|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint8_t_To_uint16_t_
|
-22.21% |
21450.205 |
16686.186 |
12.191 |
-22.21% |
12.191 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint8_t_To_uint16_t_
|
-22.21% |
21449.916 |
16686.898 |
7.821 |
-22.20% |
7.821 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint8_t_To_uint16_t_
|
-22.15% |
21450.110 |
16699.342 |
2.784 |
-22.15% |
2.784 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIRST_DIFF_LAMBDA/171
|
-21.65% |
0.373 |
0.292 |
0.000 |
-21.65% |
0.000 |
|
MultiSource/Benchmarks/Trimaran/enc-pc1/enc-pc1
Profile
|
-19.60% |
0.568 |
0.457 |
0.000 |
-19.76% |
0.000 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C++/miniFE/miniFE
Profile
|
-18.37% |
22.968 |
18.749 |
0.236 |
-17.91% |
0.236 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopWithReductionTC3
|
-16.67% |
8.577 |
7.147 |
0.000 |
-16.66% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint8_t_To_uint32_t_
|
-16.65% |
14301.557 |
11920.044 |
0.235 |
-16.66% |
0.235 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint16_t_To_uint32_t_
|
-16.65% |
14301.408 |
11919.963 |
0.959 |
-16.65% |
0.959 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopFrom_uint8_t_To_uint64_t_
|
-16.63% |
14301.761 |
11923.788 |
12.272 |
-16.63% |
12.272 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC63
|
-16.56% |
147.626 |
123.173 |
0.001 |
-16.57% |
0.001 |
|
SingleSource/Benchmarks/Shootout-C++/Shootout-C++-matrix
Profile
|
-15.64% |
6.589 |
5.559 |
0.002 |
-15.65% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_cond_load_novec_int64_t_
|
-14.69% |
799602.975 |
682154.146 |
292.223 |
-14.80% |
292.223 |
|
External/SPEC/CINT2017rate/525.x264_r/525.x264_r
Profile
|
-14.39% |
122.270 |
104.670 |
0.087 |
-14.48% |
0.087 |
|
MicroBenchmarks/ImageProcessing/Blur/blur.test:BENCHMARK_boxBlurKernel/512
|
-13.55% |
20071.086 |
17351.375 |
41.122 |
-13.95% |
41.122 |
|
MicroBenchmarks/ImageProcessing/Blur/blur.test:BENCHMARK_boxBlurKernel/128
|
-13.52% |
1075.740 |
930.354 |
0.928 |
-13.72% |
0.928 |
|
MicroBenchmarks/ImageProcessing/Blur/blur.test:BENCHMARK_boxBlurKernel/256
|
-13.47% |
4578.052 |
3961.367 |
4.031 |
-13.54% |
4.031 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_ENERGY_CALC_RAW/44217
|
-13.13% |
2318.175 |
2013.817 |
67.717 |
-10.06% |
67.717 |
|
MicroBenchmarks/ImageProcessing/Blur/blur.test:BENCHMARK_boxBlurKernel/1024
|
-12.66% |
84628.125 |
73914.667 |
84.897 |
-12.78% |
84.897 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC128
|
-12.56% |
153.671 |
134.367 |
0.662 |
-12.58% |
0.662 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC1
|
-12.52% |
5.000 |
4.374 |
0.030 |
-9.77% |
0.030 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_only_autovec_int32_t_
|
-12.22% |
1607027.586 |
1410582.150 |
4984.852 |
-11.81% |
4984.852 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopWithReductionTC8
|
-11.76% |
12.150 |
10.721 |
0.000 |
-11.76% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC1
|
-11.55% |
4.939 |
4.368 |
0.010 |
-11.30% |
0.010 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC64
|
-11.17% |
140.805 |
125.076 |
0.002 |
-11.17% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC1
|
-11.11% |
5.717 |
5.082 |
0.000 |
-11.12% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC1
|
-11.11% |
5.718 |
5.082 |
0.000 |
-11.11% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC1
|
-11.11% |
5.718 |
5.082 |
0.001 |
-11.08% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC127
|
