|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_HYDRO_2D_LAMBDA/44217
|
-63.22% |
86550.650 |
31831.504 |
8824.912 |
-64.99% |
8824.912 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_HYDRO_2D_LAMBDA/5001
|
-59.13% |
8977.164 |
3669.200 |
945.998 |
-59.74% |
945.998 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_INT_PREDICT_RAW/44217
|
-58.91% |
19474.457 |
8002.301 |
85.278 |
-11.57% |
85.278 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_INT_PREDICT_LAMBDA/44217
|
-58.10% |
19105.783 |
8005.586 |
79.085 |
-3.98% |
79.085 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint64_t_To_uint32_t_
|
-52.33% |
35221.531 |
16788.448 |
184.774 |
-52.46% |
184.774 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint64_t_To_uint16_t_
|
-51.92% |
35738.645 |
17184.326 |
67.708 |
-51.84% |
67.708 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint64_t_To_uint8_t_
|
-49.72% |
37165.070 |
18687.448 |
2.173 |
-49.58% |
2.173 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C/miniGMG/miniGMG
Profile
|
-48.26% |
8.886 |
4.598 |
0.288 |
-49.97% |
0.288 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_HYDRO_2D_RAW/44217
|
-46.62% |
94140.428 |
50255.420 |
12875.078 |
-40.63% |
12875.078 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_DIFF_PREDICT_RAW/44217
|
-44.28% |
24170.445 |
13467.157 |
249.624 |
-42.20% |
249.624 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_DIFF_PREDICT_LAMBDA/44217
|
-44.04% |
24105.376 |
13489.546 |
336.932 |
-41.61% |
336.932 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint16_t_To_uint64_t_
|
-43.88% |
18643.140 |
10462.873 |
2.129 |
-43.97% |
2.129 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIRST_DIFF_RAW/44217
|
-42.30% |
178.252 |
102.844 |
1.609 |
-27.82% |
1.609 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_HYDRO_2D_RAW/5001
|
-41.63% |
9432.437 |
5505.346 |
1300.150 |
-37.41% |
1300.150 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint8_t_To_uint64_t_
|
-41.19% |
17902.249 |
10527.923 |
7.445 |
-40.85% |
7.445 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIRST_DIFF_LAMBDA/44217
|
-41.15% |
170.641 |
100.429 |
0.952 |
-30.65% |
0.952 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_PIC_1D_LAMBDA/44217
|
-41.11% |
13526.018 |
7964.807 |
1459.789 |
-40.85% |
1459.789 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_DIFF_PREDICT_LAMBDA/5001
|
-40.67% |
2543.760 |
1509.263 |
39.987 |
-39.86% |
39.987 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint64_t_To_uint32_t_
|
-40.63% |
38251.955 |
22710.741 |
11.462 |
-40.48% |
11.462 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_DIFF_PREDICT_RAW/5001
|
-40.16% |
2520.628 |
1508.454 |
26.799 |
-41.41% |
26.799 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_INT_PREDICT_RAW/5001
|
-39.79% |
1510.933 |
909.750 |
5.137 |
-0.40% |
5.137 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/32
|
-36.70% |
1396.259 |
883.824 |
0.068 |
-36.69% |
0.068 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/64
|
-36.67% |
6181.318 |
3914.604 |
0.279 |
-36.68% |
0.279 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/16
|
-36.64% |
279.504 |
177.096 |
0.010 |
-36.63% |
0.010 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/256
|
-36.21% |
107125.993 |
68331.900 |
50.694 |
-36.23% |
50.694 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/128
|
-36.10% |
26259.523 |
16779.046 |
8.978 |
-36.13% |
8.978 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint32_t_To_uint64_t_
|
-35.28% |
22474.612 |
14545.487 |
259.995 |
-35.99% |
259.995 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint64_t_To_uint8_t_
|
-34.21% |
30079.196 |
19790.086 |
16.437 |
-34.28% |
16.437 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint64_t_To_uint16_t_
|
-33.99% |
29000.901 |
19142.799 |
46.574 |
-33.87% |
46.574 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_INT_PREDICT_LAMBDA/5001
|
-29.60% |
1286.915 |
906.015 |
8.632 |
0.14% |
8.632 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint64_t_To_uint16_t_
|
-28.42% |
25903.150 |
18542.477 |
17.116 |
-28.40% |
17.116 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint32_t_To_uint8_t_
|
-27.88% |
13475.562 |
9718.304 |
4.661 |
-27.85% |
4.661 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_DISC_ORD_RAW/44217
|
-27.84% |
14067.336 |
10150.939 |
1299.750 |
-23.91% |
1299.750 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_PIC_2D_LAMBDA/44217
|
-27.54% |
11880.044 |
8608.122 |
23.635 |
-21.48% |
23.635 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC128
|
-27.50% |
1291.987 |
936.752 |
2.916 |
-27.54% |
2.916 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_PIC_2D_RAW/44217
|
-27.26% |
11888.674 |
8647.280 |
517.570 |
-22.90% |
517.570 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC128
|
-27.03% |
558.442 |
407.501 |
0.060 |
-26.91% |
0.060 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC64
|
-26.99% |
653.540 |
477.180 |
1.979 |
-26.99% |
1.979 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC32
|
-26.81% |
333.877 |
244.363 |
0.987 |
-26.82% |
0.987 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC16
|
-26.29% |
173.791 |
128.109 |
0.642 |
-26.28% |
0.642 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIRST_SUM_LAMBDA/44217
|
-26.11% |
181.741 |
134.281 |
1.005 |
-19.63% |
1.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC64
|
-25.68% |
292.241 |
217.191 |
0.052 |
-25.58% |
0.052 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint64_t_To_uint8_t_
|
-24.64% |
27182.533 |
20484.489 |
33.173 |
-24.75% |
33.173 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIRST_SUM_RAW/44217
|
-24.34% |
179.460 |
135.788 |
0.059 |
-18.37% |
0.059 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_PIC_2D_RAW/5001
|
-23.69% |
1196.433 |
913.040 |
32.952 |
-15.33% |
32.952 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC32
|
-23.21% |
158.952 |
122.052 |
0.056 |
-23.18% |
0.056 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC128
|
-23.11% |
603.960 |
464.384 |
0.034 |
-23.11% |
0.034 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC128
|
-23.11% |
603.947 |
464.378 |
0.026 |
-23.11% |
0.026 |
|
MicroBenchmarks/ImageProcessing/Blur/blur.test:BENCHMARK_boxBlurKernel/1024
|
-22.90% |
30091.302 |
23199.710 |
96.999 |
-23.05% |
96.999 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC64
|
-22.16% |
313.507 |
244.040 |
0.021 |
-22.16% |
0.021 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC64
|
-22.15% |
313.490 |
