|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_HYDRO_2D_LAMBDA/44217
|
-66.00% |
84378.312 |
28686.573 |
15604.905 |
-68.45% |
15604.905 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_HYDRO_2D_LAMBDA/5001
|
-63.57% |
9105.060 |
3316.931 |
1644.014 |
-63.60% |
1644.014 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_DISC_ORD_LAMBDA/44217
|
-56.68% |
13298.880 |
5761.432 |
2712.720 |
-59.01% |
2712.720 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint64_t_To_uint32_t_
|
-49.84% |
35255.300 |
17685.507 |
629.568 |
-49.92% |
629.568 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint64_t_To_uint16_t_
|
-49.45% |
35734.938 |
18062.768 |
542.130 |
-49.38% |
542.130 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint64_t_To_uint8_t_
|
-48.77% |
37061.196 |
18987.905 |
26.289 |
-48.77% |
26.289 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C/miniGMG/miniGMG
Profile
|
-46.93% |
8.833 |
4.688 |
0.149 |
-48.99% |
0.149 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_HYDRO_2D_RAW/44217
|
-45.80% |
92768.547 |
50278.483 |
13548.153 |
-40.61% |
13548.153 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint16_t_To_uint64_t_
|
-44.06% |
18673.809 |
10445.952 |
0.634 |
-44.06% |
0.634 |
|
MultiSource/Benchmarks/MiBench/automotive-bitcount/automotive-bitcount
Profile
|
-43.06% |
0.178 |
0.101 |
0.001 |
-18.06% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_DIFF_PREDICT_LAMBDA/44217
|
-42.12% |
23298.567 |
13485.538 |
312.890 |
-41.63% |
312.890 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_DIFF_PREDICT_RAW/44217
|
-41.89% |
23219.137 |
13493.241 |
322.986 |
-42.09% |
322.986 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_DIFF_PREDICT_LAMBDA/5001
|
-41.34% |
2570.135 |
1507.521 |
48.533 |
-39.93% |
48.533 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint8_t_To_uint64_t_
|
-40.83% |
17797.286 |
10529.767 |
5.537 |
-40.84% |
5.537 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint64_t_To_uint32_t_
|
-40.67% |
38145.684 |
22633.241 |
219.360 |
-40.68% |
219.360 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_HYDRO_2D_RAW/5001
|
-40.07% |
9414.863 |
5642.172 |
1244.555 |
-35.86% |
1244.555 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_DIFF_PREDICT_RAW/5001
|
-39.97% |
2549.290 |
1530.267 |
52.597 |
-40.57% |
52.597 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIRST_DIFF_LAMBDA/44217
|
-37.46% |
157.878 |
98.735 |
2.825 |
-31.82% |
2.825 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/32
|
-36.69% |
1396.103 |
883.823 |
0.123 |
-36.69% |
0.123 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/64
|
-36.66% |
6181.037 |
3915.234 |
0.316 |
-36.67% |
0.316 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/16
|
-36.62% |
279.456 |
177.110 |
0.010 |
-36.63% |
0.010 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/256
|
-36.17% |
107133.928 |
68382.270 |
79.666 |
-36.18% |
79.666 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/128
|
-36.10% |
26258.568 |
16778.763 |
10.859 |
-36.13% |
10.859 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint32_t_To_uint64_t_
|
-35.92% |
22635.472 |
14504.092 |
188.076 |
-36.18% |
188.076 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint64_t_To_uint8_t_
|
-34.66% |
30294.547 |
19792.986 |
61.522 |
-34.27% |
61.522 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint64_t_To_uint16_t_
|
-34.08% |
28971.213 |
19096.540 |
35.273 |
-34.03% |
35.273 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIRST_DIFF_RAW/44217
|
-34.06% |
149.817 |
98.794 |
2.043 |
-30.67% |
2.043 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, EqZero, None>
|
-31.23% |
20509.485 |
14104.049 |
0.625 |
-31.24% |
0.625 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_DISC_ORD_RAW/44217
|
-29.15% |
14232.872 |
10083.472 |
1525.293 |
-24.42% |
1525.293 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint64_t_To_uint16_t_
|
-28.71% |
25917.742 |
18476.526 |
79.709 |
-28.65% |
79.709 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint32_t_To_uint8_t_
|
-28.13% |
13514.641 |
9713.425 |
22.110 |
-27.88% |
22.110 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC128
|
-27.99% |
1292.552 |
930.758 |
4.447 |
-28.01% |
4.447 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_PIC_2D_LAMBDA/44217
|
-27.88% |
11947.523 |
8616.080 |
572.767 |
-21.41% |
572.767 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC64
|
-27.37% |
654.139 |
475.114 |
1.842 |
-27.31% |
1.842 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC32
|
-27.25% |
334.734 |
243.531 |
0.882 |
-27.07% |
0.882 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC128
|
-27.15% |
559.663 |
407.727 |
0.054 |
-26.87% |
0.054 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC16
|
-27.02% |
174.888 |
127.629 |
0.429 |
-26.56% |
0.429 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_PIC_2D_LAMBDA/5001
|
-26.62% |
1203.136 |
882.855 |
44.884 |
-20.14% |
44.884 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_PIC_2D_RAW/44217
|
-26.45% |
11841.306 |
8709.211 |
401.612 |
-22.35% |
401.612 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC64
|
-26.04% |
293.598 |
217.134 |
0.112 |
-25.59% |
0.112 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint64_t_To_uint8_t_
|
-24.97% |
27275.120 |
20464.717 |
95.579 |
-24.83% |
95.579 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, EqZero, None>
|
-23.99% |
16025.023 |
12180.963 |
0.490 |
-23.98% |
0.490 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC32
|
-23.89% |
160.321 |
122.016 |
0.065 |
-23.20% |
0.065 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC128
|
-23.05% |
602.670 |
463.767 |
0.027 |
-23.21% |
0.027 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC128
|
-22.95% |
602.656 |
464.370 |
0.018 |
-23.11% |
0.018 |
|
MicroBenchmarks/ImageProcessing/Blur/blur.test:BENCHMARK_boxBlurKernel/1024
|
-22.66% |
30144.127 |
23313.882 |
81.958 |
-22.67% |
81.958 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC127
|
-22.10% |
614.584 |
478.746 |
0.055 |
-22.18% |
0.055 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC64
|
-22.04% |
312.230 |
243.418 |
0.017 |
-22.36% |
0.017 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint8_t_To_uint32_t_
|
-21.94% |
6624.731 |
5171.070 |
3.632 |
-21.44% |
3.632 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC127
|
-21.90% |
614.593 |
479.996 |
0.033 |
-21.98% |
0.033 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint16_t_To_uint64_t_
|
-21.88% |
13265.720 |
10363.269 |
27.365 |
-21.54% |
27.365 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC64
|
-21.85% |
312.268 |
244.045 |
0.047 |
-22.16% |
0.047 |
|