-10.91% |
157.241 |
140.088 |
0.111 |
-10.91% |
0.111 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC127
|
-10.85% |
151.520 |
135.076 |
0.015 |
-10.85% |
0.015 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC128
|
-10.75% |
285.889 |
255.159 |
0.007 |
-10.75% |
0.007 |
|
MultiSource/Benchmarks/Trimaran/enc-md5/enc-md5
Profile
|
-10.74% |
3.009 |
2.685 |
0.000 |
-10.75% |
0.000 |
|
MultiSource/Benchmarks/TSVC/Searching-flt/Searching-flt
Profile
|
-10.48% |
11.678 |
10.454 |
0.031 |
-10.48% |
0.031 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC127
|
-10.35% |
283.026 |
253.735 |
5.205 |
-10.37% |
5.205 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC32
|
-10.34% |
71.472 |
64.085 |
0.002 |
-10.34% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC31
|
-10.31% |
69.327 |
62.182 |
0.001 |
-10.31% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC1
|
-9.75% |
5.175 |
4.670 |
0.138 |
-9.25% |
0.138 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC16
|
-9.62% |
37.166 |
33.590 |
0.001 |
-9.62% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC15
|
-9.53% |
35.021 |
31.685 |
0.001 |
-9.53% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC3
|
-9.09% |
7.862 |
7.147 |
0.000 |
-9.10% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint8_t>/256
|
-8.82% |
235.151 |
214.418 |
0.672 |
-9.12% |
0.672 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_FLOYD_DITHER/512
|
-8.71% |
4430.297 |
4044.428 |
15.943 |
-8.79% |
15.943 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_FLOYD_DITHER/256
|
-8.54% |
1104.497 |
1010.139 |
0.120 |
-8.51% |
0.120 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_FLOYD_DITHER/128
|
-8.49% |
272.696 |
249.540 |
0.518 |
-8.77% |
0.518 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopWithReductionTC4
|
-8.34% |
8.577 |
7.862 |
0.000 |
-8.34% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC2
|
-8.33% |
8.576 |
7.862 |
0.000 |
-8.34% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC8
|
-8.33% |
20.012 |
18.345 |
0.000 |
-8.33% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint32_t>/256
|
-8.33% |
232.342 |
212.984 |
0.002 |
-8.17% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC3
|
-8.25% |
8.577 |
7.869 |
0.014 |
-8.25% |
0.014 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<3, GreaterThanZero, First>
|
-8.01% |
24400.021 |
22446.671 |
0.327 |
-8.00% |
0.327 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC7
|
-8.00% |
17.868 |
16.438 |
0.047 |
-8.00% |
0.047 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, GreaterThanZero, First>
|
-8.00% |
36603.639 |
33676.898 |
0.678 |
-8.00% |
0.678 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<5, EqZero, First>
|
-7.99% |
14642.889 |
13472.294 |
0.209 |
-7.99% |
0.209 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIRST_DIFF_LAMBDA/5001
|
-7.94% |
10.873 |
10.010 |
0.000 |
-7.95% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC128
|
-7.93% |
150.900 |
138.938 |
0.074 |
-7.87% |
0.074 |
|
External/SPEC/CFP2017rate/508.namd_r/508.namd_r
Profile
|
-7.73% |
83.972 |
77.480 |
0.094 |
-7.78% |
0.094 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC2
|
-7.70% |
9.292 |
8.576 |
0.000 |
-7.70% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_DEL_DOT_VEC_2D_LAMBDA/2
|
-7.60% |
2.501 |
2.311 |
0.016 |
-1.44% |
0.016 |
|
SingleSource/Benchmarks/Shootout/Shootout-lists
Profile
|
-7.14% |
10.328 |
9.590 |
0.050 |
-7.21% |
0.050 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC2
|
-6.98% |
5.514 |
5.129 |