244.042 |
0.012 |
-22.16% |
0.012 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC127
|
-21.98% |
615.200 |
480.006 |
0.041 |
-21.98% |
0.041 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC127
|
-21.97% |
615.207 |
480.023 |
0.058 |
-21.97% |
0.058 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint8_t_To_uint32_t_
|
-21.65% |
6595.438 |
5167.404 |
1.890 |
-21.49% |
1.890 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC4
|
-21.43% |
17.520 |
13.766 |
0.000 |
-21.43% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_only_autovec_uint8_t_
|
-21.39% |
182412.748 |
143403.142 |
104.066 |
-21.36% |
104.066 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint16_t_To_uint32_t_
|
-21.38% |
7099.836 |
5581.715 |
1.493 |
-21.40% |
1.493 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint16_t_To_uint64_t_
|
-21.38% |
13188.564 |
10368.652 |
0.586 |
-21.50% |
0.586 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIND_FIRST_MIN_LAMBDA/171
|
-21.30% |
1.501 |
1.181 |
0.000 |
-21.28% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIND_FIRST_MIN_LAMBDA/44217
|
-21.27% |
389.471 |
306.613 |
0.224 |
-21.30% |
0.224 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC127
|
-20.93% |
275.149 |
217.568 |
1.435 |
-21.01% |
1.435 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIND_FIRST_MIN_LAMBDA/5001
|
-20.91% |
45.195 |
35.744 |
0.289 |
-21.02% |
0.289 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC128
|
-20.71% |
274.610 |
217.751 |
1.021 |
-20.74% |
1.021 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC32
|
-20.45% |
168.330 |
133.906 |
0.022 |
-20.45% |
0.022 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC32
|
-20.44% |
168.316 |
133.913 |
0.005 |
-20.45% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC63
|
-20.04% |
324.775 |
259.684 |
0.017 |
-20.04% |
0.017 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC63
|
-20.04% |
324.766 |
259.689 |
0.016 |
-20.05% |
0.016 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_PIC_2D_LAMBDA/5001
|
-19.86% |
1176.098 |
942.470 |
15.624 |
-14.75% |
15.624 |
|
SingleSource/Benchmarks/Adobe-C++/loop_unroll
Profile
|
-19.85% |
2.988 |
2.395 |
0.003 |
-22.92% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC127
|
-19.68% |
640.929 |
514.784 |
0.062 |
-19.63% |
0.062 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC64
|
-19.59% |
148.872 |
119.713 |
4.735 |
-19.46% |
4.735 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC63
|
-19.36% |
150.225 |
121.144 |
7.696 |
-19.19% |
7.696 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC16
|
-19.24% |
92.290 |
74.535 |
0.026 |
-19.23% |
0.026 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint32_t_To_uint8_t_
|
-19.18% |
13901.450 |
11235.750 |
66.018 |
-19.17% |
66.018 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint16_t_To_uint8_t_
|
-19.10% |
3818.169 |
3089.077 |
0.889 |
-19.09% |
0.889 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_VOL3D_CALC_LAMBDA/2
|
-18.80% |
8.756 |
7.110 |
0.001 |
-18.81% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_VOL3D_CALC_RAW/2
|
-18.79% |
8.755 |
7.111 |
0.000 |
-18.80% |
0.000 |
|
MultiSource/Benchmarks/MiBench/automotive-bitcount/automotive-bitcount
Profile
|
-18.78% |
0.125 |
0.101 |
0.000 |
-18.00% |
0.000 |
|
MicroBenchmarks/ImageProcessing/Dilate/Dilate.test:BENCHMARK_DILATE/1024
|
-18.77% |
7640.611 |
6206.265 |
276.877 |
-12.72% |
276.877 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC7
|
-18.75% |
28.509 |
23.163 |
0.133 |
-19.18% |
0.133 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, EqZero, None>
|
-18.75% |
20511.246 |
16665.792 |
0.590 |
-18.75% |
0.590 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC128
|
-18.70% |
570.768 |
464.049 |
3.477 |
-18.67% |
3.477 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint32_t_To_uint16_t_
|
-18.70% |
13802.315 |
11221.631 |
22.382 |
-18.73% |
22.382 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC32
|
-18.70% |
85.952 |
69.882 |
2.760 |
-18.10% |
2.760 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint64_t_To_uint32_t_
|
-18.62% |
27104.443 |
22057.215 |
25.154 |
-18.46% |
25.154 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, EqZero, Last>
|
-18.17% |
14103.685 |
11540.344 |
0.632 |
-18.18% |
0.632 |
|
MultiSource/Benchmarks/Trimaran/enc-pc1/enc-pc1
Profile
|
-18.13% |
1.105 |
0.904 |
0.000 |
-18.11% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_with_cond_arith_novec_uint8_t_
|
-17.91% |
746415.643 |
612708.768 |
469.814 |
-17.84% |
469.814 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC8
|
-17.66% |
23.151 |
19.062 |
0.079 |
-17.67% |
0.079 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC16
|
-17.65% |
95.740 |
78.846 |
0.003 |
-17.65% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC16
|
-17.64% |
95.735 |
78.844 |
0.003 |
-17.65% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC31
|
-17.63% |
86.860 |
71.543 |
2.035 |
-16.92% |
2.035 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_with_cond_arith_novec_int32_t_
|
-17.42% |
740362.714 |
611373.248 |
1245.914 |
-17.40% |
1245.914 |
|
MultiSource/Benchmarks/MiBench/security-rijndael/security-rijndael
Profile
|
-17.42% |
0.336 |
0.277 |
0.000 |
-17.22% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint8_t_To_uint64_t_
|
-17.35% |
13212.106 |
10920.298 |
10.701 |
-16.42% |
10.701 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC64
|
-17.33% |
297.850 |
246.220 |
0.019 |
-17.30% |
0.019 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC32
|
-17.26% |
161.439 |
133.574 |
0.011 |
-17.24% |
0.011 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC16
|
-17.12% |
93.238 |
77.279 |
0.015 |
-17.02% |
0.015 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC8
|
-16.80% |
58.820 |
48.938 |
0.084 |
-16.72% |
0.084 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC31
|
-16.73% |
179.584 |
149.548 |
0.007 |
-16.72% |
0.007 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC31
|
-16.72% |
179.584 |
149.549 |
0.008 |
-16.73% |
0.008 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_HYDRO_1D_RAW/171
|
-16.21% |
0.444 |
0.372 |
0.000 |
-15.84% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_VOL3D_CALC_LAMBDA/0
|
-16.11% |
1268.132 |
1063.891 |
1.733 |
-16.07% |
1.733 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_VOL3D_CALC_LAMBDA/1
|
-16.08% |
260.118 |
218.287 |
0.188 |
-16.10% |
0.188 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_VOL3D_CALC_RAW/1
|
-16.07% |
259.787 |
218.044 |
0.127 |
