|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_HYDRO_2D_LAMBDA/44217
|
-61.97% |
84378.312 |
32088.884 |
7911.467 |
-64.71% |
7911.467 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_HYDRO_2D_LAMBDA/5001
|
-59.27% |
9105.060 |
3708.295 |
863.710 |
-59.31% |
863.710 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_DISC_ORD_LAMBDA/44217
|
-51.23% |
13298.880 |
6486.120 |
1570.654 |
-53.85% |
1570.654 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_HYDRO_2D_RAW/44217
|
-50.66% |
92768.547 |
45774.219 |
17580.229 |
-45.93% |
17580.229 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint64_t_To_uint32_t_
|
-49.74% |
35255.300 |
17720.067 |
125.209 |
-49.82% |
125.209 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint64_t_To_uint16_t_
|
-48.79% |
35734.938 |
18299.925 |
1578.281 |
-48.71% |
1578.281 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint64_t_To_uint8_t_
|
-48.72% |
37061.196 |
19005.713 |
40.425 |
-48.72% |
40.425 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C/miniGMG/miniGMG
Profile
|
-47.44% |
8.833 |
4.642 |
0.140 |
-49.49% |
0.140 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_HYDRO_2D_RAW/5001
|
-44.25% |
9414.863 |
5248.565 |
1417.475 |
-40.33% |
1417.475 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint16_t_To_uint64_t_
|
-44.09% |
18673.809 |
10440.845 |
5.075 |
-44.09% |
5.075 |
|
MultiSource/Benchmarks/MiBench/automotive-bitcount/automotive-bitcount
Profile
|
-42.93% |
0.178 |
0.102 |
0.001 |
-17.88% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_DIFF_PREDICT_LAMBDA/44217
|
-42.01% |
23298.567 |
13511.358 |
336.625 |
-41.52% |
336.625 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_DIFF_PREDICT_RAW/44217
|
-41.88% |
23219.137 |
13493.940 |
300.506 |
-42.09% |
300.506 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_PIC_1D_LAMBDA/44217
|
-41.35% |
13582.457 |
7966.579 |
1461.841 |
-40.83% |
1461.841 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_DIFF_PREDICT_LAMBDA/5001
|
-41.13% |
2570.135 |
1513.011 |
29.724 |
-39.71% |
29.724 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint8_t_To_uint64_t_
|
-40.82% |
17797.286 |
10531.907 |
2.007 |
-40.83% |
2.007 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint64_t_To_uint32_t_
|
-40.62% |
38145.684 |
22651.253 |
55.995 |
-40.63% |
55.995 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_DIFF_PREDICT_RAW/5001
|
-40.42% |
2549.290 |
1518.826 |
43.402 |
-41.01% |
43.402 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/32
|
-36.70% |
1396.103 |
883.786 |
0.111 |
-36.70% |
0.111 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/64
|
-36.67% |
6181.037 |
3914.653 |
0.610 |
-36.68% |
0.610 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/16
|
-36.62% |
279.456 |
177.120 |
0.009 |
-36.62% |
0.009 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint32_t_To_uint64_t_
|
-36.31% |
22635.472 |
14415.433 |
289.965 |
-36.57% |
289.965 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/256
|
-36.23% |
107133.928 |
68316.162 |
33.040 |
-36.24% |
33.040 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/128
|
-36.13% |
26258.568 |
16770.362 |
14.386 |
-36.17% |
14.386 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIRST_DIFF_LAMBDA/44217
|
-35.20% |
157.878 |
102.309 |
0.629 |
-29.35% |
0.629 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint64_t_To_uint8_t_
|
-34.43% |
30294.547 |
19864.982 |
3.943 |
-34.03% |
3.943 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint64_t_To_uint16_t_
|
-34.22% |
28971.213 |
19058.671 |
41.939 |
-34.17% |
41.939 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIRST_DIFF_RAW/44217
|
-32.92% |
149.817 |
100.502 |
0.369 |
-29.47% |
0.369 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, EqZero, None>
|
-31.23% |
20509.485 |
14104.814 |
0.481 |
-31.23% |
0.481 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint64_t_To_uint16_t_
|
-28.79% |
25917.742 |
18456.045 |
34.566 |
-28.73% |
34.566 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint32_t_To_uint8_t_
|
-28.29% |
13514.641 |
9690.951 |
13.169 |
-28.05% |
13.169 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_PIC_2D_LAMBDA/44217
|
-27.97% |
11947.523 |
8605.470 |
54.019 |
-21.51% |
54.019 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC128
|
-27.57% |
1292.552 |
936.238 |
11.065 |
-27.58% |
11.065 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC128
|
-27.14% |
559.663 |
407.798 |
0.015 |
-26.86% |
0.015 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_PIC_2D_RAW/44217
|
-27.04% |
11841.306 |
8639.071 |
113.765 |
-22.98% |
113.765 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC64
|
-26.93% |
654.139 |
477.961 |
5.499 |
-26.87% |
5.499 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC32
|
-26.93% |
334.734 |
244.596 |
2.623 |
-26.75% |
2.623 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC16
|
-26.62% |
174.888 |
128.330 |
1.119 |
-26.16% |
1.119 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC64
|
-26.02% |
293.598 |
217.204 |
0.010 |
-25.57% |
0.010 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint64_t_To_uint8_t_
|
-24.51% |
27275.120 |
20591.012 |
2.280 |
-24.36% |
2.280 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, EqZero, None>
|
-23.98% |
16025.023 |
12181.588 |
1.112 |
-23.98% |
1.112 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC32
|
-23.89% |
160.321 |
122.027 |
0.017 |
-23.19% |
0.017 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC128
|
-23.04% |
602.670 |
463.806 |
0.003 |
-23.21% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC128
|
-22.93% |
602.656 |
464.458 |
0.007 |
-23.10% |
0.007 |
|
MicroBenchmarks/ImageProcessing/Blur/blur.test:BENCHMARK_boxBlurKernel/1024
|
-22.77% |
30144.127 |
23280.304 |
65.290 |
-22.78% |
65.290 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_PIC_2D_LAMBDA/5001
|
-22.42% |
1203.136 |
933.395 |
26.883 |
-15.57% |
26.883 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC127
|
-22.09% |
614.584 |
478.809 |
0.007 |
-22.17% |
0.007 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint8_t_To_uint32_t_
|
-22.06% |
6624.731 |
5163.424 |
9.652 |
-21.56% |
9.652 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC64
|
-22.04% |
312.230 |
243.429 |
0.017 |
-22.35% |
0.017 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint16_t_To_uint64_t_
|
-21.89% |
13265.720 |
10362.333 |
18.662 |
-21.55% |
18.662 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC127
|
-21.88% |
614.593 |
480.108 |
0.021 |
-21.96% |
0.021 |
|
SingleSource/Benchmarks/Adobe-C++/loop_unroll
Profile
|
-21.85% |
3.095 |
2.418 |
0.003 |
-22.16% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC64
