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, EqZero, None>
|
-23.99% |
16024.200 |
12180.675 |
0.504 |
-23.98% |
0.504 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_PIC_2D_RAW/44217
|
-23.55% |
11339.253 |
8668.606 |
87.749 |
-22.71% |
87.749 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC32
|
-23.22% |
158.917 |
122.014 |
0.016 |
-23.20% |
0.016 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC128
|
-23.21% |
603.922 |
463.727 |
0.037 |
-23.22% |
0.037 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC128
|
-23.11% |
603.920 |
464.373 |
0.043 |
-23.11% |
0.043 |
|
MicroBenchmarks/ImageProcessing/Blur/blur.test:BENCHMARK_boxBlurKernel/1024
|
-22.44% |
30098.918 |
23344.643 |
45.448 |
-22.57% |
45.448 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC64
|
-22.35% |
313.497 |
243.424 |
0.007 |
-22.35% |
0.007 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint16_t_To_uint64_t_
|
-22.32% |
13338.627 |
10362.077 |
0.998 |
-21.55% |
0.998 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC127
|
-22.17% |
615.163 |
478.793 |
0.028 |
-22.17% |
0.028 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC64
|
-22.15% |
313.473 |
244.040 |
0.014 |
-22.16% |
0.014 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC127
|
-21.97% |
615.223 |
480.029 |
0.024 |
-21.97% |
0.024 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint8_t_To_uint32_t_
|
-21.62% |
6603.374 |
5175.798 |
1.340 |
-21.37% |
1.340 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint16_t_To_uint32_t_
|
-21.55% |
7102.306 |
5571.600 |
0.691 |
-21.54% |
0.691 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_only_autovec_uint8_t_
|
-21.36% |
182354.350 |
143411.400 |
23.391 |
-21.35% |
23.391 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_PIC_2D_RAW/5001
|
-21.34% |
1142.964 |
899.090 |
51.491 |
-16.63% |
51.491 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIND_FIRST_MIN_LAMBDA/171
|
-21.26% |
1.501 |
1.181 |
0.000 |
-21.28% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIND_FIRST_MIN_LAMBDA/44217
|
-21.25% |
389.399 |
306.649 |
0.305 |
-21.29% |
0.305 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC32
|
-20.82% |
168.322 |
133.279 |
0.006 |
-20.82% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC127
|
-20.70% |
274.957 |
218.044 |
2.084 |
-20.84% |
2.084 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC128
|
-20.69% |
570.694 |
452.613 |
9.263 |
-20.67% |
9.263 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC32
|
-20.44% |
168.318 |
133.907 |
0.002 |
-20.45% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC63
|
-20.43% |
324.793 |
258.446 |
0.002 |
-20.43% |
0.002 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIND_FIRST_MIN_LAMBDA/5001
|
-20.38% |
45.067 |
35.883 |
0.221 |
-20.71% |
0.221 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_PIC_1D_LAMBDA/44217
|
-20.37% |
13676.121 |
10890.229 |
39.101 |
-19.12% |
39.101 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC32
|
-20.16% |
161.439 |
128.890 |
2.512 |
-20.14% |
2.512 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC128
|
-20.11% |
273.340 |
218.380 |
1.189 |
-20.51% |
1.189 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC63
|
-20.04% |
324.793 |
259.701 |
0.003 |
-20.04% |
0.003 |
|
SingleSource/Benchmarks/Adobe-C++/loop_unroll
Profile
|
-19.74% |
3.011 |
2.416 |
0.002 |
-22.23% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC127
|
-19.70% |
640.850 |
514.592 |
0.024 |
-19.66% |
0.024 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC64
|
-19.44% |
297.879 |
239.984 |
3.239 |
-19.39% |
3.239 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC64
|
-19.30% |
149.332 |
120.512 |
1.465 |
-18.92% |
1.465 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC16
|
-19.30% |
92.266 |
74.462 |
0.002 |
-19.31% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint32_t_To_uint8_t_
|
-19.06% |
13909.034 |
11257.874 |
42.731 |
-19.01% |
42.731 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint16_t_To_uint8_t_
|
-19.04% |
3816.277 |
3089.561 |
0.052 |
-19.08% |
0.052 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_INT_PREDICT_RAW/5001
|
-18.81% |
1127.936 |
915.751 |
8.508 |
0.26% |
8.508 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_VOL3D_CALC_LAMBDA/2
|
-18.79% |
8.756 |
7.111 |
0.000 |
-18.80% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_VOL3D_CALC_RAW/2
|
-18.79% |
8.757 |
7.111 |
0.000 |
-18.79% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint32_t_To_uint16_t_
|
-18.72% |
13817.329 |
11230.464 |
17.632 |
-18.66% |
17.632 |
|
MultiSource/Benchmarks/MiBench/automotive-bitcount/automotive-bitcount
Profile
|
-18.53% |
0.124 |
0.101 |
0.001 |
-18.63% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint64_t_To_uint32_t_
|
-18.45% |
27097.506 |
22097.118 |
12.488 |
-18.31% |
12.488 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint8_t_To_uint64_t_
|
-18.44% |
13387.451 |
10919.160 |
4.264 |
-16.42% |
4.264 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC16
|
-18.30% |
95.735 |
78.220 |
0.002 |
-18.30% |
0.002 |
|
MultiSource/Benchmarks/Trimaran/enc-pc1/enc-pc1
Profile
|
-18.11% |
1.104 |
0.904 |
0.000 |
-18.10% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_with_cond_arith_novec_uint8_t_
|
-17.86% |
745941.583 |
612679.554 |
188.216 |
-17.85% |
188.216 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC16
|
-17.64% |
95.736 |
78.846 |
0.001 |
-17.64% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_PIC_1D_RAW/44217
|
-17.43% |
13411.466 |
11074.210 |
12.059 |
-18.14% |
12.059 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC31
|
-17.42% |
179.590 |
148.302 |
0.005 |
-17.42% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_with_cond_arith_novec_int32_t_
|
-17.37% |
740982.520 |
612287.940 |
769.610 |
-17.28% |
769.610 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC4
|
-17.22% |
17.519 |
14.503 |
0.008 |
-17.22% |
0.008 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC16
|
-17.14% |
93.232 |
77.251 |
0.306 |
-17.05% |
0.306 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC31
|
-16.73% |
179.586 |
149.540 |
0.006 |
-16.73% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC63
|
-16.53% |
149.107 |
124.462 |
1.505 |
-16.98% |
1.505 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_VOL3D_CALC_RAW/0