-16.18% |
0.127 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_HYDRO_1D_LAMBDA/171
|
-15.94% |
0.442 |
0.372 |
0.000 |
-15.88% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_VOL3D_CALC_RAW/0
|
-15.92% |
1265.131 |
1063.726 |
0.761 |
-15.92% |
0.761 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC8
|
-15.78% |
23.777 |
20.024 |
0.001 |
-15.79% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint16_t_To_uint32_t_
|
-15.63% |
7463.023 |
6296.745 |
0.535 |
-15.62% |
0.535 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_no_runtime_checks_needed<16, int>
|
-15.38% |
24.401 |
20.648 |
0.001 |
-15.39% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC16
|
-15.10% |
33.165 |
28.157 |
0.572 |
-15.10% |
0.572 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint32_t_To_uint8_t_
|
-15.07% |
10655.932 |
9049.961 |
7.336 |
-14.59% |
7.336 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint64_t_To_uint8_t_
|
-15.01% |
21960.904 |
18665.524 |
15.567 |
-15.34% |
15.567 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC127
|
-14.97% |
605.761 |
515.078 |
0.169 |
-14.97% |
0.169 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC128
|
-14.51% |
1103.257 |
943.164 |
0.032 |
-14.51% |
0.032 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC127
|
-14.41% |
1095.289 |
937.478 |
0.043 |
-14.41% |
0.043 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint32_t_To_uint16_t_
|
-14.34% |
12834.832 |
10994.245 |
25.886 |
-14.36% |
25.886 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC64
|
-14.24% |
562.564 |
482.451 |
0.027 |
-14.20% |
0.027 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint8_t_To_uint16_t_
|
-14.15% |
3756.836 |
3225.384 |
2.332 |
-14.14% |
2.332 |
|
SingleSource/Benchmarks/Misc/salsa20
Profile
|
-14.13% |
15.386 |
13.212 |
0.001 |
-14.12% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC15
|
-14.10% |
44.434 |
38.169 |
0.007 |
-14.09% |
0.007 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC63
|
-14.02% |
554.539 |
476.817 |
0.022 |
-14.05% |
0.022 |
|
External/SPEC/CFP2017rate/508.namd_r/508.namd_r
Profile
|
-13.95% |
224.519 |
193.191 |
0.312 |
-13.59% |
0.312 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_with_cond_arith_autovec_int64_t_
|
-13.92% |
791179.196 |
681050.486 |
1087.049 |
-13.97% |
1087.049 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC8
|
-13.86% |
51.938 |
44.738 |
0.004 |
-13.86% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC3
|
-13.86% |
51.936 |
44.737 |
0.003 |
-13.86% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC7
|
-13.86% |
51.936 |
44.737 |
0.002 |
-13.86% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC1
|
-13.86% |
51.939 |
44.740 |
0.001 |
-13.85% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC2
|
-13.86% |
51.939 |
44.740 |
0.002 |
-13.85% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC4
|
-13.86% |
51.937 |
44.740 |
0.002 |
-13.85% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC32
|
-13.71% |
292.199 |
252.144 |
0.025 |
-13.65% |
0.025 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC8
|
-13.68% |
59.443 |
51.308 |
0.001 |
-13.69% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC8
|
-13.68% |
59.445 |
51.312 |
0.001 |
-13.69% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_with_cond_arith_novec_int64_t_
|
-13.68% |
789311.178 |
681370.540 |
875.500 |
-13.54% |
875.500 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint32_t_To_uint16_t_
|
-13.57% |
9975.211 |
8621.942 |
182.063 |
-12.95% |
182.063 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC4
|
-13.41% |
111.765 |
96.776 |
2.394 |
-14.42% |
2.394 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC63
|
-13.35% |
374.409 |
324.411 |
0.011 |
-13.36% |
0.011 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint32_t_To_uint8_t_
|
-13.34% |
10974.048 |
9509.660 |
17.611 |
-14.55% |
17.611 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC31
|
-13.23% |
284.101 |
246.510 |
0.017 |
-13.23% |
0.017 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC16
|
-13.16% |
51.943 |
45.108 |
0.403 |
-13.16% |
0.403 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC128
|
-13.07% |
81.344 |
70.710 |
0.002 |
-13.07% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC63
|
-12.96% |
332.897 |
289.766 |
0.141 |
-12.94% |
0.141 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint8_t_To_uint16_t_
|
-12.95% |
4541.823 |
3953.764 |
0.300 |
-12.95% |
0.300 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC16
|
-12.75% |
157.058 |
137.032 |
0.005 |
-12.70% |
0.005 |
|
SingleSource/Benchmarks/Shootout-C++/Shootout-C++-matrix
Profile
|
-12.72% |
2.509 |
2.190 |
0.000 |
-12.70% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIRST_SUM_RAW/5001
|
-12.57% |
20.345 |
17.788 |
0.626 |
2.55% |
0.626 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIRST_SUM_LAMBDA/5001
|
-12.44% |
20.311 |
17.783 |
0.332 |
0.99% |
0.332 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint16_t_To_uint8_t_
|
-12.41% |
4743.174 |
4154.438 |
0.270 |
-12.40% |
0.270 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, EqZero, None>
|
-11.99% |
16024.209 |
14102.404 |
0.900 |
-11.99% |
0.900 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC15
|
-11.77% |
148.936 |
131.403 |
0.019 |
-11.70% |
0.019 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC2
|
-11.77% |
21.275 |
18.772 |
0.001 |
-11.77% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC15
|
-11.70% |
107.003 |
94.485 |
0.007 |
-11.70% |
0.007 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC15
|
-11.70% |
106.998 |
94.482 |
0.031 |
-11.70% |
0.031 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC15
|
-11.46% |
51.937 |
45.985 |
0.004 |
-11.46% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC4
|
-11.12% |
22.528 |
20.023 |
0.002 |
-11.11% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC4
|
-11.12% |
22.526 |
20.023 |
0.000 |
-11.12% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC3
|
-11.11% |
22.525 |
20.022 |
0.001 |
-11.12% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint8_t>/51
|
-11.10% |
123.890 |
110.144 |
0.035 |
19.07% |
0.035 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint32_t_To_uint64_t_
|
-10.63% |
17089.218 |
15272.052 |
408.980 |
-11.19% |
408.980 |
|
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:benchForIC2VW1LoopWithReductionTC4
|
-10.52% |
23.777 |
21.275 |
0.001 |
-10.53% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC64
|
-10.47% |
53.815 |
48.182 |
0.000 |
