|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_INT_PREDICT_RAW/44217
|
-58.96% |
19498.200 |
8001.891 |
82.692 |
-11.57% |
82.692 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint64_t_To_uint32_t_
|
-52.30% |
35370.805 |
16870.393 |
472.676 |
-52.23% |
472.676 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint64_t_To_uint16_t_
|
-51.11% |
35885.805 |
17545.855 |
243.657 |
-50.82% |
243.657 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint64_t_To_uint8_t_
|
-49.94% |
37268.712 |
18658.083 |
46.793 |
-49.66% |
46.793 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_HYDRO_2D_RAW/44217
|
-44.57% |
91931.035 |
50960.327 |
2739.869 |
-39.80% |
2739.869 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_DIFF_PREDICT_RAW/44217
|
-44.27% |
24163.937 |
13466.394 |
293.213 |
-42.20% |
293.213 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint16_t_To_uint64_t_
|
-43.92% |
18636.547 |
10450.801 |
44.165 |
-44.04% |
44.165 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIRST_DIFF_RAW/44217
|
-43.70% |
180.150 |
101.426 |
0.798 |
-28.82% |
0.798 |
|
MultiSource/Benchmarks/MiBench/automotive-bitcount/automotive-bitcount
Profile
|
-43.33% |
0.178 |
0.101 |
0.001 |
-18.48% |
0.001 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C/miniGMG/miniGMG
Profile
|
-43.11% |
8.138 |
4.629 |
0.102 |
-49.63% |
0.102 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_DIFF_PREDICT_LAMBDA/44217
|
-42.34% |
23344.556 |
13461.436 |
344.032 |
-41.73% |
344.032 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint8_t_To_uint64_t_
|
-41.13% |
17844.864 |
10505.407 |
11.488 |
-40.98% |
11.488 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_DIFF_PREDICT_LAMBDA/5001
|
-40.97% |
2568.225 |
1515.927 |
35.524 |
-39.59% |
35.524 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_DIFF_PREDICT_RAW/5001
|
-40.84% |
2556.339 |
1512.415 |
10.438 |
-41.26% |
10.438 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint64_t_To_uint32_t_
|
-40.80% |
38198.606 |
22612.009 |
31.030 |
-40.74% |
31.030 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint32_t_To_uint64_t_
|
-39.26% |
22680.753 |
13776.022 |
211.491 |
-39.38% |
211.491 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/32
|
-36.70% |
1396.250 |
883.760 |
0.033 |
-36.70% |
0.033 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/64
|
-36.68% |
6183.016 |
3915.304 |
2.658 |
-36.67% |
2.658 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/16
|
-36.64% |
279.542 |
177.104 |
0.013 |
-36.63% |
0.013 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/256
|
-36.23% |
107114.208 |
68303.900 |
52.994 |
-36.26% |
52.994 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/128
|
-36.09% |
26265.253 |
16785.543 |
3.463 |
-36.11% |
3.463 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_HYDRO_2D_RAW/5001
|
-36.07% |
9281.142 |
5933.682 |
171.151 |
-32.54% |
171.151 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint64_t_To_uint16_t_
|
-34.76% |
29347.015 |
19147.027 |
6.019 |
-33.86% |
6.019 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint64_t_To_uint8_t_
|
-34.65% |
30245.862 |
19765.493 |
37.953 |
-34.36% |
37.953 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIRST_DIFF_LAMBDA/44217
|
-29.35% |
143.413 |
101.316 |
0.914 |
-30.04% |
0.914 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint64_t_To_uint16_t_
|
-28.68% |
25912.810 |
18480.683 |
55.765 |
-28.64% |
55.765 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_DISC_ORD_RAW/44217
|
-28.64% |
14066.410 |
10037.468 |
660.155 |
-24.76% |
660.155 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint32_t_To_uint8_t_
|
-28.09% |
13507.526 |
9712.814 |
19.244 |
-27.89% |
19.244 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_PIC_2D_LAMBDA/44217
|
-27.75% |
11957.547 |
8639.664 |
574.667 |
-21.19% |
574.667 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC128
|
-27.27% |
560.255 |
407.458 |
0.031 |
-26.92% |
0.031 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_PIC_2D_RAW/44217
|
-27.27% |
11895.579 |
8651.472 |
37.068 |
-22.87% |
37.068 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC128
|
-27.05% |
1296.455 |
945.742 |
5.115 |
-26.85% |
5.115 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC32
|
-26.52% |
335.428 |
246.485 |
1.662 |
-26.19% |
1.662 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC64
|
-26.44% |
656.177 |
482.684 |
2.703 |
-26.15% |
2.703 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC16
|
-26.14% |
174.887 |
129.180 |
1.061 |
-25.67% |
1.061 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC64
|
-26.04% |
293.603 |
217.157 |
0.075 |
-25.59% |
0.075 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIRST_SUM_RAW/44217
|
-25.15% |
181.902 |
136.149 |
0.233 |
-18.15% |
0.233 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint64_t_To_uint8_t_
|
-24.70% |
27167.649 |
20458.302 |
33.104 |
-24.85% |
33.104 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC32
|
-23.88% |
160.334 |
122.046 |
0.042 |
-23.18% |
0.042 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC128
|
-22.95% |
602.720 |
464.379 |
0.057 |
-23.11% |
0.057 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC128
|
-22.94% |
602.671 |
464.396 |
0.008 |
-23.11% |
0.008 |
|
MicroBenchmarks/ImageProcessing/Blur/blur.test:BENCHMARK_boxBlurKernel/1024
|
-22.78% |
30089.516 |
23235.462 |
71.332 |
-22.93% |
71.332 |
|
SingleSource/Benchmarks/Adobe-C++/loop_unroll
Profile
|
-22.74% |
3.105 |
2.399 |
0.001 |
-22.79% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint16_t_To_uint64_t_
|
-22.40% |
13358.486 |
10365.916 |
2.631 |
-21.52% |
2.631 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC127
|
-21.91% |
614.588 |
479.962 |
0.020 |
-21.98% |
0.020 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC127
|
-21.90% |
614.581 |
480.004 |
0.051 |
-21.98% |
0.051 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC64
|
-21.85% |
312.264 |
244.024 |
0.164 |
-22.16% |
0.164 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC64
|
-21.84% |
312.232 |
244.026 |
0.017 |
-22.16% |
0.017 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_PIC_2D_RAW/5001
|
-21.84% |
1190.909 |
930.838 |
26.760 |
-13.68% |
26.760 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint8_t_To_uint32_t_
|
-21.76% |
6603.217 |
5166.157 |
3.708 |
-21.51% |
3.708 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint16_t_To_uint32_t_
|
-21.56% |
7107.647 |
5574.970 |
4.002 |
-21.49% |
4.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC4
|
-21.43% |
17.521 |
13.766 |
0.001 |
-21.43% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_only_autovec_uint8_t_
|
-21.38% |
182340.283 |
143364.250 |
45.395 |