SingleSource/Benchmarks/Adobe-C++/loop_unroll
Profile
|
-21.82% |
3.095 |
2.420 |
0.001 |
-22.12% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint16_t_To_uint32_t_
|
-21.70% |
7111.438 |
5568.459 |
2.367 |
-21.58% |
2.367 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_only_autovec_uint8_t_
|
-21.40% |
182386.073 |
143352.285 |
64.713 |
-21.39% |
64.713 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIND_FIRST_MIN_LAMBDA/44217
|
-21.30% |
389.460 |
306.489 |
0.397 |
-21.33% |
0.397 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIND_FIRST_MIN_LAMBDA/171
|
-21.27% |
1.501 |
1.181 |
0.000 |
-21.28% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIND_FIRST_MIN_LAMBDA/5001
|
-20.43% |
45.152 |
35.926 |
0.069 |
-20.62% |
0.069 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC16
|
-20.38% |
93.528 |
74.471 |
0.024 |
-19.30% |
0.024 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC63
|
-20.27% |
324.154 |
258.439 |
0.020 |
-20.43% |
0.020 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC32
|
-20.23% |
167.068 |
133.274 |
0.009 |
-20.82% |
0.009 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC127
|
-20.05% |
274.773 |
219.680 |
0.473 |
-20.25% |
0.473 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIRST_SUM_RAW/44217
|
-20.05% |
168.845 |
134.994 |
0.875 |
-18.84% |
0.875 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC128
|
-20.03% |
273.753 |
218.919 |
1.898 |
-20.32% |
1.898 |
|
MultiSource/Benchmarks/Trimaran/enc-pc1/enc-pc1
Profile
|
-19.94% |
1.130 |
0.904 |
0.000 |
-18.10% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC63
|
-19.88% |
324.140 |
259.687 |
0.018 |
-20.05% |
0.018 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC16
|
-19.87% |
97.607 |
78.217 |
0.002 |
-18.30% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC32
|
-19.85% |
167.066 |
133.901 |
0.019 |
-20.45% |
0.019 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC127
|
-19.85% |
642.016 |
514.571 |
0.091 |
-19.66% |
0.091 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint16_t_To_uint8_t_
|
-19.05% |
3815.998 |
3089.140 |
0.095 |
-19.09% |
0.095 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_VOL3D_CALC_LAMBDA/2
|
-18.81% |
8.757 |
7.110 |
0.001 |
-18.81% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_VOL3D_CALC_RAW/2
|
-18.81% |
8.757 |
7.110 |
0.001 |
-18.80% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint64_t_To_uint32_t_
|
-18.62% |
27108.870 |
22061.129 |
87.511 |
-18.45% |
87.511 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint32_t_To_uint16_t_
|
-18.52% |
13796.574 |
11240.880 |
9.580 |
-18.59% |
9.580 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint32_t_To_uint8_t_
|
-18.46% |
13904.962 |
11337.561 |
8.608 |
-18.44% |
8.608 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIRST_SUM_LAMBDA/44217
|
-18.41% |
166.035 |
135.472 |
1.578 |
-18.92% |
1.578 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_with_cond_arith_novec_uint8_t_
|
-17.91% |
746208.375 |
612529.636 |
262.518 |
-17.87% |
262.518 |
|
MultiSource/Benchmarks/MiBench/security-rijndael/security-rijndael
Profile
|
-17.53% |
0.335 |
0.277 |
0.000 |
-17.34% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC4
|
-17.44% |
17.519 |
14.463 |
0.016 |
-17.45% |
0.016 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_with_cond_arith_novec_int32_t_
|
-17.42% |
740096.793 |
611140.330 |
1620.206 |
-17.43% |
1620.206 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC63
|
-17.25% |
149.563 |
123.767 |
4.027 |
-17.44% |
4.027 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC31
|
-17.13% |
178.955 |
148.299 |
0.003 |
-17.42% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC128
|
-17.08% |
569.490 |
472.195 |
0.046 |
-17.24% |
0.046 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC64
|
-17.03% |
148.752 |
123.422 |
0.717 |
-16.96% |
0.717 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC64
|
-16.77% |
296.587 |
246.845 |
0.030 |
-17.09% |
0.030 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC16
|
-16.55% |
94.480 |
78.844 |
0.001 |
-17.65% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC31
|
-16.46% |
179.016 |
149.544 |
0.008 |
-16.73% |
0.008 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_VOL3D_CALC_LAMBDA/0
|
-16.34% |
1267.873 |
1060.657 |
1.520 |
-16.33% |
1.520 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint8_t_To_uint64_t_
|
-16.28% |
13034.139 |
10912.475 |
3.882 |
-16.48% |
3.882 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC32
|
-16.25% |
160.183 |
134.153 |
0.037 |
-16.88% |
0.037 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_VOL3D_CALC_RAW/0
|
-16.23% |
1268.353 |
1062.524 |
1.147 |
-16.02% |
1.147 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_VOL3D_CALC_LAMBDA/1
|
-16.12% |
260.086 |
218.156 |
0.191 |
-16.15% |
0.191 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_VOL3D_CALC_RAW/1
|
-16.11% |
260.167 |
218.257 |
0.153 |
-16.10% |
0.153 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_HYDRO_1D_LAMBDA/171
|
-16.06% |
0.443 |
0.372 |
0.000 |
-15.87% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_HYDRO_1D_RAW/171
|
-15.86% |
0.442 |
0.372 |
0.000 |
-15.83% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC16
|
-15.75% |
91.995 |
77.502 |
0.201 |
-16.78% |
0.201 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint16_t_To_uint32_t_
|
-15.67% |
7462.164 |
6293.157 |
0.231 |
-15.67% |
0.231 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_PIC_2D_RAW/5001
|
-15.44% |
1100.935 |
930.958 |
20.370 |
-13.67% |
20.370 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint32_t_To_uint8_t_
|
-15.40% |
10631.770 |
8994.563 |
32.210 |
-15.11% |
32.210 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_no_runtime_checks_needed<16, int>
|
-15.38% |
24.402 |
20.648 |
0.001 |
-15.39% |
0.001 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, EqZero, Mid>
|
-15.38% |
16666.983 |
14103.427 |
1.077 |
-15.38% |
1.077 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, EqZero, First>
|
-15.38% |
16666.714 |
14103.795 |
0.622 |
-15.40% |
0.622 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, EqZero, Last>
|
-15.37% |
16670.418 |
14108.089 |
1.219 |
-15.35% |
1.219 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint32_t_To_uint16_t_
|
-15.09% |
10953.274 |
9300.058 |
171.095 |
-13.39% |
171.095 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC127
|
-14.73% |
605.208 |
516.040 |
0.062 |
-14.81% |
0.062 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC4
|
-14.69% |
112.641 |
96.095 |
0.957 |
-15.03% |
0.957 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint32_t_To_uint8_t_
|
-14.56% |
11062.107 |
