|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_HYDRO_2D_LAMBDA/44217
|
-53.17% |
88865.479 |
41616.385 |
11036.510 |
-54.23% |
11036.510 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint64_t_To_uint32_t_
|
-51.02% |
35246.326 |
17264.228 |
335.091 |
-51.11% |
335.091 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint64_t_To_uint16_t_
|
-50.45% |
35792.213 |
17734.428 |
448.060 |
-50.30% |
448.060 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C/miniGMG/miniGMG
Profile
|
-49.75% |
9.187 |
4.616 |
0.465 |
-49.77% |
0.465 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_HYDRO_2D_LAMBDA/5001
|
-49.40% |
9272.607 |
4691.776 |
1147.696 |
-48.52% |
1147.696 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint64_t_To_uint8_t_
|
-48.68% |
37027.647 |
19003.005 |
75.412 |
-48.73% |
75.412 |
|
SingleSource/Benchmarks/Polybench/stencils/seidel-2d/seidel-2d
Profile
|
-47.44% |
230.508 |
121.148 |
0.252 |
0.05% |
0.252 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_DIFF_PREDICT_RAW/44217
|
-44.87% |
24439.711 |
13472.551 |
357.008 |
-42.18% |
357.008 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint16_t_To_uint64_t_
|
-43.99% |
18639.654 |
10440.708 |
4.856 |
-44.09% |
4.856 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_DIFF_PREDICT_LAMBDA/44217
|
-41.67% |
23106.077 |
13477.232 |
352.575 |
-41.66% |
352.575 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_DISC_ORD_LAMBDA/44217
|
-41.47% |
14169.502 |
8293.966 |
1752.902 |
-40.99% |
1752.902 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint8_t_To_uint64_t_
|
-41.30% |
17859.080 |
10483.606 |
35.600 |
-41.10% |
35.600 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_DIFF_PREDICT_LAMBDA/5001
|
-41.03% |
2559.975 |
1509.570 |
45.297 |
-39.84% |
45.297 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint64_t_To_uint32_t_
|
-40.80% |
38275.289 |
22658.414 |
28.602 |
-40.62% |
28.602 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_DIFF_PREDICT_RAW/5001
|
-40.19% |
2532.671 |
1514.769 |
62.019 |
-41.17% |
62.019 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIRST_DIFF_RAW/44217
|
-39.11% |
167.129 |
101.761 |
1.027 |
-28.58% |
1.027 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/32
|
-36.70% |
1396.194 |
883.842 |
0.061 |
-36.69% |
0.061 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/64
|
-36.67% |
6181.751 |
3915.067 |
0.075 |
-36.67% |
0.075 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/16
|
-36.64% |
279.503 |
177.082 |
0.024 |
-36.64% |
0.024 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/256
|
-36.22% |
107099.327 |
68311.946 |
58.852 |
-36.25% |
58.852 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/128
|
-36.10% |
26265.460 |
16782.716 |
2.314 |
-36.12% |
2.314 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint32_t_To_uint64_t_
|
-35.92% |
22572.826 |
14463.942 |
257.978 |
-36.35% |
257.978 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint64_t_To_uint8_t_
|
-34.42% |
30186.058 |
19797.347 |
22.032 |
-34.25% |
22.032 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint64_t_To_uint16_t_
|
-34.04% |
28935.744 |
19085.514 |
24.943 |
-34.07% |
24.943 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIRST_DIFF_LAMBDA/44217
|
-33.04% |
153.367 |
102.699 |
0.320 |
-29.09% |
0.320 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, EqZero, None>
|
-31.24% |
20511.532 |
14103.749 |
0.626 |
-31.24% |
0.626 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint64_t_To_uint16_t_
|
-29.03% |
25914.085 |
18392.225 |
73.091 |
-28.98% |
73.091 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_INT_PREDICT_RAW/44217
|
-28.65% |
11156.553 |
7960.583 |
117.586 |
-12.03% |
117.586 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_HYDRO_2D_RAW/44217
|
-28.22% |
70002.829 |
50245.883 |
4154.414 |
-40.64% |
4154.414 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint32_t_To_uint8_t_
|
-28.03% |
13507.676 |
9720.885 |
21.582 |
-27.83% |
21.582 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC128
|
-27.44% |
1293.880 |
938.867 |
3.229 |
-27.38% |
3.229 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC64
|
-27.03% |
654.263 |
477.427 |
2.422 |
-26.96% |
2.422 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC128
|
-27.01% |
558.653 |
407.779 |
0.030 |
-26.86% |
0.030 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC32
|
-26.84% |
334.562 |
244.770 |
1.136 |
-26.70% |
1.136 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_PIC_2D_RAW/44217
|
-26.70% |
11802.951 |
8651.881 |
43.925 |
-22.86% |
43.925 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC16
|
-26.37% |
174.401 |
128.413 |
0.500 |
-26.11% |
0.500 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_HYDRO_2D_RAW/5001
|
-25.98% |
7633.646 |
5650.119 |
363.778 |
-35.77% |
363.778 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC64
|
-25.65% |
292.096 |
217.179 |
0.052 |
-25.58% |
0.052 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint64_t_To_uint8_t_
|
-24.57% |
27258.384 |
20561.615 |
5.183 |
-24.47% |
5.183 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, EqZero, None>
|
-23.99% |
16024.376 |
12180.902 |
0.899 |
-23.98% |
0.899 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIRST_SUM_RAW/44217
|
-23.81% |
177.435 |
135.188 |
1.107 |
-18.73% |
1.107 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_PIC_2D_RAW/5001
|
-23.39% |
1187.796 |
909.954 |
36.619 |
-15.62% |
36.619 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_PIC_2D_LAMBDA/44217
|
-23.20% |
11202.662 |
8603.722 |
576.171 |
-21.52% |
576.171 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC128
|
-23.20% |
603.901 |
463.823 |
0.032 |
-23.20% |
0.032 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC32
|
-23.14% |
158.793 |
122.042 |
0.040 |
-23.18% |
0.040 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC128
|
-23.10% |
603.915 |
464.385 |
0.034 |
-23.11% |
0.034 |
|
MicroBenchmarks/ImageProcessing/Blur/blur.test:BENCHMARK_boxBlurKernel/1024
|
-22.70% |
30084.147 |
23256.144 |
17.371 |
-22.86% |
17.371 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC64
|
-22.36% |
313.514 |
243.420 |
0.015 |
-22.36% |
0.015 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC127
|
-22.17% |
615.182 |
478.806 |
0.021 |
-22.17% |
0.021 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC64
|
-22.15% |
313.508 |
244.051 |
0.011 |
-22.15% |
0.011 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC127
|
-21.98% |
615.246 |
480.015 |
0.044 |
-21.97% |
0.044 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint16_t_To_uint32_t_
|
-21.82% |
7116.911 |
5564.060 |
4.845 |
-21.64% |
