|
MultiSource/Benchmarks/MiBench/automotive-bitcount/automotive-bitcount
Profile
|
40.42% |
0.070 |
0.099 |
0.000 |
-0.04% |
0.000 |
|
MultiSource/Benchmarks/Trimaran/enc-pc1/enc-pc1
Profile
|
37.72% |
0.462 |
0.636 |
0.000 |
11.28% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIND_FIRST_MIN_LAMBDA/5001
|
33.30% |
10.731 |
14.305 |
0.000 |
16.85% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIND_FIRST_MIN_LAMBDA/171
|
33.23% |
0.374 |
0.498 |
0.003 |
32.97% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint8_t>/999
|
27.12% |
866.955 |
1102.055 |
0.022 |
27.53% |
0.022 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint8_t>/999
|
27.07% |
1707.571 |
2169.819 |
0.044 |
28.03% |
0.044 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC1
|
26.56% |
5.083 |
6.433 |
0.000 |
12.50% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIRST_DIFF_LAMBDA/171
|
26.41% |
0.295 |
0.373 |
0.000 |
-0.01% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint8_t>/51
|
23.64% |
105.781 |
130.793 |
0.001 |
22.81% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint8_t>/51
|
23.32% |
64.327 |
79.331 |
0.002 |
24.70% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint8_t>/256
|
23.27% |
248.717 |
306.601 |
0.009 |
24.69% |
0.009 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint8_t>/256
|
23.21% |
468.150 |
576.790 |
0.005 |
26.68% |
0.005 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<1, EqZero, First>
|
23.20% |
11886.731 |
14644.455 |
1.773 |
23.08% |
1.773 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint8_t>/28
|
21.87% |
45.744 |
55.749 |
0.000 |
21.87% |
0.000 |
|
External/SPEC/CINT2017rate/525.x264_r/525.x264_r
Profile
|
21.39% |
102.360 |
124.256 |
0.012 |
1.36% |
0.012 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint8_t>/28
|
20.00% |
67.900 |
81.478 |
0.002 |
19.99% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC2
|
19.99% |
7.148 |
8.577 |
0.000 |
19.93% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC2
|
19.99% |
7.148 |
8.577 |
0.000 |
19.81% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint16_t_To_uint8_t_
|
19.98% |
11928.630 |
14311.572 |
1.429 |
19.95% |
1.429 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopFrom_uint16_t_To_uint32_t_
|
19.90% |
11928.344 |
14301.551 |
0.355 |
19.78% |
0.355 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopFrom_uint8_t_To_uint32_t_
|
19.89% |
11928.874 |
14301.766 |
0.096 |
19.84% |
0.096 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopFrom_uint16_t_To_uint8_t_
|
19.86% |
11939.772 |
14311.011 |
1.780 |
19.95% |
1.780 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint16_t_To_uint8_t_
|
19.85% |
11933.445 |
14301.825 |
5.651 |
19.89% |
5.651 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint16_t_To_uint32_t_
|
19.74% |
11944.118 |
14302.243 |
4.408 |
19.84% |
4.408 |
|
SingleSource/Benchmarks/Shootout-C++/Shootout-C++-matrix
Profile
|
18.48% |
5.561 |
6.589 |
0.000 |
-0.01% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_cond_load_autovec_int64_t_
|
17.67% |
680013.619 |
800160.367 |
648.650 |
0.07% |
648.650 |
|
MicroBenchmarks/ImageProcessing/Blur/blur.test:BENCHMARK_boxBlurKernel/512
|
17.07% |
17234.875 |
20177.657 |
32.763 |
0.06% |
32.763 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_only_autovec_int64_t_
|
17.03% |
678242.483 |
793734.091 |
445.382 |
0.02% |
445.382 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint8_t>/16
|
16.41% |
47.888 |
55.746 |
0.002 |
16.40% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint32_t>/16
|
16.27% |
30.735 |
35.736 |
0.001 |
13.63% |
0.001 |
|
MicroBenchmarks/ImageProcessing/Blur/blur.test:BENCHMARK_boxBlurKernel/256