-21.38% |
45.395 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIND_FIRST_MIN_LAMBDA/171
|
-21.27% |
1.501 |
1.181 |
0.000 |
-21.28% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIND_FIRST_MIN_LAMBDA/44217
|
-21.17% |
389.462 |
307.011 |
0.203 |
-21.19% |
0.203 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIND_FIRST_MIN_LAMBDA/5001
|
-20.90% |
45.207 |
35.761 |
0.173 |
-20.98% |
0.173 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC16
|
-20.40% |
93.661 |
74.555 |
0.017 |
-19.21% |
0.017 |
|
MultiSource/Benchmarks/Trimaran/enc-pc1/enc-pc1
Profile
|
-19.95% |
1.130 |
0.904 |
0.000 |
-18.11% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC63
|
-19.89% |
324.159 |
259.669 |
0.011 |
-20.05% |
0.011 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC63
|
-19.89% |
324.151 |
259.676 |
0.005 |
-20.05% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC127
|
-19.87% |
642.314 |
514.667 |
0.069 |
-19.65% |
0.069 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC32
|
-19.86% |
167.083 |
133.898 |
0.010 |
-20.46% |
0.010 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC32
|
-19.86% |
167.076 |
133.902 |
0.009 |
-20.45% |
0.009 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint8_t_To_uint64_t_
|
-19.80% |
13589.395 |
10898.561 |
13.595 |
-16.58% |
13.595 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC128
|
-19.73% |
274.691 |
220.503 |
0.740 |
-19.74% |
0.740 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC128
|
-19.70% |
569.500 |
457.287 |
6.743 |
-19.86% |
6.743 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC127
|
-19.43% |
275.058 |
221.623 |
1.305 |
-19.54% |
1.305 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC16
|
-19.35% |
97.759 |
78.840 |
0.007 |
-17.65% |
0.007 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint32_t_To_uint8_t_
|
-19.23% |
13904.868 |
11230.853 |
71.130 |
-19.21% |
71.130 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint16_t_To_uint8_t_
|
-19.06% |
3817.037 |
3089.489 |
0.041 |
-19.08% |
0.041 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_PIC_1D_RAW/44217
|
-18.93% |
13620.777 |
11042.360 |
81.481 |
-18.38% |
81.481 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC8
|
-18.92% |
23.151 |
18.771 |
0.178 |
-18.93% |
0.178 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_VOL3D_CALC_RAW/2
|
-18.81% |
8.757 |
7.111 |
0.000 |
-18.80% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_VOL3D_CALC_LAMBDA/2
|
-18.80% |
8.757 |
7.111 |
0.001 |
-18.80% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC32
|
-18.75% |
160.190 |
130.150 |
1.630 |
-19.36% |
1.630 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, EqZero, None>
|
-18.75% |
20512.115 |
16666.357 |
1.292 |
-18.75% |
1.292 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint32_t_To_uint16_t_
|
-18.65% |
13803.567 |
11229.559 |
8.018 |
-18.67% |
8.018 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint64_t_To_uint32_t_
|
-18.64% |
27099.460 |
22049.467 |
32.152 |
-18.49% |
32.152 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC64
|
-18.37% |
148.762 |
121.431 |
3.318 |
-18.30% |
3.318 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC64
|
-18.20% |
296.619 |
242.628 |
1.684 |
-18.50% |
1.684 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, EqZero, Last>
|
-18.17% |
14102.855 |
11540.724 |
0.651 |
-18.18% |
0.651 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_with_cond_arith_novec_uint8_t_
|
-17.85% |
746047.260 |
612854.255 |
62.198 |
-17.82% |
62.198 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIRST_SUM_LAMBDA/44217
|
-17.58% |
163.820 |
135.015 |
0.685 |
-19.19% |
0.685 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_with_cond_arith_novec_int32_t_
|
-17.55% |
740626.275 |
610639.203 |
1187.788 |
-17.50% |
1187.788 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_INT_PREDICT_RAW/5001
|
-17.32% |
1101.576 |
910.758 |
4.211 |
-0.29% |
4.211 |
|
MultiSource/Benchmarks/MiBench/security-rijndael/security-rijndael
Profile
|
-17.21% |
0.335 |
0.277 |
0.000 |
-17.14% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC16
|
-17.11% |
91.987 |
76.244 |
0.488 |
-18.13% |
0.488 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC16
|
-16.55% |
94.481 |
78.842 |
0.003 |
-17.65% |
0.003 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_PIC_2D_LAMBDA/5001
|
-16.50% |
1123.433 |
938.057 |
24.685 |
-15.15% |
24.685 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC31
|
-16.47% |
179.037 |
149.548 |
0.003 |
-16.72% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC31
|
-16.44% |
178.953 |
149.541 |
0.008 |
-16.73% |
0.008 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_VOL3D_CALC_RAW/0
|
-16.35% |
1269.511 |
1061.966 |
1.765 |
-16.06% |
1.765 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_VOL3D_CALC_LAMBDA/0
|
-16.26% |
1267.830 |
1061.741 |
2.020 |
-16.24% |
2.020 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_HYDRO_1D_RAW/171
|
-16.20% |
0.444 |
0.372 |
0.000 |
-15.84% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_VOL3D_CALC_LAMBDA/1
|
-16.14% |
260.235 |
218.223 |
0.007 |
-16.12% |
0.007 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_VOL3D_CALC_RAW/1
|
-16.14% |
260.058 |
218.092 |
0.081 |
-16.16% |
0.081 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC8
|
-15.86% |
57.572 |
48.443 |
0.319 |
-17.56% |
0.319 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC8
|
-15.78% |
23.778 |
20.024 |
0.002 |
-15.79% |
0.002 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_HYDRO_1D_LAMBDA/171
|
-15.77% |
0.441 |
0.372 |
0.000 |
-15.88% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint16_t_To_uint32_t_
|
-15.65% |
7463.468 |
6295.133 |
1.115 |
-15.64% |
1.115 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint64_t_To_uint8_t_
|
-15.64% |
22075.327 |
18621.790 |
39.278 |
-15.54% |
39.278 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC127
|
-15.40% |
605.137 |
511.955 |
1.538 |
-15.49% |
1.538 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_no_runtime_checks_needed<16, int>
|
-15.39% |
24.405 |
20.648 |
0.001 |
-15.39% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint32_t_To_uint8_t_
|
-15.18% |
10639.533 |
9024.249 |
21.876 |
-14.83% |
21.876 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC16
|
-15.09% |
33.163 |
28.159 |
0.588 |
-15.09% |
0.588 |
|
MicroBenchmarks/ImageProcessing/Dilate/Dilate.test:BENCHMARK_DILATE/1024
|
-14.64% |
7538.515 |
6434.585 |
151.040 |
-9.51% |
151.040 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC128
|
-14.47% |
1102.119 |
942.646 |
0.217 |
-14.56% |
0.217 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC64
|
-14.36% |
561.280 |
480.706 |
0.799 |