9451.799 |
71.361 |
-15.07% |
71.361 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC128
|
-14.48% |
1102.067 |
942.485 |
0.098 |
-14.58% |
0.098 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint64_t_To_uint8_t_
|
-14.47% |
22187.678 |
18977.161 |
45.651 |
-13.93% |
45.651 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC127
|
-14.47% |
1094.621 |
936.281 |
0.041 |
-14.52% |
0.041 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC64
|
-14.16% |
561.313 |
481.828 |
0.036 |
-14.31% |
0.036 |
|
SingleSource/Benchmarks/Misc/salsa20
Profile
|
-14.14% |
15.386 |
13.211 |
0.001 |
-14.13% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC63
|
-14.13% |
553.838 |
475.567 |
0.169 |
-14.27% |
0.169 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint8_t_To_uint16_t_
|
-14.03% |
3756.366 |
3229.415 |
5.219 |
-14.03% |
5.219 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_with_cond_arith_novec_int64_t_
|
-14.02% |
790685.703 |
679848.144 |
1995.745 |
-13.73% |
1995.745 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC32
|
-13.88% |
85.330 |
73.485 |
1.346 |
-13.88% |
1.346 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC1
|
-13.86% |
51.937 |
44.737 |
0.002 |
-13.86% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC7
|
-13.86% |
51.935 |
44.737 |
0.003 |
-13.86% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC2
|
-13.86% |
51.937 |
44.740 |
0.002 |
-13.85% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC3
|
-13.85% |
51.933 |
44.738 |
0.003 |
-13.86% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC4
|
-13.85% |
51.934 |
44.740 |
0.001 |
-13.85% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC8
|
-13.85% |
51.935 |
44.741 |
0.001 |
-13.86% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC63
|
-13.77% |
375.977 |
324.195 |
0.018 |
-13.42% |
0.018 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, EqZero, First>
|
-13.62% |
14103.054 |
12181.564 |
0.603 |
-13.62% |
0.603 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, EqZero, Last>
|
-13.62% |
14102.365 |
12181.867 |
0.591 |
-13.63% |
0.591 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, EqZero, Mid>
|
-13.62% |
14102.635 |
12182.213 |
0.992 |
-13.62% |
0.992 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_with_cond_arith_autovec_int64_t_
|
-13.62% |
789147.825 |
681694.117 |
628.208 |
-13.88% |
628.208 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC8
|
-13.61% |
57.581 |
49.746 |
0.001 |
-15.35% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC32
|
-13.54% |
290.965 |
251.555 |
0.002 |
-13.85% |
0.002 |
|
External/SPEC/CFP2017rate/508.namd_r/508.namd_r
Profile
|
-13.54% |
223.220 |
192.991 |
0.804 |
-13.68% |
0.804 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC8
|
-13.54% |
23.150 |
20.016 |
0.003 |
-13.55% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint32_t_To_uint16_t_
|
-13.47% |
9867.360 |
8538.268 |
94.294 |
-13.80% |
94.294 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC31
|
-13.47% |
283.454 |
245.281 |
0.019 |
-13.66% |
0.019 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint32_t_To_uint16_t_
|
-13.16% |
12783.511 |
11101.554 |
6.918 |
-13.52% |
6.918 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC8
|
-13.15% |
23.775 |
20.649 |
0.001 |
-13.16% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC128
|
-13.08% |
81.345 |
70.707 |
0.002 |
-13.08% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint8_t_To_uint16_t_
|
-12.94% |
4541.578 |
3953.884 |
0.142 |
-12.95% |
0.142 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC8
|
-12.91% |
58.194 |
50.682 |
0.005 |
-14.75% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC31
|
-12.89% |
86.300 |
75.178 |
0.549 |
-12.70% |
0.549 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_INT_PREDICT_RAW/44217
|
-12.82% |
9143.957 |
7971.268 |
100.253 |
-11.91% |
100.253 |
|
SingleSource/Benchmarks/Shootout-C++/Shootout-C++-matrix
Profile
|
-12.75% |
2.509 |
2.190 |
0.000 |
-12.71% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC63
|
-12.51% |
332.271 |
290.691 |
0.014 |
-12.66% |
0.014 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC16
|
-12.45% |
155.808 |
136.415 |
0.042 |
-13.09% |
0.042 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint16_t_To_uint8_t_
|
-12.43% |
4743.998 |
4154.388 |
0.374 |
-12.41% |
0.374 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC15
|
-12.35% |
106.376 |
93.238 |
0.003 |
-12.86% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC15
|
-12.24% |
148.286 |
130.130 |
0.017 |
-12.55% |
0.017 |
|
MicroBenchmarks/ImageProcessing/Dilate/Dilate.test:BENCHMARK_DILATE/128
|
-12.03% |
221.856 |
195.168 |
7.016 |
-14.39% |
7.016 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_INT_PREDICT_RAW/5001
|
-11.87% |
1036.614 |
913.533 |
5.837 |
0.01% |
5.837 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC8
|
-11.82% |
58.192 |
51.312 |
0.001 |
-13.69% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC16
|
-11.82% |
51.936 |
45.800 |
0.091 |
-11.82% |
0.091 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC2
|
-11.77% |
21.275 |
18.772 |
0.001 |
-11.77% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint32_t_To_uint64_t_
|
-11.66% |
17106.518 |
15112.521 |
550.497 |
-12.12% |
550.497 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC16
|
-11.45% |
33.164 |
29.365 |
0.021 |
-11.45% |
0.021 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC15
|
-11.45% |
51.937 |
45.989 |
0.003 |
-11.46% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint64_t_To_uint16_t_
|
-11.20% |
19345.108 |
17177.786 |
756.666 |
-9.51% |
756.666 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC15
|
-11.18% |
106.379 |
94.488 |
0.005 |
-11.70% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC4
|
-11.11% |
22.526 |
20.023 |
0.001 |
-11.11% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC3
|
-11.11% |
22.525 |
20.023 |
0.001 |
-11.11% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC4
|
-11.10% |
22.525 |
20.024 |
0.000 |
-11.11% |
0.000 |
|
MicroBenchmarks/ImageProcessing/Dilate/Dilate.test:BENCHMARK_DILATE/1024
|
-11.10% |
7338.539 |
6524.249 |
110.140 |
-8.25% |
110.140 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint8_t>/51
|
-10.90% |
123.645 |
110.172 |
0.374 |
19.10% |
0.374 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC8
|
-10.63% |
88.223 |
78.841 |
0.005 |
-11.81% |
0.005 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_BAND_LIN_EQ_RAW/171
|
-10.60% |
0.384 |
0.343 |
0.000 |
-6.33% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_BAND_LIN_EQ_LAMBDA/171
|
-10.60% |
0.384 |
0.343 |
0.000 |
-6.32% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_HYDRO_1D_LAMBDA/5001