4.845 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint16_t_To_uint64_t_
|
-21.79% |
13244.797 |
10359.299 |
3.446 |
-21.57% |
3.446 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint8_t_To_uint32_t_
|
-21.63% |
6587.215 |
5162.291 |
3.487 |
-21.57% |
3.487 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_only_autovec_uint8_t_
|
-21.39% |
182395.230 |
143375.213 |
91.975 |
-21.37% |
91.975 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIND_FIRST_MIN_LAMBDA/171
|
-21.29% |
1.501 |
1.181 |
0.000 |
-21.28% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIND_FIRST_MIN_LAMBDA/44217
|
-21.23% |
389.133 |
306.506 |
0.237 |
-21.32% |
0.237 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC64
|
-20.96% |
151.010 |
119.353 |
0.785 |
-19.70% |
0.785 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIND_FIRST_MIN_LAMBDA/5001
|
-20.93% |
45.234 |
35.767 |
0.036 |
-20.97% |
0.036 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC32
|
-20.82% |
168.327 |
133.278 |
0.008 |
-20.82% |
0.008 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_INT_PREDICT_LAMBDA/5001
|
-20.73% |
1103.934 |
875.041 |
19.164 |
-3.28% |
19.164 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIRST_SUM_LAMBDA/44217
|
-20.53% |
170.663 |
135.633 |
0.917 |
-18.82% |
0.917 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC32
|
-20.45% |
168.334 |
133.907 |
0.004 |
-20.45% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC63
|
-20.43% |
324.805 |
258.459 |
0.001 |
-20.42% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC128
|
-20.37% |
274.396 |
218.493 |
0.643 |
-20.47% |
0.643 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC127
|
-20.21% |
274.145 |
218.733 |
0.413 |
-20.59% |
0.413 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint32_t_To_uint8_t_
|
-20.10% |
13947.476 |
11144.192 |
105.304 |
-19.83% |
105.304 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC63
|
-20.04% |
324.754 |
259.685 |
0.027 |
-20.05% |
0.027 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC127
|
-19.69% |
641.009 |
514.819 |
0.058 |
-19.62% |
0.058 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint32_t_To_uint16_t_
|
-19.63% |
10565.558 |
8491.602 |
748.996 |
-14.27% |
748.996 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC16
|
-19.31% |
92.288 |
74.469 |
0.008 |
-19.30% |
0.008 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint16_t_To_uint8_t_
|
-19.11% |
3818.808 |
3089.209 |
0.086 |
-19.09% |
0.086 |
|
MultiSource/Benchmarks/MiBench/automotive-bitcount/automotive-bitcount
Profile
|
-19.07% |
0.125 |
0.101 |
0.000 |
-18.28% |
0.000 |
|
SingleSource/Benchmarks/Adobe-C++/loop_unroll
Profile
|
-18.91% |
2.981 |
2.418 |
0.004 |
-22.19% |
0.004 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_VOL3D_CALC_RAW/2
|
-18.80% |
8.758 |
7.111 |
0.000 |
-18.79% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_VOL3D_CALC_LAMBDA/2
|
-18.80% |
8.757 |
7.111 |
0.000 |
-18.80% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint32_t_To_uint16_t_
|
-18.47% |
13803.403 |
11253.990 |
3.532 |
-18.49% |
3.532 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint64_t_To_uint32_t_
|
-18.38% |
27088.581 |
22108.986 |
13.744 |
-18.27% |
13.744 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC16
|
-18.30% |
95.744 |
78.221 |
0.000 |
-18.30% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC63
|
-18.28% |
150.561 |
123.033 |
1.504 |
-17.93% |
1.504 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_PIC_1D_RAW/44217
|
-18.26% |
13464.660 |
11005.737 |
34.699 |
-18.65% |
34.699 |
|
MultiSource/Benchmarks/Trimaran/enc-pc1/enc-pc1
Profile
|
-18.13% |
1.105 |
0.904 |
0.000 |
-18.11% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC31
|
-18.11% |
87.110 |
71.335 |
2.059 |
-17.16% |
2.059 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_with_cond_arith_novec_uint8_t_
|
-17.96% |
746578.264 |
612521.013 |
341.461 |
-17.87% |
341.461 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint8_t_To_uint64_t_
|
-17.86% |
13275.726 |
10904.831 |
23.494 |
-16.53% |
23.494 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC16
|
-17.65% |
95.745 |
78.843 |
0.002 |
-17.65% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_with_cond_arith_novec_int32_t_
|
-17.55% |
740923.740 |
610886.236 |
366.871 |
-17.47% |
366.871 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC31
|
-17.42% |
179.596 |
148.313 |
0.004 |
-17.41% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC4
|
-17.32% |
17.520 |
14.485 |
0.010 |
-17.32% |
0.010 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC128
|
-17.25% |
570.701 |
472.230 |
0.025 |
-17.24% |
0.025 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC64
|
-17.12% |
297.866 |
246.869 |
0.018 |
-17.08% |
0.018 |
|
MultiSource/Benchmarks/MiBench/security-rijndael/security-rijndael
Profile
|
-16.97% |
0.335 |
0.278 |
0.000 |
-16.91% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_PIC_2D_LAMBDA/5001
|
-16.93% |
1063.512 |
883.412 |
38.378 |
-20.09% |
38.378 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC32
|
-16.86% |
161.449 |
134.224 |
0.013 |
-16.83% |
0.013 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC31
|
-16.72% |
179.593 |
149.559 |
0.004 |
-16.72% |
0.004 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_VOL3D_CALC_LAMBDA/0
|
-16.64% |
1267.043 |
1056.147 |
4.194 |
-16.68% |
4.194 |
|
MicroBenchmarks/ImageProcessing/Dilate/Dilate.test:BENCHMARK_DILATE/1024
|
-16.58% |
7450.028 |
6214.458 |
228.645 |
-12.60% |
228.645 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC16
|
-16.45% |
93.233 |
77.892 |
0.025 |
-16.36% |
0.025 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC32
|
-16.41% |
85.487 |
71.459 |
0.775 |
-16.25% |
0.775 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_HYDRO_1D_RAW/171
|
-16.39% |
0.445 |
0.372 |
0.000 |
-15.83% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_HYDRO_1D_LAMBDA/171
|
-16.24% |
0.444 |
0.372 |
0.000 |
-15.87% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_VOL3D_CALC_RAW/0
|
-16.24% |
1269.446 |
1063.328 |
1.378 |
-15.96% |
1.378 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_VOL3D_CALC_LAMBDA/1
|
-16.19% |
260.165 |
218.052 |
0.250 |
-16.19% |
0.250 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_VOL3D_CALC_RAW/1
|
-16.13% |
260.097 |
218.143 |
0.223 |
-16.14% |
0.223 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint16_t_To_uint32_t_
|
-15.71% |
7463.534 |
6290.848 |
1.983 |
-15.70% |
1.983 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC8
|
-15.43% |
58.820 |
49.745 |
0.002 |
-15.35% |
0.002 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, EqZero, First>
|
-15.39% |
16670.038 |
14104.070 |
0.240 |