-14.51% |
0.799 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC127
|
-14.34% |
1094.448 |
937.458 |
0.041 |
-14.41% |
0.041 |
|
SingleSource/Benchmarks/Misc/salsa20
Profile
|
-14.14% |
15.387 |
13.211 |
0.001 |
-14.12% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint32_t_To_uint16_t_
|
-14.13% |
12809.477 |
10999.049 |
21.477 |
-14.32% |
21.477 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC32
|
-14.02% |
290.965 |
250.181 |
0.939 |
-14.32% |
0.939 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint8_t_To_uint16_t_
|
-14.00% |
3757.063 |
3230.899 |
2.198 |
-13.99% |
2.198 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC63
|
-14.00% |
553.822 |
476.275 |
0.248 |
-14.14% |
0.248 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_with_cond_arith_autovec_int64_t_
|
-13.96% |
790680.850 |
680302.723 |
1564.599 |
-14.06% |
1564.599 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC3
|
-13.86% |
51.936 |
44.738 |
0.001 |
-13.86% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC8
|
-13.86% |
51.937 |
44.739 |
0.003 |
-13.86% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC4
|
-13.86% |
51.934 |
44.737 |
0.002 |
-13.86% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC1
|
-13.86% |
51.935 |
44.739 |
0.001 |
-13.85% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC2
|
-13.86% |
51.934 |
44.738 |
0.004 |
-13.86% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC7
|
-13.85% |
51.932 |
44.739 |
0.007 |
-13.85% |
0.007 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_with_cond_arith_novec_int64_t_
|
-13.82% |
789940.427 |
680735.014 |
1181.062 |
-13.62% |
1181.062 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC63
|
-13.73% |
376.003 |
324.372 |
0.049 |
-13.37% |
0.049 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_INT_PREDICT_LAMBDA/44217
|
-13.73% |
9244.557 |
7975.331 |
90.006 |
-4.35% |
90.006 |
|
External/SPEC/CFP2017rate/508.namd_r/508.namd_r
Profile
|
-13.66% |
223.259 |
192.772 |
0.850 |
-13.78% |
0.850 |
|
MultiSource/Benchmarks/TSVC/CrossingThresholds-flt/CrossingThresholds-flt
Profile
|
-13.59% |
10.735 |
9.276 |
0.082 |
-13.81% |
0.082 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC31
|
-13.52% |
87.188 |
75.402 |
0.472 |
-12.44% |
0.472 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint32_t_To_uint8_t_
|
-13.46% |
11038.766 |
9553.294 |
45.139 |
-14.16% |
45.139 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC31
|
-13.35% |
283.450 |
245.604 |
0.439 |
-13.55% |
0.439 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint64_t_To_uint16_t_
|
-13.26% |
18844.789 |
16346.554 |
423.941 |
-13.89% |
423.941 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC128
|
-13.08% |
81.348 |
70.707 |
0.002 |
-13.08% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint8_t_To_uint16_t_
|
-12.94% |
4541.556 |
3953.811 |
0.206 |
-12.95% |
0.206 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC63
|
-12.77% |
332.272 |
289.840 |
0.096 |
-12.91% |
0.096 |
|
SingleSource/Benchmarks/Shootout-C++/Shootout-C++-matrix
Profile
|
-12.72% |
2.509 |
2.190 |
0.000 |
-12.69% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIRST_SUM_RAW/5001
|
-12.64% |
20.270 |
17.707 |
0.241 |
2.08% |
0.241 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint16_t_To_uint8_t_
|
-12.41% |
4744.065 |
4155.178 |
0.122 |
-12.39% |
0.122 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC16
|
-12.24% |
155.810 |
136.744 |
0.135 |
-12.88% |
0.135 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC15
|
-12.16% |
51.936 |
45.619 |
0.169 |
-12.17% |
0.169 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC16
|
-12.03% |
51.934 |
45.684 |
0.144 |
-12.05% |
0.144 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, EqZero, None>
|
-12.01% |
16026.418 |
14101.611 |
0.868 |
-11.99% |
0.868 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC8
|
-11.83% |
58.194 |
51.308 |
0.003 |
-13.70% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC8
|
-11.82% |
58.190 |
51.310 |
0.003 |
-13.69% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC2
|
-11.76% |
21.275 |
18.772 |
0.001 |
-11.77% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC15
|
-11.64% |
148.293 |
131.026 |
0.180 |
-11.95% |
0.180 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint32_t_To_uint16_t_
|
-11.39% |
10900.266 |
9658.666 |
172.211 |
-10.05% |
172.211 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC15
|
-11.18% |
106.372 |
94.481 |
0.004 |
-11.71% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC15
|
-11.18% |
106.370 |
94.480 |
0.008 |
-11.70% |
0.008 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC4
|
-11.12% |
22.526 |
20.022 |
0.001 |
-11.12% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC3
|
-11.11% |
22.526 |
20.023 |
0.000 |
-11.11% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC4
|
-11.11% |
22.526 |
20.024 |
0.002 |
-11.11% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC63
|
-11.10% |
150.116 |
133.456 |
1.692 |
-10.98% |
1.692 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint8_t>/51
|
-11.08% |
123.886 |
110.155 |
0.127 |
19.08% |
0.127 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC32
|
-10.80% |
85.281 |
76.071 |
0.115 |
-10.85% |
0.115 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC4
|
-10.71% |
112.945 |
100.845 |
1.304 |
-10.83% |
1.304 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_BAND_LIN_EQ_RAW/171
|
-10.61% |
0.384 |
0.343 |
0.000 |
-6.33% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_BAND_LIN_EQ_LAMBDA/171
|
-10.60% |
0.384 |
0.343 |
0.000 |
-6.33% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC4
|
-10.53% |
23.777 |
21.274 |
0.001 |
-10.53% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_HYDRO_1D_LAMBDA/5001
|
-10.51% |
16.857 |
15.085 |
0.663 |
-12.16% |
0.663 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC64
|
-10.47% |
53.813 |
48.180 |
0.002 |
-10.47% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC16
|
-10.35% |
36.293 |
32.538 |
0.001 |
-10.35% |
0.001 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/16
|
-10.17% |
115.466 |
103.727 |
0.008 |
-10.17% |
0.008 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/64
|
-10.07% |
1914.575 |
1721.833 |
3.281 |
-10.01% |
3.281 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint8_t_To_uint16_t_
|
-10.07% |
5846.300 |
5257.787 |
4.458 |
-10.13% |
4.458 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint32_t_To_uint64_t_
|
-10.05% |
17028.100 |
15317.307 |
136.381 |
-10.93% |
136.381 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/32
|
-10.00% |
473.015 |
425.727 |
0.009 |
-10.00% |
0.009 |
|
MultiSource/Benchmarks/TSVC/CrossingThresholds-dbl/CrossingThresholds-dbl
