|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint8_t_To_uint16_t_
|
-22.21% |
21449.502 |
16686.186 |
12.191 |
-22.21% |
12.191 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint8_t_To_uint16_t_
|
-22.20% |
21449.781 |
16686.898 |
7.821 |
-0.00% |
7.821 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint8_t_To_uint16_t_
|
-22.15% |
21449.672 |
16699.342 |
2.784 |
0.00% |
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
|
-19.76% |
0.569 |
0.457 |
0.000 |
-0.98% |
0.000 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C++/miniFE/miniFE
Profile
|
-17.91% |
22.841 |
18.749 |
0.236 |
-16.54% |
0.236 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopWithReductionTC3
|
-16.66% |
8.576 |
7.147 |
0.000 |
-28.57% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint8_t_To_uint32_t_
|
-16.66% |
14302.108 |
11920.044 |
0.235 |
-16.65% |
0.235 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint16_t_To_uint32_t_
|
-16.65% |
14301.414 |
11919.963 |
0.959 |
-16.65% |
0.959 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopFrom_uint8_t_To_uint64_t_
|
-16.63% |
14302.726 |
11923.788 |
12.272 |
-0.03% |
12.272 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC63
|
-16.57% |
147.645 |
123.173 |
0.001 |
-11.17% |
0.001 |
|
SingleSource/Benchmarks/Shootout-C++/Shootout-C++-matrix
Profile
|
-15.65% |
6.590 |
5.559 |
0.002 |
-0.03% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_cond_load_novec_int64_t_
|
-14.80% |
800642.612 |
682154.146 |
292.223 |
-14.41% |
292.223 |
|
External/SPEC/CINT2017rate/525.x264_r/525.x264_r
Profile
|
-14.48% |
122.397 |
104.670 |
0.087 |
2.30% |
0.087 |
|
MicroBenchmarks/ImageProcessing/Blur/blur.test:BENCHMARK_boxBlurKernel/512
|
-13.95% |
20165.457 |
17351.375 |
41.122 |
0.73% |
41.122 |
|
MicroBenchmarks/ImageProcessing/Blur/blur.test:BENCHMARK_boxBlurKernel/128
|
-13.72% |
1078.239 |
930.354 |
0.928 |
0.25% |
0.928 |
|
MultiSource/Benchmarks/TSVC/NodeSplitting-flt/NodeSplitting-flt
Profile
|
-13.69% |
11.030 |
9.520 |
0.573 |
-1.26% |
0.573 |
|
MicroBenchmarks/ImageProcessing/Blur/blur.test:BENCHMARK_boxBlurKernel/256
|
-13.54% |
4581.993 |
3961.367 |
4.031 |
0.15% |
4.031 |
|
MicroBenchmarks/ImageProcessing/Blur/blur.test:BENCHMARK_boxBlurKernel/1024
|
-12.78% |
84745.125 |
73914.667 |
84.897 |
0.15% |
84.897 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC128
|
-12.58% |
153.707 |
134.367 |
0.662 |
-14.93% |
0.662 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_only_autovec_int32_t_
|
-11.81% |
1599471.396 |
1410582.150 |
4984.852 |
-0.01% |
4984.852 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopWithReductionTC8
|
-11.76% |
12.150 |
10.721 |
0.000 |
-34.78% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC1
|
-11.30% |
4.925 |
4.368 |
0.010 |
-13.93% |
0.010 |
|
MicroBenchmarks/LCALS/SubsetBRawLoops/lcalsBRaw.test:BM_MULADDSUB_RAW/44217
|
-11.21% |
330.370 |
293.321 |
12.980 |
-7.46% |
12.980 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC64
|
-11.17% |
140.799 |
125.076 |
0.002 |
-11.62% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC1
|
-11.12% |
5.718 |
5.082 |
0.000 |
-20.99% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC1
|
-11.11% |
5.718 |
5.082 |
0.000 |
-5.19% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC1
|
-11.08% |
5.716 |
5.082 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC127
|
-10.91% |
157.246 |
140.088 |
0.111 |
-27.14% |
0.111 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC127
|
-10.85% |
151.523 |
135.076 |
0.015 |
-11.48% |
0.015 |
|
MultiSource/Benchmarks/Trimaran/enc-md5/enc-md5
Profile
|
-10.75% |
3.009 |
2.685 |
0.000 |
0.03% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC128
|
-10.75% |
285.895 |
255.159 |
0.007 |
-10.74% |
0.007 |
|
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
|
-10.37% |
283.092 |
253.735 |
5.205 |
-10.35% |