|
15.82% |
3955.910 |
4581.686 |
1.378 |
-0.01% |
1.378 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint16_t>/65
|
15.44% |
82.913 |
95.712 |
1.474 |
15.43% |
1.474 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint8_t>/16
|
15.38% |
37.168 |
42.884 |
0.000 |
15.27% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIND_FIRST_MIN_RAW/5001
|
14.72% |
10.741 |
12.322 |
0.059 |
-0.09% |
0.059 |
|
MicroBenchmarks/ImageProcessing/Blur/blur.test:BENCHMARK_boxBlurKernel/1024
|
14.71% |
73810.778 |
84666.625 |
74.211 |
-0.09% |
74.211 |
|
MicroBenchmarks/ImageProcessing/Blur/blur.test:BENCHMARK_boxBlurKernel/128
|
14.63% |
937.719 |
1074.860 |
1.972 |
-0.31% |
1.972 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC64
|
14.40% |
64.121 |
73.357 |
0.874 |
14.03% |
0.874 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint8_t>/10
|
13.20% |
37.881 |
42.882 |
0.001 |
13.19% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_csa_with_cond_arith_novec_int64_t_
|
13.01% |
693293.651 |
783473.684 |
509.520 |
13.40% |
509.520 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIND_FIRST_MIN_LAMBDA/44217
|
12.80% |
117.251 |
132.265 |
0.480 |
6.69% |
0.480 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint32_t>/28
|
12.72% |
39.311 |
44.312 |
0.001 |
10.70% |
0.001 |
|
MultiSource/Benchmarks/Trimaran/enc-md5/enc-md5
Profile
|
12.07% |
2.684 |
3.008 |
0.002 |
-0.02% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchAutoVec<uint16_t>/65
|
11.94% |
143.665 |
160.817 |
0.001 |
11.38% |
0.001 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_FLOYD_DITHER/256
|
11.27% |
993.487 |
1105.431 |
0.132 |
-0.02% |
0.132 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint8_t>/10
|
10.86% |
32.879 |
36.451 |
0.001 |
10.86% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchAutoVec<uint16_t>/127
|
10.85% |
269.514 |
298.762 |
9.212 |
10.56% |
9.212 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_FLOYD_DITHER/512
|
10.80% |
4005.337 |
4437.734 |
13.486 |
0.08% |
13.486 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_cond_load_novec_int32_t_
|
10.41% |
534757.508 |
590443.692 |
4873.838 |
4.68% |
4873.838 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC2
|
9.99% |
7.147 |
7.862 |
0.000 |
-8.33% |
0.000 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<31, LessThanZero, First>
|
9.38% |
2285.040 |
2499.327 |
0.082 |
9.00% |
0.082 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_FLOYD_DITHER/128
|
9.37% |
250.637 |
274.129 |
0.172 |
0.03% |
0.172 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint32_t>/51
|
9.09% |
55.037 |
60.038 |
0.001 |
7.69% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC4
|
9.09% |
7.862 |
8.577 |
0.000 |
9.09% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC4
|
9.08% |
7.862 |
8.577 |
0.000 |
9.08% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_HYDRO_1D_LAMBDA/171
|
8.78% |
0.456 |
0.496 |
0.000 |
8.77% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint32_t>/10
|
8.50% |
33.594 |
36.451 |
0.001 |
6.24% |
0.001 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<15, GreaterThanZero, First>
|
8.50% |
4504.225 |
4887.115 |
0.389 |
8.67% |
0.389 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_cond_load_novec_int64_t_
|
7.95% |
800612.829 |
864289.246 |
754.707 |
7.74% |
754.707 |
|
SingleSource/Benchmarks/McGill/misr
Profile
|
7.71% |
0.410 |
0.442 |
0.000 |
-0.03% |
0.000 |
|
External/SPEC/CFP2017rate/508.namd_r/508.namd_r
Profile
|
7.71% |
77.758 |
83.751 |
0.143 |
-0.31% |
0.143 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIRST_DIFF_LAMBDA/5001
|
7.70% |
10.084 |
10.860 |
0.006 |
-0.13% |
0.006 |
|