|
-10.56% |
16.978 |
15.186 |
0.450 |
-11.57% |
0.450 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC4
|
-10.52% |
23.777 |
21.275 |
0.001 |
-10.53% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_PRESSURE_CALC_LAMBDA/5001
|
-10.48% |
44.883 |
40.179 |
1.693 |
-8.63% |
1.693 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC64
|
-10.47% |
53.814 |
48.180 |
0.002 |
-10.47% |
0.002 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_INT_PREDICT_LAMBDA/44217
|
-10.19% |
8862.644 |
7959.835 |
108.778 |
-4.53% |
108.778 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/16
|
-10.18% |
115.465 |
103.716 |
0.007 |
-10.17% |
0.007 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/64
|
-10.10% |
1913.693 |
1720.398 |
0.915 |
-10.08% |
0.915 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint8_t_To_uint16_t_
|
-10.08% |
5848.923 |
5259.198 |
7.988 |
-10.10% |
7.988 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC7
|
-10.08% |
80.722 |
72.584 |
0.007 |
-10.74% |
0.007 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/32
|
-9.98% |
472.945 |
425.755 |
0.029 |
-9.99% |
0.029 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/256
|
-9.92% |
31454.203 |
28333.785 |
29.130 |
-9.91% |
29.130 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC8
|
-9.76% |
25.654 |
23.151 |
0.002 |
-9.77% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC8
|
-9.75% |
25.653 |
23.152 |
0.001 |
-9.76% |
0.001 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/128
|
-9.74% |
7914.754 |
7143.952 |
1.654 |
-9.77% |
1.654 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_only_autovec_int64_t_
|
-9.63% |
333746.265 |
301605.323 |
22.721 |
-9.50% |
22.721 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC7
|
-9.61% |
32.540 |
29.411 |
0.000 |
-9.61% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC7
|
-9.52% |
26.280 |
23.777 |
0.001 |
-9.53% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC1
|
-9.52% |
13.141 |
11.889 |
0.010 |
0.00% |
0.010 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC7
|
-9.52% |
26.280 |
23.778 |
0.001 |
-9.53% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC32
|
-9.43% |
53.187 |
48.173 |
0.008 |
-9.44% |
0.008 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC127
|
-9.26% |
101.372 |
91.983 |
0.004 |
-9.71% |
0.004 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_DEL_DOT_VEC_2D_LAMBDA/1
|
-9.21% |
287.196 |
260.744 |
0.079 |
-9.19% |
0.079 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_DEL_DOT_VEC_2D_RAW/1
|
-9.21% |
287.091 |
260.649 |
0.084 |
-9.18% |
0.084 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC31
|
-9.11% |
195.854 |
178.019 |
0.006 |
-9.39% |
0.006 |
|
MultiSource/Benchmarks/FreeBench/pifft/pifft
Profile
|
-9.06% |
0.360 |
0.328 |
0.000 |
-8.68% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC7
|
-8.88% |
28.156 |
25.655 |
0.001 |
-8.89% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_DEL_DOT_VEC_2D_LAMBDA/2
|
-8.71% |
3.510 |
3.204 |
0.000 |
-8.70% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_DEL_DOT_VEC_2D_RAW/2
|
-8.71% |
3.510 |
3.204 |
0.000 |
-8.70% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC16
|
-8.62% |
36.293 |
33.165 |
0.001 |
-8.62% |
0.001 |
|
SingleSource/Benchmarks/Misc/richards_benchmark
Profile
|
-8.62% |
2.201 |
2.012 |
0.018 |
2.98% |
0.018 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_HYDRO_2D_LAMBDA/171
|
-8.56% |
88.995 |
81.381 |
0.642 |
-8.21% |
0.642 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint16_t_To_uint8_t_
|
-8.53% |
6812.674 |
6231.664 |
7.570 |
-8.57% |
7.570 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC8
|
-8.51% |
29.408 |
26.906 |
0.000 |
-8.52% |
0.000 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_runtime_checks_fail<4, int>
|
-8.50% |
16.754 |
15.329 |
0.001 |
-3.64% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint16_t_To_uint64_t_
|
-8.41% |
20329.875 |
18620.528 |
73.438 |
-7.56% |
73.438 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC64
|
-8.05% |
93.237 |
85.728 |
0.002 |
-8.06% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC4
|
-8.04% |
54.438 |
50.063 |
0.001 |
-10.06% |
0.001 |
|
MultiSource/Benchmarks/McCat/12-IOtest/iotest
Profile
|
-8.03% |
1.819 |
1.673 |
0.010 |
-8.31% |
0.010 |
|
MultiSource/Applications/lambda-0.1.3/lambda
Profile
|
-7.90% |
15.973 |
14.711 |
0.009 |
-7.30% |
0.009 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC16
|
-7.85% |
31.912 |
29.408 |
0.002 |
-7.84% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC16
|
-7.84% |
31.911 |
29.409 |
0.002 |
-7.85% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC4
|
-7.81% |
40.048 |
36.919 |
0.001 |
-10.61% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC32
|
-7.81% |
40.046 |
36.919 |
0.002 |
-7.82% |
0.002 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_DEL_DOT_VEC_2D_RAW/0
|
-7.79% |
1798.008 |
1657.874 |
0.564 |
-7.94% |
0.564 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint8_t_To_uint32_t_
|
-7.77% |
12757.745 |
11765.994 |
19.139 |
-7.93% |
19.139 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_DEL_DOT_VEC_2D_LAMBDA/0
|
-7.73% |
1799.693 |
1660.587 |
1.999 |
-7.33% |
1.999 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint16_t_To_uint64_t_
|
-7.71% |
25074.366 |
23141.695 |
98.943 |
-7.38% |
98.943 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC15
|
-7.69% |
32.538 |
30.035 |
0.000 |
-7.70% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC15
|
-7.69% |
32.537 |
30.036 |
0.002 |
-7.69% |
0.002 |
|
MultiSource/Benchmarks/VersaBench/beamformer/beamformer
Profile
|
-7.68% |
5.202 |
4.802 |
0.002 |
-7.66% |
0.002 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_HYDRO_2D_RAW/171
|
-7.64% |
88.867 |
82.078 |
0.418 |
-7.39% |
0.418 |
|
SingleSource/Benchmarks/Stanford/Puzzle
Profile
|
-7.63% |
0.248 |
0.229 |
0.000 |
-5.21% |
0.000 |
|
MultiSource/Benchmarks/Trimaran/enc-md5/enc-md5
Profile
|
-7.53% |
3.507 |
3.243 |
0.000 |
-7.49% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_DIFF_PREDICT_LAMBDA/171
|
-7.48% |
12.010 |
11.112 |
0.071 |
-7.29% |
0.071 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_xor_no_runtime_checks_needed<16, int>
|
-7.41% |
16.895 |
15.643 |
0.000 |
-7.41% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_DIFF_PREDICT_RAW/171
|
-7.23% |
11.982 |
11.116 |
0.071 |
-6.85% |
0.071 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC7
|
-7.22% |
347.713 |
322.619 |
3.980 |
-9.05% |
3.980 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC128
|
-7.21% |
173.321 |
160.816 |
0.001 |
-7.22% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint8_t>/127
|
-7.21% |