|
-16.39% |
1266.312 |
1058.826 |
2.542 |
-16.31% |
2.542 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_VOL3D_CALC_LAMBDA/0
|
-16.33% |
1268.019 |
1060.975 |
1.458 |
-16.30% |
1.458 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_VOL3D_CALC_RAW/1
|
-16.11% |
260.138 |
218.223 |
0.115 |
-16.11% |
0.115 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_VOL3D_CALC_LAMBDA/1
|
-16.10% |
260.075 |
218.191 |
0.096 |
-16.13% |
0.096 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_HYDRO_1D_RAW/171
|
-16.00% |
0.443 |
0.372 |
0.000 |
-15.84% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC8
|
-15.88% |
58.821 |
49.480 |
0.127 |
-15.80% |
0.127 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_HYDRO_1D_LAMBDA/171
|
-15.86% |
0.442 |
0.372 |
0.000 |
-15.88% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint16_t_To_uint32_t_
|
-15.69% |
7462.896 |
6292.318 |
0.525 |
-15.68% |
0.525 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC127
|
-15.46% |
605.829 |
512.149 |
1.854 |
-15.45% |
1.854 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, EqZero, First>
|
-15.39% |
16670.940 |
14104.759 |
0.514 |
-15.39% |
0.514 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_no_runtime_checks_needed<16, int>
|
-15.38% |
24.402 |
20.649 |
0.001 |
-15.38% |
0.001 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, EqZero, Mid>
|
-15.37% |
16665.928 |
14104.393 |
0.612 |
-15.37% |
0.612 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, EqZero, Last>
|
-15.34% |
16667.289 |
14109.864 |
0.241 |
-15.34% |
0.241 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC4
|
-15.33% |
112.502 |
95.250 |
1.609 |
-15.77% |
1.609 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint32_t_To_uint8_t_
|
-14.97% |
10626.378 |
9035.280 |
22.643 |
-14.72% |
22.643 |
|
MicroBenchmarks/ImageProcessing/Dilate/Dilate.test:BENCHMARK_DILATE/1024
|
-14.83% |
7440.919 |
6337.137 |
201.626 |
-10.88% |
201.626 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC8
|
-14.74% |
59.443 |
50.681 |
0.004 |
-14.75% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC128
|
-14.57% |
1103.322 |
942.533 |
0.062 |
-14.57% |
0.062 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC127
|
-14.52% |
1095.266 |
936.222 |
0.075 |
-14.52% |
0.075 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC64
|
-14.35% |
562.516 |
481.774 |
0.074 |
-14.32% |
0.074 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC63
|
-14.27% |
554.385 |
475.292 |
0.173 |
-14.32% |
0.173 |
|
SingleSource/Benchmarks/Misc/salsa20
Profile
|
-14.14% |
15.386 |
13.211 |
0.001 |
-14.12% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint64_t_To_uint8_t_
|
-14.12% |
22149.375 |
19022.057 |
40.425 |
-13.72% |
40.425 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_with_cond_arith_novec_int64_t_
|
-14.01% |
791845.757 |
680918.296 |
1186.484 |
-13.59% |
1186.484 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC32
|
-13.97% |
292.225 |
251.408 |
0.067 |
-13.90% |
0.067 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC31
|
-13.95% |
284.140 |
244.491 |
0.399 |
-13.94% |
0.399 |
|
External/SPEC/CFP2017rate/508.namd_r/508.namd_r
Profile
|
-13.94% |
223.967 |
192.742 |
0.279 |
-13.79% |
0.279 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint8_t_To_uint16_t_
|
-13.92% |
3757.398 |
3234.423 |
2.511 |
-13.90% |
2.511 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC1
|
-13.86% |
51.936 |
44.736 |
0.003 |
-13.86% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC3
|
-13.86% |
51.937 |
44.738 |
0.003 |
-13.86% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC2
|
-13.86% |
51.935 |
44.737 |
0.003 |
-13.86% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC8
|
-13.86% |
51.936 |
44.740 |
0.001 |
-13.86% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC4
|
-13.85% |
51.933 |
44.739 |
0.001 |
-13.85% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC7
|
-13.85% |
51.932 |
44.739 |
0.002 |
-13.85% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint32_t_To_uint16_t_
|
-13.79% |
12824.755 |
11056.557 |
24.441 |
-13.87% |
24.441 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_with_cond_arith_autovec_int64_t_
|
-13.78% |
791318.997 |
682288.291 |
465.802 |
-13.81% |
465.802 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC8
|
-13.68% |
59.442 |
51.311 |
0.001 |
-13.69% |
0.001 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, EqZero, First>
|
-13.62% |
14103.745 |
12182.396 |
0.578 |
-13.62% |
0.578 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, EqZero, Mid>
|
-13.62% |
14103.723 |
12182.969 |
0.316 |
-13.62% |
0.316 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, EqZero, Last>
|
-13.61% |
14102.462 |
12182.923 |
0.208 |
-13.63% |
0.208 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC8
|
-13.56% |
23.152 |
20.012 |
0.004 |
-13.56% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC32
|
-13.56% |
85.359 |
73.787 |
1.205 |
-13.52% |
1.205 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint32_t_To_uint8_t_
|
-13.46% |
11076.899 |
9586.026 |
38.529 |
-13.87% |
38.529 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC63
|
-13.43% |
374.457 |
324.176 |
0.151 |
-13.42% |
0.151 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC63
|
-13.41% |
332.906 |
288.259 |
1.143 |
-13.39% |
1.143 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC16
|
-13.18% |
157.055 |
136.359 |
0.027 |
-13.13% |
0.027 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC8
|
-13.17% |
23.779 |
20.648 |
0.001 |
-13.16% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_HYDRO_1D_LAMBDA/5001
|
-13.12% |
18.097 |
15.723 |
0.624 |
-8.45% |
0.624 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC128
|
-13.08% |
81.343 |
70.704 |
0.004 |
-13.08% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint8_t_To_uint16_t_
|
-12.96% |
4542.884 |
3954.038 |
0.201 |
-12.94% |
0.201 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC15
|
-12.86% |
107.004 |
93.239 |
0.003 |
-12.86% |
0.003 |
|
SingleSource/Benchmarks/Shootout-C++/Shootout-C++-matrix
Profile
|
-12.74% |
2.509 |
2.190 |
0.000 |
-12.71% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC15
|
-12.67% |
148.943 |
130.071 |
0.038 |
-12.59% |
0.038 |
|
MultiSource/Benchmarks/MiBench/security-rijndael/security-rijndael