Profile
|
-9.90% |
26.872 |
24.212 |
1.023 |
-0.82% |
1.023 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/256
|
-9.90% |
31449.398 |
28335.785 |
13.176 |
-9.90% |
13.176 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC16
|
-9.80% |
31.912 |
28.784 |
0.009 |
-8.01% |
0.009 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC8
|
-9.76% |
25.656 |
23.152 |
0.000 |
-9.76% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC8
|
-9.76% |
25.654 |
23.151 |
0.002 |
-9.77% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_cond_load_novec_int32_t_
|
-9.76% |
443827.896 |
400532.325 |
729.620 |
-2.48% |
729.620 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/128
|
-9.72% |
7907.678 |
7138.832 |
4.897 |
-9.83% |
4.897 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_only_autovec_int64_t_
|
-9.65% |
333574.887 |
301397.053 |
60.522 |
-9.57% |
60.522 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC7
|
-9.62% |
32.538 |
29.409 |
0.001 |
-9.62% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC7
|
-9.53% |
26.281 |
23.777 |
0.001 |
-9.53% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC1
|
-9.52% |
13.140 |
11.889 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC31
|
-9.46% |
195.877 |
177.344 |
0.018 |
-9.74% |
0.018 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_DIFF_PREDICT_RAW/171
|
-9.45% |
12.266 |
11.107 |
0.051 |
-6.92% |
0.051 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC7
|
-9.41% |
26.279 |
23.806 |
0.025 |
-9.42% |
0.025 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC8
|
-9.34% |
88.230 |
79.988 |
0.049 |
-10.53% |
0.049 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC127
|
-9.26% |
101.367 |
91.979 |
0.003 |
-9.72% |
0.003 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_DEL_DOT_VEC_2D_RAW/1
|
-9.21% |
287.091 |
260.644 |
0.102 |
-9.18% |
0.102 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_DEL_DOT_VEC_2D_LAMBDA/1
|
-9.21% |
287.025 |
260.593 |
0.020 |
-9.24% |
0.020 |
|
MultiSource/Benchmarks/McCat/12-IOtest/iotest
Profile
|
-9.09% |
1.844 |
1.676 |
0.030 |
-8.13% |
0.030 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint64_t_To_uint32_t_
|
-9.06% |
18140.473 |
16496.867 |
210.133 |
-7.39% |
210.133 |
|
MultiSource/Benchmarks/FreeBench/pifft/pifft
Profile
|
-9.04% |
0.359 |
0.327 |
0.001 |
-8.82% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC32
|
-9.02% |
53.188 |
48.392 |
0.003 |
-9.03% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC7
|
-8.88% |
28.156 |
25.656 |
0.002 |
-8.89% |
0.002 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_runtime_checks_fail<4, int>
|
-8.87% |
16.823 |
15.330 |
0.000 |
-3.64% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_INT_PREDICT_LAMBDA/5001
|
-8.77% |
1001.036 |
913.227 |
2.605 |
0.94% |
2.605 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC7
|
-8.74% |
80.720 |
73.666 |
0.079 |
-9.40% |
0.079 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_DEL_DOT_VEC_2D_RAW/2
|
-8.71% |
3.510 |
3.204 |
0.000 |
-8.70% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_DEL_DOT_VEC_2D_LAMBDA/2
|
-8.70% |
3.510 |
3.204 |
0.000 |
-8.70% |
0.000 |
|
SingleSource/Benchmarks/Misc/richards_benchmark
Profile
|
-8.62% |
2.201 |
2.011 |
0.011 |
2.96% |
0.011 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint16_t_To_uint8_t_
|
-8.55% |
6811.513 |
6229.333 |
21.275 |
-8.60% |
21.275 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC8
|
-8.51% |
29.410 |
26.907 |
0.001 |
-8.52% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_HYDRO_2D_LAMBDA/171
|
-8.51% |
88.902 |
81.339 |
0.901 |
-8.26% |
0.901 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIRST_DIFF_RAW/5001
|
-8.12% |
12.920 |
11.871 |
0.275 |
-1.53% |
0.275 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC64
|
-8.05% |
93.231 |
85.726 |
0.005 |
-8.06% |
0.005 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_DEL_DOT_VEC_2D_RAW/0
|
-7.93% |
1802.090 |
1659.235 |
4.155 |
-7.86% |
4.155 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint8_t_To_uint32_t_
|
-7.91% |
12777.773 |
11767.386 |
7.193 |
-7.91% |
7.193 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_HYDRO_2D_RAW/171
|
-7.86% |
88.771 |
81.791 |
0.203 |
-7.71% |
0.203 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC16
|
-7.85% |
31.913 |
29.409 |
0.004 |
-7.84% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC16
|
-7.85% |
31.912 |
29.409 |
0.002 |
-7.85% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC32
|
-7.81% |
40.044 |
36.918 |
0.003 |
-7.82% |
0.003 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C++/miniFE/miniFE
Profile
|
-7.77% |
16.037 |
14.790 |
0.070 |
-7.38% |
0.070 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC15
|
-7.69% |
32.537 |
30.035 |
0.002 |
-7.69% |
0.002 |
|
MultiSource/Applications/lambda-0.1.3/lambda
Profile
|
-7.69% |
15.948 |
14.722 |
0.010 |
-7.23% |
0.010 |
|
MultiSource/Benchmarks/VersaBench/beamformer/beamformer
Profile
|
-7.66% |
5.202 |
4.804 |
0.001 |
-7.63% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC15
|
-7.62% |
54.441 |
50.295 |
0.006 |
-7.62% |
0.006 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_PRESSURE_CALC_RAW/44217
|
-7.56% |
507.656 |
469.283 |
6.303 |
-6.55% |
6.303 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC31
|
-7.55% |
74.459 |
68.836 |
0.003 |
-7.56% |
0.003 |
|
MultiSource/Benchmarks/Trimaran/enc-md5/enc-md5
Profile
|
-7.54% |
3.507 |
3.243 |
0.000 |
-7.50% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_DIFF_PREDICT_LAMBDA/171
|
-7.49% |
12.011 |
11.111 |
0.036 |
-7.30% |
0.036 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_DISC_ORD_RAW/5001
|
-7.43% |
638.702 |
591.233 |
11.943 |
-11.06% |
11.943 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_DEL_DOT_VEC_2D_LAMBDA/0
|
-7.42% |
1794.868 |
1661.680 |
1.182 |
-7.27% |
1.182 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC2
|
-7.41% |
16.895 |
15.643 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_xor_no_runtime_checks_needed<16, int>
|
-7.41% |
16.895 |
15.643 |
0.001 |
-7.41% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint16_t_To_uint64_t_
|
-7.36% |
20219.236 |
18730.119 |
108.898 |
-7.01% |
108.898 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint16_t_To_uint64_t_
|
-7.35% |
25071.673 |
23229.290 |
29.932 |
-7.03% |
29.932 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC128
|
-7.23% |
173.334 |
160.807 |
0.006 |
-7.22% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint8_t>/127
|
-7.20% |
138.908 |
128.905 |
0.008 |
-7.20% |
0.008 |
|
SingleSource/Benchmarks/Stanford/Puzzle
Profile
|
-7.15% |
0.247 |
0.230 |
0.004 |
-4.81% |
0.004 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIND_FIRST_MIN_RAW/171