-15.40% |
0.240 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_no_runtime_checks_needed<16, int>
|
-15.39% |
24.403 |
20.648 |
0.000 |
-15.39% |
0.000 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, EqZero, Mid>
|
-15.38% |
16666.942 |
14103.436 |
0.715 |
-15.38% |
0.715 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, EqZero, Last>
|
-15.35% |
16667.741 |
14109.470 |
0.432 |
-15.35% |
0.432 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint32_t_To_uint8_t_
|
-14.92% |
10638.847 |
9051.140 |
37.914 |
-14.57% |
37.914 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC127
|
-14.82% |
605.837 |
516.046 |
0.015 |
-14.81% |
0.015 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC8
|
-14.74% |
59.443 |
50.682 |
0.004 |
-14.75% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint8_t_To_uint16_t_
|
-14.63% |
3757.145 |
3207.454 |
13.252 |
-14.62% |
13.252 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC128
|
-14.57% |
1103.385 |
942.648 |
0.027 |
-14.56% |
0.027 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC127
|
-14.54% |
1095.639 |
936.327 |
0.050 |
-14.51% |
0.050 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_DISC_ORD_RAW/44217
|
-14.52% |
11715.050 |
10013.585 |
651.278 |
-24.94% |
651.278 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_INT_PREDICT_LAMBDA/44217
|
-14.37% |
9323.917 |
7984.098 |
92.625 |
-4.24% |
92.625 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC64
|
-14.35% |
562.524 |
481.827 |
0.025 |
-14.31% |
0.025 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC63
|
-14.26% |
554.657 |
475.586 |
0.021 |
-14.27% |
0.021 |
|
SingleSource/Benchmarks/Misc/salsa20
Profile
|
-14.14% |
15.387 |
13.211 |
0.001 |
-14.12% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_with_cond_arith_novec_int64_t_
|
-14.08% |
793070.939 |
681377.440 |
928.378 |
-13.53% |
928.378 |
|
External/SPEC/CFP2017rate/508.namd_r/508.namd_r
Profile
|
-13.96% |
224.272 |
192.960 |
1.603 |
-13.69% |
1.603 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_with_cond_arith_autovec_int64_t_
|
-13.94% |
792316.285 |
681901.312 |
154.779 |
-13.86% |
154.779 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC32
|
-13.92% |
292.249 |
251.557 |
0.009 |
-13.85% |
0.009 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC8
|
-13.91% |
23.153 |
19.931 |
0.042 |
-13.91% |
0.042 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint64_t_To_uint8_t_
|
-13.91% |
22080.923 |
19008.947 |
28.569 |
-13.78% |
28.569 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC3
|
-13.86% |
51.938 |
44.737 |
0.004 |
-13.86% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC8
|
-13.86% |
51.939 |
44.739 |
0.003 |
-13.86% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC1
|
-13.86% |
51.936 |
44.738 |
0.004 |
-13.86% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC4
|
-13.86% |
51.936 |
44.740 |
0.001 |
-13.85% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC2
|
-13.85% |
51.936 |
44.741 |
0.004 |
-13.85% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC7
|
-13.85% |
51.934 |
44.740 |
0.001 |
-13.85% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC8
|
-13.68% |
59.444 |
51.310 |
0.003 |
-13.69% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC31
|
-13.67% |
284.143 |
245.301 |
0.018 |
-13.65% |
0.018 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, EqZero, Last>
|
-13.63% |
14104.255 |
12181.632 |
0.428 |
-13.64% |
0.428 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, EqZero, First>
|
-13.63% |
14103.023 |
12181.474 |
0.967 |
-13.63% |
0.967 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, EqZero, Mid>
|
-13.62% |
14103.566 |
12182.115 |
0.965 |
-13.62% |
0.965 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint32_t_To_uint16_t_
|
-13.61% |
12879.645 |
11126.376 |
17.867 |
-13.33% |
17.867 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint32_t_To_uint8_t_
|
-13.49% |
11038.829 |
9549.454 |
80.074 |
-14.20% |
80.074 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC63
|
-13.43% |
374.518 |
324.204 |
0.207 |
-13.41% |
0.207 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC8
|
-13.16% |
23.779 |
20.649 |
0.001 |
-13.16% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC16
|
-13.15% |
157.066 |
136.409 |
0.004 |
-13.10% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC128
|
-13.08% |
81.350 |
70.709 |
0.005 |
-13.07% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint8_t_To_uint16_t_
|
-12.97% |
4542.335 |
3953.336 |
0.571 |
-12.96% |
0.571 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC16
|
-12.95% |
51.941 |
45.217 |
0.320 |
-12.95% |
0.320 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC15
|
-12.87% |
107.007 |
93.234 |
0.004 |
-12.87% |
0.004 |
|
MicroBenchmarks/ImageProcessing/Dilate/Dilate.test:BENCHMARK_DILATE/128
|
-12.84% |
229.004 |
199.593 |
7.310 |
-12.45% |
7.310 |
|
SingleSource/Benchmarks/Shootout-C++/Shootout-C++-matrix
Profile
|
-12.74% |
2.509 |
2.189 |
0.000 |
-12.72% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_HYDRO_1D_LAMBDA/5001
|
-12.72% |
19.128 |
16.695 |
0.256 |
-2.78% |
0.256 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC63
|
-12.69% |
332.935 |
290.671 |
0.017 |
-12.67% |
0.017 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC15
|
-12.61% |
148.926 |
130.149 |
0.005 |
-12.54% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint16_t_To_uint8_t_
|
-12.41% |
4743.110 |
4154.566 |
0.708 |
-12.40% |
0.708 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIRST_SUM_RAW/5001
|
-12.36% |
20.590 |
18.044 |
0.246 |
4.03% |
0.246 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC4
|
-12.00% |
112.093 |
98.640 |
1.764 |
-12.78% |
1.764 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC8
|
-11.89% |
89.479 |
78.842 |
0.002 |
-11.81% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC2
|
-11.76% |
21.274 |
18.772 |
0.001 |
-11.77% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC15
|
-11.69% |
107.000 |
94.488 |
0.003 |
-11.70% |
0.003 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_HYDRO_1D_RAW/5001
|
-11.63% |
17.233 |
15.229 |
0.498 |
-8.73% |
0.498 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC15
|
-11.45% |
51.936 |
45.989 |
0.002 |
-11.46% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC16
|
-11.36% |
33.164 |
29.397 |
0.005 |
-11.36% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC4
|
-11.12% |
22.527 |
20.022 |
0.001 |
-11.12% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC4
|
-11.11% |
22.526 |
20.023 |
0.001 |
-11.12% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC3
|
-11.11% |
22.525 |
20.022 |
0.000 |