5.205 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC32
|
-10.34% |
71.474 |
64.085 |
0.002 |
-11.22% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC31
|
-10.31% |
69.329 |
62.182 |
0.001 |
-11.22% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_ENERGY_CALC_RAW/44217
|
-10.06% |
2239.189 |
2013.817 |
67.717 |
-3.48% |
67.717 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC1
|
-9.77% |
4.847 |
4.374 |
0.030 |
-13.45% |
0.030 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC16
|
-9.62% |
37.166 |
33.590 |
0.001 |
-11.32% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC15
|
-9.53% |
35.023 |
31.685 |
0.001 |
-11.34% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC1
|
-9.25% |
5.146 |
4.670 |
0.138 |
-8.16% |
0.138 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint8_t>/256
|
-9.12% |
235.927 |
214.418 |
0.672 |
-2.60% |
0.672 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC3
|
-9.10% |
7.862 |
7.147 |
0.000 |
-9.10% |
0.000 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_FLOYD_DITHER/512
|
-8.79% |
4434.291 |
4044.428 |
15.943 |
-0.46% |
15.943 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_FLOYD_DITHER/128
|
-8.77% |
273.519 |
249.540 |
0.518 |
-0.06% |
0.518 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_FLOYD_DITHER/256
|
-8.51% |
1104.129 |
1010.139 |
0.120 |
1.67% |
0.120 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC2
|
-8.34% |
8.577 |
7.862 |
0.000 |
41.48% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopWithReductionTC4
|
-8.34% |
8.577 |
7.862 |
0.000 |
-26.67% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC8
|
-8.33% |
20.011 |
18.345 |
0.000 |
-11.49% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC3
|
-8.25% |
8.577 |
7.869 |
0.014 |
-15.31% |
0.014 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint32_t>/256
|
-8.17% |
231.926 |
212.984 |
0.002 |
-3.87% |
0.002 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<3, GreaterThanZero, First>
|
-8.00% |
24398.606 |
22446.671 |
0.327 |
-4.16% |
0.327 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC7
|
-8.00% |
17.868 |
16.438 |
0.047 |
-11.53% |
0.047 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, GreaterThanZero, First>
|
-8.00% |
36603.682 |
33676.898 |
0.678 |
0.00% |
0.678 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<5, EqZero, First>
|
-7.99% |
14642.963 |
13472.294 |
0.209 |
-0.00% |
0.209 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIRST_DIFF_LAMBDA/5001
|
-7.95% |
10.874 |
10.010 |
0.000 |
-7.94% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC128
|
-7.87% |
150.810 |
138.938 |
0.074 |
-9.88% |
0.074 |
|
External/SPEC/CFP2017rate/508.namd_r/508.namd_r
Profile
|
-7.78% |
84.014 |
77.480 |
0.094 |
-0.00% |
0.094 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC2
|
-7.70% |
9.292 |
8.576 |
0.000 |
-0.00% |
0.000 |
|
MultiSource/Benchmarks/MiBench/telecomm-CRC32/telecomm-CRC32
Profile
|
-7.54% |
0.599 |
0.554 |
0.006 |
-3.52% |
0.006 |
|
SingleSource/Benchmarks/Shootout/Shootout-lists
Profile
|
-7.21% |
10.336 |
9.590 |
0.050 |
-0.06% |
0.050 |
|
MicroBenchmarks/ImageProcessing/Blur/blur.test:BENCHMARK_GAUSSIAN_BLUR/256
|
-6.85% |
15350.239 |
14299.041 |
1.887 |
-0.00% |
1.887 |
|
MicroBenchmarks/ImageProcessing/Blur/blur.test:BENCHMARK_GAUSSIAN_BLUR/512
|
-6.82% |
63490.455 |
59157.250 |
178.182 |
-0.20% |
178.182 |
|
MicroBenchmarks/ImageProcessing/Blur/blur.test:BENCHMARK_GAUSSIAN_BLUR/128
|
-6.82% |
3594.133 |
3349.086 |
0.209 |
-0.04% |
0.209 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopWithReductionTC7
|
-6.67% |
10.721 |
10.006 |
0.000 |
-33.33% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC7
|
-6.66% |
10.720 |
10.006 |
0.000 |
-6.67% |
0.000 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, LessThanZero, None>
|
-6.45% |
45384.920 |
42457.297 |
0.352 |
0.00% |