|
-7.15% |
1.497 |
1.390 |
0.000 |
-7.15% |
0.000 |
|
SingleSource/Benchmarks/Misc/pi
Profile
|
-7.03% |
1.783 |
1.657 |
0.000 |
-7.02% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC63
|
-6.98% |
114.515 |
106.528 |
0.015 |
-6.97% |
0.015 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC15
|
-6.94% |
45.051 |
41.923 |
0.001 |
-6.94% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC4
|
-6.86% |
54.419 |
50.683 |
0.002 |
-8.95% |
0.002 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_PRESSURE_CALC_LAMBDA/5001
|
-6.84% |
44.267 |
41.241 |
0.811 |
-6.21% |
0.811 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopWithReductionTC127
|
-6.83% |
87.602 |
81.618 |
0.256 |
1.10% |
0.256 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_runtime_checks_pass<4, int>
|
-6.66% |
16.423 |
15.329 |
0.001 |
-8.25% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC127
|
-6.66% |
194.614 |
181.656 |
0.191 |
-6.66% |
0.191 |
|
SingleSource/Benchmarks/Misc/flops-6
Profile
|
-6.56% |
1.312 |
1.226 |
0.000 |
-6.55% |
0.000 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_xor_runtime_checks_fail<16, int>
|
-6.52% |
28.785 |
26.907 |
0.001 |
-6.52% |
0.001 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_xor_runtime_checks_pass<16, int>
|
-6.52% |
28.783 |
26.906 |
0.001 |
-6.52% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC127
|
-6.43% |
68.207 |
63.824 |
0.001 |
-6.54% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC128
|
-6.42% |
68.204 |
63.822 |
0.005 |
-7.24% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_only_autovec_int32_t_
|
-6.41% |
180978.536 |
169371.564 |
508.952 |
-6.49% |
508.952 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC15
|
-6.35% |
39.420 |
36.917 |
0.001 |
-6.36% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint16_t>/127
|
-6.31% |
138.921 |
130.150 |
0.004 |
-6.31% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopWithReductionTC128
|
-6.31% |
77.588 |
72.693 |
1.074 |
1.01% |
1.074 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC4
|
-6.25% |
40.044 |
37.542 |
0.003 |
-9.10% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC4
|
-6.25% |
40.046 |
37.545 |
0.000 |
-9.09% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIND_FIRST_MIN_RAW/5001
|
-6.22% |
45.232 |
42.420 |
0.081 |
-6.44% |
0.081 |
|
SingleSource/Benchmarks/Misc-C++/Large/sphereflake
Profile
|
-6.19% |
20.013 |
18.773 |
0.001 |
-6.15% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC16
|
-6.15% |
40.671 |
38.170 |
0.001 |
-6.16% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint32_t_To_uint64_t_
|
-6.15% |
21519.403 |
20196.369 |
55.839 |
-5.85% |
55.839 |
|
SingleSource/Benchmarks/Misc/oourafft
Profile
|
-6.13% |
15.394 |
14.450 |
0.039 |
-4.26% |
0.039 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC32
|
-6.13% |
61.323 |
57.565 |
0.003 |
-6.13% |
0.003 |
|
External/SPEC/CFP2017rate/538.imagick_r/538.imagick_r
Profile
|
-6.11% |
292.246 |
274.381 |
0.334 |
-6.06% |
0.334 |
|
SingleSource/Benchmarks/Misc/perlin
Profile
|
-5.99% |
6.600 |
6.205 |
0.000 |
-5.97% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC63
|
-5.93% |
73.834 |
69.453 |
0.003 |
-6.43% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint8_t>/65
|
-5.92% |
95.120 |
89.491 |
0.003 |
-5.91% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC3
|
-5.88% |
21.274 |
20.024 |
0.000 |
-0.01% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1LoopWithReductionTC4
|
-5.72% |
15.265 |
14.391 |
0.000 |
2.26% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_ADI_RAW/5001
|
-5.71% |
2226.425 |
2099.201 |
48.251 |
-4.33% |
48.251 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC16
|
-5.66% |
33.165 |
31.287 |
0.001 |
-5.66% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC32
|
-5.64% |
44.427 |
41.922 |
0.002 |
-5.64% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC32
|
-5.63% |
44.423 |
41.922 |
0.002 |
-5.64% |
0.002 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_PIC_2D_RAW/171
|
-5.58% |
13.560 |
12.803 |
0.073 |
-5.44% |
0.073 |
|
MultiSource/Benchmarks/SciMark2-C/scimark2
Profile
|
-5.57% |
107.677 |
101.677 |
0.062 |
-5.54% |
0.062 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC31
|
-5.56% |
45.052 |
42.548 |
0.001 |
-5.56% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC31
|
-5.56% |
45.051 |
42.548 |
0.001 |
-5.58% |
0.001 |
|
MultiSource/Benchmarks/Rodinia/hotspot/hotspot
Profile
|
-5.55% |
2.037 |
1.924 |
0.005 |
-5.52% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC31
|
-5.52% |
242.576 |
229.176 |
0.135 |
-5.00% |
0.135 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIND_FIRST_MIN_RAW/44217
|
-5.47% |
389.558 |
368.247 |
0.550 |
-5.48% |
0.550 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC15
|
-5.47% |
127.647 |
120.669 |
0.194 |
-5.92% |
0.194 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint32_t>/127
|
-5.46% |
137.663 |
130.147 |
0.005 |
-5.89% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint32_t>/999
|
-5.40% |
696.521 |
658.927 |
0.048 |
-5.40% |
0.048 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint8_t_To_uint16_t_
|
-5.39% |
3625.683 |
3430.222 |
8.106 |
-5.59% |
8.106 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_PIC_2D_LAMBDA/171
|
-5.38% |
13.522 |
12.795 |
0.043 |
-5.21% |
0.043 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC1
|
-5.26% |
11.888 |
11.263 |
0.002 |
-0.01% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint32_t>/999
|
-5.23% |
1365.167 |
1293.749 |
0.081 |
-5.22% |
0.081 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_BAND_LIN_EQ_LAMBDA/5001
|
-5.14% |
21.409 |
20.310 |
0.084 |
-2.35% |
0.084 |
|
SingleSource/Benchmarks/Polybench/stencils/jacobi-2d/jacobi-2d
Profile
|
-5.09% |
32.000 |
30.373 |
0.148 |
-5.74% |
0.148 |
|
MultiSource/Benchmarks/MiBench/consumer-typeset/consumer-typeset
Profile
|
-5.02% |
0.749 |
0.711 |
0.005 |
-0.89% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC32
|
-4.94% |
50.059 |
47.589 |
0.021 |
-4.92% |
0.021 |
|
External/SPEC/CINT2017rate/500.perlbench_r/500.perlbench_r
Profile
|
-4.93% |
153.193 |
145.641 |
0.246 |
-0.72% |
0.246 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC4
|
-4.88% |
25.654 |
24.403 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_PRESSURE_CALC_LAMBDA/44217
|
-4.84% |
500.218 |
476.001 |
2.953 |
-4.52% |
2.953 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint32_t>/256
|
-4.82% |
364.219 |
346.660 |
0.005 |
-4.81% |
0.005 |
|
MultiSource/Applications/siod/siod
Profile
|
-4.81% |
8.333 |
7.932 |
0.005 |
-0.34% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC15
|
-4.80% |
32.536 |
30.973 |
0.003 |
-4.81% |
0.003 |
|