138.924 |
128.909 |
0.005 |
-7.20% |
0.005 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIND_FIRST_MIN_RAW/171
|
-7.20% |
1.497 |
1.389 |
0.000 |
-7.19% |
0.000 |
|
SingleSource/Benchmarks/Misc/pi
Profile
|
-7.04% |
1.782 |
1.657 |
0.000 |
-7.02% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC15
|
-6.95% |
45.055 |
41.925 |
0.095 |
-6.94% |
0.095 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC8
|
-6.93% |
26.220 |
24.403 |
0.001 |
-9.32% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC15
|
-6.90% |
54.439 |
50.684 |
0.002 |
-6.90% |
0.002 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_runtime_checks_pass<4, int>
|
-6.85% |
16.457 |
15.330 |
0.001 |
-8.25% |
0.001 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C++/miniFE/miniFE
Profile
|
-6.83% |
16.035 |
14.940 |
0.068 |
-6.44% |
0.068 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC31
|
-6.72% |
74.465 |
69.464 |
0.004 |
-6.71% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC3
|
-6.66% |
46.926 |
43.801 |
0.001 |
-7.90% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC2
|
-6.58% |
16.896 |
15.784 |
0.129 |
0.84% |
0.129 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC63
|
-6.55% |
114.504 |
106.999 |
0.007 |
-6.56% |
0.007 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_xor_runtime_checks_fail<16, int>
|
-6.53% |
28.783 |
26.905 |
0.003 |
-6.52% |
0.003 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_xor_runtime_checks_pass<16, int>
|
-6.52% |
28.782 |
26.905 |
0.001 |
-6.52% |
0.001 |
|
SingleSource/Benchmarks/Misc/flops-6
Profile
|
-6.52% |
1.312 |
1.226 |
0.001 |
-6.55% |
0.001 |
|
SingleSource/Benchmarks/Misc/oourafft
Profile
|
-6.48% |
15.457 |
14.455 |
0.036 |
-4.23% |
0.036 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_only_autovec_int32_t_
|
-6.46% |
180977.392 |
169279.921 |
532.968 |
-6.54% |
532.968 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC127
|
-6.39% |
2384.349 |
2231.965 |
21.557 |
-8.02% |
21.557 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC15
|
-6.35% |
39.421 |
36.917 |
0.002 |
-6.35% |
0.002 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIND_FIRST_MIN_RAW/5001
|
-6.35% |
45.384 |
42.505 |
0.061 |
-6.25% |
0.061 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC127
|
-6.33% |
194.601 |
182.277 |
0.256 |
-6.34% |
0.256 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint16_t>/127
|
-6.31% |
138.913 |
130.149 |
0.008 |
-6.31% |
0.008 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC7
|
-6.25% |
70.081 |
65.702 |
0.005 |
-7.09% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC4
|
-6.24% |
40.046 |
37.545 |
0.002 |
-9.09% |
0.002 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_BAND_LIN_EQ_RAW/5001
|
-6.21% |
21.428 |
20.097 |
0.033 |
-2.55% |
0.033 |
|
SingleSource/Benchmarks/Misc-C++/Large/sphereflake
Profile
|
-6.20% |
20.012 |
18.771 |
0.003 |
-6.16% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC16
|
-6.15% |
40.670 |
38.170 |
0.001 |
-6.16% |
0.001 |
|
MultiSource/Benchmarks/MiBench/telecomm-gsm/telecomm-gsm
Profile
|
-6.04% |
0.663 |
0.623 |
0.000 |
-6.01% |
0.000 |
|
External/SPEC/CFP2017rate/538.imagick_r/538.imagick_r
Profile
|
-5.95% |
292.027 |
274.665 |
0.526 |
-5.96% |
0.526 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC16
|
-5.94% |
31.932 |
30.036 |
0.084 |
-4.01% |
0.084 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC63
|
-5.92% |
73.830 |
69.456 |
0.002 |
-6.42% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint8_t>/65
|
-5.92% |
95.117 |
89.482 |
0.003 |
-5.92% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC3
|
-5.81% |
21.274 |
20.037 |
0.016 |
0.06% |
0.016 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC16
|
-5.66% |
33.162 |
31.286 |
0.001 |
-5.66% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC32
|
-5.64% |
44.425 |
41.922 |
0.002 |
-5.64% |
0.002 |
|
External/SPEC/CINT2017rate/500.perlbench_r/500.perlbench_r
Profile
|
-5.63% |
153.168 |
144.537 |
0.443 |
-1.47% |
0.443 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC32
|
-5.63% |
44.426 |
41.924 |
0.002 |
-5.64% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1LoopWithReductionTC4
|
-5.61% |
15.247 |
14.392 |
0.001 |
2.26% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint32_t_To_uint64_t_
|
-5.61% |
21497.512 |
20291.798 |
4.610 |
-5.40% |
4.610 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC128
|
-5.58% |
68.207 |
64.405 |
0.024 |
-6.39% |
0.024 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC31
|
-5.56% |
242.502 |
229.026 |
0.008 |
-5.06% |
0.008 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC31
|
-5.55% |
45.052 |
42.550 |
0.001 |
-5.58% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC31
|
-5.55% |
45.051 |
42.549 |
0.001 |
-5.56% |
0.001 |
|
MultiSource/Benchmarks/SciMark2-C/scimark2
Profile
|
-5.54% |
107.707 |
101.736 |
0.032 |
-5.48% |
0.032 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC127
|
-5.53% |
68.201 |
64.428 |
0.011 |
-5.66% |
0.011 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_BAND_LIN_EQ_LAMBDA/5001
|
-5.46% |
21.326 |
20.162 |
0.025 |
-3.06% |
0.025 |
|
MultiSource/Benchmarks/Rodinia/hotspot/hotspot
Profile
|
-5.45% |
2.038 |
1.926 |
0.006 |
-5.38% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint32_t>/127
|
-5.45% |
137.654 |
130.151 |
0.006 |
-5.88% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC32
|
-5.42% |
61.323 |
57.999 |
0.083 |
-5.42% |
0.083 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIND_FIRST_MIN_RAW/44217
|
-5.40% |
389.614 |
368.579 |
0.327 |
-5.39% |
0.327 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint32_t>/999
|
-5.38% |
696.450 |
658.958 |
0.019 |
-5.39% |
0.019 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC1
|
-5.37% |
88.025 |
83.297 |
0.831 |
-6.39% |
0.831 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_ENERGY_CALC_RAW/5001
|
-5.35% |
440.052 |
416.516 |
7.476 |
-2.85% |
7.476 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_PIC_2D_LAMBDA/171
|
-5.31% |
13.515 |
12.797 |
0.048 |
-5.19% |
0.048 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint8_t_To_uint16_t_
|
-5.29% |
3626.353 |
3434.398 |
9.888 |
-5.48% |
9.888 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC1
|
-5.26% |
11.888 |
11.263 |
0.000 |
-0.01% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC1
|
-5.26% |
11.889 |
11.264 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_PIC_2D_RAW/171
|
-5.25% |
13.522 |
12.812 |
0.062 |
-5.37% |
0.062 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint32_t>/999
|
-5.22% |
1364.996 |
1293.698 |
0.012 |
-5.23% |
0.012 |
|
MultiSource/Applications/aha/aha
Profile
|
-5.16% |
5.004 |
4.745 |