SingleSource/Benchmarks/Shootout/Shootout-lists
Profile
|
7.65% |
9.603 |
10.337 |
0.010 |
0.02% |
0.010 |
|
MicroBenchmarks/ImageProcessing/Blur/blur.test:BENCHMARK_GAUSSIAN_BLUR/128
|
7.55% |
3340.929 |
3593.118 |
0.099 |
-0.03% |
0.099 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint32_t>/10
|
7.31% |
29.305 |
31.448 |
0.000 |
10.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC7
|
7.14% |
10.007 |
10.721 |
0.000 |
7.14% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC7
|
7.13% |
10.007 |
10.721 |
0.000 |
7.13% |
0.000 |
|
MicroBenchmarks/ImageProcessing/Blur/blur.test:BENCHMARK_GAUSSIAN_BLUR/256
|
7.09% |
14330.612 |
15345.978 |
16.084 |
-0.03% |
16.084 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC1
|
6.66% |
5.361 |
5.718 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC1
|
6.66% |
5.361 |
5.718 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC1
|
6.66% |
5.361 |
5.718 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC31
|
6.56% |
148.897 |
158.668 |
0.005 |
5.97% |
0.005 |
|
MultiSource/Applications/JM/lencod/lencod
Profile
|
6.43% |
13.747 |
14.630 |
0.010 |
0.84% |
0.010 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIND_FIRST_MIN_RAW/171
|
6.40% |
0.388 |
0.413 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC32
|
6.38% |
153.851 |
163.671 |
0.003 |
6.76% |
0.003 |
|
MicroBenchmarks/ImageProcessing/Blur/blur.test:BENCHMARK_GAUSSIAN_BLUR/512
|
6.32% |
59674.667 |
63448.455 |
16.573 |
-0.07% |
16.573 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC4
|
6.24% |
11.436 |
12.150 |
0.000 |
6.24% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC128
|
6.06% |
614.617 |
651.861 |
0.028 |
5.37% |
0.028 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC127
|
5.99% |
611.655 |
648.272 |
0.021 |
5.37% |
0.021 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1LoopWithReductionTC2
|
5.95% |
5.111 |
5.415 |
0.020 |
0.21% |
0.020 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC64
|
5.94% |
305.611 |
323.777 |
0.004 |
5.40% |
0.004 |
|
MultiSource/Benchmarks/Trimaran/enc-rc4/enc-rc4
Profile
|
5.92% |
1.828 |
1.936 |
0.004 |
0.04% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC2
|
5.88% |
5.118 |
5.419 |
0.013 |
-36.82% |
0.013 |
|
SingleSource/Benchmarks/Adobe-C++/loop_unroll
Profile
|
5.80% |
1.619 |
1.713 |
0.001 |
-0.05% |
0.001 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_no_runtime_checks_needed<16, int>
|
5.76% |
37.167 |
39.309 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<5, LessThanZero, None>
|
5.50% |
20535.442 |
21665.831 |
0.335 |
2.77% |
0.335 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_xor_no_runtime_checks_needed<16, int>
|
5.40% |
26.446 |
27.874 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIRST_DIFF_LAMBDA/44217
|
5.34% |
91.165 |
96.035 |
0.038 |
-0.04% |
0.038 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopTC31
|
5.29% |
274.053 |
288.548 |
0.005 |
0.09% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC31
|
5.28% |
274.066 |
288.528 |
0.012 |
0.12% |
0.012 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC31
|
5.21% |
274.084 |
288.363 |
0.005 |
0.02% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC8
|
5.15% |
41.461 |
43.597 |
0.001 |
5.05% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopTC128
|
5.15% |
1131.467 |
1189.694 |
0.075 |
-0.20% |
0.075 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC64
|
5.13% |
566.790 |
595.873 |
0.059 |
0.03% |
0.059 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopTC64
|
5.13% |
566.768 |
595.840 |
0.047 |
0.02% |
0.047 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC128
|
5.10% |
1132.058 |
1189.838 |
0.494 |
0.05% |