-10.47% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC8
|
-10.43% |
89.422 |
80.095 |
0.003 |
-10.41% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC16
|
-10.34% |
36.292 |
32.538 |
0.000 |
-10.35% |
0.000 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/16
|
-10.17% |
115.465 |
103.719 |
0.010 |
-10.17% |
0.010 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopFrom_uint32_t_To_uint16_t_
|
-10.17% |
8103.216 |
7279.466 |
198.667 |
-2.30% |
198.667 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint8_t_To_uint16_t_
|
-10.07% |
5853.154 |
5263.836 |
8.427 |
-10.03% |
8.427 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/64
|
-10.02% |
1913.276 |
1721.532 |
0.306 |
-10.02% |
0.306 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/32
|
-10.00% |
473.007 |
425.727 |
0.019 |
-9.99% |
0.019 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/256
|
-9.97% |
31449.613 |
28313.467 |
25.521 |
-9.97% |
25.521 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint64_t_To_uint32_t_
|
-9.97% |
18212.944 |
16397.912 |
206.023 |
-7.95% |
206.023 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/128
|
-9.83% |
7920.401 |
7141.790 |
2.300 |
-9.80% |
2.300 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_DIFF_PREDICT_LAMBDA/171
|
-9.80% |
12.316 |
11.109 |
0.086 |
-7.31% |
0.086 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC8
|
-9.76% |
25.655 |
23.151 |
0.001 |
-9.76% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC8
|
-9.75% |
25.655 |
23.152 |
0.000 |
-9.76% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC31
|
-9.74% |
196.484 |
177.343 |
0.034 |
-9.74% |
0.034 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC16
|
-9.71% |
31.878 |
28.782 |
0.001 |
-8.01% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_DIFF_PREDICT_RAW/171
|
-9.66% |
12.297 |
11.109 |
0.116 |
-6.90% |
0.116 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC7
|
-9.62% |
32.540 |
29.409 |
0.000 |
-9.62% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_only_autovec_int64_t_
|
-9.60% |
333364.358 |
301345.582 |
473.609 |
-9.58% |
473.609 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC7
|
-9.53% |
26.281 |
23.777 |
0.001 |
-9.53% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC127
|
-9.47% |
101.607 |
91.987 |
0.003 |
-9.71% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC7
|
-9.39% |
26.280 |
23.812 |
0.032 |
-9.40% |
0.032 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint64_t_To_uint16_t_
|
-9.38% |
18981.885 |
17200.887 |
240.704 |
-9.39% |
240.704 |
|
MultiSource/Benchmarks/McCat/12-IOtest/iotest
Profile
|
-9.32% |
1.855 |
1.682 |
0.015 |
-7.83% |
0.015 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_DEL_DOT_VEC_2D_RAW/1
|
-9.24% |
287.045 |
260.518 |
0.156 |
-9.22% |
0.156 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC7
|
-9.24% |
81.347 |
73.834 |
0.004 |
-9.20% |
0.004 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_DEL_DOT_VEC_2D_LAMBDA/1
|
-9.21% |
287.107 |
260.662 |
0.149 |
-9.21% |
0.149 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC4
|
-9.09% |
41.300 |
37.545 |
0.002 |
-9.09% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC4
|
-9.09% |
41.297 |
37.543 |
0.002 |
-9.10% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC32
|
-9.02% |
53.189 |
48.393 |
0.013 |
-9.02% |
0.013 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_PRESSURE_CALC_RAW/5001
|
-9.02% |
46.524 |
42.330 |
0.829 |
-5.09% |
0.829 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC4
|
-8.99% |
55.690 |
50.683 |
0.003 |
-8.95% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC7
|
-8.89% |
28.157 |
25.654 |
0.001 |
-8.90% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_DEL_DOT_VEC_2D_LAMBDA/2
|
-8.71% |
3.510 |
3.204 |
0.000 |
-8.70% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC4
|
-8.70% |
14.392 |
13.140 |
0.001 |
-8.71% |
0.001 |
|
MultiSource/Benchmarks/FreeBench/pifft/pifft
Profile
|
-8.70% |
0.358 |
0.327 |
0.001 |
-8.75% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_DEL_DOT_VEC_2D_RAW/2
|
-8.70% |
3.510 |
3.204 |
0.000 |
-8.71% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC16
|
-8.70% |
14.392 |
13.140 |
0.001 |
-8.71% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC1
|
-8.70% |
14.392 |
13.140 |
0.000 |
-8.70% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC3
|
-8.70% |
14.392 |
13.140 |
0.001 |
-8.70% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC15
|
-8.70% |
14.392 |
13.140 |
0.000 |
-8.70% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC1
|
-8.70% |
14.393 |
13.142 |
0.001 |
-8.70% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC3
|
-8.70% |
14.391 |
13.140 |
0.001 |
-8.70% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC7
|
-8.70% |
14.391 |
13.140 |
0.000 |
-8.70% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC2
|
-8.70% |
14.392 |
13.140 |
0.000 |
-8.69% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC15
|
-8.69% |
14.392 |
13.141 |
0.000 |
-8.70% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC8
|
-8.69% |
14.392 |
13.141 |
0.000 |
-8.70% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC4
|
-8.69% |
14.392 |
13.140 |
0.000 |
-8.70% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC2
|
-8.69% |
14.391 |
13.141 |
0.000 |
-8.69% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC7
|
-8.69% |
14.391 |
13.141 |
0.001 |
-8.69% |
0.001 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_runtime_checks_pass<4, int>
|
-8.69% |
16.789 |
15.330 |
0.001 |
-8.25% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC16
|
-8.69% |
14.391 |
13.140 |
0.002 |
-8.69% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC8
|
-8.69% |
14.391 |
13.140 |
0.000 |
-8.70% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC8
|
-8.51% |
29.409 |
26.905 |
0.001 |
-8.52% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint16_t_To_uint8_t_
|
-8.51% |
6810.136 |
6230.482 |
12.294 |
-8.59% |
12.294 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint8_t>/28
|
-8.25% |
82.595 |
75.785 |
0.027 |
12.13% |
0.027 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint8_t_To_uint32_t_
|
-8.23% |
12783.283 |
11731.537 |
20.630 |
-8.19% |
20.630 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC64
|
-8.07% |
93.243 |
85.719 |
0.004 |
-8.07% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC16
|
-7.85% |
31.913 |
29.409 |
0.002 |
-7.85% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC16
|
-7.84% |
31.912 |
29.409 |
0.001 |
-7.84% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint16_t_To_uint64_t_