0.022 |
-5.40% |
0.022 |
|
MultiSource/Benchmarks/MiBench/telecomm-CRC32/telecomm-CRC32
Profile
|
-6.92% |
0.595 |
0.554 |
0.006 |
-7.54% |
0.006 |
|
MicroBenchmarks/ImageProcessing/Blur/blur.test:BENCHMARK_GAUSSIAN_BLUR/256
|
-6.83% |
15347.522 |
14299.041 |
1.887 |
-6.85% |
1.887 |
|
MicroBenchmarks/ImageProcessing/Blur/blur.test:BENCHMARK_GAUSSIAN_BLUR/128
|
-6.82% |
3594.021 |
3349.086 |
0.209 |
-6.82% |
0.209 |
|
MicroBenchmarks/ImageProcessing/Blur/blur.test:BENCHMARK_GAUSSIAN_BLUR/512
|
-6.71% |
63409.545 |
59157.250 |
178.182 |
-6.82% |
178.182 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopWithReductionTC7
|
-6.67% |
10.721 |
10.006 |
0.000 |
-6.67% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC7
|
-6.66% |
10.721 |
10.006 |
0.000 |
-6.66% |
0.000 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, LessThanZero, None>
|
-6.45% |
45382.586 |
42457.297 |
0.352 |
-6.45% |
0.352 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint32_t>/256
|
-6.41% |
423.825 |
396.667 |
0.003 |
-5.46% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC1
|
-6.25% |
5.718 |
5.360 |
0.000 |
-6.25% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC8
|
-6.25% |
11.435 |
10.720 |
0.000 |
-6.26% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC8
|
-6.25% |
11.435 |
10.720 |
0.000 |
-6.26% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1LoopWithReductionTC7
|
-6.25% |
11.436 |
10.721 |
0.000 |
-6.25% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC1
|
-6.25% |
5.717 |
5.360 |
0.000 |
-6.25% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC15
|
-5.94% |
145.133 |
136.516 |
0.003 |
-5.90% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC4
|
-5.89% |
12.150 |
11.435 |
0.000 |
-5.89% |
0.000 |
|
SingleSource/Benchmarks/Adobe-C++/loop_unroll
Profile
|
-5.88% |
1.717 |
1.616 |
0.001 |
-5.71% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC2
|
-5.71% |
5.429 |
5.119 |
0.030 |
-4.77% |
0.030 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC2
|
-5.61% |
5.427 |
5.123 |
0.025 |
-5.58% |
0.025 |
|
SingleSource/Benchmarks/Misc/salsa20
Profile
|
-5.55% |
10.977 |
10.368 |
0.000 |
-5.56% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_cond_load_autovec_int32_t_
|
-5.48% |
546473.026 |
516503.058 |
2230.438 |
-5.18% |
2230.438 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC127
|
-5.48% |
159.175 |
150.456 |
0.056 |
-5.52% |
0.056 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_no_runtime_checks_needed<16, int>
|
-5.46% |
39.310 |
37.165 |
0.001 |
-5.45% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopTC3
|
-5.40% |
28.485 |
26.947 |
0.006 |
-5.41% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopWithReductionTC2
|
-5.35% |
5.432 |
5.141 |
0.007 |
-5.78% |
0.007 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1LoopWithReductionTC1
|
-5.28% |
5.382 |
5.098 |
0.040 |
6.52% |
0.040 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC63
|
-5.15% |
589.732 |
559.333 |
0.006 |
-5.33% |
0.006 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIRST_DIFF_LAMBDA/44217
|
-5.15% |
96.090 |
91.141 |
0.925 |
-5.13% |
0.925 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_xor_no_runtime_checks_needed<16, int>
|
-5.13% |
27.874 |
26.444 |
0.001 |
-5.13% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC31
|
-4.96% |
288.304 |
274.018 |
0.016 |
-4.95% |
0.016 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopTC127
|
-4.92% |
1183.591 |
1125.357 |
0.015 |
-4.93% |
0.015 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC31