0.494 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint32_t>/16
|
5.08% |
42.171 |
44.314 |
0.000 |
3.33% |
0.000 |
|
MultiSource/Benchmarks/VersaBench/ecbdes/ecbdes
Profile
|
5.08% |
3.829 |
4.024 |
0.000 |
-0.02% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC128
|
5.08% |
1132.292 |
1189.802 |
0.018 |
-0.00% |
0.018 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC15
|
5.07% |
136.522 |
143.443 |
0.078 |
0.31% |
0.078 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopTC63
|
5.07% |
559.352 |
587.690 |
0.090 |
0.07% |
0.090 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC63
|
5.04% |
559.359 |
587.577 |
0.062 |
-0.02% |
0.062 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC127
|
5.04% |
1125.091 |
1181.779 |
0.014 |
0.00% |
0.014 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC64
|
5.03% |
567.373 |
595.927 |
0.028 |
0.06% |
0.028 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC127
|
5.03% |
1125.148 |
1181.717 |
0.015 |
0.11% |
0.015 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC63
|
5.02% |
559.348 |
587.449 |
0.072 |
-0.57% |
0.072 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopTC127
|
4.97% |
1125.815 |
1181.805 |
0.021 |
-0.16% |
0.021 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<8, LessThanZero, Last>
|
4.86% |
14664.467 |
15377.422 |
0.238 |
-0.01% |
0.238 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<15, LessThanZero, Mid>
|
4.86% |
7822.709 |
8202.895 |
0.120 |
-0.02% |
0.120 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint32_t>/28
|
4.81% |
59.326 |
62.179 |
0.002 |
3.56% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopTC3
|
4.78% |
27.436 |
28.748 |
0.004 |
0.90% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC7
|
4.76% |
15.010 |
15.724 |
0.000 |
46.64% |
0.000 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<8, LessThanZero, None>
|
4.68% |
15038.519 |
15742.752 |
0.648 |
2.36% |
0.648 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC2
|
4.68% |
5.134 |
5.375 |
0.028 |
-0.94% |
0.028 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC7
|
4.68% |
36.930 |
38.659 |
0.648 |
4.66% |
0.648 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopTC8
|
4.65% |
70.590 |
73.873 |
0.002 |
0.33% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC8
|
4.56% |
70.564 |
73.779 |
0.001 |
0.36% |
0.001 |
|
SingleSource/Benchmarks/Misc/salsa20
Profile
|
4.53% |
10.432 |
10.905 |
0.000 |
-0.66% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC2
|
4.50% |
5.155 |
5.386 |
0.026 |
-0.65% |
0.026 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC8
|
4.48% |
70.564 |
73.722 |
0.001 |
-0.11% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint64_t>/51
|
4.46% |
130.087 |
135.890 |
0.133 |
5.62% |
0.133 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC63
|
4.40% |
306.010 |
319.478 |
0.007 |
5.65% |
0.007 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint16_t_To_uint32_t_
|
4.36% |
20567.550 |
21464.798 |
5.969 |
0.05% |
5.969 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopTC16
|
4.33% |
146.345 |
152.685 |
0.001 |
0.08% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC16
|
4.33% |
146.344 |
152.680 |
0.001 |
0.09% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC16
|
4.32% |
146.350 |
152.673 |
0.002 |
0.02% |
0.002 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIND_FIRST_MIN_RAW/44217
|
4.28% |
121.454 |
126.656 |
1.124 |
-0.52% |
1.124 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopTC15
|
4.28% |
136.525 |
142.369 |
0.711 |
0.82% |
0.711 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC2
|
4.17% |
5.186 |
5.402 |
0.063 |
0.49% |