|
-7.84% |
20225.844 |
18639.951 |
93.870 |
-7.46% |
93.870 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC32
|
-7.81% |
40.048 |
36.919 |
0.001 |
-7.82% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIRST_DIFF_LAMBDA/5001
|
-7.77% |
12.791 |
11.797 |
0.325 |
-3.23% |
0.325 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC15
|
-7.69% |
32.538 |
30.035 |
0.001 |
-7.69% |
0.001 |
|
MultiSource/Benchmarks/VersaBench/beamformer/beamformer
Profile
|
-7.68% |
5.201 |
4.802 |
0.003 |
-7.67% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC15
|
-7.64% |
54.438 |
50.277 |
0.016 |
-7.65% |
0.016 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_HYDRO_2D_RAW/171
|
-7.57% |
88.905 |
82.178 |
0.522 |
-7.28% |
0.522 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_DEL_DOT_VEC_2D_LAMBDA/0
|
-7.55% |
1800.060 |
1664.229 |
5.530 |
-7.13% |
5.530 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC31
|
-7.54% |
74.458 |
68.843 |
0.013 |
-7.55% |
0.013 |
|
MultiSource/Benchmarks/Trimaran/enc-md5/enc-md5
Profile
|
-7.54% |
3.507 |
3.243 |
0.000 |
-7.49% |
0.000 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_xor_no_runtime_checks_needed<16, int>
|
-7.41% |
16.895 |
15.643 |
0.001 |
-7.42% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint16_t_To_uint64_t_
|
-7.40% |
25053.868 |
23199.290 |
46.308 |
-7.15% |
46.308 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_HYDRO_2D_LAMBDA/171
|
-7.33% |
88.619 |
82.122 |
0.510 |
-7.37% |
0.510 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC128
|
-7.28% |
68.832 |
63.823 |
0.002 |
-7.24% |
0.002 |
|
MultiSource/Applications/lambda-0.1.3/lambda
Profile
|
-7.27% |
15.871 |
14.717 |
0.007 |
-7.27% |
0.007 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC127
|
-7.27% |
68.828 |
63.824 |
0.001 |
-6.54% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_DEL_DOT_VEC_2D_RAW/0
|
-7.25% |
1798.239 |
1667.923 |
1.024 |
-7.38% |
1.024 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint8_t>/127
|
-7.21% |
138.911 |
128.894 |
0.019 |
-7.21% |
0.019 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC128
|
-7.21% |
173.326 |
160.833 |
0.004 |
-7.21% |
0.004 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIND_FIRST_MIN_RAW/171
|
-7.18% |
1.497 |
1.390 |
0.000 |
-7.14% |
0.000 |
|
SingleSource/Benchmarks/Misc/pi
Profile
|
-7.02% |
1.782 |
1.657 |
0.000 |
-7.02% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC63
|
-6.96% |
114.506 |
106.539 |
0.070 |
-6.96% |
0.070 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC15
|
-6.94% |
45.051 |
41.924 |
0.002 |
-6.94% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC8
|
-6.78% |
26.848 |
25.029 |
0.001 |
-7.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC127
|
-6.61% |
194.619 |
181.750 |
0.111 |
-6.61% |
0.111 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC2
|
-6.56% |
38.171 |
35.668 |
0.001 |
-6.56% |
0.001 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C++/miniFE/miniFE
Profile
|
-6.55% |
15.818 |
14.783 |
0.099 |
-7.43% |
0.099 |
|
SingleSource/Benchmarks/Misc/flops-6
Profile
|
-6.53% |
1.311 |
1.225 |
0.001 |
-6.63% |
0.001 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_xor_runtime_checks_pass<16, int>
|
-6.52% |
28.783 |
26.905 |
0.000 |
-6.52% |
0.000 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_xor_runtime_checks_fail<16, int>
|
-6.52% |
28.782 |
26.906 |
0.003 |
-6.52% |
0.003 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_PIC_1D_RAW/5001
|
-6.48% |
359.444 |
336.151 |
4.401 |
-2.57% |
4.401 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_only_autovec_int32_t_
|
-6.42% |
180891.179 |
169279.532 |
163.032 |
-6.54% |
163.032 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC63
|
-6.35% |
74.163 |
69.456 |
0.006 |
-6.42% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC15
|
-6.34% |
39.418 |
36.920 |
0.000 |
-6.35% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint16_t>/127
|
-6.30% |
138.912 |
130.154 |
0.005 |
-6.30% |
0.005 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIND_FIRST_MIN_RAW/5001
|
-6.29% |
45.294 |
42.444 |
0.010 |
-6.39% |
0.010 |
|
SingleSource/Benchmarks/Misc-C++/Large/sphereflake
Profile
|
-6.24% |
20.014 |
18.766 |
0.003 |
-6.18% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC16
|
-6.17% |
40.676 |
38.168 |
0.003 |
-6.16% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC32
|
-6.12% |
61.323 |
57.568 |
0.003 |
-6.12% |
0.003 |
|
SingleSource/Benchmarks/Misc/perlin
Profile
|
-5.98% |
6.599 |
6.204 |
0.000 |
-5.97% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint8_t>/65
|
-5.92% |
95.111 |
89.484 |
0.004 |
-5.92% |
0.004 |
|
MultiSource/Benchmarks/MiBench/telecomm-gsm/telecomm-gsm
Profile
|
-5.89% |
0.663 |
0.624 |
0.000 |
-5.96% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint32_t>/127
|
-5.88% |
138.276 |
130.151 |
0.005 |
-5.88% |
0.005 |
|
SingleSource/Benchmarks/Polybench/stencils/jacobi-2d/jacobi-2d
Profile
|
-5.83% |
32.212 |
30.334 |
0.087 |
-5.86% |
0.087 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC32
|
-5.79% |
24.403 |
22.989 |
0.338 |
-5.79% |
0.338 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_PRESSURE_CALC_LAMBDA/5001
|
-5.72% |
44.790 |
42.229 |
0.984 |
-3.97% |
0.984 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_BAND_LIN_EQ_RAW/5001
|
-5.67% |
21.232 |
20.029 |
0.277 |
-2.88% |
0.277 |
|
SingleSource/Benchmarks/Misc/oourafft
Profile
|
-5.67% |
15.328 |
14.459 |
0.049 |
-4.20% |
0.049 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC16
|
-5.66% |
33.164 |
31.287 |
0.000 |
-5.66% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC32
|
-5.64% |
44.427 |
41.921 |
0.003 |
-5.64% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC32
|
-5.63% |
44.428 |
41.925 |
0.001 |
-5.64% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC15
|
-5.60% |
128.269 |
121.086 |
0.017 |
-5.59% |
0.017 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC31
|
-5.58% |
45.062 |
42.549 |
0.001 |
-5.58% |
0.001 |
|
MultiSource/Benchmarks/SciMark2-C/scimark2
Profile
|
-5.57% |
107.716 |
101.720 |
0.069 |
-5.50% |
0.069 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC31
|
-5.55% |
45.051 |
42.549 |
0.003 |
-5.56% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC127
|
-5.50% |
2387.637 |
2256.416 |
34.489 |
-7.01% |
34.489 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint8_t_To_uint16_t_
|
-5.48% |
3629.066 |
3430.274 |
5.415 |
-5.59% |
5.415 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint32_t>/999