0.002 |
0.18% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC2
|
-5.08% |
36.915 |
35.041 |
0.001 |
-8.20% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint8_t>/28
|
-5.00% |
80.674 |
76.638 |
0.311 |
13.39% |
0.311 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC4
|
-4.88% |
25.656 |
24.403 |
0.001 |
-0.01% |
0.001 |
|
MultiSource/Applications/siod/siod
Profile
|
-4.84% |
8.322 |
7.919 |
0.005 |
-0.51% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint32_t>/256
|
-4.81% |
364.164 |
346.648 |
0.023 |
-4.81% |
0.023 |
|
MultiSource/Benchmarks/TSVC/LinearDependence-dbl/LinearDependence-dbl
Profile
|
-4.74% |
23.814 |
22.685 |
0.365 |
0.58% |
0.365 |
|
SingleSource/Benchmarks/Polybench/stencils/jacobi-2d/jacobi-2d
Profile
|
-4.72% |
31.941 |
30.434 |
0.125 |
-5.55% |
0.125 |
|
SingleSource/Benchmarks/Misc/revertBits
Profile
|
-4.67% |
0.641 |
0.611 |
0.000 |
-4.68% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC15
|
-4.65% |
127.638 |
121.705 |
0.002 |
-5.11% |
0.002 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<64, GreaterThanZero, None>
|
-4.60% |
3050.979 |
2910.482 |
14.718 |
-0.05% |
14.718 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint16_t>/65
|
-4.60% |
95.108 |
90.730 |
0.007 |
-4.61% |
0.007 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_runtime_checks_pass<16, int>
|
-4.60% |
54.438 |
51.934 |
0.003 |
-4.60% |
0.003 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_runtime_checks_fail<16, int>
|
-4.60% |
54.435 |
51.932 |
0.003 |
-4.60% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC2
|
-4.54% |
13.765 |
13.140 |
0.000 |
0.00% |
0.000 |
|
MultiSource/Benchmarks/Rodinia/pathfinder/pathfinder
Profile
|
-4.47% |
1.279 |
1.222 |
0.009 |
-2.85% |
0.009 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC31
|
-4.46% |
70.079 |
66.951 |
0.004 |
-4.47% |
0.004 |
|
External/SPEC/CINT2017rate/531.deepsjeng_r/531.deepsjeng_r
Profile
|
-4.46% |
267.314 |
255.389 |
0.258 |
-1.82% |
0.258 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC7
|
-4.46% |
70.083 |
66.960 |
0.003 |
-5.32% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint8_t_To_uint64_t_
|
-4.44% |
23539.698 |
22495.173 |
14.972 |
-4.21% |
14.972 |
|
MultiSource/Applications/JM/lencod/lencod
Profile
|
-4.39% |
33.053 |
31.601 |
0.023 |
-2.89% |
0.023 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_ENERGY_CALC_RAW/171
|
-4.32% |
14.217 |
13.603 |
0.012 |
-4.48% |
0.012 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_ENERGY_CALC_LAMBDA/171
|
-4.29% |
14.214 |
13.605 |
0.013 |
-4.51% |
0.013 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint64_t>/999
|
-4.27% |
1811.441 |
1734.103 |
0.147 |
-4.26% |
0.147 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_PRESSURE_CALC_RAW/44217
|
-4.22% |
500.746 |
479.611 |
3.841 |
-4.50% |
3.841 |
|
SingleSource/Benchmarks/Misc/flops-5
Profile
|
-4.19% |
2.022 |
1.937 |
0.000 |
-4.15% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint64_t>/999
|
-4.16% |
3595.458 |
3445.767 |
0.120 |
-4.14% |
0.120 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint64_t>/256
|
-4.08% |
935.558 |
897.365 |
0.043 |
-4.08% |
0.043 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC31
|
-4.03% |
61.943 |
59.444 |
0.001 |
-4.04% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC3
|
-4.01% |
15.644 |
15.017 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint32_t_To_uint16_t_
|
-4.00% |
9882.214 |
9487.125 |
19.502 |
-3.97% |
19.502 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_only_autovec_uint8_t_
|
-3.98% |
96166.597 |
92342.749 |
13.251 |
-3.97% |
13.251 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint8_t>/16
|
-3.98% |
68.636 |
65.907 |
0.841 |
7.42% |
0.841 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint32_t>/256
|
-3.96% |
221.508 |
212.742 |
0.006 |
-3.96% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC32
|
-3.95% |
63.194 |
60.697 |
0.001 |
-3.96% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC4
|
-3.93% |
358.146 |
344.059 |
3.539 |
-1.52% |
3.539 |
|
External/SPEC/CFP2017rate/519.lbm_r/519.lbm_r
Profile
|
-3.88% |
199.905 |
192.158 |
1.401 |
-4.25% |
1.401 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint64_t_To_uint32_t_
|
-3.84% |
19376.477 |
18632.938 |
132.099 |
-3.42% |
132.099 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC31
|
-3.76% |
94.344 |
90.801 |
0.068 |
-3.25% |
0.068 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC2
|
-3.70% |
16.895 |
16.270 |
0.003 |
0.00% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC2
|
-3.70% |
16.894 |
16.269 |
0.001 |
0.00% |
0.001 |
|
SingleSource/Benchmarks/Shootout/Shootout-matrix
Profile
|
-3.69% |
3.864 |
3.721 |
0.000 |
-3.68% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC63
|
-3.67% |
43.175 |
41.590 |
0.085 |
-3.94% |
0.085 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint64_t>/256
|
-3.65% |
514.354 |
495.571 |
0.026 |
-3.66% |
0.026 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_PRESSURE_CALC_LAMBDA/44217
|
-3.61% |
495.751 |
477.845 |
4.787 |
-4.15% |
4.787 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC64
|
-3.60% |
69.457 |
66.954 |
0.002 |
-3.61% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC64
|
-3.60% |
69.454 |
66.954 |
0.003 |
-3.60% |
0.003 |
|
SingleSource/Benchmarks/BenchmarkGame/n-body
Profile
|
-3.58% |
2.731 |
2.634 |
0.000 |
21.70% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC63
|
-3.57% |
70.084 |
67.580 |
0.001 |
-3.57% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint16_t_To_uint8_t_
|
-3.57% |
2874.686 |
2772.182 |
0.704 |
-3.68% |
0.704 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC63
|
-3.56% |
70.077 |
67.581 |
0.002 |
-3.58% |
0.002 |
|
MultiSource/Benchmarks/nbench/nbench
Profile
|
-3.54% |
6.105 |
5.889 |
0.001 |
-3.88% |
0.001 |
|
MicroBenchmarks/ImageProcessing/Dilate/Dilate.test:BENCHMARK_DILATE/256
|
-3.46% |
1054.152 |
1017.718 |
6.117 |
-4.64% |
6.117 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC64
|
-3.41% |
43.177 |
41.706 |
0.015 |
-3.40% |
0.015 |
|
MultiSource/Benchmarks/Olden/health/health
Profile
|
-3.37% |
1.607 |
1.552 |
0.004 |
-2.45% |
0.004 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_FLOYD_DITHER/256
|
-3.37% |
1794.171 |
1733.771 |
6.095 |
0.01% |
6.095 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint32_t>/65
|
-3.33% |
93.851 |
90.729 |
0.006 |
-3.98% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint16_t>/999
|
-3.16% |
515.006 |
498.710 |
0.021 |
-3.17% |
0.021 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint16_t_To_uint8_t_
|
-3.14% |
4513.055 |
4371.297 |
3.076 |
-3.23% |
3.076 |
|
SingleSource/Benchmarks/Shootout/Shootout-lists