-11.12% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint8_t>/51
|
-10.86% |
123.896 |
110.443 |
0.073 |
19.39% |
0.073 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC7
|
-10.77% |
81.347 |
72.584 |
0.003 |
-10.73% |
0.003 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_BAND_LIN_EQ_LAMBDA/171
|
-10.61% |
0.384 |
0.343 |
0.000 |
-6.33% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_BAND_LIN_EQ_RAW/171
|
-10.61% |
0.384 |
0.343 |
0.000 |
-6.33% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC4
|
-10.60% |
41.296 |
36.919 |
0.000 |
-10.61% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC7
|
-10.55% |
29.004 |
25.944 |
1.076 |
-9.48% |
1.076 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC4
|
-10.53% |
23.779 |
21.274 |
0.001 |
-10.53% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC64
|
-10.48% |
53.817 |
48.179 |
0.002 |
-10.48% |
0.002 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/16
|
-10.19% |
115.462 |
103.702 |
0.016 |
-10.19% |
0.016 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint32_t_To_uint16_t_
|
-10.18% |
10771.128 |
9675.096 |
168.250 |
-9.89% |
168.250 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint8_t_To_uint16_t_
|
-10.12% |
5846.955 |
5255.384 |
6.086 |
-10.17% |
6.086 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC4
|
-10.11% |
55.691 |
50.063 |
0.001 |
-10.06% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC8
|
-10.09% |
27.144 |
24.404 |
0.001 |
-9.32% |
0.001 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/64
|
-10.01% |
1912.802 |
1721.350 |
1.226 |
-10.03% |
1.226 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/32
|
-9.99% |
473.033 |
425.789 |
0.004 |
-9.98% |
0.004 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/256
|
-9.86% |
31441.424 |
28340.173 |
15.721 |
-9.89% |
15.721 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC127
|
-9.79% |
101.971 |
91.985 |
0.003 |
-9.71% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC8
|
-9.76% |
25.657 |
23.152 |
0.001 |
-9.76% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC8
|
-9.76% |
25.657 |
23.152 |
0.002 |
-9.76% |
0.002 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_DIFF_PREDICT_RAW/171
|
-9.71% |
12.302 |
11.107 |
0.063 |
-6.92% |
0.063 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/128
|
-9.71% |
7913.452 |
7145.049 |
1.310 |
-9.75% |
1.310 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC32
|
-9.67% |
53.186 |
48.043 |
0.063 |
-9.68% |
0.063 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_only_autovec_int64_t_
|
-9.63% |
332665.675 |
300635.469 |
561.627 |
-9.80% |
561.627 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC7
|
-9.61% |
32.537 |
29.411 |
0.000 |
-9.61% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC7
|
-9.52% |
26.279 |
23.777 |
0.002 |
-9.53% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC7
|
-9.52% |
26.280 |
23.778 |
0.001 |
-9.53% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_DISC_ORD_LAMBDA/5001
|
-9.43% |
639.711 |
579.397 |
14.318 |
-9.09% |
14.318 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC31
|
-9.39% |
196.488 |
178.035 |
0.003 |
-9.38% |
0.003 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_DEL_DOT_VEC_2D_LAMBDA/1
|
-9.29% |
287.289 |
260.596 |
0.098 |
-9.24% |
0.098 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_DEL_DOT_VEC_2D_RAW/1
|
-9.20% |
287.133 |
260.719 |
0.059 |
-9.15% |
0.059 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC4
|
-9.08% |
41.296 |
37.546 |
0.001 |
-9.09% |
0.001 |
|
MultiSource/Benchmarks/FreeBench/pifft/pifft
Profile
|
-8.89% |
0.359 |
0.327 |
0.001 |
-8.83% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC7
|
-8.89% |
28.158 |
25.655 |
0.001 |
-8.90% |
0.001 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_runtime_checks_pass<4, int>
|
-8.89% |
16.825 |
15.329 |
0.000 |
-8.25% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_DEL_DOT_VEC_2D_RAW/2
|
-8.71% |
3.510 |
3.204 |
0.001 |
-8.71% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_DEL_DOT_VEC_2D_LAMBDA/2
|
-8.70% |
3.510 |
3.204 |
0.000 |
-8.69% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC16
|
-8.62% |
36.293 |
33.165 |
0.001 |
-8.62% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint16_t_To_uint8_t_
|
-8.52% |
6809.945 |
6229.622 |
3.909 |
-8.60% |
3.909 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC8
|
-8.52% |
29.411 |
26.905 |
0.001 |
-8.52% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint16_t_To_uint64_t_
|
-8.44% |
20339.252 |
18623.022 |
66.973 |
-7.55% |
66.973 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint8_t_To_uint32_t_
|
-8.37% |
12804.180 |
11732.848 |
27.290 |
-8.18% |
27.290 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC2
|
-8.19% |
38.170 |
35.043 |
0.001 |
-8.19% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint8_t>/28
|
-8.11% |
82.605 |
75.910 |
0.225 |
12.31% |
0.225 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC64
|
-8.05% |
93.231 |
85.726 |
0.001 |
-8.06% |
0.001 |
|
MultiSource/Benchmarks/McCat/12-IOtest/iotest
Profile
|
-8.01% |
1.833 |
1.686 |
0.021 |
-7.60% |
0.021 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC3
|
-7.89% |
47.554 |
43.803 |
0.000 |
-7.90% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC16
|
-7.84% |
31.912 |
29.410 |
0.001 |
-7.84% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC16
|
-7.84% |
31.912 |
29.410 |
0.001 |
-7.84% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC32
|
-7.81% |
40.046 |
36.918 |
0.001 |
-7.82% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_DEL_DOT_VEC_2D_LAMBDA/0
|
-7.74% |
1795.007 |
1656.029 |
6.197 |
-7.59% |
6.197 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC15
|
-7.70% |
32.540 |
30.035 |
0.001 |
-7.69% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC15
|
-7.69% |
32.538 |
30.036 |
0.001 |
-7.69% |
0.001 |
|
MultiSource/Benchmarks/VersaBench/beamformer/beamformer
Profile
|
-7.61% |
5.200 |
4.804 |
0.001 |
-7.63% |
0.001 |
|
MultiSource/Benchmarks/Trimaran/enc-md5/enc-md5
Profile
|
-7.53% |
3.507 |
3.243 |
0.000 |
-7.48% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint32_t_To_uint64_t_
|
-7.49% |
17092.447 |
15811.446 |
251.588 |
-8.05% |
251.588 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_xor_no_runtime_checks_needed<16, int>
|
-7.41% |
16.895 |
15.643 |
0.002 |
-7.42% |
0.002 |
|
MultiSource/Applications/lambda-0.1.3/lambda
Profile
|
-7.27% |
15.874 |
14.721 |
0.003 |
-7.24% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC128
|
-7.23% |
173.345 |
160.812 |
0.012 |
-7.22% |
0.012 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIND_FIRST_MIN_RAW/171
|
-7.23% |
1.497 |
1.389 |
0.000 |