|
-5.40% |
696.571 |
658.955 |
0.041 |
-5.39% |
0.041 |
|
External/SPEC/CFP2017rate/538.imagick_r/538.imagick_r
Profile
|
-5.38% |
291.006 |
275.358 |
0.315 |
-5.73% |
0.315 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIND_FIRST_MIN_RAW/44217
|
-5.38% |
389.296 |
368.370 |
0.256 |
-5.45% |
0.256 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_BAND_LIN_EQ_LAMBDA/5001
|
-5.36% |
21.181 |
20.045 |
0.056 |
-3.63% |
0.056 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC7
|
-5.31% |
70.710 |
66.951 |
0.002 |
-5.33% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC7
|
-5.31% |
70.710 |
66.951 |
0.004 |
-5.32% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC3
|
-5.27% |
47.557 |
45.049 |
0.002 |
-5.27% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC1
|
-5.26% |
11.889 |
11.263 |
0.001 |
-5.27% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint32_t>/999
|
-5.21% |
1364.928 |
1293.844 |
0.090 |
-5.22% |
0.090 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_PIC_2D_LAMBDA/171
|
-5.15% |
13.453 |
12.760 |
0.055 |
-5.47% |
0.055 |
|
MultiSource/Benchmarks/Rodinia/hotspot/hotspot
Profile
|
-5.12% |
2.035 |
1.931 |
0.003 |
-5.14% |
0.003 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_PIC_2D_RAW/171
|
-5.09% |
13.520 |
12.831 |
0.057 |
-5.23% |
0.057 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC32
|
-4.99% |
50.054 |
47.558 |
0.035 |
-4.98% |
0.035 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC31
|
-4.96% |
241.159 |
229.209 |
0.027 |
-4.98% |
0.027 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint32_t_To_uint64_t_
|
-4.94% |
21327.188 |
20274.224 |
69.716 |
-5.49% |
69.716 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint32_t>/256
|
-4.82% |
364.197 |
346.650 |
0.012 |
-4.81% |
0.012 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC15
|
-4.81% |
32.537 |
30.974 |
0.001 |
-4.81% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1LoopWithReductionTC3
|
-4.76% |
13.141 |
12.515 |
0.001 |
5.26% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC32
|
-4.73% |
24.405 |
23.251 |
0.259 |
-4.73% |
0.259 |
|
SingleSource/Benchmarks/Misc/revertBits
Profile
|
-4.70% |
0.641 |
0.611 |
0.000 |
-4.69% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_PRESSURE_CALC_RAW/44217
|
-4.69% |
504.539 |
480.887 |
1.245 |
-4.24% |
1.245 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopFrom_uint32_t_To_uint64_t_
|
-4.66% |
14363.396 |
13694.670 |
78.690 |
-0.77% |
78.690 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint16_t>/65
|
-4.60% |
95.111 |
90.732 |
0.005 |
-4.61% |
0.005 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_runtime_checks_pass<16, int>
|
-4.60% |
54.440 |
51.936 |
0.001 |
-4.59% |
0.001 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_runtime_checks_fail<16, int>
|
-4.60% |
54.435 |
51.933 |
0.002 |
-4.60% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC31
|
-4.58% |
93.779 |
89.487 |
0.119 |
-4.65% |
0.119 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_runtime_checks_fail<4, int>
|
-4.57% |
16.064 |
15.329 |
0.000 |
-3.64% |
0.000 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C++/HPCCG/HPCCG
Profile
|
-4.54% |
3.925 |
3.746 |
0.042 |
-4.30% |
0.042 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC2
|
-4.54% |
13.765 |
13.140 |
0.000 |
-4.54% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint32_t_To_uint16_t_
|
-4.52% |
9849.981 |
9405.213 |
42.820 |
-4.80% |
42.820 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC31
|
-4.46% |
70.081 |
66.955 |
0.005 |
-4.46% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint16_t_To_uint8_t_
|
-4.40% |
2874.394 |
2748.024 |
7.071 |
-4.52% |
7.071 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC64
|
-4.35% |
43.176 |
41.297 |
0.001 |
-4.35% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC63
|
-4.35% |
43.177 |
41.300 |
0.001 |
-4.61% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint8_t_To_uint64_t_
|
-4.25% |
23471.939 |
22473.222 |
15.132 |
-4.30% |
15.132 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_ENERGY_CALC_LAMBDA/171
|
-4.25% |
14.203 |
13.600 |
0.018 |
-4.55% |
0.018 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint64_t>/999
|
-4.22% |
1811.156 |
1734.665 |
0.104 |
-4.23% |
0.104 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_cond_load_novec_int32_t_
|
-4.18% |
418429.551 |
400938.632 |
71.649 |
-2.38% |
71.649 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_PRESSURE_CALC_LAMBDA/44217
|
-4.17% |
503.440 |
482.466 |
3.842 |
-3.22% |
3.842 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint64_t>/999
|
-4.15% |
3595.224 |
3445.852 |
0.350 |
-4.14% |
0.350 |
|
SingleSource/Benchmarks/Misc/flops-5
Profile
|
-4.11% |
2.020 |
1.937 |
0.001 |
-4.15% |
0.001 |
|
MicroBenchmarks/ImageProcessing/Dilate/Dilate.test:BENCHMARK_DILATE/256
|
-4.08% |
1059.875 |
1016.607 |
3.153 |
-4.75% |
3.153 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint64_t>/256
|
-4.06% |
935.590 |
897.566 |
0.004 |
-4.06% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC31
|
-4.04% |
61.947 |
59.445 |
0.001 |
-4.04% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_ENERGY_CALC_RAW/171
|
-4.02% |
14.203 |
13.632 |
0.013 |
-4.27% |
0.013 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC32
|
-4.00% |
31.286 |
30.034 |
0.002 |
-4.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC3
|
-4.00% |
15.644 |
15.018 |
0.000 |
-4.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_only_autovec_uint8_t_
|
-4.00% |
96168.923 |
92326.491 |
5.724 |
-3.98% |
5.724 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint32_t>/65
|
-3.97% |
94.486 |
90.733 |
0.001 |
-3.97% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC32
|
-3.96% |
63.199 |
60.696 |
0.000 |
-3.96% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint32_t>/256
|
-3.96% |
221.506 |
212.739 |
0.042 |
-3.96% |
0.042 |
|
External/SPEC/CFP2017rate/519.lbm_r/519.lbm_r
Profile
|
-3.91% |
200.030 |
192.218 |
1.380 |
-4.22% |
1.380 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint64_t_To_uint32_t_
|
-3.89% |
19377.814 |
18623.180 |
37.031 |
-3.47% |
37.031 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<32, LessThanZero, None>
|
-3.86% |
4589.812 |
4412.816 |
29.219 |
0.01% |
29.219 |
|
External/SPEC/CFP2017rate/544.nab_r/544.nab_r
Profile
|
-3.81% |
476.181 |
458.018 |
0.105 |
-4.16% |
0.105 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC31
|
-3.81% |
31.225 |
30.035 |
0.000 |
-3.70% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_cond_load_autovec_int64_t_