|
-4.91% |
288.168 |
274.026 |
0.019 |
-4.91% |
0.019 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC128
|
-4.90% |
1189.643 |
1131.402 |
0.035 |
-4.86% |
0.035 |
|
MultiSource/Benchmarks/VersaBench/ecbdes/ecbdes
Profile
|
-4.87% |
4.024 |
3.828 |
0.001 |
-4.88% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopTC31
|
-4.87% |
288.258 |
274.226 |
0.021 |
-4.87% |
0.021 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC128
|
-4.87% |
1189.736 |
1131.839 |
0.017 |
-4.87% |
0.017 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopTC64
|
-4.86% |
595.628 |
566.684 |
0.020 |
-4.86% |
0.020 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC64
|
-4.84% |
595.619 |
566.764 |
0.010 |
-4.84% |
0.010 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC127
|
-4.84% |
1182.371 |
1125.196 |
0.013 |
-4.67% |
0.013 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC64
|
-4.83% |
595.537 |
566.781 |
0.010 |
-4.82% |
0.010 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopTC128
|
-4.82% |
1189.770 |
1132.442 |
0.015 |
-5.00% |
0.015 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC63
|
-4.81% |
587.569 |
559.329 |
0.011 |
-4.82% |
0.011 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC127
|
-4.79% |
1181.705 |
1125.054 |
0.284 |
-4.80% |
0.284 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_DEL_DOT_VEC_2D_RAW/1
|
-4.76% |
200.057 |
190.533 |
1.412 |
-2.67% |
1.412 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<15, LessThanZero, Mid>
|
-4.74% |
8204.215 |
7815.499 |
0.106 |
-4.74% |
0.106 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopTC63
|
-4.71% |
586.986 |
559.344 |
0.027 |
-4.75% |
0.027 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_ENERGY_CALC_LAMBDA/44217
|
-4.69% |
2141.076 |
2040.708 |
9.854 |
-1.28% |
9.854 |
|
MultiSource/Applications/JM/lencod/lencod
Profile
|
-4.56% |
14.409 |
13.752 |
0.011 |
-4.93% |
0.011 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC7
|
-4.55% |
15.724 |
15.009 |
0.000 |
-4.55% |
0.000 |
|
External/SPEC/CINT2017rate/523.xalancbmk_r/523.xalancbmk_r
Profile
|
-4.48% |
214.543 |
204.922 |
1.487 |
-4.06% |
1.487 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC8
|
-4.41% |
73.807 |
70.551 |
0.001 |
-4.41% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_DEL_DOT_VEC_2D_LAMBDA/1
|
-4.39% |
198.703 |
189.989 |
0.649 |
-3.75% |
0.649 |
|
MultiSource/Applications/kimwitu++/kc
Profile
|
-4.36% |
0.280 |
0.267 |
0.003 |
-1.35% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC15
|
-4.32% |
142.681 |
136.515 |
0.002 |
-4.43% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC3
|
-4.25% |
28.608 |
27.393 |
0.006 |
-4.26% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint16_t_To_uint32_t_
|
-4.24% |
21470.953 |
20561.182 |
35.973 |
-4.16% |
35.973 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC3
|
-4.20% |
28.578 |
27.378 |
0.017 |
-3.77% |
0.017 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint16_t_To_uint32_t_
|
-4.14% |
21450.158 |
20561.421 |
32.458 |
-4.15% |
32.458 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC16
|
-4.12% |
152.630 |
146.344 |
0.002 |
-4.12% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopTC16
|
-4.07% |
152.547 |
146.335 |
0.005 |
-4.08% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopTC8
|
-4.07% |
73.628 |
70.634 |
0.003 |
-4.07% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC16
|
-4.05% |
152.540 |
146.359 |
0.003 |
-4.05% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC2
|
-4.04% |
20.834 |