Profile
|
-3.14% |
11.316 |
10.962 |
0.016 |
-3.10% |
0.016 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC31
|
-3.13% |
60.074 |
58.194 |
0.001 |
-3.45% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1BigLoopWithReductionTC1
|
-3.12% |
20.023 |
19.398 |
0.000 |
-3.13% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchVecWithRuntimeChecks4PointersDBeforeA/1000
|
-3.10% |
5020941.532 |
4865342.278 |
82.295 |
-3.08% |
82.295 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC15
|
-3.07% |
532.485 |
516.116 |
4.978 |
-1.76% |
4.978 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC128
|
-3.06% |
2932.099 |
2842.517 |
32.335 |
-4.43% |
32.335 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC31
|
-3.06% |
891.432 |
864.197 |
8.590 |
-5.76% |
8.590 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC127
|
-3.05% |
3082.737 |
2988.627 |
33.801 |
-4.48% |
33.801 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1LoopWithReductionTC7
|
-3.03% |
20.649 |
20.024 |
0.001 |
3.21% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC8
|
-2.99% |
41.926 |
40.672 |
0.002 |
-0.01% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC7
|
-2.98% |
37.542 |
36.422 |
0.045 |
0.35% |
0.045 |
|
MultiSource/Benchmarks/FreeBench/fourinarow/fourinarow
Profile
|
-2.97% |
0.654 |
0.635 |
0.001 |
-2.46% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_ENERGY_CALC_LAMBDA/44217
|
-2.84% |
4365.741 |
4241.767 |
5.856 |
-1.91% |
5.856 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint16_t>/999
|
-2.84% |
1013.736 |
984.968 |
0.042 |
-2.85% |
0.042 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC64
|
-2.81% |
111.375 |
108.250 |
0.005 |
-2.81% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC1
|
-2.79% |
22.527 |
21.900 |
0.001 |
-2.78% |
0.001 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C/CoMD/CoMD
Profile
|
-2.78% |
9.899 |
9.623 |
0.003 |
-2.79% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC1
|
-2.78% |
22.526 |
21.900 |
0.002 |
-2.78% |
0.002 |
|
MultiSource/Applications/ClamAV/clamscan
Profile
|
-2.78% |
0.496 |
0.482 |
0.001 |
-1.49% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1LoopWithReductionTC8
|
-2.77% |
22.525 |
21.901 |
0.000 |
2.93% |
0.000 |
|
MultiSource/Benchmarks/MiBench/consumer-typeset/consumer-typeset
Profile
|
-2.76% |
0.742 |
0.721 |
0.004 |
-0.18% |
0.004 |
|
External/SPEC/CFP2017rate/511.povray_r/511.povray_r
Profile
|
-2.75% |
34.486 |
33.540 |
0.035 |
-0.73% |
0.035 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC32
|
-2.74% |
50.183 |
48.809 |
0.057 |
-2.48% |
0.057 |
|
MultiSource/Benchmarks/Fhourstones-3.1/fhourstones3.1
Profile
|
-2.67% |
4.030 |
3.923 |
0.009 |
-1.23% |
0.009 |
|
SingleSource/Benchmarks/Misc-C++/oopack_v1p8
Profile
|
-2.65% |
0.480 |
0.467 |
0.000 |
-9.98% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC32
|
-2.64% |
23.777 |
23.150 |
0.001 |
-5.14% |
0.001 |
|
MultiSource/Benchmarks/FreeBench/mason/mason
Profile
|
-2.63% |
0.553 |
0.538 |
0.000 |
-2.68% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC31
|
-2.63% |
23.777 |
23.152 |
0.001 |
-5.13% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC32
|
-2.63% |
23.775 |
23.151 |
0.001 |
-5.13% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC31
|
-2.62% |
23.776 |
23.152 |
0.000 |
-5.13% |
0.000 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<32, EqZero, None>
|
-2.60% |
4446.680 |
4330.997 |
40.117 |
-1.82% |
40.117 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC63
|
-2.60% |
120.131 |
117.009 |
0.011 |
-2.61% |
0.011 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint8_t>/10
|
-2.55% |
48.804 |
47.558 |
0.030 |
2.47% |
0.030 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint8_t_To_uint32_t_
|
-2.52% |
7076.549 |
6898.188 |
1.044 |
-2.53% |
1.044 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint64_t_To_uint8_t_
|
-2.52% |
19761.399 |
19264.348 |
30.179 |
-2.91% |
30.179 |
|
External/SPEC/CFP2017rate/544.nab_r/544.nab_r
Profile
|
-2.47% |
472.028 |
460.356 |
0.094 |
-3.67% |
0.094 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<63, GreaterThanZero, None>
|
-2.47% |
4742.608 |
4625.372 |
6.410 |
-0.05% |
6.410 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint8_t>/16
|
-2.47% |
59.472 |
58.004 |
0.457 |
7.78% |
0.457 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchVecWithRuntimeChecks4PointersDBeforeA/32
|
-2.45% |
166192.169 |
162117.962 |
6.277 |
-2.46% |
6.277 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_only_autovec_int64_t_
|
-2.44% |
1449289.503 |
1413920.966 |
1113.818 |
-2.28% |
1113.818 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<63, LessThanZero, First>
|
-2.42% |
1641.561 |
1601.878 |
2.311 |
-0.01% |
2.311 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint64_t>/10
|
-2.39% |
56.411 |
55.062 |
0.087 |
-0.07% |
0.087 |
|
MultiSource/Benchmarks/mafft/pairlocalalign
Profile
|
-2.37% |
93.837 |
91.614 |
0.383 |
-2.60% |
0.383 |
|
MultiSource/Benchmarks/sim/sim
Profile
|
-2.36% |
9.685 |
9.457 |
0.015 |
-2.52% |
0.015 |
|
MicroBenchmarks/ImageProcessing/Blur/blur.test:BENCHMARK_boxBlurKernel/128
|
-2.35% |
437.345 |
427.050 |
1.787 |
-1.66% |
1.787 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_FLOYD_DITHER/128
|
-2.35% |
436.987 |
426.737 |
1.894 |
-2.90% |
1.894 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC63
|
-2.34% |
107.000 |
104.501 |
0.002 |
-2.34% |
0.002 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_FLOYD_DITHER/512
|
-2.33% |
6648.488 |
6493.365 |
19.841 |
-2.28% |
19.841 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC64
|
-2.32% |
108.252 |
105.743 |
0.005 |
-2.31% |
0.005 |
|
MultiSource/Benchmarks/Fhourstones/fhourstones
Profile
|
-2.28% |
11.010 |
10.758 |
0.055 |
-0.09% |
0.055 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint16_t_To_uint32_t_
|
-2.21% |
11296.010 |
11046.138 |
57.170 |
-2.61% |
57.170 |
|
SingleSource/Benchmarks/Misc/flops-1
Profile
|
-2.18% |
9.002 |
8.806 |
0.000 |
-2.15% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopFrom_uint32_t_To_uint8_t_
|
-2.17% |
7634.626 |
7468.889 |
9.867 |
-0.13% |
9.867 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C/SimpleMOC/SimpleMOC
Profile
|
-2.15% |
10.437 |
10.212 |
0.026 |
-1.85% |
0.026 |
|
SingleSource/Benchmarks/Misc-C++/Large/ray
Profile
|
-2.15% |
12.108 |
11.848 |
0.002 |
-2.08% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint32_t_To_uint64_t_
|
-2.13% |
26412.691 |
25850.951 |
7.464 |
-1.64% |
7.464 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC128
|
-2.10% |
119.515 |
117.010 |
0.005 |
-2.10% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC128
|
-2.09% |
119.515 |