Profile
|
-12.61% |
0.335 |
0.292 |
0.000 |
-12.61% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint16_t_To_uint8_t_
|
-12.40% |
4742.978 |
4154.726 |
0.375 |
-12.40% |
0.375 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC15
|
-12.14% |
51.934 |
45.628 |
0.173 |
-12.15% |
0.173 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC31
|
-12.09% |
86.311 |
75.874 |
0.221 |
-11.89% |
0.221 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC16
|
-11.94% |
51.937 |
45.735 |
0.122 |
-11.95% |
0.122 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC8
|
-11.87% |
89.442 |
78.825 |
0.012 |
-11.83% |
0.012 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC2
|
-11.77% |
21.275 |
18.771 |
0.001 |
-11.77% |
0.001 |
|
MultiSource/Benchmarks/TSVC/NodeSplitting-dbl/NodeSplitting-dbl
Profile
|
-11.70% |
28.533 |
25.195 |
0.427 |
-4.62% |
0.427 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC15
|
-11.69% |
106.998 |
94.489 |
0.001 |
-11.70% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIRST_SUM_LAMBDA/5001
|
-11.56% |
20.573 |
18.196 |
0.348 |
3.34% |
0.348 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC16
|
-11.36% |
33.161 |
29.396 |
0.006 |
-11.36% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC4
|
-11.11% |
22.526 |
20.023 |
0.000 |
-11.11% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC3
|
-11.11% |
22.524 |
20.022 |
0.002 |
-11.12% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC4
|
-11.11% |
22.525 |
20.023 |
0.002 |
-11.11% |
0.002 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_PRESSURE_CALC_LAMBDA/5001
|
-10.92% |
45.244 |
40.303 |
1.899 |
-8.35% |
1.899 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint8_t>/51
|
-10.90% |
123.895 |
110.396 |
0.161 |
19.34% |
0.161 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC7
|
-10.80% |
81.347 |
72.565 |
0.012 |
-10.76% |
0.012 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIRST_DIFF_LAMBDA/5001
|
-10.64% |
13.085 |
11.694 |
0.362 |
-4.08% |
0.362 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC4
|
-10.60% |
41.296 |
36.919 |
0.002 |
-10.61% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC4
|
-10.52% |
23.778 |
21.276 |
0.001 |
-10.53% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC64
|
-10.47% |
53.815 |
48.180 |
0.002 |
-10.47% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint64_t_To_uint16_t_
|
-10.44% |
19168.392 |
17167.388 |
633.619 |
-9.57% |
633.619 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/16
|
-10.18% |
115.476 |
103.719 |
0.007 |
-10.17% |
0.007 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/64
|
-10.11% |
1914.102 |
1720.490 |
11.973 |
-10.08% |
11.973 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC4
|
-10.10% |
55.689 |
50.064 |
0.000 |
-10.06% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint8_t_To_uint16_t_
|
-10.02% |
5848.785 |
5262.535 |
2.948 |
-10.05% |
2.948 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC31
|
-10.01% |
196.478 |
176.810 |
0.577 |
-10.01% |
0.577 |
|
SingleSource/Benchmarks/Misc-C++/oopack_v1p8
Profile
|
-9.99% |
0.519 |
0.467 |
0.000 |
-9.96% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC127
|
-9.99% |
102.192 |
91.986 |
0.003 |
-9.71% |
0.003 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/32
|
-9.98% |
472.958 |
425.734 |
0.029 |
-9.99% |
0.029 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/256
|
-9.95% |
31442.288 |
28314.632 |
26.077 |
-9.97% |
26.077 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_only_autovec_int64_t_
|
-9.94% |
333401.427 |
300247.354 |
628.180 |
-9.91% |
628.180 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/128
|
-9.80% |
7913.099 |
7137.401 |
4.062 |
-9.85% |
4.062 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC7
|
-9.80% |
353.707 |
319.059 |
4.820 |
-10.05% |
4.820 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC8
|
-9.76% |
25.654 |
23.150 |
0.001 |
-9.77% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC8
|
-9.76% |
25.656 |
23.152 |
0.001 |
-9.76% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC8
|
-9.74% |
27.037 |
24.403 |
0.000 |
-9.33% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_DIFF_PREDICT_LAMBDA/171
|
-9.72% |
12.308 |
11.111 |
0.069 |
-7.30% |
0.069 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC7
|
-9.61% |
32.538 |
29.410 |
0.001 |
-9.61% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC7
|
-9.52% |
26.279 |
23.776 |
0.001 |
-9.53% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC7
|
-9.51% |
26.278 |
23.778 |
0.001 |
-9.53% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC32
|
-9.51% |
53.183 |
48.127 |
0.022 |
-9.52% |
0.022 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_DEL_DOT_VEC_2D_LAMBDA/1
|
-9.25% |
287.154 |
260.593 |
0.271 |
-9.24% |
0.271 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_DEL_DOT_VEC_2D_RAW/1
|
-9.24% |
287.084 |
260.555 |
0.042 |
-9.21% |
0.042 |
|
MultiSource/Benchmarks/FreeBench/pifft/pifft
Profile
|
-9.11% |
0.359 |
0.326 |
0.001 |
-9.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC4
|
-9.09% |
41.296 |
37.544 |
0.001 |
-9.09% |
0.001 |
|
MultiSource/Benchmarks/McCat/12-IOtest/iotest
Profile
|
-9.01% |
1.860 |
1.693 |
0.028 |
-7.24% |
0.028 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC7
|
-8.89% |
28.157 |
25.654 |
0.001 |
-8.90% |
0.001 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_runtime_checks_pass<4, int>
|
-8.75% |
16.800 |
15.330 |
0.001 |
-8.25% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_DEL_DOT_VEC_2D_RAW/2
|
-8.71% |
3.510 |
3.204 |
0.000 |
-8.71% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_DEL_DOT_VEC_2D_LAMBDA/2
|
-8.70% |
3.510 |
3.204 |
0.000 |
-8.70% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC16
|
-8.62% |
36.293 |
33.164 |
0.001 |
-8.62% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_HYDRO_1D_RAW/5001
|
-8.59% |
16.319 |
14.918 |
0.304 |
-10.59% |
0.304 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint16_t_To_uint8_t_
|
-8.54% |
6811.849 |
6230.387 |
4.614 |
-8.59% |
4.614 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC8
|
-8.51% |
29.410 |
26.906 |
0.001 |
-8.52% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint8_t>/28
|
-8.27% |
82.596 |
75.762 |
0.038 |
12.09% |
0.038 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_DISC_ORD_LAMBDA/5001