-7.19% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint8_t>/127
|
-7.22% |
138.922 |
128.896 |
0.012 |
-7.21% |
0.012 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_HYDRO_2D_RAW/171
|
-7.20% |
88.574 |
82.198 |
0.269 |
-7.25% |
0.269 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_DEL_DOT_VEC_2D_RAW/0
|
-7.18% |
1791.896 |
1663.195 |
1.180 |
-7.64% |
1.180 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_HYDRO_2D_LAMBDA/171
|
-7.11% |
88.160 |
81.890 |
0.374 |
-7.63% |
0.374 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint16_t_To_uint64_t_
|
-7.09% |
25100.903 |
23322.220 |
30.517 |
-6.66% |
30.517 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC7
|
-7.08% |
70.710 |
65.703 |
0.002 |
-7.08% |
0.002 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_DIFF_PREDICT_LAMBDA/171
|
-7.05% |
11.953 |
11.110 |
0.064 |
-7.30% |
0.064 |
|
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 |
41.923 |
0.016 |
-6.94% |
0.016 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC15
|
-6.90% |
54.443 |
50.685 |
0.002 |
-6.90% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC31
|
-6.72% |
74.461 |
69.456 |
0.002 |
-6.73% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_only_autovec_int32_t_
|
-6.60% |
181271.654 |
169307.845 |
193.854 |
-6.52% |
193.854 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC63
|
-6.56% |
114.516 |
106.999 |
0.160 |
-6.56% |
0.160 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_xor_runtime_checks_fail<16, int>
|
-6.52% |
28.783 |
26.907 |
0.003 |
-6.52% |
0.003 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_xor_runtime_checks_pass<16, int>
|
-6.51% |
28.782 |
26.909 |
0.001 |
-6.51% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC127
|
-6.46% |
68.827 |
64.383 |
0.030 |
-5.72% |
0.030 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC128
|
-6.41% |
68.829 |
64.420 |
0.014 |
-6.37% |
0.014 |
|
SingleSource/Benchmarks/Misc/flops-6
Profile
|
-6.40% |
1.311 |
1.227 |
0.000 |
-6.49% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC15
|
-6.35% |
39.420 |
36.919 |
0.001 |
-6.35% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint16_t>/127
|
-6.31% |
138.909 |
130.145 |
0.006 |
-6.31% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC63
|
-6.26% |
74.096 |
69.458 |
0.001 |
-6.42% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIND_FIRST_MIN_RAW/5001
|
-6.26% |
45.314 |
42.478 |
0.047 |
-6.31% |
0.047 |
|
SingleSource/Benchmarks/Misc-C++/Large/sphereflake
Profile
|
-6.25% |
20.014 |
18.764 |
0.004 |
-6.19% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint32_t_To_uint64_t_
|
-6.21% |
21557.973 |
20219.328 |
113.558 |
-5.74% |
113.558 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC127
|
-6.20% |
194.617 |
182.545 |
0.132 |
-6.20% |
0.132 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_BAND_LIN_EQ_LAMBDA/5001
|
-6.18% |
21.431 |
20.106 |
0.058 |
-3.33% |
0.058 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC16
|
-6.15% |
40.671 |
38.168 |
0.001 |
-6.16% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_BAND_LIN_EQ_RAW/5001
|
-6.10% |
21.547 |
20.232 |
0.301 |
-1.89% |
0.301 |
|
MultiSource/Benchmarks/Rodinia/hotspot/hotspot
Profile
|
-6.04% |
2.035 |
1.912 |
0.009 |
-6.07% |
0.009 |
|
External/SPEC/CFP2017rate/538.imagick_r/538.imagick_r
Profile
|
-5.97% |
292.828 |
275.334 |
0.324 |
-5.73% |
0.324 |
|
MultiSource/Benchmarks/MiBench/telecomm-gsm/telecomm-gsm
Profile
|
-5.95% |
0.663 |
0.623 |
0.000 |
-6.03% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint8_t>/65
|
-5.92% |
95.112 |
89.480 |
0.005 |
-5.92% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint32_t>/127
|
-5.87% |
138.276 |
130.154 |
0.011 |
-5.88% |
0.011 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC16
|
-5.67% |
31.842 |
30.035 |
0.002 |
-4.01% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC16
|
-5.66% |
33.162 |
31.287 |
0.003 |
-5.66% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC32
|
-5.64% |
44.429 |
41.922 |
0.002 |
-5.64% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC32
|
-5.63% |
44.430 |
41.927 |
0.002 |
-5.63% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC31
|
-5.58% |
45.065 |
42.549 |
0.002 |
-5.58% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC31
|
-5.55% |
45.054 |
42.552 |
0.005 |
-5.55% |
0.005 |
|
MultiSource/Benchmarks/SciMark2-C/scimark2
Profile
|
-5.54% |
107.686 |
101.724 |
0.010 |
-5.50% |
0.010 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint8_t_To_uint16_t_
|
-5.48% |
3630.226 |
3431.220 |
6.328 |
-5.56% |
6.328 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C++/miniFE/miniFE
Profile
|
-5.48% |
15.806 |
14.940 |
0.119 |
-6.44% |
0.119 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIND_FIRST_MIN_RAW/44217
|
-5.39% |
389.538 |
368.531 |
0.131 |
-5.40% |
0.131 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint32_t>/999
|
-5.39% |
696.493 |
658.965 |
0.025 |
-5.39% |
0.025 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC7
|
-5.31% |
70.712 |
66.956 |
0.001 |
-5.32% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopWithReductionTC1
|
-5.27% |
11.889 |
11.263 |
0.000 |
-5.26% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint32_t>/999
|
-5.23% |
1365.038 |
1293.671 |
0.055 |
-5.23% |
0.055 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_PIC_2D_LAMBDA/171
|
-5.20% |
13.482 |
12.780 |
0.051 |
-5.32% |
0.051 |
|
SingleSource/Benchmarks/Stanford/Puzzle
Profile
|
-5.16% |
0.241 |
0.229 |
0.005 |
-5.17% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC32
|
-5.15% |
61.320 |
58.164 |
0.015 |
-5.15% |
0.015 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC32
|
-5.13% |
24.405 |
23.152 |
0.001 |
-5.13% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC31
|
-5.13% |
24.405 |
23.152 |
0.001 |
-5.13% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC31
|
-5.13% |
24.404 |
23.152 |
0.000 |
-5.13% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC32
|
-5.13% |
24.404 |
23.153 |
0.002 |
-5.12% |
0.002 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_PRESSURE_CALC_RAW/44217
|
-5.13% |
504.117 |
478.276 |
4.692 |
-4.76% |
4.692 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC15
|
-5.12% |
128.275 |
121.708 |
0.002 |
-5.11% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC31
|
-5.07% |
241.260 |
229.036 |
0.059 |
-5.05% |
0.059 |
|
SingleSource/Benchmarks/Misc/oourafft
Profile
|
-5.02% |
15.425 |
14.649 |
0.085 |
-2.94% |
0.085 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_PIC_2D_RAW/171
|
-4.87% |
13.520 |
12.862 |
0.042 |
-5.00% |
0.042 |
|
MicroBenchmarks/harris/harris.test:BENCHMARK_HARRIS/2048/2048
|
-4.86% |
166034.239 |
157960.008 |
2829.548 |