|
-21.84% |
312.268 |
244.067 |
0.012 |
-22.15% |
0.012 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint16_t_To_uint32_t_
|
-21.69% |
7111.438 |
5568.770 |
3.673 |
-21.58% |
3.673 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_only_autovec_uint8_t_
|
-21.36% |
182386.073 |
143420.551 |
233.689 |
-21.35% |
233.689 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIND_FIRST_MIN_LAMBDA/171
|
-21.27% |
1.501 |
1.181 |
0.000 |
-21.28% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIND_FIRST_MIN_LAMBDA/44217
|
-21.20% |
389.460 |
306.884 |
0.330 |
-21.23% |
0.330 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIRST_SUM_RAW/44217
|
-20.62% |
168.845 |
134.030 |
0.661 |
-19.42% |
0.661 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIND_FIRST_MIN_LAMBDA/5001
|
-20.47% |
45.152 |
35.911 |
0.151 |
-20.65% |
0.151 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC16
|
-20.38% |
93.528 |
74.465 |
0.009 |
-19.31% |
0.009 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC127
|
-20.37% |
274.773 |
218.792 |
1.188 |
-20.57% |
1.188 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC63
|
-20.27% |
324.154 |
258.457 |
0.008 |
-20.42% |
0.008 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC32
|
-20.22% |
167.068 |
133.288 |
0.007 |
-20.82% |
0.007 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC128
|
-20.00% |
273.753 |
219.012 |
0.207 |
-20.28% |
0.207 |
|
MultiSource/Benchmarks/Trimaran/enc-pc1/enc-pc1
Profile
|
-19.96% |
1.130 |
0.904 |
0.000 |
-18.12% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC63
|
-19.88% |
324.140 |
259.693 |
0.009 |
-20.04% |
0.009 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC16
|
-19.87% |
97.607 |
78.214 |
0.004 |
-18.31% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC32
|
-19.85% |
167.066 |
133.901 |
0.007 |
-20.45% |
0.007 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC127
|
-19.81% |
642.016 |
514.803 |
0.260 |
-19.62% |
0.260 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC64
|
-19.38% |
148.752 |
119.917 |
0.405 |
-19.32% |
0.405 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC63
|
-19.13% |
149.563 |
120.955 |
0.556 |
-19.32% |
0.556 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint16_t_To_uint8_t_
|
-19.05% |
3815.998 |
3089.225 |
0.227 |
-19.09% |
0.227 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_VOL3D_CALC_LAMBDA/2
|
-18.80% |
8.757 |
7.110 |
0.000 |
-18.81% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_VOL3D_CALC_RAW/2
|
-18.79% |
8.757 |
7.112 |
0.000 |
-18.78% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint32_t_To_uint8_t_
|
-18.76% |
13904.962 |
11295.916 |
25.959 |
-18.74% |
25.959 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIRST_SUM_LAMBDA/44217
|
-18.64% |
166.035 |
135.080 |
0.447 |
-19.16% |
0.447 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint64_t_To_uint32_t_
|
-18.62% |
27108.870 |
22062.164 |
13.160 |
-18.44% |
13.160 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint32_t_To_uint16_t_
|
-18.47% |
13796.574 |
11247.765 |
4.042 |
-18.54% |
4.042 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_with_cond_arith_novec_uint8_t_
|
-17.87% |
746208.375 |
612832.419 |
514.618 |
-17.82% |
514.618 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC128
|
-17.87% |
569.490 |
467.725 |
2.084 |
-18.03% |
2.084 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_PIC_2D_RAW/5001
|
-17.40% |
1100.935 |
909.390 |
33.716 |
-15.67% |
33.716 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC4
|
-17.38% |
17.519 |
14.475 |
0.024 |
-17.38% |
0.024 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_with_cond_arith_novec_int32_t_
|
-17.36% |
740096.793 |
611581.619 |
453.145 |
-17.38% |
453.145 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC31
|
-17.13% |
178.955 |
148.294 |
0.011 |
-17.42% |
0.011 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC64
|
-16.94% |
296.587 |
246.332 |
0.242 |
-17.26% |
0.242 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC32
|
-16.92% |
85.330 |
70.891 |
0.238 |
-16.92% |
0.238 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC16
|
-16.55% |
94.480 |
78.841 |
0.003 |
-17.65% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC31
|
-16.45% |
179.016 |
149.560 |
0.007 |
-16.72% |
0.007 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC32
|
-16.30% |
160.183 |
134.075 |
0.085 |
-16.93% |
0.085 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_VOL3D_CALC_LAMBDA/0
|
-16.26% |
1267.873 |
1061.698 |
1.193 |
-16.24% |
1.193 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint8_t_To_uint64_t_
|
-16.24% |
13034.139 |
10917.850 |
7.833 |
-16.43% |
7.833 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_VOL3D_CALC_RAW/0
|
-16.21% |
1268.353 |
1062.698 |
0.708 |
-16.01% |
0.708 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_VOL3D_CALC_RAW/1
|
-16.13% |
260.167 |
218.212 |
0.112 |
-16.11% |
0.112 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_VOL3D_CALC_LAMBDA/1
|
-16.06% |
260.086 |
218.306 |
0.374 |
-16.09% |
0.374 |
|
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
|
-15.85% |
0.442 |
0.372 |
0.000 |
-15.83% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC31
|
-15.85% |
86.300 |
72.619 |
0.762 |
-15.67% |
0.762 |
|
MicroBenchmarks/ImageProcessing/Dilate/Dilate.test:BENCHMARK_DILATE/128
|
-15.71% |
221.856 |
187.004 |
11.728 |
-17.97% |
11.728 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint16_t_To_uint32_t_
|
-15.66% |
7462.164 |
6293.337 |
1.288 |
-15.66% |
1.288 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint32_t_To_uint8_t_
|
-15.48% |
10631.770 |
8986.486 |
28.455 |
-15.18% |
28.455 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_no_runtime_checks_needed<16, int>
|
-15.38% |
24.402 |
20.648 |
0.002 |
-15.39% |
0.002 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, EqZero, First>
|
-15.37% |
16666.714 |
14104.312 |
0.795 |
-15.40% |
0.795 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, EqZero, Mid>
|
-15.37% |
16666.983 |
14105.677 |
0.231 |
-15.36% |
0.231 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, EqZero, Last>
|
-15.36% |
16670.418 |
14110.110 |
0.399 |
-15.34% |
0.399 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC16
|
-15.33% |
91.995 |
77.895 |
0.004 |
-16.35% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC127
|
-14.85% |
605.208 |
515.361 |
0.318 |
-14.92% |
0.318 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint64_t_To_uint8_t_
|
-14.51% |
22187.678 |
18967.224 |
49.440 |
-13.97% |
49.440 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC128
|
-14.47% |
1102.067 |
942.582 |
0.068 |
-14.57% |