|
-8.21% |
641.341 |
588.687 |
6.063 |
-7.63% |
6.063 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC2
|
-8.20% |
38.169 |
35.041 |
0.002 |
-8.20% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC64
|
-8.05% |
93.230 |
85.723 |
0.004 |
-8.06% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint32_t_To_uint64_t_
|
-7.97% |
16525.119 |
15207.658 |
312.766 |
-11.56% |
312.766 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint16_t_To_uint64_t_
|
-7.90% |
20252.021 |
18652.353 |
80.709 |
-7.40% |
80.709 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC3
|
-7.89% |
47.554 |
43.801 |
0.002 |
-7.90% |
0.002 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIRST_DIFF_RAW/5001
|
-7.84% |
12.443 |
11.467 |
0.265 |
-4.89% |
0.265 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC16
|
-7.84% |
31.911 |
29.410 |
0.000 |
-7.84% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC16
|
-7.84% |
31.909 |
29.409 |
0.001 |
-7.84% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC32
|
-7.80% |
40.044 |
36.920 |
0.001 |
-7.81% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_DISC_ORD_RAW/5001
|
-7.80% |
643.211 |
593.067 |
4.727 |
-10.78% |
4.727 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC15
|
-7.70% |
32.538 |
30.033 |
0.001 |
-7.70% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_DEL_DOT_VEC_2D_RAW/0
|
-7.69% |
1796.311 |
1658.137 |
2.626 |
-7.93% |
2.626 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC15
|
-7.69% |
32.537 |
30.036 |
0.002 |
-7.69% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint8_t_To_uint32_t_
|
-7.68% |
12766.388 |
11786.164 |
16.451 |
-7.77% |
16.451 |
|
MultiSource/Benchmarks/VersaBench/beamformer/beamformer
Profile
|
-7.60% |
5.200 |
4.805 |
0.003 |
-7.62% |
0.003 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_HYDRO_2D_RAW/171
|
-7.59% |
88.880 |
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/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC127
|
-7.46% |
2404.153 |
2224.827 |
21.632 |
-8.32% |
21.632 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_DEL_DOT_VEC_2D_LAMBDA/0
|
-7.43% |
1789.513 |
1656.587 |
2.662 |
-7.56% |
2.662 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_xor_no_runtime_checks_needed<16, int>
|
-7.42% |
16.896 |
15.643 |
0.001 |
-7.42% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC1
|
-7.29% |
88.687 |
82.223 |
1.500 |
-7.60% |
1.500 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIND_FIRST_MIN_RAW/171
|
-7.24% |
1.498 |
1.389 |
0.000 |
-7.19% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC128
|
-7.22% |
173.335 |
160.819 |
0.011 |
-7.22% |
0.011 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint8_t>/127
|
-7.20% |
138.906 |
128.899 |
0.007 |
-7.21% |
0.007 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint16_t_To_uint64_t_
|
-7.19% |
25010.247 |
23211.172 |
30.715 |
-7.10% |
30.715 |
|
MultiSource/Applications/lambda-0.1.3/lambda
Profile
|
-7.17% |
15.862 |
14.724 |
0.002 |
-7.22% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC7
|
-7.08% |
70.709 |
65.703 |
0.001 |
-7.09% |
0.001 |
|
MicroBenchmarks/harris/harris.test:BENCHMARK_HARRIS/2048/2048
|
-7.02% |
169513.301 |
157609.300 |
4164.641 |
-5.64% |
4164.641 |
|
SingleSource/Benchmarks/Misc/pi
Profile
|
-7.01% |
1.782 |
1.657 |
0.000 |
-7.01% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC15
|
-6.94% |
45.051 |
41.925 |
0.024 |
-6.94% |
0.024 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC15
|
-6.89% |
54.440 |
50.687 |
0.006 |
-6.90% |
0.006 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C/miniAMR/miniAMR
Profile
|
-6.89% |
3.458 |
3.220 |
0.048 |
-0.90% |
0.048 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_HYDRO_2D_LAMBDA/171
|
-6.82% |
88.257 |
82.237 |
0.966 |
-7.24% |
0.966 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC128
|
-6.74% |
68.826 |
64.185 |
0.106 |
-6.71% |
0.106 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC31
|
-6.72% |
74.457 |
69.456 |
0.004 |
-6.73% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC63
|
-6.56% |
114.512 |
107.000 |
0.057 |
-6.56% |
0.057 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_xor_runtime_checks_pass<16, int>
|
-6.52% |
28.784 |
26.906 |
0.003 |
-6.52% |
0.003 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_xor_runtime_checks_fail<16, int>
|
-6.52% |
28.786 |
26.909 |
0.000 |
-6.51% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC127
|
-6.42% |
194.609 |
182.110 |
0.318 |
-6.42% |
0.318 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_runtime_checks_fail<4, int>
|
-6.38% |
16.375 |
15.331 |
0.000 |
-3.63% |
0.000 |
|
SingleSource/Benchmarks/Misc/flops-6
Profile
|
-6.37% |
1.311 |
1.228 |
0.000 |
-6.46% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC15
|
-6.34% |
39.419 |
36.918 |
0.003 |
-6.35% |
0.003 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_BAND_LIN_EQ_RAW/171
|
-6.34% |
0.366 |
0.343 |
0.000 |
-6.34% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_BAND_LIN_EQ_LAMBDA/171
|
-6.32% |
0.366 |
0.343 |
0.000 |
-6.32% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_only_autovec_int32_t_
|
-6.32% |
180886.634 |
169462.444 |
415.388 |
-6.44% |
415.388 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint16_t>/127
|
-6.30% |
138.901 |
130.156 |
0.004 |
-6.30% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC127
|
-6.28% |
68.593 |
64.286 |
0.073 |
-5.87% |
0.073 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC63
|
-6.28% |
74.112 |
69.460 |
0.002 |
-6.42% |
0.002 |
|
SingleSource/Benchmarks/Misc-C++/Large/sphereflake
Profile
|
-6.22% |
20.011 |
18.766 |
0.004 |
-6.18% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC16
|
-6.14% |
40.669 |
38.170 |
0.001 |
-6.16% |
0.001 |
|
MultiSource/Benchmarks/MiBench/telecomm-gsm/telecomm-gsm
Profile
|
-5.97% |
0.663 |
0.623 |
0.000 |
-6.04% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint8_t>/65
|
-5.91% |
95.106 |
89.482 |
0.006 |
-5.92% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint32_t>/127
|
-5.88% |
138.286 |
130.150 |
0.010 |
-5.88% |
0.010 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIND_FIRST_MIN_RAW/5001
|
-5.86% |
45.123 |
42.479 |
0.033 |
-6.31% |
0.033 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC16
|
-5.83% |
31.894 |
30.036 |
0.001 |