0.063 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<8, GreaterThanZero, First>
|
4.12% |
8443.096 |
8790.897 |
2.971 |
4.24% |
2.971 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC4
|
4.08% |
23.348 |
24.301 |
0.000 |
4.08% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC15
|
4.00% |
136.526 |
141.988 |
0.093 |
-2.13% |
0.093 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC15
|
3.96% |
75.625 |
78.619 |
0.002 |
3.94% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC16
|
3.84% |
80.527 |
83.623 |
0.002 |
3.70% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC3
|
3.75% |
27.417 |
28.445 |
0.032 |
-0.58% |
0.032 |
|
MultiSource/Benchmarks/mafft/pairlocalalign
Profile
|
3.75% |
46.185 |
47.916 |
0.003 |
0.77% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC3
|
3.74% |
27.431 |
28.458 |
0.009 |
0.03% |
0.009 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC32
|
3.70% |
282.852 |
293.318 |
0.007 |
0.11% |
0.007 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_DEL_DOT_VEC_2D_LAMBDA/1
|
3.70% |
191.141 |
198.211 |
0.388 |
-0.09% |
0.388 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_VOL3D_CALC_RAW/2
|
3.66% |
7.490 |
7.764 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopTC32
|
3.63% |
282.931 |
293.212 |
0.015 |
0.06% |
0.015 |
|
MultiSource/Benchmarks/sim/sim
Profile
|
3.60% |
6.380 |
6.609 |
0.009 |
-1.49% |
0.009 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC32
|
3.60% |
282.846 |
293.019 |
0.020 |
0.00% |
0.020 |
|
MultiSource/Applications/siod/siod
Profile
|
3.49% |
5.470 |
5.661 |
0.060 |
3.64% |
0.060 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<3, LessThanZero, Mid>
|
3.47% |
25467.690 |
26351.238 |
0.437 |
0.01% |
0.437 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, LessThanZero, Last>
|
3.47% |
38203.962 |
39528.150 |
1.082 |
-0.02% |
1.082 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, LessThanZero, None>
|
3.44% |
42458.543 |
43920.630 |
2.450 |
-3.23% |
2.450 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_VOL3D_CALC_LAMBDA/2
|
3.34% |
7.513 |
7.764 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_two_loads<uint32_t>/10
|
3.33% |
21.443 |
22.157 |
0.000 |
3.32% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_two_loads<uint32_t>/51
|
3.33% |
21.442 |
22.156 |
0.001 |
3.32% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_two_loads<uint32_t>/999
|
3.33% |
21.442 |
22.156 |
0.001 |
3.33% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_two_loads<uint32_t>/16
|
3.33% |
21.443 |
22.156 |
0.001 |
3.32% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_two_loads<uint32_t>/28
|
3.33% |
21.443 |
22.157 |
0.001 |
3.32% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_two_loads<uint32_t>/256
|
3.33% |
21.443 |
22.156 |
0.001 |
3.32% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_two_loads<uint8_t>/999
|
3.23% |
22.156 |
22.872 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_two_loads<uint8_t>/256
|
3.23% |
22.157 |
22.872 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint32_t>/999
|
3.22% |
22.157 |
22.872 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint32_t>/256
|
3.22% |
22.157 |
22.871 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_two_loads<uint8_t>/28
|
3.22% |
22.157 |
22.871 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_two_loads<uint8_t>/51
|
3.22% |
22.157 |
22.871 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint32_t>/28
|
3.22% |
22.157 |
22.871 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint32_t>/51
|
3.22% |
22.157 |
22.871 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_two_loads<uint8_t>/16
|
3.22% |
22.157 |
22.871 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint16_t>/51