0.068 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC127
|
-14.46% |
1094.621 |
936.364 |
0.008 |
-14.51% |
0.008 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint32_t_To_uint8_t_
|
-14.39% |
11062.107 |
9470.108 |
30.890 |
-14.91% |
30.890 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint8_t_To_uint16_t_
|
-14.25% |
3756.366 |
3221.261 |
7.086 |
-14.25% |
7.086 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_with_cond_arith_novec_int64_t_
|
-14.23% |
790685.703 |
678195.454 |
2407.904 |
-13.94% |
2407.904 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC64
|
-14.16% |
561.313 |
481.844 |
0.015 |
-14.31% |
0.015 |
|
SingleSource/Benchmarks/Misc/salsa20
Profile
|
-14.14% |
15.386 |
13.211 |
0.001 |
-14.12% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC63
|
-14.12% |
553.838 |
475.615 |
0.021 |
-14.26% |
0.021 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC1
|
-13.86% |
51.937 |
44.740 |
0.002 |
-13.85% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC2
|
-13.85% |
51.937 |
44.741 |
0.001 |
-13.85% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC4
|
-13.85% |
51.934 |
44.740 |
0.002 |
-13.85% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC3
|
-13.85% |
51.933 |
44.741 |
0.003 |
-13.85% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC7
|
-13.85% |
51.935 |
44.743 |
0.004 |
-13.85% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC8
|
-13.85% |
51.935 |
44.743 |
0.002 |
-13.85% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC63
|
-13.76% |
375.977 |
324.227 |
0.029 |
-13.41% |
0.029 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC8
|
-13.74% |
57.581 |
49.671 |
0.034 |
-15.47% |
0.034 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_with_cond_arith_autovec_int64_t_
|
-13.74% |
789147.825 |
680758.031 |
1509.973 |
-14.00% |
1509.973 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, EqZero, First>
|
-13.62% |
14103.054 |
12182.305 |
0.594 |
-13.62% |
0.594 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, EqZero, Mid>
|
-13.62% |
14102.635 |
12182.093 |
0.784 |
-13.62% |
0.784 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, EqZero, Last>
|
-13.62% |
14102.365 |
12182.036 |
0.575 |
-13.63% |
0.575 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC32
|
-13.54% |
290.965 |
251.557 |
0.032 |
-13.85% |
0.032 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC8
|
-13.54% |
23.150 |
20.016 |
0.003 |
-13.55% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC31
|
-13.46% |
283.454 |
245.315 |
0.010 |
-13.65% |
0.010 |
|
External/SPEC/CFP2017rate/508.namd_r/508.namd_r
Profile
|
-13.43% |
223.220 |
193.247 |
0.874 |
-13.57% |
0.874 |
|
MicroBenchmarks/ImageProcessing/Dilate/Dilate.test:BENCHMARK_DILATE/1024
|
-13.42% |
7338.539 |
6353.664 |
206.827 |
-10.64% |
206.827 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC4
|
-13.18% |
112.641 |
97.791 |
2.474 |
-13.53% |
2.474 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC8
|
-13.15% |
23.775 |
20.649 |
0.001 |
-13.16% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint32_t_To_uint16_t_
|
-13.13% |
12783.511 |
11105.388 |
14.976 |
-13.49% |
14.976 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC128
|
-13.08% |
81.345 |
70.707 |
0.003 |
-13.08% |
0.003 |
|
MultiSource/Benchmarks/MiBench/security-rijndael/security-rijndael
Profile
|
-12.95% |
0.335 |
0.292 |
0.001 |
-12.75% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint8_t_To_uint16_t_
|
-12.94% |
4541.578 |
3953.969 |
0.211 |
-12.94% |
0.211 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC8
|
-12.90% |
58.194 |
50.687 |
0.001 |
-14.74% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_INT_PREDICT_RAW/44217
|
-12.78% |
9143.957 |
7975.073 |
104.430 |
-11.87% |
104.430 |
|
SingleSource/Benchmarks/Shootout-C++/Shootout-C++-matrix
Profile
|
-12.75% |
2.509 |
2.189 |
0.000 |
-12.72% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC16
|
-12.70% |
51.936 |
45.343 |
0.041 |
-12.70% |
0.041 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC63
|
-12.52% |
332.271 |
290.687 |
0.025 |
-12.66% |
0.025 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC16
|
-12.45% |
155.808 |
136.409 |
0.006 |
-13.10% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint16_t_To_uint8_t_
|
-12.43% |
4743.998 |
4154.219 |
0.512 |
-12.41% |
0.512 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC15
|
-12.35% |
106.376 |
93.235 |
0.002 |
-12.87% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC15
|
-12.23% |
148.286 |
130.152 |
0.009 |
-12.54% |
0.009 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_INT_PREDICT_RAW/5001
|
-12.22% |
1036.614 |
909.915 |
5.021 |
-0.38% |
5.021 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint32_t_To_uint16_t_
|
-12.07% |
10953.274 |
9631.109 |
230.635 |
-10.30% |
230.635 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC8
|
-11.83% |
58.192 |
51.310 |
0.002 |
-13.69% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC2
|
-11.77% |
21.275 |
18.771 |
0.001 |
-11.77% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint32_t_To_uint16_t_
|
-11.55% |
9867.360 |
8727.269 |
252.217 |
-11.89% |
252.217 |
|
MultiSource/Benchmarks/McCat/12-IOtest/iotest
Profile
|
-11.53% |
1.819 |
1.610 |
0.041 |
-11.79% |
0.041 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC15
|
-11.47% |
51.937 |
45.983 |
0.014 |
-11.47% |
0.014 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC16
|
-11.37% |
33.164 |
29.393 |
0.007 |
-11.37% |
0.007 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC15
|
-11.18% |
106.379 |
94.485 |
0.001 |
-11.70% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC4
|
-11.11% |
22.525 |
20.023 |
0.001 |
-11.12% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC4
|
-11.11% |
22.526 |
20.024 |
0.000 |
-11.11% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC3
|
-11.11% |
22.525 |
20.024 |
0.001 |
-11.11% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint8_t>/51
|
-10.91% |
123.645 |
110.152 |
0.341 |
19.08% |
0.341 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC8
|
-10.63% |
88.223 |
78.844 |
0.001 |
-11.81% |
0.001 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C/miniAMR/miniAMR
Profile
|
-10.61% |
3.176 |
2.839 |
0.128 |
-12.64% |
0.128 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_BAND_LIN_EQ_RAW/171
|
-10.61% |
0.384 |
0.343 |
0.000 |
-6.33% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_BAND_LIN_EQ_LAMBDA/171
|
-10.60% |
0.384 |
0.343 |
0.000 |
-6.32% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC4
|
-10.52% |
23.777 |
21.275 |
0.000 |
-10.53% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC64
|
-10.47% |
53.814 |
48.180 |