-5.43% |
2829.548 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC64
|
-4.86% |
43.710 |
41.587 |
0.058 |
-3.68% |
0.058 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint32_t>/256
|
-4.81% |
364.163 |
346.639 |
0.033 |
-4.81% |
0.033 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint8_t>/16
|
-4.81% |
59.885 |
57.006 |
0.449 |
5.92% |
0.449 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC7
|
-4.76% |
349.608 |
332.975 |
3.232 |
-6.13% |
3.232 |
|
SingleSource/Benchmarks/Misc/revertBits
Profile
|
-4.66% |
0.641 |
0.611 |
0.000 |
-4.68% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC15
|
-4.64% |
44.784 |
42.704 |
0.450 |
-3.89% |
0.450 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint16_t>/65
|
-4.61% |
95.117 |
90.728 |
0.010 |
-4.61% |
0.010 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_runtime_checks_fail<16, int>
|
-4.60% |
54.438 |
51.935 |
0.002 |
-4.60% |
0.002 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_runtime_checks_pass<16, int>
|
-4.58% |
54.434 |
51.939 |
0.000 |
-4.59% |
0.000 |
|
SingleSource/Benchmarks/Polybench/stencils/jacobi-2d/jacobi-2d
Profile
|
-4.54% |
31.967 |
30.514 |
0.028 |
-5.31% |
0.028 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopWithReductionTC2
|
-4.52% |
13.767 |
13.144 |
0.003 |
-4.52% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC31
|
-4.47% |
70.084 |
66.950 |
0.004 |
-4.47% |
0.004 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<32, EqZero, Last>
|
-4.37% |
7126.261 |
6814.958 |
69.309 |
-3.38% |
69.309 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC8
|
-4.36% |
14.392 |
13.766 |
0.001 |
-4.36% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC2
|
-4.35% |
14.392 |
13.766 |
0.000 |
-4.35% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC4
|
-4.35% |
14.392 |
13.766 |
0.000 |
-4.36% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC15
|
-4.35% |
14.392 |
13.765 |
0.001 |
-4.36% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC7
|
-4.35% |
14.392 |
13.766 |
0.002 |
-4.35% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC1
|
-4.35% |
14.394 |
13.768 |
0.001 |
-4.34% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC1
|
-4.35% |
14.392 |
13.766 |
0.000 |
-4.34% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC16
|
-4.35% |
14.392 |
13.766 |
0.001 |
-4.35% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC3
|
-4.35% |
14.392 |
13.766 |
0.001 |
-4.36% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC2
|
-4.35% |
14.392 |
13.766 |
0.000 |
-4.34% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC3
|
-4.35% |
14.391 |
13.766 |
0.000 |
-4.35% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC15
|
-4.35% |
14.392 |
13.767 |
0.001 |
-4.35% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC8
|
-4.35% |
14.391 |
13.766 |
0.001 |
-4.36% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC7
|
-4.34% |
14.392 |
13.766 |
0.001 |
-4.34% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC4
|
-4.34% |
14.391 |
13.766 |
0.000 |
-4.35% |
0.000 |
|
MicroBenchmarks/ImageProcessing/Dilate/Dilate.test:BENCHMARK_DILATE/256
|
-4.31% |
1061.946 |
1016.181 |
1.754 |
-4.79% |
1.754 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_nested_cond_load_novec_int32_t_
|
-4.30% |
650220.385 |
622239.377 |
326.742 |
-3.55% |
326.742 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint64_t>/999
|
-4.30% |
1811.585 |
1733.776 |
0.353 |
-4.28% |
0.353 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_INT_PREDICT_RAW/5001
|
-4.27% |
952.216 |
911.570 |
5.327 |
-0.20% |
5.327 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint8_t_To_uint64_t_
|
-4.27% |
23509.913 |
22506.456 |
22.078 |
-4.16% |
22.078 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint64_t>/999
|
-4.16% |
3595.308 |
3445.813 |
0.189 |
-4.14% |
0.189 |
|
SingleSource/Benchmarks/Misc/flops-5
Profile
|
-4.15% |
2.021 |
1.937 |
0.001 |
-4.15% |
0.001 |
|
MicroBenchmarks/ImageProcessing/Dilate/Dilate.test:BENCHMARK_DILATE/512
|
-4.14% |
3611.836 |
3462.481 |
33.471 |
-3.39% |
33.471 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC16
|
-4.12% |
14.393 |
13.800 |
0.151 |
-4.12% |
0.151 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_ENERGY_CALC_RAW/171
|
-4.11% |
14.207 |
13.623 |
0.008 |
-4.34% |
0.008 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint64_t_To_uint32_t_
|
-4.11% |
19399.980 |
18602.878 |
46.223 |
-3.57% |
46.223 |
|
External/SPEC/CFP2017rate/519.lbm_r/519.lbm_r
Profile
|
-4.09% |
200.669 |
192.470 |
1.244 |
-4.09% |
1.244 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_ENERGY_CALC_LAMBDA/171
|
-4.09% |
14.205 |
13.624 |
0.012 |
-4.38% |
0.012 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint64_t>/256
|
-4.08% |
935.469 |
897.345 |
0.056 |
-4.09% |
0.056 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC31
|
-4.04% |
61.949 |
59.445 |
0.003 |
-4.04% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint32_t>/65
|
-3.98% |
94.486 |
90.731 |
0.004 |
-3.98% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC1
|
-3.97% |
88.093 |
84.594 |
1.246 |
-4.93% |
1.246 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_only_autovec_uint8_t_
|
-3.97% |
96169.271 |
92351.086 |
10.528 |
-3.96% |
10.528 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC32
|
-3.97% |
63.203 |
60.694 |
0.003 |
-3.96% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint32_t>/256
|
-3.96% |
221.512 |
212.741 |
0.009 |
-3.96% |
0.009 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC3
|
-3.85% |
16.269 |
15.643 |
0.001 |
-3.85% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC63
|
-3.77% |
43.178 |
41.550 |
0.068 |
-4.03% |
0.068 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_ADI_LAMBDA/44217
|
-3.71% |
19920.043 |
19181.962 |
207.824 |
-2.53% |
207.824 |
|
SingleSource/Benchmarks/Shootout/Shootout-matrix
Profile
|
-3.69% |
3.864 |
3.721 |
0.000 |
-3.68% |
0.000 |
|
MultiSource/Benchmarks/TSVC/NodeSplitting-dbl/NodeSplitting-dbl
Profile
|
-3.69% |
26.947 |
25.952 |
0.244 |
-1.75% |
0.244 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<31, EqZero, First>
|
-3.68% |
3346.110 |
3223.026 |
0.080 |
-3.69% |
0.080 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint16_t_To_uint8_t_
|
-3.68% |
2872.550 |
2766.963 |
4.896 |
-3.87% |
4.896 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint64_t>/256
|
-3.65% |
514.389 |
495.605 |
0.005 |
-3.65% |
0.005 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_runtime_checks_fail<4, int>
|
-3.62% |
15.905 |
15.330 |
0.001 |
-3.64% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC64
|
-3.61% |
69.458 |
66.952 |
0.006 |
-3.61% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC64