|
3.22% |
22.158 |
22.872 |
0.000 |
3.22% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint16_t>/256
|
3.22% |
22.158 |
22.872 |
0.000 |
3.22% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_two_loads<uint8_t>/10
|
3.22% |
22.157 |
22.871 |
0.000 |
-0.01% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint32_t>/16
|
3.22% |
22.158 |
22.872 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint16_t>/28
|
3.22% |
22.158 |
22.871 |
0.000 |
3.22% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint32_t>/10
|
3.22% |
22.158 |
22.871 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint16_t>/999
|
3.22% |
22.158 |
22.871 |
0.001 |
3.22% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint16_t>/16
|
3.22% |
22.158 |
22.871 |
0.001 |
3.22% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint16_t>/10
|
3.21% |
22.159 |
22.871 |
0.001 |
3.22% |
0.001 |
|
MicroBenchmarks/ImageProcessing/Blur/blur.test:BENCHMARK_GAUSSIAN_BLUR/1024
|
3.13% |
253765.667 |
261709.667 |
2.126 |
0.01% |
2.126 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<3, EqZero, Last>
|
3.11% |
29338.642 |
30251.124 |
0.512 |
3.32% |
0.512 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<5, GreaterThanZero, Mid>
|
3.11% |
17606.122 |
18153.391 |
0.226 |
3.32% |
0.226 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<3, LessThanZero, Last>
|
3.11% |
29339.676 |
30251.523 |
1.101 |
0.00% |
1.101 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<3, LessThanZero, None>
|
3.06% |
30298.273 |
31226.346 |
0.556 |
0.00% |
0.556 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<16, EqZero, First>
|
3.05% |
5689.196 |
5862.988 |
0.052 |
3.18% |
0.052 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, LessThanZero, Mid>
|
3.02% |
22740.521 |
23426.998 |
0.789 |
3.21% |
0.789 |
|
MultiSource/Benchmarks/PAQ8p/paq8p
Profile
|
3.01% |
131.822 |
135.792 |
0.062 |
3.29% |
0.062 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<7, EqZero, Mid>
|
2.97% |
13408.972 |
13807.022 |
0.234 |
3.11% |
0.234 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, LessThanZero, None>
|
2.84% |
24205.290 |
24892.038 |
0.392 |
0.00% |
0.392 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<8, GreaterThanZero, Mid>
|
2.79% |
12467.851 |
12815.101 |
0.460 |
2.92% |
0.460 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint8_t>/127
|
2.78% |
166.540 |
171.172 |
0.443 |
0.60% |
0.443 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<5, EqZero, Last>
|
2.77% |
19942.450 |
20495.842 |
0.247 |
2.93% |
0.247 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<32, EqZero, Mid>
|
2.75% |
3124.118 |
3210.043 |
0.269 |
2.88% |
0.269 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<5, LessThanZero, Last>
|
2.74% |
20517.368 |
21079.958 |
0.856 |
2.80% |
0.856 |
|
MicroBenchmarks/Builtins/Int128/Builtins.test:BM_DivideIntrinsic128UniformDivisor<__uint128_t>
|
2.74% |
37.447 |
38.472 |
0.136 |
2.96% |
0.136 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C++/miniFE/miniFE
Profile
|
2.73% |
22.342 |
22.952 |
0.086 |
0.12% |
0.086 |
|
MultiSource/Applications/aha/aha
Profile
|
2.66% |
3.775 |
3.876 |
0.000 |
-0.43% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_PRESSURE_CALC_RAW/171
|
2.65% |
1.322 |
1.357 |
0.000 |
9.58% |
0.000 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<6, GreaterThanZero, Last>
|
2.62% |
17582.107 |
18042.921 |
0.443 |
2.76% |
0.443 |
|
SingleSource/Benchmarks/Misc/revertBits
Profile
|
2.58% |
0.401 |
0.411 |
0.000 |
-0.02% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC2
|
2.54% |
20.007 |
20.515 |
0.016 |
-1.52% |
0.016 |
|
SingleSource/Benchmarks/Shootout/Shootout-ary3