0.001 |
-10.47% |
0.001 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/16
|
-10.16% |
115.465 |
103.732 |
0.004 |
-10.16% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint8_t_To_uint16_t_
|
-10.12% |
5848.923 |
5257.215 |
4.744 |
-10.14% |
4.744 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC7
|
-10.08% |
80.722 |
72.586 |
0.001 |
-10.73% |
0.001 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/64
|
-10.08% |
1913.693 |
1720.870 |
0.918 |
-10.06% |
0.918 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/32
|
-9.98% |
472.945 |
425.767 |
0.010 |
-9.99% |
0.010 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/256
|
-9.91% |
31454.203 |
28338.638 |
8.419 |
-9.89% |
8.419 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_only_autovec_int64_t_
|
-9.83% |
333746.265 |
300954.085 |
571.003 |
-9.70% |
571.003 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/128
|
-9.82% |
7914.754 |
7137.625 |
4.628 |
-9.85% |
4.628 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC8
|
-9.76% |
25.653 |
23.150 |
0.002 |
-9.77% |
0.002 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_INT_PREDICT_LAMBDA/44217
|
-9.75% |
8862.644 |
7998.410 |
86.693 |
-4.07% |
86.693 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC8
|
-9.75% |
25.654 |
23.153 |
0.001 |
-9.76% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC7
|
-9.62% |
32.540 |
29.410 |
0.001 |
-9.61% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC1
|
-9.53% |
13.141 |
11.889 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC7
|
-9.52% |
26.280 |
23.777 |
0.001 |
-9.53% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC7
|
-9.52% |
26.280 |
23.778 |
0.002 |
-9.53% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC32
|
-9.43% |
53.187 |
48.170 |
0.007 |
-9.44% |
0.007 |
|
MultiSource/Benchmarks/FreeBench/pifft/pifft
Profile
|
-9.42% |
0.360 |
0.326 |
0.002 |
-9.03% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC127
|
-9.26% |
101.372 |
91.988 |
0.004 |
-9.71% |
0.004 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_DEL_DOT_VEC_2D_LAMBDA/1
|
-9.25% |
287.196 |
260.631 |
0.083 |
-9.23% |
0.083 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_DEL_DOT_VEC_2D_RAW/1
|
-9.25% |
287.091 |
260.545 |
0.042 |
-9.22% |
0.042 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC31
|
-9.11% |
195.854 |
178.021 |
0.011 |
-9.39% |
0.011 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_HYDRO_1D_LAMBDA/5001
|
-8.97% |
16.978 |
15.455 |
0.310 |
-10.00% |
0.310 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC7
|
-8.89% |
28.156 |
25.653 |
0.001 |
-8.90% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint32_t_To_uint64_t_
|
-8.88% |
17106.518 |
15587.850 |
301.062 |
-9.35% |
301.062 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_DEL_DOT_VEC_2D_RAW/2
|
-8.71% |
3.510 |
3.204 |
0.000 |
-8.71% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_DEL_DOT_VEC_2D_LAMBDA/2
|
-8.70% |
3.510 |
3.205 |
0.000 |
-8.69% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC16
|
-8.62% |
36.293 |
33.165 |
0.002 |
-8.62% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint16_t_To_uint64_t_
|
-8.61% |
20329.875 |
18580.391 |
62.691 |
-7.76% |
62.691 |
|
SingleSource/Benchmarks/Misc/richards_benchmark
Profile
|
-8.59% |
2.201 |
2.012 |
0.012 |
3.01% |
0.012 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint16_t_To_uint8_t_
|
-8.55% |
6812.674 |
6230.159 |
3.615 |
-8.59% |
3.615 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC8
|
-8.51% |
29.408 |
26.906 |
0.001 |
-8.52% |
0.001 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_runtime_checks_fail<4, int>
|
-8.49% |
16.754 |
15.330 |
0.001 |
-3.63% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_HYDRO_2D_LAMBDA/171
|
-8.17% |
88.995 |
81.726 |
1.229 |
-7.82% |
1.229 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint64_t_To_uint16_t_
|
-8.12% |
19345.108 |
17774.947 |
300.910 |
-6.37% |
300.910 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC64
|
-8.09% |
93.237 |
85.696 |
0.015 |
-8.09% |
0.015 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC4
|
-8.04% |
54.438 |
50.060 |
0.002 |
-10.07% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC16
|
-7.84% |
31.911 |
29.408 |
0.001 |
-7.85% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC16
|
-7.84% |
31.912 |
29.411 |
0.001 |
-7.84% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_HYDRO_1D_RAW/5001
|
-7.84% |
16.622 |
15.319 |
0.390 |
-8.19% |
0.390 |
|
MultiSource/Applications/lambda-0.1.3/lambda
Profile
|
-7.83% |
15.973 |
14.723 |
0.005 |
-7.23% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC32
|
-7.82% |
40.046 |
36.916 |
0.002 |
-7.82% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC4
|
-7.81% |
40.048 |
36.919 |
0.001 |
-10.61% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_DEL_DOT_VEC_2D_LAMBDA/0
|
-7.80% |
1799.693 |
1659.369 |
6.477 |
-7.40% |
6.477 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_DEL_DOT_VEC_2D_RAW/0
|
-7.71% |
1798.008 |
1659.374 |
2.556 |
-7.86% |
2.556 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC15
|
-7.70% |
32.538 |
30.033 |
0.002 |
-7.70% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC15
|
-7.70% |
32.537 |
30.033 |
0.002 |
-7.70% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint8_t_To_uint32_t_
|
-7.68% |
12757.745 |
11778.268 |
11.605 |
-7.83% |
11.605 |
|
MultiSource/Benchmarks/VersaBench/beamformer/beamformer
Profile
|
-7.67% |
5.202 |
4.803 |
0.001 |
-7.65% |
0.001 |
|
SingleSource/Benchmarks/Stanford/Puzzle
Profile
|
-7.61% |
0.248 |
0.229 |
0.005 |
-5.19% |
0.005 |
|
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
|
-7.50% |
12.010 |
11.110 |
0.045 |
-7.31% |
0.045 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint16_t_To_uint64_t_
|
-7.43% |
25074.366 |
23211.874 |
46.357 |
-7.10% |
46.357 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_xor_no_runtime_checks_needed<16, int>
|
-7.40% |
16.895 |
15.644 |
0.000 |
-7.41% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_DIFF_PREDICT_RAW/171
|
-7.27% |
11.982 |
11.111 |
0.065 |
-6.89% |
0.065 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC128
|
-7.22% |
173.321 |
160.801 |
0.012 |
-7.23% |
0.012 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint8_t>/127
|
-7.22% |
138.924 |
128.893 |
0.011 |
-7.21% |
0.011 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIND_FIRST_MIN_RAW/171
|
-7.20% |
1.497 |
1.389 |
0.000 |
-7.19% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_HYDRO_2D_RAW/171
|
-7.09% |
88.867 |
82.564 |
0.376 |
-6.84% |
0.376 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_DISC_ORD_RAW/5001
|
-7.08% |
647.649 |
601.821 |
16.017 |