|
-3.61% |
69.459 |
66.952 |
0.003 |
-3.61% |
0.003 |
|
MultiSource/Applications/JM/lencod/lencod
Profile
|
-3.59% |
32.763 |
31.586 |
0.024 |
-2.93% |
0.024 |
|
SingleSource/Benchmarks/BenchmarkGame/n-body
Profile
|
-3.58% |
2.731 |
2.633 |
0.000 |
21.69% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC63
|
-3.57% |
70.084 |
67.580 |
0.002 |
-3.58% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC63
|
-3.57% |
70.082 |
67.581 |
0.002 |
-3.57% |
0.002 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_PRESSURE_CALC_LAMBDA/44217
|
-3.54% |
503.035 |
485.218 |
1.589 |
-2.67% |
1.589 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC127
|
-3.48% |
2384.361 |
2301.322 |
19.525 |
-5.16% |
19.525 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_ENERGY_CALC_RAW/5001
|
-3.46% |
435.164 |
420.101 |
1.866 |
-2.01% |
1.866 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_ENERGY_CALC_LAMBDA/5001
|
-3.39% |
437.105 |
422.295 |
1.098 |
-3.59% |
1.098 |
|
MultiSource/Benchmarks/nbench/nbench
Profile
|
-3.38% |
6.119 |
5.912 |
0.001 |
-3.51% |
0.001 |
|
External/SPEC/CFP2017rate/544.nab_r/544.nab_r
Profile
|
-3.31% |
476.167 |
460.421 |
0.141 |
-3.65% |
0.141 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint32_t_To_uint16_t_
|
-3.24% |
9834.185 |
9515.950 |
15.132 |
-3.68% |
15.132 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC31
|
-3.20% |
93.779 |
90.778 |
0.011 |
-3.28% |
0.011 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint16_t_To_uint8_t_
|
-3.17% |
4511.936 |
4368.802 |
4.619 |
-3.29% |
4.619 |
|
SingleSource/Benchmarks/Shootout/Shootout-lists
Profile
|
-3.16% |
11.317 |
10.959 |
0.005 |
-3.12% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint16_t>/999
|
-3.16% |
514.967 |
498.693 |
0.071 |
-3.17% |
0.071 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1BigLoopWithReductionTC1
|
-3.13% |
20.024 |
19.398 |
0.001 |
-3.13% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC31
|
-3.13% |
60.072 |
58.193 |
0.004 |
-3.46% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchVecWithRuntimeChecks4PointersDBeforeA/1000
|
-3.10% |
5020476.302 |
4864986.382 |
460.402 |
-3.09% |
460.402 |
|
MultiSource/Benchmarks/TSVC/Recurrences-dbl/Recurrences-dbl
Profile
|
-2.94% |
10.345 |
10.041 |
0.035 |
-3.05% |
0.035 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C/CoMD/CoMD
Profile
|
-2.88% |
9.907 |
9.621 |
0.007 |
-2.80% |
0.007 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint16_t>/999
|
-2.84% |
1013.756 |
985.009 |
0.006 |
-2.85% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC64
|
-2.83% |
111.389 |
108.242 |
0.014 |
-2.82% |
0.014 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC32
|
-2.81% |
31.289 |
30.410 |
0.032 |
-2.80% |
0.032 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<31, GreaterThanZero, Last>
|
-2.79% |
8332.157 |
8099.522 |
13.960 |
-2.36% |
13.960 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC1
|
-2.79% |
22.528 |
21.900 |
0.001 |
-2.78% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC1
|
-2.78% |
22.527 |
21.900 |
0.004 |
-2.78% |
0.004 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, LessThanZero, None>
|
-2.66% |
37511.074 |
36514.910 |
8.135 |
-2.82% |
8.135 |
|
MultiSource/Benchmarks/FreeBench/mason/mason
Profile
|
-2.65% |
0.553 |
0.538 |
0.000 |
-2.71% |
0.000 |
|
MultiSource/Benchmarks/sim/sim
Profile
|
-2.64% |
9.700 |
9.443 |
0.026 |
-2.65% |
0.026 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC63
|
-2.61% |
120.150 |
117.012 |
0.005 |
-2.61% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_only_autovec_int64_t_
|
-2.60% |
1449612.921 |
1411871.711 |
1601.495 |
-2.43% |
1601.495 |
|
SingleSource/Benchmarks/Misc-C++/oopack_v1p8
Profile
|
-2.58% |
0.480 |
0.467 |
0.000 |
-9.96% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint8_t_To_uint32_t_
|
-2.58% |
7078.169 |
6895.355 |
1.532 |
-2.57% |
1.532 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_FLOYD_DITHER/256
|
-2.58% |
1786.593 |
1740.545 |
16.626 |
0.40% |
16.626 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint64_t_To_uint8_t_
|
-2.56% |
19750.688 |
19244.676 |
58.718 |
-3.01% |
58.718 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC31
|
-2.55% |
31.253 |
30.456 |
0.045 |
-2.35% |
0.045 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint8_t>/10
|
-2.54% |
48.803 |
47.562 |
0.011 |
2.48% |
0.011 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_FLOYD_DITHER/128
|
-2.54% |
437.801 |
426.693 |
1.662 |
-2.91% |
1.662 |
|
MultiSource/Benchmarks/mafft/pairlocalalign
Profile
|
-2.51% |
94.098 |
91.736 |
0.314 |
-2.47% |
0.314 |
|
MultiSource/Applications/sgefa/sgefa
Profile
|
-2.47% |
0.580 |
0.565 |
0.003 |
-1.40% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchVecWithRuntimeChecks4PointersDBeforeA/32
|
-2.43% |
166174.483 |
162134.613 |
3.084 |
-2.45% |
3.084 |
|
MultiSource/Benchmarks/FreeBench/fourinarow/fourinarow
Profile
|
-2.41% |
0.650 |
0.634 |
0.001 |
-2.49% |
0.001 |
|
MultiSource/Benchmarks/Olden/health/health
Profile
|
-2.36% |
1.592 |
1.554 |
0.005 |
-2.34% |
0.005 |
|
SingleSource/Benchmarks/Misc/fbench
Profile
|
-2.35% |
5.763 |
5.627 |
0.000 |
-2.32% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC63
|
-2.33% |
106.996 |
104.500 |
0.002 |
-2.34% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC32
|
-2.33% |
49.976 |
48.810 |
0.258 |
-2.48% |
0.258 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC64
|
-2.32% |
108.258 |
105.749 |
0.017 |
-2.31% |
0.017 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C/SimpleMOC/SimpleMOC
Profile
|
-2.25% |
10.444 |
10.209 |
0.048 |
-1.89% |
0.048 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_EOS_LAMBDA/5001
|
-2.21% |
30.162 |
29.494 |
0.231 |
-0.47% |
0.231 |
|
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% |
12.105 |
11.850 |
0.000 |
-2.07% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC128
|
-2.10% |
119.521 |
117.011 |
0.005 |
-2.10% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC127
|
-2.09% |
120.148 |
117.635 |
0.008 |
-2.08% |
0.008 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC128
|
-2.09% |
119.509 |
117.011 |
0.008 |
-2.10% |
0.008 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC127
|
-2.08% |
120.140 |
117.637 |
0.003 |
-2.09% |
0.003 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_EOS_RAW/171
|
-1.99% |
0.873 |
0.855 |
0.001 |
-1.79% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint32_t>/10
|
-1.99% |
47.246 |
46.306 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint32_t_To_uint64_t_
|
-1.99% |
26352.690 |
25828.429 |
25.300 |
-1.72% |
25.300 |
|
MultiSource/Benchmarks/Rodinia/pathfinder/pathfinder