0.352 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC8
|
-6.26% |
11.436 |
10.720 |
0.000 |
-6.25% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC8
|
-6.26% |
11.436 |
10.720 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC1
|
-6.25% |
5.718 |
5.360 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC1
|
-6.25% |
5.718 |
5.360 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1LoopWithReductionTC7
|
-6.25% |
11.435 |
10.721 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC15
|
-5.90% |
145.081 |
136.516 |
0.003 |
-0.00% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC4
|
-5.89% |
12.150 |
11.435 |
0.000 |
-5.89% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopWithReductionTC2
|
-5.78% |
5.456 |
5.141 |
0.007 |
-34.61% |
0.007 |
|
SingleSource/Benchmarks/Adobe-C++/loop_unroll
Profile
|
-5.71% |
1.714 |
1.616 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC2
|
-5.58% |
5.426 |
5.123 |
0.025 |
-0.99% |
0.025 |
|
SingleSource/Benchmarks/Misc/salsa20
Profile
|
-5.56% |
10.978 |
10.368 |
0.000 |
-0.61% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC127
|
-5.52% |
159.254 |
150.456 |
0.056 |
-5.81% |
0.056 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint32_t>/256
|
-5.46% |
419.561 |
396.667 |
0.003 |
-0.54% |
0.003 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_no_runtime_checks_needed<16, int>
|
-5.45% |
39.309 |
37.165 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopTC3
|
-5.41% |
28.488 |
26.947 |
0.006 |
-1.78% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC2
|
-5.40% |
5.422 |
5.129 |
0.022 |
-1.00% |
0.022 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC63
|
-5.33% |
590.800 |
559.333 |
0.006 |
-0.00% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_cond_load_autovec_int32_t_
|
-5.18% |
544708.398 |
516503.058 |
2230.438 |
-12.69% |
2230.438 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_xor_no_runtime_checks_needed<16, int>
|
-5.13% |
27.874 |
26.444 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIRST_DIFF_LAMBDA/44217
|
-5.13% |
96.070 |
91.141 |
0.925 |
-5.15% |
0.925 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopTC128
|
-5.00% |
1192.039 |
1132.442 |
0.015 |
0.09% |
0.015 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC31
|
-4.95% |
288.299 |
274.018 |
0.016 |
-0.00% |
0.016 |
|
MultiSource/Applications/JM/lencod/lencod
Profile
|
-4.93% |
14.466 |
13.752 |
0.011 |
0.45% |
0.011 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopTC127
|
-4.93% |
1183.661 |
1125.357 |
0.015 |
0.01% |
0.015 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC31
|
-4.91% |
288.178 |
274.026 |
0.019 |
0.01% |
0.019 |
|
MultiSource/Benchmarks/VersaBench/ecbdes/ecbdes
Profile
|
-4.88% |
4.024 |
3.828 |
0.001 |
-0.02% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC128
|
-4.87% |
1189.840 |
1131.839 |
0.017 |
-0.02% |
0.017 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopTC31
|
-4.87% |
288.266 |
274.226 |
0.021 |
0.06% |
0.021 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopTC64
|
-4.86% |
595.656 |
566.684 |
0.020 |
-0.01% |
0.020 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC128
|
-4.86% |
1189.167 |
1131.402 |
0.035 |
-0.06% |
0.035 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC64
|
-4.84% |
595.601 |
566.764 |
0.010 |
-0.00% |
0.010 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC63
|
-4.82% |
587.669 |
559.329 |
0.011 |
0.00% |
0.011 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC64
|
-4.82% |
595.471 |
566.781 |
0.010 |
-0.10% |
0.010 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC127
|
-4.80% |
1181.753 |
1125.054 |
0.284 |
-0.00% |
0.284 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC2
|
-4.77% |
5.376 |
5.119 |
0.030 |
-0.65% |
0.030 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopTC63
|
-4.75% |
587.219 |
559.344 |
0.027 |