-9.47% |
16.017 |
|
SingleSource/Benchmarks/Misc/pi
Profile
|
-7.02% |
1.782 |
1.657 |
0.000 |
-7.01% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_PRESSURE_CALC_LAMBDA/5001
|
-6.99% |
44.883 |
41.747 |
1.042 |
-5.06% |
1.042 |
|
SingleSource/Benchmarks/Misc/oourafft
Profile
|
-6.97% |
15.457 |
14.380 |
0.107 |
-4.73% |
0.107 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC15
|
-6.95% |
45.055 |
41.924 |
0.002 |
-6.94% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC8
|
-6.92% |
26.220 |
24.405 |
0.003 |
-9.32% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC15
|
-6.89% |
54.439 |
50.690 |
0.012 |
-6.89% |
0.012 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C++/miniFE/miniFE
Profile
|
-6.88% |
16.035 |
14.932 |
0.076 |
-6.49% |
0.076 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_runtime_checks_pass<4, int>
|
-6.84% |
16.457 |
15.331 |
0.001 |
-8.24% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_PRESSURE_CALC_RAW/5001
|
-6.79% |
43.318 |
40.379 |
0.577 |
-9.47% |
0.577 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC2
|
-6.75% |
16.896 |
15.756 |
0.089 |
0.66% |
0.089 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC31
|
-6.72% |
74.465 |
69.462 |
0.014 |
-6.72% |
0.014 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC3
|
-6.65% |
46.926 |
43.803 |
0.001 |
-7.89% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIND_FIRST_MIN_RAW/5001
|
-6.58% |
45.384 |
42.400 |
0.156 |
-6.48% |
0.156 |
|
SingleSource/Benchmarks/Misc/flops-6
Profile
|
-6.57% |
1.312 |
1.226 |
0.001 |
-6.59% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC63
|
-6.55% |
114.504 |
106.999 |
0.172 |
-6.56% |
0.172 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_xor_runtime_checks_fail<16, int>
|
-6.52% |
28.783 |
26.907 |
0.001 |
-6.52% |
0.001 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_xor_runtime_checks_pass<16, int>
|
-6.52% |
28.782 |
26.906 |
0.001 |
-6.52% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC15
|
-6.35% |
39.421 |
36.917 |
0.002 |
-6.36% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC127
|
-6.34% |
194.601 |
182.257 |
0.267 |
-6.35% |
0.267 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_only_autovec_int32_t_
|
-6.34% |
180977.392 |
169503.970 |
388.774 |
-6.41% |
388.774 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint16_t>/127
|
-6.31% |
138.913 |
130.153 |
0.005 |
-6.31% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC7
|
-6.25% |
70.081 |
65.701 |
0.004 |
-7.09% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC4
|
-6.25% |
40.046 |
37.544 |
0.003 |
-9.09% |
0.003 |
|
SingleSource/Benchmarks/Misc-C++/Large/sphereflake
Profile
|
-6.23% |
20.012 |
18.766 |
0.005 |
-6.18% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC7
|
-6.15% |
347.713 |
326.321 |
7.202 |
-8.00% |
7.202 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC16
|
-6.15% |
40.670 |
38.168 |
0.003 |
-6.16% |
0.003 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_BAND_LIN_EQ_RAW/5001
|
-6.05% |
21.428 |
20.131 |
0.083 |
-2.38% |
0.083 |
|
External/SPEC/CFP2017rate/538.imagick_r/538.imagick_r
Profile
|
-6.04% |
292.027 |
274.393 |
0.811 |
-6.06% |
0.811 |
|
MultiSource/Benchmarks/MiBench/telecomm-gsm/telecomm-gsm
Profile
|
-5.97% |
0.663 |
0.624 |
0.000 |
-5.94% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC16
|
-5.94% |
31.932 |
30.036 |
0.001 |
-4.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC63
|
-5.93% |
73.830 |
69.451 |
0.003 |
-6.43% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint8_t>/65
|
-5.93% |
95.117 |
89.480 |
0.007 |
-5.92% |
0.007 |
|
MultiSource/Benchmarks/Rodinia/hotspot/hotspot
Profile
|
-5.91% |
2.038 |
1.917 |
0.021 |
-5.84% |
0.021 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint8_t>/28
|
-5.87% |
80.674 |
75.934 |
0.152 |
12.35% |
0.152 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC3
|
-5.77% |
21.274 |
20.047 |
0.041 |
0.11% |
0.041 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC16
|
-5.66% |
33.162 |
31.287 |
0.000 |
-5.66% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC32
|
-5.63% |
44.425 |
41.922 |
0.002 |
-5.64% |
0.002 |
|
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 |
0.000 |
2.27% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_PIC_2D_LAMBDA/171
|
-5.57% |
13.515 |
12.762 |
0.064 |
-5.45% |
0.064 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC31
|
-5.56% |
45.051 |
42.547 |
0.002 |
-5.56% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC31
|
-5.55% |
242.502 |
229.039 |
0.017 |
-5.05% |
0.017 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC31
|
-5.55% |
45.052 |
42.551 |
0.001 |
-5.58% |
0.001 |
|
MultiSource/Benchmarks/SciMark2-C/scimark2
Profile
|
-5.55% |
107.707 |
101.733 |
0.036 |
-5.49% |
0.036 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC127
|
-5.52% |
68.201 |
64.439 |
0.006 |
-5.64% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC128
|
-5.51% |
68.207 |
64.449 |
0.003 |
-6.33% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint32_t_To_uint64_t_
|
-5.50% |
21497.512 |
20314.751 |
15.040 |
-5.30% |
15.040 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint8_t_To_uint16_t_
|
-5.47% |
3626.353 |
3427.976 |
5.857 |
-5.65% |
5.857 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint32_t>/127
|
-5.44% |
137.654 |
130.164 |
0.001 |
-5.87% |
0.001 |
|
SingleSource/Benchmarks/Polybench/stencils/jacobi-2d/jacobi-2d
Profile
|
-5.42% |
31.941 |
30.210 |
0.194 |
-6.25% |
0.194 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint32_t>/999
|
-5.39% |
696.450 |
658.908 |
0.053 |
-5.40% |
0.053 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC32
|
-5.35% |
61.323 |
58.041 |
0.064 |
-5.35% |
0.064 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIND_FIRST_MIN_RAW/44217
|
-5.35% |
389.614 |
368.787 |
0.187 |
-5.34% |
0.187 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_BAND_LIN_EQ_LAMBDA/5001
|
-5.32% |
21.326 |
20.190 |
0.064 |
-2.93% |
0.064 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC1
|
-5.26% |
11.889 |
11.263 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC1
|
-5.26% |
11.888 |
11.263 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint32_t>/999
|
-5.23% |
1364.996 |
1293.596 |
0.110 |
-5.23% |
0.110 |
|
MultiSource/Applications/aha/aha
Profile
|
-5.11% |
5.004 |
4.748 |
0.001 |
-0.20% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC2
|
-5.08% |
36.915 |
35.040 |
0.002 |
-8.20% |
0.002 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_PIC_2D_RAW/171
|
-5.07% |
13.522 |
12.837 |
0.057 |
-5.19% |
0.057 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC127
|
-5.05% |
2384.349 |
2264.018 |
40.437 |