|
-3.78% |
552434.065 |
531574.866 |
892.698 |
-3.81% |
892.698 |
|
MultiSource/Benchmarks/nbench/nbench
Profile
|
-3.70% |
6.115 |
5.888 |
0.003 |
-3.89% |
0.003 |
|
SingleSource/Benchmarks/Shootout/Shootout-matrix
Profile
|
-3.70% |
3.864 |
3.721 |
0.000 |
-3.68% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint8_t>/16
|
-3.68% |
60.014 |
57.807 |
0.258 |
7.41% |
0.258 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_nested_cond_load_novec_int32_t_
|
-3.67% |
650485.851 |
626632.756 |
63.913 |
-2.87% |
63.913 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint64_t_To_uint8_t_
|
-3.66% |
19746.494 |
19024.562 |
40.425 |
-4.12% |
40.425 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint64_t>/256
|
-3.64% |
514.380 |
495.642 |
0.013 |
-3.65% |
0.013 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<31, EqZero, First>
|
-3.64% |
3346.183 |
3224.411 |
2.562 |
-3.64% |
2.562 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC31
|
-3.62% |
60.380 |
58.193 |
0.005 |
-3.46% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC64
|
-3.60% |
69.458 |
66.955 |
0.002 |
-3.60% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC64
|
-3.60% |
69.456 |
66.953 |
0.001 |
-3.61% |
0.001 |
|
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% |
70.088 |
67.582 |
0.013 |
-3.58% |
0.013 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC63
|
-3.57% |
70.079 |
67.578 |
0.001 |
-3.57% |
0.001 |
|
MultiSource/Benchmarks/TSVC/NodeSplitting-dbl/NodeSplitting-dbl
Profile
|
-3.55% |
26.793 |
25.841 |
0.269 |
-2.17% |
0.269 |
|
MultiSource/Applications/JM/lencod/lencod
Profile
|
-3.55% |
32.770 |
31.607 |
0.038 |
-2.87% |
0.038 |
|
MultiSource/Benchmarks/Rodinia/pathfinder/pathfinder
Profile
|
-3.45% |
1.263 |
1.220 |
0.009 |
-3.04% |
0.009 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint16_t_To_uint32_t_
|
-3.42% |
11284.401 |
10898.666 |
12.483 |
-3.91% |
12.483 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC64
|
-3.36% |
111.378 |
107.631 |
0.006 |
-3.37% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint16_t_To_uint8_t_
|
-3.17% |
4514.233 |
4371.324 |
10.309 |
-3.23% |
10.309 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint16_t>/999
|
-3.15% |
514.993 |
498.753 |
0.013 |
-3.16% |
0.013 |
|
SingleSource/Benchmarks/Shootout/Shootout-lists
Profile
|
-3.15% |
11.316 |
10.960 |
0.005 |
-3.12% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1BigLoopWithReductionTC1
|
-3.13% |
20.023 |
19.397 |
0.004 |
-3.14% |
0.004 |
|
MicroBenchmarks/LCALS/SubsetBRawLoops/lcalsBRaw.test:BM_INIT3_RAW/171
|
-3.11% |
0.427 |
0.414 |
0.004 |
-0.30% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchVecWithRuntimeChecks4PointersDBeforeA/1000
|
-3.07% |
5020347.403 |
4866129.042 |
562.436 |
-3.06% |
562.436 |
|
SingleSource/Benchmarks/BenchmarkGame/puzzle
Profile
|
-3.02% |
0.876 |
0.849 |
0.003 |
-2.22% |
0.003 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<31, GreaterThanZero, Last>
|
-2.97% |
8348.528 |
8100.508 |
18.323 |
-2.35% |
18.323 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint16_t>/999
|
-2.84% |
1013.823 |
985.061 |
0.129 |
-2.84% |
0.129 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C/CoMD/CoMD
Profile
|
-2.83% |
9.906 |
9.625 |
0.002 |
-2.76% |
0.002 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_FLOYD_DITHER/256
|
-2.78% |
1794.244 |
1744.436 |
6.088 |
0.63% |
6.088 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC1
|
-2.77% |
22.526 |
21.902 |
0.001 |
-2.77% |
0.001 |
|
MultiSource/Benchmarks/FreeBench/pcompress2/pcompress2
Profile
|
-2.73% |
0.405 |
0.394 |
0.001 |
-2.61% |
0.001 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_FLOYD_DITHER/128
|
-2.70% |
437.575 |
425.759 |
1.723 |
-3.12% |
1.723 |
|
MultiSource/Benchmarks/FreeBench/mason/mason
Profile
|
-2.67% |
0.553 |
0.538 |
0.000 |
-2.72% |
0.000 |
|
SingleSource/Benchmarks/Misc-C++/oopack_v1p8
Profile
|
-2.63% |
0.480 |
0.467 |
0.000 |
-10.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC63
|
-2.61% |
120.145 |
117.012 |
0.008 |
-2.61% |
0.008 |
|
MultiSource/Benchmarks/sim/sim
Profile
|
-2.60% |
9.701 |
9.449 |
0.012 |
-2.60% |
0.012 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC31
|
-2.56% |
24.404 |
23.778 |
0.004 |
-2.56% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint8_t>/10
|
-2.56% |
48.807 |
47.560 |
0.010 |
2.47% |
0.010 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC31
|
-2.55% |
24.402 |
23.780 |
0.017 |
-2.55% |
0.017 |
|
MultiSource/Benchmarks/mafft/pairlocalalign
Profile
|
-2.54% |
94.013 |
91.629 |
0.368 |
-2.59% |
0.368 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint8_t_To_uint32_t_
|
-2.53% |
7077.629 |
6898.648 |
1.425 |
-2.52% |
1.425 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<32, EqZero, Last>
|
-2.53% |
7029.249 |
6851.640 |
24.127 |
-2.85% |
24.127 |
|
MultiSource/Benchmarks/Bullet/bullet
Profile
|
-2.51% |
30.550 |
29.784 |
0.165 |
-2.12% |
0.165 |
|
MultiSource/Benchmarks/FreeBench/fourinarow/fourinarow
Profile
|
-2.43% |
0.651 |
0.635 |
0.001 |
-2.43% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchVecWithRuntimeChecks4PointersDBeforeA/32
|
-2.42% |
166202.823 |
162185.542 |
176.558 |
-2.42% |
176.558 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_FLOYD_DITHER/512
|
-2.40% |
6648.394 |
6488.801 |
36.026 |
-2.35% |
36.026 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC63
|
-2.39% |
130.145 |
127.032 |
0.074 |
-2.41% |
0.074 |
|
MicroBenchmarks/ImageProcessing/Dilate/Dilate.test:BENCHMARK_DILATE/512
|
-2.39% |
3536.613 |
3452.047 |
12.677 |
-3.68% |
12.677 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_ENERGY_CALC_RAW/44217
|
-2.38% |
4352.425 |
4248.723 |
6.174 |
-1.91% |
6.174 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC63
|
-2.34% |
107.002 |
104.500 |
0.003 |
-2.34% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint32_t_To_uint64_t_
|
-2.28% |
26371.663 |
25771.151 |
46.689 |
-1.94% |
46.689 |
|
MultiSource/Benchmarks/TSVC/ControlLoops-flt/ControlLoops-flt
Profile
|
-2.26% |
5.492 |
5.368 |
0.032 |
-1.45% |
0.032 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_nested_cond_load_novec_uint8_t_
|
-2.24% |
504512.505 |
493208.302 |
421.857 |
-2.28% |
421.857 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_only_autovec_int64_t_
|
-2.22% |
1448879.652 |
1416727.769 |
1477.944 |
-2.09% |
1477.944 |
|
External/SPEC/CINT2017rate/531.deepsjeng_r/531.deepsjeng_r
Profile
|
-2.22% |
260.106 |
254.340 |
0.432 |
-2.22% |