19.992 |
0.005 |
-4.03% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC8
|
-4.01% |
73.501 |
70.552 |
0.001 |
-4.01% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_PRESSURE_CALC_RAW/44217
|
-3.71% |
385.264 |
370.958 |
5.125 |
-1.09% |
5.125 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, LessThanZero, Last>
|
-3.70% |
39530.777 |
38067.051 |
0.690 |
-3.72% |
0.690 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<3, LessThanZero, Mid>
|
-3.69% |
26349.268 |
25376.291 |
3.603 |
-3.69% |
3.603 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_IMP_HYDRO_2D_LAMBDA/171
|
-3.56% |
12.375 |
11.934 |
0.136 |
-4.58% |
0.136 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_VOL3D_CALC_LAMBDA/2
|
-3.52% |
7.764 |
7.490 |
0.017 |
-3.54% |
0.017 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_VOL3D_CALC_RAW/2
|
-3.52% |
7.764 |
7.491 |
0.001 |
-3.52% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopTC15
|
-3.47% |
141.094 |
136.192 |
0.167 |
-3.47% |
0.167 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopTC32
|
-3.45% |
292.879 |
282.774 |
0.053 |
-3.44% |
0.053 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C/SimpleMOC/SimpleMOC
Profile
|
-3.44% |
8.546 |
8.252 |
0.007 |
-3.42% |
0.007 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint32_t>/10
|
-3.39% |
42.167 |
40.738 |
0.001 |
-3.40% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC32
|
-3.39% |
292.749 |
282.835 |
0.008 |
-3.44% |
0.008 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC32
|
-3.36% |
292.689 |
282.842 |
0.002 |
-3.37% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint32_t>/16
|
-3.28% |
43.598 |
42.169 |
0.001 |
-3.28% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC128
|
-3.25% |
157.357 |
152.239 |
0.006 |
-3.19% |
0.006 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<3, LessThanZero, Last>
|
-3.22% |
30251.113 |
29275.891 |
36.209 |
-3.22% |
36.209 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<5, LessThanZero, Mid>
|
-3.22% |
18153.415 |
17568.811 |
0.198 |
-3.22% |
0.198 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_two_loads<uint8_t>/256
|
-3.13% |
22.871 |
22.156 |
0.000 |
-3.12% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_two_loads<uint8_t>/999
|
-3.13% |
22.870 |
22.156 |
0.001 |
-3.13% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_two_loads<uint8_t>/51
|
-3.13% |
22.870 |
22.156 |
0.000 |
-3.12% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_two_loads<uint8_t>/16
|
-3.13% |
22.870 |
22.155 |
0.000 |
-3.13% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_two_loads<uint8_t>/28
|
-3.12% |
22.871 |
22.156 |
0.000 |
-3.12% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_two_loads<uint8_t>/10
|
-3.12% |
22.870 |
22.156 |
0.000 |
-3.13% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopTC2
|
-3.03% |
20.625 |
20.000 |
0.000 |
-3.09% |
0.000 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<16, LessThanZero, First>
|
-3.02% |
6046.071 |
5863.516 |
0.226 |
-3.02% |
0.226 |
|
MicroBenchmarks/ImageProcessing/Blur/blur.test:BENCHMARK_GAUSSIAN_BLUR/1024
|
-3.00% |
261638.667 |
253790.000 |
220.349 |
-3.01% |
220.349 |
|
MultiSource/Benchmarks/mafft/pairlocalalign
Profile
|
-2.97% |
47.512 |
46.099 |
0.007 |
-2.95% |
0.007 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC2
|
-2.96% |
20.606 |
19.996 |
0.001 |
-3.04% |
0.001 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, GreaterThanZero, None>
|
-2.94% |
24891.623 |
24160.574 |
0.185 |
-2.94% |