-6.70% |
40.437 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<64, GreaterThanZero, None>
|
-5.00% |
3050.979 |
2898.285 |
6.618 |
-0.29% |
6.618 |
|
MultiSource/Applications/siod/siod
Profile
|
-4.96% |
8.322 |
7.909 |
0.015 |
-0.64% |
0.015 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC4
|
-4.88% |
25.656 |
24.405 |
0.001 |
-0.00% |
0.001 |
|
External/SPEC/CINT2017rate/500.perlbench_r/500.perlbench_r
Profile
|
-4.88% |
153.168 |
145.700 |
0.352 |
-0.68% |
0.352 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint32_t>/256
|
-4.81% |
364.164 |
346.654 |
0.009 |
-4.81% |
0.009 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_ENERGY_CALC_LAMBDA/5001
|
-4.72% |
441.350 |
420.539 |
7.523 |
-4.00% |
7.523 |
|
SingleSource/Benchmarks/Misc/revertBits
Profile
|
-4.68% |
0.641 |
0.611 |
0.000 |
-4.69% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC15
|
-4.65% |
127.638 |
121.707 |
0.004 |
-5.11% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint16_t>/65
|
-4.60% |
95.108 |
90.734 |
0.005 |
-4.61% |
0.005 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_runtime_checks_pass<16, int>
|
-4.59% |
54.438 |
51.938 |
0.001 |
-4.59% |
0.001 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_runtime_checks_fail<16, int>
|
-4.59% |
54.435 |
51.939 |
0.002 |
-4.59% |
0.002 |
|
External/SPEC/CINT2017rate/531.deepsjeng_r/531.deepsjeng_r
Profile
|
-4.58% |
267.314 |
255.066 |
0.310 |
-1.94% |
0.310 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC2
|
-4.54% |
13.765 |
13.140 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC7
|
-4.47% |
70.083 |
66.953 |
0.003 |
-5.33% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC31
|
-4.46% |
70.079 |
66.956 |
0.002 |
-4.46% |
0.002 |
|
MultiSource/Applications/JM/lencod/lencod
Profile
|
-4.38% |
33.053 |
31.605 |
0.011 |
-2.87% |
0.011 |
|
MultiSource/Benchmarks/Rodinia/pathfinder/pathfinder
Profile
|
-4.32% |
1.279 |
1.224 |
0.009 |
-2.69% |
0.009 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint64_t>/999
|
-4.27% |
1811.441 |
1734.065 |
0.174 |
-4.26% |
0.174 |
|
SingleSource/Benchmarks/Misc/flops-5
Profile
|
-4.26% |
2.022 |
1.936 |
0.002 |
-4.22% |
0.002 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_ENERGY_CALC_RAW/171
|
-4.25% |
14.217 |
13.614 |
0.006 |
-4.40% |
0.006 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_ENERGY_CALC_LAMBDA/171
|
-4.21% |
14.214 |
13.616 |
0.005 |
-4.44% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint8_t_To_uint64_t_
|
-4.21% |
23539.698 |
22549.376 |
74.286 |
-3.98% |
74.286 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint64_t>/999
|
-4.16% |
3595.458 |
3445.726 |
0.219 |
-4.14% |
0.219 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_PRESSURE_CALC_RAW/44217
|
-4.11% |
500.746 |
480.170 |
2.570 |
-4.39% |
2.570 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_PRESSURE_CALC_LAMBDA/44217
|
-4.09% |
495.751 |
475.474 |
2.472 |
-4.63% |
2.472 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint64_t>/256
|
-4.08% |
935.558 |
897.376 |
0.024 |
-4.08% |
0.024 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC31
|
-4.04% |
61.943 |
59.442 |
0.007 |
-4.04% |
0.007 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC3
|
-4.00% |
15.644 |
15.018 |
0.000 |
-0.01% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_only_autovec_uint8_t_
|
-3.99% |
96166.597 |
92330.160 |
11.623 |
-3.98% |
11.623 |
|
External/SPEC/CFP2017rate/519.lbm_r/519.lbm_r
Profile
|
-3.99% |
199.905 |
191.936 |
1.508 |
-4.36% |
1.508 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint32_t>/256
|
-3.96% |
221.508 |
212.744 |
0.014 |
-3.95% |
0.014 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC32
|
-3.95% |
63.194 |
60.698 |
0.005 |
-3.96% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint64_t_To_uint32_t_
|
-3.84% |
19376.477 |
18633.273 |
6.708 |
-3.42% |
6.708 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint32_t_To_uint16_t_
|
-3.82% |
9882.214 |
9504.559 |
6.236 |
-3.80% |
6.236 |
|
MicroBenchmarks/ImageProcessing/Dilate/Dilate.test:BENCHMARK_DILATE/256
|
-3.81% |
1054.152 |
1014.028 |
6.389 |
-4.99% |
6.389 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC31
|
-3.78% |
94.344 |
90.776 |
0.009 |
-3.28% |
0.009 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIRST_DIFF_RAW/171
|
-3.75% |
0.276 |
0.266 |
0.001 |
-3.82% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint8_t>/16
|
-3.75% |
59.472 |
57.243 |
0.606 |
6.36% |
0.606 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC2
|
-3.70% |
16.894 |
16.268 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC2
|
-3.70% |
16.895 |
16.269 |
0.001 |
-0.00% |
0.001 |
|
SingleSource/Benchmarks/Shootout/Shootout-matrix
Profile
|
-3.69% |
3.864 |
3.721 |
0.001 |
-3.68% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC63
|
-3.69% |
43.175 |
41.581 |
0.103 |
-3.96% |
0.103 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint16_t_To_uint8_t_
|
-3.68% |
2874.686 |
2768.950 |
4.761 |
-3.80% |
4.761 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint64_t>/256
|
-3.65% |
514.354 |
495.595 |
0.014 |
-3.65% |
0.014 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC64
|
-3.60% |
69.457 |
66.957 |
0.001 |
-3.61% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC64
|
-3.59% |
69.454 |
66.959 |
0.003 |
-3.60% |
0.003 |
|
SingleSource/Benchmarks/BenchmarkGame/n-body
Profile
|
-3.59% |
2.731 |
2.633 |
0.000 |
21.69% |
0.000 |
|
MultiSource/Benchmarks/MiBench/consumer-typeset/consumer-typeset
Profile
|
-3.58% |
0.742 |
0.715 |
0.004 |
-0.32% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC63
|
-3.57% |
70.084 |
67.582 |
0.001 |
-3.57% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC63
|
-3.56% |
70.077 |
67.583 |
0.002 |
-3.58% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC64
|
-3.39% |
43.177 |
41.712 |
0.006 |
-3.39% |
0.006 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_PIC_1D_RAW/5001
|
-3.35% |
347.390 |
335.736 |
4.283 |
-2.69% |
4.283 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint32_t>/65
|
-3.32% |
93.851 |
90.737 |
0.000 |
-3.97% |
0.000 |
|
MultiSource/Benchmarks/nbench/nbench
Profile
|
-3.30% |
6.105 |
5.904 |
0.001 |
-3.64% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_ENERGY_CALC_RAW/5001
|
-3.27% |
440.052 |
425.663 |
1.328 |
-0.72% |
1.328 |
|
MultiSource/Benchmarks/Olden/health/health
Profile
|
-3.19% |
1.607 |
1.555 |
0.005 |
-2.27% |
0.005 |
|
MultiSource/Benchmarks/TSVC/NodeSplitting-dbl/NodeSplitting-dbl
Profile
|
-3.16% |
26.880 |
26.030 |
0.300 |
-1.46% |
0.300 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint16_t>/999
|
-3.16% |
515.006 |
498.714 |
0.020 |
-3.17% |