0.432 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_ENERGY_CALC_LAMBDA/44217
|
-2.19% |
4340.849 |
4245.683 |
10.047 |
-1.82% |
10.047 |
|
SingleSource/Benchmarks/Misc/flops-1
Profile
|
-2.18% |
9.002 |
8.806 |
0.000 |
-2.15% |
0.000 |
|
MultiSource/Benchmarks/Olden/health/health
Profile
|
-2.16% |
1.595 |
1.560 |
0.004 |
-1.95% |
0.004 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<6, GreaterThanZero, None>
|
-2.11% |
29720.398 |
29092.166 |
14.041 |
-1.64% |
14.041 |
|
SingleSource/Benchmarks/Misc-C++/Large/ray
Profile
|
-2.10% |
12.104 |
11.849 |
0.002 |
-2.08% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC128
|
-2.10% |
119.523 |
117.013 |
0.726 |
-2.10% |
0.726 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC128
|
-2.09% |
119.509 |
117.006 |
0.005 |
-2.10% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC127
|
-2.09% |
120.145 |
117.635 |
0.003 |
-2.09% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC127
|
-2.08% |
120.137 |
117.633 |
0.009 |
-2.09% |
0.009 |
|
SingleSource/Benchmarks/Misc/ReedSolomon
Profile
|
-2.07% |
20.819 |
20.389 |
0.001 |
-1.96% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_EOS_RAW/171
|
-2.00% |
0.873 |
0.855 |
0.001 |
-1.80% |
0.001 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<16, LessThanZero, Mid>
|
-1.93% |
8665.014 |
8497.531 |
4.937 |
-1.88% |
4.937 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C/SimpleMOC/SimpleMOC
Profile
|
-1.90% |
10.430 |
10.232 |
0.031 |
-1.67% |
0.031 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_INT_PREDICT_LAMBDA/171
|
-1.89% |
6.925 |
6.795 |
0.009 |
-1.88% |
0.009 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint16_t>/256
|
-1.84% |
272.837 |
267.812 |
0.024 |
-1.84% |
0.024 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<16, EqZero, Mid>
|
-1.82% |
8656.606 |
8499.283 |
0.614 |
-1.82% |
0.614 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint8_t>/28
|
-1.78% |
124.708 |
122.490 |
0.072 |
18.81% |
0.072 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC128
|
-1.77% |
211.489 |
207.751 |
1.019 |
-1.78% |
1.019 |
|
MultiSource/Applications/sgefa/sgefa
Profile
|
-1.76% |
0.577 |
0.566 |
0.001 |
-1.25% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_EOS_LAMBDA/171
|
-1.74% |
0.871 |
0.856 |
0.001 |
-1.65% |
0.001 |
|
MicroBenchmarks/ImageProcessing/Blur/blur.test:BENCHMARK_boxBlurKernel/512
|
-1.73% |
6634.814 |
6520.275 |
9.950 |
-1.41% |
9.950 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<32, LessThanZero, Mid>
|
-1.71% |
4570.941 |
4492.995 |
6.231 |
-1.71% |
6.231 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint64_t>/51
|
-1.69% |
148.299 |
145.792 |
0.009 |
-1.70% |
0.009 |
|
MultiSource/Benchmarks/VersaBench/ecbdes/ecbdes
Profile
|
-1.66% |
5.141 |
5.056 |
0.001 |
-1.63% |
0.001 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, LessThanZero, None>
|
-1.65% |
37670.557 |
37047.640 |
28.319 |
-1.41% |
28.319 |
|
MicroBenchmarks/ImageProcessing/Blur/blur.test:BENCHMARK_boxBlurKernel/128
|
-1.63% |
426.091 |
419.148 |
2.382 |
-3.48% |
2.382 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_INT_PREDICT_RAW/171
|
-1.61% |
6.917 |
6.806 |
0.011 |
-1.71% |
0.011 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint16_t_To_uint32_t_
|
-1.58% |
13515.400 |
13301.802 |
19.120 |
-1.35% |
19.120 |
|
External/SPEC/CFP2017rate/511.povray_r/511.povray_r
Profile
|
-1.58% |
33.990 |
33.454 |
0.061 |
-0.98% |
0.061 |
|
SingleSource/Benchmarks/Misc/mandel-2
Profile
|
-1.56% |
2.536 |
2.496 |
0.000 |
-1.55% |
0.000 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<6, LessThanZero, Mid>
|
-1.55% |
23861.210 |
23491.283 |
6.674 |
-0.32% |
6.674 |
|
MultiSource/Benchmarks/Fhourstones-3.1/fhourstones3.1
Profile
|
-1.50% |
3.972 |
3.912 |
0.005 |
-1.50% |
0.005 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, GreaterThanZero, None>
|
-1.49% |
37059.294 |
36506.197 |
1.428 |
-1.80% |
1.428 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_csa_with_in_loop_arith_novec_int64_t_
|
-1.49% |
1028012.557 |
1012701.996 |
169.121 |
-1.50% |
169.121 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC64
|
-1.44% |
86.344 |
85.102 |
0.168 |
-1.45% |
0.168 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC127
|
-1.42% |
220.262 |
217.132 |
0.021 |
-1.43% |
0.021 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint64_t>/51
|
-1.36% |
229.010 |
225.892 |
0.014 |
-1.36% |
0.014 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<8, LessThanZero, Mid>
|
-1.30% |
19488.931 |
19235.209 |
1.545 |
-1.03% |
1.545 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC127
|
-1.28% |
197.110 |
194.593 |
0.013 |
-1.27% |
0.013 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC128
|
-1.26% |
198.364 |
195.858 |
0.010 |
-1.27% |
0.010 |
|
External/SPEC/CINT2017rate/525.x264_r/525.x264_r
Profile
|
-1.23% |
129.916 |
128.318 |
0.147 |
-0.87% |
0.147 |
|
MultiSource/Applications/obsequi/Obsequi
Profile
|
-1.20% |
7.685 |
7.592 |
0.011 |
-0.90% |
0.011 |
|
MultiSource/Benchmarks/MallocBench/cfrac/cfrac
Profile
|
-1.20% |
2.780 |
2.747 |
0.005 |
-1.20% |
0.005 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<32, GreaterThanZero, Mid>
|
-1.17% |
4549.056 |
4495.995 |
1.135 |
-1.31% |
1.135 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<7, EqZero, None>
|
-1.16% |
27187.833 |
26872.709 |
11.699 |
-1.13% |
11.699 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_sinhf_novec_float_
|
-1.14% |
2242.536 |
2216.947 |
0.587 |
-1.11% |
0.587 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<64, LessThanZero, Last>
|
-1.13% |
4180.019 |
4132.786 |
1.760 |
-0.91% |
1.760 |
|
SingleSource/Benchmarks/SmallPT/smallpt
Profile
|
-1.12% |
30.041 |
29.705 |
0.001 |
-1.08% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC2
|
-1.12% |
13.289 |
13.141 |
0.001 |
-0.10% |
0.001 |
|
MultiSource/Benchmarks/ASC_Sequoia/AMGmk/AMGmk
Profile
|
-1.10% |
33.169 |
32.806 |
0.018 |
-0.76% |
0.018 |
|
MultiSource/Applications/hexxagon/hexxagon
Profile
|
-1.08% |
14.890 |
14.730 |
0.003 |
0.83% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_sinhf_autovec_float_
|
-1.06% |
2241.545 |
2217.701 |
0.583 |
-1.11% |
0.583 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopFrom_uint64_t_To_uint16_t_
|
-1.06% |
14805.475 |
14648.823 |
17.199 |
-1.26% |
17.199 |
|
MultiSource/Benchmarks/llubenchmark/llu
Profile
|
-1.02% |
55.793 |
55.222 |
0.099 |
-0.35% |
0.099 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_sinh_novec_double_
|
-1.02% |
2470.245 |
2445.044 |
1.878 |
-1.17% |
1.878 |