Profile
|
2.52% |
4.450 |
4.562 |
0.033 |
-3.77% |
0.033 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<6, LessThanZero, None>
|
2.52% |
18074.577 |
18529.438 |
4.206 |
-0.01% |
4.206 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint64_t>/10
|
2.50% |
28.590 |
29.304 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC128
|
2.49% |
155.515 |
159.391 |
0.005 |
-17.41% |
0.005 |
|
MultiSource/Benchmarks/ASC_Sequoia/IRSmk/IRSmk
Profile
|
2.45% |
15.487 |
15.866 |
0.135 |
0.51% |
0.135 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<7, EqZero, None>
|
2.39% |
16342.423 |
16732.443 |
0.053 |
2.56% |
0.053 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC128
|
2.38% |
157.973 |
161.729 |
0.274 |
5.20% |
0.274 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC2
|
2.33% |
20.003 |
20.470 |
0.021 |
-0.74% |
0.021 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint32_t>/51
|
2.32% |
92.203 |
94.342 |
0.002 |
0.75% |
0.002 |
|
MultiSource/Benchmarks/nbench/nbench
Profile
|
2.24% |
3.782 |
3.867 |
0.009 |
2.29% |
0.009 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC8
|
2.22% |
10.721 |
10.959 |
0.000 |
-33.33% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint32_t>/10
|
2.22% |
32.164 |
32.877 |
0.001 |
2.21% |
0.001 |
|
MultiSource/Applications/hexxagon/hexxagon
Profile
|
2.22% |
9.028 |
9.228 |
0.005 |
-3.68% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC8
|
2.22% |
10.721 |
10.959 |
0.000 |
-4.17% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC8
|
2.22% |
10.722 |
10.959 |
0.000 |
0.00% |
0.000 |
|
MultiSource/Applications/SPASS/SPASS
Profile
|
2.19% |
25.568 |
26.127 |
0.105 |
2.35% |
0.105 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint8_t>/10
|
2.12% |
33.593 |
34.306 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopTC2
|
2.11% |
20.010 |
20.433 |
0.011 |
-0.99% |
0.011 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1BigLoopWithReductionTC64
|
2.08% |
305.598 |
311.956 |
0.174 |
1.55% |
0.174 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_VOL3D_CALC_RAW/1
|
2.07% |
206.858 |
211.138 |
0.485 |
0.04% |
0.485 |
|
External/SPEC/CINT2017rate/505.mcf_r/505.mcf_r
Profile
|
2.06% |
154.386 |
157.563 |
0.725 |
-0.49% |
0.725 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint16_t>/10
|
1.96% |
36.454 |
37.166 |
0.001 |
1.92% |
0.001 |
|
SingleSource/Benchmarks/Adobe-C++/functionobjects
Profile
|
1.94% |
5.948 |
6.063 |
0.004 |
-0.00% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC128
|
1.80% |
285.900 |
291.053 |
0.596 |
1.10% |
0.596 |
|
MultiSource/Benchmarks/Fhourstones/fhourstones
Profile
|
1.79% |
2.346 |
2.388 |
0.010 |
3.15% |
0.010 |
|
External/SPEC/CINT2017rate/500.perlbench_r/500.perlbench_r
Profile
|
1.71% |
101.321 |
103.051 |
0.199 |
1.91% |
0.199 |
|
External/SPEC/CINT2017rate/523.xalancbmk_r/523.xalancbmk_r
Profile
|
1.69% |
210.728 |
214.297 |
0.829 |
0.12% |
0.829 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint8_t>/16
|
1.69% |
42.169 |
42.881 |
0.002 |
-0.01% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint16_t>/16
|
1.66% |
42.887 |
43.599 |
0.000 |
-3.17% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC128
|
1.65% |
158.192 |
160.805 |
0.006 |
3.44% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_asinf_autovec_float_
|
1.64% |
385.902 |
392.230 |
0.118 |
1.76% |
0.118 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_expf_novec_float_
|
1.57% |
456.278 |
463.433 |
0.130 |
1.69% |
0.130 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<31, LessThanZero, None>
|
1.57% |
5178.180 |
5259.288 |
2.334 |
-0.13% |
2.334 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint16_t>/10