0.020 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint16_t_To_uint8_t_
|
-3.14% |
4513.055 |
4371.387 |
1.764 |
-3.23% |
1.764 |
|
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 |
0.001 |
-3.13% |
0.001 |
|
External/SPEC/CFP2017rate/511.povray_r/511.povray_r
Profile
|
-3.10% |
34.486 |
33.416 |
0.019 |
-1.09% |
0.019 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchVecWithRuntimeChecks4PointersDBeforeA/1000
|
-3.10% |
5020941.532 |
4865222.778 |
361.926 |
-3.08% |
361.926 |
|
SingleSource/Benchmarks/Shootout/Shootout-lists
Profile
|
-3.10% |
11.316 |
10.966 |
0.002 |
-3.06% |
0.002 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_FLOYD_DITHER/256
|
-3.05% |
1794.171 |
1739.386 |
9.700 |
0.33% |
9.700 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1LoopWithReductionTC7
|
-3.03% |
20.649 |
20.022 |
0.001 |
3.20% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC7
|
-2.98% |
37.542 |
36.422 |
0.106 |
0.35% |
0.106 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC8
|
-2.98% |
41.926 |
40.677 |
0.004 |
-0.00% |
0.004 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_ENERGY_CALC_LAMBDA/44217
|
-2.88% |
4365.741 |
4240.210 |
30.008 |
-1.95% |
30.008 |
|
MultiSource/Benchmarks/FreeBench/fourinarow/fourinarow
Profile
|
-2.85% |
0.654 |
0.635 |
0.001 |
-2.34% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint8_t>/16
|
-2.84% |
68.636 |
66.687 |
0.539 |
8.69% |
0.539 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint16_t>/999
|
-2.84% |
1013.736 |
984.968 |
0.018 |
-2.85% |
0.018 |
|
MultiSource/Applications/ClamAV/clamscan
Profile
|
-2.81% |
0.496 |
0.482 |
0.002 |
-1.53% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC64
|
-2.80% |
111.375 |
108.253 |
0.006 |
-2.81% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC1
|
-2.78% |
22.527 |
21.901 |
0.002 |
-2.77% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC1
|
-2.77% |
22.526 |
21.901 |
0.002 |
-2.77% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1LoopWithReductionTC8
|
-2.77% |
22.525 |
21.900 |
0.001 |
2.93% |
0.001 |
|
MultiSource/Benchmarks/Fhourstones-3.1/fhourstones3.1
Profile
|
-2.77% |
4.030 |
3.919 |
0.004 |
-1.33% |
0.004 |
|
MicroBenchmarks/ImageProcessing/Dilate/Dilate.test:BENCHMARK_DILATE/512
|
-2.74% |
3546.762 |
3449.465 |
28.952 |
-3.76% |
28.952 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC32
|
-2.74% |
50.183 |
48.810 |
0.030 |
-2.48% |
0.030 |
|
MultiSource/Benchmarks/FreeBench/mason/mason
Profile
|
-2.70% |
0.553 |
0.538 |
0.000 |
-2.74% |
0.000 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C/CoMD/CoMD
Profile
|
-2.67% |
9.899 |
9.634 |
0.007 |
-2.68% |
0.007 |
|
SingleSource/Benchmarks/Misc-C++/oopack_v1p8
Profile
|
-2.65% |
0.480 |
0.467 |
0.000 |
-9.98% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC31
|
-2.63% |
23.777 |
23.150 |
0.005 |
-5.13% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC31
|
-2.63% |
23.776 |
23.151 |
0.014 |
-5.13% |
0.014 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC32
|
-2.63% |
23.777 |
23.153 |
0.001 |
-5.13% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC32
|
-2.62% |
23.775 |
23.153 |
0.001 |
-5.12% |
0.001 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<32, EqZero, None>
|
-2.61% |
4446.680 |
4330.541 |
38.676 |
-1.83% |
38.676 |
|
MultiSource/Benchmarks/TSVC/ControlLoops-flt/ControlLoops-flt
Profile
|
-2.61% |
5.435 |
5.294 |
0.042 |
-2.82% |
0.042 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC63
|
-2.60% |
120.131 |
117.011 |
0.007 |
-2.61% |
0.007 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint8_t>/10
|
-2.56% |
48.804 |
47.554 |
0.008 |
2.46% |
0.008 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint32_t_To_uint64_t_
|
-2.55% |
26412.691 |
25738.240 |
30.196 |
-2.06% |
30.196 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint8_t_To_uint32_t_
|
-2.50% |
7076.549 |
6899.880 |
0.624 |
-2.51% |
0.624 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<63, GreaterThanZero, None>
|
-2.47% |
4742.608 |
4625.310 |
0.084 |
-0.06% |
0.084 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchVecWithRuntimeChecks4PointersDBeforeA/32
|
-2.45% |
166192.169 |
162123.291 |
0.512 |
-2.45% |
0.512 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_cond_load_autovec_int64_t_
|
-2.44% |
556572.382 |
542992.628 |
3740.953 |
-1.74% |
3740.953 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<63, LessThanZero, First>
|
-2.42% |
1641.561 |
1601.801 |
0.971 |
-0.01% |
0.971 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_FLOYD_DITHER/128
|
-2.41% |
436.987 |
426.467 |
1.843 |
-2.96% |
1.843 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_only_autovec_int64_t_
|
-2.40% |
1449289.503 |
1414464.299 |
581.634 |
-2.25% |
581.634 |
|
External/SPEC/CFP2017rate/544.nab_r/544.nab_r
Profile
|
-2.39% |
472.028 |
460.747 |
0.067 |
-3.59% |
0.067 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint64_t>/10
|
-2.39% |
56.411 |
55.066 |
0.048 |
-0.06% |
0.048 |
|
MultiSource/Benchmarks/mafft/pairlocalalign
Profile
|
-2.37% |
93.837 |
91.616 |
0.293 |
-2.60% |
0.293 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC63
|
-2.34% |
107.000 |
104.494 |
0.006 |
-2.35% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC64
|
-2.31% |
108.252 |
105.752 |
0.003 |
-2.31% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint64_t_To_uint8_t_
|
-2.25% |
19761.399 |
19317.166 |
13.800 |
-2.64% |
13.800 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C/SimpleMOC/SimpleMOC
Profile
|
-2.20% |
10.437 |
10.207 |
0.036 |
-1.90% |
0.036 |
|
MultiSource/Benchmarks/sim/sim
Profile
|
-2.20% |
9.685 |
9.472 |
0.020 |
-2.36% |
0.020 |
|
SingleSource/Benchmarks/Misc/flops-1
Profile
|
-2.17% |
9.002 |
8.806 |
0.000 |
-2.15% |
0.000 |
|
MultiSource/Benchmarks/Bullet/bullet
Profile
|
-2.17% |
30.399 |
29.741 |
0.215 |
-2.27% |
0.215 |
|
SingleSource/Benchmarks/Misc-C++/Large/ray
Profile
|
-2.14% |
12.108 |
11.849 |
0.000 |
-2.08% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopFrom_uint32_t_To_uint8_t_
|
-2.12% |
7634.626 |
7473.075 |
15.350 |
-0.07% |
15.350 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC128
|
-2.10% |
119.515 |
117.006 |
0.006 |
-2.10% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC128
|
-2.09% |
119.515 |
117.015 |
0.005 |
-2.10% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC127
|
-2.08% |
120.137 |
117.634 |
0.003 |
-2.09% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC127
|
-2.08% |
120.130 |
117.636 |
0.003 |
-2.08% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint16_t_To_uint32_t_
|
-2.07% |
11296.010 |
11062.384 |
40.716 |
-2.47% |
40.716 |
|
MultiSource/Benchmarks/Fhourstones/fhourstones