0.185 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, LessThanZero, None>
|
-2.94% |
24890.979 |
24160.195 |
0.045 |
-2.93% |
0.045 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<16, GreaterThanZero, Mid>
|
-2.92% |
6228.599 |
6046.528 |
0.055 |
-2.93% |
0.055 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopWithReductionTC1
|
-2.88% |
4.741 |
4.604 |
0.030 |
-1.77% |
0.030 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_ENERGY_CALC_LAMBDA/171
|
-2.85% |
5.877 |
5.710 |
0.030 |
-2.66% |
0.030 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint8_t>/256
|
-2.78% |
411.683 |
400.256 |
2.505 |
-2.75% |
2.505 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<8, LessThanZero, Mid>
|
-2.76% |
13181.373 |
12817.033 |
0.165 |
-2.76% |
0.165 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint8_t>/999
|
-2.71% |
765.526 |
744.747 |
0.672 |
-2.82% |
0.672 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<6, LessThanZero, Last>
|
-2.69% |
18044.778 |
17558.844 |
3.775 |
-2.69% |
3.775 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint64_t>/256
|
-2.63% |
408.120 |
397.373 |
0.013 |
-1.59% |
0.013 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<6, LessThanZero, None>
|
-2.63% |
18530.363 |
18043.645 |
0.197 |
-2.63% |
0.197 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<6, EqZero, None>
|
-2.63% |
18530.907 |
18044.441 |
0.183 |
-2.62% |
0.183 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint32_t>/16
|
-2.60% |
55.032 |
53.604 |
0.001 |
-2.60% |
0.001 |
|
SingleSource/Benchmarks/Misc/revertBits
Profile
|
-2.54% |
0.411 |
0.401 |
0.000 |
-2.51% |
0.000 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<64, GreaterThanZero, Mid>
|
-2.51% |
1792.533 |
1747.495 |
0.024 |
-2.51% |
0.024 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<64, EqZero, Mid>
|
-2.51% |
1792.464 |
1747.473 |
0.039 |
-2.52% |
0.039 |
|
MultiSource/Benchmarks/TSVC/CrossingThresholds-dbl/CrossingThresholds-dbl
Profile
|
-2.50% |
9.857 |
9.610 |
0.004 |
-2.30% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC16
|
-2.50% |
28.589 |
27.874 |
0.001 |
-2.50% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_ENERGY_CALC_LAMBDA/5001
|
-2.48% |
225.808 |
220.200 |
2.080 |
-3.59% |
2.080 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<64, LessThanZero, None>
|
-2.39% |
1883.945 |
1838.937 |
0.047 |
-2.39% |
0.047 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<8, LessThanZero, None>
|
-2.38% |
15378.111 |
15012.268 |
0.228 |
-2.38% |
0.228 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_DEL_DOT_VEC_2D_RAW/2
|
-2.38% |
2.368 |
2.311 |
0.016 |
-2.81% |
0.016 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<8, EqZero, None>
|
-2.38% |
15376.538 |
15011.173 |
0.249 |
-2.38% |
0.249 |
|
SingleSource/Benchmarks/Misc-C++/Large/ray
Profile
|
-2.29% |
7.670 |
7.494 |
0.014 |
-2.34% |
0.014 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint32_t>/16
|
-2.27% |
31.447 |
30.732 |
0.001 |
-2.27% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint32_t>/999
|
-2.25% |
760.471 |
743.331 |
0.013 |
-2.72% |
0.013 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint32_t>/10
|
-2.22% |
32.161 |
31.447 |
0.001 |
-2.22% |
0.001 |
|
SingleSource/Benchmarks/CoyoteBench/huffbench
Profile
|
-2.21% |
32.022 |
31.314 |
0.053 |
-2.25% |
0.053 |
|
SingleSource/Benchmarks/Misc/fbench
Profile
|
-2.19% |
2.930 |
2.866 |
0.001 |
-2.24% |
0.001 |
|
External/SPEC/CFP2017rate/544.nab_r/544.nab_r
Profile
|
-2.18% |
280.016 |
273.916 |
0.013 |
-2.20% |