SingleSource/Benchmarks/Misc/revertBits
Profile
|
-4.68% |
0.641 |
0.611 |
0.000 |
-4.67% |
0.000 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_runtime_checks_fail<16, int>
|
-4.61% |
54.444 |
51.934 |
0.001 |
-4.60% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint16_t>/65
|
-4.61% |
95.117 |
90.733 |
0.004 |
-4.61% |
0.004 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_runtime_checks_pass<16, int>
|
-4.60% |
54.439 |
51.934 |
0.009 |
-4.60% |
0.009 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC31
|
-4.59% |
93.981 |
89.670 |
0.020 |
-4.46% |
0.020 |
|
External/SPEC/CINT2017rate/531.deepsjeng_r/531.deepsjeng_r
Profile
|
-4.58% |
267.534 |
255.292 |
0.553 |
-1.85% |
0.553 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC2
|
-4.56% |
13.767 |
13.140 |
0.001 |
-8.70% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC1
|
-4.56% |
13.769 |
13.141 |
0.001 |
-8.70% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC3
|
-4.55% |
13.766 |
13.140 |
0.001 |
-8.71% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC4
|
-4.55% |
13.767 |
13.141 |
0.001 |
-8.70% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC8
|
-4.55% |
13.767 |
13.140 |
0.000 |
-8.70% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC15
|
-4.55% |
13.766 |
13.140 |
0.001 |
-8.70% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC4
|
-4.55% |
13.767 |
13.140 |
0.001 |
-8.70% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC8
|
-4.55% |
13.766 |
13.140 |
0.001 |
-8.70% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC1
|
-4.55% |
13.766 |
13.140 |
0.001 |
-8.70% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC15
|
-4.55% |
13.766 |
13.140 |
0.001 |
-8.70% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC2
|
-4.54% |
13.766 |
13.141 |
0.000 |
-8.69% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC16
|
-4.54% |
13.766 |
13.140 |
0.000 |
-8.70% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC3
|
-4.54% |
13.766 |
13.140 |
0.000 |
-8.70% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC2
|
-4.54% |
13.766 |
13.141 |
0.001 |
-0.10% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC16
|
-4.54% |
13.765 |
13.141 |
0.000 |
-8.69% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC7
|
-4.54% |
13.766 |
13.141 |
0.000 |
-8.69% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC7
|
-4.54% |
13.765 |
13.141 |
0.000 |
-8.69% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC8
|
-4.50% |
26.208 |
25.029 |
0.001 |
-7.00% |
0.001 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C++/HPCCG/HPCCG
Profile
|
-4.48% |
3.926 |
3.750 |
0.042 |
-4.22% |
0.042 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC31
|
-4.47% |
70.084 |
66.954 |
0.005 |
-4.46% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC7
|
-4.46% |
70.080 |
66.951 |
0.016 |
-5.32% |
0.016 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC7
|
-4.46% |
70.082 |
66.960 |
0.004 |
-5.32% |
0.004 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_FLOYD_DITHER/256
|
-4.45% |
1824.387 |
1743.155 |
2.251 |
0.55% |
2.251 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_cond_load_autovec_int64_t_
|
-4.40% |
556010.681 |
531542.906 |
566.988 |
-3.82% |
566.988 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint64_t_To_uint32_t_
|
-4.35% |
19390.528 |
18546.628 |
55.604 |
-3.87% |
55.604 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC63
|
-4.35% |
43.176 |
41.297 |
0.001 |
-4.61% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC64
|
-4.35% |
43.174 |
41.297 |
0.002 |
-4.35% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint16_t_To_uint8_t_
|
-4.34% |
2873.718 |
2748.988 |
9.966 |
-4.49% |
9.966 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint32_t_To_uint16_t_
|
-4.26% |
9837.354 |
9417.836 |
17.892 |
-4.68% |
17.892 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint64_t>/999
|
-4.23% |
1811.192 |
1734.601 |
0.091 |
-4.23% |
0.091 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint8_t_To_uint64_t_
|
-4.21% |
23381.729 |
22397.192 |
11.307 |
-4.63% |
11.307 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint8_t>/28
|
-4.20% |
79.102 |
75.776 |
0.250 |
12.11% |
0.250 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_ENERGY_CALC_RAW/171
|
-4.19% |
14.202 |
13.607 |
0.019 |
-4.45% |
0.019 |
|
MultiSource/Applications/aha/aha
Profile
|
-4.16% |
5.004 |
4.795 |
0.000 |
0.73% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint64_t>/999
|
-4.16% |
3595.245 |
3445.821 |
0.207 |
-4.14% |
0.207 |
|
SingleSource/Benchmarks/Misc/flops-5
Profile
|
-4.13% |
2.020 |
1.937 |
0.001 |
-4.16% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint64_t>/256
|
-4.08% |
935.630 |
897.424 |
0.067 |
-4.08% |
0.067 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_PIC_1D_RAW/5001
|
-4.08% |
346.961 |
332.817 |
2.991 |
-3.54% |
2.991 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC31
|
-4.04% |
61.946 |
59.443 |
0.004 |
-4.04% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC3
|
-4.00% |
46.931 |
45.053 |
0.002 |
-5.27% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_only_autovec_uint8_t_
|
-3.99% |
96175.835 |
92343.069 |
3.138 |
-3.97% |
3.138 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint64_t_To_uint8_t_
|
-3.97% |
19739.800 |
18956.188 |
56.746 |
-4.46% |
56.746 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint32_t>/256
|
-3.97% |
221.532 |
212.741 |
0.004 |
-3.96% |
0.004 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_ENERGY_CALC_LAMBDA/171
|
-3.96% |
14.197 |
13.635 |
0.011 |
-4.30% |
0.011 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC32
|
-3.96% |
63.196 |
60.695 |
0.003 |
-3.96% |
0.003 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_ENERGY_CALC_LAMBDA/5001
|
-3.87% |
434.370 |
417.552 |
2.570 |
-4.68% |
2.570 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopWithReductionTC3
|
-3.84% |
16.268 |
15.643 |
0.001 |
-0.00% |
0.001 |
|
External/SPEC/CFP2017rate/519.lbm_r/519.lbm_r
Profile
|
-3.79% |
199.805 |
192.224 |
1.379 |
-4.21% |
1.379 |
|
External/SPEC/CINT2017rate/523.xalancbmk_r/523.xalancbmk_r
Profile
|
-3.76% |
244.094 |
234.908 |
0.827 |
-2.51% |
0.827 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC2
|
-3.70% |
16.895 |
16.269 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC2
|
-3.70% |
16.894 |
16.269 |
0.000 |
-0.00% |
0.000 |
|
SingleSource/Benchmarks/Shootout/Shootout-matrix
Profile
|
-3.69% |
3.864 |
3.721 |
0.000 |
-3.68% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint8_t>/16
|
-3.67% |
59.535 |
57.349 |
0.162 |
6.56% |
0.162 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint64_t>/256
|
-3.65% |
514.413 |
495.611 |
0.025 |
-3.65% |