-4.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint8_t_To_uint16_t_
|
-5.77% |
3638.947 |
3428.987 |
2.210 |
-5.62% |
2.210 |
|
SingleSource/Benchmarks/Stanford/Puzzle
Profile
|
-5.74% |
0.241 |
0.228 |
0.001 |
-5.72% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC16
|
-5.65% |
33.162 |
31.289 |
0.001 |
-5.65% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC32
|
-5.64% |
44.427 |
41.921 |
0.003 |
-5.64% |
0.003 |
|
External/SPEC/CFP2017rate/538.imagick_r/538.imagick_r
Profile
|
-5.64% |
290.918 |
274.520 |
0.421 |
-6.01% |
0.421 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C++/miniFE/miniFE
Profile
|
-5.63% |
15.842 |
14.950 |
0.056 |
-6.38% |
0.056 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC32
|
-5.63% |
44.427 |
41.925 |
0.001 |
-5.64% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint32_t_To_uint64_t_
|
-5.61% |
21435.058 |
20233.493 |
38.658 |
-5.68% |
38.658 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIND_FIRST_MIN_RAW/44217
|
-5.58% |
389.892 |
368.121 |
0.466 |
-5.51% |
0.466 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC31
|
-5.58% |
45.063 |
42.547 |
0.002 |
-5.58% |
0.002 |
|
SingleSource/Benchmarks/Polybench/stencils/jacobi-2d/jacobi-2d
Profile
|
-5.58% |
31.944 |
30.161 |
0.202 |
-6.40% |
0.202 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC31
|
-5.56% |
45.053 |
42.549 |
0.001 |
-5.56% |
0.001 |
|
MultiSource/Benchmarks/SciMark2-C/scimark2
Profile
|
-5.55% |
107.722 |
101.747 |
0.018 |
-5.47% |
0.018 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIRST_SUM_RAW/5001
|
-5.54% |
18.631 |
17.600 |
0.390 |
1.46% |
0.390 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC31
|
-5.52% |
905.399 |
855.394 |
14.314 |
-6.72% |
14.314 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_PRESSURE_CALC_RAW/5001
|
-5.51% |
46.211 |
43.664 |
0.481 |
-2.10% |
0.481 |
|
MultiSource/Benchmarks/TSVC/ControlFlow-flt/ControlFlow-flt
Profile
|
-5.47% |
30.320 |
28.660 |
0.567 |
-0.27% |
0.567 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint32_t>/999
|
-5.40% |
696.538 |
658.914 |
0.066 |
-5.40% |
0.066 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC32
|
-5.40% |
61.316 |
58.006 |
0.090 |
-5.41% |
0.090 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC128
|
-5.39% |
2968.520 |
2808.413 |
49.597 |
-5.58% |
49.597 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC127
|
-5.38% |
3120.351 |
2952.533 |
51.895 |
-5.63% |
51.895 |
|
MultiSource/Benchmarks/Rodinia/hotspot/hotspot
Profile
|
-5.36% |
2.040 |
1.931 |
0.009 |
-5.18% |
0.009 |
|
MultiSource/Benchmarks/TSVC/ControlLoops-dbl/ControlLoops-dbl
Profile
|
-5.32% |
11.129 |
10.537 |
0.180 |
-4.38% |
0.180 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC7
|
-5.31% |
70.709 |
66.952 |
0.004 |
-5.33% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopWithReductionTC1
|
-5.26% |
11.889 |
11.264 |
0.000 |
-5.26% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint32_t>/999
|
-5.23% |
1365.058 |
1293.663 |
0.054 |
-5.23% |
0.054 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC15
|
-5.19% |
128.277 |
121.622 |
0.036 |
-5.17% |
0.036 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_PIC_2D_LAMBDA/171
|
-5.17% |
13.467 |
12.770 |
0.054 |
-5.39% |
0.054 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_PIC_2D_RAW/171
|
-5.14% |
13.522 |
12.827 |
0.062 |
-5.26% |
0.062 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC32
|
-5.14% |
24.404 |
23.151 |
0.002 |
-5.13% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC32
|
-5.13% |
24.403 |
23.151 |
0.001 |
-5.14% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC31
|
-5.13% |
24.404 |
23.152 |
0.001 |
-5.13% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC31
|
-5.13% |
24.403 |
23.152 |
0.003 |
-5.13% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC31
|
-5.05% |
241.230 |
229.041 |
0.046 |
-5.05% |
0.046 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC64
|
-5.02% |
43.798 |
41.598 |
0.060 |
-3.65% |
0.060 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_PRESSURE_CALC_LAMBDA/44217
|
-4.80% |
505.479 |
481.208 |
2.125 |
-3.48% |
2.125 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint32_t>/256
|
-4.80% |
364.152 |
346.677 |
0.007 |
-4.80% |
0.007 |
|
SingleSource/Benchmarks/Misc/revertBits
Profile
|
-4.68% |
0.641 |
0.611 |
0.000 |
-4.67% |
0.000 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_runtime_checks_fail<16, int>
|
-4.61% |
54.441 |
51.933 |
0.002 |
-4.60% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint16_t>/65
|
-4.61% |
95.113 |
90.732 |
0.008 |
-4.61% |
0.008 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_runtime_checks_pass<16, int>
|
-4.59% |
54.438 |
51.937 |
0.002 |
-4.59% |
0.002 |
|
External/SPEC/CFP2017rate/519.lbm_r/519.lbm_r
Profile
|
-4.54% |
200.547 |
191.449 |
1.860 |
-4.60% |
1.860 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopWithReductionTC2
|
-4.52% |
13.766 |
13.143 |
0.004 |
-4.52% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC31
|
-4.47% |
70.080 |
66.950 |
0.005 |
-4.47% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC63
|
-4.46% |
1638.025 |
1565.008 |
26.280 |
-4.79% |
26.280 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_ENERGY_CALC_RAW/5001
|
-4.42% |
435.453 |
416.195 |
3.453 |
-2.93% |
3.453 |
|
SingleSource/Benchmarks/Misc/oourafft
Profile
|
-4.41% |
15.073 |
14.409 |
0.080 |
-4.53% |
0.080 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_ENERGY_CALC_RAW/171
|
-4.38% |
14.221 |
13.598 |
0.012 |
-4.51% |
0.012 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC4
|
-4.36% |
14.392 |
13.765 |
0.001 |
-4.36% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC2
|
-4.36% |
14.392 |
13.765 |
0.001 |
-4.35% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC7
|
-4.35% |
14.392 |
13.765 |
0.000 |
-4.35% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC8
|
-4.35% |
14.392 |
13.765 |
0.001 |
-4.36% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint8_t_To_uint64_t_
|
-4.35% |
23485.786 |
22463.984 |
73.898 |
-4.34% |
73.898 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_PIC_1D_RAW/5001
|
-4.35% |
350.845 |
335.583 |
1.323 |
-2.74% |
1.323 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC15
|
-4.35% |
14.392 |
13.766 |
0.003 |
-4.35% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC1
|
-4.35% |