-0.00% |
0.027 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<15, LessThanZero, Mid>
|
-4.74% |
8204.573 |
7815.499 |
0.106 |
0.01% |
0.106 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC127
|
-4.67% |
1180.363 |
1125.196 |
0.013 |
0.01% |
0.013 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_IMP_HYDRO_2D_LAMBDA/171
|
-4.58% |
12.507 |
11.934 |
0.136 |
0.37% |
0.136 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_PIC_1D_RAW/44217
|
-4.56% |
1280.958 |
1222.562 |
9.022 |
-0.33% |
9.022 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC7
|
-4.55% |
15.724 |
15.009 |
0.000 |
39.98% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC15
|
-4.43% |
142.837 |
136.515 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC8
|
-4.41% |
73.807 |
70.551 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC3
|
-4.26% |
28.611 |
27.393 |
0.006 |
-0.07% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint16_t_To_uint32_t_
|
-4.16% |
21453.141 |
20561.182 |
35.973 |
-4.14% |
35.973 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint16_t_To_uint32_t_
|
-4.15% |
21451.356 |
20561.421 |
32.458 |
-4.20% |
32.458 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC16
|
-4.12% |
152.626 |
146.344 |
0.002 |
0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopTC16
|
-4.08% |
152.554 |
146.335 |
0.005 |
-0.00% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopTC8
|
-4.07% |
73.631 |
70.634 |
0.003 |
0.05% |
0.003 |
|
External/SPEC/CINT2017rate/523.xalancbmk_r/523.xalancbmk_r
Profile
|
-4.06% |
213.599 |
204.922 |
1.487 |
-1.10% |
1.487 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC16
|
-4.05% |
152.540 |
146.359 |
0.003 |
0.01% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC2
|
-4.03% |
20.832 |
19.992 |
0.005 |
-0.01% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC8
|
-4.01% |
73.498 |
70.552 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC3
|
-3.77% |
28.450 |
27.378 |
0.017 |
-0.14% |
0.017 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_DEL_DOT_VEC_2D_LAMBDA/1
|
-3.75% |
197.400 |
189.989 |
0.649 |
-0.14% |
0.649 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, LessThanZero, Last>
|
-3.72% |
39537.480 |
38067.051 |
0.690 |
-0.00% |
0.690 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<3, LessThanZero, Mid>
|
-3.69% |
26348.054 |
25376.291 |
3.603 |
0.01% |
3.603 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_ENERGY_CALC_LAMBDA/5001
|
-3.59% |
228.397 |
220.200 |
2.080 |
0.52% |
2.080 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_VOL3D_CALC_LAMBDA/2
|
-3.54% |
7.765 |
7.490 |
0.017 |
0.00% |
0.017 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_VOL3D_CALC_RAW/2
|
-3.52% |
7.764 |
7.491 |
0.001 |
0.01% |
0.001 |
|
SingleSource/Benchmarks/Polybench/stencils/heat-3d/heat-3d
Profile
|
-3.47% |
18.686 |
18.038 |
0.207 |
-0.52% |
0.207 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopTC15
|
-3.47% |
141.083 |
136.192 |
0.167 |
-0.46% |
0.167 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopTC32
|
-3.44% |
292.859 |
282.774 |
0.053 |
-0.06% |
0.053 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC32
|
-3.44% |
292.910 |
282.835 |
0.008 |
-0.00% |
0.008 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C/SimpleMOC/SimpleMOC
Profile
|
-3.42% |
8.545 |
8.252 |
0.007 |
0.42% |
0.007 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint32_t>/10
|
-3.40% |
42.171 |
40.738 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC32
|
-3.37% |
292.714 |
282.842 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint32_t>/16
|
-3.28% |
43.600 |
42.169 |
0.001 |
-7.81% |
0.001 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<3, LessThanZero, Last>
|
-3.22% |
30250.519 |
29275.891 |
36.209 |
0.00% |
36.209 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<5, LessThanZero, Mid>
|
-3.22% |