0.013 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_HYDRO_2D_LAMBDA/44217
|
-2.18% |
29962.565 |
29309.833 |
245.252 |
-1.60% |
245.252 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC8
|
-2.17% |
10.959 |
10.721 |
0.000 |
-2.17% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_nested_cond_load_autovec_int32_t_
|
-2.12% |
1024545.052 |
1002871.942 |
2141.887 |
-2.20% |
2141.887 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint32_t>/10
|
-2.09% |
34.307 |
33.591 |
0.001 |
-2.09% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC15
|
-2.00% |
35.737 |
35.022 |
0.000 |
-2.00% |
0.000 |
|
SingleSource/Benchmarks/Stanford/FloatMM
Profile
|
-1.99% |
0.769 |
0.753 |
0.000 |
-1.98% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint32_t>/16
|
-1.89% |
37.879 |
37.164 |
0.001 |
-1.89% |
0.001 |
|
MultiSource/Applications/aha/aha
Profile
|
-1.85% |
3.874 |
3.802 |
0.001 |
-2.32% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint32_t>/999
|
-1.83% |
1485.925 |
1458.687 |
0.061 |
-1.55% |
0.061 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint32_t>/28
|
-1.79% |
40.025 |
39.309 |
0.001 |
-1.79% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint32_t>/28
|
-1.77% |
80.765 |
79.335 |
0.001 |
-1.77% |
0.001 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C/Pathfinder/PathFinder
Profile
|
-1.71% |
7.221 |
7.098 |
0.024 |
-1.65% |
0.024 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_DEL_DOT_VEC_2D_RAW/0
|
-1.70% |
1221.621 |
1200.830 |
0.442 |
-1.13% |
0.442 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_only_autovec_uint8_t_
|
-1.68% |
803720.046 |
790223.729 |
1642.876 |
-1.54% |
1642.876 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint32_t>/16
|
-1.67% |
42.884 |
42.169 |
0.001 |
-1.67% |
0.001 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<31, LessThanZero, Mid>
|
-1.64% |
5092.493 |
5008.980 |
1.257 |
-1.61% |
1.257 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_ICCG_LAMBDA/44217
|
-1.64% |
291.346 |
286.574 |
0.308 |
-2.56% |
0.308 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint32_t>/51
|
-1.61% |
88.625 |
87.194 |
0.003 |
-1.61% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint8_t>/16
|
-1.61% |
44.312 |
43.597 |
0.000 |
-1.61% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_VOL3D_CALC_LAMBDA/1
|
-1.60% |
208.805 |
205.466 |
0.690 |
-1.55% |
0.690 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_nested_cond_load_novec_int32_t_
|
-1.54% |
1020696.035 |
1004974.026 |
1435.214 |
-1.52% |
1435.214 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint32_t>/51
|
-1.53% |
93.629 |
92.195 |
0.004 |
-1.53% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint32_t>/28
|
-1.51% |
95.060 |
93.628 |
0.002 |
-1.51% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint32_t>/10
|
-1.49% |
47.885 |
47.171 |
0.001 |
-1.49% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_VOL3D_CALC_RAW/1
|
-1.46% |
207.997 |
204.956 |
0.957 |
-2.04% |
0.957 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_DEL_DOT_VEC_2D_LAMBDA/0
|
-1.45% |
1215.586 |
1197.985 |
2.124 |
-1.92% |
2.124 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_csa_with_in_loop_arith_autovec_uint8_t_
|
-1.43% |
519844.361 |
512432.452 |
1328.783 |
-1.29% |
1328.783 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint32_t>/28
|
-1.41% |
50.745 |
50.030 |
0.001 |
-1.41% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1LoopWithReductionTC15
|
-1.35% |
17.630 |
17.391 |
0.000 |
-1.36% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC15