14.394 |
13.768 |
0.001 |
-4.34% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC3
|
-4.35% |
14.391 |
13.765 |
0.001 |
-4.35% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC1
|
-4.35% |
14.391 |
13.766 |
0.001 |
-4.35% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC4
|
-4.35% |
14.391 |
13.766 |
0.001 |
-4.35% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC3
|
-4.35% |
14.392 |
13.766 |
0.000 |
-4.35% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC15
|
-4.34% |
14.391 |
13.766 |
0.000 |
-4.35% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC7
|
-4.34% |
14.391 |
13.766 |
0.000 |
-4.34% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC16
|
-4.34% |
14.391 |
13.766 |
0.002 |
-4.35% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC2
|
-4.34% |
14.391 |
13.766 |
0.000 |
-4.34% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC63
|
-4.34% |
1730.554 |
1655.492 |
24.783 |
-4.70% |
24.783 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC8
|
-4.34% |
14.391 |
13.767 |
0.000 |
-4.35% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_nested_cond_load_novec_int32_t_
|
-4.32% |
650612.650 |
622487.876 |
290.384 |
-3.51% |
290.384 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint32_t_To_uint16_t_
|
-4.32% |
9856.316 |
9430.376 |
40.592 |
-4.55% |
40.592 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint64_t>/999
|
-4.26% |
1811.234 |
1734.101 |
0.035 |
-4.26% |
0.035 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_ENERGY_CALC_LAMBDA/171
|
-4.21% |
14.207 |
13.608 |
0.023 |
-4.49% |
0.023 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint64_t>/999
|
-4.15% |
3594.979 |
3445.690 |
0.219 |
-4.14% |
0.219 |
|
MicroBenchmarks/LCALS/SubsetBLambdaLoops/lcalsBLambda.test:BM_MULADDSUB_LAMBDA/171
|
-4.14% |
0.430 |
0.413 |
0.003 |
-1.24% |
0.003 |
|
SingleSource/Benchmarks/Misc/flops-5
Profile
|
-4.14% |
2.021 |
1.937 |
0.001 |
-4.14% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC63
|
-4.10% |
43.459 |
41.679 |
0.022 |
-3.73% |
0.022 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC64
|
-4.09% |
1486.756 |
1425.995 |
23.128 |
-4.33% |
23.128 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint64_t_To_uint32_t_
|
-4.07% |
19356.268 |
18567.791 |
55.986 |
-3.76% |
55.986 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint64_t>/256
|
-4.07% |
935.484 |
897.386 |
0.036 |
-4.08% |
0.036 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_PRESSURE_CALC_RAW/44217
|
-4.05% |
499.264 |
479.064 |
3.780 |
-4.61% |
3.780 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC31
|
-4.04% |
61.947 |
59.442 |
0.004 |
-4.04% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint8_t>/16
|
-4.00% |
60.019 |
57.620 |
0.230 |
7.06% |
0.230 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_only_autovec_uint8_t_
|
-3.97% |
96150.395 |
92331.585 |
19.347 |
-3.98% |
19.347 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint32_t>/65
|
-3.97% |
94.484 |
90.736 |
0.000 |
-3.97% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC32
|
-3.97% |
63.200 |
60.694 |
0.003 |
-3.96% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint32_t>/256
|
-3.95% |
221.500 |
212.755 |
0.004 |
-3.95% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC32
|
-3.93% |
31.287 |
30.057 |
0.183 |
-3.93% |
0.183 |
|
SingleSource/Benchmarks/Misc/ffbench
Profile
|
-3.92% |
11.069 |
10.635 |
0.138 |
-4.05% |
0.138 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC3
|
-3.85% |
16.269 |
15.643 |
0.001 |
-3.85% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC15
|
-3.81% |
44.637 |
42.937 |
0.407 |
-3.36% |
0.407 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<31, EqZero, First>
|
-3.69% |
3346.442 |
3222.795 |
0.304 |
-3.69% |
0.304 |
|
SingleSource/Benchmarks/Shootout/Shootout-matrix
Profile
|
-3.69% |
3.864 |
3.721 |
0.000 |
-3.68% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint16_t_To_uint8_t_
|
-3.67% |
2874.554 |
2769.076 |
1.719 |
-3.79% |
1.719 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint64_t>/256
|
-3.65% |
514.369 |
495.618 |
0.036 |
-3.65% |
0.036 |
|
MultiSource/Benchmarks/nbench/nbench
Profile
|
-3.64% |
6.127 |
5.904 |
0.003 |
-3.63% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC64
|
-3.61% |
69.457 |
66.951 |
0.002 |
-3.61% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC64
|
-3.59% |
69.449 |
66.953 |
0.002 |
-3.60% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC63
|
-3.59% |
70.088 |
67.575 |
0.003 |
-3.59% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC63
|
-3.57% |
70.078 |
67.575 |
0.003 |
-3.58% |
0.003 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<32, EqZero, Last>
|
-3.57% |
7066.874 |
6814.645 |
47.557 |
-3.38% |
47.557 |
|
MicroBenchmarks/ImageProcessing/Dilate/Dilate.test:BENCHMARK_DILATE/256
|
-3.53% |
1059.116 |
1021.767 |
0.514 |
-4.26% |
0.514 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC31
|
-3.52% |
60.316 |
58.194 |
0.001 |
-3.45% |
0.001 |
|
External/SPEC/CFP2017rate/544.nab_r/544.nab_r
Profile
|
-3.51% |
477.395 |
460.629 |
0.075 |
-3.61% |
0.075 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_FLOYD_DITHER/256
|
-3.47% |
1800.258 |
1737.764 |
14.899 |
0.24% |
14.899 |
|
MicroBenchmarks/LCALS/SubsetBRawLoops/lcalsBRaw.test:BM_MULADDSUB_RAW/171
|
-3.41% |
0.426 |
0.412 |
0.000 |
-1.52% |
0.000 |
|
MultiSource/Applications/JM/lencod/lencod
Profile
|
-3.33% |
32.698 |
31.610 |
0.030 |
-2.86% |
0.030 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_BAND_LIN_EQ_RAW/5001
|
-3.30% |
20.862 |
20.173 |
0.056 |
-2.18% |
0.056 |
|
MultiSource/Benchmarks/Rodinia/pathfinder/pathfinder
Profile
|
-3.28% |
1.263 |
1.221 |
0.009 |
-2.89% |
0.009 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC31
|
-3.24% |
93.849 |
90.804 |
0.058 |
-3.25% |
0.058 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint16_t_To_uint8_t_
|
-3.22% |
4516.442 |
4370.894 |
3.888 |
-3.24% |
3.888 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint16_t>/999
|
-3.15% |
514.952 |
498.732 |
0.017 |
-3.16% |
0.017 |
|
SingleSource/Benchmarks/Shootout/Shootout-lists
Profile
|
-3.13% |
11.316 |
10.961 |
0.007 |
-3.11% |
0.007 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1BigLoopWithReductionTC1
|
-3.13% |
20.024 |
19.396 |
0.001 |
-3.14% |
0.001 |
|
MicroBenchmarks/ImageProcessing/Dilate/Dilate.test:BENCHMARK_DILATE/512