18153.635 |
17568.811 |
0.198 |
-3.22% |
0.198 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC128
|
-3.19% |
157.252 |
152.239 |
0.006 |
-21.40% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_two_loads<uint8_t>/16
|
-3.13% |
22.872 |
22.155 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_two_loads<uint8_t>/10
|
-3.13% |
22.872 |
22.156 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_two_loads<uint8_t>/999
|
-3.13% |
22.871 |
22.156 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_two_loads<uint8_t>/28
|
-3.12% |
22.870 |
22.156 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_two_loads<uint8_t>/256
|
-3.12% |
22.870 |
22.156 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_two_loads<uint8_t>/51
|
-3.12% |
22.870 |
22.156 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopTC2
|
-3.09% |
20.636 |
20.000 |
0.000 |
-0.05% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC2
|
-3.04% |
20.621 |
19.996 |
0.001 |
-0.06% |
0.001 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<16, LessThanZero, First>
|
-3.02% |
6046.351 |
5863.516 |
0.226 |
-0.00% |
0.226 |
|
MicroBenchmarks/ImageProcessing/Blur/blur.test:BENCHMARK_GAUSSIAN_BLUR/1024
|
-3.01% |
261662.333 |
253790.000 |
220.349 |
0.02% |
220.349 |
|
MultiSource/Benchmarks/mafft/pairlocalalign
Profile
|
-2.95% |
47.502 |
46.099 |
0.007 |
-0.20% |
0.007 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, GreaterThanZero, None>
|
-2.94% |
24891.556 |
24160.574 |
0.185 |
-2.94% |
0.185 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, LessThanZero, None>
|
-2.93% |
24890.335 |
24160.195 |
0.045 |
0.00% |
0.045 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<16, GreaterThanZero, Mid>
|
-2.93% |
6229.056 |
6046.528 |
0.055 |
-0.01% |
0.055 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint8_t>/999
|
-2.82% |
766.355 |
744.747 |
0.672 |
-1.23% |
0.672 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_DEL_DOT_VEC_2D_RAW/2
|
-2.81% |
2.378 |
2.311 |
0.016 |
-1.46% |
0.016 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<8, LessThanZero, Mid>
|
-2.76% |
13181.481 |
12817.033 |
0.165 |
0.01% |
0.165 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint8_t>/256
|
-2.75% |
411.584 |
400.256 |
2.505 |
-4.01% |
2.505 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint32_t>/999
|
-2.72% |
764.097 |
743.331 |
0.013 |
-1.14% |
0.013 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<6, LessThanZero, Last>
|
-2.69% |
18044.416 |
17558.844 |
3.775 |
-2.69% |
3.775 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_DEL_DOT_VEC_2D_RAW/1
|
-2.67% |
195.753 |
190.533 |
1.412 |
0.14% |
1.412 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_ENERGY_CALC_LAMBDA/171
|
-2.66% |
5.866 |
5.710 |
0.030 |
-0.86% |
0.030 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<6, LessThanZero, None>
|
-2.63% |
18531.556 |
18043.645 |
0.197 |
-0.03% |
0.197 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<6, EqZero, None>
|
-2.62% |
18530.563 |
18044.441 |
0.183 |
-2.63% |
0.183 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint32_t>/16
|
-2.60% |
55.032 |
53.604 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_ICCG_LAMBDA/44217
|
-2.56% |
294.116 |
286.574 |
0.308 |
0.98% |
0.308 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_IMP_HYDRO_2D_LAMBDA/5001
|
-2.52% |
385.598 |
375.883 |
0.956 |
-1.14% |
0.956 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<64, EqZero, Mid>
|
-2.52% |
1792.616 |
1747.473 |
0.039 |
-0.00% |
0.039 |
|
SingleSource/Benchmarks/Misc/revertBits
Profile
|
-2.51% |
0.411 |
0.401 |
0.000 |
-0.04% |
0.000 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<64, GreaterThanZero, Mid>
|
-2.51% |
1792.477 |
1747.495 |
0.024 |
-2.51% |
0.024 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC16
|
-2.50% |
28.587 |
27.874 |
0.001 |
50.98% |