|
-1.35% |
17.630 |
17.391 |
0.000 |
-1.35% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC15
|
-1.35% |
17.630 |
17.391 |
0.001 |
-1.35% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC15
|
-1.35% |
17.630 |
17.391 |
0.001 |
-1.35% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC15
|
-1.35% |
17.630 |
17.392 |
0.000 |
-1.36% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopWithReductionTC15
|
-1.35% |
17.629 |
17.391 |
0.000 |
-1.35% |
0.000 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<63, LessThanZero, None>
|
-1.30% |
3092.542 |
3052.458 |
0.905 |
-1.29% |
0.905 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint32_t>/51
|
-1.28% |
55.748 |
55.033 |
0.002 |
-1.28% |
0.002 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_MAT_X_MAT_LAMBDA/44217
|
-1.26% |
1043364.000 |
1030214.000 |
4641.466 |
-1.37% |
4641.466 |
|
MultiSource/Benchmarks/Rodinia/backprop/backprop
Profile
|
-1.25% |
2.516 |
2.485 |
0.006 |
1.67% |
0.006 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<31, EqZero, Mid>
|
-1.22% |
5009.747 |
4948.415 |
4.383 |
-1.14% |
4.383 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/16
|
-1.21% |
120.528 |
119.069 |
0.001 |
-1.19% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint32_t>/28
|
-1.20% |
59.321 |
58.608 |
0.000 |
-1.21% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_PIC_2D_RAW/171
|
-1.20% |
5.125 |
5.064 |
0.013 |
-0.70% |
0.013 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_VOL3D_CALC_RAW/0
|
-1.20% |
1013.461 |
1001.349 |
2.705 |
-0.88% |
2.705 |
|
MultiSource/Benchmarks/TSVC/LoopRestructuring-flt/LoopRestructuring-flt
Profile
|
-1.19% |
7.628 |
7.537 |
0.017 |
-0.88% |
0.017 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint8_t>/28
|
-1.19% |
60.038 |
59.322 |
0.001 |
-1.19% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint32_t>/28
|
-1.19% |
60.037 |
59.321 |
0.001 |
-1.20% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIND_FIRST_MIN_LAMBDA/5001
|
-1.19% |
12.152 |
12.007 |
0.004 |
-1.45% |
0.004 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_INT_PREDICT_LAMBDA/171
|
-1.17% |
2.092 |
2.067 |
0.000 |
-1.17% |
0.000 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/32
|
-1.14% |
599.468 |
592.649 |
0.152 |
-1.14% |
0.152 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint32_t>/16
|
-1.14% |
62.895 |
62.180 |
0.001 |
-1.14% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint32_t>/51
|
-1.10% |
130.083 |
128.646 |
0.002 |
-1.11% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_erff_novec_float_
|
-1.10% |
529.276 |
523.435 |
0.613 |
-1.10% |
0.613 |
|
External/SPEC/CFP2017rate/511.povray_r/511.povray_r
Profile
|
-1.09% |
16.918 |
16.733 |
0.026 |
-1.38% |
0.026 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint64_t>/999
|
-1.06% |
1475.126 |
1459.454 |
4.721 |
-0.63% |
4.721 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/256
|
-1.04% |
45812.600 |
45335.400 |
39.108 |
-0.92% |
39.108 |
|
MicroBenchmarks/ImageProcessing/AnisotropicDiffusion/AnisotropicDiffusion.test:BENCHMARK_ANISTROPIC_DIFFUSION/32
|
-1.04% |
891.097 |
881.838 |
1.054 |
-0.98% |
1.054 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_MAT_X_MAT_RAW/44217
|
-1.04% |
1035773.000 |
1025046.000 |
3992.805 |
-1.00% |
3992.805 |
|
MultiSource/Applications/lambda-0.1.3/lambda
Profile
|
-1.02% |
22.250 |
22.022 |
0.012 |
-1.07% |
0.012 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/64
|
-1.02% |
2649.678 |
2622.588 |
0.431 |
-1.03% |
0.431 |