|
-3.12% |
3613.548 |
3500.983 |
20.286 |
-2.32% |
20.286 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchVecWithRuntimeChecks4PointersDBeforeA/1000
|
-3.07% |
5019667.245 |
4865339.396 |
230.272 |
-3.08% |
230.272 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<31, GreaterThanZero, Last>
|
-3.07% |
8355.620 |
8099.272 |
0.814 |
-2.37% |
0.814 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIRST_DIFF_RAW/44217
|
-3.01% |
104.866 |
101.714 |
0.975 |
-28.62% |
0.975 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, LessThanZero, None>
|
-2.92% |
37605.644 |
36507.563 |
56.730 |
-2.84% |
56.730 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint16_t>/999
|
-2.83% |
1013.693 |
985.011 |
0.019 |
-2.85% |
0.019 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC64
|
-2.80% |
111.376 |
108.254 |
0.002 |
-2.81% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC1
|
-2.78% |
22.527 |
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/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC31
|
-2.76% |
31.244 |
30.382 |
0.046 |
-2.59% |
0.046 |
|
MultiSource/Benchmarks/mafft/pairlocalalign
Profile
|
-2.70% |
94.157 |
91.614 |
0.350 |
-2.60% |
0.350 |
|
MultiSource/Benchmarks/FreeBench/mason/mason
Profile
|
-2.68% |
0.553 |
0.538 |
0.000 |
-2.68% |
0.000 |
|
External/SPEC/CINT2017rate/523.xalancbmk_r/523.xalancbmk_r
Profile
|
-2.62% |
246.479 |
240.012 |
0.711 |
-0.39% |
0.711 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C/CoMD/CoMD
Profile
|
-2.60% |
9.899 |
9.642 |
0.003 |
-2.60% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC63
|
-2.60% |
120.143 |
117.021 |
0.049 |
-2.60% |
0.049 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<64, EqZero, Mid>
|
-2.60% |
2759.430 |
2687.809 |
6.682 |
-2.06% |
6.682 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_FLOYD_DITHER/512
|
-2.59% |
6655.053 |
6482.985 |
20.934 |
-2.44% |
20.934 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint8_t>/10
|
-2.55% |
48.803 |
47.558 |
0.029 |
2.47% |
0.029 |
|
MultiSource/Benchmarks/FreeBench/fourinarow/fourinarow
Profile
|
-2.52% |
0.650 |
0.634 |
0.001 |
-2.54% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint8_t_To_uint32_t_
|
-2.51% |
7077.373 |
6899.723 |
0.993 |
-2.51% |
0.993 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC32
|
-2.49% |
50.052 |
48.808 |
0.002 |
-2.49% |
0.002 |
|
MultiSource/Benchmarks/sim/sim
Profile
|
-2.47% |
9.697 |
9.458 |
0.035 |
-2.50% |
0.035 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchVecWithRuntimeChecks4PointersDBeforeA/32
|
-2.45% |
166195.997 |
162124.053 |
11.064 |
-2.45% |
11.064 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint8_t>/16
|
-2.44% |
86.588 |
84.474 |
0.007 |
11.81% |
0.007 |
|
SingleSource/Benchmarks/BenchmarkGame/puzzle
Profile
|
-2.42% |
0.870 |
0.849 |
0.004 |
-2.23% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_only_autovec_int64_t_
|
-2.40% |
1448605.238 |
1413885.606 |
1666.857 |
-2.29% |
1666.857 |
|
MultiSource/Benchmarks/Olden/health/health
Profile
|
-2.39% |
1.598 |
1.559 |
0.002 |
-2.02% |
0.002 |
|
MultiSource/Applications/sgefa/sgefa
Profile
|
-2.36% |
0.579 |
0.566 |
0.002 |
-1.39% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint32_t_To_uint64_t_
|
-2.35% |
26413.775 |
25793.303 |
29.951 |
-1.85% |
29.951 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC63
|
-2.35% |
106.999 |
104.490 |
0.006 |
-2.35% |
0.006 |
|
SingleSource/Benchmarks/Misc/fbench
Profile
|
-2.34% |
5.762 |
5.627 |
0.000 |
-2.32% |
0.000 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_FLOYD_DITHER/128
|
-2.34% |
436.857 |
426.643 |
2.695 |
-2.92% |
2.695 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC64
|
-2.31% |
108.250 |
105.745 |
0.004 |
-2.31% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint64_t_To_uint8_t_
|
-2.31% |
19764.958 |
19307.602 |
42.233 |
-2.69% |
42.233 |
|
MultiSource/Benchmarks/tramp3d-v4/tramp3d-v4
Profile
|
-2.29% |
1.079 |
1.055 |
0.002 |
-1.95% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint16_t_To_uint32_t_
|
-2.26% |
11284.092 |
11028.769 |
16.648 |
-2.77% |
16.648 |
|
MultiSource/Benchmarks/TSVC/LinearDependence-flt/LinearDependence-flt
Profile
|
-2.18% |
14.063 |
13.756 |
0.039 |
-0.49% |
0.039 |
|
SingleSource/Benchmarks/Misc/flops-1
Profile
|
-2.17% |
9.002 |
8.806 |
0.000 |
-2.15% |
0.000 |
|
SingleSource/Benchmarks/Misc-C++/Large/ray
Profile
|
-2.10% |
12.103 |
11.849 |
0.001 |
-2.08% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC128
|
-2.09% |
119.514 |
117.014 |
0.003 |
-2.10% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC128
|
-2.09% |
119.505 |
117.010 |
0.003 |
-2.10% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC127
|
-2.09% |
120.144 |
117.636 |
0.008 |
-2.09% |
0.008 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC127
|
-2.08% |
120.142 |
117.642 |
0.001 |
-2.08% |
0.001 |
|
SingleSource/Benchmarks/Polybench/stencils/fdtd-2d/fdtd-2d
Profile
|
-2.07% |
19.799 |
19.388 |
0.153 |
-0.59% |
0.153 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_EOS_RAW/171
|
-2.02% |
0.873 |
0.856 |
0.002 |
-1.74% |
0.002 |
|
External/SPEC/CINT2017rate/531.deepsjeng_r/531.deepsjeng_r
Profile
|
-1.97% |
260.597 |
255.457 |
0.123 |
-1.79% |
0.123 |
|
SingleSource/Benchmarks/Misc/ReedSolomon
Profile
|
-1.96% |
20.820 |
20.412 |
0.000 |
-1.85% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_ENERGY_CALC_LAMBDA/5001
|
-1.94% |
433.334 |
424.912 |
1.482 |
-3.00% |
1.482 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<16, EqZero, None>
|
-1.94% |
8175.868 |
8017.077 |
53.461 |
-1.96% |
53.461 |
|
MultiSource/Benchmarks/Bullet/bullet
Profile
|
-1.93% |
30.546 |
29.958 |
0.084 |
-1.55% |
0.084 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<3, GreaterThanZero, None>
|
-1.92% |
45058.675 |
44194.333 |
117.831 |
-2.10% |
117.831 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<64, GreaterThanZero, Mid>
|
-1.86% |
2742.615 |
2691.621 |
16.494 |
-1.97% |
16.494 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<32, EqZero, None>
|
-1.84% |
4412.055 |
4330.790 |
3.745 |
-1.83% |
3.745 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<16, EqZero, Mid>
|
-1.84% |
8657.188 |
8497.764 |
57.741 |
-1.84% |
57.741 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C/SimpleMOC/SimpleMOC