0.025 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC64
|
-3.61% |
69.458 |
66.953 |
0.004 |
-3.60% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC64
|
-3.60% |
69.453 |
66.952 |
0.003 |
-3.61% |
0.003 |
|
MultiSource/Applications/JM/lencod/lencod
Profile
|
-3.60% |
33.041 |
31.852 |
0.028 |
-2.11% |
0.028 |
|
SingleSource/Benchmarks/BenchmarkGame/n-body
Profile
|
-3.58% |
2.731 |
2.634 |
0.000 |
21.70% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC63
|
-3.57% |
70.084 |
67.579 |
0.008 |
-3.57% |
0.008 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC63
|
-3.57% |
70.079 |
67.577 |
0.009 |
-3.59% |
0.009 |
|
MultiSource/Benchmarks/Rodinia/pathfinder/pathfinder
Profile
|
-3.54% |
1.266 |
1.221 |
0.008 |
-2.91% |
0.008 |
|
MultiSource/Benchmarks/sim/sim
Profile
|
-3.50% |
9.667 |
9.328 |
0.001 |
-3.84% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopWithReductionTC4
|
-3.45% |
18.146 |
17.520 |
0.001 |
-0.00% |
0.001 |
|
MultiSource/Benchmarks/TSVC/ControlLoops-flt/ControlLoops-flt
Profile
|
-3.42% |
5.520 |
5.331 |
0.061 |
-2.13% |
0.061 |
|
MultiSource/Benchmarks/nbench/nbench
Profile
|
-3.41% |
6.105 |
5.897 |
0.001 |
-3.75% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC2
|
-3.40% |
36.922 |
35.668 |
0.003 |
-6.56% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC64
|
-3.38% |
111.388 |
107.622 |
0.004 |
-3.38% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC7
|
-3.34% |
37.544 |
36.290 |
0.004 |
-0.01% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint32_t>/65
|
-3.33% |
93.858 |
90.729 |
0.002 |
-3.98% |
0.002 |
|
MicroBenchmarks/ImageProcessing/Dilate/Dilate.test:BENCHMARK_DILATE/256
|
-3.33% |
1052.213 |
1017.191 |
4.687 |
-4.69% |
4.687 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint16_t_To_uint32_t_
|
-3.26% |
11238.973 |
10872.089 |
17.887 |
-4.15% |
17.887 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC127
|
-3.26% |
2403.087 |
2324.760 |
20.980 |
-4.20% |
20.980 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_ADI_RAW/44217
|
-3.20% |
19997.730 |
19357.248 |
210.005 |
-1.98% |
210.005 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint16_t>/999
|
-3.16% |
515.013 |
498.733 |
0.015 |
-3.16% |
0.015 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint16_t_To_uint8_t_
|
-3.16% |
4512.093 |
4369.494 |
8.884 |
-3.27% |
8.884 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC31
|
-3.13% |
60.069 |
58.190 |
0.007 |
-3.46% |
0.007 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1BigLoopWithReductionTC1
|
-3.13% |
20.024 |
19.398 |
0.001 |
-3.13% |
0.001 |
|
SingleSource/Benchmarks/Shootout/Shootout-lists
Profile
|
-3.12% |
11.316 |
10.963 |
0.002 |
-3.09% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchVecWithRuntimeChecks4PointersDBeforeA/1000
|
-3.09% |
5020760.173 |
4865539.333 |
630.444 |
-3.07% |
630.444 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1LoopWithReductionTC7
|
-3.03% |
20.649 |
20.024 |
0.000 |
3.21% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_ENERGY_CALC_RAW/5001
|
-3.00% |
433.759 |
420.734 |
3.643 |
-1.87% |
3.643 |
|
External/SPEC/CFP2017rate/544.nab_r/544.nab_r
Profile
|
-3.00% |
472.233 |
458.060 |
0.168 |
-4.15% |
0.168 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC8
|
-2.99% |
41.923 |
40.671 |
0.004 |
-0.01% |
0.004 |
|
External/SPEC/CFP2017rate/511.povray_r/511.povray_r
Profile
|
-2.96% |
34.511 |
33.489 |
0.002 |
-0.88% |
0.002 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C/CoMD/CoMD
Profile
|
-2.92% |
9.908 |
9.618 |
0.008 |
-2.83% |
0.008 |
|
MicroBenchmarks/ImageProcessing/Dilate/Dilate.test:BENCHMARK_DILATE/512
|
-2.91% |
3606.986 |
3502.138 |
15.451 |
-2.29% |
15.451 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<63, GreaterThanZero, None>
|
-2.90% |
4742.197 |
4604.691 |
3.152 |
0.02% |
3.152 |
|
MultiSource/Benchmarks/FreeBench/fourinarow/fourinarow
Profile
|
-2.87% |
0.654 |
0.635 |
0.000 |
-2.39% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint16_t>/999
|
-2.84% |
1013.804 |
985.062 |
0.012 |
-2.84% |
0.012 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_ENERGY_CALC_LAMBDA/44217
|
-2.81% |
4356.452 |
4233.854 |
5.964 |
-2.09% |
5.964 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC1
|
-2.78% |
22.527 |
21.901 |
0.001 |
-2.77% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1LoopWithReductionTC8
|
-2.78% |
22.527 |
21.901 |
0.001 |
2.93% |
0.001 |
|
MultiSource/Benchmarks/FreeBench/mason/mason
Profile
|
-2.69% |
0.553 |
0.538 |
0.000 |
-2.74% |
0.000 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_FLOYD_DITHER/512
|
-2.68% |
6653.191 |
6475.072 |
12.718 |
-2.56% |
12.718 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC63
|
-2.64% |
130.497 |
127.054 |
0.173 |
-2.39% |
0.173 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopWithReductionTC7
|
-2.64% |
23.778 |
23.151 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_FLOYD_DITHER/128
|
-2.62% |
437.971 |
426.513 |
0.603 |
-2.95% |
0.603 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC63
|
-2.61% |
120.142 |
117.010 |
0.002 |
-2.61% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint8_t>/10
|
-2.57% |
48.809 |
47.556 |
0.018 |
2.47% |
0.018 |
|
SingleSource/Benchmarks/Misc-C++/oopack_v1p8
Profile
|
-2.54% |
0.479 |
0.467 |
0.000 |
-9.96% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint8_t_To_uint32_t_
|
-2.53% |
7076.494 |
6897.242 |
1.126 |
-2.54% |
1.126 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint8_t>/16
|
-2.42% |
68.402 |
66.749 |
0.427 |
8.79% |
0.427 |
|
MultiSource/Benchmarks/mafft/pairlocalalign
Profile
|
-2.40% |
93.966 |
91.707 |
0.055 |
-2.50% |
0.055 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchVecWithRuntimeChecks4PointersDBeforeA/32
|
-2.36% |
166194.770 |
162273.149 |
184.009 |
-2.36% |
184.009 |
|
MultiSource/Benchmarks/TSVC/NodeSplitting-dbl/NodeSplitting-dbl
Profile
|
-2.36% |
26.212 |
25.593 |
0.191 |
-3.11% |
0.191 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC63
|
-2.34% |
107.005 |
104.496 |
0.005 |
-2.34% |
0.005 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<63, LessThanZero, First>
|
-2.33% |
1640.117 |
1601.939 |
1.033 |
-0.01% |
1.033 |
|
MultiSource/Applications/sgefa/sgefa
Profile
|
-2.32% |
0.577 |
0.563 |
0.003 |
-1.75% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC64
|
-2.32% |
108.252 |
105.746 |
0.003 |
-2.31% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_only_autovec_int64_t_
|
-2.27% |
1451048.664 |
1418096.600 |
216.496 |
-2.00% |
216.496 |
|
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
|
-2.14% |
12.108 |
11.849 |
0.001 |
-2.08% |
0.001 |
|
SingleSource/Benchmarks/BenchmarkGame/puzzle
Profile
|
-2.10% |
0.872 |
0.854 |
0.002 |