117.012 |
0.002 |
-2.10% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC127
|
-2.08% |
120.137 |
117.634 |
0.006 |
-2.09% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC127
|
-2.08% |
120.130 |
117.636 |
0.001 |
-2.08% |
0.001 |
|
MicroBenchmarks/ImageProcessing/Dilate/Dilate.test:BENCHMARK_DILATE/512
|
-1.99% |
3546.762 |
3476.163 |
16.101 |
-3.01% |
16.101 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_nested_cond_load_novec_int32_t_
|
-1.95% |
634604.563 |
622260.239 |
157.419 |
-3.55% |
157.419 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<64, GreaterThanZero, Mid>
|
-1.92% |
2741.160 |
2688.445 |
3.526 |
-2.09% |
3.526 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<31, EqZero, None>
|
-1.92% |
8049.043 |
7894.553 |
32.191 |
-1.26% |
32.191 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_EOS_LAMBDA/171
|
-1.88% |
0.871 |
0.855 |
0.001 |
-1.78% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint16_t>/256
|
-1.83% |
272.809 |
267.826 |
0.009 |
-1.84% |
0.009 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_ENERGY_CALC_RAW/44217
|
-1.81% |
4353.007 |
4274.174 |
16.126 |
-1.32% |
16.126 |
|
MultiSource/Benchmarks/VersaBench/ecbdes/ecbdes
Profile
|
-1.79% |
5.150 |
5.058 |
0.001 |
-1.59% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC15
|
-1.78% |
70.079 |
68.835 |
0.004 |
0.00% |
0.004 |
|
MultiSource/Benchmarks/TSVC/ControlLoops-flt/ControlLoops-flt
Profile
|
-1.75% |
5.435 |
5.340 |
0.031 |
-1.96% |
0.031 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1LoopWithReductionTC15
|
-1.75% |
35.667 |
35.041 |
0.002 |
1.81% |
0.002 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_EOS_RAW/171
|
-1.72% |
0.871 |
0.856 |
0.002 |
-1.74% |
0.002 |
|
SingleSource/Benchmarks/Misc/ReedSolomon
Profile
|
-1.72% |
20.768 |
20.412 |
0.000 |
-1.85% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint64_t>/51
|
-1.69% |
148.292 |
145.792 |
0.001 |
-1.70% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1LoopWithReductionTC16
|
-1.67% |
37.545 |
36.919 |
0.001 |
1.72% |
0.001 |
|
MultiSource/Benchmarks/Bullet/bullet
Profile
|
-1.67% |
30.399 |
29.893 |
0.148 |
-1.77% |
0.148 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_INT_PREDICT_RAW/171
|
-1.66% |
6.925 |
6.810 |
0.019 |
-1.65% |
0.019 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC63
|
-1.66% |
130.763 |
128.599 |
0.062 |
-1.20% |
0.062 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC128
|
-1.63% |
211.489 |
208.034 |
0.082 |
-1.65% |
0.082 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint8_t>/10
|
-1.57% |
66.741 |
65.693 |
0.003 |
6.42% |
0.003 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_INT_PREDICT_LAMBDA/171
|
-1.57% |
6.915 |
6.807 |
0.011 |
-1.71% |
0.011 |
|
MicroBenchmarks/Builtins/Int128/Builtins.test:BM_RemainderIntrinsic128SmallDivisor<__uint128_t>
|
-1.57% |
72.453 |
71.318 |
0.009 |
-0.57% |
0.009 |
|
SingleSource/Benchmarks/Misc/mandel-2
Profile
|
-1.55% |
2.535 |
2.496 |
0.000 |
-1.54% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_csa_with_in_loop_arith_novec_int64_t_
|
-1.54% |
1029666.173 |
1013791.721 |
165.718 |
-1.40% |
165.718 |
|
MicroBenchmarks/ImageProcessing/Blur/blur.test:BENCHMARK_boxBlurKernel/512
|
-1.50% |
6617.899 |
6518.329 |
19.477 |
-1.44% |
19.477 |
|
MultiSource/Benchmarks/TSVC/NodeSplitting-dbl/NodeSplitting-dbl
Profile
|
-1.49% |
26.880 |
26.480 |
0.023 |
0.24% |
0.023 |
|
MultiSource/Applications/obsequi/Obsequi
Profile
|
-1.46% |
7.681 |
7.569 |
0.020 |
-1.20% |
0.020 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, LessThanZero, None>
|
-1.45% |
37035.009 |
36499.822 |
35.315 |
-2.86% |
35.315 |
|
External/SPEC/CINT2017rate/525.x264_r/525.x264_r
Profile
|
-1.39% |
129.791 |
127.982 |
0.263 |
-1.13% |
0.263 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC127
|
-1.39% |
220.276 |
217.214 |
0.026 |
-1.39% |
0.026 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_csa_with_cond_arith_novec_int64_t_
|
-1.38% |
745714.087 |
735395.788 |
1569.652 |
-1.25% |
1569.652 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint64_t>/51
|
-1.37% |
229.015 |
225.887 |
0.011 |
-1.36% |
0.011 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<3, GreaterThanZero, Mid>
|
-1.34% |
37818.785 |
37312.083 |
62.211 |
-0.26% |
62.211 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, GreaterThanZero, Last>
|
-1.33% |
35727.462 |
35251.135 |
1.823 |
0.00% |
1.823 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC127
|
-1.27% |
197.096 |
194.598 |
0.005 |
-1.27% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC128
|
-1.26% |
198.352 |
195.860 |
0.002 |
-1.26% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_nested_cond_load_novec_uint8_t_
|
-1.25% |
502962.579 |
496696.297 |
26.159 |
-1.59% |
26.159 |
|
External/SPEC/CINT2017rate/541.leela_r/541.leela_r
Profile
|
-1.23% |
228.527 |
225.720 |
0.708 |
-1.60% |
0.708 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<64, EqZero, None>
|
-1.19% |
2937.891 |
2902.807 |
12.336 |
-0.91% |
12.336 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint8_t_To_uint32_t_
|
-1.19% |
12066.659 |
11922.932 |
24.255 |
-1.65% |
24.255 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, LessThanZero, Mid>
|
-1.16% |
56413.650 |
55757.229 |
26.798 |
-1.36% |
26.798 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<63, EqZero, Mid>
|
-1.13% |
4116.629 |
4069.942 |
0.660 |
-0.02% |
0.660 |
|
SingleSource/Benchmarks/SmallPT/smallpt
Profile
|
-1.12% |
30.044 |
29.706 |
0.004 |
-1.07% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_sinhf_novec_float_
|
-1.12% |
2241.744 |
2216.640 |
0.887 |
-1.12% |
0.887 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<63, GreaterThanZero, First>
|
-1.11% |
1614.332 |
1596.352 |
0.099 |
-0.41% |
0.099 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_sinhf_autovec_float_
|
-1.10% |
2241.435 |
2216.732 |
1.162 |
-1.16% |
1.162 |
|
MicroBenchmarks/Builtins/Int128/Builtins.test:BM_RemainderIntrinsic128UniformDivisor<__int128_t>
|
-1.09% |
66.844 |
66.116 |
0.269 |
-0.17% |
0.269 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC31
|
-1.06% |
30.660 |
30.335 |
0.081 |
-2.74% |
0.081 |
|
External/SPEC/CINT2017rate/523.xalancbmk_r/523.xalancbmk_r
Profile
|
-1.05% |
245.899 |
243.329 |
0.609 |
0.43% |
0.609 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_csa_with_cond_arith_autovec_int64_t_
|
-1.02% |
745391.087 |
737811.377 |
444.750 |
-0.96% |
444.750 |
|
MicroBenchmarks/LoopInterchange/LoopInterchange.test:BENCHMARK_LI1
|
-1.02% |
1517.145 |
1501.727 |
4.181 |
-0.19% |
4.181 |
|
SingleSource/Benchmarks/Misc/fbench
Profile
|
-1.00% |
5.685 |
5.628 |
0.000 |
-2.32% |
0.000 |