0.001 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<64, LessThanZero, None>
|
-2.39% |
1884.020 |
1838.937 |
0.047 |
-0.04% |
0.047 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<8, LessThanZero, None>
|
-2.38% |
15378.883 |
15012.268 |
0.228 |
-0.00% |
0.228 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<8, EqZero, None>
|
-2.38% |
15377.183 |
15011.173 |
0.249 |
-0.00% |
0.249 |
|
SingleSource/Benchmarks/Misc-C++/Large/ray
Profile
|
-2.34% |
7.674 |
7.494 |
0.014 |
-0.44% |
0.014 |
|
MultiSource/Applications/aha/aha
Profile
|
-2.32% |
3.892 |
3.802 |
0.001 |
0.71% |
0.001 |
|
MultiSource/Benchmarks/TSVC/CrossingThresholds-dbl/CrossingThresholds-dbl
Profile
|
-2.30% |
9.836 |
9.610 |
0.004 |
-0.15% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint32_t>/16
|
-2.27% |
31.447 |
30.732 |
0.001 |
-0.00% |
0.001 |
|
SingleSource/Benchmarks/CoyoteBench/huffbench
Profile
|
-2.25% |
32.034 |
31.314 |
0.053 |
-18.21% |
0.053 |
|
SingleSource/Benchmarks/Misc/fbench
Profile
|
-2.24% |
2.932 |
2.866 |
0.001 |
0.03% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint32_t>/10
|
-2.22% |
32.162 |
31.447 |
0.001 |
-2.22% |
0.001 |
|
External/SPEC/CFP2017rate/544.nab_r/544.nab_r
Profile
|
-2.20% |
280.086 |
273.916 |
0.013 |
-1.16% |
0.013 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_nested_cond_load_autovec_int32_t_
|
-2.20% |
1025420.354 |
1002871.942 |
2141.887 |
-2.18% |
2141.887 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC8
|
-2.17% |
10.959 |
10.721 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint32_t>/10
|
-2.09% |
34.308 |
33.591 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_VOL3D_CALC_RAW/1
|
-2.04% |
209.231 |
204.956 |
0.957 |
-0.37% |
0.957 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC15
|
-2.00% |
35.737 |
35.022 |
0.000 |
0.00% |
0.000 |
|
SingleSource/Benchmarks/Stanford/FloatMM
Profile
|
-1.98% |
0.769 |
0.753 |
0.000 |
0.01% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_DEL_DOT_VEC_2D_LAMBDA/0
|
-1.92% |
1221.399 |
1197.985 |
2.124 |
0.00% |
2.124 |
|
MultiSource/Benchmarks/TSVC/ControlFlow-dbl/ControlFlow-dbl
Profile
|
-1.91% |
10.945 |
10.736 |
0.073 |
-0.30% |
0.073 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint32_t>/16
|
-1.89% |
37.881 |
37.164 |
0.001 |
-1.89% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint32_t>/28
|
-1.79% |
40.026 |
39.309 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint32_t>/28
|
-1.77% |
80.765 |
79.335 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopWithReductionTC1
|
-1.77% |
4.687 |
4.604 |
0.030 |
-8.92% |
0.030 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint32_t>/16
|
-1.67% |
42.885 |
42.169 |
0.001 |
0.00% |
0.001 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C/Pathfinder/PathFinder
Profile
|
-1.65% |
7.217 |
7.098 |
0.024 |
-1.05% |
0.024 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<31, LessThanZero, Mid>
|
-1.61% |
5091.194 |
5008.980 |
1.257 |
-0.65% |
1.257 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint8_t>/16
|
-1.61% |
44.313 |
43.597 |
0.000 |
-3.17% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint32_t>/51
|
-1.61% |
88.624 |
87.194 |
0.003 |
-7.58% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint64_t>/256
|
-1.59% |
403.811 |
397.373 |
0.013 |
-0.00% |
0.013 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint32_t>/999
|
-1.55% |
1481.706 |
1458.687 |
0.061 |
-0.15% |
0.061 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_VOL3D_CALC_LAMBDA/1
|
-1.55% |
208.694 |
205.466 |
0.690 |
-1.12% |
0.690 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_only_autovec_uint8_t_
|
-1.54% |
802556.962 |
790223.729 |
1642.876 |
-0.01% |
1642.876 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint32_t>/51
|
-1.53% |
93.627 |
92.195 |
0.004 |
-0.01% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_nested_cond_load_novec_int32_t_