|
1.51% |
47.175 |
47.887 |
0.001 |
-0.01% |
0.001 |
|
SingleSource/Benchmarks/Stanford/FloatMM
Profile
|
1.48% |
0.757 |
0.769 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint64_t>/10
|
1.46% |
48.603 |
49.314 |
0.001 |
4.53% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC31
|
1.44% |
49.321 |
50.030 |
0.001 |
52.16% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint16_t_To_uint64_t_
|
1.41% |
21891.085 |
22200.361 |
7.900 |
-0.00% |
7.900 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_BAND_LIN_EQ_LAMBDA/44217
|
1.41% |
83.990 |
85.174 |
0.420 |
-1.58% |
0.420 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC15
|
1.37% |
17.392 |
17.630 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC15
|
1.36% |
17.393 |
17.630 |
0.000 |
-0.01% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC15
|
1.36% |
17.393 |
17.630 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC15
|
1.36% |
17.393 |
17.630 |
0.000 |
-33.33% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetBLambdaLoops/lcalsBLambda.test:BM_MULADDSUB_LAMBDA/44217
|
1.35% |
332.885 |
337.387 |
1.657 |
3.09% |
1.657 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_ENERGY_CALC_LAMBDA/5001
|
1.34% |
223.942 |
226.946 |
0.613 |
-0.64% |
0.613 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_DEL_DOT_VEC_2D_LAMBDA/0
|
1.32% |
1202.997 |
1218.896 |
1.486 |
-0.20% |
1.486 |
|
MultiSource/Benchmarks/Ptrdist/anagram/anagram
Profile
|
1.31% |
1.887 |
1.911 |
0.000 |
-0.02% |
0.000 |
|
External/SPEC/CFP2017rate/544.nab_r/544.nab_r
Profile
|
1.30% |
276.601 |
280.191 |
0.047 |
0.00% |
0.047 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/16
|
1.29% |
119.073 |
120.609 |
0.021 |
0.04% |
0.021 |
|
External/SPEC/CINT2017rate/531.deepsjeng_r/531.deepsjeng_r
Profile
|
1.26% |
136.880 |
138.603 |
0.139 |
0.85% |
0.139 |
|
SingleSource/Benchmarks/Misc/ReedSolomon
Profile
|
1.20% |
9.520 |
9.634 |
0.002 |
0.76% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint8_t>/28
|
1.20% |
59.326 |
60.037 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_DEL_DOT_VEC_2D_RAW/0
|
1.16% |
1202.110 |
1216.047 |
2.446 |
0.12% |
2.446 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<31, GreaterThanZero, None>
|
1.13% |
5191.120 |
5250.015 |
2.095 |
1.20% |
2.095 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_csa_with_in_loop_arith_autovec_uint8_t_
|
1.11% |
514119.941 |
519841.791 |
802.342 |
0.14% |
802.342 |
|
MicroBenchmarks/ImageProcessing/AnisotropicDiffusion/AnisotropicDiffusion.test:BENCHMARK_ANISTROPIC_DIFFUSION/128
|
1.05% |
18120.410 |
18310.342 |
15.534 |
0.33% |
15.534 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_INT_PREDICT_LAMBDA/171
|
1.04% |
2.070 |
2.091 |
0.004 |
-0.01% |
0.004 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_EOS_RAW/44217
|
1.04% |
397.016 |
401.128 |
0.128 |
-0.05% |
0.128 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, EqZero, Mid>
|
1.03% |
8351.629 |
8437.610 |
0.187 |
-0.03% |
0.187 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_MAT_X_MAT_LAMBDA/44217
|
1.03% |
1038044.000 |
1048718.000 |
1203.127 |
-0.21% |
1203.127 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/32
|
1.02% |
593.427 |
599.480 |
0.222 |
-0.00% |
0.222 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<31, GreaterThanZero, Mid>
|
1.02% |
4952.785 |
5003.146 |
1.878 |
1.02% |
1.878 |
|
MicroBenchmarks/ImageProcessing/AnisotropicDiffusion/AnisotropicDiffusion.test:BENCHMARK_ANISTROPIC_DIFFUSION/256
|
1.01% |
75075.000 |
75832.444 |
73.132 |
0.26% |
73.132 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/64
|
1.00% |
2623.629 |
2649.977 |
0.170 |
-0.00% |
0.170 |