Profile
|
-2.00% |
11.010 |
10.789 |
0.026 |
0.10% |
0.026 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_ENERGY_CALC_RAW/44217
|
-1.93% |
4353.007 |
4269.144 |
8.931 |
-1.44% |
8.931 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_nested_cond_load_novec_int32_t_
|
-1.91% |
634604.563 |
622496.102 |
323.695 |
-3.51% |
323.695 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC63
|
-1.86% |
130.763 |
128.330 |
0.148 |
-1.41% |
0.148 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopFrom_uint32_t_To_uint16_t_
|
-1.86% |
7729.343 |
7585.711 |
33.626 |
1.81% |
33.626 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_EOS_LAMBDA/171
|
-1.85% |
0.871 |
0.855 |
0.002 |
-1.75% |
0.002 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIRST_DIFF_LAMBDA/5001
|
-1.84% |
12.065 |
11.843 |
0.050 |
-2.85% |
0.050 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<64, GreaterThanZero, Mid>
|
-1.83% |
2741.160 |
2691.009 |
16.943 |
-1.99% |
16.943 |
|
MultiSource/Benchmarks/VersaBench/ecbdes/ecbdes
Profile
|
-1.83% |
5.150 |
5.056 |
0.002 |
-1.62% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint16_t>/256
|
-1.83% |
272.809 |
267.830 |
0.013 |
-1.84% |
0.013 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_FLOYD_DITHER/512
|
-1.82% |
6648.488 |
6527.181 |
6.766 |
-1.78% |
6.766 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC15
|
-1.76% |
70.079 |
68.846 |
0.004 |
0.01% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1LoopWithReductionTC15
|
-1.75% |
35.667 |
35.042 |
0.002 |
1.81% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_csa_with_in_loop_arith_novec_int64_t_
|
-1.74% |
1029666.173 |
1011727.170 |
301.147 |
-1.60% |
301.147 |
|
SingleSource/Benchmarks/Misc/ReedSolomon
Profile
|
-1.71% |
20.768 |
20.412 |
0.002 |
-1.85% |
0.002 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_EOS_LAMBDA/44217
|
-1.69% |
273.759 |
269.127 |
1.610 |
-0.15% |
1.610 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint64_t>/51
|
-1.68% |
148.292 |
145.796 |
0.004 |
-1.69% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1LoopWithReductionTC16
|
-1.67% |
37.545 |
36.917 |
0.001 |
1.71% |
0.001 |
|
MicroBenchmarks/Builtins/Int128/Builtins.test:BM_RemainderIntrinsic128SmallDivisor<__uint128_t>
|
-1.60% |
72.453 |
71.291 |
0.025 |
-0.61% |
0.025 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_INT_PREDICT_RAW/171
|
-1.59% |
6.925 |
6.815 |
0.000 |
-1.58% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint8_t>/10
|
-1.57% |
66.741 |
65.692 |
0.007 |
6.42% |
0.007 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_INT_PREDICT_LAMBDA/171
|
-1.55% |
6.915 |
6.808 |
0.003 |
-1.69% |
0.003 |
|
SingleSource/Benchmarks/Misc/mandel-2
Profile
|
-1.55% |
2.535 |
2.496 |
0.000 |
-1.54% |
0.000 |
|
MultiSource/Benchmarks/tramp3d-v4/tramp3d-v4
Profile
|
-1.50% |
1.074 |
1.058 |
0.002 |
-1.61% |
0.002 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, LessThanZero, None>
|
-1.48% |
37035.009 |
36488.441 |
21.506 |
-2.89% |
21.506 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC128
|
-1.47% |
211.489 |
208.377 |
0.020 |
-1.48% |
0.020 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<31, EqZero, None>
|
-1.47% |
8049.043 |
7930.865 |
7.858 |
-0.80% |
7.858 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC127
|
-1.40% |
220.276 |
217.187 |
0.074 |
-1.40% |
0.074 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint64_t>/51
|
-1.37% |
229.015 |
225.881 |
0.009 |
-1.37% |
0.009 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_csa_with_cond_arith_novec_int64_t_
|
-1.34% |
745714.087 |
735746.178 |
572.520 |
-1.20% |
572.520 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, GreaterThanZero, Last>
|
-1.33% |
35727.462 |
35251.387 |
2.813 |
0.00% |
2.813 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_EOS_RAW/171
|
-1.32% |
0.871 |
0.859 |
0.001 |
-1.35% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_nested_cond_load_novec_uint8_t_
|
-1.31% |
502962.579 |
496356.411 |
471.102 |
-1.66% |
471.102 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint8_t>/10
|
-1.29% |
54.490 |
53.788 |
0.247 |
3.55% |
0.247 |
|
MicroBenchmarks/Builtins/Int128/Builtins.test:BM_RemainderIntrinsic128UniformDivisor<__int128_t>
|
-1.29% |
66.844 |
65.984 |
0.228 |
-0.37% |
0.228 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC127
|
-1.26% |
197.096 |
194.603 |
0.012 |
-1.27% |
0.012 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC128
|
-1.26% |
198.352 |
195.851 |
0.007 |
-1.27% |
0.007 |
|
MicroBenchmarks/ImageProcessing/Blur/blur.test:BENCHMARK_boxBlurKernel/512
|
-1.26% |
6617.899 |
6534.757 |
10.128 |
-1.19% |
10.128 |
|
External/SPEC/CINT2017rate/541.leela_r/541.leela_r
Profile
|
-1.23% |
228.527 |
225.712 |
0.274 |
-1.60% |
0.274 |
|
External/SPEC/CINT2017rate/525.x264_r/525.x264_r
Profile
|
-1.23% |
129.791 |
128.194 |
0.213 |
-0.97% |
0.213 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint8_t_To_uint32_t_
|
-1.15% |
12066.659 |
11928.360 |
8.256 |
-1.60% |
8.256 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_csa_with_cond_arith_autovec_int64_t_
|
-1.14% |
745391.087 |
736868.084 |
240.364 |
-1.08% |
240.364 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C++/PENNANT/PENNANT
Profile
|
-1.14% |
4.790 |
4.736 |
0.019 |
-1.69% |
0.019 |
|
External/SPEC/CINT2017rate/523.xalancbmk_r/523.xalancbmk_r
Profile
|
-1.14% |
245.899 |
243.102 |
0.689 |
0.34% |
0.689 |
|
SingleSource/Benchmarks/SmallPT/smallpt
Profile
|
-1.13% |
30.044 |
29.704 |
0.004 |
-1.08% |
0.004 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<3, LessThanZero, None>
|
-1.13% |
45716.844 |
45199.302 |
43.430 |
-0.07% |
43.430 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, LessThanZero, Mid>
|
-1.13% |
56413.650 |
55778.488 |
21.091 |
-1.32% |
21.091 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_sinhf_novec_float_
|
-1.11% |
2241.744 |
2216.828 |
0.788 |
-1.12% |
0.788 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<63, GreaterThanZero, First>
|
-1.11% |
1614.332 |
1596.492 |
0.069 |
-0.40% |
0.069 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<32, LessThanZero, Last>
|
-1.10% |
6893.145 |
6817.368 |
12.014 |
-0.68% |
12.014 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<63, EqZero, Mid>
|
-1.09% |
4116.629 |
4071.605 |
5.234 |
-0.02% |
5.234 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_sinhf_autovec_float_
|
-1.08% |
2241.435 |
2217.333 |
0.608 |
-1.13% |
0.608 |
|
MultiSource/Benchmarks/PAQ8p/paq8p
Profile
|
-1.07% |
166.229 |
164.444 |
0.467 |
-0.05% |
0.467 |
|
SingleSource/Benchmarks/Misc/fbench
Profile
|
-1.00% |
5.685 |
5.628 |
0.000 |
-2.32% |
0.000 |