Profile
|
-1.98% |
1.257 |
1.233 |
0.003 |
-2.00% |
0.003 |
|
SingleSource/Benchmarks/Misc/ReedSolomon
Profile
|
-1.97% |
20.821 |
20.410 |
0.002 |
-1.86% |
0.002 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<16, EqZero, None>
|
-1.97% |
8177.114 |
8016.094 |
12.776 |
-1.98% |
12.776 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<16, GreaterThanZero, First>
|
-1.96% |
8615.298 |
8446.256 |
22.607 |
-0.59% |
22.607 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<64, GreaterThanZero, Mid>
|
-1.85% |
2734.275 |
2683.804 |
15.772 |
-2.26% |
15.772 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_FLOYD_DITHER/512
|
-1.84% |
6645.402 |
6522.880 |
24.644 |
-1.84% |
24.644 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint16_t>/256
|
-1.83% |
272.812 |
267.816 |
0.007 |
-1.84% |
0.007 |
|
MicroBenchmarks/ImageProcessing/Blur/blur.test:BENCHMARK_boxBlurKernel/512
|
-1.82% |
6652.983 |
6531.805 |
24.352 |
-1.24% |
24.352 |
|
MultiSource/Benchmarks/TSVC/LoopRerolling-flt/LoopRerolling-flt
Profile
|
-1.79% |
11.486 |
11.281 |
0.059 |
-1.06% |
0.059 |
|
MultiSource/Benchmarks/Bullet/bullet
Profile
|
-1.76% |
30.402 |
29.866 |
0.146 |
-1.86% |
0.146 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint16_t_To_uint32_t_
|
-1.71% |
11310.803 |
11117.058 |
27.292 |
-1.99% |
27.292 |
|
External/SPEC/CFP2017rate/511.povray_r/511.povray_r
Profile
|
-1.71% |
33.935 |
33.354 |
0.063 |
-1.28% |
0.063 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<64, EqZero, Mid>
|
-1.71% |
2739.187 |
2692.394 |
12.088 |
-1.89% |
12.088 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_csa_with_in_loop_arith_novec_int64_t_
|
-1.70% |
1029552.953 |
1012100.239 |
698.476 |
-1.56% |
698.476 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint64_t>/51
|
-1.69% |
148.297 |
145.791 |
0.009 |
-1.70% |
0.009 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_EOS_LAMBDA/171
|
-1.69% |
0.870 |
0.856 |
0.002 |
-1.70% |
0.002 |
|
External/SPEC/CINT2017rate/531.deepsjeng_r/531.deepsjeng_r
Profile
|
-1.68% |
259.941 |
255.561 |
0.046 |
-1.75% |
0.046 |
|
MultiSource/Benchmarks/VersaBench/ecbdes/ecbdes
Profile
|
-1.67% |
5.142 |
5.056 |
0.002 |
-1.63% |
0.002 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<3, GreaterThanZero, None>
|
-1.62% |
45108.794 |
44380.246 |
269.039 |
-1.69% |
269.039 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<32, LessThanZero, Mid>
|
-1.60% |
4570.614 |
4497.542 |
18.002 |
-1.61% |
18.002 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_INT_PREDICT_LAMBDA/171
|
-1.59% |
6.923 |
6.813 |
0.009 |
-1.61% |
0.009 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_nested_cond_load_novec_uint8_t_
|
-1.58% |
504351.791 |
496384.809 |
93.895 |
-1.65% |
93.895 |
|
SingleSource/Benchmarks/Misc/mandel-2
Profile
|
-1.56% |
2.536 |
2.496 |
0.000 |
-1.54% |
0.000 |
|
MultiSource/Benchmarks/TSVC/LoopRestructuring-dbl/LoopRestructuring-dbl
Profile
|
-1.54% |
63.286 |
62.311 |
0.194 |
0.89% |
0.194 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC128
|
-1.49% |
211.519 |
208.373 |
0.013 |
-1.49% |
0.013 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, LessThanZero, Mid>
|
-1.45% |
56577.111 |
55756.229 |
37.197 |
-1.36% |
37.197 |
|
MultiSource/Benchmarks/Fhourstones-3.1/fhourstones3.1
Profile
|
-1.42% |
3.974 |
3.917 |
0.010 |
-1.36% |
0.010 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC127
|
-1.42% |
220.285 |
217.153 |
0.025 |
-1.42% |
0.025 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<6, LessThanZero, Mid>
|
-1.42% |
23870.239 |
23530.978 |
5.979 |
-0.15% |
5.979 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_INT_PREDICT_RAW/171
|
-1.42% |
6.911 |
6.813 |
0.007 |
-1.61% |
0.007 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_ENERGY_CALC_LAMBDA/44217
|
-1.41% |
4334.275 |
4272.993 |
4.767 |
-1.19% |
4.767 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint64_t>/51
|
-1.36% |
229.007 |
225.891 |
0.028 |
-1.36% |
0.028 |
|
MultiSource/Benchmarks/tramp3d-v4/tramp3d-v4
Profile
|
-1.34% |
1.074 |
1.059 |
0.001 |
-1.52% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC63
|
-1.33% |
130.116 |
128.383 |
0.109 |
-1.37% |
0.109 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<8, LessThanZero, Mid>
|
-1.32% |
19494.554 |
19237.257 |
12.303 |
-1.02% |
12.303 |
|
MultiSource/Benchmarks/MallocBench/cfrac/cfrac
Profile
|
-1.30% |
2.781 |
2.745 |
0.000 |
-1.27% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC127
|
-1.28% |
197.123 |
194.595 |
0.007 |
-1.27% |
0.007 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_csa_with_cond_arith_autovec_int64_t_
|
-1.28% |
745187.787 |
735640.689 |
211.247 |
-1.25% |
211.247 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<16, EqZero, Mid>
|
-1.28% |
8661.582 |
8550.899 |
30.820 |
-1.23% |
30.820 |
|
SingleSource/Benchmarks/BenchmarkGame/puzzle
Profile
|
-1.28% |
0.865 |
0.854 |
0.001 |
-1.75% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC128
|
-1.26% |
198.355 |
195.857 |
0.007 |
-1.27% |
0.007 |
|
External/SPEC/CINT2017rate/525.x264_r/525.x264_r
Profile
|
-1.22% |
129.153 |
127.578 |
0.126 |
-1.44% |
0.126 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<32, GreaterThanZero, Mid>
|
-1.20% |
4551.345 |
4496.509 |
1.958 |
-1.29% |
1.958 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<16, LessThanZero, Last>
|
-1.19% |
13142.097 |
12986.172 |
2.511 |
-1.19% |
2.511 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<3, EqZero, Mid>
|
-1.17% |
37605.913 |
37167.373 |
19.691 |
-1.15% |
19.691 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, LessThanZero, Mid>
|
-1.15% |
31882.402 |
31515.725 |
74.107 |
-0.84% |
74.107 |
|
MultiSource/Applications/obsequi/Obsequi
Profile
|
-1.15% |
7.683 |
7.595 |
0.015 |
-0.86% |
0.015 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_sinhf_novec_float_
|
-1.13% |
2243.166 |
2217.924 |
0.368 |
-1.07% |
0.368 |
|
SingleSource/Benchmarks/SmallPT/smallpt
Profile
|
-1.12% |
30.048 |
29.711 |
0.001 |
-1.06% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_sinhf_autovec_float_
|
-1.08% |
2241.559 |
2217.333 |
0.530 |
-1.13% |
0.530 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint8_t>/16
|
-1.06% |
85.377 |
84.470 |
0.002 |
11.81% |
0.002 |
|
MicroBenchmarks/Builtins/Int128/Builtins.test:BM_RemainderIntrinsic128UniformDivisor<__uint128_t>
|
-1.03% |
55.766 |
55.194 |
0.055 |
-0.99% |
0.055 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_ENERGY_CALC_RAW/44217
|
-1.01% |
4331.305 |
4287.613 |
10.191 |
-1.01% |
10.191 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_ORDERED_DITHER/128/8
|
-1.01% |
2145.552 |
2123.986 |
5.478 |
0.59% |
5.478 |