-1.75% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC128
|
-2.10% |
119.521 |
117.016 |
0.006 |
-2.10% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC127
|
-2.09% |
120.143 |
117.632 |
0.003 |
-2.09% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC127
|
-2.08% |
120.143 |
117.642 |
0.002 |
-2.08% |
0.002 |
|
MultiSource/Benchmarks/Fhourstones-3.1/fhourstones3.1
Profile
|
-2.06% |
4.047 |
3.964 |
0.013 |
-0.19% |
0.013 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC31
|
-2.04% |
30.660 |
30.034 |
0.001 |
-3.71% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC32
|
-2.04% |
30.658 |
30.033 |
0.002 |
-4.00% |
0.002 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_BAND_LIN_EQ_RAW/5001
|
-2.02% |
20.383 |
19.971 |
0.139 |
-3.16% |
0.139 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<3, GreaterThanZero, Mid>
|
-2.02% |
37984.197 |
37216.791 |
47.329 |
0.12% |
47.329 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C/SimpleMOC/SimpleMOC
Profile
|
-2.02% |
10.453 |
10.242 |
0.012 |
-1.56% |
0.012 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_nested_cond_load_novec_uint8_t_
|
-1.91% |
502841.852 |
493223.853 |
98.715 |
-2.28% |
98.715 |
|
MultiSource/Benchmarks/Olden/health/health
Profile
|
-1.85% |
1.594 |
1.565 |
0.002 |
-1.67% |
0.002 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_EOS_RAW/171
|
-1.85% |
0.872 |
0.856 |
0.002 |
-1.70% |
0.002 |
|
MultiSource/Benchmarks/VersaBench/ecbdes/ecbdes
Profile
|
-1.84% |
5.150 |
5.055 |
0.001 |
-1.64% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint16_t>/256
|
-1.84% |
272.844 |
267.813 |
0.021 |
-1.84% |
0.021 |
|
MultiSource/Benchmarks/Bullet/bullet
Profile
|
-1.82% |
30.362 |
29.809 |
0.179 |
-2.04% |
0.179 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<16, LessThanZero, Mid>
|
-1.81% |
8658.598 |
8502.220 |
3.778 |
-1.82% |
3.778 |
|
SingleSource/Benchmarks/Misc/ReedSolomon
Profile
|
-1.79% |
20.760 |
20.390 |
0.001 |
-1.96% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC15
|
-1.78% |
70.079 |
68.833 |
0.003 |
-0.00% |
0.003 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_INT_PREDICT_RAW/171
|
-1.77% |
6.916 |
6.794 |
0.004 |
-1.88% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1LoopWithReductionTC15
|
-1.75% |
35.665 |
35.039 |
0.002 |
1.81% |
0.002 |
|
MicroBenchmarks/Builtins/Int128/Builtins.test:BM_RemainderIntrinsic128UniformDivisor<__int128_t>
|
-1.74% |
66.799 |
65.633 |
0.299 |
-0.90% |
0.299 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_EOS_LAMBDA/171
|
-1.72% |
0.872 |
0.857 |
0.000 |
-1.61% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopWithReductionTC63
|
-1.70% |
57.481 |
56.503 |
0.066 |
1.45% |
0.066 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_INT_PREDICT_LAMBDA/171
|
-1.70% |
6.926 |
6.808 |
0.006 |
-1.69% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint64_t>/51
|
-1.69% |
148.303 |
145.792 |
0.007 |
-1.70% |
0.007 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_csa_with_in_loop_arith_novec_int64_t_
|
-1.69% |
1029274.049 |
1011916.420 |
548.902 |
-1.58% |
548.902 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1LoopWithReductionTC16
|
-1.66% |
37.542 |
36.918 |
0.001 |
1.72% |
0.001 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<7, GreaterThanZero, Mid>
|
-1.60% |
20468.782 |
20140.932 |
1.937 |
0.01% |
1.937 |
|
MultiSource/Benchmarks/tramp3d-v4/tramp3d-v4
Profile
|
-1.59% |
1.076 |
1.059 |
0.001 |
-1.57% |
0.001 |
|
MicroBenchmarks/Builtins/Int128/Builtins.test:BM_RemainderIntrinsic128SmallDivisor<__uint128_t>
|
-1.58% |
72.454 |
71.307 |
0.028 |
-0.59% |
0.028 |
|
SingleSource/Benchmarks/Misc/mandel-2
Profile
|
-1.58% |
2.536 |
2.496 |
0.000 |
-1.55% |
0.000 |
|
MultiSource/Applications/minisat/minisat
Profile
|
-1.56% |
61.522 |
60.565 |
0.323 |
-0.85% |
0.323 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, LessThanZero, Mid>
|
-1.50% |
31897.455 |
31418.205 |
16.816 |
-1.15% |
16.816 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint32_t_To_uint64_t_
|
-1.48% |
26244.782 |
25855.485 |
17.718 |
-1.62% |
17.718 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<6, LessThanZero, Mid>
|
-1.48% |
23838.985 |
23487.029 |
2.046 |
-0.34% |
2.046 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, LessThanZero, Mid>
|
-1.46% |
56587.283 |
55760.304 |
4.024 |
-1.36% |
4.024 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC127
|
-1.43% |
220.265 |
217.124 |
0.010 |
-1.43% |
0.010 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopWithReductionTC31
|
-1.41% |
44.427 |
43.801 |
0.002 |
1.44% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint16_t_To_uint32_t_
|
-1.38% |
13485.113 |
13298.626 |
28.627 |
-1.37% |
28.627 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_only_novec_int32_t_
|
-1.38% |
1153859.182 |
1137933.695 |
271.296 |
1.35% |
271.296 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC64
|
-1.37% |
86.467 |
85.281 |
0.088 |
-1.24% |
0.088 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint64_t>/51
|
-1.36% |
229.014 |
225.894 |
0.015 |
-1.36% |
0.015 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_nested_cond_load_novec_int32_t_
|
-1.34% |
634788.710 |
626287.146 |
304.300 |
-2.92% |
304.300 |
|
MultiSource/Benchmarks/Fhourstones/fhourstones
Profile
|
-1.32% |
10.921 |
10.776 |
0.020 |
-0.02% |
0.020 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_only_novec_int64_t_
|
-1.29% |
1437123.715 |
1418540.140 |
927.831 |
-1.05% |
927.831 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC127
|
-1.27% |
197.109 |
194.605 |
0.008 |
-1.27% |
0.008 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC128
|
-1.26% |
198.360 |
195.851 |
0.010 |
-1.27% |
0.010 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<6, GreaterThanZero, First>
|
-1.17% |
16199.791 |
16010.848 |
1.430 |
0.00% |
1.430 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, GreaterThanZero, Last>
|
-1.16% |
35662.767 |
35249.326 |
2.697 |
-0.00% |
2.697 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<3, LessThanZero, None>
|
-1.16% |
45449.139 |
44922.859 |
34.357 |
-0.20% |
34.357 |
|
SingleSource/Benchmarks/SmallPT/smallpt
Profile
|
-1.11% |
30.039 |
29.706 |
0.001 |
-1.08% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_sinhf_autovec_float_
|
-1.10% |
2242.514 |
2217.907 |
0.411 |
-1.10% |
0.411 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_ENERGY_CALC_RAW/44217
|
-1.08% |
4308.452 |
4262.101 |
8.266 |
-1.60% |
8.266 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_sinhf_novec_float_
|
-1.06% |
2242.112 |
2218.321 |
0.305 |
-1.05% |
0.305 |
|
SingleSource/Benchmarks/Misc/fbench
Profile
|
-1.01% |
5.685 |
5.628 |
0.000 |
-2.32% |
0.000 |