Profile
|
-1.83% |
10.403 |
10.213 |
0.040 |
-1.85% |
0.040 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint16_t>/256
|
-1.83% |
272.808 |
267.821 |
0.010 |
-1.84% |
0.010 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_EOS_LAMBDA/171
|
-1.80% |
0.872 |
0.856 |
0.001 |
-1.68% |
0.001 |
|
SingleSource/Benchmarks/Shootout-C++/Shootout-C++-hash2
Profile
|
-1.75% |
9.349 |
9.186 |
0.024 |
-1.61% |
0.024 |
|
MultiSource/Benchmarks/TSVC/ControlLoops-flt/ControlLoops-flt
Profile
|
-1.71% |
5.427 |
5.334 |
0.006 |
-2.08% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_nested_cond_load_novec_uint8_t_
|
-1.70% |
504697.254 |
496099.025 |
209.882 |
-1.71% |
209.882 |
|
MultiSource/Benchmarks/TSVC/Expansion-flt/Expansion-flt
Profile
|
-1.69% |
11.546 |
11.350 |
0.066 |
0.27% |
0.066 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint64_t>/51
|
-1.69% |
148.289 |
145.786 |
0.008 |
-1.70% |
0.008 |
|
External/SPEC/CFP2017rate/511.povray_r/511.povray_r
Profile
|
-1.66% |
33.911 |
33.348 |
0.092 |
-1.30% |
0.092 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<32, LessThanZero, Mid>
|
-1.66% |
4570.685 |
4494.941 |
12.524 |
-1.66% |
12.524 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_INT_PREDICT_RAW/171
|
-1.63% |
6.925 |
6.812 |
0.007 |
-1.63% |
0.007 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_INT_PREDICT_LAMBDA/171
|
-1.63% |
6.918 |
6.805 |
0.014 |
-1.74% |
0.014 |
|
MultiSource/Benchmarks/VersaBench/ecbdes/ecbdes
Profile
|
-1.62% |
5.141 |
5.058 |
0.001 |
-1.59% |
0.001 |
|
MultiSource/Benchmarks/ASC_Sequoia/CrystalMk/CrystalMk
Profile
|
-1.59% |
15.575 |
15.328 |
0.000 |
-1.57% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_csa_with_in_loop_arith_novec_int64_t_
|
-1.57% |
1028658.748 |
1012520.256 |
300.474 |
-1.52% |
300.474 |
|
SingleSource/Benchmarks/Misc/mandel-2
Profile
|
-1.53% |
2.535 |
2.496 |
0.000 |
-1.53% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint32_t>/10
|
-1.49% |
57.853 |
56.990 |
0.076 |
-0.10% |
0.076 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC128
|
-1.49% |
211.503 |
208.353 |
0.013 |
-1.50% |
0.013 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_ENERGY_CALC_LAMBDA/44217
|
-1.45% |
4304.631 |
4242.059 |
10.066 |
-1.90% |
10.066 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC63
|
-1.44% |
130.146 |
128.270 |
0.198 |
-1.46% |
0.198 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC127
|
-1.42% |
220.265 |
217.146 |
0.073 |
-1.42% |
0.073 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<6, LessThanZero, Mid>
|
-1.40% |
23853.484 |
23518.730 |
4.647 |
-0.20% |
4.647 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint32_t>/10
|
-1.37% |
46.948 |
46.305 |
0.029 |
0.00% |
0.029 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint64_t>/51
|
-1.35% |
229.002 |
225.901 |
0.006 |
-1.36% |
0.006 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C++/PENNANT/PENNANT
Profile
|
-1.35% |
4.802 |
4.738 |
0.017 |
-1.65% |
0.017 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_EOS_LAMBDA/44217
|
-1.33% |
273.064 |
269.421 |
0.941 |
-0.04% |
0.941 |
|
MultiSource/Benchmarks/TSVC/Searching-dbl/Searching-dbl
Profile
|
-1.32% |
7.647 |
7.546 |
0.031 |
-1.57% |
0.031 |
|
SingleSource/Benchmarks/Shootout-C++/Shootout-C++-heapsort
Profile
|
-1.31% |
22.301 |
22.008 |
0.113 |
0.04% |
0.113 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<3, EqZero, Mid>
|
-1.31% |
37656.164 |
37164.708 |
2.699 |
-1.15% |
2.699 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<16, GreaterThanZero, First>
|
-1.29% |
8580.901 |
8470.002 |
10.662 |
-0.31% |
10.662 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC127
|
-1.27% |
197.111 |
194.601 |
0.008 |
-1.27% |
0.008 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC128
|
-1.26% |
198.352 |
195.847 |
0.011 |
-1.27% |
0.011 |
|
MicroBenchmarks/ImageProcessing/Blur/blur.test:BENCHMARK_boxBlurKernel/512
|
-1.25% |
6614.923 |
6532.041 |
28.352 |
-1.23% |
28.352 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<8, LessThanZero, Mid>
|
-1.22% |
19468.758 |
19230.777 |
7.676 |
-1.05% |
7.676 |
|
External/SPEC/CINT2017rate/541.leela_r/541.leela_r
Profile
|
-1.22% |
228.471 |
225.688 |
0.405 |
-1.61% |
0.405 |
|
MultiSource/Benchmarks/Fhourstones-3.1/fhourstones3.1
Profile
|
-1.21% |
3.973 |
3.925 |
0.007 |
-1.17% |
0.007 |
|
MultiSource/Benchmarks/MallocBench/cfrac/cfrac
Profile
|
-1.18% |
2.778 |
2.745 |
0.001 |
-1.27% |
0.001 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, LessThanZero, Mid>
|
-1.14% |
31890.884 |
31526.899 |
79.796 |
-0.80% |
79.796 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_sinhf_novec_float_
|
-1.12% |
2242.300 |
2217.117 |
0.508 |
-1.10% |
0.508 |
|
SingleSource/Benchmarks/SmallPT/smallpt
Profile
|
-1.12% |
30.042 |
29.706 |
0.003 |
-1.08% |
0.003 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<16, LessThanZero, Last>
|
-1.11% |
13141.460 |
12996.236 |
24.798 |
-1.11% |
24.798 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_sinhf_autovec_float_
|
-1.10% |
2241.713 |
2217.031 |
0.294 |
-1.14% |
0.294 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_PLANCKIAN_RAW/44217
|
-1.09% |
4455.468 |
4406.718 |
16.227 |
0.22% |
16.227 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_csa_with_cond_arith_autovec_int64_t_
|
-1.05% |
744661.635 |
736808.645 |
260.692 |
-1.09% |
260.692 |
|
External/SPEC/CINT2017rate/525.x264_r/525.x264_r
Profile
|
-1.05% |
129.450 |
128.096 |
0.092 |
-1.04% |
0.092 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, LessThanZero, Mid>
|
-1.04% |
56359.949 |
55772.450 |
12.870 |
-1.34% |
12.870 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<31, EqZero, None>
|
-1.04% |
8012.132 |
7929.173 |
25.167 |
-0.82% |
25.167 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, LessThanZero, Last>
|
-1.03% |
56376.028 |
55793.784 |
20.074 |
-0.45% |
20.074 |
|
MicroBenchmarks/Builtins/Int128/Builtins.test:BM_RemainderIntrinsic128UniformDivisor<__int128_t>
|
-1.03% |
66.741 |
66.054 |
0.247 |
-0.27% |
0.247 |
|
MicroBenchmarks/Builtins/Int128/Builtins.test:BM_RemainderIntrinsic128UniformDivisor<__uint128_t>
|
-1.03% |
55.743 |
55.170 |
0.086 |
-1.03% |
0.086 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_sinh_novec_double_
|
-1.00% |
2469.998 |
2445.247 |
0.353 |
-1.16% |
0.353 |