|
-1.52% |
1020456.681 |
1004974.026 |
1435.214 |
-2.06% |
1435.214 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint32_t>/28
|
-1.51% |
95.063 |
93.628 |
0.002 |
-7.09% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint32_t>/10
|
-1.49% |
47.885 |
47.171 |
0.001 |
-4.35% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIND_FIRST_MIN_LAMBDA/5001
|
-1.45% |
12.183 |
12.007 |
0.004 |
11.88% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint32_t>/28
|
-1.41% |
50.746 |
50.030 |
0.001 |
-1.41% |
0.001 |
|
External/SPEC/CFP2017rate/511.povray_r/511.povray_r
Profile
|
-1.38% |
16.967 |
16.733 |
0.026 |
-2.06% |
0.026 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_MAT_X_MAT_LAMBDA/44217
|
-1.37% |
1044507.000 |
1030214.000 |
4641.466 |
-0.40% |
4641.466 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC15
|
-1.36% |
17.631 |
17.392 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1LoopWithReductionTC15
|
-1.36% |
17.630 |
17.391 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC15
|
-1.35% |
17.630 |
17.391 |
0.001 |
-35.97% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC15
|
-1.35% |
17.630 |
17.391 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC15
|
-1.35% |
17.630 |
17.391 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopWithReductionTC15
|
-1.35% |
17.629 |
17.391 |
0.000 |
-34.23% |
0.000 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<63, LessThanZero, None>
|
-1.29% |
3092.455 |
3052.458 |
0.905 |
-1.27% |
0.905 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_csa_with_in_loop_arith_autovec_uint8_t_
|
-1.29% |
519106.049 |
512432.452 |
1328.783 |
0.18% |
1328.783 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint32_t>/51
|
-1.28% |
55.748 |
55.033 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_ENERGY_CALC_LAMBDA/44217
|
-1.28% |
2067.220 |
2040.708 |
9.854 |
-0.85% |
9.854 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint32_t>/28
|
-1.21% |
59.325 |
58.608 |
0.000 |
-6.82% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint32_t>/28
|
-1.20% |
60.040 |
59.321 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint8_t>/28
|
-1.19% |
60.037 |
59.322 |
0.001 |
-1.19% |
0.001 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/16
|
-1.19% |
120.500 |
119.069 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_INT_PREDICT_LAMBDA/171
|
-1.17% |
2.092 |
2.067 |
0.000 |
0.13% |
0.000 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/32
|
-1.14% |
599.504 |
592.649 |
0.152 |
-0.06% |
0.152 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint32_t>/16
|
-1.14% |
62.899 |
62.180 |
0.001 |
-6.45% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIND_FIRST_MIN_RAW/44217
|
-1.14% |
127.325 |
125.875 |
0.529 |
-2.77% |
0.529 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<31, EqZero, Mid>
|
-1.14% |
5005.320 |
4948.415 |
4.383 |
-0.01% |
4.383 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_DEL_DOT_VEC_2D_RAW/0
|
-1.13% |
1214.587 |
1200.830 |
0.442 |
-0.00% |
0.442 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint32_t>/51
|
-1.11% |
130.087 |
128.646 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_erff_novec_float_
|
-1.10% |
529.279 |
523.435 |
0.613 |
-0.92% |
0.613 |
|
MultiSource/Applications/lambda-0.1.3/lambda
Profile
|
-1.07% |
22.260 |
22.022 |
0.012 |
-0.53% |
0.012 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/64
|
-1.03% |
2650.008 |
2622.588 |
0.431 |
-0.02% |
0.431 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<63, EqZero, Last>
|
-1.03% |
3127.867 |
3095.776 |
3.922 |
-0.90% |
3.922 |
|
SingleSource/Benchmarks/Shootout-C++/Shootout-C++-hash2
Profile
|
-1.02% |
5.185 |
5.132 |
0.001 |
-0.12% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_MAT_X_MAT_RAW/44217
|
-1.00% |
1035436.000 |
1025046.000 |
3992.805 |
-1.29% |
3992.805 |